Merge http://ftp.arm.linux.org.uk/pub/linux/arm/kernel/git-cur/linux-2.6-arm into for-rmk

CREDITS

@@ -317,6 +317,14 @@ S: 2322 37th Ave SW
 S: Seattle, Washington 98126-2010
 S: USA
 
+N: Muli Ben-Yehuda
+E: mulix@mulix.org
+E: muli@il.ibm.com
+W: http://www.mulix.org
+D: trident OSS sound driver, x86-64 dma-ops and Calgary IOMMU,
+D: KVM and Xen bits and other misc. hackery.
+S: Haifa, Israel
+
 N: Johannes Berg
 E: johannes@sipsolutions.net
 W: http://johannes.sipsolutions.net/
@@ -3344,8 +3352,7 @@ S: Spain
 N: Linus Torvalds
 E: torvalds@linux-foundation.org
 D: Original kernel hacker
-S: 12725 SW Millikan Way, Suite 400
-S: Beaverton, Oregon 97005
+S: Portland, Oregon 97005
 S: USA
 
 N: Marcelo Tosatti

Documentation/00-INDEX

@@ -89,8 +89,6 @@ cciss.txt
 	- info, major/minor #'s for Compaq's SMART Array Controllers.
 cdrom/
 	- directory with information on the CD-ROM drivers that Linux has.
-cli-sti-removal.txt
-	- cli()/sti() removal guide.
 computone.txt
 	- info on Computone Intelliport II/Plus Multiport Serial Driver.
 connector/
@@ -361,8 +359,6 @@ telephony/
 	- directory with info on telephony (e.g. voice over IP) support.
 time_interpolators.txt
 	- info on time interpolators.
-tipar.txt
-	- information about Parallel link cable for Texas Instruments handhelds.
 tty.txt
 	- guide to the locking policies of the tty layer.
 uml/

Documentation/ABI/testing/sysfs-class-regulator

@@ -0,0 +1,315 @@
+What:		/sys/class/regulator/.../state
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		state. This holds the regulator output state.
+
+		This will be one of the following strings:
+
+		'enabled'
+		'disabled'
+		'unknown'
+
+		'enabled' means the regulator output is ON and is supplying
+		power to the system.
+
+		'disabled' means the regulator output is OFF and is not
+		supplying power to the system..
+
+		'unknown' means software cannot determine the state.
+
+		NOTE: this field can be used in conjunction with microvolts
+		and microamps to determine regulator output levels.
+
+
+What:		/sys/class/regulator/.../type
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		type. This holds the regulator type.
+
+		This will be one of the following strings:
+
+		'voltage'
+		'current'
+		'unknown'
+
+		'voltage' means the regulator output voltage can be controlled
+		by software.
+
+		'current' means the regulator output current limit can be
+		controlled by software.
+
+		'unknown' means software cannot control either voltage or
+		current limit.
+
+
+What:		/sys/class/regulator/.../microvolts
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		microvolts. This holds the regulator output voltage setting
+		measured in microvolts (i.e. E-6 Volts).
+
+		NOTE: This value should not be used to determine the regulator
+		output voltage level as this value is the same regardless of
+		whether the regulator is enabled or disabled.
+
+
+What:		/sys/class/regulator/.../microamps
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		microamps. This holds the regulator output current limit
+		setting measured in microamps (i.e. E-6 Amps).
+
+		NOTE: This value should not be used to determine the regulator
+		output current level as this value is the same regardless of
+		whether the regulator is enabled or disabled.
+
+
+What:		/sys/class/regulator/.../opmode
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		opmode. This holds the regulator operating mode setting.
+
+		The opmode value can be one of the following strings:
+
+		'fast'
+		'normal'
+		'idle'
+		'standby'
+		'unknown'
+
+		The modes are described in include/linux/regulator/regulator.h
+
+		NOTE: This value should not be used to determine the regulator
+		output operating mode as this value is the same regardless of
+		whether the regulator is enabled or disabled.
+
+
+What:		/sys/class/regulator/.../min_microvolts
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		min_microvolts. This holds the minimum safe working regulator
+		output voltage setting for this domain measured in microvolts.
+
+		NOTE: this will return the string 'constraint not defined' if
+		the power domain has no min microvolts constraint defined by
+		platform code.
+
+
+What:		/sys/class/regulator/.../max_microvolts
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		max_microvolts. This holds the maximum safe working regulator
+		output voltage setting for this domain measured in microvolts.
+
+		NOTE: this will return the string 'constraint not defined' if
+		the power domain has no max microvolts constraint defined by
+		platform code.
+
+
+What:		/sys/class/regulator/.../min_microamps
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		min_microamps. This holds the minimum safe working regulator
+		output current limit setting for this domain measured in
+		microamps.
+
+		NOTE: this will return the string 'constraint not defined' if
+		the power domain has no min microamps constraint defined by
+		platform code.
+
+
+What:		/sys/class/regulator/.../max_microamps
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		max_microamps. This holds the maximum safe working regulator
+		output current limit setting for this domain measured in
+		microamps.
+
+		NOTE: this will return the string 'constraint not defined' if
+		the power domain has no max microamps constraint defined by
+		platform code.
+
+
+What:		/sys/class/regulator/.../num_users
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		num_users. This holds the number of consumer devices that
+		have called regulator_enable() on this regulator.
+
+
+What:		/sys/class/regulator/.../requested_microamps
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		requested_microamps. This holds the total requested load
+		current in microamps for this regulator from all its consumer
+		devices.
+
+
+What:		/sys/class/regulator/.../parent
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Some regulator directories will contain a link called parent.
+		This points to the parent or supply regulator if one exists.
+
+What:		/sys/class/regulator/.../suspend_mem_microvolts
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_mem_microvolts. This holds the regulator output
+		voltage setting for this domain measured in microvolts when
+		the system is suspended to memory.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to memory voltage defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_disk_microvolts
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_disk_microvolts. This holds the regulator output
+		voltage setting for this domain measured in microvolts when
+		the system is suspended to disk.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to disk voltage defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_standby_microvolts
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_standby_microvolts. This holds the regulator output
+		voltage setting for this domain measured in microvolts when
+		the system is suspended to standby.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to standby voltage defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_mem_mode
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_mem_mode. This holds the regulator operating mode
+		setting for this domain when the system is suspended to
+		memory.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to memory mode defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_disk_mode
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_disk_mode. This holds the regulator operating mode
+		setting for this domain when the system is suspended to disk.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to disk mode defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_standby_mode
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_standby_mode. This holds the regulator operating mode
+		setting for this domain when the system is suspended to
+		standby.
+
+		NOTE: this will return the string 'not defined' if
+		the power domain has no suspend to standby mode defined by
+		platform code.
+
+What:		/sys/class/regulator/.../suspend_mem_state
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_mem_state. This holds the regulator operating state
+		when suspended to memory.
+
+		This will be one of the following strings:
+
+		'enabled'
+		'disabled'
+		'not defined'
+
+What:		/sys/class/regulator/.../suspend_disk_state
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_disk_state. This holds the regulator operating state
+		when suspended to disk.
+
+		This will be one of the following strings:
+
+		'enabled'
+		'disabled'
+		'not defined'
+
+What:		/sys/class/regulator/.../suspend_standby_state
+Date:		May 2008
+KernelVersion:	2.6.26
+Contact:	Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Description:
+		Each regulator directory will contain a field called
+		suspend_standby_state. This holds the regulator operating
+		state when suspended to standby.
+
+		This will be one of the following strings:
+
+		'enabled'
+		'disabled'
+		'not defined'

Documentation/ABI/testing/sysfs-dev

@@ -0,0 +1,20 @@
+What:		/sys/dev
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Dan Williams <dan.j.williams@intel.com>
+Description:	The /sys/dev tree provides a method to look up the sysfs
+		path for a device using the information returned from
+		stat(2).  There are two directories, 'block' and 'char',
+		beneath /sys/dev containing symbolic links with names of
+		the form "<major>:<minor>".  These links point to the
+		corresponding sysfs path for the given device.
+
+		Example:
+		$ readlink /sys/dev/block/8:32
+		../../block/sdc
+
+		Entries in /sys/dev/char and /sys/dev/block will be
+		dynamically created and destroyed as devices enter and
+		leave the system.
+
+Users:		mdadm <linux-raid@vger.kernel.org>

Documentation/ABI/testing/sysfs-devices-memory

@@ -0,0 +1,24 @@
+What:		/sys/devices/system/memory
+Date:		June 2008
+Contact:	Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+		The /sys/devices/system/memory contains a snapshot of the
+		internal state of the kernel memory blocks. Files could be
+		added or removed dynamically to represent hot-add/remove
+		operations.
+
+Users:		hotplug memory add/remove tools
+		https://w3.opensource.ibm.com/projects/powerpc-utils/
+
+What:		/sys/devices/system/memory/memoryX/removable
+Date:		June 2008
+Contact:	Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/removable
+		indicates whether this memory block is removable or not.
+		This is useful for a user-level agent to determine
+		identify removable sections of the memory before attempting
+		potentially expensive hot-remove memory operation
+
+Users:		hotplug memory remove tools
+		https://w3.opensource.ibm.com/projects/powerpc-utils/

Documentation/ABI/testing/sysfs-firmware-acpi

@@ -29,46 +29,46 @@ Description:
 
 		$ cd /sys/firmware/acpi/interrupts
 		$ grep . *
-		error:0
-		ff_gbl_lock:0
-		ff_pmtimer:0
-		ff_pwr_btn:0
-		ff_rt_clk:0
-		ff_slp_btn:0
-		gpe00:0
-		gpe01:0
-		gpe02:0
-		gpe03:0
-		gpe04:0
-		gpe05:0
-		gpe06:0
-		gpe07:0
-		gpe08:0
-		gpe09:174
-		gpe0A:0
-		gpe0B:0
-		gpe0C:0
-		gpe0D:0
-		gpe0E:0
-		gpe0F:0
-		gpe10:0
-		gpe11:60
-		gpe12:0
-		gpe13:0
-		gpe14:0
-		gpe15:0
-		gpe16:0
-		gpe17:0
-		gpe18:0
-		gpe19:7
-		gpe1A:0
-		gpe1B:0
-		gpe1C:0
-		gpe1D:0
-		gpe1E:0
-		gpe1F:0
-		gpe_all:241
-		sci:241
+		error:	     0
+		ff_gbl_lock:	   0   enable
+		ff_pmtimer:	  0  invalid
+		ff_pwr_btn:	  0   enable
+		ff_rt_clk:	 2  disable
+		ff_slp_btn:	  0  invalid
+		gpe00:	     0	invalid
+		gpe01:	     0	 enable
+		gpe02:	   108	 enable
+		gpe03:	     0	invalid
+		gpe04:	     0	invalid
+		gpe05:	     0	invalid
+		gpe06:	     0	 enable
+		gpe07:	     0	 enable
+		gpe08:	     0	invalid
+		gpe09:	     0	invalid
+		gpe0A:	     0	invalid
+		gpe0B:	     0	invalid
+		gpe0C:	     0	invalid
+		gpe0D:	     0	invalid
+		gpe0E:	     0	invalid
+		gpe0F:	     0	invalid
+		gpe10:	     0	invalid
+		gpe11:	     0	invalid
+		gpe12:	     0	invalid
+		gpe13:	     0	invalid
+		gpe14:	     0	invalid
+		gpe15:	     0	invalid
+		gpe16:	     0	invalid
+		gpe17:	  1084	 enable
+		gpe18:	     0	 enable
+		gpe19:	     0	invalid
+		gpe1A:	     0	invalid
+		gpe1B:	     0	invalid
+		gpe1C:	     0	invalid
+		gpe1D:	     0	invalid
+		gpe1E:	     0	invalid
+		gpe1F:	     0	invalid
+		gpe_all:    1192
+		sci:	1194
 
 		sci - The total number of times the ACPI SCI
 		has claimed an interrupt.
@@ -89,6 +89,13 @@ Description:
 
 		error - an interrupt that can't be accounted for above.
 
+		invalid: it's either a wakeup GPE or a GPE/Fixed Event that
+			doesn't have an event handler.
+
+		disable: the GPE/Fixed Event is valid but disabled.
+
+		enable: the GPE/Fixed Event is valid and enabled.
+
 		Root has permission to clear any of these counters.  Eg.
 		# echo 0 > gpe11
 
@@ -97,3 +104,43 @@ Description:
 
 		None of these counters has an effect on the function
 		of the system, they are simply statistics.
+
+		Besides this, user can also write specific strings to these files
+		to enable/disable/clear ACPI interrupts in user space, which can be
+		used to debug some ACPI interrupt storm issues.
+
+		Note that only writting to VALID GPE/Fixed Event is allowed,
+		i.e. user can only change the status of runtime GPE and
+		Fixed Event with event handler installed.
+
+		Let's take power button fixed event for example, please kill acpid
+		and other user space applications so that the machine won't shutdown
+		when pressing the power button.
+		# cat ff_pwr_btn
+		0
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		3
+		# echo disable > ff_pwr_btn
+		# cat ff_pwr_btn
+		disable
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		disable
+		# echo enable > ff_pwr_btn
+		# cat ff_pwr_btn
+		4
+		/*
+		 * this is because the status bit is set even if the enable bit is cleared,
+		 * and it triggers an ACPI fixed event when the enable bit is set again
+		 */
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		7
+		# echo disable > ff_pwr_btn
+		# press the power button for 3 times;
+		# echo clear > ff_pwr_btn	/* clear the status bit */
+		# echo disable > ff_pwr_btn
+		# cat ff_pwr_btn
+		7
+

Documentation/ABI/testing/sysfs-kernel-mm

@@ -0,0 +1,6 @@
+What:		/sys/kernel/mm
+Date:		July 2008
+Contact:	Nishanth Aravamudan <nacc@us.ibm.com>, VM maintainers
+Description:
+		/sys/kernel/mm/ should contain any and all VM
+		related information in /sys/kernel/.

Documentation/ABI/testing/sysfs-kernel-mm-hugepages

@@ -0,0 +1,15 @@
+What:		/sys/kernel/mm/hugepages/
+Date:		June 2008
+Contact:	Nishanth Aravamudan <nacc@us.ibm.com>, hugetlb maintainers
+Description:
+		/sys/kernel/mm/hugepages/ contains a number of subdirectories
+		of the form hugepages-<size>kB, where <size> is the page size
+		of the hugepages supported by the kernel/CPU combination.
+
+		Under these directories are a number of files:
+			nr_hugepages
+			nr_overcommit_hugepages
+			free_hugepages
+			surplus_hugepages
+			resv_hugepages
+		See Documentation/vm/hugetlbpage.txt for details.

Documentation/CodingStyle

@@ -474,25 +474,29 @@ make a good program).
 So, you can either get rid of GNU emacs, or change it to use saner
 values.  To do the latter, you can stick the following in your .emacs file:
 
-(defun linux-c-mode ()
-  "C mode with adjusted defaults for use with the Linux kernel."
-  (interactive)
-  (c-mode)
-  (c-set-style "K&R")
-  (setq tab-width 8)
-  (setq indent-tabs-mode t)
-  (setq c-basic-offset 8))
-
-This will define the M-x linux-c-mode command.  When hacking on a
-module, if you put the string -*- linux-c -*- somewhere on the first
-two lines, this mode will be automatically invoked. Also, you may want
-to add
-
-(setq auto-mode-alist (cons '("/usr/src/linux.*/.*\\.[ch]$" . linux-c-mode)
-			auto-mode-alist))
-
-to your .emacs file if you want to have linux-c-mode switched on
-automagically when you edit source files under /usr/src/linux.
+(defun c-lineup-arglist-tabs-only (ignored)
+  "Line up argument lists by tabs, not spaces"
+  (let* ((anchor (c-langelem-pos c-syntactic-element))
+	 (column (c-langelem-2nd-pos c-syntactic-element))
+	 (offset (- (1+ column) anchor))
+	 (steps (floor offset c-basic-offset)))
+    (* (max steps 1)
+       c-basic-offset)))
+
+(add-hook 'c-mode-hook
+          (lambda ()
+            (let ((filename (buffer-file-name)))
+              ;; Enable kernel mode for the appropriate files
+              (when (and filename
+                         (string-match "~/src/linux-trees" filename))
+                (setq indent-tabs-mode t)
+                (c-set-style "linux")
+                (c-set-offset 'arglist-cont-nonempty
+                              '(c-lineup-gcc-asm-reg
+                                c-lineup-arglist-tabs-only))))))
+
+This will make emacs go better with the kernel coding style for C
+files below ~/src/linux-trees.
 
 But even if you fail in getting emacs to do sane formatting, not
 everything is lost: use "indent".

Documentation/DMA-API.txt

@@ -298,10 +298,10 @@ recommended that you never use these unless you really know what the
 cache width is.
 
 int
-dma_mapping_error(dma_addr_t dma_addr)
+dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
 int
-pci_dma_mapping_error(dma_addr_t dma_addr)
+pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
 
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned

Documentation/DMA-attributes.txt

@@ -22,3 +22,12 @@ ready and available in memory.  The DMA of the "completion indication"
 could race with data DMA.  Mapping the memory used for completion
 indications with DMA_ATTR_WRITE_BARRIER would prevent the race.
 
+DMA_ATTR_WEAK_ORDERING
+----------------------
+
+DMA_ATTR_WEAK_ORDERING specifies that reads and writes to the mapping
+may be weakly ordered, that is that reads and writes may pass each other.
+
+Since it is optional for platforms to implement DMA_ATTR_WEAK_ORDERING,
+those that do not will simply ignore the attribute and exhibit default
+behavior.

Documentation/DocBook/Makefile

@@ -12,7 +12,7 @@ DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml videobook.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
+	    mac80211.xml debugobjects.xml sh.xml
 
 ###
 # The build process is as follows (targets):

Documentation/DocBook/gadget.tmpl

@@ -524,6 +524,44 @@ These utilities include endpoint autoconfiguration.
 <!-- !Edrivers/usb/gadget/epautoconf.c -->
 </sect1>
 
+<sect1 id="composite"><title>Composite Device Framework</title>
+
+<para>The core API is sufficient for writing drivers for composite
+USB devices (with more than one function in a given configuration),
+and also multi-configuration devices (also more than one function,
+but not necessarily sharing a given configuration).
+There is however an optional framework which makes it easier to
+reuse and combine functions.
+</para>
+
+<para>Devices using this framework provide a <emphasis>struct
+usb_composite_driver</emphasis>, which in turn provides one or
+more <emphasis>struct usb_configuration</emphasis> instances.
+Each such configuration includes at least one
+<emphasis>struct usb_function</emphasis>, which packages a user
+visible role such as "network link" or "mass storage device".
+Management functions may also exist, such as "Device Firmware
+Upgrade".
+</para>
+
+!Iinclude/linux/usb/composite.h
+!Edrivers/usb/gadget/composite.c
+
+</sect1>
+
+<sect1 id="functions"><title>Composite Device Functions</title>
+
+<para>At this writing, a few of the current gadget drivers have
+been converted to this framework.
+Near-term plans include converting all of them, except for "gadgetfs".
+</para>
+
+!Edrivers/usb/gadget/f_acm.c
+!Edrivers/usb/gadget/f_serial.c
+
+</sect1>
+
+
 </chapter>
 
 <chapter id="controllers"><title>Peripheral Controller Drivers</title>

Documentation/DocBook/kernel-locking.tmpl

@@ -219,10 +219,10 @@
    </para>
 
    <sect1 id="lock-intro">
-   <title>Three Main Types of Kernel Locks: Spinlocks, Mutexes and Semaphores</title>
+   <title>Two Main Types of Kernel Locks: Spinlocks and Mutexes</title>
 
    <para>
-     There are three main types of kernel locks.  The fundamental type
+     There are two main types of kernel locks.  The fundamental type
      is the spinlock 
      (<filename class="headerfile">include/asm/spinlock.h</filename>),
      which is a very simple single-holder lock: if you can't get the 
@@ -239,14 +239,6 @@
      can't sleep (see <xref linkend="sleeping-things"/>), and so have to
      use a spinlock instead.
    </para>
-   <para>
-     The third type is a semaphore
-     (<filename class="headerfile">include/linux/semaphore.h</filename>): it
-     can have more than one holder at any time (the number decided at
-     initialization time), although it is most commonly used as a
-     single-holder lock (a mutex).  If you can't get a semaphore, your
-     task will be suspended and later on woken up - just like for mutexes.
-   </para>
    <para>
      Neither type of lock is recursive: see
      <xref linkend="deadlock"/>.
@@ -278,7 +270,7 @@
     </para>
 
     <para>
-      Semaphores still exist, because they are required for
+      Mutexes still exist, because they are required for
       synchronization between <firstterm linkend="gloss-usercontext">user 
       contexts</firstterm>, as we will see below.
     </para>
@@ -289,18 +281,17 @@
 
      <para>
        If you have a data structure which is only ever accessed from
-       user context, then you can use a simple semaphore
-       (<filename>linux/linux/semaphore.h</filename>) to protect it.  This
-       is the most trivial case: you initialize the semaphore to the number 
-       of resources available (usually 1), and call
-       <function>down_interruptible()</function> to grab the semaphore, and 
-       <function>up()</function> to release it.  There is also a 
-       <function>down()</function>, which should be avoided, because it 
+       user context, then you can use a simple mutex
+       (<filename>include/linux/mutex.h</filename>) to protect it.  This
+       is the most trivial case: you initialize the mutex.  Then you can
+       call <function>mutex_lock_interruptible()</function> to grab the mutex,
+       and <function>mutex_unlock()</function> to release it.  There is also a 
+       <function>mutex_lock()</function>, which should be avoided, because it 
        will not return if a signal is received.
      </para>
 
      <para>
-       Example: <filename>linux/net/core/netfilter.c</filename> allows 
+       Example: <filename>net/netfilter/nf_sockopt.c</filename> allows 
        registration of new <function>setsockopt()</function> and 
        <function>getsockopt()</function> calls, with
        <function>nf_register_sockopt()</function>.  Registration and 
@@ -515,7 +506,7 @@
       <listitem>
 	<para>
           If you are in a process context (any syscall) and want to
-	lock other process out, use a semaphore.  You can take a semaphore
+	lock other process out, use a mutex.  You can take a mutex
 	and sleep (<function>copy_from_user*(</function> or
 	<function>kmalloc(x,GFP_KERNEL)</function>).
       </para>
@@ -662,7 +653,7 @@
 <entry>SLBH</entry>
 <entry>SLBH</entry>
 <entry>SLBH</entry>
-<entry>DI</entry>
+<entry>MLI</entry>
 <entry>None</entry>
 </row>
 
@@ -692,8 +683,8 @@
 <entry>spin_lock_bh</entry>
 </row>
 <row>
-<entry>DI</entry>
-<entry>down_interruptible</entry>
+<entry>MLI</entry>
+<entry>mutex_lock_interruptible</entry>
 </row>
 
 </tbody>
@@ -1310,7 +1301,7 @@ as Alan Cox says, <quote>Lock data, not code</quote>.
     <para>
       There is a coding bug where a piece of code tries to grab a
       spinlock twice: it will spin forever, waiting for the lock to
-      be released (spinlocks, rwlocks and semaphores are not
+      be released (spinlocks, rwlocks and mutexes are not
       recursive in Linux).  This is trivial to diagnose: not a
       stay-up-five-nights-talk-to-fluffy-code-bunnies kind of
       problem.
@@ -1335,7 +1326,7 @@ as Alan Cox says, <quote>Lock data, not code</quote>.
 
     <para>
       This complete lockup is easy to diagnose: on SMP boxes the
-      watchdog timer or compiling with <symbol>DEBUG_SPINLOCKS</symbol> set
+      watchdog timer or compiling with <symbol>DEBUG_SPINLOCK</symbol> set
       (<filename>include/linux/spinlock.h</filename>) will show this up 
       immediately when it happens.
     </para>
@@ -1558,7 +1549,7 @@ the amount of locking which needs to be done.
    <title>Read/Write Lock Variants</title>
 
    <para>
-      Both spinlocks and semaphores have read/write variants:
+      Both spinlocks and mutexes have read/write variants:
       <type>rwlock_t</type> and <structname>struct rw_semaphore</structname>.
       These divide users into two classes: the readers and the writers.  If
       you are only reading the data, you can get a read lock, but to write to
@@ -1681,7 +1672,7 @@ the amount of locking which needs to be done.
  #include &lt;linux/slab.h&gt;
  #include &lt;linux/string.h&gt;
 +#include &lt;linux/rcupdate.h&gt;
- #include &lt;linux/semaphore.h&gt;
+ #include &lt;linux/mutex.h&gt;
  #include &lt;asm/errno.h&gt;
 
  struct object
@@ -1913,7 +1904,7 @@ machines due to caching.
        </listitem>
        <listitem>
         <para>
-          <function> put_user()</function>
+          <function>put_user()</function>
         </para>
        </listitem>
       </itemizedlist>
@@ -1927,13 +1918,13 @@ machines due to caching.
 
      <listitem>
       <para>
-      <function>down_interruptible()</function> and
-      <function>down()</function>
+      <function>mutex_lock_interruptible()</function> and
+      <function>mutex_lock()</function>
       </para>
       <para>
-       There is a <function>down_trylock()</function> which can be
+       There is a <function>mutex_trylock()</function> which can be
        used inside interrupt context, as it will not sleep.
-       <function>up()</function> will also never sleep.
+       <function>mutex_unlock()</function> will also never sleep.
       </para>
      </listitem>
     </itemizedlist>
@@ -2023,7 +2014,7 @@ machines due to caching.
       <para>
         Prior to 2.5, or when <symbol>CONFIG_PREEMPT</symbol> is
         unset, processes in user context inside the kernel would not
-        preempt each other (ie. you had that CPU until you have it up,
+        preempt each other (ie. you had that CPU until you gave it up,
         except for interrupts).  With the addition of
         <symbol>CONFIG_PREEMPT</symbol> in 2.5.4, this changed: when
         in user context, higher priority tasks can "cut in": spinlocks

Documentation/DocBook/kgdb.tmpl

@@ -98,6 +98,24 @@
     "Kernel debugging" select "KGDB: kernel debugging with remote gdb".
     </para>
     <para>
+    It is advised, but not required that you turn on the
+    CONFIG_FRAME_POINTER kernel option.  This option inserts code to
+    into the compiled executable which saves the frame information in
+    registers or on the stack at different points which will allow a
+    debugger such as gdb to more accurately construct stack back traces
+    while debugging the kernel.
+    </para>
+    <para>
+    If the architecture that you are using supports the kernel option
+    CONFIG_DEBUG_RODATA, you should consider turning it off.  This
+    option will prevent the use of software breakpoints because it
+    marks certain regions of the kernel's memory space as read-only.
+    If kgdb supports it for the architecture you are using, you can
+    use hardware breakpoints if you desire to run with the
+    CONFIG_DEBUG_RODATA option turned on, else you need to turn off
+    this option.
+    </para>
+    <para>
     Next you should choose one of more I/O drivers to interconnect debugging
     host and debugged target.  Early boot debugging requires a KGDB
     I/O driver that supports early debugging and the driver must be

Documentation/DocBook/procfs-guide.tmpl

@@ -29,12 +29,12 @@
 
     <revhistory>
       <revision>
-	<revnumber>1.0&nbsp;</revnumber>
+	<revnumber>1.0</revnumber>
 	<date>May 30, 2001</date>
 	<revremark>Initial revision posted to linux-kernel</revremark>
       </revision>
       <revision>
-	<revnumber>1.1&nbsp;</revnumber>
+	<revnumber>1.1</revnumber>
 	<date>June 3, 2001</date>
 	<revremark>Revised after comments from linux-kernel</revremark>
       </revision>

Documentation/DocBook/s390-drivers.tmpl

@@ -100,7 +100,7 @@
       the hardware structures represented here, please consult the Principles
       of Operation.
     </para>
-!Iinclude/asm-s390/cio.h
+!Iarch/s390/include/asm/cio.h
     </sect1>
     <sect1 id="ccwdev">
      <title>ccw devices</title>
@@ -114,7 +114,7 @@
       ccw device structure. Device drivers must not bypass those functions
       or strange side effects may happen.
     </para>
-!Iinclude/asm-s390/ccwdev.h
+!Iarch/s390/include/asm/ccwdev.h
 !Edrivers/s390/cio/device.c
 !Edrivers/s390/cio/device_ops.c
     </sect1>
@@ -125,7 +125,7 @@
 	measurement data which is made available by the channel subsystem
 	for each channel attached device.
   </para>
-!Iinclude/asm-s390/cmb.h
+!Iarch/s390/include/asm/cmb.h
 !Edrivers/s390/cio/cmf.c
     </sect1>
   </chapter>
@@ -142,7 +142,7 @@
   </para>
    <sect1 id="ccwgroupdevices">
     <title>ccw group devices</title>
-!Iinclude/asm-s390/ccwgroup.h
+!Iarch/s390/include/asm/ccwgroup.h
 !Edrivers/s390/cio/ccwgroup.c
    </sect1>
   </chapter>

Documentation/DocBook/sh.tmpl

@@ -0,0 +1,105 @@
+<?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="sh-drivers">
+ <bookinfo>
+  <title>SuperH Interfaces Guide</title>
+  
+  <authorgroup>
+   <author>
+    <firstname>Paul</firstname>
+    <surname>Mundt</surname>
+    <affiliation>
+     <address>
+      <email>lethal@linux-sh.org</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <copyright>
+   <year>2008</year>
+   <holder>Paul Mundt</holder>
+  </copyright>
+  <copyright>
+   <year>2008</year>
+   <holder>Renesas Technology Corp.</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 program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+      
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 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>
+ </bookinfo>
+
+<toc></toc>
+
+  <chapter id="mm">
+    <title>Memory Management</title>
+    <sect1 id="sh4">
+    <title>SH-4</title>
+      <sect2 id="sq">
+        <title>Store Queue API</title>
+!Earch/sh/kernel/cpu/sh4/sq.c
+      </sect2>
+    </sect1>
+    <sect1 id="sh5">
+      <title>SH-5</title>
+      <sect2 id="tlb">
+	<title>TLB Interfaces</title>
+!Iarch/sh/mm/tlb-sh5.c
+!Iarch/sh/include/asm/tlb_64.h
+      </sect2>
+    </sect1>
+  </chapter>
+  <chapter id="clk">
+    <title>Clock Framework Extensions</title>
+!Iarch/sh/include/asm/clock.h
+  </chapter>
+  <chapter id="mach">
+    <title>Machine Specific Interfaces</title>
+    <sect1 id="dreamcast">
+      <title>mach-dreamcast</title>
+!Iarch/sh/boards/mach-dreamcast/rtc.c
+    </sect1>
+    <sect1 id="x3proto">
+      <title>mach-x3proto</title>
+!Earch/sh/boards/mach-x3proto/ilsel.c
+    </sect1>
+  </chapter>
+  <chapter id="busses">
+    <title>Busses</title>
+    <sect1 id="superhyway">
+      <title>SuperHyway</title>
+!Edrivers/sh/superhyway/superhyway.c
+    </sect1>
+
+    <sect1 id="maple">
+      <title>Maple</title>
+!Edrivers/sh/maple/maple.c
+    </sect1>
+  </chapter>
+</book>

Documentation/DocBook/uio-howto.tmpl

@@ -21,6 +21,18 @@
     </affiliation>
 </author>
 
+<copyright>
+	<year>2006-2008</year>
+	<holder>Hans-Jürgen Koch.</holder>
+</copyright>
+
+<legalnotice>
+<para>
+This documentation is Free Software licensed under the terms of the
+GPL version 2.
+</para>
+</legalnotice>
+
 <pubdate>2006-12-11</pubdate>
 
 <abstract>
@@ -29,6 +41,12 @@
 </abstract>
 
 <revhistory>
+	<revision>
+	<revnumber>0.5</revnumber>
+	<date>2008-05-22</date>
+	<authorinitials>hjk</authorinitials>
+	<revremark>Added description of write() function.</revremark>
+	</revision>
 	<revision>
 	<revnumber>0.4</revnumber>
 	<date>2007-11-26</date>
@@ -57,20 +75,9 @@
 </bookinfo>
 
 <chapter id="aboutthisdoc">
-<?dbhtml filename="about.html"?>
+<?dbhtml filename="aboutthis.html"?>
 <title>About this document</title>
 
-<sect1 id="copyright">
-<?dbhtml filename="copyright.html"?>
-<title>Copyright and License</title>
-<para>
-      Copyright (c) 2006 by Hans-Jürgen Koch.</para>
-<para>
-This documentation is Free Software licensed under the terms of the
-GPL version 2.
-</para>
-</sect1>
-
 <sect1 id="translations">
 <?dbhtml filename="translations.html"?>
 <title>Translations</title>
@@ -189,6 +196,30 @@ interested in translating it, please email me
 	represents the total interrupt count. You can use this number
 	to figure out if you missed some interrupts.
 	</para>
+	<para>
+	For some hardware that has more than one interrupt source internally,
+	but not separate IRQ mask and status registers, there might be
+	situations where userspace cannot determine what the interrupt source
+	was if the kernel handler disables them by writing to the chip's IRQ
+	register. In such a case, the kernel has to disable the IRQ completely
+	to leave the chip's register untouched. Now the userspace part can
+	determine the cause of the interrupt, but it cannot re-enable
+	interrupts. Another cornercase is chips where re-enabling interrupts
+	is a read-modify-write operation to a combined IRQ status/acknowledge
+	register. This would be racy if a new interrupt occurred
+	simultaneously.
+	</para>
+	<para>
+	To address these problems, UIO also implements a write() function. It
+	is normally not used and can be ignored for hardware that has only a
+	single interrupt source or has separate IRQ mask and status registers.
+	If you need it, however, a write to <filename>/dev/uioX</filename>
+	will call the <function>irqcontrol()</function> function implemented
+	by the driver. You have to write a 32-bit value that is usually either
+	0 or 1 to disable or enable interrupts. If a driver does not implement
+	<function>irqcontrol()</function>, <function>write()</function> will
+	return with <varname>-ENOSYS</varname>.
+	</para>
 
 	<para>
 	To handle interrupts properly, your custom kernel module can
@@ -362,6 +393,14 @@ device is actually used.
 <function>open()</function>, you will probably also want a custom
 <function>release()</function> function.
 </para></listitem>
+
+<listitem><para>
+<varname>int (*irqcontrol)(struct uio_info *info, s32 irq_on)
+</varname>: Optional. If you need to be able to enable or disable
+interrupts from userspace by writing to <filename>/dev/uioX</filename>,
+you can implement this function. The parameter <varname>irq_on</varname>
+will be 0 to disable interrupts and 1 to enable them.
+</para></listitem>
 </itemizedlist>
 
 <para>

Documentation/HOWTO

@@ -358,7 +358,7 @@ Here is a list of some of the different kernel trees available:
     - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
 	git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
 
-    - SCSI, James Bottomley <James.Bottomley@SteelEye.com>
+    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
 	git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
 
     - x86, Ingo Molnar <mingo@elte.hu>

Documentation/Intel-IOMMU.txt

@@ -48,7 +48,7 @@ IOVA generation is pretty generic. We used the same technique as vmalloc()
 but these are not global address spaces, but separate for each domain.
 Different DMA engines may support different number of domains.
 
-We also allocate gaurd pages with each mapping, so we can attempt to catch
+We also allocate guard pages with each mapping, so we can attempt to catch
 any overflow that might happen.
 
 
@@ -112,4 +112,4 @@ TBD
 
 - For compatibility testing, could use unity map domain for all devices, just
   provide a 1-1 for all useful memory under a single domain for all devices.
-- API for paravirt ops for abstracting functionlity for VMM folks.
+- API for paravirt ops for abstracting functionality for VMM folks.

Documentation/RCU/NMI-RCU.txt

@@ -93,6 +93,9 @@ Since NMI handlers disable preemption, synchronize_sched() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
 to free up the handler's data as soon as synchronize_sched() returns.
 
+Important note: for this to work, the architecture in question must
+invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
+
 
 Answer to Quick Quiz
 

Documentation/RCU/RTFP.txt

@@ -52,6 +52,10 @@ of each iteration.  Unfortunately, chaotic relaxation requires highly
 structured data, such as the matrices used in scientific programs, and
 is thus inapplicable to most data structures in operating-system kernels.
 
+In 1992, Henry (now Alexia) Massalin completed a dissertation advising
+parallel programmers to defer processing when feasible to simplify
+synchronization.  RCU makes extremely heavy use of this advice.
+
 In 1993, Jacobson [Jacobson93] verbally described what is perhaps the
 simplest deferred-free technique: simply waiting a fixed amount of time
 before freeing blocks awaiting deferred free.  Jacobson did not describe
@@ -138,6 +142,13 @@ blocking in read-side critical sections appeared [PaulEMcKenney2006c],
 Robert Olsson described an RCU-protected trie-hash combination
 [RobertOlsson2006a].
 
+2007 saw the journal version of the award-winning RCU paper from 2006
+[ThomasEHart2007a], as well as a paper demonstrating use of Promela
+and Spin to mechanically verify an optimization to Oleg Nesterov's
+QRCU [PaulEMcKenney2007QRCUspin], a design document describing
+preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
+LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
+PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
 Bibtex Entries
 
@@ -202,6 +213,20 @@ Bibtex Entries
 ,Year="1991"
 }
 
+@phdthesis{HMassalinPhD
+,author="H. Massalin"
+,title="Synthesis: An Efficient Implementation of Fundamental Operating
+System Services"
+,school="Columbia University"
+,address="New York, NY"
+,year="1992"
+,annotation="
+	Mondo optimizing compiler.
+	Wait-free stuff.
+	Good advice: defer work to avoid synchronization.
+"
+}
+
 @unpublished{Jacobson93
 ,author="Van Jacobson"
 ,title="Avoid Read-Side Locking Via Delayed Free"
@@ -635,3 +660,86 @@ Revised:
 "
 }
 
+@unpublished{PaulEMcKenney2007PreemptibleRCU
+,Author="Paul E. McKenney"
+,Title="The design of preemptible read-copy-update"
+,month="October"
+,day="8"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/253651/}
+[Viewed October 25, 2007]"
+,annotation="
+	LWN article describing the design of preemptible RCU.
+"
+}
+
+########################################################################
+#
+#	"What is RCU?" LWN series.
+#
+
+@unpublished{PaulEMcKenney2007WhatIsRCUFundamentally
+,Author="Paul E. McKenney and Jonathan Walpole"
+,Title="What is {RCU}, Fundamentally?"
+,month="December"
+,day="17"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/262464/}
+[Viewed December 27, 2007]"
+,annotation="
+	Lays out the three basic components of RCU: (1) publish-subscribe,
+	(2) wait for pre-existing readers to complete, and (2) maintain
+	multiple versions.
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUUsage
+,Author="Paul E. McKenney"
+,Title="What is {RCU}? Part 2: Usage"
+,month="January"
+,day="4"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/263130/}
+[Viewed January 4, 2008]"
+,annotation="
+	Lays out six uses of RCU:
+	1. RCU is a Reader-Writer Lock Replacement
+	2. RCU is a Restricted Reference-Counting Mechanism
+	3. RCU is a Bulk Reference-Counting Mechanism
+	4. RCU is a Poor Man's Garbage Collector
+	5. RCU is a Way of Providing Existence Guarantees
+	6. RCU is a Way of Waiting for Things to Finish 
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUAPI
+,Author="Paul E. McKenney"
+,Title="{RCU} part 3: the {RCU} {API}"
+,month="January"
+,day="17"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/264090/}
+[Viewed January 10, 2008]"
+,annotation="
+	Gives an overview of the Linux-kernel RCU API and a brief annotated RCU
+	bibliography.
+"
+}
+
+@article{DinakarGuniguntala2008IBMSysJ
+,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
+,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
+,Year="2008"
+,Month="April"
+,journal="IBM Systems Journal"
+,volume="47"
+,number="2"
+,pages="@@-@@"
+,annotation="
+	RCU, realtime RCU, sleepable RCU, performance.
+"
+}

Documentation/RCU/checklist.txt

@@ -13,10 +13,13 @@ over a rather long period of time, but improvements are always welcome!
 	detailed performance measurements show that RCU is nonetheless
 	the right tool for the job.
 
