Merge branch 'master' of /home/cbou/linux-2.6

Conflicts: drivers/power/Kconfig drivers/power/Makefile
author: Anton Vorontsov <cbouatmailru@gmail.com> 2008-07-29 18:05:23 -0400
committer: Anton Vorontsov <cbouatmailru@gmail.com> 2008-07-29 18:05:23 -0400
commit: 9fec6060d9e48ed7db0dac0e16d0f0f0e615b7f6 (patch)
tree: 74b41f31a08f6500ff3dfcf64ba21e2d9a8e87e5 /Documentation
parent: fece418418f51e92dd7e67e17c5e3fe5a28d3279 (diff)
parent: 6e86841d05f371b5b9b86ce76c02aaee83352298 (diff)
219 files changed, 9336 insertions, 3331 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 1977fab38656..6de71308a906 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -361,8 +361,6 @@ 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/
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 4bd9ea539129..44f52a4f5903 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -26,3 +26,37 @@ Description:
                I/O statistics of partition <part>. The format is the
                same as the above-written /sys/block/<disk>/stat
                format.
+What:           /sys/block/<disk>/integrity/format
+Date:           June 2008
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Metadata format for integrity capable block device.
+                E.g. T10-DIF-TYPE1-CRC.
+What:           /sys/block/<disk>/integrity/read_verify
+Date:           June 2008
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Indicates whether the block layer should verify the
+                integrity of read requests serviced by devices that
+                support sending integrity metadata.
+What:           /sys/block/<disk>/integrity/tag_size
+Date:           June 2008
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Number of bytes of integrity tag space available per
+                512 bytes of data.
+What:           /sys/block/<disk>/integrity/write_generate
+Date:           June 2008
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Indicates whether the block layer should automatically
+                generate checksums for write requests bound for
+                devices that support receiving integrity metadata.
diff --git a/Documentation/ABI/testing/sysfs-bus-css b/Documentation/ABI/testing/sysfs-bus-css
new file mode 100644
index 000000000000..b585ec258a08
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-css
@@ -0,0 +1,35 @@
+What:           /sys/bus/css/devices/.../type
+Date:           March 2008
+Contact:        Cornelia Huck <cornelia.huck@de.ibm.com>
+                linux-s390@vger.kernel.org
+Description:    Contains the subchannel type, as reported by the hardware.
+                This attribute is present for all subchannel types.
+What:           /sys/bus/css/devices/.../modalias
+Date:           March 2008
+Contact:        Cornelia Huck <cornelia.huck@de.ibm.com>
+                linux-s390@vger.kernel.org
+Description:    Contains the module alias as reported with uevents.
+                It is of the format css:t<type> and present for all
+                subchannel types.
+What:           /sys/bus/css/drivers/io_subchannel/.../chpids
+Date:           December 2002
+Contact:        Cornelia Huck <cornelia.huck@de.ibm.com>
+                linux-s390@vger.kernel.org
+Description:    Contains the ids of the channel paths used by this
+                subchannel, as reported by the channel subsystem
+                during subchannel recognition.
+                Note: This is an I/O-subchannel specific attribute.
+Users:          s390-tools, HAL
+What:           /sys/bus/css/drivers/io_subchannel/.../pimpampom
+Date:           December 2002
+Contact:        Cornelia Huck <cornelia.huck@de.ibm.com>
+                linux-s390@vger.kernel.org
+Description:    Contains the PIM/PAM/POM values, as reported by the
+                channel subsystem when last queried by the common I/O
+                layer (this implies that this attribute is not neccessarily
+                in sync with the values current in the channel subsystem).
+                Note: This is an I/O-subchannel specific attribute.
+Users:          s390-tools, HAL
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index 5ac1e01bbd48..5f500977b42f 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -14,6 +14,10 @@ MAJOR:MINOR
        non-block filesystems which provide their own BDI, such as NFS
        and FUSE.
+MAJOR:MINOR-fuseblk
+        Value of st_dev on fuseblk filesystems.
 default
        The default backing dev, used for non-block device backed
diff --git a/Documentation/ABI/testing/sysfs-dev b/Documentation/ABI/testing/sysfs-dev
new file mode 100644
index 000000000000..a9f2b8b0530f
--- /dev/null
+++ b/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>
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
new file mode 100644
index 000000000000..7a16fe1e2270
--- /dev/null
+++ b/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/
diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi
index 9470ed9afcc0..f27be7d1a49f 100644
--- a/Documentation/ABI/testing/sysfs-firmware-acpi
+++ b/Documentation/ABI/testing/sysfs-firmware-acpi
@@ -29,46 +29,46 @@ Description:
                $ cd /sys/firmware/acpi/interrupts
                $ grep . *
-                error:0
+                error:       0
-                ff_gbl_lock:0
+                ff_gbl_lock:       0   enable
-                ff_pmtimer:0
+                ff_pmtimer:       0  invalid
-                ff_pwr_btn:0
+                ff_pwr_btn:       0   enable
-                ff_rt_clk:0
+                ff_rt_clk:       2  disable
-                ff_slp_btn:0
+                ff_slp_btn:       0  invalid
-                gpe00:0
+                gpe00:       0  invalid
-                gpe01:0