-	The other exception would be where performance is not an issue,
-	and RCU provides a simpler implementation.  An example of this
-	situation is the dynamic NMI code in the Linux 2.6 kernel,
-	at least on architectures where NMIs are rare.
+	Another exception is where performance is not an issue, and RCU
+	provides a simpler implementation.  An example of this situation
+	is the dynamic NMI code in the Linux 2.6 kernel, at least on
+	architectures where NMIs are rare.
+
+	Yet another exception is where the low real-time latency of RCU's
+	read-side primitives is critically important.
 
 1.	Does the update code have proper mutual exclusion?
 
@@ -39,9 +42,10 @@ over a rather long period of time, but improvements are always welcome!
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
-	to suppress preemption (or bottom halves, in the case of
-	rcu_read_lock_bh()) in the read-side critical sections,
-	and are also an excellent aid to readability.
+	to prevent grace periods from ending prematurely, which
+	could result in data being unceremoniously freed out from
+	under your read-side code, which can greatly increase the
+	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
 	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
@@ -54,15 +58,30 @@ over a rather long period of time, but improvements are always welcome!
 	be running while updates are in progress.  There are a number
 	of ways to handle this concurrency, depending on the situation:
 
-	a.	Make updates appear atomic to readers.  For example,
+	a.	Use the RCU variants of the list and hlist update
+		primitives to add, remove, and replace elements on an
+		RCU-protected list.  Alternatively, use the RCU-protected
+		trees that have been added to the Linux kernel.
+
+		This is almost always the best approach.
+
+	b.	Proceed as in (a) above, but also maintain per-element
+		locks (that are acquired by both readers and writers)
+		that guard per-element state.  Of course, fields that
+		the readers refrain from accessing can be guarded by the
+		update-side lock.
+
+		This works quite well, also.
+
+	c.	Make updates appear atomic to readers.  For example,
 		pointer updates to properly aligned fields will appear
 		atomic, as will individual atomic primitives.  Operations
 		performed under a lock and sequences of multiple atomic
 		primitives will -not- appear to be atomic.
 
-		This is almost always the best approach.
+		This can work, but is starting to get a bit tricky.
 
-	b.	Carefully order the updates and the reads so that
+	d.	Carefully order the updates and the reads so that
 		readers see valid data at all phases of the update.
 		This is often more difficult than it sounds, especially
 		given modern CPUs' tendency to reorder memory references.
@@ -123,18 +142,22 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
-	is used, the callback function must be written to be called
-	from softirq context.  In particular, it cannot block.
+5.	If call_rcu(), or a related primitive such as call_rcu_bh() or
+	call_rcu_sched(), is used, the callback function must be
+	written to be called from softirq context.  In particular,
+	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.
+	any sort of irq context.  Ditto for synchronize_sched() and
+	synchronize_srcu().
 
 7.	If the updater uses call_rcu(), then the corresponding readers
 	must use rcu_read_lock() and rcu_read_unlock().  If the updater
 	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  Mixing things up
-	will result in confusion and broken kernels.
+	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
+	uses call_rcu_sched(), then the corresponding readers must
+	disable preemption.  Mixing things up will result in confusion
+	and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -143,9 +166,9 @@ over a rather long period of time, but improvements are always welcome!
 	such cases is a must, of course!  And the jury is still out on
 	whether the increased speed is worth it.
 
-8.	Although synchronize_rcu() is a bit slower than is call_rcu(),
-	it usually results in simpler code.  So, unless update
-	performance is critically important or the updaters cannot block,
+8.	Although synchronize_rcu() is slower than is call_rcu(), it
+	usually results in simpler code.  So, unless update performance
+	is critically important or the updaters cannot block,
 	synchronize_rcu() should be used in preference to call_rcu().
 
 	An especially important property of the synchronize_rcu()
@@ -187,23 +210,23 @@ over a rather long period of time, but improvements are always welcome!
 		number of updates per grace period.
 
 9.	All RCU list-traversal primitives, which include
-	list_for_each_rcu(), list_for_each_entry_rcu(),
+	rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
-	must be within an RCU read-side critical section.  RCU
+	must be either within an RCU read-side critical section or
+	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
 	rcu_read_lock_bh() and rcu_read_unlock_bh().
 
-	Use of the _rcu() list-traversal primitives outside of an
-	RCU read-side critical section causes no harm other than
-	a slight performance degradation on Alpha CPUs.  It can
-	also be quite helpful in reducing code bloat when common
-	code is shared between readers and updaters.
+	The reason that it is permissible to use RCU list-traversal
+	primitives when the update-side lock is held is that doing so
+	can be quite helpful in reducing code bloat when common code is
+	shared between readers and updaters.
 
 10.	Conversely, if you are in an RCU read-side critical section,
-	you -must- use the "_rcu()" variants of the list macros.
-	Failing to do so will break Alpha and confuse people reading
-	your code.
+	and you don't hold the appropriate update-side lock, you -must-
+	use the "_rcu()" variants of the list macros.  Failing to do so
+	will break Alpha and confuse people reading your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -230,6 +253,14 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
+	RCU callbacks are -usually- executed on the same CPU that executed
+	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
+	but are by -no- means guaranteed to be.  For example, if a given
+	CPU goes offline while having an RCU callback pending, then that
+	RCU callback will execute on some surviving CPU.  (If this was
+	not the case, a self-spawning RCU callback would prevent the
+	victim CPU from ever going offline.)
+
 14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
 	may only be invoked from process context.  Unlike other forms of
 	RCU, it -is- permissible to block in an SRCU read-side critical

Documentation/RCU/torture.txt

@@ -10,23 +10,30 @@ status messages via printk(), which can be examined via the dmesg
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
 
 This module has the following parameters:
 
-nreaders	This is the number of RCU reading threads supported.
-		The default is twice the number of CPUs.  Why twice?
-		To properly exercise RCU implementations with preemptible
-		read-side critical sections.
+irqreaders	Says to invoke RCU readers from irq level.  This is currently
+		done via timers.  Defaults to "1" for variants of RCU that
+		permit this.  (Or, more accurately, variants of RCU that do
+		-not- permit this know to ignore this variable.)
 
 nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		writer threads repeatedly use the synchronous "wait for
@@ -37,6 +44,16 @@ nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		to trigger special cases caused by multiple writers, such as
 		the synchronize_srcu() early return optimization.
 
+nreaders	This is the number of RCU reading threads supported.
+		The default is twice the number of CPUs.  Why twice?
+		To properly exercise RCU implementations with preemptible
+		read-side critical sections.
+
+shuffle_interval
+		The number of seconds to keep the test threads affinitied
+		to a particular subset of the CPUs, defaults to 3 seconds.
+		Used in conjunction with test_no_idle_hz.
+
 stat_interval	The number of seconds between output of torture
 		statistics (via printk()).  Regardless of the interval,
 		statistics are printed when the module is unloaded.
@@ -44,10 +61,11 @@ stat_interval	The number of seconds between output of torture
 		be printed -only- when the module is unloaded, and this
 		is the default.
 
-shuffle_interval
-		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 5 seconds.
-		Used in conjunction with test_no_idle_hz.
+stutter		The length of time to run the test before pausing for this
+		same period of time.  Defaults to "stutter=5", so as
+		to run and pause for (roughly) five-second intervals.
+		Specifying "stutter=0" causes the test to run continuously
+		without pausing, which is the old default behavior.
 
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to

Documentation/RCU/whatisRCU.txt

@@ -1,3 +1,11 @@
+Please note that the "What is RCU?" LWN series is an excellent place
+to start learning about RCU:
+
+1.	What is RCU, Fundamentally?  http://lwn.net/Articles/262464/
+2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
+3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
+
+
 What is RCU?
 
 RCU is a synchronization mechanism that was added to the Linux kernel
@@ -772,26 +780,18 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-Markers for RCU read-side critical sections:
-
-	rcu_read_lock
-	rcu_read_unlock
-	rcu_read_lock_bh
-	rcu_read_unlock_bh
-	srcu_read_lock
-	srcu_read_unlock
-
 RCU pointer/list traversal:
 
 	rcu_dereference
+	list_for_each_entry_rcu
+	hlist_for_each_entry_rcu
+
 	list_for_each_rcu		(to be deprecated in favor of
 					 list_for_each_entry_rcu)
-	list_for_each_entry_rcu
 	list_for_each_continue_rcu	(to be deprecated in favor of new
 					 list_for_each_entry_continue_rcu)
-	hlist_for_each_entry_rcu
 
-RCU pointer update:
+RCU pointer/list update:
 
 	rcu_assign_pointer
 	list_add_rcu
@@ -799,16 +799,36 @@ RCU pointer update:
 	list_del_rcu
 	list_replace_rcu
 	hlist_del_rcu
+	hlist_add_after_rcu
+	hlist_add_before_rcu
 	hlist_add_head_rcu
+	hlist_replace_rcu
+	list_splice_init_rcu()
 
-RCU grace period:
+RCU:	Critical sections	Grace period		Barrier
+
+	rcu_read_lock		synchronize_net		rcu_barrier
+	rcu_read_unlock		synchronize_rcu
+				call_rcu
+
+
+bh:	Critical sections	Grace period		Barrier
+
+	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
+	rcu_read_unlock_bh
+
+
+sched:	Critical sections	Grace period		Barrier
+
+	[preempt_disable]	synchronize_sched	rcu_barrier_sched
+	[and friends]		call_rcu_sched
+
+
+SRCU:	Critical sections	Grace period		Barrier
+
+	srcu_read_lock		synchronize_srcu	N/A
+	srcu_read_unlock
 
-	synchronize_net
-	synchronize_sched
-	synchronize_rcu
-	synchronize_srcu
-	call_rcu
-	call_rcu_bh
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.

Documentation/SubmittingPatches

@@ -528,7 +528,33 @@ See more details on the proper patch format in the following
 references.
 
 
+16) Sending "git pull" requests  (from Linus emails)
 
+Please write the git repo address and branch name alone on the same line
+so that I can't even by mistake pull from the wrong branch, and so
+that a triple-click just selects the whole thing.
+
+So the proper format is something along the lines of:
+
+	"Please pull from
+
+		git://jdelvare.pck.nerim.net/jdelvare-2.6 i2c-for-linus
+
+	 to get these changes:"
+
+so that I don't have to hunt-and-peck for the address and inevitably
+get it wrong (actually, I've only gotten it wrong a few times, and
+checking against the diffstat tells me when I get it wrong, but I'm
+just a lot more comfortable when I don't have to "look for" the right
+thing to pull, and double-check that I have the right branch-name).
+
+
+Please use "git diff -M --stat --summary" to generate the diffstat:
+the -M enables rename detection, and the summary enables a summary of
+new/deleted or renamed files.
+
+With rename detection, the statistics are rather different [...]
+because git will notice that a fair number of the changes are renames.
 
 -----------------------------------
 SECTION 2 - HINTS, TIPS, AND TRICKS

Documentation/accounting/delay-accounting.txt

@@ -11,6 +11,7 @@ the delays experienced by a task while
 a) waiting for a CPU (while being runnable)
 b) completion of synchronous block I/O initiated by the task
 c) swapping in pages
+d) memory reclaim
 
 and makes these statistics available to userspace through
 the taskstats interface.
@@ -41,7 +42,7 @@ this structure. See
      include/linux/taskstats.h
 for a description of the fields pertaining to delay accounting.
 It will generally be in the form of counters returning the cumulative
-delay seen for cpu, sync block I/O, swapin etc.
+delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
 
 Taking the difference of two successive readings of a given
 counter (say cpu_delay_total) for a task will give the delay
@@ -94,7 +95,9 @@ CPU	count	real total	virtual total	delay total
 	7876	92005750	100000000	24001500
 IO	count	delay total
 	0	0
-MEM	count	delay total
+SWAP	count	delay total
+	0	0
+RECLAIM	count	delay total
 	0	0
 
 Get delays seen in executing a given simple command
@@ -108,5 +111,7 @@ CPU	count	real total	virtual total	delay total
 	6	4000250		4000000		0
 IO	count	delay total
 	0	0
-MEM	count	delay total
+SWAP	count	delay total
+	0	0
+RECLAIM	count	delay total
 	0	0

Documentation/accounting/getdelays.c

@@ -196,14 +196,18 @@ void print_delayacct(struct taskstats *t)
 	       "      %15llu%15llu%15llu%15llu\n"
 	       "IO    %15s%15s\n"
 	       "      %15llu%15llu\n"
-	       "MEM   %15s%15s\n"
+	       "SWAP  %15s%15s\n"
+	       "      %15llu%15llu\n"
+	       "RECLAIM  %12s%15s\n"
 	       "      %15llu%15llu\n",
 	       "count", "real total", "virtual total", "delay total",
 	       t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total,
 	       t->cpu_delay_total,
 	       "count", "delay total",
 	       t->blkio_count, t->blkio_delay_total,
-	       "count", "delay total", t->swapin_count, t->swapin_delay_total);
+	       "count", "delay total", t->swapin_count, t->swapin_delay_total,
+	       "count", "delay total",
+	       t->freepages_count, t->freepages_delay_total);
 }
 
 void task_context_switch_counts(struct taskstats *t)

Documentation/accounting/taskstats-struct.txt

@@ -6,7 +6,7 @@ This document contains an explanation of the struct taskstats fields.
 There are three different groups of fields in the struct taskstats:
 
 1) Common and basic accounting fields
-    If CONFIG_TASKSTATS is set, the taskstats inteface is enabled and
+    If CONFIG_TASKSTATS is set, the taskstats interface is enabled and
     the common fields and basic accounting fields are collected for
     delivery at do_exit() of a task.
 2) Delay accounting fields
@@ -26,6 +26,8 @@ There are three different groups of fields in the struct taskstats:
 
 5) Time accounting for SMT machines
 
+6) Extended delay accounting fields for memory reclaim
+
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
 
@@ -170,4 +172,9 @@ struct taskstats {
 	__u64	ac_utimescaled;		/* utime scaled on frequency etc */
 	__u64	ac_stimescaled;		/* stime scaled on frequency etc */
 	__u64	cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
+
+6) Extended delay accounting fields for memory reclaim
+	/* Delay waiting for memory reclaim */
+	__u64	freepages_count;
+	__u64	freepages_delay_total;
 }

Documentation/arm/IXP4xx

@@ -32,7 +32,7 @@ Linux currently supports the following features on the IXP4xx chips:
 - Flash access (MTD/JFFS)
 - I2C through GPIO on IXP42x
 - GPIO for input/output/interrupts 
-  See include/asm-arm/arch-ixp4xx/platform.h for access functions.
+  See arch/arm/mach-ixp4xx/include/mach/platform.h for access functions.
 - Timers (watchdog, OS)
 
 The following components of the chips are not supported by Linux and

Documentation/arm/Interrupts

@@ -138,14 +138,8 @@ So, what's changed?
 
                 Set active the IRQ edge(s)/level.  This replaces the
                 SA1111 INTPOL manipulation, and the set_GPIO_IRQ_edge()
-                function.  Type should be one of the following:
-
-                #define IRQT_NOEDGE     (0)
-                #define IRQT_RISING     (__IRQT_RISEDGE)
-                #define IRQT_FALLING    (__IRQT_FALEDGE)
-                #define IRQT_BOTHEDGE   (__IRQT_RISEDGE|__IRQT_FALEDGE)
-                #define IRQT_LOW        (__IRQT_LOWLVL)
-                #define IRQT_HIGH       (__IRQT_HIGHLVL)
+                function.  Type should be one of IRQ_TYPE_xxx defined in
+		<linux/irq.h>
 
 3. set_GPIO_IRQ_edge() is obsolete, and should be replaced by set_irq_type.
 
@@ -164,7 +158,7 @@ So, what's changed?
    be re-checked for pending events.  (see the Neponset IRQ handler for
    details).
 
-7. fixup_irq() is gone, as is include/asm-arm/arch-*/irq.h
+7. fixup_irq() is gone, as is arch/arm/mach-*/include/mach/irq.h
 
 Please note that this will not solve all problems - some of them are
 hardware based.  Mixing level-based and edge-based IRQs on the same

Documentation/arm/README

@@ -79,7 +79,7 @@ Machine/Platform support
   To this end, we now have arch/arm/mach-$(MACHINE) directories which are
   designed to house the non-driver files for a particular machine (eg, PCI,
   memory management, architecture definitions etc).  For all future
-  machines, there should be a corresponding include/asm-arm/arch-$(MACHINE)
+  machines, there should be a corresponding arch/arm/mach-$(MACHINE)/include/mach
   directory.
 
 
@@ -176,7 +176,7 @@ Kernel entry (head.S)
   class typically based around one or more system on a chip devices, and
   acts as a natural container around the actual implementations.  These
   classes are given directories - arch/arm/mach-<class> and
-  include/asm-arm/arch-<class> - which contain the source files to
+  arch/arm/mach-<class> - which contain the source files to/include/mach
   support the machine class.  This directories also contain any machine
   specific supporting code.
 

Documentation/arm/Samsung-S3C24XX/GPIO.txt

@@ -16,13 +16,13 @@ Introduction
 Headers
 -------
 
-  See include/asm-arm/arch-s3c2410/regs-gpio.h for the list
+  See arch/arm/mach-s3c2410/include/mach/regs-gpio.h for the list
   of GPIO pins, and the configuration values for them. This
-  is included by using #include <asm/arch/regs-gpio.h>
+  is included by using #include <mach/regs-gpio.h>
 
   The GPIO management functions are defined in the hardware
-  header include/asm-arm/arch-s3c2410/hardware.h which can be
-  included by #include <asm/arch/hardware.h>
+  header arch/arm/mach-s3c2410/include/mach/hardware.h which can be
+  included by #include <mach/hardware.h>
 
   A useful amount of documentation can be found in the hardware
   header on how the GPIO functions (and others) work.

Documentation/arm/Samsung-S3C24XX/Overview.txt

@@ -36,7 +36,7 @@ Layout
   in arch/arm/mach-s3c2410 and S3C2440 in arch/arm/mach-s3c2440
 
   Register, kernel and platform data definitions are held in the
-  include/asm-arm/arch-s3c2410 directory.
+  arch/arm/mach-s3c2410 directory./include/mach
 
 
 Machines

Documentation/arm/Samsung-S3C24XX/USB-Host.txt

@@ -49,7 +49,7 @@ Board Support
 Platform Data
 -------------
 
-  See linux/include/asm-arm/arch-s3c2410/usb-control.h for the
+  See arch/arm/mach-s3c2410/include/mach/usb-control.h for the
   descriptions of the platform device data. An implementation
   can be found in linux/arch/arm/mach-s3c2410/usb-simtec.c .
 

Documentation/bt8xxgpio.txt

@@ -0,0 +1,67 @@
+===============================================================
+==  BT8XXGPIO driver                                         ==
+==                                                           ==
+==  A driver for a selfmade cheap BT8xx based PCI GPIO-card  ==
+==                                                           ==
+==  For advanced documentation, see                          ==
+==  http://www.bu3sch.de/btgpio.php                          ==
+===============================================================
+
+
+A generic digital 24-port PCI GPIO card can be built out of an ordinary
+Brooktree bt848, bt849, bt878 or bt879 based analog TV tuner card. The
+Brooktree chip is used in old analog Hauppauge WinTV PCI cards. You can easily
+find them used for low prices on the net.
+
+The bt8xx chip does have 24 digital GPIO ports.
+These ports are accessible via 24 pins on the SMD chip package.
+
+
+==============================================
+==  How to physically access the GPIO pins  ==
+==============================================
+
+The are several ways to access these pins. One might unsolder the whole chip
+and put it on a custom PCI board, or one might only unsolder each individual
+GPIO pin and solder that to some tiny wire. As the chip package really is tiny
+there are some advanced soldering skills needed in any case.
+
+The physical pinouts are drawn in the following ASCII art.
+The GPIO pins are marked with G00-G23
+
+                                           G G G G G G G G G G G G     G G G G G G
+                                           0 0 0 0 0 0 0 0 0 0 1 1     1 1 1 1 1 1
+                                           0 1 2 3 4 5 6 7 8 9 0 1     2 3 4 5 6 7
+           | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
+           ---------------------------------------------------------------------------
+         --|                               ^                                     ^   |--
+         --|                               pin 86                           pin 67   |--
+         --|                                                                         |--
+         --|                                                               pin 61 >  |-- G18
+         --|                                                                         |-- G19
+         --|                                                                         |-- G20
+         --|                                                                         |-- G21
+         --|                                                                         |-- G22
+         --|                                                               pin 56 >  |-- G23
+         --|                                                                         |--
+         --|                           Brooktree 878/879                             |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|   O                                                                     |--
+         --|                                                                         |--
+           ---------------------------------------------------------------------------
+           | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
+           ^
+           This is pin 1
+

Documentation/cli-sti-removal.txt

@@ -1,133 +0,0 @@
-
-#### cli()/sti() removal guide, started by Ingo Molnar <mingo@redhat.com>
-
-
-as of 2.5.28, five popular macros have been removed on SMP, and
-are being phased out on UP:
-
- cli(), sti(), save_flags(flags), save_flags_cli(flags), restore_flags(flags)
-
-until now it was possible to protect driver code against interrupt
-handlers via a cli(), but from now on other, more lightweight methods
-have to be used for synchronization, such as spinlocks or semaphores.
-
-for example, driver code that used to do something like:
-
-	struct driver_data;
-
-	irq_handler (...)
-	{
-		....
-		driver_data.finish = 1;
-		driver_data.new_work = 0;
-		....
-	}
-
-	...
-
-	ioctl_func (...)
-	{
-		...
-		cli();
-		...
-		driver_data.finish = 0;
-		driver_data.new_work = 2;
-		...
-		sti();
-		...
-	}
-
-was SMP-correct because the cli() function ensured that no
-interrupt handler (amongst them the above irq_handler()) function
-would execute while the cli()-ed section is executing.
-
-but from now on a more direct method of locking has to be used:
-
-	DEFINE_SPINLOCK(driver_lock);
-	struct driver_data;
-
-	irq_handler (...)
-	{
-		unsigned long flags;
-		....
-		spin_lock_irqsave(&driver_lock, flags);
-		....
-		driver_data.finish = 1;
-		driver_data.new_work = 0;
-		....
-		spin_unlock_irqrestore(&driver_lock, flags);
-		....
-	}
-
-	...
-
-	ioctl_func (...)
-	{
-		...
-		spin_lock_irq(&driver_lock);
-		...
-		driver_data.finish = 0;
-		driver_data.new_work = 2;
-		...
-		spin_unlock_irq(&driver_lock);
-		...
-	}
-
-the above code has a number of advantages:
-
-- the locking relation is easier to understand - actual lock usage
-  pinpoints the critical sections. cli() usage is too opaque.
-  Easier to understand means it's easier to debug.
-
-- it's faster, because spinlocks are faster to acquire than the
-  potentially heavily-used IRQ lock. Furthermore, your driver does
-  not have to wait eg. for a big heavy SCSI interrupt to finish,
-  because the driver_lock spinlock is only used by your driver.
-  cli() on the other hand was used by many drivers, and extended
-  the critical section to the whole IRQ handler function - creating
-  serious lock contention.
-
- 
-to make the transition easier, we've still kept the cli(), sti(),
-save_flags(), save_flags_cli() and restore_flags() macros defined
-on UP systems - but their usage will be phased out until 2.6 is
-released.
-
-drivers that want to disable local interrupts (interrupts on the
-current CPU), can use the following five macros:
-
-  local_irq_disable(), local_irq_enable(), local_save_flags(flags),
-  local_irq_save(flags), local_irq_restore(flags)
-
-but beware, their meaning and semantics are much simpler, far from
-that of the old cli(), sti(), save_flags(flags) and restore_flags(flags)
-SMP meaning:
-
-    local_irq_disable()       => turn local IRQs off
-
-    local_irq_enable()        => turn local IRQs on
-
-    local_save_flags(flags)   => save the current IRQ state into flags. The
-                                 state can be on or off. (on some
-                                 architectures there's even more bits in it.)
-
-    local_irq_save(flags)     => save the current IRQ state into flags and
-                                 disable interrupts.
-
-    local_irq_restore(flags)  => restore the IRQ state from flags.
-
-(local_irq_save can save both irqs on and irqs off state, and
-local_irq_restore can restore into both irqs on and irqs off state.)
-
-another related change is that synchronize_irq() now takes a parameter:
-synchronize_irq(irq). This change too has the purpose of making SMP
-synchronization more lightweight - this way you can wait for your own
-interrupt handler to finish, no need to wait for other IRQ sources.
-
-
-why were these changes done? The main reason was the architectural burden
-of maintaining the cli()/sti() interface - it became a real problem. The
-new interrupt system is much more streamlined, easier to understand, debug,
-and it's also a bit faster - the same happened to it that will happen to
-cli()/sti() using drivers once they convert to spinlocks :-)
-

Documentation/controllers/memory.txt

@@ -242,8 +242,7 @@ rmdir() if there are no tasks.
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
 3. Teach controller to account for shared-pages
-4. Start reclamation when the limit is lowered
-5. Start reclamation in the background when the limit is
+4. Start reclamation in the background when the limit is
    not yet hit but the usage is getting closer
 
 Summary

Documentation/cpu-freq/governors.txt

@@ -122,7 +122,7 @@ around '10000' or more.
 show_sampling_rate_(min|max): the minimum and maximum sampling rates
 available that you may set 'sampling_rate' to.
 
-up_threshold: defines what the average CPU usaged between the samplings
+up_threshold: defines what the average CPU usage between the samplings
 of 'sampling_rate' needs to be for the kernel to make a decision on
 whether it should increase the frequency.  For example when it is set
 to its default value of '80' it means that between the checking

Documentation/edac.txt

@@ -222,74 +222,9 @@ both csrow2 and csrow3 are populated, this indicates a dual ranked
 set of DIMMs for channels 0 and 1.
 
 
-Within each of the 'mc','mcX' and 'csrowX' directories are several
+Within each of the 'mcX' and 'csrowX' directories are several
 EDAC control and attribute files.
 
-
-============================================================================
-DIRECTORY 'mc'
-
-In directory 'mc' are EDAC system overall control and attribute files:
-
-
-Panic on UE control file:
-
-	'edac_mc_panic_on_ue'
-
-	An uncorrectable error will cause a machine panic.  This is usually
-	desirable.  It is a bad idea to continue when an uncorrectable error
-	occurs - it is indeterminate what was uncorrected and the operating
-	system context might be so mangled that continuing will lead to further
-	corruption. If the kernel has MCE configured, then EDAC will never
-	notice the UE.
-
-	LOAD TIME: module/kernel parameter: panic_on_ue=[0|1]
-
-	RUN TIME:  echo "1" >/sys/devices/system/edac/mc/edac_mc_panic_on_ue
-
-
-Log UE control file:
-
-	'edac_mc_log_ue'
-
-	Generate kernel messages describing uncorrectable errors.  These errors
-	are reported through the system message log system.  UE statistics
-	will be accumulated even when UE logging is disabled.
-
-	LOAD TIME: module/kernel parameter: log_ue=[0|1]
-
-	RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ue
-
-
-Log CE control file:
-
-	'edac_mc_log_ce'
-
-	Generate kernel messages describing correctable errors.  These
-	errors are reported through the system message log system.
-	CE statistics will be accumulated even when CE logging is disabled.
-
-	LOAD TIME: module/kernel parameter: log_ce=[0|1]
-
-	RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ce
-
-
-Polling period control file:
-
-	'edac_mc_poll_msec'
-
-	The time period, in milliseconds, for polling for error information.
-	Too small a value wastes resources.  Too large a value might delay
-	necessary handling of errors and might loose valuable information for
-	locating the error.  1000 milliseconds (once each second) is the current
-	default. Systems which require all the bandwidth they can get, may
-	increase this.
-
-	LOAD TIME: module/kernel parameter: poll_msec=[0|1]
-
-	RUN TIME: echo "1000" >/sys/devices/system/edac/mc/edac_mc_poll_msec
-
-
 ============================================================================
 'mcX' DIRECTORIES
 
@@ -392,7 +327,7 @@ Sdram memory scrubbing rate:
 	'sdram_scrub_rate'
 
 	Read/Write attribute file that controls memory scrubbing. The scrubbing
-	rate is set by writing a minimum bandwith in bytes/sec to the attribute
+	rate is set by writing a minimum bandwidth in bytes/sec to the attribute
 	file. The rate will be translated to an internal value that gives at
 	least the specified rate.
 
@@ -537,7 +472,6 @@ Channel 1 DIMM Label control file:
 	motherboard specific and determination of this information
 	must occur in userland at this time.
 
-
 ============================================================================
 SYSTEM LOGGING
 
@@ -570,7 +504,6 @@ error type, a notice of "no info" and then an optional,
 driver-specific error message.
 
 
-
 ============================================================================
 PCI Bus Parity Detection
 
@@ -604,6 +537,74 @@ Enable/Disable PCI Parity checking control file:
 	echo "0" >/sys/devices/system/edac/pci/check_pci_parity
 
 
+Parity Count:
+
+	'pci_parity_count'
+
+	This attribute file will display the number of parity errors that
+	have been detected.
+
+
+============================================================================
+MODULE PARAMETERS
+
+Panic on UE control file:
+
+	'edac_mc_panic_on_ue'
+
+	An uncorrectable error will cause a machine panic.  This is usually
+	desirable.  It is a bad idea to continue when an uncorrectable error
+	occurs - it is indeterminate what was uncorrected and the operating
+	system context might be so mangled that continuing will lead to further
+	corruption. If the kernel has MCE configured, then EDAC will never
+	notice the UE.
+
+	LOAD TIME: module/kernel parameter: edac_mc_panic_on_ue=[0|1]
+
+	RUN TIME:  echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue
+
+
+Log UE control file:
+
+	'edac_mc_log_ue'
+
+	Generate kernel messages describing uncorrectable errors.  These errors
+	are reported through the system message log system.  UE statistics
+	will be accumulated even when UE logging is disabled.
+
+	LOAD TIME: module/kernel parameter: edac_mc_log_ue=[0|1]
+
+	RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue
+
+
+Log CE control file:
+
+	'edac_mc_log_ce'
+
+	Generate kernel messages describing correctable errors.  These
+	errors are reported through the system message log system.
+	CE statistics will be accumulated even when CE logging is disabled.
+
+	LOAD TIME: module/kernel parameter: edac_mc_log_ce=[0|1]
+
+	RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce
+
+
+Polling period control file:
+
+	'edac_mc_poll_msec'
+
+	The time period, in milliseconds, for polling for error information.
+	Too small a value wastes resources.  Too large a value might delay
+	necessary handling of errors and might loose valuable information for
+	locating the error.  1000 milliseconds (once each second) is the current
+	default. Systems which require all the bandwidth they can get, may
+	increase this.
+
+	LOAD TIME: module/kernel parameter: edac_mc_poll_msec=[0|1]
+
+	RUN TIME: echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec
+
 
 Panic on PCI PARITY Error:
 
@@ -614,21 +615,13 @@ Panic on PCI PARITY Error:
 	error has been detected.
 
 
-	module/kernel parameter: panic_on_pci_parity=[0|1]
+	module/kernel parameter: edac_panic_on_pci_pe=[0|1]
 
 	Enable:
-	echo "1" >/sys/devices/system/edac/pci/panic_on_pci_parity
+	echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe
 
 	Disable:
-	echo "0" >/sys/devices/system/edac/pci/panic_on_pci_parity
-
-
-Parity Count:
-
-	'pci_parity_count'
-
-	This attribute file will display the number of parity errors that
-	have been detected.
+	echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe
 
 
 

Documentation/fb/sh7760fb.txt

@@ -0,0 +1,131 @@
+SH7760/SH7763 integrated LCDC Framebuffer driver
+================================================
+
+0. Overwiew
+-----------
+The SH7760/SH7763 have an integrated LCD Display controller (LCDC) which
+supports (in theory) resolutions ranging from 1x1 to 1024x1024,
+with color depths ranging from 1 to 16 bits, on STN, DSTN and TFT Panels.
+
+Caveats:
+* Framebuffer memory must be a large chunk allocated at the top
+  of Area3 (HW requirement). Because of this requirement you should NOT
+  make the driver a module since at runtime it may become impossible to
+  get a large enough contiguous chunk of memory.
+
+* The driver does not support changing resolution while loaded
+  (displays aren't hotpluggable anyway)
+
+* Heavy flickering may be observed
+  a) if you're using 15/16bit color modes at >= 640x480 px resolutions,
+  b) during PCMCIA (or any other slow bus) activity.
+
+* Rotation works only 90degress clockwise, and only if horizontal
+  resolution is <= 320 pixels.
+
+files:   drivers/video/sh7760fb.c
+        include/asm-sh/sh7760fb.h
+        Documentation/fb/sh7760fb.txt
+
+1. Platform setup
+-----------------
+SH7760:
+ Video data is fetched via the DMABRG DMA engine, so you have to
+ configure the SH DMAC for DMABRG mode (write 0x94808080 to the
+ DMARSRA register somewhere at boot).
+
+ PFC registers PCCR and PCDR must be set to peripheral mode.
+ (write zeros to both).
+
+The driver does NOT do the above for you since board setup is, well, job
+of the board setup code.
+
+2. Panel definitions
+--------------------
+The LCDC must explicitly be told about the type of LCD panel
+attached.  Data must be wrapped in a "struct sh7760fb_platdata" and
+passed to the driver as platform_data.
+
+Suggest you take a closer look at the SH7760 Manual, Section 30.
+(http://documentation.renesas.com/eng/products/mpumcu/e602291_sh7760.pdf)
+
+The following code illustrates what needs to be done to
+get the framebuffer working on a 640x480 TFT:
+
+====================== cut here ======================================
+
+#include <linux/fb.h>
+#include <asm/sh7760fb.h>
+
+/*
+ * NEC NL6440bc26-01 640x480 TFT
+ * dotclock 25175 kHz
+ * Xres                640     Yres            480
+ * Htotal      800     Vtotal          525
+ * HsynStart   656     VsynStart       490
+ * HsynLenn    30      VsynLenn        2
+ *
+ * The linux framebuffer layer does not use the syncstart/synclen
+ * values but right/left/upper/lower margin values. The comments
+ * for the x_margin explain how to calculate those from given
+ * panel sync timings.
+ */
+static struct fb_videomode nl6448bc26 = {
+       .name           = "NL6448BC26",
+       .refresh        = 60,
+       .xres           = 640,
+       .yres           = 480,
+       .pixclock       = 39683,        /* in picoseconds! */
+       .hsync_len      = 30,
+       .vsync_len      = 2,
+       .left_margin    = 114,  /* HTOT - (HSYNSLEN + HSYNSTART) */
+       .right_margin   = 16,   /* HSYNSTART - XRES */
+       .upper_margin   = 33,   /* VTOT - (VSYNLEN + VSYNSTART) */
+       .lower_margin   = 10,   /* VSYNSTART - YRES */
+       .sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+       .vmode          = FB_VMODE_NONINTERLACED,
+       .flag           = 0,
+};
+
+static struct sh7760fb_platdata sh7760fb_nl6448 = {
+       .def_mode       = &nl6448bc26,
+       .ldmtr          = LDMTR_TFT_COLOR_16,   /* 16bit TFT panel */
+       .lddfr          = LDDFR_8BPP,           /* we want 8bit output */
+       .ldpmmr         = 0x0070,
+       .ldpspr         = 0x0500,
+       .ldaclnr        = 0,
+       .ldickr         = LDICKR_CLKSRC(LCDC_CLKSRC_EXTERNAL) |
+                         LDICKR_CLKDIV(1),
+       .rotate         = 0,
+       .novsync        = 1,
+       .blank          = NULL,
+};
+
+/* SH7760:
+ * 0xFE300800: 256 * 4byte xRGB palette ram
+ * 0xFE300C00: 42 bytes ctrl registers
+ */
+static struct resource sh7760_lcdc_res[] = {
+       [0] = {
+               .start  = 0xFE300800,
+               .end    = 0xFE300CFF,
+               .flags  = IORESOURCE_MEM,
+       },
+       [1] = {
+               .start  = 65,
+               .end    = 65,
+               .flags  = IORESOURCE_IRQ,
+       },
+};
+
+static struct platform_device sh7760_lcdc_dev = {
+       .dev    = {
+               .platform_data = &sh7760fb_nl6448,
+       },
+       .name           = "sh7760-lcdc",
+       .id             = -1,
+       .resource       = sh7760_lcdc_res,
+       .num_resources  = ARRAY_SIZE(sh7760_lcdc_res),
+};
+
+====================== cut here ======================================

Documentation/fb/tridentfb.txt

@@ -3,11 +3,25 @@ Tridentfb is a framebuffer driver for some Trident chip based cards.
 The following list of chips is thought to be supported although not all are
 tested:
 
-those from the Image series with Cyber in their names - accelerated
-those with Blade in their names (Blade3D,CyberBlade...) - accelerated
-the newer CyberBladeXP family  - nonaccelerated
-
-Only PCI/AGP based cards are supported, none of the older Tridents.
+those from the TGUI series 9440/96XX and with Cyber in their names
+those from the Image series and with Cyber in their names
+those with Blade in their names (Blade3D,CyberBlade...)
+the newer CyberBladeXP family
+
+All families are accelerated. Only PCI/AGP based cards are supported,
+none of the older Tridents.
+The driver supports 8, 16 and 32 bits per pixel depths.
+The TGUI family requires a line length to be power of 2 if acceleration
+is enabled. This means that range of possible resolutions and bpp is
+limited comparing to the range if acceleration is disabled (see list
+of parameters below).
+
+Known bugs:
+1. The driver randomly locks up on 3DImage975 chip with acceleration
+   enabled. The same happens in X11 (Xorg).
+2. The ramdac speeds require some more fine tuning. It is possible to
+   switch resolution which the chip does not support at some depths for
+   older chips.
 
 How to use it?
 ==============
@@ -17,12 +31,11 @@ video=tridentfb
 
 The parameters for tridentfb are concatenated with a ':' as in this example.
 
-video=tridentfb:800x600,bpp=16,noaccel
+video=tridentfb:800x600-16@75,noaccel
 
 The second level parameters that tridentfb understands are:
 
 noaccel - turns off acceleration (when it doesn't work for your card)
-accel - force text acceleration (for boards which by default are noacceled)
 
 fp	- use flat panel related stuff
 crt 	- assume monitor is present instead of fp
@@ -31,21 +44,24 @@ center 	- for flat panels and resolutions smaller than native size center the
 	  image, otherwise use
 stretch
 
-memsize - integer value in Kb, use if your card's memory size is misdetected.
+memsize - integer value in KB, use if your card's memory size is misdetected.
 	  look at the driver output to see what it says when initializing.
-memdiff - integer value in Kb,should be nonzero if your card reports
-	  more memory than it actually has.For instance mine is 192K less than
+
+memdiff - integer value in KB, should be nonzero if your card reports
+	  more memory than it actually has. For instance mine is 192K less than
 	  detection says in all three BIOS selectable situations 2M, 4M, 8M.
 	  Only use if your video memory is taken from main memory hence of
-	  configurable size.Otherwise use memsize.
-	  If in some modes which barely fit the memory you see garbage at the bottom
-	  this might help by not letting change to that mode anymore.
+	  configurable size. Otherwise use memsize.
+	  If in some modes which barely fit the memory you see garbage
+	  at the bottom this might help by not letting change to that mode
+	  anymore.
 
 nativex - the width in pixels of the flat panel.If you know it (usually 1024
 	  800 or 1280) and it is not what the driver seems to detect use it.
 
-bpp  - bits per pixel (8,16 or 32)
-mode - a mode name like 800x600 (as described in Documentation/fb/modedb.txt)
+bpp	- bits per pixel (8,16 or 32)
+mode	- a mode name like 800x600-8@75 as described in
+	  Documentation/fb/modedb.txt
 
 Using insane values for the above parameters will probably result in driver
 misbehaviour so take care(for instance memsize=12345678 or memdiff=23784 or

Documentation/feature-removal-schedule.txt

@@ -47,6 +47,30 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 
 ---------------------------
 
+What:	old tuner-3036 i2c driver
+When:	2.6.28
+Why:	This driver is for VERY old i2c-over-parallel port teletext receiver
+	boxes. Rather then spending effort on converting this driver to V4L2,
+	and since it is extremely unlikely that anyone still uses one of these
+	devices, it was decided to drop it.
+Who:	Hans Verkuil <hverkuil@xs4all.nl>
+	Mauro Carvalho Chehab <mchehab@infradead.org>
+
+ ---------------------------
+
+What:   V4L2 dpc7146 driver
+When:   2.6.28
+Why:    Old driver for the dpc7146 demonstration board that is no longer
+	relevant. The last time this was tested on actual hardware was
+	probably around 2002. Since this is a driver for a demonstration
+	board the decision was made to remove it rather than spending a
+	lot of effort continually updating this driver to stay in sync
+	with the latest internal V4L2 or I2C API.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
+	Mauro Carvalho Chehab <mchehab@infradead.org>
+
+---------------------------
+
 What:	PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
 When:	November 2005
 Files:	drivers/pcmcia/: pcmcia_ioctl.c
@@ -138,24 +162,6 @@ Who:	Kay Sievers <kay.sievers@suse.de>
 
 ---------------------------
 
-What:	find_task_by_pid
-When:	2.6.26
-Why:	With pid namespaces, calling this funciton will return the
-	wrong task when called from inside a namespace.
-
-	The best way to save a task pid and find a task by this
-	pid later, is to find this task's struct pid pointer (or get
-	it directly from the task) and call pid_task() later.
-
-	If someone really needs to get a task by its pid_t, then
-	he most likely needs the find_task_by_vpid() to get the
-	task from the same namespace as the current task is in, but
-	this may be not so in general.
-
-Who:	Pavel Emelyanov <xemul@openvz.org>
-
----------------------------
-
 What:	ACPI procfs interface
 When:	July 2008
 Why:	ACPI sysfs conversion should be finished by January 2008.
@@ -300,11 +306,15 @@ Who:	ocfs2-devel@oss.oracle.com
 
 ---------------------------
 
-What:	asm/semaphore.h
-When:	2.6.26
-Why:	Implementation became generic; users should now include
-	linux/semaphore.h instead.
-Who:	Matthew Wilcox <willy@linux.intel.com>
+What:	SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD,
+	SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD
+When: 	June 2009
+Why:    A newer version of the options have been introduced in 2005 that
+	removes the limitions of the old API.  The sctp library has been
+        converted to use these new options at the same time.  Any user
+	space app that directly uses the old options should convert to using
+	the new options.
+Who:	Vlad Yasevich <vladislav.yasevich@hp.com>
 
 ---------------------------
 
@@ -314,3 +324,23 @@ Why:	This option was introduced just to allow older lm-sensors userspace
 	to keep working over the upgrade to 2.6.26. At the scheduled time of
 	removal fixed lm-sensors (2.x or 3.x) should be readily available.
 Who:	Rene Herman <rene.herman@gmail.com>
+
+---------------------------
+
+What:	Code that is now under CONFIG_WIRELESS_EXT_SYSFS
+	(in net/core/net-sysfs.c)
+When:	After the only user (hal) has seen a release with the patches
+	for enough time, probably some time in 2010.
+Why:	Over 1K .text/.data size reduction, data is available in other
+	ways (ioctls)
+Who:	Johannes Berg <johannes@sipsolutions.net>
+
+---------------------------
+
+What: CONFIG_NF_CT_ACCT
+When: 2.6.29
+Why:  Accounting can now be enabled/disabled without kernel recompilation.
+      Currently used only to set a default value for a feature that is also
+      controlled by a kernel/module/sysfs/sysctl parameter.
+Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
+

Documentation/filesystems/Locking

@@ -510,6 +510,7 @@ prototypes:
 	void (*close)(struct vm_area_struct*);
 	int (*fault)(struct vm_area_struct*, struct vm_fault *);
 	int (*page_mkwrite)(struct vm_area_struct *, struct page *);
+	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
 		BKL	mmap_sem	PageLocked(page)
@@ -517,6 +518,7 @@ open:		no	yes
 close:		no	yes
 fault:		no	yes
 page_mkwrite:	no	yes		no
+access:		no	yes
 
 	->page_mkwrite() is called when a previously read-only page is
 about to become writeable. The file system is responsible for
@@ -525,6 +527,11 @@ taking to lock out truncate, the page range should be verified to be
 within i_size. The page mapping should also be checked that it is not
 NULL.
 
+	->access() is called when get_user_pages() fails in
+acces_process_vm(), typically used to debug a process through
+/proc/pid/mem or ptrace.  This function is needed only for
+VM_IO | VM_PFNMAP VMAs.
+
 ================================================================================
 			Dubious stuff
 

Documentation/filesystems/bfs.txt

@@ -26,11 +26,11 @@ You can simplify mounting by just typing:
 
 this will allocate the first available loopback device (and load loop.o 
 kernel module if necessary) automatically. If the loopback driver is not
-loaded automatically, make sure that your kernel is compiled with kmod 
-support (CONFIG_KMOD) enabled. Beware that umount will not
-deallocate /dev/loopN device if /etc/mtab file on your system is a
-symbolic link to /proc/mounts. You will need to do it manually using
-"-d" switch of losetup(8). Read losetup(8) manpage for more info.
+loaded automatically, make sure that you have compiled the module and
+that modprobe is functioning. Beware that umount will not deallocate
+/dev/loopN device if /etc/mtab file on your system is a symbolic link to
+/proc/mounts. You will need to do it manually using "-d" switch of
+losetup(8). Read losetup(8) manpage for more info.
 
 To create the BFS image under UnixWare you need to find out first which
 slice contains it. The command prtvtoc(1M) is your friend:

Documentation/filesystems/configfs/configfs.txt

@@ -311,9 +311,20 @@ the subsystem must be ready for it.
 [An Example]
 
 The best example of these basic concepts is the simple_children
-subsystem/group and the simple_child item in configfs_example.c  It
-shows a trivial object displaying and storing an attribute, and a simple
-group creating and destroying these children.
+subsystem/group and the simple_child item in configfs_example_explicit.c
+and configfs_example_macros.c.  It shows a trivial object displaying and
+storing an attribute, and a simple group creating and destroying these
+children.
+
+The only difference between configfs_example_explicit.c and
+configfs_example_macros.c is how the attributes of the childless item
+are defined.  The childless item has extended attributes, each with
+their own show()/store() operation.  This follows a convention commonly
+used in sysfs.  configfs_example_explicit.c creates these attributes
+by explicitly defining the structures involved.  Conversely
+configfs_example_macros.c uses some convenience macros from configfs.h
+to define the attributes.  These macros are similar to their sysfs
+counterparts.
 
 [Hierarchy Navigation and the Subsystem Mutex]
 

Documentation/filesystems/configfs/configfs_example.c

@@ -1,485 +0,0 @@
-/*
- * vim: noexpandtab ts=8 sts=0 sw=8:
- *
- * configfs_example.c - This file is a demonstration module containing
- *      a number of configfs subsystems.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
- *
- * Based on sysfs:
- * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
- *
- * configfs Copyright (C) 2005 Oracle.  All rights reserved.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-#include <linux/configfs.h>
-
-
-
-/*
- * 01-childless
- *
- * This first example is a childless subsystem.  It cannot create
- * any config_items.  It just has attributes.
- *
- * Note that we are enclosing the configfs_subsystem inside a container.
- * This is not necessary if a subsystem has no attributes directly
- * on the subsystem.  See the next example, 02-simple-children, for
- * such a subsystem.
- */
-
-struct childless {
-	struct configfs_subsystem subsys;
-	int showme;
-	int storeme;
-};
-
-struct childless_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct childless *, char *);
-	ssize_t (*store)(struct childless *, const char *, size_t);
-};
-
-static inline struct childless *to_childless(struct config_item *item)
-{
-	return item ? container_of(to_configfs_subsystem(to_config_group(item)), struct childless, subsys) : NULL;
-}
-
-static ssize_t childless_showme_read(struct childless *childless,
-				     char *page)
-{
-	ssize_t pos;
-
-	pos = sprintf(page, "%d\n", childless->showme);
-	childless->showme++;
-
-	return pos;
-}
-
-static ssize_t childless_storeme_read(struct childless *childless,
-				      char *page)
-{
-	return sprintf(page, "%d\n", childless->storeme);
-}
-
-static ssize_t childless_storeme_write(struct childless *childless,
-				       const char *page,
-				       size_t count)
-{
-	unsigned long tmp;
-	char *p = (char *) page;
-
-	tmp = simple_strtoul(p, &p, 10);
-	if (!p || (*p && (*p != '\n')))
-		return -EINVAL;
-
-	if (tmp > INT_MAX)
-		return -ERANGE;
-
-	childless->storeme = tmp;
-
-	return count;
-}
-
-static ssize_t childless_description_read(struct childless *childless,
-					  char *page)
-{
-	return sprintf(page,
-"[01-childless]\n"
-"\n"
-"The childless subsystem is the simplest possible subsystem in\n"
-"configfs.  It does not support the creation of child config_items.\n"
-"It only has a few attributes.  In fact, it isn't much different\n"
-"than a directory in /proc.\n");
-}
-
-static struct childless_attribute childless_attr_showme = {
-	.attr	= { .ca_owner = THIS_MODULE, .ca_name = "showme", .ca_mode = S_IRUGO },
-	.show	= childless_showme_read,
-};
-static struct childless_attribute childless_attr_storeme = {
-	.attr	= { .ca_owner = THIS_MODULE, .ca_name = "storeme", .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= childless_storeme_read,
-	.store	= childless_storeme_write,
-};
-static struct childless_attribute childless_attr_description = {
-	.attr = { .ca_owner = THIS_MODULE, .ca_name = "description", .ca_mode = S_IRUGO },
-	.show = childless_description_read,
-};
-
-static struct configfs_attribute *childless_attrs[] = {
-	&childless_attr_showme.attr,
-	&childless_attr_storeme.attr,
-	&childless_attr_description.attr,
-	NULL,
-};
-
-static ssize_t childless_attr_show(struct config_item *item,
-				   struct configfs_attribute *attr,
-				   char *page)
-{
-	struct childless *childless = to_childless(item);
-	struct childless_attribute *childless_attr =
-		container_of(attr, struct childless_attribute, attr);
-	ssize_t ret = 0;
-
-	if (childless_attr->show)
-		ret = childless_attr->show(childless, page);
-	return ret;
-}
-
-static ssize_t childless_attr_store(struct config_item *item,
-				    struct configfs_attribute *attr,
-				    const char *page, size_t count)
-{
-	struct childless *childless = to_childless(item);
-	struct childless_attribute *childless_attr =
-		container_of(attr, struct childless_attribute, attr);
-	ssize_t ret = -EINVAL;
-
-	if (childless_attr->store)
-		ret = childless_attr->store(childless, page, count);
-	return ret;
-}
-
-static struct configfs_item_operations childless_item_ops = {
-	.show_attribute		= childless_attr_show,
-	.store_attribute	= childless_attr_store,
-};
-
-static struct config_item_type childless_type = {
-	.ct_item_ops	= &childless_item_ops,
-	.ct_attrs	= childless_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-static struct childless childless_subsys = {
-	.subsys = {
-		.su_group = {
-			.cg_item = {
-				.ci_namebuf = "01-childless",
-				.ci_type = &childless_type,
-			},
-		},
-	},
-};
-
-
-/* ----------------------------------------------------------------- */
-
-/*
- * 02-simple-children
- *
- * This example merely has a simple one-attribute child.  Note that
- * there is no extra attribute structure, as the child's attribute is
- * known from the get-go.  Also, there is no container for the
- * subsystem, as it has no attributes of its own.
- */
-
-struct simple_child {
-	struct config_item item;
-	int storeme;
-};
-
-static inline struct simple_child *to_simple_child(struct config_item *item)
-{
-	return item ? container_of(item, struct simple_child, item) : NULL;
-}
-
-static struct configfs_attribute simple_child_attr_storeme = {
-	.ca_owner = THIS_MODULE,
-	.ca_name = "storeme",
-	.ca_mode = S_IRUGO | S_IWUSR,
-};
-
-static struct configfs_attribute *simple_child_attrs[] = {
-	&simple_child_attr_storeme,
-	NULL,
-};
-
-static ssize_t simple_child_attr_show(struct config_item *item,
-				      struct configfs_attribute *attr,
-				      char *page)
-{
-	ssize_t count;
-	struct simple_child *simple_child = to_simple_child(item);
-
-	count = sprintf(page, "%d\n", simple_child->storeme);
-
-	return count;
-}
-
-static ssize_t simple_child_attr_store(struct config_item *item,
-				       struct configfs_attribute *attr,
-				       const char *page, size_t count)
-{
-	struct simple_child *simple_child = to_simple_child(item);
-	unsigned long tmp;
-	char *p = (char *) page;
-
-	tmp = simple_strtoul(p, &p, 10);
-	if (!p || (*p && (*p != '\n')))
-		return -EINVAL;
-
-	if (tmp > INT_MAX)
-		return -ERANGE;
-
-	simple_child->storeme = tmp;
-
-	return count;
-}
-
-static void simple_child_release(struct config_item *item)
-{
-	kfree(to_simple_child(item));
-}
-
-static struct configfs_item_operations simple_child_item_ops = {
-	.release		= simple_child_release,
-	.show_attribute		= simple_child_attr_show,
-	.store_attribute	= simple_child_attr_store,
-};
-
-static struct config_item_type simple_child_type = {
-	.ct_item_ops	= &simple_child_item_ops,
-	.ct_attrs	= simple_child_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-
-struct simple_children {
-	struct config_group group;
-};
-
-static inline struct simple_children *to_simple_children(struct config_item *item)
-{
-	return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
-}
-
-static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
-{
-	struct simple_child *simple_child;
-
-	simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
-	if (!simple_child)
-		return NULL;
-
-
-	config_item_init_type_name(&simple_child->item, name,
-				   &simple_child_type);
-
-	simple_child->storeme = 0;
-
-	return &simple_child->item;
-}
-
-static struct configfs_attribute simple_children_attr_description = {
-	.ca_owner = THIS_MODULE,
-	.ca_name = "description",
-	.ca_mode = S_IRUGO,
-};
-
-static struct configfs_attribute *simple_children_attrs[] = {
-	&simple_children_attr_description,
-	NULL,
-};
-
-static ssize_t simple_children_attr_show(struct config_item *item,
-			   		 struct configfs_attribute *attr,
-			   		 char *page)
-{
-	return sprintf(page,
-"[02-simple-children]\n"
-"\n"
-"This subsystem allows the creation of child config_items.  These\n"
-"items have only one attribute that is readable and writeable.\n");
-}
-
-static void simple_children_release(struct config_item *item)
-{
-	kfree(to_simple_children(item));
-}
-
-static struct configfs_item_operations simple_children_item_ops = {
-	.release 	= simple_children_release,
-	.show_attribute	= simple_children_attr_show,
-};
-
-/*
- * Note that, since no extra work is required on ->drop_item(),
- * no ->drop_item() is provided.
- */
-static struct configfs_group_operations simple_children_group_ops = {
-	.make_item	= simple_children_make_item,
-};
-
-static struct config_item_type simple_children_type = {
-	.ct_item_ops	= &simple_children_item_ops,
-	.ct_group_ops	= &simple_children_group_ops,
-	.ct_attrs	= simple_children_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-static struct configfs_subsystem simple_children_subsys = {
-	.su_group = {
-		.cg_item = {
-			.ci_namebuf = "02-simple-children",
-			.ci_type = &simple_children_type,
-		},
-	},
-};
-
-
-/* ----------------------------------------------------------------- */
-
-/*
- * 03-group-children
- *
- * This example reuses the simple_children group from above.  However,
- * the simple_children group is not the subsystem itself, it is a
- * child of the subsystem.  Creation of a group in the subsystem creates
- * a new simple_children group.  That group can then have simple_child
- * children of its own.
- */
-
-static struct config_group *group_children_make_group(struct config_group *group, const char *name)
-{
-	struct simple_children *simple_children;
-
-	simple_children = kzalloc(sizeof(struct simple_children),
-				  GFP_KERNEL);
-	if (!simple_children)
-		return NULL;
-
-
-	config_group_init_type_name(&simple_children->group, name,
-				    &simple_children_type);
-
-	return &simple_children->group;
-}
-
-static struct configfs_attribute group_children_attr_description = {
-	.ca_owner = THIS_MODULE,
-	.ca_name = "description",
-	.ca_mode = S_IRUGO,
-};
-
-static struct configfs_attribute *group_children_attrs[] = {
-	&group_children_attr_description,
-	NULL,
-};
-
-static ssize_t group_children_attr_show(struct config_item *item,
-			   		struct configfs_attribute *attr,
-			   		char *page)
-{
-	return sprintf(page,
-"[03-group-children]\n"
-"\n"
-"This subsystem allows the creation of child config_groups.  These\n"
-"groups are like the subsystem simple-children.\n");
-}
-
-static struct configfs_item_operations group_children_item_ops = {
-	.show_attribute	= group_children_attr_show,
-};
-
-/*
- * Note that, since no extra work is required on ->drop_item(),
- * no ->drop_item() is provided.
- */
-static struct configfs_group_operations group_children_group_ops = {
-	.make_group	= group_children_make_group,
-};
-
-static struct config_item_type group_children_type = {
-	.ct_item_ops	= &group_children_item_ops,
-	.ct_group_ops	= &group_children_group_ops,
-	.ct_attrs	= group_children_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-static struct configfs_subsystem group_children_subsys = {
-	.su_group = {
-		.cg_item = {
-			.ci_namebuf = "03-group-children",
-			.ci_type = &group_children_type,
-		},
-	},
-};
-
-/* ----------------------------------------------------------------- */
-
-/*
- * We're now done with our subsystem definitions.
- * For convenience in this module, here's a list of them all.  It
- * allows the init function to easily register them.  Most modules
- * will only have one subsystem, and will only call register_subsystem
- * on it directly.
- */
-static struct configfs_subsystem *example_subsys[] = {
-	&childless_subsys.subsys,
-	&simple_children_subsys,
-	&group_children_subsys,
-	NULL,
-};
-
-static int __init configfs_example_init(void)
-{
-	int ret;
-	int i;
-	struct configfs_subsystem *subsys;
-
-	for (i = 0; example_subsys[i]; i++) {
-		subsys = example_subsys[i];
-
-		config_group_init(&subsys->su_group);
-		mutex_init(&subsys->su_mutex);
-		ret = configfs_register_subsystem(subsys);
-		if (ret) {
-			printk(KERN_ERR "Error %d while registering subsystem %s\n",
-			       ret,
-			       subsys->su_group.cg_item.ci_namebuf);
-			goto out_unregister;
-		}
-	}
-
-	return 0;
-
-out_unregister:
-	for (; i >= 0; i--) {
-		configfs_unregister_subsystem(example_subsys[i]);
-	}
-
-	return ret;
-}
-
-static void __exit configfs_example_exit(void)
-{
-	int i;
-
-	for (i = 0; example_subsys[i]; i++) {
-		configfs_unregister_subsystem(example_subsys[i]);
-	}
-}
-
-module_init(configfs_example_init);
-module_exit(configfs_example_exit);
-MODULE_LICENSE("GPL");

Documentation/filesystems/configfs/configfs_example_explicit.c

@@ -0,0 +1,485 @@
+/*
+ * vim: noexpandtab ts=8 sts=0 sw=8:
+ *
+ * configfs_example_explicit.c - This file is a demonstration module
+ *      containing a number of configfs subsystems.  It explicitly defines
+ *      each structure without using the helper macros defined in
+ *      configfs.h.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+
+
+/*
+ * 01-childless
+ *
+ * This first example is a childless subsystem.  It cannot create
+ * any config_items.  It just has attributes.
+ *
+ * Note that we are enclosing the configfs_subsystem inside a container.
+ * This is not necessary if a subsystem has no attributes directly
+ * on the subsystem.  See the next example, 02-simple-children, for
+ * such a subsystem.
+ */
+
+struct childless {
+	struct configfs_subsystem subsys;
+	int showme;
+	int storeme;
+};
+
+struct childless_attribute {
+	struct configfs_attribute attr;
+	ssize_t (*show)(struct childless *, char *);
+	ssize_t (*store)(struct childless *, const char *, size_t);
+};
+
+static inline struct childless *to_childless(struct config_item *item)
+{
+	return item ? container_of(to_configfs_subsystem(to_config_group(item)), struct childless, subsys) : NULL;
+}
+
+static ssize_t childless_showme_read(struct childless *childless,
+				     char *page)
+{
+	ssize_t pos;
+
+	pos = sprintf(page, "%d\n", childless->showme);
+	childless->showme++;
+
+	return pos;
+}
+
+static ssize_t childless_storeme_read(struct childless *childless,
+				      char *page)
+{
+	return sprintf(page, "%d\n", childless->storeme);
+}
+
+static ssize_t childless_storeme_write(struct childless *childless,
+				       const char *page,
+				       size_t count)
+{
+	unsigned long tmp;
+	char *p = (char *) page;
+
+	tmp = simple_strtoul(p, &p, 10);
+	if (!p || (*p && (*p != '\n')))
+		return -EINVAL;
+
+	if (tmp > INT_MAX)
+		return -ERANGE;
+
+	childless->storeme = tmp;
+
+	return count;
+}
+
+static ssize_t childless_description_read(struct childless *childless,
+					  char *page)
+{
+	return sprintf(page,
+"[01-childless]\n"
+"\n"
+"The childless subsystem is the simplest possible subsystem in\n"
+"configfs.  It does not support the creation of child config_items.\n"
+"It only has a few attributes.  In fact, it isn't much different\n"
+"than a directory in /proc.\n");
+}
+
+static struct childless_attribute childless_attr_showme = {
+	.attr	= { .ca_owner = THIS_MODULE, .ca_name = "showme", .ca_mode = S_IRUGO },
+	.show	= childless_showme_read,
+};
+static struct childless_attribute childless_attr_storeme = {
+	.attr	= { .ca_owner = THIS_MODULE, .ca_name = "storeme", .ca_mode = S_IRUGO | S_IWUSR },
+	.show	= childless_storeme_read,
+	.store	= childless_storeme_write,
+};
+static struct childless_attribute childless_attr_description = {
+	.attr = { .ca_owner = THIS_MODULE, .ca_name = "description", .ca_mode = S_IRUGO },
+	.show = childless_description_read,
+};
+
+static struct configfs_attribute *childless_attrs[] = {
+	&childless_attr_showme.attr,
+	&childless_attr_storeme.attr,
+	&childless_attr_description.attr,
+	NULL,
+};
+
+static ssize_t childless_attr_show(struct config_item *item,
+				   struct configfs_attribute *attr,
+				   char *page)
+{
+	struct childless *childless = to_childless(item);
+	struct childless_attribute *childless_attr =
+		container_of(attr, struct childless_attribute, attr);
+	ssize_t ret = 0;
+
+	if (childless_attr->show)
+		ret = childless_attr->show(childless, page);
+	return ret;
+}
+
+static ssize_t childless_attr_store(struct config_item *item,
+				    struct configfs_attribute *attr,
+				    const char *page, size_t count)
+{
+	struct childless *childless = to_childless(item);
+	struct childless_attribute *childless_attr =
+		container_of(attr, struct childless_attribute, attr);
+	ssize_t ret = -EINVAL;
+
+	if (childless_attr->store)
+		ret = childless_attr->store(childless, page, count);
+	return ret;
+}
+
+static struct configfs_item_operations childless_item_ops = {
+	.show_attribute		= childless_attr_show,
+	.store_attribute	= childless_attr_store,
+};
+
+static struct config_item_type childless_type = {
+	.ct_item_ops	= &childless_item_ops,
+	.ct_attrs	= childless_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct childless childless_subsys = {
+	.subsys = {
+		.su_group = {
+			.cg_item = {
+				.ci_namebuf = "01-childless",
+				.ci_type = &childless_type,
+			},
+		},
+	},
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 02-simple-children
+ *
+ * This example merely has a simple one-attribute child.  Note that
+ * there is no extra attribute structure, as the child's attribute is
+ * known from the get-go.  Also, there is no container for the
+ * subsystem, as it has no attributes of its own.
+ */
+
+struct simple_child {
+	struct config_item item;
+	int storeme;
+};
+
+static inline struct simple_child *to_simple_child(struct config_item *item)
+{
+	return item ? container_of(item, struct simple_child, item) : NULL;
+}
+
+static struct configfs_attribute simple_child_attr_storeme = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "storeme",
+	.ca_mode = S_IRUGO | S_IWUSR,
+};
+
+static struct configfs_attribute *simple_child_attrs[] = {
+	&simple_child_attr_storeme,
+	NULL,
+};
+
+static ssize_t simple_child_attr_show(struct config_item *item,
+				      struct configfs_attribute *attr,
+				      char *page)
+{
+	ssize_t count;
+	struct simple_child *simple_child = to_simple_child(item);
+
+	count = sprintf(page, "%d\n", simple_child->storeme);
+
+	return count;
+}
+
+static ssize_t simple_child_attr_store(struct config_item *item,
+				       struct configfs_attribute *attr,
+				       const char *page, size_t count)
+{
+	struct simple_child *simple_child = to_simple_child(item);
+	unsigned long tmp;
+	char *p = (char *) page;
+
+	tmp = simple_strtoul(p, &p, 10);
+	if (!p || (*p && (*p != '\n')))
+		return -EINVAL;
+
+	if (tmp > INT_MAX)
+		return -ERANGE;
+
+	simple_child->storeme = tmp;
+
+	return count;
+}
+
+static void simple_child_release(struct config_item *item)
+{
+	kfree(to_simple_child(item));
+}
+
+static struct configfs_item_operations simple_child_item_ops = {
+	.release		= simple_child_release,
+	.show_attribute		= simple_child_attr_show,
+	.store_attribute	= simple_child_attr_store,
+};
+
+static struct config_item_type simple_child_type = {
+	.ct_item_ops	= &simple_child_item_ops,
+	.ct_attrs	= simple_child_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+
+struct simple_children {
+	struct config_group group;
+};
+
+static inline struct simple_children *to_simple_children(struct config_item *item)
+{
+	return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
+}
+
+static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
+{
+	struct simple_child *simple_child;
+
+	simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
+	if (!simple_child)
+		return ERR_PTR(-ENOMEM);
+
+	config_item_init_type_name(&simple_child->item, name,
+				   &simple_child_type);
+
+	simple_child->storeme = 0;
+
+	return &simple_child->item;
+}
+
+static struct configfs_attribute simple_children_attr_description = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "description",
+	.ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *simple_children_attrs[] = {
+	&simple_children_attr_description,
+	NULL,
+};
+
+static ssize_t simple_children_attr_show(struct config_item *item,
+					 struct configfs_attribute *attr,
+					 char *page)
+{
+	return sprintf(page,
+"[02-simple-children]\n"
+"\n"
+"This subsystem allows the creation of child config_items.  These\n"
+"items have only one attribute that is readable and writeable.\n");
+}
+
+static void simple_children_release(struct config_item *item)
+{
+	kfree(to_simple_children(item));
+}
+
+static struct configfs_item_operations simple_children_item_ops = {
+	.release	= simple_children_release,
+	.show_attribute	= simple_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations simple_children_group_ops = {
+	.make_item	= simple_children_make_item,
+};
+
+static struct config_item_type simple_children_type = {
+	.ct_item_ops	= &simple_children_item_ops,
+	.ct_group_ops	= &simple_children_group_ops,
+	.ct_attrs	= simple_children_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct configfs_subsystem simple_children_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "02-simple-children",
+			.ci_type = &simple_children_type,
+		},
+	},
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 03-group-children
+ *
+ * This example reuses the simple_children group from above.  However,
+ * the simple_children group is not the subsystem itself, it is a
+ * child of the subsystem.  Creation of a group in the subsystem creates
+ * a new simple_children group.  That group can then have simple_child
+ * children of its own.
+ */
+
+static struct config_group *group_children_make_group(struct config_group *group, const char *name)
+{
+	struct simple_children *simple_children;
+
+	simple_children = kzalloc(sizeof(struct simple_children),
+				  GFP_KERNEL);
+	if (!simple_children)
+		return ERR_PTR(-ENOMEM);
+
+	config_group_init_type_name(&simple_children->group, name,
+				    &simple_children_type);
+
+	return &simple_children->group;
+}
+
+static struct configfs_attribute group_children_attr_description = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "description",
+	.ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *group_children_attrs[] = {
+	&group_children_attr_description,
+	NULL,
+};
+
+static ssize_t group_children_attr_show(struct config_item *item,
+					struct configfs_attribute *attr,
+					char *page)
+{
+	return sprintf(page,
+"[03-group-children]\n"
+"\n"
+"This subsystem allows the creation of child config_groups.  These\n"
+"groups are like the subsystem simple-children.\n");
+}
+
+static struct configfs_item_operations group_children_item_ops = {
+	.show_attribute	= group_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations group_children_group_ops = {
+	.make_group	= group_children_make_group,
+};
+
+static struct config_item_type group_children_type = {
+	.ct_item_ops	= &group_children_item_ops,
+	.ct_group_ops	= &group_children_group_ops,
+	.ct_attrs	= group_children_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct configfs_subsystem group_children_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "03-group-children",
+			.ci_type = &group_children_type,
+		},
+	},
+};
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * We're now done with our subsystem definitions.
+ * For convenience in this module, here's a list of them all.  It
+ * allows the init function to easily register them.  Most modules
+ * will only have one subsystem, and will only call register_subsystem
+ * on it directly.
+ */
+static struct configfs_subsystem *example_subsys[] = {
+	&childless_subsys.subsys,
+	&simple_children_subsys,
+	&group_children_subsys,
+	NULL,
+};
+
+static int __init configfs_example_init(void)
+{
+	int ret;
+	int i;
+	struct configfs_subsystem *subsys;
+
+	for (i = 0; example_subsys[i]; i++) {
+		subsys = example_subsys[i];
+
+		config_group_init(&subsys->su_group);
+		mutex_init(&subsys->su_mutex);
+		ret = configfs_register_subsystem(subsys);
+		if (ret) {
+			printk(KERN_ERR "Error %d while registering subsystem %s\n",
+			       ret,
+			       subsys->su_group.cg_item.ci_namebuf);
+			goto out_unregister;
+		}
+	}
+
+	return 0;
+
+out_unregister:
+	for (; i >= 0; i--) {
+		configfs_unregister_subsystem(example_subsys[i]);
+	}
+
+	return ret;
+}
+
+static void __exit configfs_example_exit(void)
+{
+	int i;
+
+	for (i = 0; example_subsys[i]; i++) {
+		configfs_unregister_subsystem(example_subsys[i]);
+	}
+}
+
+module_init(configfs_example_init);
+module_exit(configfs_example_exit);
+MODULE_LICENSE("GPL");

Documentation/filesystems/configfs/configfs_example_macros.c

@@ -0,0 +1,448 @@
+/*
+ * vim: noexpandtab ts=8 sts=0 sw=8:
+ *
+ * configfs_example_macros.c - This file is a demonstration module
+ *      containing a number of configfs subsystems.  It uses the helper
+ *      macros defined by configfs.h
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+
+
+/*
+ * 01-childless
+ *
+ * This first example is a childless subsystem.  It cannot create
+ * any config_items.  It just has attributes.
+ *
+ * Note that we are enclosing the configfs_subsystem inside a container.
+ * This is not necessary if a subsystem has no attributes directly
+ * on the subsystem.  See the next example, 02-simple-children, for
+ * such a subsystem.
+ */
+
+struct childless {
+	struct configfs_subsystem subsys;
+	int showme;
+	int storeme;
+};
+
+static inline struct childless *to_childless(struct config_item *item)
+{
+	return item ? container_of(to_configfs_subsystem(to_config_group(item)), struct childless, subsys) : NULL;
+}
+
+CONFIGFS_ATTR_STRUCT(childless);
+#define CHILDLESS_ATTR(_name, _mode, _show, _store)	\
+struct childless_attribute childless_attr_##_name = __CONFIGFS_ATTR(_name, _mode, _show, _store)
+#define CHILDLESS_ATTR_RO(_name, _show)	\
+struct childless_attribute childless_attr_##_name = __CONFIGFS_ATTR_RO(_name, _show);
+
+static ssize_t childless_showme_read(struct childless *childless,
+				     char *page)
+{
+	ssize_t pos;
+
+	pos = sprintf(page, "%d\n", childless->showme);
+	childless->showme++;
+
+	return pos;
+}
+
+static ssize_t childless_storeme_read(struct childless *childless,
+				      char *page)
+{
+	return sprintf(page, "%d\n", childless->storeme);
+}
+
+static ssize_t childless_storeme_write(struct childless *childless,
+				       const char *page,
+				       size_t count)
+{
+	unsigned long tmp;
+	char *p = (char *) page;
+
+	tmp = simple_strtoul(p, &p, 10);
+	if (!p || (*p && (*p != '\n')))
+		return -EINVAL;
+
+	if (tmp > INT_MAX)
+		return -ERANGE;
+
+	childless->storeme = tmp;
+
+	return count;
+}
+
+static ssize_t childless_description_read(struct childless *childless,
+					  char *page)
+{
+	return sprintf(page,
+"[01-childless]\n"
+"\n"
+"The childless subsystem is the simplest possible subsystem in\n"
+"configfs.  It does not support the creation of child config_items.\n"
+"It only has a few attributes.  In fact, it isn't much different\n"
+"than a directory in /proc.\n");
+}
+
+CHILDLESS_ATTR_RO(showme, childless_showme_read);
+CHILDLESS_ATTR(storeme, S_IRUGO | S_IWUSR, childless_storeme_read,
+	       childless_storeme_write);
+CHILDLESS_ATTR_RO(description, childless_description_read);
+
+static struct configfs_attribute *childless_attrs[] = {
+	&childless_attr_showme.attr,
+	&childless_attr_storeme.attr,
+	&childless_attr_description.attr,
+	NULL,
+};
+
+CONFIGFS_ATTR_OPS(childless);
+static struct configfs_item_operations childless_item_ops = {
+	.show_attribute		= childless_attr_show,
+	.store_attribute	= childless_attr_store,
+};
+
+static struct config_item_type childless_type = {
+	.ct_item_ops	= &childless_item_ops,
+	.ct_attrs	= childless_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct childless childless_subsys = {
+	.subsys = {
+		.su_group = {
+			.cg_item = {
+				.ci_namebuf = "01-childless",
+				.ci_type = &childless_type,
+			},
+		},
+	},
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 02-simple-children
+ *
+ * This example merely has a simple one-attribute child.  Note that
+ * there is no extra attribute structure, as the child's attribute is
+ * known from the get-go.  Also, there is no container for the
+ * subsystem, as it has no attributes of its own.
+ */
+
+struct simple_child {
+	struct config_item item;
+	int storeme;
+};
+
+static inline struct simple_child *to_simple_child(struct config_item *item)
+{
+	return item ? container_of(item, struct simple_child, item) : NULL;
+}
+
+static struct configfs_attribute simple_child_attr_storeme = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "storeme",
+	.ca_mode = S_IRUGO | S_IWUSR,
+};
+
+static struct configfs_attribute *simple_child_attrs[] = {
+	&simple_child_attr_storeme,
+	NULL,
+};
+
+static ssize_t simple_child_attr_show(struct config_item *item,
+				      struct configfs_attribute *attr,
+				      char *page)
+{
+	ssize_t count;
+	struct simple_child *simple_child = to_simple_child(item);
+
+	count = sprintf(page, "%d\n", simple_child->storeme);
+
+	return count;
+}
+
+static ssize_t simple_child_attr_store(struct config_item *item,
+				       struct configfs_attribute *attr,
+				       const char *page, size_t count)
+{
+	struct simple_child *simple_child = to_simple_child(item);
+	unsigned long tmp;
+	char *p = (char *) page;
+
+	tmp = simple_strtoul(p, &p, 10);
+	if (!p || (*p && (*p != '\n')))
+		return -EINVAL;
+
+	if (tmp > INT_MAX)
+		return -ERANGE;
+
+	simple_child->storeme = tmp;
+
+	return count;
+}
+
+static void simple_child_release(struct config_item *item)
+{
+	kfree(to_simple_child(item));
+}
+
+static struct configfs_item_operations simple_child_item_ops = {
+	.release		= simple_child_release,
+	.show_attribute		= simple_child_attr_show,
+	.store_attribute	= simple_child_attr_store,
+};
+
+static struct config_item_type simple_child_type = {
+	.ct_item_ops	= &simple_child_item_ops,
+	.ct_attrs	= simple_child_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+
+struct simple_children {
+	struct config_group group;
+};
+
+static inline struct simple_children *to_simple_children(struct config_item *item)
+{
+	return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
+}
+
+static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
+{
+	struct simple_child *simple_child;
+
+	simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
+	if (!simple_child)
+		return ERR_PTR(-ENOMEM);
+
+	config_item_init_type_name(&simple_child->item, name,
+				   &simple_child_type);
+
+	simple_child->storeme = 0;
+
+	return &simple_child->item;
+}
+
+static struct configfs_attribute simple_children_attr_description = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "description",
+	.ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *simple_children_attrs[] = {
+	&simple_children_attr_description,
+	NULL,
+};
+
+static ssize_t simple_children_attr_show(struct config_item *item,
+					 struct configfs_attribute *attr,
+					 char *page)
+{
+	return sprintf(page,
+"[02-simple-children]\n"
+"\n"
+"This subsystem allows the creation of child config_items.  These\n"
+"items have only one attribute that is readable and writeable.\n");
+}
+
+static void simple_children_release(struct config_item *item)
+{
+	kfree(to_simple_children(item));
+}
+
+static struct configfs_item_operations simple_children_item_ops = {
+	.release	= simple_children_release,
+	.show_attribute	= simple_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations simple_children_group_ops = {
+	.make_item	= simple_children_make_item,
+};
+
+static struct config_item_type simple_children_type = {
+	.ct_item_ops	= &simple_children_item_ops,
+	.ct_group_ops	= &simple_children_group_ops,
+	.ct_attrs	= simple_children_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct configfs_subsystem simple_children_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "02-simple-children",
+			.ci_type = &simple_children_type,
+		},
+	},
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 03-group-children
+ *
+ * This example reuses the simple_children group from above.  However,
+ * the simple_children group is not the subsystem itself, it is a
+ * child of the subsystem.  Creation of a group in the subsystem creates
+ * a new simple_children group.  That group can then have simple_child
+ * children of its own.
+ */
+
+static struct config_group *group_children_make_group(struct config_group *group, const char *name)
+{
+	struct simple_children *simple_children;
+
+	simple_children = kzalloc(sizeof(struct simple_children),
+				  GFP_KERNEL);
+	if (!simple_children)
+		return ERR_PTR(-ENOMEM);
+
+	config_group_init_type_name(&simple_children->group, name,
+				    &simple_children_type);
+
+	return &simple_children->group;
+}
+
+static struct configfs_attribute group_children_attr_description = {
+	.ca_owner = THIS_MODULE,
+	.ca_name = "description",
+	.ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *group_children_attrs[] = {
+	&group_children_attr_description,
+	NULL,
+};
+
+static ssize_t group_children_attr_show(struct config_item *item,
+					struct configfs_attribute *attr,
+					char *page)
+{
+	return sprintf(page,
+"[03-group-children]\n"
+"\n"
+"This subsystem allows the creation of child config_groups.  These\n"
+"groups are like the subsystem simple-children.\n");
+}
+
+static struct configfs_item_operations group_children_item_ops = {
+	.show_attribute	= group_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations group_children_group_ops = {
+	.make_group	= group_children_make_group,
+};
+
+static struct config_item_type group_children_type = {
+	.ct_item_ops	= &group_children_item_ops,
+	.ct_group_ops	= &group_children_group_ops,
+	.ct_attrs	= group_children_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct configfs_subsystem group_children_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "03-group-children",
+			.ci_type = &group_children_type,
+		},
+	},
+};
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * We're now done with our subsystem definitions.
+ * For convenience in this module, here's a list of them all.  It
+ * allows the init function to easily register them.  Most modules
+ * will only have one subsystem, and will only call register_subsystem
+ * on it directly.
+ */
+static struct configfs_subsystem *example_subsys[] = {
+	&childless_subsys.subsys,
+	&simple_children_subsys,
+	&group_children_subsys,
+	NULL,
+};
+
+static int __init configfs_example_init(void)
+{
+	int ret;
+	int i;
+	struct configfs_subsystem *subsys;
+
+	for (i = 0; example_subsys[i]; i++) {
+		subsys = example_subsys[i];
+
+		config_group_init(&subsys->su_group);
+		mutex_init(&subsys->su_mutex);
+		ret = configfs_register_subsystem(subsys);
+		if (ret) {
+			printk(KERN_ERR "Error %d while registering subsystem %s\n",
+			       ret,
+			       subsys->su_group.cg_item.ci_namebuf);
+			goto out_unregister;
+		}
+	}
+
+	return 0;
+
+out_unregister:
+	for (; i >= 0; i--) {
+		configfs_unregister_subsystem(example_subsys[i]);
+	}
+
+	return ret;
+}
+
+static void __exit configfs_example_exit(void)
+{
+	int i;
+
+	for (i = 0; example_subsys[i]; i++) {
+		configfs_unregister_subsystem(example_subsys[i]);
+	}
+}
+
+module_init(configfs_example_init);
+module_exit(configfs_example_exit);
+MODULE_LICENSE("GPL");

Documentation/filesystems/nfs-rdma.txt

@@ -5,7 +5,7 @@
 ################################################################################
 
  Author: NetApp and Open Grid Computing
- Date: April 15, 2008
+ Date: May 29, 2008
 
 Table of Contents
 ~~~~~~~~~~~~~~~~~
@@ -60,16 +60,18 @@ Installation
     The procedures described in this document have been tested with
     distributions from Red Hat's Fedora Project (http://fedora.redhat.com/).
 
-  - Install nfs-utils-1.1.1 or greater on the client
+  - Install nfs-utils-1.1.2 or greater on the client
 
-    An NFS/RDMA mount point can only be obtained by using the mount.nfs
-    command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs
-    you are using, type:
+    An NFS/RDMA mount point can be obtained by using the mount.nfs command in
+    nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils
+    version with support for NFS/RDMA mounts, but for various reasons we
+    recommend using nfs-utils-1.1.2 or greater). To see which version of
+    mount.nfs you are using, type:
 
-    > /sbin/mount.nfs -V
+    $ /sbin/mount.nfs -V
 
-    If the version is less than 1.1.1 or the command does not exist,
-    then you will need to install the latest version of nfs-utils.
+    If the version is less than 1.1.2 or the command does not exist,
+    you should install the latest version of nfs-utils.
 
     Download the latest package from:
 
@@ -77,22 +79,33 @@ Installation
 
     Uncompress the package and follow the installation instructions.
 
-    If you will not be using GSS and NFSv4, the installation process
-    can be simplified by disabling these features when running configure:
+    If you will not need the idmapper and gssd executables (you do not need
+    these to create an NFS/RDMA enabled mount command), the installation
+    process can be simplified by disabling these features when running
+    configure:
 
-    > ./configure --disable-gss --disable-nfsv4
+    $ ./configure --disable-gss --disable-nfsv4
 
-    For more information on this see the package's README and INSTALL files.
+    To build nfs-utils you will need the tcp_wrappers package installed. For
+    more information on this see the package's README and INSTALL files.
 
     After building the nfs-utils package, there will be a mount.nfs binary in
     the utils/mount directory. This binary can be used to initiate NFS v2, v3,
-    or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4.
-    The standard technique is to create a symlink called mount.nfs4 to mount.nfs.
+    or v4 mounts. To initiate a v4 mount, the binary must be called
+    mount.nfs4.  The standard technique is to create a symlink called
+    mount.nfs4 to mount.nfs.
 
-    NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed
+    This mount.nfs binary should be installed at /sbin/mount.nfs as follows:
+
+    $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs
+
+    In this location, mount.nfs will be invoked automatically for NFS mounts
+    by the system mount commmand.
+
+    NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed
     on the NFS client machine. You do not need this specific version of
     nfs-utils on the server. Furthermore, only the mount.nfs command from
-    nfs-utils-1.1.1 is needed on the client.
+    nfs-utils-1.1.2 is needed on the client.
 
   - Install a Linux kernel with NFS/RDMA
 
@@ -156,8 +169,8 @@ Check RDMA and NFS Setup
     this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel
     card:
 
-    > modprobe ib_mthca
-    > modprobe ib_ipoib
+    $ modprobe ib_mthca
+    $ modprobe ib_ipoib
 
     If you are using InfiniBand, make sure there is a Subnet Manager (SM)
     running on the network. If your IB switch has an embedded SM, you can
@@ -166,7 +179,7 @@ Check RDMA and NFS Setup
 
     If an SM is running on your network, you should see the following:
 
-    > cat /sys/class/infiniband/driverX/ports/1/state
+    $ cat /sys/class/infiniband/driverX/ports/1/state
     4: ACTIVE
 
     where driverX is mthca0, ipath5, ehca3, etc.
@@ -174,10 +187,10 @@ Check RDMA and NFS Setup
     To further test the InfiniBand software stack, use IPoIB (this
     assumes you have two IB hosts named host1 and host2):
 
-    host1> ifconfig ib0 a.b.c.x
-    host2> ifconfig ib0 a.b.c.y
-    host1> ping a.b.c.y
-    host2> ping a.b.c.x
+    host1$ ifconfig ib0 a.b.c.x
+    host2$ ifconfig ib0 a.b.c.y
+    host1$ ping a.b.c.y
+    host2$ ping a.b.c.x
 
     For other device types, follow the appropriate procedures.
 
@@ -202,11 +215,11 @@ NFS/RDMA Setup
     /vol0   192.168.0.47(fsid=0,rw,async,insecure,no_root_squash)
     /vol0   192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash)
 
-    The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the
-    cleint's iWARP address(es) for an RNIC.
+    The IP address(es) is(are) the client's IPoIB address for an InfiniBand
+    HCA or the cleint's iWARP address(es) for an RNIC.
 
-    NOTE: The "insecure" option must be used because the NFS/RDMA client does not
-    use a reserved port.
+    NOTE: The "insecure" option must be used because the NFS/RDMA client does
+    not use a reserved port.
 
  Each time a machine boots:
 
@@ -214,43 +227,45 @@ NFS/RDMA Setup
 
     For InfiniBand using a Mellanox adapter:
 
-    > modprobe ib_mthca
-    > modprobe ib_ipoib
-    > ifconfig ib0 a.b.c.d
+    $ modprobe ib_mthca
+    $ modprobe ib_ipoib
+    $ ifconfig ib0 a.b.c.d
 
     NOTE: use unique addresses for the client and server
 
   - Start the NFS server
 
-    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
-    load the RDMA transport module:
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA transport module:
 
-    > modprobe svcrdma
+    $ modprobe svcrdma
 
-    Regardless of how the server was built (module or built-in), start the server:
+    Regardless of how the server was built (module or built-in), start the
+    server:
 
-    > /etc/init.d/nfs start
+    $ /etc/init.d/nfs start
 
     or
 
-    > service nfs start
+    $ service nfs start
 
     Instruct the server to listen on the RDMA transport:
 
-    > echo rdma 2050 > /proc/fs/nfsd/portlist
+    $ echo rdma 2050 > /proc/fs/nfsd/portlist
 
   - On the client system
 
-    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
-    load the RDMA client module:
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA client module:
 
-    > modprobe xprtrdma.ko
+    $ modprobe xprtrdma.ko
 
-    Regardless of how the client was built (module or built-in), issue the mount.nfs command:
+    Regardless of how the client was built (module or built-in), use this
+    command to mount the NFS/RDMA server:
 
-    > /path/to/your/mount.nfs <IPoIB-server-name-or-address>:/<export> /mnt -i -o rdma,port=2050
+    $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt
 
-    To verify that the mount is using RDMA, run "cat /proc/mounts" and check the
-    "proto" field for the given mount.
+    To verify that the mount is using RDMA, run "cat /proc/mounts" and check
+    the "proto" field for the given mount.
 
   Congratulations! You're using NFS/RDMA!

Documentation/filesystems/omfs.txt

@@ -0,0 +1,106 @@
+Optimized MPEG Filesystem (OMFS)
+
+Overview
+========
+
+OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR
+and Rio Karma MP3 player.  The filesystem is extent-based, utilizing
+block sizes from 2k to 8k, with hash-based directories.  This
+filesystem driver may be used to read and write disks from these
+devices.
+
+Note, it is not recommended that this FS be used in place of a general
+filesystem for your own streaming media device.  Native Linux filesystems
+will likely perform better.
+
+More information is available at:
+
+    http://linux-karma.sf.net/
+
+Various utilities, including mkomfs and omfsck, are included with
+omfsprogs, available at:
+
+    http://bobcopeland.com/karma/
+
+Instructions are included in its README.
+
+Options
+=======
+
+OMFS supports the following mount-time options:
+
+    uid=n        - make all files owned by specified user
+    gid=n        - make all files owned by specified group
+    umask=xxx    - set permission umask to xxx
+    fmask=xxx    - set umask to xxx for files
+    dmask=xxx    - set umask to xxx for directories
+
+Disk format
+===========
+
+OMFS discriminates between "sysblocks" and normal data blocks.  The sysblock
+group consists of super block information, file metadata, directory structures,
+and extents.  Each sysblock has a header containing CRCs of the entire
+sysblock, and may be mirrored in successive blocks on the disk.  A sysblock may
+have a smaller size than a data block, but since they are both addressed by the
+same 64-bit block number, any remaining space in the smaller sysblock is
+unused.
+
+Sysblock header information:
+
+struct omfs_header {
+        __be64 h_self;                  /* FS block where this is located */
+        __be32 h_body_size;             /* size of useful data after header */
+        __be16 h_crc;                   /* crc-ccitt of body_size bytes */
+        char h_fill1[2];
+        u8 h_version;                   /* version, always 1 */
+        char h_type;                    /* OMFS_INODE_X */
+        u8 h_magic;                     /* OMFS_IMAGIC */
+        u8 h_check_xor;                 /* XOR of header bytes before this */
+        __be32 h_fill2;
+};
+
+Files and directories are both represented by omfs_inode:
+
+struct omfs_inode {
+        struct omfs_header i_head;      /* header */
+        __be64 i_parent;                /* parent containing this inode */
+        __be64 i_sibling;               /* next inode in hash bucket */
+        __be64 i_ctime;                 /* ctime, in milliseconds */
+        char i_fill1[35];
+        char i_type;                    /* OMFS_[DIR,FILE] */
+        __be32 i_fill2;
+        char i_fill3[64];
+        char i_name[OMFS_NAMELEN];      /* filename */
+        __be64 i_size;                  /* size of file, in bytes */
+};
+
+Directories in OMFS are implemented as a large hash table.  Filenames are
+hashed then prepended into the bucket list beginning at OMFS_DIR_START.
+Lookup requires hashing the filename, then seeking across i_sibling pointers
+until a match is found on i_name.  Empty buckets are represented by block
+pointers with all-1s (~0).
+
+A file is an omfs_inode structure followed by an extent table beginning at
+OMFS_EXTENT_START:
+
+struct omfs_extent_entry {
+        __be64 e_cluster;               /* start location of a set of blocks */
+        __be64 e_blocks;                /* number of blocks after e_cluster */
+};
+
+struct omfs_extent {
+        __be64 e_next;                  /* next extent table location */
+        __be32 e_extent_count;          /* total # extents in this table */
+        __be32 e_fill;
+        struct omfs_extent_entry e_entry;       /* start of extent entries */
+};
+
+Each extent holds the block offset followed by number of blocks allocated to
+the extent.  The final extent in each table is a terminator with e_cluster
+being ~0 and e_blocks being ones'-complement of the total number of blocks
+in the table.
+
+If this table overflows, a continuation inode is written and pointed to by
+e_next.  These have a header but lack the rest of the inode structure.
+

Documentation/filesystems/proc.txt

@@ -296,6 +296,7 @@ Table 1-4: Kernel info in /proc
  uptime      System uptime                                     
  version     Kernel version                                    
  video	     bttv info of video resources			(2.4)
+ vmallocinfo Show vmalloced areas
 ..............................................................................
 
 You can,  for  example,  check  which interrupts are currently in use and what
@@ -557,6 +558,49 @@ VmallocTotal: total size of vmalloc memory area
  VmallocUsed: amount of vmalloc area which is used
 VmallocChunk: largest contigious block of vmalloc area which is free
 
+..............................................................................
+
+vmallocinfo:
+
+Provides information about vmalloced/vmaped areas. One line per area,
+containing the virtual address range of the area, size in bytes,
+caller information of the creator, and optional information depending
+on the kind of area :
+
+ pages=nr    number of pages
+ phys=addr   if a physical address was specified
+ ioremap     I/O mapping (ioremap() and friends)
+ vmalloc     vmalloc() area
+ vmap        vmap()ed pages
+ user        VM_USERMAP area
+ vpages      buffer for pages pointers was vmalloced (huge area)
+ N<node>=nr  (Only on NUMA kernels)
+             Number of pages allocated on memory node <node>
+
+> cat /proc/vmallocinfo
+0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
+  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
+0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
+  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
+0xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
+  phys=7fee8000 ioremap
+0xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
+  phys=7fee7000 ioremap
+0xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
+0xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
+  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
+0xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
+  pages=2 vmalloc N1=2
+0xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
+  /0x130 [x_tables] pages=4 vmalloc N0=4
+0xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
+   pages=14 vmalloc N2=14
+0xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
+   pages=4 vmalloc N1=4
+0xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
+   pages=2 vmalloc N1=2
+0xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
+   pages=10 vmalloc N0=10
 
 1.3 IDE devices in /proc/ide
 ----------------------------
@@ -887,7 +931,7 @@ group_prealloc  max_to_scan  mb_groups  mb_history  min_to_scan  order2_req
 stats  stream_req
 
 mb_groups:
-This file gives the details of mutiblock allocator buddy cache of free blocks
+This file gives the details of multiblock allocator buddy cache of free blocks
 
 mb_history:
 Multiblock allocation history.
@@ -1430,7 +1474,7 @@ used because pages_free(1355) is smaller than watermark + protection[2]
 normal page requirement. If requirement is DMA zone(index=0), protection[0]
 (=0) is used.
 
-zone[i]'s protection[j] is calculated by following exprssion.
+zone[i]'s protection[j] is calculated by following expression.
 
 (i < j):
   zone[i]->protection[j]

Documentation/filesystems/relay.txt

@@ -294,6 +294,16 @@ user-defined data with a channel, and is immediately available
 (including in create_buf_file()) via chan->private_data or
 buf->chan->private_data.
 
+Buffer-only channels
+--------------------
+
+These channels have no files associated and can be created with
+relay_open(NULL, NULL, ...). Such channels are useful in scenarios such
+as when doing early tracing in the kernel, before the VFS is up. In these
+cases, one may open a buffer-only channel and then call
+relay_late_setup_files() when the kernel is ready to handle files,
+to expose the buffered data to the userspace.
+
 Channel 'modes'
 ---------------
 

Documentation/filesystems/sysfs.txt

@@ -248,6 +248,7 @@ The top level sysfs directory looks like:
 block/
 bus/
 class/
+dev/
 devices/
 firmware/
 net/
@@ -274,6 +275,11 @@ fs/ contains a directory for some filesystems.  Currently each
 filesystem wanting to export attributes must create its own hierarchy
 below fs/ (see ./fuse.txt for an example).
 
+dev/ contains two directories char/ and block/. Inside these two
+directories there are symlinks named <major>:<minor>.  These symlinks
+point to the sysfs directory for the given device.  /sys/dev provides a
+quick way to lookup the sysfs interface for a device from the result of
+a stat(2) operation.
 
 More information can driver-model specific features can be found in
 Documentation/driver-model/. 

Documentation/filesystems/ubifs.txt

@@ -0,0 +1,164 @@
+Introduction
+=============
+
+UBIFS file-system stands for UBI File System. UBI stands for "Unsorted
+Block Images". UBIFS is a flash file system, which means it is designed
+to work with flash devices. It is important to understand, that UBIFS
+is completely different to any traditional file-system in Linux, like
+Ext2, XFS, JFS, etc. UBIFS represents a separate class of file-systems
+which work with MTD devices, not block devices. The other Linux
+file-system of this class is JFFS2.
+
+To make it more clear, here is a small comparison of MTD devices and
+block devices.
+
+1 MTD devices represent flash devices and they consist of eraseblocks of
+  rather large size, typically about 128KiB. Block devices consist of
+  small blocks, typically 512 bytes.
+2 MTD devices support 3 main operations - read from some offset within an
+  eraseblock, write to some offset within an eraseblock, and erase a whole
+  eraseblock. Block  devices support 2 main operations - read a whole
+  block and write a whole block.
+3 The whole eraseblock has to be erased before it becomes possible to
+  re-write its contents. Blocks may be just re-written.
+4 Eraseblocks become worn out after some number of erase cycles -
+  typically 100K-1G for SLC NAND and NOR flashes, and 1K-10K for MLC
+  NAND flashes. Blocks do not have the wear-out property.
+5 Eraseblocks may become bad (only on NAND flashes) and software should
+  deal with this. Blocks on hard drives typically do not become bad,
+  because hardware has mechanisms to substitute bad blocks, at least in
+  modern LBA disks.
+
+It should be quite obvious why UBIFS is very different to traditional
+file-systems.
+
+UBIFS works on top of UBI. UBI is a separate software layer which may be
+found in drivers/mtd/ubi. UBI is basically a volume management and
+wear-leveling layer. It provides so called UBI volumes which is a higher
+level abstraction than a MTD device. The programming model of UBI devices
+is very similar to MTD devices - they still consist of large eraseblocks,
+they have read/write/erase operations, but UBI devices are devoid of
+limitations like wear and bad blocks (items 4 and 5 in the above list).
+
+In a sense, UBIFS is a next generation of JFFS2 file-system, but it is
+very different and incompatible to JFFS2. The following are the main
+differences.
+
+* JFFS2 works on top of MTD devices, UBIFS depends on UBI and works on
+  top of UBI volumes.
+* JFFS2 does not have on-media index and has to build it while mounting,
+  which requires full media scan. UBIFS maintains the FS indexing
+  information on the flash media and does not require full media scan,
+  so it mounts many times faster than JFFS2.
+* JFFS2 is a write-through file-system, while UBIFS supports write-back,
+  which makes UBIFS much faster on writes.
+
+Similarly to JFFS2, UBIFS supports on-the-flight compression which makes
+it possible to fit quite a lot of data to the flash.
+
+Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts.
+It does not need stuff like ckfs.ext2. UBIFS automatically replays its
+journal and recovers from crashes, ensuring that the on-flash data
+structures are consistent.
+
+UBIFS scales logarithmically (most of the data structures it uses are
+trees), so the mount time and memory consumption do not linearly depend
+on the flash size, like in case of JFFS2. This is because UBIFS
+maintains the FS index on the flash media. However, UBIFS depends on
+UBI, which scales linearly. So overall UBI/UBIFS stack scales linearly.
+Nevertheless, UBI/UBIFS scales considerably better than JFFS2.
+
+The authors of UBIFS believe, that it is possible to develop UBI2 which
+would scale logarithmically as well. UBI2 would support the same API as UBI,
+but it would be binary incompatible to UBI. So UBIFS would not need to be
+changed to use UBI2
+
+
+Mount options
+=============
+
+(*) == default.
+
+norm_unmount (*)	commit on unmount; the journal is committed
+			when the file-system is unmounted so that the
+			next mount does not have to replay the journal
+			and it becomes very fast;
+fast_unmount		do not commit on unmount; this option makes
+			unmount faster, but the next mount slower
+			because of the need to replay the journal.
+
+
+Quick usage instructions
+========================
+
+The UBI volume to mount is specified using "ubiX_Y" or "ubiX:NAME" syntax,
+where "X" is UBI device number, "Y" is UBI volume number, and "NAME" is
+UBI volume name.
+
+Mount volume 0 on UBI device 0 to /mnt/ubifs:
+$ mount -t ubifs ubi0_0 /mnt/ubifs
+
+Mount "rootfs" volume of UBI device 0 to /mnt/ubifs ("rootfs" is volume
+name):
+$ mount -t ubifs ubi0:rootfs /mnt/ubifs
+
+The following is an example of the kernel boot arguments to attach mtd0
+to UBI and mount volume "rootfs":
+ubi.mtd=0 root=ubi0:rootfs rootfstype=ubifs
+
+
+Module Parameters for Debugging
+===============================
+
+When UBIFS has been compiled with debugging enabled, there are 3 module
+parameters that are available to control aspects of testing and debugging.
+The parameters are unsigned integers where each bit controls an option.
+The parameters are:
+
+debug_msgs	Selects which debug messages to display, as follows:
+
+		Message Type				Flag value
+
+		General messages			1
+		Journal messages			2
+		Mount messages				4
+		Commit messages				8
+		LEB search messages			16
+		Budgeting messages			32
+		Garbage collection messages		64
+		Tree Node Cache (TNC) messages		128
+		LEB properties (lprops) messages	256
+		Input/output messages			512
+		Log messages				1024
+		Scan messages				2048
+		Recovery messages			4096
+
+debug_chks	Selects extra checks that UBIFS can do while running:
+
+		Check					Flag value
+
+		General checks				1
+		Check Tree Node Cache (TNC)		2
+		Check indexing tree size		4
+		Check orphan area			8
+		Check old indexing tree			16
+		Check LEB properties (lprops)		32
+		Check leaf nodes and inodes		64
+
+debug_tsts	Selects a mode of testing, as follows:
+
+		Test mode				Flag value
+
+		Force in-the-gaps method		2
+		Failure mode for recovery testing	4
+
+For example, set debug_msgs to 5 to display General messages and Mount
+messages.
+
+
+References
+==========
+
+UBIFS documentation and FAQ/HOWTO at the MTD web site:
+http://www.linux-mtd.infradead.org/doc/ubifs.html
+http://www.linux-mtd.infradead.org/faq/ubifs.html

Documentation/filesystems/vfat.txt

@@ -96,6 +96,14 @@ shortname=lower|win95|winnt|mixed
 			emulate the Windows 95 rule for create.
 		 Default setting is `lower'.
 
+tz=UTC        -- Interpret timestamps as UTC rather than local time.
+                 This option disables the conversion of timestamps
+                 between local time (as used by Windows on FAT) and UTC
+                 (which Linux uses internally).  This is particuluarly
+                 useful when mounting devices (like digital cameras)
+                 that are set to UTC in order to avoid the pitfalls of
+                 local time.
+
 <bool>: 0,1,yes,no,true,false
 
 TODO

Documentation/filesystems/vfs.txt

@@ -143,7 +143,7 @@ struct file_system_type {
 
 The get_sb() method has the following arguments:
 
-  struct file_system_type *fs_type: decribes the filesystem, partly initialized
+  struct file_system_type *fs_type: describes the filesystem, partly initialized
   	by the specific filesystem code
 
   int flags: mount flags
@@ -895,9 +895,9 @@ struct dentry_operations {
 	iput() yourself
 
   d_dname: called when the pathname of a dentry should be generated.
-	Usefull for some pseudo filesystems (sockfs, pipefs, ...) to delay
+	Useful for some pseudo filesystems (sockfs, pipefs, ...) to delay
 	pathname generation. (Instead of doing it when dentry is created,
-	its done only when the path is needed.). Real filesystems probably
+	it's done only when the path is needed.). Real filesystems probably
 	dont want to use it, because their dentries are present in global
 	dcache hash, so their hash should be an invariant. As no lock is
 	held, d_dname() should not try to modify the dentry itself, unless

Documentation/ftrace.txt

@@ -4,9 +4,11 @@
 Copyright 2008 Red Hat Inc.
    Author:   Steven Rostedt <srostedt@redhat.com>
   License:   The GNU Free Documentation License, Version 1.2
-Reviewers:   Elias Oltmanns and Randy Dunlap
+               (dual licensed under the GPL v2)
+Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
+	     John Kacur, and David Teigland.
 
-Writen for: 2.6.26-rc8 linux-2.6-tip.git tip/tracing/ftrace branch
+Written for: 2.6.27-rc1
 
 Introduction
 ------------
@@ -18,10 +20,11 @@ issues that take place outside of user-space.
 
 Although ftrace is the function tracer, it also includes an
 infrastructure that allows for other types of tracing. Some of the
-tracers that are currently in ftrace is a tracer to trace
+tracers that are currently in ftrace include a tracer to trace
 context switches, the time it takes for a high priority task to
 run after it was woken up, the time interrupts are disabled, and
-more.
+more (ftrace allows for tracer plugins, which means that the list of
+tracers can always grow).
 
 
 The File System
@@ -35,6 +38,8 @@ To mount the debugfs system:
   # mkdir /debug
   # mount -t debugfs nodev /debug
 
+(Note: it is more common to mount at /sys/kernel/debug, but for simplicity
+ this document will use /debug)
 
 That's it! (assuming that you have ftrace configured into your kernel)
 
@@ -50,20 +55,19 @@ of ftrace. Here is a list of some of the key files:
 
   available_tracers : This holds the different types of tracers that
 		have been compiled into the kernel. The tracers
-		listed here can be configured by echoing in their
-		name into current_tracer.
+		listed here can be configured by echoing their name
+		into current_tracer.
 
   tracing_enabled : This sets or displays whether the current_tracer
 		is activated and tracing or not. Echo 0 into this
-		file to disable the tracer or 1 (or non-zero) to
-		enable it.
+		file to disable the tracer or 1 to enable it.
 
   trace : This file holds the output of the trace in a human readable
-		format.
+		format (described below).
 
   latency_trace : This file shows the same trace but the information
 		is organized more to display possible latencies
-		in the system.
+		in the system (described below).
 
   trace_pipe : The output is the same as the "trace" file but this
 		file is meant to be streamed with live tracing.
@@ -75,7 +79,7 @@ of ftrace. Here is a list of some of the key files:
 		file, it is consumed, and will not be read
 		again with a sequential read. The "trace" and
 		"latency_trace" files are static, and if the
-		tracer isn't adding more data, they will display
+		tracer is not adding more data, they will display
 		the same information every time they are read.
 
   iter_ctrl : This file lets the user control the amount of data
@@ -92,10 +96,10 @@ of ftrace. Here is a list of some of the key files:
 
   trace_entries : This sets or displays the number of trace
 		entries each CPU buffer can hold. The tracer buffers
-		are the same size for each CPU, so care must be
-		taken when modifying the trace_entries. The trace
-		buffers are allocated in pages (blocks of memory that
-		the kernel uses for allocation, usually 4 KB in size).
+		are the same size for each CPU. The displayed number
+		is the size of the CPU buffer and not total size. The
+		trace buffers are allocated in pages (blocks of memory
+		that the kernel uses for allocation, usually 4 KB in size).
 		Since each entry is smaller than a page, if the last
 		allocated page has room for more entries than were
 		requested, the rest of the page is used to allocate
@@ -112,20 +116,19 @@ of ftrace. Here is a list of some of the key files:
 		on specified CPUS. The format is a hex string
 		representing the CPUS.
 
-  set_ftrace_filter : When dynamic ftrace is configured in, the
-		code is dynamically modified to disable calling
-		of the function profiler (mcount). This lets
-		tracing be configured in with practically no overhead
-		in performance.  This also has a side effect of
-		enabling or disabling specific functions to be
-		traced.  Echoing in names of functions into this
-		file will limit the trace to only these functions.
-
-  set_ftrace_notrace: This has the opposite effect that
-		set_ftrace_filter has. Any function that is added
-		here will not be traced. If a function exists
-		in both set_ftrace_filter and set_ftrace_notrace,
-		the function will _not_ be traced.
+  set_ftrace_filter : When dynamic ftrace is configured in (see the
+		section below "dynamic ftrace"), the code is dynamically
+		modified (code text rewrite) to disable calling of the
+		function profiler (mcount). This lets tracing be configured
+		in with practically no overhead in performance.  This also
+		has a side effect of enabling or disabling specific functions
+		to be traced. Echoing names of functions into this file
+		will limit the trace to only those functions.
+
+  set_ftrace_notrace: This has an effect opposite to that of
+		set_ftrace_filter. Any function that is added here will not
+		be traced. If a function exists in both set_ftrace_filter
+		and set_ftrace_notrace,	the function will _not_ be traced.
 
   available_filter_functions : When a function is encountered the first
 		time by the dynamic tracer, it is recorded and
@@ -133,32 +136,31 @@ of ftrace. Here is a list of some of the key files:
 		lists the functions that have been recorded
 		by the dynamic tracer and these functions can
 		be used to set the ftrace filter by the above
-		"set_ftrace_filter" file.
+		"set_ftrace_filter" file. (See the section "dynamic ftrace"
+		below for more details).
 
 
 The Tracers
 -----------
 
-Here are the list of current tracers that can be configured.
+Here is the list of current tracers that may be configured.
 
   ftrace - function tracer that uses mcount to trace all functions.
-		It is possible to filter out which functions that are
-		to be traced when dynamic ftrace is configured in.
 
   sched_switch - traces the context switches between tasks.
 
-  irqsoff - traces the areas that disable interrupts and saves off
+  irqsoff - traces the areas that disable interrupts and saves
   		the trace with the longest max latency.
 		See tracing_max_latency.  When a new max is recorded,
 		it replaces the old trace. It is best to view this
-		trace with the latency_trace file.
+		trace via the latency_trace file.
 
-  preemptoff - Similar to irqsoff but traces and records the time
-		preemption is disabled.
+  preemptoff - Similar to irqsoff but traces and records the amount of
+		time for which preemption is disabled.
 
   preemptirqsoff - Similar to irqsoff and preemptoff, but traces and
-		 records the largest time irqs and/or preemption is
-		 disabled.
+		 records the largest time for which irqs and/or preemption
+		 is disabled.
 
   wakeup - Traces and records the max latency that it takes for
 		the highest priority task to get scheduled after
@@ -171,13 +173,13 @@ Here are the list of current tracers that can be configured.
 Examples of using the tracer
 ----------------------------
 
-Here are typical examples of using the tracers with only controlling
-them with the debugfs interface (without using any user-land utilities).
+Here are typical examples of using the tracers when controlling them only
+with the debugfs interface (without using any user-land utilities).
 
 Output format:
 --------------
 
-Here's an example of the output format of the file "trace"
+Here is an example of the output format of the file "trace"
 
                              --------
 # tracer: ftrace
@@ -189,14 +191,15 @@ Here's an example of the output format of the file "trace"
             bash-4251  [01] 10152.583855: _atomic_dec_and_lock <-dput
                              --------
 
-A header is printed with the trace that is represented. In this case
-the tracer is "ftrace". Then a header showing the format. Task name
-"bash", the task PID "4251", the CPU that it was running on
+A header is printed with the tracer name that is represented by the trace.
+In this case the tracer is "ftrace". Then a header showing the format. Task
+name "bash", the task PID "4251", the CPU that it was running on
 "01", the timestamp in <secs>.<usecs> format, the function name that was
 traced "path_put" and the parent function that called this function
-"path_walk".
+"path_walk". The timestamp is the time at which the function was
+entered.
 
-The sched_switch tracer also includes tracing of task wake ups and
+The sched_switch tracer also includes tracing of task wakeups and
 context switches.
 
      ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +  2916:115:S
@@ -206,7 +209,7 @@ context switches.
      kondemand/1-2916  [01]  1453.070013:   2916:115:S ==>     7:115:R
      ksoftirqd/1-7     [01]  1453.070013:      7:115:S ==>     0:140:R
 
-Wake ups are represented by a "+" and the context switches show
+Wake ups are represented by a "+" and the context switches are shown as
 "==>".  The format is:
 
  Context switches:
@@ -221,7 +224,7 @@ Wake ups are represented by a "+" and the context switches show
 
   <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
 
-The prio is the internal kernel priority, which is inverse to the
+The prio is the internal kernel priority, which is the inverse of the
 priority that is usually displayed by user-space tools. Zero represents
 the highest priority (99). Prio 100 starts the "nice" priorities with
 100 being equal to nice -20 and 139 being nice 19. The prio "140" is
@@ -232,7 +235,7 @@ Latency trace format
 --------------------
 
 For traces that display latency times, the latency_trace file gives
-a bit more information to see why a latency happened. Here's a typical
+somewhat more information to see why a latency happened. Here is a typical
 trace.
 
 # tracer: irqsoff
@@ -260,21 +263,20 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8
   <idle>-0     0d.s1   98us : trace_hardirqs_on (do_softirq)
 
 
-vim:ft=help
-
 
-This shows that the current tracer is "irqsoff" tracing the time
-interrupts are disabled. It gives the trace version and the kernel
-this was executed on (2.6.26-rc8). Then it displays the max latency
-in microsecs (97 us). The number of trace entries displayed
-by the total number recorded (both are three: #3/3). The type of
+This shows that the current tracer is "irqsoff" tracing the time for which
+interrupts were disabled. It gives the trace version and the version
+of the kernel upon which this was executed on (2.6.26-rc8). Then it displays
+the max latency in microsecs (97 us). The number of trace entries displayed
+and the total number recorded (both are three: #3/3). The type of
 preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero
-and reserved for later use. #P is the number of online CPUS (#P:2).
+and are reserved for later use. #P is the number of online CPUS (#P:2).
 
-The task is the process that was running when the latency happened.
+The task is the process that was running when the latency occurred.
 (swapper pid: 0).
 
-The start and stop that caused the latencies:
+The start and stop (the functions in which the interrupts were disabled and
+enabled respectively) that caused the latencies:
 
   apic_timer_interrupt is where the interrupts were disabled.
   do_softirq is where they were enabled again.
@@ -286,14 +288,14 @@ explains which is which.
 
   pid: The PID of that process.
 
-  CPU#: The CPU that the process was running on.
+  CPU#: The CPU which the process was running on.
 
   irqs-off: 'd' interrupts are disabled. '.' otherwise.
 
   need-resched: 'N' task need_resched is set, '.' otherwise.
 
   hardirq/softirq:
-	'H' - hard irq happened inside a softirq.
+	'H' - hard irq occurred inside a softirq.
 	'h' - hard irq is running
 	's' - soft irq is running
 	'.' - normal context.
@@ -303,7 +305,7 @@ explains which is which.
 The above is mostly meaningful for kernel developers.
 
   time: This differs from the trace file output. The trace file output
-	included an absolute timestamp. The timestamp used by the
+	includes an absolute timestamp. The timestamp used by the
 	latency_trace file is relative to the start of the trace.
 
   delay: This is just to help catch your eye a bit better. And
@@ -385,7 +387,7 @@ Here are the available options:
 sched_switch
 ------------
 
-This tracer simply records schedule switches. Here's an example
+This tracer simply records schedule switches. Here is an example
 of how to use it.
 
  # echo sched_switch > /debug/tracing/current_tracer
@@ -421,8 +423,8 @@ the name of the trace and points to the options. The "FUNCTION"
 is a misnomer since here it represents the wake ups and context
 switches.
 
-The sched_switch only lists the wake ups (represented with '+')
-and context switches ('==>') with the previous task or current
+The sched_switch file only lists the wake ups (represented with '+')
+and context switches ('==>') with the previous task or current task
 first followed by the next task or task waking up. The format for both
 of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO
 is the inverse of the actual priority with zero (0) being the highest
@@ -437,7 +439,8 @@ The task states are:
 
  R - running : wants to run, may not actually be running
  S - sleep   : process is waiting to be woken up (handles signals)
- D - deep sleep : process must be woken up (ignores signals)
+ D - disk sleep (uninterruptible sleep) : process must be woken up
+					(ignores signals)
  T - stopped : process suspended
  t - traced  : process is being traced (with something like gdb)
  Z - zombie  : process waiting to be cleaned up
@@ -447,8 +450,8 @@ The task states are:
 ftrace_enabled
 --------------
 
-The following tracers give different output depending on whether
-or not the sysctl ftrace_enabled is set. To set ftrace_enabled,
+The following tracers (listed below) give different output depending
+on whether or not the sysctl ftrace_enabled is set. To set ftrace_enabled,
 one can either use the sysctl function or set it via the proc
 file system interface.
 
@@ -475,13 +478,12 @@ interrupt from triggering or the mouse interrupt from letting the
 kernel know of a new mouse event. The result is a latency with the
 reaction time.
 
-The irqsoff tracer tracks the time interrupts are disabled to the time
-they are re-enabled. When a new maximum latency is hit, it saves off
-the trace so that it may be retrieved at a later time. Every time a
-new maximum in reached, the old saved trace is discarded and the new
-trace is saved.
+The irqsoff tracer tracks the time for which interrupts are disabled.
+When a new maximum latency is hit, the tracer saves the trace leading up
+to that latency point so that every time a new maximum is reached, the old
+saved trace is discarded and the new trace is saved.
 
-To reset the maximum, echo 0 into tracing_max_latency. Here's an
+To reset the maximum, echo 0 into tracing_max_latency. Here is an
 example:
 
  # echo irqsoff > /debug/tracing/current_tracer
@@ -493,14 +495,14 @@ example:
  # cat /debug/tracing/latency_trace
 # tracer: irqsoff
 #
-irqsoff latency trace v1.1.5 on 2.6.26-rc8
+irqsoff latency trace v1.1.5 on 2.6.26
 --------------------------------------------------------------------
- latency: 6 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+ latency: 12 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
     -----------------
-    | task: bash-4269 (uid:0 nice:0 policy:0 rt_prio:0)
+    | task: bash-3730 (uid:0 nice:0 policy:0 rt_prio:0)
     -----------------
- => started at: copy_page_range
- => ended at:   copy_page_range
+ => started at: sys_setpgid
+ => ended at:   sys_setpgid
 
 #                _------=> CPU#
 #               / _-----=> irqs-off
@@ -511,21 +513,19 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8
 #              |||||     delay
 #  cmd     pid ||||| time  |   caller
 #     \   /    |||||   \   |   /
-    bash-4269  1...1    0us+: _spin_lock (copy_page_range)
-    bash-4269  1...1    7us : _spin_unlock (copy_page_range)
-    bash-4269  1...2    7us : trace_preempt_on (copy_page_range)
-
+    bash-3730  1d...    0us : _write_lock_irq (sys_setpgid)
+    bash-3730  1d..1    1us+: _write_unlock_irq (sys_setpgid)
+    bash-3730  1d..2   14us : trace_hardirqs_on (sys_setpgid)
 
-vim:ft=help
 
-Here we see that that we had a latency of 6 microsecs (which is
-very good). The spin_lock in copy_page_range disabled interrupts.
-The difference between the 6 and the displayed timestamp 7us is
-because the clock must have incremented between the time of recording
-the max latency and recording the function that had that latency.
+Here we see that that we had a latency of 12 microsecs (which is
+very good). The _write_lock_irq in sys_setpgid disabled interrupts.
+The difference between the 12 and the displayed timestamp 14us occurred
+because the clock was incremented between the time of recording the max
+latency and the time of recording the function that had that latency.
 
-Note the above had ftrace_enabled not set. If we set the ftrace_enabled,
-we get a much larger output:
+Note the above example had ftrace_enabled not set. If we set the
+ftrace_enabled, we get a much larger output:
 
 # tracer: irqsoff
 #
@@ -571,12 +571,10 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8
       ls-4339  0d..2   51us : trace_hardirqs_on (__alloc_pages_internal)
 
 
-vim:ft=help
-
 
 Here we traced a 50 microsecond latency. But we also see all the
 functions that were called during that time. Note that by enabling
-function tracing, we endure an added overhead. This overhead may
+function tracing, we incur an added overhead. This overhead may
 extend the latency times. But nevertheless, this trace has provided
 some very helpful debugging information.
 
@@ -590,8 +588,9 @@ for preemption to be enabled again before it can preempt a lower
 priority task.
 
 The preemptoff tracer traces the places that disable preemption.
-Like the irqsoff, it records the maximum latency that preemption
-was disabled. The control of preemptoff is much like the irqsoff.
+Like the irqsoff tracer, it records the maximum latency for which preemption
+was disabled. The control of preemptoff tracer is much like the irqsoff
+tracer.
 
  # echo preemptoff > /debug/tracing/current_tracer
  # echo 0 > /debug/tracing/tracing_max_latency
@@ -625,8 +624,6 @@ preemptoff latency trace v1.1.5 on 2.6.26-rc8
     sshd-4261  0d.s1   30us : trace_preempt_on (__do_softirq)
 
 
-vim:ft=help
-
 This has some more changes. Preemption was disabled when an interrupt
 came in (notice the 'h'), and was enabled while doing a softirq.
 (notice the 's'). But we also see that interrupts have been disabled
@@ -694,16 +691,16 @@ The above is an example of the preemptoff trace with ftrace_enabled
 set. Here we see that interrupts were disabled the entire time.
 The irq_enter code lets us know that we entered an interrupt 'h'.
 Before that, the functions being traced still show that it is not
-in an interrupt, but we can see by the functions themselves that
+in an interrupt, but we can see from the functions themselves that
 this is not the case.
 
-Notice that the __do_softirq when called doesn't have a preempt_count.
-It may seem that we missed a preempt enabled. What really happened
-is that the preempt count is held on the threads stack and we
+Notice that __do_softirq when called does not have a preempt_count.
+It may seem that we missed a preempt enabling. What really happened
+is that the preempt count is held on the thread's stack and we
 switched to the softirq stack (4K stacks in effect). The code
 does not copy the preempt count, but because interrupts are disabled,
-we don't need to worry about it. Having a tracer like this is good
-to let people know what really happens inside the kernel.
+we do not need to worry about it. Having a tracer like this is good
+for letting people know what really happens inside the kernel.
 
 
 preemptirqsoff
@@ -713,7 +710,7 @@ Knowing the locations that have interrupts disabled or preemption
 disabled for the longest times is helpful. But sometimes we would
 like to know when either preemption and/or interrupts are disabled.
 
-The following code:
+Consider the following code:
 
     local_irq_disable();
     call_function_with_irqs_off();
@@ -769,12 +766,10 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
       ls-4860  0d.s1  294us : trace_preempt_on (__do_softirq)
 
 
-vim:ft=help
-
 
 The trace_hardirqs_off_thunk is called from assembly on x86 when
 interrupts are disabled in the assembly code. Without the function
-tracing, we don't know if interrupts were enabled within the preemption
+tracing, we do not know if interrupts were enabled within the preemption
 points. We do see that it started with preemption enabled.
 
 Here is a trace with ftrace_enabled set:
@@ -865,19 +860,19 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
 
 This is a very interesting trace. It started with the preemption of
 the ls task. We see that the task had the "need_resched" bit set
-with the 'N' in the trace.  Interrupts are disabled in the spin_lock
-and the trace started. We see that a schedule took place to run
+via the 'N' in the trace.  Interrupts were disabled before the spin_lock
+at the beginning of the trace. We see that a schedule took place to run
 sshd.  When the interrupts were enabled, we took an interrupt.
 On return from the interrupt handler, the softirq ran. We took another
-interrupt while running the softirq as we see with the capital 'H'.
+interrupt while running the softirq as we see from the capital 'H'.
 
 
 wakeup
 ------
 
-In Real-Time environment it is very important to know the wakeup
-time it takes for the highest priority task that wakes up to the
-time it executes. This is also known as "schedule latency".
+In a Real-Time environment it is very important to know the wakeup
+time it takes for the highest priority task that is woken up to the
+time that it executes. This is also known as "schedule latency".
 I stress the point that this is about RT tasks. It is also important
 to know the scheduling latency of non-RT tasks, but the average
 schedule latency is better for non-RT tasks. Tools like
@@ -926,8 +921,6 @@ wakeup latency trace v1.1.5 on 2.6.26-rc8
   <idle>-0     1d..4    4us : schedule (cpu_idle)
 
 
-vim:ft=help
-
 
 Running this on an idle system, we see that it only took 4 microseconds
 to perform the task switch.  Note, since the trace marker in the
@@ -996,15 +989,15 @@ ksoftirq-7     1d..6   49us : sub_preempt_count (_spin_unlock)
 ksoftirq-7     1d..4   50us : schedule (__cond_resched)
 
 The interrupt went off while running ksoftirqd. This task runs at
-SCHED_OTHER. Why didn't we see the 'N' set early? This may be
+SCHED_OTHER. Why did not we see the 'N' set early? This may be
 a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K stacks
-configured, the interrupt and softirq runs with their own stack.
+configured, the interrupt and softirq run with their own stack.
 Some information is held on the top of the task's stack (need_resched
 and preempt_count are both stored there). The setting of the NEED_RESCHED
 bit is done directly to the task's stack, but the reading of the
 NEED_RESCHED is done by looking at the current stack, which in this case
 is the stack for the hard interrupt. This hides the fact that NEED_RESCHED
-has been set. We don't see the 'N' until we switch back to the task's
+has been set. We do not see the 'N' until we switch back to the task's
 assigned stack.
 
 ftrace
@@ -1044,14 +1037,14 @@ this tracer is a nop.
 [...]
 
 
-Note: It is sometimes better to enable or disable tracing directly from
-a program, because the buffer may be overflowed by the echo commands
-before you get to the point you want to trace. It is also easier to
-stop the tracing at the point that you hit the part that you are
-interested in. Since the ftrace buffer is a ring buffer with the
-oldest data being overwritten, usually it is sufficient to start the
-tracer with an echo command but have you code stop it. Something
-like the following is usually appropriate for this.
+Note: ftrace uses ring buffers to store the above entries. The newest data
+may overwrite the oldest data. Sometimes using echo to stop the trace
+is not sufficient because the tracing could have overwritten the data
+that you wanted to record. For this reason, it is sometimes better to
+disable tracing directly from a program. This allows you to stop the
+tracing at the point that you hit the part that you are interested in.
+To disable the tracing directly from a C program, something like following
+code snippet can be used:
 
 int trace_fd;
 [...]
@@ -1060,20 +1053,26 @@ int main(int argc, char *argv[]) {
 	trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY);
 	[...]
 	if (condition_hit()) {
-	write(trace_fd, "0", 1);
+		write(trace_fd, "0", 1);
 	}
 	[...]
 }
 
+Note: Here we hard coded the path name. The debugfs mount is not
+guaranteed to be at /debug (and is more commonly at /sys/kernel/debug).
+For simple one time traces, the above is sufficent. For anything else,
+a search through /proc/mounts may be needed to find where the debugfs
+file-system is mounted.
 
 dynamic ftrace
 --------------
 
-If CONFIG_DYNAMIC_FTRACE is set, then the system will run with
+If CONFIG_DYNAMIC_FTRACE is set, the system will run with
 virtually no overhead when function tracing is disabled. The way
 this works is the mcount function call (placed at the start of
 every kernel function, produced by the -pg switch in gcc), starts
-of pointing to a simple return.
+of pointing to a simple return. (Enabling FTRACE will include the
+-pg switch in the compiling of the kernel.)
 
 When dynamic ftrace is initialized, it calls kstop_machine to make
 the machine act like a uniprocessor so that it can freely modify code
@@ -1086,15 +1085,15 @@ Later on the ftraced kernel thread is awoken and will again call
 kstop_machine if new functions have been recorded. The ftraced thread
 will change all calls to mcount to "nop".  Just calling mcount
 and having mcount return has shown a 10% overhead. By converting
-it to a nop, there is no recordable overhead to the system.
+it to a nop, there is no measurable overhead to the system.
 
 One special side-effect to the recording of the functions being
-traced, is that we can now selectively choose which functions we
-want to trace and which ones we want the mcount calls to remain as
+traced is that we can now selectively choose which functions we
+wish to trace and which ones we want the mcount calls to remain as
 nops.
 
 Two files are used, one for enabling and one for disabling the tracing
-of recorded functions. They are:
+of specified functions. They are:
 
   set_ftrace_filter
 
@@ -1116,7 +1115,7 @@ pick_next_task_fair
 mutex_lock
 [...]
 
-If I'm only interested in sys_nanosleep and hrtimer_interrupt:
+If I am only interested in sys_nanosleep and hrtimer_interrupt:
 
  # echo sys_nanosleep hrtimer_interrupt \
 		> /debug/tracing/set_ftrace_filter
@@ -1133,21 +1132,21 @@ If I'm only interested in sys_nanosleep and hrtimer_interrupt:
           usleep-4134  [00]  1317.070111: sys_nanosleep <-syscall_call
           <idle>-0     [00]  1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt
 
-To see what functions are being traced, you can cat the file:
+To see which functions are being traced, you can cat the file:
 
  # cat /debug/tracing/set_ftrace_filter
 hrtimer_interrupt
 sys_nanosleep
 
 
-Perhaps this isn't enough. The filters also allow simple wild cards.
+Perhaps this is not enough. The filters also allow simple wild cards.
 Only the following are currently available
 
   <match>*  - will match functions that begin with <match>
   *<match>  - will match functions that end with <match>
   *<match>* - will match functions that have <match> in it
 
-Thats all the wild cards that are allowed.
+These are the only wild cards which are supported.
 
   <match>*<match> will not work.
 
@@ -1258,15 +1257,15 @@ calls that need to be converted into nops. If there are not any, then
 it simply goes back to sleep. But if there are some, it will call
 kstop_machine to convert the calls to nops.
 
-There may be a case that you do not want this added latency.
+There may be a case in which you do not want this added latency.
 Perhaps you are doing some audio recording and this activity might
 cause skips in the playback. There is an interface to disable
-and enable the ftraced kernel thread.
+and enable the "ftraced" kernel thread.
 
  # echo 0 > /debug/tracing/ftraced_enabled
 
-This will disable the calling of the kstop_machine to update the
-mcount calls to nops. Remember that there's a large overhead
+This will disable the calling of kstop_machine to update the
+mcount calls to nops. Remember that there is a large overhead
 to calling mcount. Without this kernel thread, that overhead will
 exist.
 
@@ -1282,8 +1281,8 @@ that uses ftrace function recording.
 trace_pipe
 ----------
 
-The trace_pipe outputs the same as trace, but the effect on the
-tracing is different. Every read from trace_pipe is consumed.
+The trace_pipe outputs the same content as the trace file, but the effect
+on the tracing is different. Every read from trace_pipe is consumed.
 This means that subsequent reads will be different. The trace
 is live.
 
@@ -1313,7 +1312,7 @@ is live.
             bash-4043  [00] 41.267111: select_task_rq_rt <-try_to_wake_up
 
 
-Note, reading the trace_pipe will block until more input is added.
+Note, reading the trace_pipe file will block until more input is added.
 By changing the tracer, trace_pipe will issue an EOF. We needed
 to set the ftrace tracer _before_ cating the trace_pipe file.
 
@@ -1322,7 +1321,7 @@ trace entries
 -------------
 
 Having too much or not enough data can be troublesome in diagnosing
-some issue in the kernel. The file trace_entries is used to modify
+an issue in the kernel. The file trace_entries is used to modify
 the size of the internal trace buffers. The number listed
 is the number of entries that can be recorded per CPU. To know
 the full size, multiply the number of possible CPUS with the
@@ -1332,7 +1331,8 @@ number of entries.
 65620
 
 Note, to modify this, you must have tracing completely disabled. To do that,
-echo "none" into the current_tracer.
+echo "none" into the current_tracer. If the current_tracer is not set
+to "none", an EINVAL error will be returned.
 
  # echo none > /debug/tracing/current_tracer
  # echo 100000 > /debug/tracing/trace_entries
@@ -1341,18 +1341,18 @@ echo "none" into the current_tracer.
 
 
 Notice that we echoed in 100,000 but the size is 100,045. The entries
-are held by individual pages. It allocates the number of pages it takes
+are held in individual pages. It allocates the number of pages it takes
 to fulfill the request. If more entries may fit on the last page
-it will add them.
+then they will be added.
 
  # echo 1 > /debug/tracing/trace_entries
  # cat /debug/tracing/trace_entries
 85
 
-This shows us that 85 entries can fit on a single page.
+This shows us that 85 entries can fit in a single page.
 
-The number of pages that will be allocated is a percentage of available
-memory. Allocating too much will produce an error.
+The number of pages which will be allocated is limited to a percentage
+of available memory. Allocating too much will produce an error.
 
  # echo 1000000000000 > /debug/tracing/trace_entries
 -bash: echo: write error: Cannot allocate memory

Documentation/gpio.txt

@@ -347,15 +347,12 @@ necessarily be nonportable.
 Dynamic definition of GPIOs is not currently standard; for example, as
 a side effect of configuring an add-on board with some GPIO expanders.
 
-These calls are purely for kernel space, but a userspace API could be built
-on top of them.
-
 
 GPIO implementor's framework (OPTIONAL)
 =======================================
 As noted earlier, there is an optional implementation framework making it
 easier for platforms to support different kinds of GPIO controller using
-the same programming interface.
+the same programming interface.  This framework is called "gpiolib".
 
 As a debugging aid, if debugfs is available a /sys/kernel/debug/gpio file
 will be found there.  That will list all the controllers registered through
@@ -392,11 +389,21 @@ either NULL or the label associated with that GPIO when it was requested.
 
 Platform Support
 ----------------
-To support this framework, a platform's Kconfig will "select HAVE_GPIO_LIB"
+To support this framework, a platform's Kconfig will "select" either
+ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
 They may also want to provide a custom value for ARCH_NR_GPIOS.
 
+ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+into the kernel on that architecture.
+
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+can enable it and build it into the kernel optionally.
+
+If neither of these options are selected, the platform does not support
+GPIOs through GPIO-lib and the code cannot be enabled by the user.
+
 Trivial implementations of those functions can directly use framework
 code, which always dispatches through the gpio_chip:
 
@@ -439,4 +446,120 @@ becomes available.  That may mean the device should not be registered until
 calls for that GPIO can work.  One way to address such dependencies is for
 such gpio_chip controllers to provide setup() and teardown() callbacks to
 board specific code; those board specific callbacks would register devices
-once all the necessary resources are available.
+once all the necessary resources are available, and remove them later when
+the GPIO controller device becomes unavailable.
+
+
+Sysfs Interface for Userspace (OPTIONAL)
+========================================
+Platforms which use the "gpiolib" implementors framework may choose to
+configure a sysfs user interface to GPIOs.  This is different from the
+debugfs interface, since it provides control over GPIO direction and
+value instead of just showing a gpio state summary.  Plus, it could be
+present on production systems without debugging support.
+
+Given approprate hardware documentation for the system, userspace could
+know for example that GPIO #23 controls the write protect line used to
+protect boot loader segments in flash memory.  System upgrade procedures
+may need to temporarily remove that protection, first importing a GPIO,
+then changing its output state, then updating the code before re-enabling
+the write protection.  In normal use, GPIO #23 would never be touched,
+and the kernel would have no need to know about it.
+
+Again depending on appropriate hardware documentation, on some systems
+userspace GPIO can be used to determine system configuration data that
+standard kernels won't know about.  And for some tasks, simple userspace
+GPIO drivers could be all that the system really needs.
+
+Note that standard kernel drivers exist for common "LEDs and Buttons"
+GPIO tasks:  "leds-gpio" and "gpio_keys", respectively.  Use those
+instead of talking directly to the GPIOs; they integrate with kernel
+frameworks better than your userspace code could.
+
+
+Paths in Sysfs
+--------------
+There are three kinds of entry in /sys/class/gpio:
+
+   -	Control interfaces used to get userspace control over GPIOs;
+
+   -	GPIOs themselves; and
+
+   -	GPIO controllers ("gpio_chip" instances).
+
+That's in addition to standard files including the "device" symlink.
+
+The control interfaces are write-only:
+
+    /sys/class/gpio/
+
+    	"export" ... Userspace may ask the kernel to export control of
+		a GPIO to userspace by writing its number to this file.
+
+		Example:  "echo 19 > export" will create a "gpio19" node
+		for GPIO #19, if that's not requested by kernel code.
+
+    	"unexport" ... Reverses the effect of exporting to userspace.
+
+		Example:  "echo 19 > unexport" will remove a "gpio19"
+		node exported using the "export" file.
+
+GPIO signals have paths like /sys/class/gpio/gpio42/ (for GPIO #42)
+and have the following read/write attributes:
+
+    /sys/class/gpio/gpioN/
+
+	"direction" ... reads as either "in" or "out".  This value may
+		normally be written.  Writing as "out" defaults to
+		initializing the value as low.  To ensure glitch free
+		operation, values "low" and "high" may be written to
+		configure the GPIO as an output with that initial value.
+
+		Note that this attribute *will not exist* if the kernel
+		doesn't support changing the direction of a GPIO, or
+		it was exported by kernel code that didn't explicitly
+		allow userspace to reconfigure this GPIO's direction.
+
+	"value" ... reads as either 0 (low) or 1 (high).  If the GPIO
+		is configured as an output, this value may be written;
+		any nonzero value is treated as high.
+
+GPIO controllers have paths like /sys/class/gpio/chipchip42/ (for the
+controller implementing GPIOs starting at #42) and have the following
+read-only attributes:
+
+    /sys/class/gpio/gpiochipN/
+
+    	"base" ... same as N, the first GPIO managed by this chip
+
+    	"label" ... provided for diagnostics (not always unique)
+
+    	"ngpio" ... how many GPIOs this manges (N to N + ngpio - 1)
+
+Board documentation should in most cases cover what GPIOs are used for
+what purposes.  However, those numbers are not always stable; GPIOs on
+a daughtercard might be different depending on the base board being used,
+or other cards in the stack.  In such cases, you may need to use the
+gpiochip nodes (possibly in conjunction with schematics) to determine
+the correct GPIO number to use for a given signal.
+
+
+Exporting from Kernel code
+--------------------------
+Kernel code can explicitly manage exports of GPIOs which have already been
+requested using gpio_request():
+
+	/* export the GPIO to userspace */
+	int gpio_export(unsigned gpio, bool direction_may_change);
+
+	/* reverse gpio_export() */
+	void gpio_unexport();
+
+After a kernel driver requests a GPIO, it may only be made available in
+the sysfs interface by gpio_export().  The driver can control whether the
+signal direction may change.  This helps drivers prevent userspace code
+from accidentally clobbering important system state.
+
+This explicit exporting can help with debugging (by making some kinds
+of experiments easier), or can provide an always-there interface that's
+suitable for documenting as part of a board support package.

Documentation/hwmon/dme1737

@@ -22,6 +22,10 @@ Module Parameters
 			and PWM output control functions. Using this parameter
 			shouldn't be required since the BIOS usually takes care
 			of this.
+* probe_all_addr: bool	Include non-standard LPC addresses 0x162e and 0x164e
+			when probing for ISA devices. This is required for the
+			following boards:
+			- VIA EPIA SN18000
 
 Note that there is no need to use this parameter if the driver loads without
 complaining. The driver will say so if it is necessary.

Documentation/hwmon/lm85

@@ -96,11 +96,6 @@ initial testing of the ADM1027 it was 1.00 degC steps. Analog Devices has
 confirmed this "bug". The ADT7463 is reported to work as described in the
 documentation. The current lm85 driver does not show the offset register.
 
-The ADT7463 has a THERM asserted counter. This counter has a 22.76ms
-resolution and a range of 5.8 seconds. The driver implements a 32-bit
-accumulator of the counter value to extend the range to over a year. The
-counter will stay at it's max value until read.
-
 See the vendor datasheets for more information. There is application note
 from National (AN-1260) with some additional information about the LM85.
 The Analog Devices datasheet is very detailed and describes a procedure for
@@ -206,13 +201,15 @@ Configuration choices:
 
 The National LM85's have two vendor specific configuration
 features. Tach. mode and Spinup Control. For more details on these,
-see the LM85 datasheet or Application Note AN-1260.
+see the LM85 datasheet or Application Note AN-1260. These features
+are not currently supported by the lm85 driver.
 
 The Analog Devices ADM1027 has several vendor specific enhancements.
 The number of pulses-per-rev of the fans can be set, Tach monitoring
 can be optimized for PWM operation, and an offset can be applied to
 the temperatures to compensate for systemic errors in the
-measurements.
+measurements. These features are not currently supported by the lm85
+driver.
 
 In addition to the ADM1027 features, the ADT7463 also has Tmin control
 and THERM asserted counts. Automatic Tmin control acts to adjust the

Documentation/i2c/chips/max6875

@@ -49,7 +49,7 @@ $ modprobe max6875 force=0,0x50
 
 The MAX6874/MAX6875 ignores address bit 0, so this driver attaches to multiple
 addresses.  For example, for address 0x50, it also reserves 0x51.
-The even-address instance is called 'max6875', the odd one is 'max6875 subclient'.
+The even-address instance is called 'max6875', the odd one is 'dummy'.
 
 
 Programming the chip using i2c-dev

Documentation/i2c/chips/pca9539

@@ -7,7 +7,7 @@ drivers/gpio/pca9539.c instead.
 Supported chips:
   * Philips PCA9539
     Prefix: 'pca9539'
-    Addresses scanned: 0x74 - 0x77
+    Addresses scanned: none
     Datasheet:
         http://www.semiconductors.philips.com/acrobat/datasheets/PCA9539_2.pdf
 
@@ -23,6 +23,14 @@ The input sense can also be inverted.
 The 16 lines are split between two bytes.
 
 
+Detection
+---------
+
+The PCA9539 is difficult to detect and not commonly found in PC machines,
+so you have to pass the I2C bus and address of the installed PCA9539
+devices explicitly to the driver at load time via the force=... parameter.
+
+
 Sysfs entries
 -------------
 

Documentation/i2c/chips/pcf8574

@@ -4,13 +4,13 @@ Kernel driver pcf8574
 Supported chips:
   * Philips PCF8574
     Prefix: 'pcf8574'
-    Addresses scanned: I2C 0x20 - 0x27
+    Addresses scanned: none
     Datasheet: Publicly available at the Philips Semiconductors website
                http://www.semiconductors.philips.com/pip/PCF8574P.html
 
  * Philips PCF8574A
     Prefix: 'pcf8574a'
-    Addresses scanned: I2C 0x38 - 0x3f
+    Addresses scanned: none
     Datasheet: Publicly available at the Philips Semiconductors website
                http://www.semiconductors.philips.com/pip/PCF8574P.html
 
@@ -38,12 +38,10 @@ For more informations see the datasheet.
 Accessing PCF8574(A) via /sys interface
 -------------------------------------
 
-! Be careful !
 The PCF8574(A) is plainly impossible to detect ! Stupid chip.
-So every chip with address in the interval [20..27] and [38..3f] are
-detected as PCF8574(A). If you have other chips in this address
-range, the workaround is to load this module after the one
-for your others chips.
+So, you have to pass the I2C bus and address of the installed PCF857A
+and PCF8574A devices explicitly to the driver at load time via the
+force=... parameter.
 
 On detection (i.e. insmod, modprobe et al.), directories are being
 created for each detected PCF8574(A):

Documentation/i2c/chips/pcf8575

@@ -40,12 +40,9 @@ Detection
 ---------
 
 There is no method known to detect whether a chip on a given I2C address is
-a PCF8575 or whether it is any other I2C device. So there are two alternatives
-to let the driver find the installed PCF8575 devices:
-- Load this driver after any other I2C driver for I2C devices with addresses
-  in the range 0x20 .. 0x27.
-- Pass the I2C bus and address of the installed PCF8575 devices explicitly to
-  the driver at load time via the probe=... or force=... parameters.
+a PCF8575 or whether it is any other I2C device, so you have to pass the I2C
+bus and address of the installed PCF8575 devices explicitly to the driver at
+load time via the force=... parameter.
 
 /sys interface
 --------------

Documentation/i2c/upgrading-clients

@@ -0,0 +1,281 @@
+Upgrading I2C Drivers to the new 2.6 Driver Model
+=================================================
+
+Ben Dooks <ben-linux@fluff.org>
+
+Introduction
+------------
+
+This guide outlines how to alter existing Linux 2.6 client drivers from
+the old to the new new binding methods.
+
+
+Example old-style driver
+------------------------
+
+
+struct example_state {
+	struct i2c_client	client;
+	....
+};
+
+static struct i2c_driver example_driver;
+
+static unsigned short ignore[] = { I2C_CLIENT_END };
+static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END };
+
+I2C_CLIENT_INSMOD;
+
+static int example_attach(struct i2c_adapter *adap, int addr, int kind)
+{
+	struct example_state *state;
+	struct device *dev = &adap->dev;  /* to use for dev_ reports */
+	int ret;
+
+	state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+	if (state == NULL) {
+		dev_err(dev, "failed to create our state\n");
+		return -ENOMEM;
+	}
+
+	example->client.addr    = addr;
+	example->client.flags   = 0;
+	example->client.adapter = adap;
+
+	i2c_set_clientdata(&state->i2c_client, state);
+	strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE);
+
+	ret = i2c_attach_client(&state->i2c_client);
+	if (ret < 0) {
+		dev_err(dev, "failed to attach client\n");
+		kfree(state);
+		return ret;
+	}
+
+	dev = &state->i2c_client.dev;
+
+	/* rest of the initialisation goes here. */
+
+	dev_info(dev, "example client created\n");
+
+	return 0;
+}
+
+static int __devexit example_detach(struct i2c_client *client)
+{
+	struct example_state *state = i2c_get_clientdata(client);
+
+	i2c_detach_client(client);
+	kfree(state);
+	return 0;
+}
+
+static int example_attach_adapter(struct i2c_adapter *adap)
+{
+	return i2c_probe(adap, &addr_data, example_attach);
+}
+
+static struct i2c_driver example_driver = {
+ 	.driver		= {
+		.owner		= THIS_MODULE,
+		.name		= "example",
+	},
+	.attach_adapter = example_attach_adapter,
+	.detach_client	= __devexit_p(example_detach),
+	.suspend	= example_suspend,
+	.resume		= example_resume,
+};
+
+
+Updating the client
+-------------------
+
+The new style binding model will check against a list of supported
+devices and their associated address supplied by the code registering
+the busses. This means that the driver .attach_adapter and
+.detach_adapter methods can be removed, along with the addr_data,
+as follows:
+
+- static struct i2c_driver example_driver;
+
+- static unsigned short ignore[] = { I2C_CLIENT_END };
+- static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END };
+
+- I2C_CLIENT_INSMOD;
+
+- static int example_attach_adapter(struct i2c_adapter *adap)
+- {
+- 	return i2c_probe(adap, &addr_data, example_attach);
+- }
+
+ static struct i2c_driver example_driver = {
+-	.attach_adapter = example_attach_adapter,
+-	.detach_client	= __devexit_p(example_detach),
+ }
+
+Add the probe and remove methods to the i2c_driver, as so:
+
+ static struct i2c_driver example_driver = {
++	.probe		= example_probe,
++	.remove		= __devexit_p(example_remove),
+ }
+
+Change the example_attach method to accept the new parameters
+which include the i2c_client that it will be working with:
+
+- static int example_attach(struct i2c_adapter *adap, int addr, int kind)
++ static int example_probe(struct i2c_client *client,
++			   const struct i2c_device_id *id)
+
+Change the name of example_attach to example_probe to align it with the
+i2c_driver entry names. The rest of the probe routine will now need to be
+changed as the i2c_client has already been setup for use.
+
+The necessary client fields have already been setup before
+the probe function is called, so the following client setup
+can be removed:
+
+-	example->client.addr    = addr;
+-	example->client.flags   = 0;
+-	example->client.adapter = adap;
+-
+-	strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE);
+
+The i2c_set_clientdata is now:
+
+-	i2c_set_clientdata(&state->client, state);
++	i2c_set_clientdata(client, state);
+
+The call to i2c_attach_client is no longer needed, if the probe
+routine exits successfully, then the driver will be automatically
+attached by the core. Change the probe routine as so:
+
+-	ret = i2c_attach_client(&state->i2c_client);
+-	if (ret < 0) {
+-		dev_err(dev, "failed to attach client\n");
+-		kfree(state);
+-		return ret;
+-	}
+
+
+Remove the storage of 'struct i2c_client' from the 'struct example_state'
+as we are provided with the i2c_client in our example_probe. Instead we
+store a pointer to it for when it is needed.
+
+struct example_state {
+-	struct i2c_client	client;
++	struct i2c_client	*client;
+
+the new i2c client as so:
+
+-	struct device *dev = &adap->dev;  /* to use for dev_ reports */
++ 	struct device *dev = &i2c_client->dev;  /* to use for dev_ reports */
+
+And remove the change after our client is attached, as the driver no
+longer needs to register a new client structure with the core:
+
+-	dev = &state->i2c_client.dev;
+
+In the probe routine, ensure that the new state has the client stored
+in it:
+
+static int example_probe(struct i2c_client *i2c_client,
+			 const struct i2c_device_id *id)
+{
+	struct example_state *state;
+ 	struct device *dev = &i2c_client->dev;
+	int ret;
+
+	state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+	if (state == NULL) {
+		dev_err(dev, "failed to create our state\n");
+		return -ENOMEM;
+	}
+
++	state->client = i2c_client;
+
+Update the detach method, by changing the name to _remove and
+to delete the i2c_detach_client call. It is possible that you
+can also remove the ret variable as it is not not needed for
+any of the core functions.
+
+- static int __devexit example_detach(struct i2c_client *client)
++ static int __devexit example_remove(struct i2c_client *client)
+{
+	struct example_state *state = i2c_get_clientdata(client);
+
+-	i2c_detach_client(client);
+
+And finally ensure that we have the correct ID table for the i2c-core
+and other utilities:
+
++ struct i2c_device_id example_idtable[] = {
++       { "example", 0 },
++       { }
++};
++
++MODULE_DEVICE_TABLE(i2c, example_idtable);
+
+static struct i2c_driver example_driver = {
+ 	.driver		= {
+		.owner		= THIS_MODULE,
+		.name		= "example",
+	},
++	.id_table	= example_ids,
+
+
+Our driver should now look like this:
+
+struct example_state {
+	struct i2c_client	*client;
+	....
+};
+
+static int example_probe(struct i2c_client *client,
+		     	 const struct i2c_device_id *id)
+{
+	struct example_state *state;
+	struct device *dev = &client->dev;
+
+	state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+	if (state == NULL) {
+		dev_err(dev, "failed to create our state\n");
+		return -ENOMEM;
+	}
+
+	state->client = client;
+	i2c_set_clientdata(client, state);
+
+	/* rest of the initialisation goes here. */
+
+	dev_info(dev, "example client created\n");
+
+	return 0;
+}
+
+static int __devexit example_remove(struct i2c_client *client)
+{
+	struct example_state *state = i2c_get_clientdata(client);
+
+	kfree(state);
+	return 0;
+}
+
+static struct i2c_device_id example_idtable[] = {
+	{ "example", 0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, example_idtable);
+
+static struct i2c_driver example_driver = {
+ 	.driver		= {
+		.owner		= THIS_MODULE,
+		.name		= "example",
+	},
+	.id_table	= example_idtable,
+	.probe		= example_probe,
+	.remove		= __devexit_p(example_remove),
+	.suspend	= example_suspend,
+	.resume		= example_resume,
+};

Documentation/ia64/kvm.txt

@@ -50,9 +50,9 @@ Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qe
 		/usr/local/bin/qemu-system-ia64 -smp xx -m 512 -hda $your_image
 		(xx is the number of virtual processors for the guest, now the maximum value is 4)
 
-5. Known possibile issue on some platforms with old Firmware.
+5. Known possible issue on some platforms with old Firmware.
 
-If meet strange host crashe issues, try to solve it through either of the following ways:
+In the event of strange host crash issues, try to solve it through either of the following ways:
 
 (1): Upgrade your Firmware to the latest one.
 
@@ -65,8 +65,8 @@ index 0b53344..f02b0f7 100644
 	mov ar.pfs = loc1
 	mov rp = loc0
 	;;
--	srlz.d				// seralize restoration of psr.l
-+	srlz.i			// seralize restoration of psr.l
+-	srlz.d				// serialize restoration of psr.l
++	srlz.i			// serialize restoration of psr.l
 +	;;
 	br.ret.sptk.many b0
  END(ia64_pal_call_static)

Documentation/ia64/paravirt_ops.txt

@@ -0,0 +1,137 @@
+Paravirt_ops on IA64
+====================
+                          21 May 2008, Isaku Yamahata <yamahata@valinux.co.jp>
+
+
+Introduction
+------------
+The aim of this documentation is to help with maintainability and/or to
+encourage people to use paravirt_ops/IA64.
+
+paravirt_ops (pv_ops in short) is a way for virtualization support of
+Linux kernel on x86. Several ways for virtualization support were
+proposed, paravirt_ops is the winner.
+On the other hand, now there are also several IA64 virtualization
+technologies like kvm/IA64, xen/IA64 and many other academic IA64
+hypervisors so that it is good to add generic virtualization
+infrastructure on Linux/IA64.
+
+
+What is paravirt_ops?
+---------------------
+It has been developed on x86 as virtualization support via API, not ABI.
+It allows each hypervisor to override operations which are important for
+hypervisors at API level. And it allows a single kernel binary to run on
+all supported execution environments including native machine.
+Essentially paravirt_ops is a set of function pointers which represent
+operations corresponding to low level sensitive instructions and high
+level functionalities in various area. But one significant difference
+from usual function pointer table is that it allows optimization with
+binary patch. It is because some of these operations are very
+performance sensitive and indirect call overhead is not negligible.
+With binary patch, indirect C function call can be transformed into
+direct C function call or in-place execution to eliminate the overhead.
+
+Thus, operations of paravirt_ops are classified into three categories.
+- simple indirect call
+  These operations correspond to high level functionality so that the
+  overhead of indirect call isn't very important.
+
+- indirect call which allows optimization with binary patch
+  Usually these operations correspond to low level instructions. They
+  are called frequently and performance critical. So the overhead is
+  very important.
+
+- a set of macros for hand written assembly code
+  Hand written assembly codes (.S files) also need paravirtualization
+  because they include sensitive instructions or some of code paths in
+  them are very performance critical.
+
+
+The relation to the IA64 machine vector
+---------------------------------------
+Linux/IA64 has the IA64 machine vector functionality which allows the
+kernel to switch implementations (e.g. initialization, ipi, dma api...)
+depending on executing platform.
+We can replace some implementations very easily defining a new machine
+vector. Thus another approach for virtualization support would be
+enhancing the machine vector functionality.
+But paravirt_ops approach was taken because
+- virtualization support needs wider support than machine vector does.
+  e.g. low level instruction paravirtualization. It must be
+       initialized very early before platform detection.
+
+- virtualization support needs more functionality like binary patch.
+  Probably the calling overhead might not be very large compared to the
+  emulation overhead of virtualization. However in the native case, the
+  overhead should be eliminated completely.
+  A single kernel binary should run on each environment including native,
+  and the overhead of paravirt_ops on native environment should be as
+  small as possible.
+
+- for full virtualization technology, e.g. KVM/IA64 or
+  Xen/IA64 HVM domain, the result would be
+  (the emulated platform machine vector. probably dig) + (pv_ops).
+  This means that the virtualization support layer should be under
+  the machine vector layer.
+
+Possibly it might be better to move some function pointers from
+paravirt_ops to machine vector. In fact, Xen domU case utilizes both
+pv_ops and machine vector.
+
+
+IA64 paravirt_ops
+-----------------
+In this section, the concrete paravirt_ops will be discussed.
+Because of the architecture difference between ia64 and x86, the
+resulting set of functions is very different from x86 pv_ops.
+
+- C function pointer tables
+They are not very performance critical so that simple C indirect
+function call is acceptable. The following structures are defined at
+this moment. For details see linux/include/asm-ia64/paravirt.h
+  - struct pv_info
+    This structure describes the execution environment.
+  - struct pv_init_ops
+    This structure describes the various initialization hooks.
+  - struct pv_iosapic_ops
+    This structure describes hooks to iosapic operations.
+  - struct pv_irq_ops
+    This structure describes hooks to irq related operations
+  - struct pv_time_op
+    This structure describes hooks to steal time accounting.
+
+- a set of indirect calls which need optimization
+Currently this class of functions correspond to a subset of IA64
+intrinsics. At this moment the optimization with binary patch isn't
+implemented yet.
+struct pv_cpu_op is defined. For details see
+linux/include/asm-ia64/paravirt_privop.h
+Mostly they correspond to ia64 intrinsics 1-to-1.
+Caveat: Now they are defined as C indirect function pointers, but in
+order to support binary patch optimization, they will be changed
+using GCC extended inline assembly code.
+
+- a set of macros for hand written assembly code (.S files)
+For maintenance purpose, the taken approach for .S files is single
+source code and compile multiple times with different macros definitions.
+Each pv_ops instance must define those macros to compile.
+The important thing here is that sensitive, but non-privileged
+instructions must be paravirtualized and that some privileged
+instructions also need paravirtualization for reasonable performance.
+Developers who modify .S files must be aware of that. At this moment
+an easy checker is implemented to detect paravirtualization breakage.
+But it doesn't cover all the cases.
+
+Sometimes this set of macros is called pv_cpu_asm_op. But there is no
+corresponding structure in the source code.
+Those macros mostly 1:1 correspond to a subset of privileged
+instructions. See linux/include/asm-ia64/native/inst.h.
+And some functions written in assembly also need to be overrided so
+that each pv_ops instance have to define some macros. Again see
+linux/include/asm-ia64/native/inst.h.
+
+
+Those structures must be initialized very early before start_kernel.
+Probably initialized in head.S using multi entry point or some other trick.
+For native case implementation see linux/arch/ia64/kernel/paravirt.c.

Documentation/input/cs461x.txt

@@ -31,7 +31,7 @@ The driver works with ALSA drivers simultaneously. For example, the xracer
 uses joystick as input device and PCM device as sound output in one time.
 There are no sound or input collisions detected. The source code have
 comments about them; but I've found the joystick can be initialized 
-separately of ALSA modules. So, you canm use only one joystick driver
+separately of ALSA modules. So, you can use only one joystick driver
 without ALSA drivers. The ALSA drivers are not needed to compile or
 run this driver.
 

Documentation/input/gameport-programming.txt

@@ -1,5 +1,3 @@
-$Id: gameport-programming.txt,v 1.3 2001/04/24 13:51:37 vojtech Exp $
-
 Programming gameport drivers
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

Documentation/input/input.txt

@@ -1,7 +1,6 @@
 			  Linux Input drivers v1.0
 	       (c) 1999-2001 Vojtech Pavlik <vojtech@ucw.cz>
 			     Sponsored by SuSE
-	    $Id: input.txt,v 1.8 2002/05/29 03:15:01 bradleym Exp $
 ----------------------------------------------------------------------------
 
 0. Disclaimer

Documentation/input/joystick-api.txt

@@ -5,8 +5,6 @@
 
 			      7 Aug 1998
 
-	$Id: joystick-api.txt,v 1.2 2001/05/08 21:21:23 vojtech Exp $
-
 1. Initialization
 ~~~~~~~~~~~~~~~~~
 

Documentation/input/joystick-parport.txt

@@ -2,7 +2,6 @@
 	       (c) 1998-2000 Vojtech Pavlik <vojtech@ucw.cz>
 	       (c) 1998 Andree Borrmann <a.borrmann@tu-bs.de>
 			     Sponsored by SuSE
-	$Id: joystick-parport.txt,v 1.6 2001/09/25 09:31:32 vojtech Exp $
 ----------------------------------------------------------------------------
 
 0. Disclaimer

Documentation/input/joystick.txt

@@ -1,7 +1,6 @@
 		       Linux Joystick driver v2.0.0
 	       (c) 1996-2000 Vojtech Pavlik <vojtech@ucw.cz>
 			     Sponsored by SuSE
-	   $Id: joystick.txt,v 1.12 2002/03/03 12:13:07 jdeneux Exp $
 ----------------------------------------------------------------------------
 
 0. Disclaimer

Documentation/ioctl/hdio.txt

@@ -508,12 +508,13 @@ HDIO_DRIVE_RESET		execute a device reset
 
 	error returns:
 	  EACCES	Access denied:  requires CAP_SYS_ADMIN
+	  ENXIO		No such device:	phy dead or ctl_addr == 0
+	  EIO		I/O error:	reset timed out or hardware error
 
 	notes:
 
-	  Abort any current command, prevent anything else from being
-	  queued, execute a reset on the device, and issue BLKRRPART
-	  ioctl on the block device.
+	  Execute a reset on the device as soon as the current IO
+	  operation has completed.
 
 	  Executes an ATAPI soft reset if applicable, otherwise
 	  executes an ATA soft reset on the controller.

Documentation/ioctl/ioctl-decoding.txt

@@ -1,6 +1,6 @@
 To decode a hex IOCTL code:
 
-Most architecures use this generic format, but check
+Most architectures use this generic format, but check
 include/ARCH/ioctl.h for specifics, e.g. powerpc
 uses 3 bits to encode read/write and 13 bits for size.
 
@@ -18,7 +18,7 @@ uses 3 bits to encode read/write and 13 bits for size.
  7-0	function #
 
 
- So for example 0x82187201 is a read with arg length of 0x218,
+So for example 0x82187201 is a read with arg length of 0x218,
 character 'r' function 1. Grepping the source reveals this is:
 
 #define VFAT_IOCTL_READDIR_BOTH         _IOR('r', 1, struct dirent [2])

Documentation/iostats.txt

@@ -143,7 +143,7 @@ disk and partition statistics are consistent again. Since we still don't
 keep record of the partition-relative address, an operation is attributed to
 the partition which contains the first sector of the request after the
 eventual merges. As requests can be merged across partition, this could lead
-to some (probably insignificant) innacuracy.
+to some (probably insignificant) inaccuracy.
 
 Additional notes
 ----------------

Documentation/isdn/README.mISDN

@@ -0,0 +1,6 @@
+mISDN is a new modular ISDN driver, in the long term it should replace
+the old I4L driver architecture for passiv ISDN cards.
+It was designed to allow a broad range of applications and interfaces
+but only have the basic function in kernel, the interface to the user
+space is based on sockets with a own address family AF_ISDN.
+

Documentation/kdump/kdump.txt

@@ -65,26 +65,26 @@ Install kexec-tools
 
 2) Download the kexec-tools user-space package from the following URL:
 
-http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools-testing.tar.gz
+http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools.tar.gz
 
-This is a symlink to the latest version, which at the time of writing is
-20061214, the only release of kexec-tools-testing so far. As other versions
-are released, the older ones will remain available at
-http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/
+This is a symlink to the latest version.
 
-Note: Latest kexec-tools-testing git tree is available at
+The latest kexec-tools git tree is available at:
 
-git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools-testing.git
+git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools.git
 or
-http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools-testing.git;a=summary
+http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools.git
+
+More information about kexec-tools can be found at
+http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/README.html
 
 3) Unpack the tarball with the tar command, as follows:
 
-   tar xvpzf kexec-tools-testing.tar.gz
+   tar xvpzf kexec-tools.tar.gz
 
 4) Change to the kexec-tools directory, as follows:
 
-   cd kexec-tools-testing-VERSION
+   cd kexec-tools-VERSION
 
 5) Configure the package, as follows:
 

Documentation/kernel-parameters.txt

@@ -87,7 +87,8 @@ parameter is applicable:
 	SH	SuperH architecture is enabled.
 	SMP	The kernel is an SMP kernel.
 	SPARC	Sparc architecture is enabled.
-	SWSUSP	Software suspend is enabled.
+	SWSUSP	Software suspend (hibernation) is enabled.
+	SUSPEND	System suspend states are enabled.
 	TS	Appropriate touchscreen support is enabled.
 	USB	USB support is enabled.
 	USBHID	USB Human Interface Device support is enabled.
@@ -147,10 +148,16 @@ and is between 256 and 4096 characters. It is defined in the file
 			default: 0
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep }
+			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering }
 			See Documentation/power/video.txt for s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
+			s4_nohwsig prevents ACPI hardware signature from being
+			used during resume from hibernation.
+			old_ordering causes the ACPI 1.0 ordering of the _PTS
+			control method, wrt putting devices into low power
+			states, to be enforced (the ACPI 2.0 ordering of _PTS is
+			used by default).
 
 	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
@@ -770,8 +777,22 @@ and is between 256 and 4096 characters. It is defined in the file
 	hisax=		[HW,ISDN]
 			See Documentation/isdn/README.HiSax.
 
-	hugepages=	[HW,X86-32,IA-64] Maximal number of HugeTLB pages.
-	hugepagesz=	[HW,IA-64,PPC] The size of the HugeTLB pages.
+	hugepages=	[HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
+	hugepagesz=	[HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
+			On x86-64 and powerpc, this option can be specified
+			multiple times interleaved with hugepages= to reserve
+			huge pages of different sizes. Valid pages sizes on
+			x86-64 are 2M (when the CPU supports "pse") and 1G
+			(when the CPU supports the "pdpe1gb" cpuinfo flag)
+			Note that 1GB pages can only be allocated at boot time
+			using hugepages= and not freed afterwards.
+	default_hugepagesz=
+			[same as hugepagesz=] The size of the default
+			HugeTLB page size. This is the size represented by
+			the legacy /proc/ hugepages APIs, used for SHM, and
+			default size when mounting hugetlbfs filesystems.
+			Defaults to the default architecture's huge page size
+			if not specified.
 
 	i8042.direct	[HW] Put keyboard port into non-translated mode
 	i8042.dumbkbd	[HW] Pretend that controller can only read data from
@@ -818,7 +839,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			See Documentation/ide/ide.txt.
 
 	idle=		[X86]
-			Format: idle=poll or idle=mwait
+			Format: idle=poll or idle=mwait, idle=halt, idle=nomwait
 			Poll forces a polling idle loop that can slightly improves the performance
 			of waking up a idle CPU, but will use a lot of power and make the system
 			run hot. Not recommended.
@@ -826,6 +847,9 @@ and is between 256 and 4096 characters. It is defined in the file
 			to not use it because it doesn't save as much power as a normal idle
 			loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same
 			as idle=poll.
+			idle=halt. Halt is forced to be used for CPU idle.
+			In such case C2/C3 won't be used again.
+			idle=nomwait. Disable mwait for CPU C-states
 
 	ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
 			Claim all unknown PCI IDE storage controllers.
@@ -1199,7 +1223,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			         or
 			         memmap=0x10000$0x18690000
 
-	memtest=	[KNL,X86_64] Enable memtest
+	memtest=	[KNL,X86] Enable memtest
 			Format: <integer>
 			range: 0,4 : pattern number
 			default : 0 <disable>
@@ -1218,6 +1242,14 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	mga=		[HW,DRM]
 
+	mminit_loglevel=
+			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
+			parameter allows control of the logging verbosity for
+			the additional memory initialisation checks. A value
+			of 0 disables mminit logging and a level of 4 will
+			log everything. Information is printed at KERN_DEBUG
+			so loglevel=8 may also need to be specified.
+
 	mousedev.tap_time=
 			[MOUSE] Maximum time between finger touching and
 			leaving touchpad surface for touch to be considered
@@ -1272,6 +1304,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			This usage is only documented in each driver source
 			file if at all.
 
+	nf_conntrack.acct=
+			[NETFILTER] Enable connection tracking flow accounting
+			0 to disable accounting
+			1 to enable accounting
+			Default value depends on CONFIG_NF_CT_ACCT that is
+			going to be removed in 2.6.29.
+
 	nfsaddrs=	[NFS]
 			See Documentation/filesystems/nfsroot.txt.
 
@@ -1534,6 +1573,9 @@ and is between 256 and 4096 characters. It is defined in the file
 				Use with caution as certain devices share
 				address decoders between ROMs and other
 				resources.
+		norom		[X86-32,X86_64] Do not assign address space to
+				expansion ROMs that do not already have
+				BIOS assigned address ranges.
 		irqmask=0xMMMM	[X86-32] Set a bit mask of IRQs allowed to be
 				assigned automatically to PCI devices. You can
 				make the kernel exclude IRQs of your ISA cards
@@ -2017,6 +2059,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	snd-ymfpci=	[HW,ALSA]
 
+	softlockup_panic=
+			[KNL] Should the soft-lockup detector generate panics.
+
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/sonypi.txt
 
@@ -2081,6 +2126,12 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	tdfx=		[HW,DRM]
 
+	test_suspend=	[SUSPEND]
+			Specify "mem" (for Suspend-to-RAM) or "standby" (for
+			standby suspend) as the system sleep state to briefly
+			enter during system startup.  The system is woken from
+			this state using a wakeup-capable RTC alarm.
+
 	thash_entries=	[KNL,NET]
 			Set number of hash buckets for TCP connection
 
@@ -2108,13 +2159,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			<deci-seconds>: poll all this frequency
 			0: no polling (default)
 
-	tipar.timeout=	[HW,PPT]
-			Set communications timeout in tenths of a second
-			(default 15).
-
-	tipar.delay=	[HW,PPT]
-			Set inter-bit delay in microseconds (default 10).
-
 	tmscsim=	[HW,SCSI]
 			See comment before function dc390_setup() in
 			drivers/scsi/tmscsim.c.
@@ -2148,6 +2192,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Note that genuine overcurrent events won't be
 			reported either.
 
+	unknown_nmi_panic
+			[X86-32,X86-64]
+			Set unknown_nmi_panic=1 early on boot.
+
 	usbcore.autosuspend=
 			[USB] The autosuspend time delay (in seconds) used
 			for newly-detected USB devices (default 2).  This

Documentation/keys.txt

@@ -864,7 +864,7 @@ payload contents" for more information.
     request_key_with_auxdata() respectively.
 
     These two functions return with the key potentially still under
-    construction.  To wait for contruction completion, the following should be
+    construction.  To wait for construction completion, the following should be
     called:
 
 	int wait_for_key_construction(struct key *key, bool intr);

Documentation/kprobes.txt

@@ -172,6 +172,7 @@ architectures:
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
 - arm
+- ppc
 
 3. Configuring Kprobes
 

Documentation/laptops/acer-wmi.txt

@@ -174,8 +174,6 @@ The LED is exposed through the LED subsystem, and can be found in:
 The mail LED is autodetected, so if you don't have one, the LED device won't
 be registered.
 
-If you have a mail LED that is not green, please report this to me.
-
 Backlight
 *********
 

Documentation/laptops/thinkpad-acpi.txt

@@ -1,7 +1,7 @@
 		     ThinkPad ACPI Extras Driver
 
-                            Version 0.20
-                          April 09th, 2008
+                            Version 0.21
+                           May 29th, 2008
 
                Borislav Deianov <borislav@users.sf.net>
              Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -621,7 +621,8 @@ Bluetooth
 ---------
 
 procfs: /proc/acpi/ibm/bluetooth
-sysfs device attribute: bluetooth_enable
+sysfs device attribute: bluetooth_enable (deprecated)
+sysfs rfkill class: switch "tpacpi_bluetooth_sw"
 
 This feature shows the presence and current state of a ThinkPad
 Bluetooth device in the internal ThinkPad CDC slot.
@@ -643,8 +644,12 @@ Sysfs notes:
 		0: disables Bluetooth / Bluetooth is disabled
 		1: enables Bluetooth / Bluetooth is enabled.
 
-	Note: this interface will be probably be superseded by the
-	generic rfkill class, so it is NOT to be considered stable yet.
+	Note: this interface has been superseded by the	generic rfkill
+	class.  It has been deprecated, and it will be removed in year
+	2010.
+
+	rfkill controller switch "tpacpi_bluetooth_sw": refer to
+	Documentation/rfkill.txt for details.
 
 Video output control -- /proc/acpi/ibm/video
 --------------------------------------------
@@ -1374,7 +1379,8 @@ EXPERIMENTAL: WAN
 -----------------
 
 procfs: /proc/acpi/ibm/wan
-sysfs device attribute: wwan_enable
+sysfs device attribute: wwan_enable (deprecated)
+sysfs rfkill class: switch "tpacpi_wwan_sw"
 
 This feature is marked EXPERIMENTAL because the implementation
 directly accesses hardware registers and may not work as expected. USE
@@ -1404,8 +1410,12 @@ Sysfs notes:
 		0: disables WWAN card / WWAN card is disabled
 		1: enables WWAN card / WWAN card is enabled.
 
-	Note: this interface will be probably be superseded by the
-	generic rfkill class, so it is NOT to be considered stable yet.
+	Note: this interface has been superseded by the	generic rfkill
+	class.  It has been deprecated, and it will be removed in year
+	2010.
+
+	rfkill controller switch "tpacpi_wwan_sw": refer to
+	Documentation/rfkill.txt for details.
 
 Multiple Commands, Module Parameters
 ------------------------------------

Documentation/leds-class.txt

@@ -59,7 +59,7 @@ Hardware accelerated blink of LEDs
 
 Some LEDs can be programmed to blink without any CPU interaction. To
 support this feature, a LED driver can optionally implement the
-blink_set() function (see <linux/leds.h>). If implemeted, triggers can
+blink_set() function (see <linux/leds.h>). If implemented, triggers can
 attempt to use it before falling back to software timers. The blink_set()
 function should return 0 if the blink setting is supported, or -EINVAL
 otherwise, which means that LED blinking will be handled by software.

Documentation/lguest/lguest.c

@@ -36,11 +36,13 @@
 #include <sched.h>
 #include <limits.h>
 #include <stddef.h>
+#include <signal.h>
 #include "linux/lguest_launcher.h"
 #include "linux/virtio_config.h"
 #include "linux/virtio_net.h"
 #include "linux/virtio_blk.h"
 #include "linux/virtio_console.h"
+#include "linux/virtio_rng.h"
 #include "linux/virtio_ring.h"
 #include "asm-x86/bootparam.h"
 /*L:110 We can ignore the 39 include files we need for this program, but I do
@@ -64,8 +66,8 @@ typedef uint8_t u8;
 #endif
 /* We can have up to 256 pages for devices. */
 #define DEVICE_PAGES 256
-/* This will occupy 2 pages: it must be a power of 2. */
-#define VIRTQUEUE_NUM 128
+/* This will occupy 3 pages: it must be a power of 2. */
+#define VIRTQUEUE_NUM 256
 
 /*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
  * this, and although I wouldn't recommend it, it works quite nicely here. */
@@ -74,12 +76,19 @@ static bool verbose;
 	do { if (verbose) printf(args); } while(0)
 /*:*/
 
-/* The pipe to send commands to the waker process */
-static int waker_fd;
+/* File descriptors for the Waker. */
+struct {
+	int pipe[2];
+	int lguest_fd;
+} waker_fds;
+
 /* The pointer to the start of guest memory. */
 static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
 static unsigned long guest_limit, guest_max;
+/* The pipe for signal hander to write to. */
+static int timeoutpipe[2];
+static unsigned int timeout_usec = 500;
 
 /* a per-cpu variable indicating whose vcpu is currently running */
 static unsigned int __thread cpu_id;
@@ -155,11 +164,14 @@ struct virtqueue
 	/* Last available index we saw. */
 	u16 last_avail_idx;
 
-	/* The routine to call when the Guest pings us. */
-	void (*handle_output)(int fd, struct virtqueue *me);
+	/* The routine to call when the Guest pings us, or timeout. */
+	void (*handle_output)(int fd, struct virtqueue *me, bool timeout);
 
 	/* Outstanding buffers */
 	unsigned int inflight;
+
+	/* Is this blocked awaiting a timer? */
+	bool blocked;
 };
 
 /* Remember the arguments to the program so we can "reboot" */
@@ -190,6 +202,9 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 	return iov->iov_base;
 }
 
+/* Wrapper for the last available index.  Makes it easier to change. */
+#define lg_last_avail(vq)	((vq)->last_avail_idx)
+
 /* The virtio configuration space is defined to be little-endian.  x86 is
  * little-endian too, but it's nice to be explicit so we have these helpers. */
 #define cpu_to_le16(v16) (v16)
@@ -199,6 +214,33 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 #define le32_to_cpu(v32) (v32)
 #define le64_to_cpu(v64) (v64)
 
+/* Is this iovec empty? */
+static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_iov; i++)
+		if (iov[i].iov_len)
+			return false;
+	return true;
+}
+
+/* Take len bytes from the front of this iovec. */
+static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_iov; i++) {
+		unsigned int used;
+
+		used = iov[i].iov_len < len ? iov[i].iov_len : len;
+		iov[i].iov_base += used;
+		iov[i].iov_len -= used;
+		len -= used;
+	}
+	assert(len == 0);
+}
+
 /* The device virtqueue descriptors are followed by feature bitmasks. */
 static u8 *get_feature_bits(struct device *dev)
 {
@@ -254,6 +296,7 @@ static void *map_zeroed_pages(unsigned int num)
 		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
 	if (addr == MAP_FAILED)
 		err(1, "Mmaping %u pages of /dev/zero", num);
+	close(fd);
 
 	return addr;
 }
@@ -540,69 +583,64 @@ static void add_device_fd(int fd)
  * watch, but handing a file descriptor mask through to the kernel is fairly
  * icky.
  *
- * Instead, we fork off a process which watches the file descriptors and writes
+ * Instead, we clone off a thread which watches the file descriptors and writes
  * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
  * stop running the Guest.  This causes the Launcher to return from the
  * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
  * the LHREQ_BREAK and wake us up again.
  *
  * This, of course, is merely a different *kind* of icky.
+ *
+ * Given my well-known antipathy to threads, I'd prefer to use processes.  But
+ * it's easier to share Guest memory with threads, and trivial to share the
+ * devices.infds as the Launcher changes it.
  */
-static void wake_parent(int pipefd, int lguest_fd)
+static int waker(void *unused)
 {
-	/* Add the pipe from the Launcher to the fdset in the device_list, so
-	 * we watch it, too. */
-	add_device_fd(pipefd);
+	/* Close the write end of the pipe: only the Launcher has it open. */
+	close(waker_fds.pipe[1]);
 
 	for (;;) {
 		fd_set rfds = devices.infds;
 		unsigned long args[] = { LHREQ_BREAK, 1 };
+		unsigned int maxfd = devices.max_infd;
+
+		/* We also listen to the pipe from the Launcher. */
+		FD_SET(waker_fds.pipe[0], &rfds);
+		if (waker_fds.pipe[0] > maxfd)
+			maxfd = waker_fds.pipe[0];
 
 		/* Wait until input is ready from one of the devices. */
-		select(devices.max_infd+1, &rfds, NULL, NULL, NULL);
-		/* Is it a message from the Launcher? */
-		if (FD_ISSET(pipefd, &rfds)) {
-			int fd;
-			/* If read() returns 0, it means the Launcher has
-			 * exited.  We silently follow. */
-			if (read(pipefd, &fd, sizeof(fd)) == 0)
-				exit(0);
-			/* Otherwise it's telling us to change what file
-			 * descriptors we're to listen to.  Positive means
-			 * listen to a new one, negative means stop
-			 * listening. */
-			if (fd >= 0)
-				FD_SET(fd, &devices.infds);
-			else
-				FD_CLR(-fd - 1, &devices.infds);
-		} else /* Send LHREQ_BREAK command. */
-			pwrite(lguest_fd, args, sizeof(args), cpu_id);
+		select(maxfd+1, &rfds, NULL, NULL, NULL);
+
+		/* Message from Launcher? */
+		if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
+			char c;
+			/* If this fails, then assume Launcher has exited.
+			 * Don't do anything on exit: we're just a thread! */
+			if (read(waker_fds.pipe[0], &c, 1) != 1)
+				_exit(0);
+			continue;
+		}
+
+		/* Send LHREQ_BREAK command to snap the Launcher out of it. */
+		pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
 	}
+	return 0;
 }
 
 /* This routine just sets up a pipe to the Waker process. */
-static int setup_waker(int lguest_fd)
-{
-	int pipefd[2], child;
-
-	/* We create a pipe to talk to the Waker, and also so it knows when the
-	 * Launcher dies (and closes pipe). */
-	pipe(pipefd);
-	child = fork();
-	if (child == -1)
-		err(1, "forking");
-
-	if (child == 0) {
-		/* We are the Waker: close the "writing" end of our copy of the
-		 * pipe and start waiting for input. */
-		close(pipefd[1]);
-		wake_parent(pipefd[0], lguest_fd);
-	}
-	/* Close the reading end of our copy of the pipe. */
-	close(pipefd[0]);
+static void setup_waker(int lguest_fd)
+{
+	/* This pipe is closed when Launcher dies, telling Waker. */
+	if (pipe(waker_fds.pipe) != 0)
+		err(1, "Creating pipe for Waker");
 
-	/* Here is the fd used to talk to the waker. */
-	return pipefd[1];
+	/* Waker also needs to know the lguest fd */
+	waker_fds.lguest_fd = lguest_fd;
+
+	if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
+		err(1, "Creating Waker");
 }
 
 /*
@@ -661,19 +699,22 @@ static unsigned get_vq_desc(struct virtqueue *vq,
 			    unsigned int *out_num, unsigned int *in_num)
 {
 	unsigned int i, head;
+	u16 last_avail;
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
-	if ((u16)(vq->vring.avail->idx - vq->last_avail_idx) > vq->vring.num)
+	last_avail = lg_last_avail(vq);
+	if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
 		errx(1, "Guest moved used index from %u to %u",
-		     vq->last_avail_idx, vq->vring.avail->idx);
+		     last_avail, vq->vring.avail->idx);
 
 	/* If there's nothing new since last we looked, return invalid. */
-	if (vq->vring.avail->idx == vq->last_avail_idx)
+	if (vq->vring.avail->idx == last_avail)
 		return vq->vring.num;
 
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
-	head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num];
+	head = vq->vring.avail->ring[last_avail % vq->vring.num];
+	lg_last_avail(vq)++;
 
 	/* If their number is silly, that's a fatal mistake. */
 	if (head >= vq->vring.num)
@@ -821,8 +862,8 @@ static bool handle_console_input(int fd, struct device *dev)
 				unsigned long args[] = { LHREQ_BREAK, 0 };
 				/* Close the fd so Waker will know it has to
 				 * exit. */
-				close(waker_fd);
-				/* Just in case waker is blocked in BREAK, send
+				close(waker_fds.pipe[1]);
+				/* Just in case Waker is blocked in BREAK, send
 				 * unbreak now. */
 				write(fd, args, sizeof(args));
 				exit(2);
@@ -839,7 +880,7 @@ static bool handle_console_input(int fd, struct device *dev)
 
 /* Handling output for console is simple: we just get all the output buffers
  * and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq)
+static void handle_console_output(int fd, struct virtqueue *vq, bool timeout)
 {
 	unsigned int head, out, in;
 	int len;
@@ -854,6 +895,21 @@ static void handle_console_output(int fd, struct virtqueue *vq)
 	}
 }
 
+static void block_vq(struct virtqueue *vq)
+{
+	struct itimerval itm;
+
+	vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+	vq->blocked = true;
+
+	itm.it_interval.tv_sec = 0;
+	itm.it_interval.tv_usec = 0;
+	itm.it_value.tv_sec = 0;
+	itm.it_value.tv_usec = timeout_usec;
+
+	setitimer(ITIMER_REAL, &itm, NULL);
+}
+
 /*
  * The Network
  *
@@ -861,22 +917,34 @@ static void handle_console_output(int fd, struct virtqueue *vq)
  * and write them (ignoring the first element) to this device's file descriptor
  * (/dev/net/tun).
  */
-static void handle_net_output(int fd, struct virtqueue *vq)
+static void handle_net_output(int fd, struct virtqueue *vq, bool timeout)
 {
-	unsigned int head, out, in;
+	unsigned int head, out, in, num = 0;
 	int len;
 	struct iovec iov[vq->vring.num];
+	static int last_timeout_num;
 
 	/* Keep getting output buffers from the Guest until we run out. */
 	while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
 		if (in)
 			errx(1, "Input buffers in output queue?");
-		/* Check header, but otherwise ignore it (we told the Guest we
-		 * supported no features, so it shouldn't have anything
-		 * interesting). */
-		(void)convert(&iov[0], struct virtio_net_hdr);
-		len = writev(vq->dev->fd, iov+1, out-1);
+		len = writev(vq->dev->fd, iov, out);
+		if (len < 0)
+			err(1, "Writing network packet to tun");
 		add_used_and_trigger(fd, vq, head, len);
+		num++;
+	}
+
+	/* Block further kicks and set up a timer if we saw anything. */
+	if (!timeout && num)
+		block_vq(vq);
+
+	if (timeout) {
+		if (num < last_timeout_num)
+			timeout_usec += 10;
+		else if (timeout_usec > 1)
+			timeout_usec--;
+		last_timeout_num = num;
 	}
 }
 
@@ -887,7 +955,6 @@ static bool handle_tun_input(int fd, struct device *dev)
 	unsigned int head, in_num, out_num;
 	int len;
 	struct iovec iov[dev->vq->vring.num];
-	struct virtio_net_hdr *hdr;
 
 	/* First we need a network buffer from the Guests's recv virtqueue. */
 	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
@@ -896,25 +963,23 @@ static bool handle_tun_input(int fd, struct device *dev)
 		 * early, the Guest won't be ready yet.  Wait until the device
 		 * status says it's ready. */
 		/* FIXME: Actually want DRIVER_ACTIVE here. */
-		if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
-			warn("network: no dma buffer!");
+
+		/* Now tell it we want to know if new things appear. */
+		dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+		wmb();
+
 		/* We'll turn this back on if input buffers are registered. */
 		return false;
 	} else if (out_num)
 		errx(1, "Output buffers in network recv queue?");
 
-	/* First element is the header: we set it to 0 (no features). */
-	hdr = convert(&iov[0], struct virtio_net_hdr);
-	hdr->flags = 0;
-	hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
 	/* Read the packet from the device directly into the Guest's buffer. */
-	len = readv(dev->fd, iov+1, in_num-1);
+	len = readv(dev->fd, iov, in_num);
 	if (len <= 0)
 		err(1, "reading network");
 
 	/* Tell the Guest about the new packet. */
-	add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);
+	add_used_and_trigger(fd, dev->vq, head, len);
 
 	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
 		((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
@@ -927,11 +992,18 @@ static bool handle_tun_input(int fd, struct device *dev)
 /*L:215 This is the callback attached to the network and console input
  * virtqueues: it ensures we try again, in case we stopped console or net
  * delivery because Guest didn't have any buffers. */
-static void enable_fd(int fd, struct virtqueue *vq)
+static void enable_fd(int fd, struct virtqueue *vq, bool timeout)
 {
 	add_device_fd(vq->dev->fd);
-	/* Tell waker to listen to it again */
-	write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+	/* Snap the Waker out of its select loop. */
+	write(waker_fds.pipe[1], "", 1);
+}
+
+static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout)
+{
+	/* We don't need to know again when Guest refills receive buffer. */
+	vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+	enable_fd(fd, vq, timeout);
 }
 
 /* When the Guest tells us they updated the status field, we handle it. */
@@ -951,7 +1023,7 @@ static void update_device_status(struct device *dev)
 		for (vq = dev->vq; vq; vq = vq->next) {
 			memset(vq->vring.desc, 0,
 			       vring_size(vq->config.num, getpagesize()));
-			vq->last_avail_idx = 0;
+			lg_last_avail(vq) = 0;
 		}
 	} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
 		warnx("Device %s configuration FAILED", dev->name);
@@ -960,10 +1032,10 @@ static void update_device_status(struct device *dev)
 
 		verbose("Device %s OK: offered", dev->name);
 		for (i = 0; i < dev->desc->feature_len; i++)
-			verbose(" %08x", get_feature_bits(dev)[i]);
+			verbose(" %02x", get_feature_bits(dev)[i]);
 		verbose(", accepted");
 		for (i = 0; i < dev->desc->feature_len; i++)
-			verbose(" %08x", get_feature_bits(dev)
+			verbose(" %02x", get_feature_bits(dev)
 				[dev->desc->feature_len+i]);
 
 		if (dev->ready)
@@ -1000,7 +1072,7 @@ static void handle_output(int fd, unsigned long addr)
 			if (strcmp(vq->dev->name, "console") != 0)
 				verbose("Output to %s\n", vq->dev->name);
 			if (vq->handle_output)
-				vq->handle_output(fd, vq);
+				vq->handle_output(fd, vq, false);
 			return;
 		}
 	}
@@ -1014,6 +1086,29 @@ static void handle_output(int fd, unsigned long addr)
 	      strnlen(from_guest_phys(addr), guest_limit - addr));
 }
 
+static void handle_timeout(int fd)
+{
+	char buf[32];
+	struct device *i;
+	struct virtqueue *vq;
+
+	/* Clear the pipe */
+	read(timeoutpipe[0], buf, sizeof(buf));
+
+	/* Check each device and virtqueue: flush blocked ones. */
+	for (i = devices.dev; i; i = i->next) {
+		for (vq = i->vq; vq; vq = vq->next) {
+			if (!vq->blocked)
+				continue;
+
+			vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+			vq->blocked = false;
+			if (vq->handle_output)
+				vq->handle_output(fd, vq, true);
+		}
+	}
+}
+
 /* This is called when the Waker wakes us up: check for incoming file
  * descriptors. */
 static void handle_input(int fd)
@@ -1024,16 +1119,20 @@ static void handle_input(int fd)
 	for (;;) {
 		struct device *i;
 		fd_set fds = devices.infds;
+		int num;
 
+		num = select(devices.max_infd+1, &fds, NULL, NULL, &poll);
+		/* Could get interrupted */
+		if (num < 0)
+			continue;
 		/* If nothing is ready, we're done. */
-		if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0)
+		if (num == 0)
 			break;
 
 		/* Otherwise, call the device(s) which have readable file
 		 * descriptors and a method of handling them.  */
 		for (i = devices.dev; i; i = i->next) {
 			if (i->handle_input && FD_ISSET(i->fd, &fds)) {
-				int dev_fd;
 				if (i->handle_input(fd, i))
 					continue;
 
@@ -1043,13 +1142,12 @@ static void handle_input(int fd)
 				 * buffers to deliver into.  Console also uses
 				 * it when it discovers that stdin is closed. */
 				FD_CLR(i->fd, &devices.infds);
-				/* Tell waker to ignore it too, by sending a
-				 * negative fd number (-1, since 0 is a valid
-				 * FD number). */
-				dev_fd = -i->fd - 1;
-				write(waker_fd, &dev_fd, sizeof(dev_fd));
 			}
 		}
+
+		/* Is this the timeout fd? */
+		if (FD_ISSET(timeoutpipe[0], &fds))
+			handle_timeout(fd);
 	}
 }
 
@@ -1098,7 +1196,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 /* Each device descriptor is followed by the description of its virtqueues.  We
  * specify how many descriptors the virtqueue is to have. */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
-			  void (*handle_output)(int fd, struct virtqueue *me))
+			  void (*handle_output)(int, struct virtqueue *, bool))
 {
 	unsigned int pages;
 	struct virtqueue **i, *vq = malloc(sizeof(*vq));
@@ -1114,6 +1212,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->last_avail_idx = 0;
 	vq->dev = dev;
 	vq->inflight = 0;
+	vq->blocked = false;
 
 	/* Initialize the configuration. */
 	vq->config.num = num_descs;
@@ -1246,6 +1345,24 @@ static void setup_console(void)
 }
 /*:*/
 
+static void timeout_alarm(int sig)
+{
+	write(timeoutpipe[1], "", 1);
+}
+
+static void setup_timeout(void)
+{
+	if (pipe(timeoutpipe) != 0)
+		err(1, "Creating timeout pipe");
+
+	if (fcntl(timeoutpipe[1], F_SETFL,
+		  fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0)
+		err(1, "Making timeout pipe nonblocking");
+
+	add_device_fd(timeoutpipe[0]);
+	signal(SIGALRM, timeout_alarm);
+}
+
 /*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
@@ -1264,10 +1381,25 @@ static void setup_console(void)
 
 static u32 str2ip(const char *ipaddr)
 {
-	unsigned int byte[4];
+	unsigned int b[4];
 
-	sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
-	return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+	if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
+		errx(1, "Failed to parse IP address '%s'", ipaddr);
+	return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
+}
+
+static void str2mac(const char *macaddr, unsigned char mac[6])
+{
+	unsigned int m[6];
+	if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
+		   &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
+		errx(1, "Failed to parse mac address '%s'", macaddr);
+	mac[0] = m[0];
+	mac[1] = m[1];
+	mac[2] = m[2];
+	mac[3] = m[3];
+	mac[4] = m[4];
+	mac[5] = m[5];
 }
 
 /* This code is "adapted" from libbridge: it attaches the Host end of the
@@ -1288,6 +1420,7 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 		errx(1, "interface %s does not exist!", if_name);
 
 	strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
+	ifr.ifr_name[IFNAMSIZ-1] = '\0';
 	ifr.ifr_ifindex = ifidx;
 	if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
 		err(1, "can't add %s to bridge %s", if_name, br_name);
@@ -1296,64 +1429,90 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 /* This sets up the Host end of the network device with an IP address, brings
  * it up so packets will flow, the copies the MAC address into the hwaddr
  * pointer. */
-static void configure_device(int fd, const char *devname, u32 ipaddr,
-			     unsigned char hwaddr[6])
+static void configure_device(int fd, const char *tapif, u32 ipaddr)
 {
 	struct ifreq ifr;
 	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
 
-	/* Don't read these incantations.  Just cut & paste them like I did! */
 	memset(&ifr, 0, sizeof(ifr));
-	strcpy(ifr.ifr_name, devname);
+	strcpy(ifr.ifr_name, tapif);
+
+	/* Don't read these incantations.  Just cut & paste them like I did! */
 	sin->sin_family = AF_INET;
 	sin->sin_addr.s_addr = htonl(ipaddr);
 	if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
-		err(1, "Setting %s interface address", devname);
+		err(1, "Setting %s interface address", tapif);
 	ifr.ifr_flags = IFF_UP;
 	if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
-		err(1, "Bringing interface %s up", devname);
+		err(1, "Bringing interface %s up", tapif);
+}
+
+static void get_mac(int fd, const char *tapif, unsigned char hwaddr[6])
+{
+	struct ifreq ifr;
+
+	memset(&ifr, 0, sizeof(ifr));
+	strcpy(ifr.ifr_name, tapif);
 
 	/* SIOC stands for Socket I/O Control.  G means Get (vs S for Set
 	 * above).  IF means Interface, and HWADDR is hardware address.
 	 * Simple! */
 	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
-		err(1, "getting hw address for %s", devname);
+		err(1, "getting hw address for %s", tapif);
 	memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
 }
 
-/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
- * routing, but the principle is the same: it uses the "tun" device to inject
- * packets into the Host as if they came in from a normal network card.  We
- * just shunt packets between the Guest and the tun device. */
-static void setup_tun_net(const char *arg)
+static int get_tun_device(char tapif[IFNAMSIZ])
 {
-	struct device *dev;
 	struct ifreq ifr;
-	int netfd, ipfd;
-	u32 ip;
-	const char *br_name = NULL;
-	struct virtio_net_config conf;
+	int netfd;
+
+	/* Start with this zeroed.  Messy but sure. */
+	memset(&ifr, 0, sizeof(ifr));
 
 	/* We open the /dev/net/tun device and tell it we want a tap device.  A
 	 * tap device is like a tun device, only somehow different.  To tell
 	 * the truth, I completely blundered my way through this code, but it
 	 * works now! */
 	netfd = open_or_die("/dev/net/tun", O_RDWR);
-	memset(&ifr, 0, sizeof(ifr));
-	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
 	strcpy(ifr.ifr_name, "tap%d");
 	if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
 		err(1, "configuring /dev/net/tun");
+
+	if (ioctl(netfd, TUNSETOFFLOAD,
+		  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
+		err(1, "Could not set features for tun device");
+
 	/* We don't need checksums calculated for packets coming in this
 	 * device: trust us! */
 	ioctl(netfd, TUNSETNOCSUM, 1);
 
+	memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
+	return netfd;
+}
+
+/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
+ * routing, but the principle is the same: it uses the "tun" device to inject
+ * packets into the Host as if they came in from a normal network card.  We
+ * just shunt packets between the Guest and the tun device. */
+static void setup_tun_net(char *arg)
+{
+	struct device *dev;
+	int netfd, ipfd;
+	u32 ip = INADDR_ANY;
+	bool bridging = false;
+	char tapif[IFNAMSIZ], *p;
+	struct virtio_net_config conf;
+
+	netfd = get_tun_device(tapif);
+
 	/* First we create a new network device. */
 	dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
 
 	/* Network devices need a receive and a send queue, just like
 	 * console. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+	add_virtqueue(dev, VIRTQUEUE_NUM, net_enable_fd);
 	add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
 
 	/* We need a socket to perform the magic network ioctls to bring up the
@@ -1364,28 +1523,56 @@ static void setup_tun_net(const char *arg)
 
 	/* If the command line was --tunnet=bridge:<name> do bridging. */
 	if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
-		ip = INADDR_ANY;
-		br_name = arg + strlen(BRIDGE_PFX);
-		add_to_bridge(ipfd, ifr.ifr_name, br_name);
-	} else /* It is an IP address to set up the device with */
+		arg += strlen(BRIDGE_PFX);
+		bridging = true;
+	}
+
+	/* A mac address may follow the bridge name or IP address */
+	p = strchr(arg, ':');
+	if (p) {
+		str2mac(p+1, conf.mac);
+		*p = '\0';
+	} else {
+		p = arg + strlen(arg);
+		/* None supplied; query the randomly assigned mac. */
+		get_mac(ipfd, tapif, conf.mac);
+	}
+
+	/* arg is now either an IP address or a bridge name */
+	if (bridging)
+		add_to_bridge(ipfd, tapif, arg);
+	else
 		ip = str2ip(arg);
 
-	/* Set up the tun device, and get the mac address for the interface. */
-	configure_device(ipfd, ifr.ifr_name, ip, conf.mac);
+	/* Set up the tun device. */
+	configure_device(ipfd, tapif, ip);
 
 	/* Tell Guest what MAC address to use. */
 	add_feature(dev, VIRTIO_NET_F_MAC);
 	add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
+	/* Expect Guest to handle everything except UFO */
+	add_feature(dev, VIRTIO_NET_F_CSUM);
+	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
+	add_feature(dev, VIRTIO_NET_F_MAC);
+	add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
+	add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
+	add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
+	add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
+	add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
+	add_feature(dev, VIRTIO_NET_F_HOST_ECN);
 	set_config(dev, sizeof(conf), &conf);
 
 	/* We don't need the socket any more; setup is done. */
 	close(ipfd);
 
-	verbose("device %u: tun net %u.%u.%u.%u\n",
-		devices.device_num++,
-		(u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
-	if (br_name)
-		verbose("attached to bridge: %s\n", br_name);
+	devices.device_num++;
+
+	if (bridging)
+		verbose("device %u: tun %s attached to bridge: %s\n",
+			devices.device_num, tapif, arg);
+	else
+		verbose("device %u: tun %s: %s\n",
+			devices.device_num, tapif, arg);
 }
 
 /* Our block (disk) device should be really simple: the Guest asks for a block
@@ -1550,7 +1737,7 @@ static bool handle_io_finish(int fd, struct device *dev)
 }
 
 /* When the Guest submits some I/O, we just need to wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq)
+static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout)
 {
 	struct vblk_info *vblk = vq->dev->priv;
 	char c = 0;
@@ -1621,6 +1808,64 @@ static void setup_block_file(const char *filename)
 	verbose("device %u: virtblock %llu sectors\n",
 		devices.device_num, le64_to_cpu(conf.capacity));
 }
+
+/* Our random number generator device reads from /dev/random into the Guest's
+ * input buffers.  The usual case is that the Guest doesn't want random numbers
+ * and so has no buffers although /dev/random is still readable, whereas
+ * console is the reverse.
+ *
+ * The same logic applies, however. */
+static bool handle_rng_input(int fd, struct device *dev)
+{
+	int len;
+	unsigned int head, in_num, out_num, totlen = 0;
+	struct iovec iov[dev->vq->vring.num];
+
+	/* First we need a buffer from the Guests's virtqueue. */
+	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
+
+	/* If they're not ready for input, stop listening to this file
+	 * descriptor.  We'll start again once they add an input buffer. */
+	if (head == dev->vq->vring.num)
+		return false;
+
+	if (out_num)
+		errx(1, "Output buffers in rng?");
+
+	/* This is why we convert to iovecs: the readv() call uses them, and so
+	 * it reads straight into the Guest's buffer.  We loop to make sure we
+	 * fill it. */
+	while (!iov_empty(iov, in_num)) {
+		len = readv(dev->fd, iov, in_num);
+		if (len <= 0)
+			err(1, "Read from /dev/random gave %i", len);
+		iov_consume(iov, in_num, len);
+		totlen += len;
+	}
+
+	/* Tell the Guest about the new input. */
+	add_used_and_trigger(fd, dev->vq, head, totlen);
+
+	/* Everything went OK! */
+	return true;
+}
+
+/* And this creates a "hardware" random number device for the Guest. */
+static void setup_rng(void)
+{
+	struct device *dev;
+	int fd;
+
+	fd = open_or_die("/dev/random", O_RDONLY);
+
+	/* The device responds to return from I/O thread. */
+	dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input);
+
+	/* The device has one virtqueue, where the Guest places inbufs. */
+	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+
+	verbose("device %u: rng\n", devices.device_num++);
+}
 /* That's the end of device setup. */
 
 /*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
@@ -1628,11 +1873,12 @@ static void __attribute__((noreturn)) restart_guest(void)
 {
 	unsigned int i;
 
-	/* Closing pipes causes the Waker thread and io_threads to die, and
-	 * closing /dev/lguest cleans up the Guest.  Since we don't track all
-	 * open fds, we simply close everything beyond stderr. */
+	/* Since we don't track all open fds, we simply close everything beyond
+	 * stderr. */
 	for (i = 3; i < FD_SETSIZE; i++)
 		close(i);
+
+	/* The exec automatically gets rid of the I/O and Waker threads. */
 	execv(main_args[0], main_args);
 	err(1, "Could not exec %s", main_args[0]);
 }
@@ -1663,7 +1909,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
 		/* ERESTART means that we need to reboot the guest */
 		} else if (errno == ERESTART) {
 			restart_guest();
-		/* EAGAIN means the Waker wanted us to look at some input.
+		/* EAGAIN means a signal (timeout).
 		 * Anything else means a bug or incompatible change. */
 		} else if (errno != EAGAIN)
 			err(1, "Running guest failed");
@@ -1691,13 +1937,14 @@ static struct option opts[] = {
 	{ "verbose", 0, NULL, 'v' },
 	{ "tunnet", 1, NULL, 't' },
 	{ "block", 1, NULL, 'b' },
+	{ "rng", 0, NULL, 'r' },
 	{ "initrd", 1, NULL, 'i' },
 	{ NULL },
 };
 static void usage(void)
 {
 	errx(1, "Usage: lguest [--verbose] "
-	     "[--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
+	     "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n"
 	     "|--block=<filename>|--initrd=<filename>]...\n"
 	     "<mem-in-mb> vmlinux [args...]");
 }
@@ -1765,6 +2012,9 @@ int main(int argc, char *argv[])
 		case 'b':
 			setup_block_file(optarg);
 			break;
+		case 'r':
+			setup_rng();
+			break;
 		case 'i':
 			initrd_name = optarg;
 			break;
@@ -1783,6 +2033,9 @@ int main(int argc, char *argv[])
 	/* We always have a console device */
 	setup_console();
 
+	/* We can timeout waiting for Guest network transmit. */
+	setup_timeout();
+
 	/* Now we load the kernel */
 	start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
 
@@ -1826,10 +2079,10 @@ int main(int argc, char *argv[])
 	 * /dev/lguest file descriptor. */
 	lguest_fd = tell_kernel(pgdir, start);
 
-	/* We fork off a child process, which wakes the Launcher whenever one
-	 * of the input file descriptors needs attention.  We call this the
-	 * Waker, and we'll cover it in a moment. */
-	waker_fd = setup_waker(lguest_fd);
+	/* We clone off a thread, which wakes the Launcher whenever one of the
+	 * input file descriptors needs attention.  We call this the Waker, and
+	 * we'll cover it in a moment. */
+	setup_waker(lguest_fd);
 
 	/* Finally, run the Guest.  This doesn't return. */
 	run_guest(lguest_fd);

Documentation/local_ops.txt

@@ -36,7 +36,7 @@ It can be done by slightly modifying the standard atomic operations : only
 their UP variant must be kept. It typically means removing LOCK prefix (on
 i386 and x86_64) and any SMP sychronization barrier. If the architecture does
 not have a different behavior between SMP and UP, including asm-generic/local.h
-in your archtecture's local.h is sufficient.
+in your architecture's local.h is sufficient.
 
 The local_t type is defined as an opaque signed long by embedding an
 atomic_long_t inside a structure. This is made so a cast from this type to a

Documentation/md.txt

@@ -236,6 +236,11 @@ All md devices contain:
      writing the word for the desired state, however some states
      cannot be explicitly set, and some transitions are not allowed.
 
+     Select/poll works on this file.  All changes except between
+     	active_idle and active (which can be frequent and are not
+	very interesting) are notified.  active->active_idle is
+	reported if the metadata is externally managed.
+
      clear
          No devices, no size, no level
          Writing is equivalent to STOP_ARRAY ioctl
@@ -292,6 +297,10 @@ Each directory contains:
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
+	      blocked  - device has failed, metadata is "external",
+	                 and the failure hasn't been acknowledged yet.
+			 Writes that would write to this device if
+			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
@@ -301,6 +310,12 @@ Each directory contains:
 	Writing "remove" removes the device from the array.
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
+	Writing "blocked" sets the "blocked" flag.
+	Writing "-blocked" clear the "blocked" flag and allows writes
+		to complete.
+
+	This file responds to select/poll. Any change to 'faulty'
+	or 'blocked' causes an event.
 
       errors
 	An approximate count of read errors that have been detected on
@@ -332,7 +347,7 @@ Each directory contains:
         for storage of data.  This will normally be the same as the
 	component_size.  This can be written while assembling an
         array.  If a value less than the current component_size is
-        written, component_size will be reduced to this value.
+        written, it will be rejected.
 
 
 An active md device will also contain and entry for each active device
@@ -381,6 +396,19 @@ also have
 	'check' and 'repair' will start the appropriate process
            providing the current state is 'idle'.
 
+      This file responds to select/poll.  Any important change in the value
+      triggers a poll event.  Sometimes the value will briefly be
+      "recover" if a recovery seems to be needed, but cannot be
+      achieved. In that case, the transition to "recover" isn't
+      notified, but the transition away is.
+
+   degraded
+      This contains a count of the number of devices by which the
+      arrays is degraded.  So an optimal array with show '0'.  A
+      single failed/missing drive will show '1', etc.
+      This file responds to select/poll, any increase or decrease
+      in the count of missing devices will trigger an event.
+
    mismatch_count
       When performing 'check' and 'repair', and possibly when
       performing 'resync', md will count the number of errors that are

Documentation/moxa-smartio

@@ -1,14 +1,22 @@
 =============================================================================
-
-	MOXA Smartio Family Device Driver Ver 1.1 Installation Guide
-		    for Linux Kernel 2.2.x and 2.0.3x
-	       Copyright (C) 1999, Moxa Technologies Co, Ltd.
+          MOXA Smartio/Industio Family Device Driver Installation Guide
+		    for Linux Kernel 2.4.x, 2.6.x
+	       Copyright (C) 2008, Moxa Inc.
 =============================================================================
+Date: 01/21/2008
+
 Content
 
 1. Introduction
 2. System Requirement
 3. Installation
+   3.1 Hardware installation
+   3.2 Driver files
+   3.3 Device naming convention
+   3.4 Module driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x.
+   3.6 Custom configuration
+   3.7 Verify driver installation
 4. Utilities
 5. Setserial
 6. Troubleshooting
@@ -16,27 +24,48 @@ Content
 -----------------------------------------------------------------------------
 1. Introduction
 
-   The Smartio family Linux driver, Ver. 1.1, supports following multiport
+   The Smartio/Industio/UPCI family Linux driver supports following multiport
    boards.
 
-    -C104P/H/HS, C104H/PCI, C104HS/PCI, CI-104J 4 port multiport board.
-    -C168P/H/HS, C168H/PCI 8 port multiport board.
-
-   This driver has been modified a little and cleaned up from the Moxa
-   contributed driver code and merged into Linux 2.2.14pre. In particular
-   official major/minor numbers have been assigned which are different to
-   those the original Moxa supplied driver used.
+    - 2 ports multiport board
+	CP-102U, CP-102UL, CP-102UF
+	CP-132U-I, CP-132UL,
+	CP-132, CP-132I, CP132S, CP-132IS,
+	CI-132, CI-132I, CI-132IS,
+	(C102H, C102HI, C102HIS, C102P, CP-102, CP-102S)
+
+    - 4 ports multiport board
+	CP-104EL,
+	CP-104UL, CP-104JU,
+	CP-134U, CP-134U-I,
+	C104H/PCI, C104HS/PCI,
+	CP-114, CP-114I, CP-114S, CP-114IS, CP-114UL,
+	C104H, C104HS,
+	CI-104J, CI-104JS,
+	CI-134, CI-134I, CI-134IS,
+	(C114HI, CT-114I, C104P)
+	POS-104UL,
+	CB-114,
+	CB-134I
+
+    - 8 ports multiport board
+	CP-118EL, CP-168EL,
+	CP-118U, CP-168U,
+	C168H/PCI,
+	C168H, C168HS,
+	(C168P),
+	CB-108
 
    This driver and installation procedure have been developed upon Linux Kernel
-   2.2.5 and backward compatible to 2.0.3x. This driver supports Intel x86 and
-   Alpha hardware platform. In order to maintain compatibility, this version
-   has also been properly tested with RedHat, OpenLinux, TurboLinux and
-   S.u.S.E Linux. However, if compatibility problem occurs, please contact
-   Moxa at support@moxa.com.tw.
+   2.4.x and 2.6.x. This driver supports Intel x86 hardware platform. In order
+   to maintain compatibility, this version has also been properly tested with
+   RedHat, Mandrake, Fedora and S.u.S.E Linux. However, if compatibility problem
+   occurs, please contact Moxa at support@moxa.com.tw.
 
    In addition to device driver, useful utilities are also provided in this
    version. They are
-    - msdiag     Diagnostic program for detecting installed Moxa Smartio boards.
+    - msdiag     Diagnostic program for displaying installed Moxa
+                 Smartio/Industio boards.
     - msmon      Monitor program to observe data count and line status signals.
     - msterm     A simple terminal program which is useful in testing serial
 	         ports.
@@ -47,8 +76,7 @@ Content
    GNU General Public License in this version. Please refer to GNU General
    Public License announcement in each source code file for more detail.
 
-   In Moxa's ftp sites, you may always find latest driver at
-   ftp://ftp.moxa.com  or ftp://ftp.moxa.com.tw.
+   In Moxa's Web sites, you may always find latest driver at http://web.moxa.com.
 
    This version of driver can be installed as Loadable Module (Module driver)
    or built-in into kernel (Static driver). You may refer to following
@@ -61,18 +89,27 @@ Content
 
 -----------------------------------------------------------------------------
 2. System Requirement
-   - Hardware platform: Intel x86 or Alpha machine
-   - Kernel version: 2.0.3x or 2.2.x
+   - Hardware platform: Intel x86 machine
+   - Kernel version: 2.4.x or 2.6.x
    - gcc version 2.72 or later
    - Maximum 4 boards can be installed in combination
 
 -----------------------------------------------------------------------------
 3. Installation
 
+   3.1 Hardware installation
+   3.2 Driver files
+   3.3 Device naming convention
+   3.4 Module driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x, 2.6.x.
+   3.6 Custom configuration
+   3.7 Verify driver installation
+
+
    3.1 Hardware installation
 
-       There are two types of buses, ISA and PCI, for Smartio family multiport
-       board.
+       There are two types of buses, ISA and PCI, for Smartio/Industio
+       family multiport board.
 
        ISA board
        ---------
@@ -81,47 +118,57 @@ Content
        installation procedure in User's Manual before proceed any further.
        Please make sure the JP1 is open after the ISA board is set properly.
 
-       PCI board
-       ---------
+       PCI/UPCI board
+       --------------
        You may need to adjust IRQ usage in BIOS to avoid from IRQ conflict
        with other ISA devices. Please refer to hardware installation
        procedure in User's Manual in advance.
 
-       IRQ Sharing
+       PCI IRQ Sharing
        -----------
        Each port within the same multiport board shares the same IRQ. Up to
-       4 Moxa Smartio Family multiport boards can be installed together on
-       one system and they can share the same IRQ.
+       4 Moxa Smartio/Industio PCI Family multiport boards can be installed
+       together on one system and they can share the same IRQ.
+
 
-   3.2 Driver files and device naming convention
+   3.2 Driver files
 
        The driver file may be obtained from ftp, CD-ROM or floppy disk. The
        first step, anyway, is to copy driver file "mxser.tgz" into specified
        directory. e.g. /moxa. The execute commands as below.
 
+       # cd /
+       # mkdir moxa
        # cd /moxa
-       # tar xvf /dev/fd0 
+       # tar xvf /dev/fd0
+
        or
+
+       # cd /
+       # mkdir moxa
        # cd /moxa
        # cp /mnt/cdrom/<driver directory>/mxser.tgz .
        # tar xvfz mxser.tgz
 
+
+   3.3 Device naming convention
+
        You may find all the driver and utilities files in /moxa/mxser.
        Following installation procedure depends on the model you'd like to
-       run the driver. If you prefer module driver, please refer to 3.3.
-       If static driver is required, please refer to 3.4.
+       run the driver. If you prefer module driver, please refer to 3.4.
+       If static driver is required, please refer to 3.5.
 
        Dialin and callout port
        -----------------------
-       This driver remains traditional serial device properties. There're
+       This driver remains traditional serial device properties. There are
        two special file name for each serial port. One is dial-in port
        which is named "ttyMxx". For callout port, the naming convention
        is "cumxx".
 
        Device naming when more than 2 boards installed
        -----------------------------------------------
-       Naming convention for each Smartio multiport board is pre-defined
-       as below.
+       Naming convention for each Smartio/Industio multiport board is
+       pre-defined as below.
 
        Board Num.	 Dial-in Port	      Callout port
        1st board	ttyM0  - ttyM7	      cum0  - cum7
@@ -129,6 +176,12 @@ Content
        3rd board	ttyM16 - ttyM23       cum16 - cum23
        4th board	ttyM24 - ttym31       cum24 - cum31
 
+
+       !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+       Under Kernel 2.6 the cum Device is Obsolete. So use ttyM*
+       device instead.
+       !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+
        Board sequence
        --------------
        This driver will activate ISA boards according to the parameter set
@@ -138,69 +191,131 @@ Content
        For PCI boards, their sequence will be after ISA boards and C168H/PCI
        has higher priority than C104H/PCI boards.
 
-   3.3 Module driver configuration
+   3.4 Module driver configuration
        Module driver is easiest way to install. If you prefer static driver
        installation, please skip this paragraph.
-       1. Find "Makefile" in /moxa/mxser, then run
 
-	  # make install
+
+       ------------- Prepare to use the MOXA driver--------------------
+       3.4.1 Create tty device with correct major number
+          Before using MOXA driver, your system must have the tty devices
+          which are created with driver's major number. We offer one shell
+          script "msmknod" to simplify the procedure.
+          This step is only needed to be executed once. But you still
+          need to do this procedure when:
+          a. You change the driver's major number. Please refer the "3.7"
+             section.
+          b. Your total installed MOXA boards number is changed. Maybe you
+             add/delete one MOXA board.
+          c. You want to change the tty name. This needs to modify the
+             shell script "msmknod"
+
+          The procedure is:
+	  # cd /moxa/mxser/driver
+	  # ./msmknod
+
+          This shell script will require the major number for dial-in
+          device and callout device to create tty device. You also need
+          to specify the total installed MOXA board number. Default major
+          numbers for dial-in device and callout device are 30, 35. If
+          you need to change to other number, please refer section "3.7"
+          for more detailed procedure.
+          Msmknod will delete any special files occupying the same device
+          naming.
+
+       3.4.2 Build the MOXA driver and utilities
+          Before using the MOXA driver and utilities, you need compile the
+          all the source code. This step is only need to be executed once.
+          But you still re-compile the source code if you modify the source
+          code. For example, if you change the driver's major number (see
+          "3.7" section), then you need to do this step again.
+
+          Find "Makefile" in /moxa/mxser, then run
+
+	  # make clean; make install
+
+          !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!
+	  For Red Hat 9, Red Hat Enterprise Linux AS3/ES3/WS3 & Fedora Core1:
+	  # make clean; make installsp1
+
+	  For Red Hat Enterprise Linux AS4/ES4/WS4:
+	  # make clean; make installsp2
+          !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!
 
 	  The driver files "mxser.o" and utilities will be properly compiled
-	  and copied to system directories respectively.Then run
+	  and copied to system directories respectively.
 
-	  # insmod mxser
+       ------------- Load MOXA driver--------------------
+       3.4.3 Load the MOXA driver
 
-	  to activate the modular driver. You may run "lsmod" to check
-	  if "mxser.o" is activated.
+	  # modprobe mxser <argument>
 
-       2. Create special files by executing "msmknod".
-	  # cd /moxa/mxser/driver
-	  # ./msmknod
+	  will activate the module driver. You may run "lsmod" to check
+	  if "mxser" is activated. If the MOXA board is ISA board, the
+          <argument> is needed. Please refer to section "3.4.5" for more
+          information.
+
+
+       ------------- Load MOXA driver on boot --------------------
+       3.4.4 For the above description, you may manually execute
+          "modprobe mxser" to activate this driver and run
+	  "rmmod mxser" to remove it.
+          However, it's better to have a boot time configuration to
+          eliminate manual operation. Boot time configuration can be
+          achieved by rc file. We offer one "rc.mxser" file to simplify
+          the procedure under "moxa/mxser/driver".
 
-	  Default major numbers for dial-in device and callout device are
-	  174, 175. Msmknod will delete any special files occupying the same
-	  device naming.
+          But if you use ISA board, please modify the "modprobe ..." command
+          to add the argument (see "3.4.5" section). After modifying the
+          rc.mxser, please try to execute "/moxa/mxser/driver/rc.mxser"
+          manually to make sure the modification is ok. If any error
+          encountered, please try to modify again. If the modification is
+          completed, follow the below step.
 
-       3. Up to now, you may manually execute "insmod mxser" to activate
-	  this driver and run "rmmod mxser" to remove it. However, it's
-	  better to have a boot time configuration to eliminate manual
-	  operation.
-	  Boot time configuration can be achieved by rc file. Run following
-	  command for setting rc files.
+	  Run following command for setting rc files.
 
 	  # cd /moxa/mxser/driver
 	  # cp ./rc.mxser /etc/rc.d
 	  # cd /etc/rc.d
 
-	  You may have to modify part of the content in rc.mxser to specify
-          parameters for ISA board. Please refer to rc.mxser for more detail.
-          Find "rc.serial". If "rc.serial" doesn't exist, create it by vi.
-	  Add "rc.mxser" in last line. Next, open rc.local by vi
-	  and append following content.
+	  Check "rc.serial" is existed or not. If "rc.serial" doesn't exist,
+	  create it by vi, run "chmod 755 rc.serial" to change the permission.
+	  Add "/etc/rc.d/rc.mxser" in last line,
 
-	  if [ -f /etc/rc.d/rc.serial ]; then
-	     sh /etc/rc.d/rc.serial
-	  fi
+          Reboot and check if moxa.o activated by "lsmod" command.
 
-       4. Reboot and check if mxser.o activated by "lsmod" command.
-       5. If you'd like to drive Smartio ISA boards in the system, you'll
-	  have to add parameter to specify CAP address of given board while
-          activating "mxser.o". The format for parameters are as follows.
+       3.4.5. If you'd like to drive Smartio/Industio ISA boards in the system,
+          you'll have to add parameter to specify CAP address of given
+	  board while activating "mxser.o". The format for parameters are
+	  as follows.
 
-	  insmod mxser ioaddr=0x???,0x???,0x???,0x???
+	  modprobe mxser ioaddr=0x???,0x???,0x???,0x???
 				|      |     |	  |
 				|      |     |	  +- 4th ISA board
 				|      |     +------ 3rd ISA board
 				|      +------------ 2nd ISA board
 				+------------------- 1st ISA board
 
-   3.4 Static driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x
+
+       Note: To use static driver, you must install the linux kernel
+             source package.
+
+       3.5.1 Backup the built-in driver in the kernel.
+          # cd /usr/src/linux/drivers/char
+          # mv mxser.c mxser.c.old
+
+          For Red Hat 7.x user, you need to create link:
+          # cd /usr/src
+          # ln -s linux-2.4 linux
 
-       1. Create link
+       3.5.2 Create link
 	  # cd /usr/src/linux/drivers/char
 	  # ln -s /moxa/mxser/driver/mxser.c mxser.c
 
-       2. Add CAP address list for ISA boards
+       3.5.3 Add CAP address list for ISA boards. For PCI boards user,
+          please skip this step.
+
 	  In module mode, the CAP address for ISA board is given by
 	  parameter. In static driver configuration, you'll have to
 	  assign it within driver's source code. If you will not
@@ -222,73 +337,55 @@ Content
 	     static int mxserBoardCAP[]
 	     = {0x280, 0x180, 0x00, 0x00};
 
-       3. Modify tty_io.c
-	  # cd /usr/src/linux/drivers/char/
-	  # vi tty_io.c
-	    Find pty_init(), insert "mxser_init()" as
+       3.5.4 Setup kernel configuration
 
-	    pty_init();
-	    mxser_init();
+          Configure the kernel:
 
-       4. Modify tty.h
-	  # cd /usr/src/linux/include/linux
-	  # vi tty.h
-	    Find extern int tty_init(void), insert "mxser_init()" as
+            # cd /usr/src/linux
+            # make menuconfig
 
-	    extern int tty_init(void);
-	    extern int mxser_init(void);
-     
-       5. Modify Makefile
-	  # cd /usr/src/linux/drivers/char
-	  # vi Makefile
-	    Find L_OBJS := tty_io.o ...... random.o, add
-	    "mxser.o" at last of this line as
-	    L_OBJS := tty_io.o ....... mxser.o
+          You will go into a menu-driven system. Please select [Character
+          devices][Non-standard serial port support], enable the [Moxa
+          SmartIO support] driver with "[*]" for built-in (not "[M]"), then
+          select [Exit] to exit this program.
 
-       6. Rebuild kernel
-	  The following are for Linux kernel rebuilding,for your reference only.
+       3.5.5 Rebuild kernel
+	  The following are for Linux kernel rebuilding, for your
+          reference only.
 	  For appropriate details, please refer to the Linux document.
 
-	  If 'lilo' utility is installed, please use 'make zlilo' to rebuild
-	  kernel. If 'lilo' is not installed, please follow the following steps.
-
 	   a. cd /usr/src/linux
-	   b. make clean			     /* take a few minutes */
-	   c. make bzImage		   /* take probably 10-20 minutes */
-	   d. Backup original boot kernel.		  /* optional step */
-	   e. cp /usr/src/linux/arch/i386/boot/bzImage /boot/vmlinuz
+	   b. make clean	     /* take a few minutes */
+	   c. make dep		     /* take a few minutes */
+	   d. make bzImage	     /* take probably 10-20 minutes */
+	   e. make install	     /* copy boot image to correct position */
 	   f. Please make sure the boot kernel (vmlinuz) is in the
-	      correct position. If you use 'lilo' utility, you should
-	      check /etc/lilo.conf 'image' item specified the path
-	      which is the 'vmlinuz' path, or you will load wrong
-	      (or old) boot kernel image (vmlinuz).
-	   g. chmod 400 /vmlinuz
-	   h. lilo
-	   i. rdev -R /vmlinuz 1
-	   j. sync
-
-	  Note that if the result of "make zImage" is ERROR, then you have to
-	  go back to Linux configuration Setup. Type "make config" in directory
-	  /usr/src/linux or "setup".
-
-	  Since system include file, /usr/src/linux/include/linux/interrupt.h,
-	  is modified each time the MOXA driver is installed, kernel rebuilding
-	  is inevitable. And it takes about 10 to 20 minutes depends on the
-	  machine.
-
-       7. Make utility
-	  # cd /moxa/mxser/utility
-	  # make install
-       
-       8. Make special file
+	      correct position.
+	   g. If you use 'lilo' utility, you should check /etc/lilo.conf
+	      'image' item specified the path which is the 'vmlinuz' path,
+	      or you will load wrong (or old) boot kernel image (vmlinuz).
+	      After checking /etc/lilo.conf, please run "lilo".
+
+	  Note that if the result of "make bzImage" is ERROR, then you have to
+	  go back to Linux configuration Setup. Type "make menuconfig" in
+          directory /usr/src/linux.
+
+
+       3.5.6 Make tty device and special file
           # cd /moxa/mxser/driver
           # ./msmknod
 
-       9. Reboot
+       3.5.7 Make utility
+	  # cd /moxa/mxser/utility
+	  # make clean; make install
+
+       3.5.8 Reboot
 
-   3.5 Custom configuration
+
+
+   3.6 Custom configuration
        Although this driver already provides you default configuration, you
-       still can change the device name and major number.The instruction to
+       still can change the device name and major number. The instruction to
        change these parameters are shown as below.
 
        Change Device name
@@ -306,33 +403,37 @@ Content
        2 free major numbers for this driver. There are 3 steps to change
        major numbers.
 
-       1. Find free major numbers
+       3.6.1 Find free major numbers
 	  In /proc/devices, you may find all the major numbers occupied
 	  in the system. Please select 2 major numbers that are available.
 	  e.g. 40, 45.
-       2. Create special files
+       3.6.2 Create special files
 	  Run /moxa/mxser/driver/msmknod to create special files with
 	  specified major numbers.
-       3. Modify driver with new major number
+       3.6.3 Modify driver with new major number
 	  Run vi to open /moxa/mxser/driver/mxser.c. Locate the line
 	  contains "MXSERMAJOR". Change the content as below.
 	  #define	  MXSERMAJOR		  40
 	  #define	  MXSERCUMAJOR		  45
-       4. Run # make install in /moxa/mxser/driver.
+       3.6.4 Run "make clean; make install" in /moxa/mxser/driver.
 
-   3.6 Verify driver installation
+   3.7 Verify driver installation
        You may refer to /var/log/messages to check the latest status
        log reported by this driver whenever it's activated.
+
 -----------------------------------------------------------------------------
 4. Utilities
    There are 3 utilities contained in this driver. They are msdiag, msmon and
    msterm. These 3 utilities are released in form of source code. They should
    be compiled into executable file and copied into /usr/bin.
 
+   Before using these utilities, please load driver (refer 3.4 & 3.5) and
+   make sure you had run the "msmknod" utility.
+
    msdiag - Diagnostic
    --------------------
-   This utility provides the function to detect what Moxa Smartio multiport
-   board exists in the system.
+   This utility provides the function to display what Moxa Smartio/Industio
+   board found by driver in the system.
 
    msmon - Port Monitoring
    -----------------------
@@ -353,12 +454,13 @@ Content
    application, for example, sending AT command to a modem connected to the
    port or used as a terminal for login purpose. Note that this is only a
    dumb terminal emulation without handling full screen operation.
+
 -----------------------------------------------------------------------------
 5. Setserial
 
    Supported Setserial parameters are listed as below.
 
-   uart 	  set UART type(16450-->disable FIFO, 16550A-->enable FIFO)
+   uart		  set UART type(16450-->disable FIFO, 16550A-->enable FIFO)
    close_delay	  set the amount of time(in 1/100 of a second) that DTR
 		  should be kept low while being closed.
    closing_wait   set the amount of time(in 1/100 of a second) that the
@@ -366,7 +468,13 @@ Content
 		  being closed, before the receiver is disable.
    spd_hi	  Use  57.6kb  when  the application requests 38.4kb.
    spd_vhi	  Use  115.2kb	when  the application requests 38.4kb.
+   spd_shi	  Use  230.4kb	when  the application requests 38.4kb.
+   spd_warp	  Use  460.8kb	when  the application requests 38.4kb.
    spd_normal	  Use  38.4kb  when  the application requests 38.4kb.
+   spd_cust	  Use  the custom divisor to set the speed when  the
+		  application requests 38.4kb.
+   divisor	  This option set the custom divison.
+   baud_base	  This option set the base baud rate.
 
 -----------------------------------------------------------------------------
 6. Troubleshooting
@@ -375,8 +483,9 @@ Content
    possible. If all the possible solutions fail, please contact our technical
    support team to get more help.
 
-   Error msg: More than 4 Moxa Smartio family boards found. Fifth board and
-	      after are ignored.
+
+   Error msg: More than 4 Moxa Smartio/Industio family boards found. Fifth board
+              and after are ignored.
    Solution:
    To avoid this problem, please unplug fifth and after board, because Moxa
    driver supports up to 4 boards.
@@ -384,7 +493,7 @@ Content
    Error msg: Request_irq fail, IRQ(?) may be conflict with another device.
    Solution:
    Other PCI or ISA devices occupy the assigned IRQ. If you are not sure
-   which device causes the situation,please check /proc/interrupts to find
+   which device causes the situation, please check /proc/interrupts to find
    free IRQ and simply change another free IRQ for Moxa board.
 
    Error msg: Board #: C1xx Series(CAP=xxx) interrupt number invalid.
@@ -397,15 +506,18 @@ Content
    Moxa ISA board needs an interrupt vector.Please refer to user's manual
    "Hardware Installation" chapter to set interrupt vector.
 
-   Error msg: Couldn't install MOXA Smartio family driver!
+   Error msg: Couldn't install MOXA Smartio/Industio family driver!
    Solution:
    Load Moxa driver fail, the major number may conflict with other devices.
-   Please refer to previous section 3.5 to change a free major number for
+   Please refer to previous section 3.7 to change a free major number for
    Moxa driver.
 
-   Error msg: Couldn't install MOXA Smartio family callout driver!
+   Error msg: Couldn't install MOXA Smartio/Industio family callout driver!
    Solution:
    Load Moxa callout driver fail, the callout device major number may
-   conflict with other devices. Please refer to previous section 3.5 to
+   conflict with other devices. Please refer to previous section 3.7 to
    change a free callout device major number for Moxa driver.
+
+
 -----------------------------------------------------------------------------
+

Documentation/networking/bonding.txt

@@ -289,35 +289,73 @@ downdelay
 fail_over_mac
 
 	Specifies whether active-backup mode should set all slaves to
-	the same MAC address (the traditional behavior), or, when
-	enabled, change the bond's MAC address when changing the
-	active interface (i.e., fail over the MAC address itself).
-
-	Fail over MAC is useful for devices that cannot ever alter
-	their MAC address, or for devices that refuse incoming
-	broadcasts with their own source MAC (which interferes with
-	the ARP monitor).
-
-	The down side of fail over MAC is that every device on the
-	network must be updated via gratuitous ARP, vs. just updating
-	a switch or set of switches (which often takes place for any
-	traffic, not just ARP traffic, if the switch snoops incoming
-	traffic to update its tables) for the traditional method.  If
-	the gratuitous ARP is lost, communication may be disrupted.
-
-	When fail over MAC is used in conjuction with the mii monitor,
-	devices which assert link up prior to being able to actually
-	transmit and receive are particularly susecptible to loss of
-	the gratuitous ARP, and an appropriate updelay setting may be
-	required.
-
-	A value of 0 disables fail over MAC, and is the default.  A
-	value of 1 enables fail over MAC.  This option is enabled
-	automatically if the first slave added cannot change its MAC
-	address.  This option may be modified via sysfs only when no
-	slaves are present in the bond.
-
-	This option was added in bonding version 3.2.0.
+	the same MAC address at enslavement (the traditional
+	behavior), or, when enabled, perform special handling of the
+	bond's MAC address in accordance with the selected policy.
+
+	Possible values are:
+
+	none or 0
+
+		This setting disables fail_over_mac, and causes
+		bonding to set all slaves of an active-backup bond to
+		the same MAC address at enslavement time.  This is the
+		default.
+
+	active or 1
+
+		The "active" fail_over_mac policy indicates that the
+		MAC address of the bond should always be the MAC
+		address of the currently active slave.  The MAC
+		address of the slaves is not changed; instead, the MAC
+		address of the bond changes during a failover.
+
+		This policy is useful for devices that cannot ever
+		alter their MAC address, or for devices that refuse
+		incoming broadcasts with their own source MAC (which
+		interferes with the ARP monitor).
+
+		The down side of this policy is that every device on
+		the network must be updated via gratuitous ARP,
+		vs. just updating a switch or set of switches (which
+		often takes place for any traffic, not just ARP
+		traffic, if the switch snoops incoming traffic to
+		update its tables) for the traditional method.  If the
+		gratuitous ARP is lost, communication may be
+		disrupted.
+
+		When this policy is used in conjuction with the mii
+		monitor, devices which assert link up prior to being
+		able to actually transmit and receive are particularly
+		susecptible to loss of the gratuitous ARP, and an
+		appropriate updelay setting may be required.
+
+	follow or 2
+
+		The "follow" fail_over_mac policy causes the MAC
+		address of the bond to be selected normally (normally
+		the MAC address of the first slave added to the bond).
+		However, the second and subsequent slaves are not set
+		to this MAC address while they are in a backup role; a
+		slave is programmed with the bond's MAC address at
+		failover time (and the formerly active slave receives
+		the newly active slave's MAC address).
+
+		This policy is useful for multiport devices that
+		either become confused or incur a performance penalty
+		when multiple ports are programmed with the same MAC
+		address.
+
+
+	The default policy is none, unless the first slave cannot
+	change its MAC address, in which case the active policy is
+	selected by default.
+
+	This option may be modified via sysfs only when no slaves are
+	present in the bond.
+
+	This option was added in bonding version 3.2.0.  The "follow"
+	policy was added in bonding version 3.3.0.
 
 lacp_rate
 
@@ -338,7 +376,8 @@ max_bonds
 	Specifies the number of bonding devices to create for this
 	instance of the bonding driver.  E.g., if max_bonds is 3, and
 	the bonding driver is not already loaded, then bond0, bond1
-	and bond2 will be created.  The default value is 1.
+	and bond2 will be created.  The default value is 1.  Specifying
+	a value of 0 will load bonding, but will not create any devices.
 
 miimon
 
@@ -501,6 +540,17 @@ mode
 		swapped with the new curr_active_slave that was
 		chosen.
 
+num_grat_arp
+
+	Specifies the number of gratuitous ARPs to be issued after a
+	failover event.  One gratuitous ARP is issued immediately after
+	the failover, subsequent ARPs are sent at a rate of one per link
+	monitor interval (arp_interval or miimon, whichever is active).
+
+	The valid range is 0 - 255; the default value is 1.  This option
+	affects only the active-backup mode.  This option was added for
+	bonding version 3.3.0.
+
 primary
 
 	A string (eth0, eth2, etc) specifying which slave is the
@@ -581,7 +631,7 @@ xmit_hash_policy
 		in environments where a layer3 gateway device is
 		required to reach most destinations.
 
-		This algorithm is 802.3ad complient.
+		This algorithm is 802.3ad compliant.
 
 	layer3+4
 

Documentation/networking/can.txt

@@ -186,7 +186,7 @@ solution for a couple of reasons:
 
   The Linux network devices (by default) just can handle the
   transmission and reception of media dependent frames. Due to the
-  arbritration on the CAN bus the transmission of a low prio CAN-ID
+  arbitration on the CAN bus the transmission of a low prio CAN-ID
   may be delayed by the reception of a high prio CAN frame. To
   reflect the correct* traffic on the node the loopback of the sent
   data has to be performed right after a successful transmission. If
@@ -481,7 +481,7 @@ solution for a couple of reasons:
   - stats_timer: To calculate the Socket CAN core statistics
     (e.g. current/maximum frames per second) this 1 second timer is
     invoked at can.ko module start time by default. This timer can be
-    disabled by using stattimer=0 on the module comandline.
+    disabled by using stattimer=0 on the module commandline.
 
   - debug: (removed since SocketCAN SVN r546)
 

Documentation/networking/dm9000.txt

@@ -0,0 +1,167 @@
+DM9000 Network driver
+=====================
+
+Copyright 2008 Simtec Electronics,
+	  Ben Dooks <ben@simtec.co.uk> <ben-linux@fluff.org>
+
+
+Introduction
+------------
+
+This file describes how to use the DM9000 platform-device based network driver
+that is contained in the files drivers/net/dm9000.c and drivers/net/dm9000.h.
+
+The driver supports three DM9000 variants, the DM9000E which is the first chip
+supported as well as the newer DM9000A and DM9000B devices. It is currently
+maintained and tested by Ben Dooks, who should be CC: to any patches for this
+driver.
+
+
+Defining the platform device
+----------------------------
+
+The minimum set of resources attached to the platform device are as follows:
+
+    1) The physical address of the address register
+    2) The physical address of the data register
+    3) The IRQ line the device's interrupt pin is connected to.
+
+These resources should be specified in that order, as the ordering of the
+two address regions is important (the driver expects these to be address
+and then data).
+
+An example from arch/arm/mach-s3c2410/mach-bast.c is:
+
+static struct resource bast_dm9k_resource[] = {
+	[0] = {
+		.start = S3C2410_CS5 + BAST_PA_DM9000,
+		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 3,
+		.flags = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start = S3C2410_CS5 + BAST_PA_DM9000 + 0x40,
+		.end   = S3C2410_CS5 + BAST_PA_DM9000 + 0x40 + 0x3f,
+		.flags = IORESOURCE_MEM,
+	},
+	[2] = {
+		.start = IRQ_DM9000,
+		.end   = IRQ_DM9000,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
+	}
+};
+
+static struct platform_device bast_device_dm9k = {
+	.name		= "dm9000",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
+	.resource	= bast_dm9k_resource,
+};
+
+Note the setting of the IRQ trigger flag in bast_dm9k_resource[2].flags,
+as this will generate a warning if it is not present. The trigger from
+the flags field will be passed to request_irq() when registering the IRQ
+handler to ensure that the IRQ is setup correctly.
+
+This shows a typical platform device, without the optional configuration
+platform data supplied. The next example uses the same resources, but adds
+the optional platform data to pass extra configuration data:
+
+static struct dm9000_plat_data bast_dm9k_platdata = {
+	.flags		= DM9000_PLATF_16BITONLY,
+};
+
+static struct platform_device bast_device_dm9k = {
+	.name		= "dm9000",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(bast_dm9k_resource),
+	.resource	= bast_dm9k_resource,
+	.dev		= {
+		.platform_data = &bast_dm9k_platdata,
+	}
+};
+
+The platform data is defined in include/linux/dm9000.h and described below.
+
+
+Platform data
+-------------
+
+Extra platform data for the DM9000 can describe the IO bus width to the
+device, whether or not an external PHY is attached to the device and
+the availability of an external configuration EEPROM.
+
+The flags for the platform data .flags field are as follows:
+
+DM9000_PLATF_8BITONLY
+
+	The IO should be done with 8bit operations.
+
+DM9000_PLATF_16BITONLY
+
+	The IO should be done with 16bit operations.
+
+DM9000_PLATF_32BITONLY
+
+	The IO should be done with 32bit operations.
+
+DM9000_PLATF_EXT_PHY
+
+	The chip is connected to an external PHY.
+
+DM9000_PLATF_NO_EEPROM
+
+	This can be used to signify that the board does not have an
+	EEPROM, or that the EEPROM should be hidden from the user.
+
+DM9000_PLATF_SIMPLE_PHY
+
+	Switch to using the simpler PHY polling method which does not
+	try and read the MII PHY state regularly. This is only available
+	when using the internal PHY. See the section on link state polling
+	for more information.
+
+	The config symbol DM9000_FORCE_SIMPLE_PHY_POLL, Kconfig entry
+	"Force simple NSR based PHY polling" allows this flag to be
+	forced on at build time.
+
+
+PHY Link state polling
+----------------------
+
+The driver keeps track of the link state and informs the network core
+about link (carrier) availablilty. This is managed by several methods
+depending on the version of the chip and on which PHY is being used.
+
+For the internal PHY, the original (and currently default) method is
+to read the MII state, either when the status changes if we have the
+necessary interrupt support in the chip or every two seconds via a
+periodic timer.
+
+To reduce the overhead for the internal PHY, there is now the option
+of using the DM9000_FORCE_SIMPLE_PHY_POLL config, or DM9000_PLATF_SIMPLE_PHY
+platform data option to read the summary information without the
+expensive MII accesses. This method is faster, but does not print
+as much information.
+
+When using an external PHY, the driver currently has to poll the MII
+link status as there is no method for getting an interrupt on link change.
+
+
+DM9000A / DM9000B
+-----------------
+
+These chips are functionally similar to the DM9000E and are supported easily
+by the same driver. The features are:
+
+   1) Interrupt on internal PHY state change. This means that the periodic
+      polling of the PHY status may be disabled on these devices when using
+      the internal PHY.
+
+   2) TCP/UDP checksum offloading, which the driver does not currently support.
+
+
+ethtool
+-------
+
+The driver supports the ethtool interface for access to the driver
+state information, the PHY state and the EEPROM.

Documentation/networking/e1000.txt

@@ -513,21 +513,11 @@ Additional Configurations
   Intel(R) PRO/1000 PT Dual Port Server Connection
   Intel(R) PRO/1000 PT Dual Port Server Adapter
   Intel(R) PRO/1000 PF Dual Port Server Adapter
-  Intel(R) PRO/1000 PT Quad Port Server Adapter 
+  Intel(R) PRO/1000 PT Quad Port Server Adapter
 
   NAPI
   ----
-  NAPI (Rx polling mode) is supported in the e1000 driver.  NAPI is enabled
-  or disabled based on the configuration of the kernel.  To override
-  the default, use the following compile-time flags.
-
-  To enable NAPI, compile the driver module, passing in a configuration option:
-
-       make CFLAGS_EXTRA=-DE1000_NAPI install
-
-  To disable NAPI, compile the driver module, passing in a configuration option:
-
-       make CFLAGS_EXTRA=-DE1000_NO_NAPI install
+  NAPI (Rx polling mode) is enabled in the e1000 driver.
 
   See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
 

Documentation/networking/ip-sysctl.txt

@@ -551,8 +551,9 @@ icmp_echo_ignore_broadcasts - BOOLEAN
 icmp_ratelimit - INTEGER
 	Limit the maximal rates for sending ICMP packets whose type matches
 	icmp_ratemask (see below) to specific targets.
-	0 to disable any limiting, otherwise the maximal rate in jiffies(1)
-	Default: 100
+	0 to disable any limiting,
+	otherwise the minimal space between responses in milliseconds.
+	Default: 1000
 
 icmp_ratemask - INTEGER
 	Mask made of ICMP types for which rates are being limited.
@@ -1023,11 +1024,23 @@ max_addresses - INTEGER
 	autoconfigured addresses.
 	Default: 16
 
+disable_ipv6 - BOOLEAN
+	Disable IPv6 operation.
+	Default: FALSE (enable IPv6 operation)
+
+accept_dad - INTEGER
+	Whether to accept DAD (Duplicate Address Detection).
+	0: Disable DAD
+	1: Enable DAD (default)
+	2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
+	   link-local address has been found.
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.
-	0 to disable any limiting, otherwise the maximal rate in jiffies(1)
-	Default: 100
+	0 to disable any limiting,
+	otherwise the minimal space between responses in milliseconds.
+	Default: 1000
 
 
 IPv6 Update by:

Documentation/networking/ixgb.txt

@@ -1,7 +1,7 @@
-Linux* Base Driver for the Intel(R) PRO/10GbE Family of Adapters
-================================================================
+Linux Base Driver for 10 Gigabit Intel(R) Network Connection
+=============================================================
 
-November 17, 2004
+October 9, 2007
 
 
 Contents
@@ -9,94 +9,151 @@ Contents
 
 - In This Release
 - Identifying Your Adapter
+- Building and Installation
 - Command Line Parameters
 - Improving Performance
+- Additional Configurations
+- Known Issues/Troubleshooting
 - Support
 
 
+
 In This Release
 ===============
 
-This file describes the Linux* Base Driver for the Intel(R) PRO/10GbE Family 
-of Adapters, version 1.0.x.  
+This file describes the ixgb Linux Base Driver for the 10 Gigabit Intel(R)
+Network Connection.  This driver includes support for Itanium(R)2-based
+systems.
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your 10 Gigabit adapter.  All hardware requirements listed apply
+to use with Linux.
+
+The following features are available in this kernel:
+ - Native VLANs
+ - Channel Bonding (teaming)
+ - SNMP
+
+Channel Bonding documentation can be found in the Linux kernel source:
+/Documentation/networking/bonding.txt
+
+The driver information previously displayed in the /proc filesystem is not
+supported in this release.  Alternatively, you can use ethtool (version 1.6
+or later), lspci, and ifconfig to obtain the same information.
+
+Instructions on updating ethtool can be found in the section "Additional
+Configurations" later in this document.
 
-For questions related to hardware requirements, refer to the documentation 
-supplied with your Intel PRO/10GbE adapter. All hardware requirements listed 
-apply to use with Linux.
 
 Identifying Your Adapter
 ========================
 
-To verify your Intel adapter is supported, find the board ID number on the 
-adapter. Look for a label that has a barcode and a number in the format  
-A12345-001. 
+The following Intel network adapters are compatible with the drivers in this
+release:
+
+Controller  Adapter Name                 Physical Layer
+----------  ------------                 --------------
+82597EX     Intel(R) PRO/10GbE LR/SR/CX4 10G Base-LR (1310 nm optical fiber)
+            Server Adapters              10G Base-SR (850 nm optical fiber)
+                                         10G Base-CX4(twin-axial copper cabling)
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/network/sb/CS-012904.htm
+
+
+Building and Installation
+=========================
+
+select m for "Intel(R) PRO/10GbE support" located at:
+      Location:
+        -> Device Drivers
+          -> Network device support (NETDEVICES [=y])
+            -> Ethernet (10000 Mbit) (NETDEV_10000 [=y])
+1. make modules && make modules_install
+
+2. Load the module:
+
+    modprobe ixgb <parameter>=<value>
+
+   The insmod command can be used if the full
+   path to the driver module is specified.  For example:
+
+     insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgb/ixgb.ko
+
+   With 2.6 based kernels also make sure that older ixgb drivers are
+   removed from the kernel, before loading the new module:
 
-Use the above information and the Adapter & Driver ID Guide at:
+     rmmod ixgb; modprobe ixgb
 
-  http://support.intel.com/support/network/adapter/pro100/21397.htm
+3. Assign an IP address to the interface by entering the following, where
+   x is the interface number:
 
-For the latest Intel network drivers for Linux, go to:
+     ifconfig ethx <IP_address>
+
+4. Verify that the interface works. Enter the following, where <IP_address>
+   is the IP address for another machine on the same subnet as the interface
+   that is being tested:
+
+     ping  <IP_address>
 
-    http://downloadfinder.intel.com/scripts-df/support_intel.asp
 
 Command Line Parameters
 =======================
 
-If the driver is built as a module, the  following optional parameters are 
-used by entering them on the command line with the modprobe or insmod command
-using this syntax:
+If the driver is built as a module, the  following optional parameters are
+used by entering them on the command line with the modprobe command using
+this syntax:
 
      modprobe ixgb [<option>=<VAL1>,<VAL2>,...]
 
-     insmod ixgb [<option>=<VAL1>,<VAL2>,...]
+For example, with two 10GbE PCI adapters, entering:
 
-For example, with two PRO/10GbE PCI adapters, entering:
+     modprobe ixgb TxDescriptors=80,128
 
-    insmod ixgb TxDescriptors=80,128
-
-loads the ixgb driver with 80 TX resources for the first adapter and 128 TX 
+loads the ixgb driver with 80 TX resources for the first adapter and 128 TX
 resources for the second adapter.
 
 The default value for each parameter is generally the recommended setting,
-unless otherwise noted. Also, if the driver is statically built into the
-kernel, the driver is loaded with the default values for all the parameters.
-Ethtool can be used to change some of the parameters at runtime.
+unless otherwise noted.
 
 FlowControl
 Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
 Default: Read from the EEPROM
-         If EEPROM is not detected, default is 3
-    This parameter controls the automatic generation(Tx) and response(Rx) to 
-    Ethernet PAUSE frames.
+         If EEPROM is not detected, default is 1
+    This parameter controls the automatic generation(Tx) and response(Rx) to
+    Ethernet PAUSE frames.  There are hardware bugs associated with enabling
+    Tx flow control so beware.
 
 RxDescriptors
 Valid Range: 64-512
 Default Value: 512
-    This value is the number of receive descriptors allocated by the driver. 
-    Increasing this value allows the driver to buffer more incoming packets. 
-    Each descriptor is 16 bytes.  A receive buffer is also allocated for 
-    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes, 
-    depending on the MTU setting. When the MTU size is 1500 or less, the 
+    This value is the number of receive descriptors allocated by the driver.
+    Increasing this value allows the driver to buffer more incoming packets.
+    Each descriptor is 16 bytes.  A receive buffer is also allocated for
+    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes,
+    depending on the MTU setting.  When the MTU size is 1500 or less, the
     receive buffer size is 2048 bytes. When the MTU is greater than 1500 the
-    receive buffer size will be either 4056, 8192, or 16384 bytes. The 
+    receive buffer size will be either 4056, 8192, or 16384 bytes.  The
     maximum MTU size is 16114.
 
 RxIntDelay
 Valid Range: 0-65535 (0=off)
-Default Value: 6
-    This value delays the generation of receive interrupts in units of 
-    0.8192 microseconds.  Receive interrupt reduction can improve CPU 
-    efficiency if properly tuned for specific network traffic. Increasing 
-    this value adds extra latency to frame reception and can end up 
-    decreasing the throughput of TCP traffic. If the system is reporting 
-    dropped receives, this value may be set too high, causing the driver to 
+Default Value: 72
+    This value delays the generation of receive interrupts in units of
+    0.8192 microseconds.  Receive interrupt reduction can improve CPU
+    efficiency if properly tuned for specific network traffic.  Increasing
+    this value adds extra latency to frame reception and can end up
+    decreasing the throughput of TCP traffic.  If the system is reporting
+    dropped receives, this value may be set too high, causing the driver to
     run out of available receive descriptors.
 
 TxDescriptors
 Valid Range: 64-4096
 Default Value: 256
     This value is the number of transmit descriptors allocated by the driver.
-    Increasing this value allows the driver to queue more transmits. Each 
+    Increasing this value allows the driver to queue more transmits.  Each
     descriptor is 16 bytes.
 
 XsumRX
@@ -105,51 +162,49 @@ Default Value: 1
     A value of '1' indicates that the driver should enable IP checksum
     offload for received packets (both UDP and TCP) to the adapter hardware.
 
-XsumTX
-Valid Range: 0-1
-Default Value: 1
-    A value of '1' indicates that the driver should enable IP checksum
-    offload for transmitted packets (both UDP and TCP) to the adapter 
-    hardware.
 
 Improving Performance
 =====================
 
-With the Intel PRO/10 GbE adapter, the default Linux configuration will very 
-likely limit the total available throughput artificially.  There is a set of 
-things that when applied together increase the ability of Linux to transmit 
-and receive data.  The following enhancements were originally acquired from
-settings published at http://www.spec.org/web99 for various submitted results 
-using Linux.
+With the 10 Gigabit server adapters, the default Linux configuration will
+very likely limit the total available throughput artificially.  There is a set
+of configuration changes that, when applied together, will increase the ability
+of Linux to transmit and receive data.  The following enhancements were
+originally acquired from settings published at http://www.spec.org/web99/ for
+various submitted results using Linux.
 
-NOTE: These changes are only suggestions, and serve as a starting point for 
-tuning your network performance.
+NOTE: These changes are only suggestions, and serve as a starting point for
+      tuning your network performance.
 
 The changes are made in three major ways, listed in order of greatest effect:
-- Use ifconfig to modify the mtu (maximum transmission unit) and the txqueuelen 
+- Use ifconfig to modify the mtu (maximum transmission unit) and the txqueuelen
   parameter.
 - Use sysctl to modify /proc parameters (essentially kernel tuning)
-- Use setpci to modify the MMRBC field in PCI-X configuration space to increase 
+- Use setpci to modify the MMRBC field in PCI-X configuration space to increase
   transmit burst lengths on the bus.
 
-NOTE: setpci modifies the adapter's configuration registers to allow it to read 
-up to 4k bytes at a time (for transmits).  However, for some systems the 
-behavior after modifying this register may be undefined (possibly errors of some 
-kind). A power-cycle, hard reset or explicitly setting the e6 register back to 
-22 (setpci -d 8086:1048 e6.b=22) may be required to get back to a stable 
-configuration.
+NOTE: setpci modifies the adapter's configuration registers to allow it to read
+up to 4k bytes at a time (for transmits).  However, for some systems the
+behavior after modifying this register may be undefined (possibly errors of
+some kind).  A power-cycle, hard reset or explicitly setting the e6 register
+back to 22 (setpci -d 8086:1a48 e6.b=22) may be required to get back to a
+stable configuration.
 
 - COPY these lines and paste them into ixgb_perf.sh:
 #!/bin/bash
-echo "configuring network performance , edit this file to change the interface"
+echo "configuring network performance , edit this file to change the interface
+or device ID of 10GbE card"
 # set mmrbc to 4k reads, modify only Intel 10GbE device IDs
-setpci -d 8086:1048 e6.b=2e
-# set the MTU (max transmission unit) - it requires your switch and clients to change too!
+# replace 1a48 with appropriate 10GbE device's ID installed on the system,
+# if needed.
+setpci -d 8086:1a48 e6.b=2e
+# set the MTU (max transmission unit) - it requires your switch and clients
+# to change as well.
 # set the txqueuelen
 # your ixgb adapter should be loaded as eth1 for this to work, change if needed
 ifconfig eth1 mtu 9000 txqueuelen 1000 up
-# call the sysctl utility to modify /proc/sys entries 
-sysctl -p ./sysctl_ixgb.conf 
+# call the sysctl utility to modify /proc/sys entries
+sysctl -p ./sysctl_ixgb.conf
 - END ixgb_perf.sh
 
 - COPY these lines and paste them into sysctl_ixgb.conf:
@@ -159,54 +214,220 @@ sysctl -p ./sysctl_ixgb.conf
 # several network benchmark tests, your mileage may vary
 
 ### IPV4 specific settings
-net.ipv4.tcp_timestamps = 0 # turns TCP timestamp support off, default 1, reduces CPU use
-net.ipv4.tcp_sack = 0 # turn SACK support off, default on
-# on systems with a VERY fast bus -> memory interface this is the big gainer 
-net.ipv4.tcp_rmem = 10000000 10000000 10000000 # sets min/default/max TCP read buffer, default 4096 87380 174760
-net.ipv4.tcp_wmem = 10000000 10000000 10000000 # sets min/pressure/max TCP write buffer, default 4096 16384 131072
-net.ipv4.tcp_mem = 10000000 10000000 10000000 # sets min/pressure/max TCP buffer space, default 31744 32256 32768
+# turn TCP timestamp support off, default 1, reduces CPU use
+net.ipv4.tcp_timestamps = 0
+# turn SACK support off, default on
+# on systems with a VERY fast bus -> memory interface this is the big gainer
+net.ipv4.tcp_sack = 0
+# set min/default/max TCP read buffer, default 4096 87380 174760
+net.ipv4.tcp_rmem = 10000000 10000000 10000000
+# set min/pressure/max TCP write buffer, default 4096 16384 131072
+net.ipv4.tcp_wmem = 10000000 10000000 10000000
+# set min/pressure/max TCP buffer space, default 31744 32256 32768
+net.ipv4.tcp_mem = 10000000 10000000 10000000
 
 ### CORE settings (mostly for socket and UDP effect)
-net.core.rmem_max = 524287 # maximum receive socket buffer size, default 131071
-net.core.wmem_max = 524287 # maximum send socket buffer size, default 131071
-net.core.rmem_default = 524287 # default receive socket buffer size, default 65535
-net.core.wmem_default = 524287 # default send socket buffer size, default 65535
-net.core.optmem_max = 524287 # maximum amount of option memory buffers, default 10240
-net.core.netdev_max_backlog = 300000 # number of unprocessed input packets before kernel starts dropping them, default 300
+# set maximum receive socket buffer size, default 131071
+net.core.rmem_max = 524287
+# set maximum send socket buffer size, default 131071
+net.core.wmem_max = 524287
+# set default receive socket buffer size, default 65535
+net.core.rmem_default = 524287
+# set default send socket buffer size, default 65535
+net.core.wmem_default = 524287
+# set maximum amount of option memory buffers, default 10240
+net.core.optmem_max = 524287
+# set number of unprocessed input packets before kernel starts dropping them; default 300
+net.core.netdev_max_backlog = 300000
 - END sysctl_ixgb.conf
 
-Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface 
-your ixgb driver is using.
+Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface
+your ixgb driver is using and/or replace '1a48' with appropriate 10GbE device's
+ID installed on the system.
 
-NOTE: Unless these scripts are added to the boot process, these changes will 
-only last only until the next system reboot.
+NOTE: Unless these scripts are added to the boot process, these changes will
+      only last only until the next system reboot.
 
 
 Resolving Slow UDP Traffic
 --------------------------
+If your server does not seem to be able to receive UDP traffic as fast as it
+can receive TCP traffic, it could be because Linux, by default, does not set
+the network stack buffers as large as they need to be to support high UDP
+transfer rates.  One way to alleviate this problem is to allow more memory to
+be used by the IP stack to store incoming data.
 
-If your server does not seem to be able to receive UDP traffic as fast as it 
-can receive TCP traffic, it could be because Linux, by default, does not set 
-the network stack buffers as large as they need to be to support high UDP 
-transfer rates. One way to alleviate this problem is to allow more memory to 
-be used by the IP stack to store incoming data. 
-
-For instance, use the commands: 
+For instance, use the commands:
     sysctl -w net.core.rmem_max=262143
 and
     sysctl -w net.core.rmem_default=262143
-to increase the read buffer memory max and default to 262143 (256k - 1) from 
-defaults of max=131071 (128k - 1) and default=65535 (64k - 1). These variables 
-will increase the amount of memory used by the network stack for receives, and 
+to increase the read buffer memory max and default to 262143 (256k - 1) from
+defaults of max=131071 (128k - 1) and default=65535 (64k - 1).  These variables
+will increase the amount of memory used by the network stack for receives, and
 can be increased significantly more if necessary for your application.
 
+
+Additional Configurations
+=========================
+
+  Configuring the Driver on Different Distributions
+  -------------------------------------------------
+  Configuring a network driver to load properly when the system is started is
+  distribution dependent. Typically, the configuration process involves adding
+  an alias line to /etc/modprobe.conf as well as editing other system startup
+  scripts and/or configuration files.  Many popular Linux distributions ship
+  with tools to make these changes for you.  To learn the proper way to
+  configure a network device for your system, refer to your distribution
+  documentation.  If during this process you are asked for the driver or module
+  name, the name for the Linux Base Driver for the Intel 10GbE Family of
+  Adapters is ixgb.
+
+  Viewing Link Messages
+  ---------------------
+  Link messages will not be displayed to the console if the distribution is
+  restricting system messages. In order to see network driver link messages on
+  your console, set dmesg to eight by entering the following:
+
+       dmesg -n 8
+
+  NOTE: This setting is not saved across reboots.
+
+
+  Jumbo Frames
+  ------------
+  The driver supports Jumbo Frames for all adapters. Jumbo Frames support is
+  enabled by changing the MTU to a value larger than the default of 1500.
+  The maximum value for the MTU is 16114.  Use the ifconfig command to
+  increase the MTU size.  For example:
+
+        ifconfig ethx mtu 9000 up
+
+  The maximum MTU setting for Jumbo Frames is 16114.  This value coincides
+  with the maximum Jumbo Frames size of 16128.
+
+
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  Ethtool
+  version 1.6 or later is required for this functionality.
+
+  The latest release of ethtool can be found from
+  http://sourceforge.net/projects/gkernel
+
+  NOTE: Ethtool 1.6 only supports a limited set of ethtool options. Support
+        for a more complete ethtool feature set can be enabled by upgrading
+        to the latest version.
+
+
+  NAPI
+  ----
+
+  NAPI (Rx polling mode) is supported in the ixgb driver.  NAPI is enabled
+  or disabled based on the configuration of the kernel.  see CONFIG_IXGB_NAPI
+
+  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
+
+
+Known Issues/Troubleshooting
+============================
+
+  NOTE: After installing the driver, if your Intel Network Connection is not
+  working, verify in the "In This Release" section of the readme that you have
+  installed the correct driver.
+
+  Intel(R) PRO/10GbE CX4 Server Adapter Cable Interoperability Issue with
+  Fujitsu XENPAK Module in SmartBits Chassis
+  ---------------------------------------------------------------------
+  Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4
+  Server adapter is connected to a Fujitsu XENPAK CX4 module in a SmartBits
+  chassis using 15 m/24AWG cable assemblies manufactured by Fujitsu or Leoni.
+  The CRC errors may be received either by the Intel(R) PRO/10GbE CX4
+  Server adapter or the SmartBits. If this situation occurs using a different
+  cable assembly may resolve the issue.
+
+  CX4 Server Adapter Cable Interoperability Issues with HP Procurve 3400cl
+  Switch Port
+  ------------------------------------------------------------------------
+  Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4 Server
+  adapter is connected to an HP Procurve 3400cl switch port using short cables
+  (1 m or shorter). If this situation occurs, using a longer cable may resolve
+  the issue.
+
+  Excessive CRC errors may be observed using Fujitsu 24AWG cable assemblies that
+  Are 10 m or longer or where using a Leoni 15 m/24AWG cable assembly. The CRC
+  errors may be received either by the CX4 Server adapter or at the switch. If
+  this situation occurs, using a different cable assembly may resolve the issue.
+
+
+  Jumbo Frames System Requirement
+  -------------------------------
+  Memory allocation failures have been observed on Linux systems with 64 MB
+  of RAM or less that are running Jumbo Frames.  If you are using Jumbo
+  Frames, your system may require more than the advertised minimum
+  requirement of 64 MB of system memory.
+
+
+  Performance Degradation with Jumbo Frames
+  -----------------------------------------
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments.  If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
+
+
+  Allocating Rx Buffers when Using Jumbo Frames
+  ---------------------------------------------
+  Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if
+  the available memory is heavily fragmented. This issue may be seen with PCI-X
+  adapters or with packet split disabled. This can be reduced or eliminated
+  by changing the amount of available memory for receive buffer allocation, by
+  increasing /proc/sys/vm/min_free_kbytes.
+
+
+  Multiple Interfaces on Same Ethernet Broadcast Network
+  ------------------------------------------------------
+  Due to the default ARP behavior on Linux, it is not possible to have
+  one system on two IP networks in the same Ethernet broadcast domain
+  (non-partitioned switch) behave as expected.  All Ethernet interfaces
+  will respond to IP traffic for any IP address assigned to the system.
+  This results in unbalanced receive traffic.
+
+  If you have multiple interfaces in a server, do either of the following:
+
+  - Turn on ARP filtering by entering:
+      echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+
+  - Install the interfaces in separate broadcast domains - either in
+    different switches or in a switch partitioned to VLANs.
+
+
+  UDP Stress Test Dropped Packet Issue
+  --------------------------------------
+  Under small packets UDP stress test with 10GbE driver, the Linux system
+  may drop UDP packets due to the fullness of socket buffers. You may want
+  to change the driver's Flow Control variables to the minimum value for
+  controlling packet reception.
+
+
+  Tx Hangs Possible Under Stress
+  ------------------------------
+  Under stress conditions, if TX hangs occur, turning off TSO
+  "ethtool -K eth0 tso off" may resolve the problem.
+
+
 Support
 =======
 
-For general information and support, go to the Intel support website at:
+For general information, go to the Intel support website at:
 
     http://support.intel.com
 
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
 If an issue is identified with the released source code on the supported
-kernel with a supported adapter, email the specific information related to 
-the issue to linux.nics@intel.com.
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net

Documentation/networking/mac80211_hwsim/README

@@ -0,0 +1,67 @@
+mac80211_hwsim - software simulator of 802.11 radio(s) for mac80211
+Copyright (c) 2008, Jouni Malinen <j@w1.fi>
+
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
+
+
+Introduction
+
+mac80211_hwsim is a Linux kernel module that can be used to simulate
+arbitrary number of IEEE 802.11 radios for mac80211. It can be used to
+test most of the mac80211 functionality and user space tools (e.g.,
+hostapd and wpa_supplicant) in a way that matches very closely with
+the normal case of using real WLAN hardware. From the mac80211 view
+point, mac80211_hwsim is yet another hardware driver, i.e., no changes
+to mac80211 are needed to use this testing tool.
+
+The main goal for mac80211_hwsim is to make it easier for developers
+to test their code and work with new features to mac80211, hostapd,
+and wpa_supplicant. The simulated radios do not have the limitations
+of real hardware, so it is easy to generate an arbitrary test setup
+and always reproduce the same setup for future tests. In addition,
+since all radio operation is simulated, any channel can be used in
+tests regardless of regulatory rules.
+
+mac80211_hwsim kernel module has a parameter 'radios' that can be used
+to select how many radios are simulated (default 2). This allows
+configuration of both very simply setups (e.g., just a single access
+point and a station) or large scale tests (multiple access points with
+hundreds of stations).
+
+mac80211_hwsim works by tracking the current channel of each virtual
+radio and copying all transmitted frames to all other radios that are
+currently enabled and on the same channel as the transmitting
+radio. Software encryption in mac80211 is used so that the frames are
+actually encrypted over the virtual air interface to allow more
+complete testing of encryption.
+
+A global monitoring netdev, hwsim#, is created independent of
+mac80211. This interface can be used to monitor all transmitted frames
+regardless of channel.
+
+
+Simple example
+
+This example shows how to use mac80211_hwsim to simulate two radios:
+one to act as an access point and the other as a station that
+associates with the AP. hostapd and wpa_supplicant are used to take
+care of WPA2-PSK authentication. In addition, hostapd is also
+processing access point side of association.
+
+Please note that the current Linux kernel does not enable AP mode, so a
+simple patch is needed to enable AP mode selection:
+http://johannes.sipsolutions.net/patches/kernel/all/LATEST/006-allow-ap-vlan-modes.patch
+
+
+# Build mac80211_hwsim as part of kernel configuration
+
+# Load the module
+modprobe mac80211_hwsim
+
+# Run hostapd (AP) for wlan0
+hostapd hostapd.conf
+
+# Run wpa_supplicant (station) for wlan1
+wpa_supplicant -Dwext -iwlan1 -c wpa_supplicant.conf

Documentation/networking/mac80211_hwsim/hostapd.conf

@@ -0,0 +1,11 @@
+interface=wlan0
+driver=nl80211
+
+hw_mode=g
+channel=1
+ssid=mac80211 test
+
+wpa=2
+wpa_key_mgmt=WPA-PSK
+wpa_pairwise=CCMP
+wpa_passphrase=12345678

Documentation/networking/mac80211_hwsim/wpa_supplicant.conf

@@ -0,0 +1,10 @@
+ctrl_interface=/var/run/wpa_supplicant
+
+network={
+	ssid="mac80211 test"
+	psk="12345678"
+	key_mgmt=WPA-PSK
+	proto=WPA2
+	pairwise=CCMP
+	group=CCMP
+}

Documentation/networking/multiqueue.txt

@@ -3,19 +3,11 @@
 		===========================================
 
 Section 1: Base driver requirements for implementing multiqueue support
-Section 2: Qdisc support for multiqueue devices
-Section 3: Brief howto using PRIO or RR for multiqueue devices
-
 
 Intro: Kernel support for multiqueue devices
 ---------------------------------------------------------
 
-Kernel support for multiqueue devices is only an API that is presented to the
-netdevice layer for base drivers to implement.  This feature is part of the
-core networking stack, and all network devices will be running on the
-multiqueue-aware stack.  If a base driver only has one queue, then these
-changes are transparent to that driver.
-
+Kernel support for multiqueue devices is always present.
 
 Section 1: Base driver requirements for implementing multiqueue support
 -----------------------------------------------------------------------
@@ -32,84 +24,4 @@ netif_{start|stop|wake}_subqueue() functions to manage each queue while the
 device is still operational.  netdev->queue_lock is still used when the device
 comes online or when it's completely shut down (unregister_netdev(), etc.).
 
-Finally, the base driver should indicate that it is a multiqueue device.  The
-feature flag NETIF_F_MULTI_QUEUE should be added to the netdev->features
-bitmap on device initialization.  Below is an example from e1000:
-
-#ifdef CONFIG_E1000_MQ
-	if ( (adapter->hw.mac.type == e1000_82571) ||
-	     (adapter->hw.mac.type == e1000_82572) ||
-	     (adapter->hw.mac.type == e1000_80003es2lan))
-		netdev->features |= NETIF_F_MULTI_QUEUE;
-#endif
-
-
-Section 2: Qdisc support for multiqueue devices
------------------------------------------------
-
-Currently two qdiscs support multiqueue devices.  A new round-robin qdisc,
-sch_rr, and sch_prio. The qdisc is responsible for classifying the skb's to
-bands and queues, and will store the queue mapping into skb->queue_mapping.
-Use this field in the base driver to determine which queue to send the skb
-to.
-
-sch_rr has been added for hardware that doesn't want scheduling policies from
-software, so it's a straight round-robin qdisc.  It uses the same syntax and
-classification priomap that sch_prio uses, so it should be intuitive to
-configure for people who've used sch_prio.
-
-In order to utilitize the multiqueue features of the qdiscs, the network
-device layer needs to enable multiple queue support.  This can be done by
-selecting NETDEVICES_MULTIQUEUE under Drivers.
-
-The PRIO qdisc naturally plugs into a multiqueue device.  If
-NETDEVICES_MULTIQUEUE is selected, then on qdisc load, the number of
-bands requested is compared to the number of queues on the hardware.  If they
-are equal, it sets a one-to-one mapping up between the queues and bands.  If
-they're not equal, it will not load the qdisc.  This is the same behavior
-for RR.  Once the association is made, any skb that is classified will have
-skb->queue_mapping set, which will allow the driver to properly queue skb's
-to multiple queues.
-
-
-Section 3: Brief howto using PRIO and RR for multiqueue devices
----------------------------------------------------------------
-
-The userspace command 'tc,' part of the iproute2 package, is used to configure
-qdiscs.  To add the PRIO qdisc to your network device, assuming the device is
-called eth0, run the following command:
-
-# tc qdisc add dev eth0 root handle 1: prio bands 4 multiqueue
-
-This will create 4 bands, 0 being highest priority, and associate those bands
-to the queues on your NIC.  Assuming eth0 has 4 Tx queues, the band mapping
-would look like:
-
-band 0 => queue 0
-band 1 => queue 1
-band 2 => queue 2
-band 3 => queue 3
-
-Traffic will begin flowing through each queue if your TOS values are assigning
-traffic across the various bands.  For example, ssh traffic will always try to
-go out band 0 based on TOS -> Linux priority conversion (realtime traffic),
-so it will be sent out queue 0.  ICMP traffic (pings) fall into the "normal"
-traffic classification, which is band 1.  Therefore pings will be send out
-queue 1 on the NIC.
-
-Note the use of the multiqueue keyword.  This is only in versions of iproute2
-that support multiqueue networking devices; if this is omitted when loading
-a qdisc onto a multiqueue device, the qdisc will load and operate the same
-if it were loaded onto a single-queue device (i.e. - sends all traffic to
-queue 0).
-
-Another alternative to multiqueue band allocation can be done by using the
-multiqueue option and specify 0 bands.  If this is the case, the qdisc will
-allocate the number of bands to equal the number of queues that the device
-reports, and bring the qdisc online.
-
-The behavior of tc filters remains the same, where it will override TOS priority
-classification.
-
-
 Author: Peter P. Waskiewicz Jr. <peter.p.waskiewicz.jr@intel.com>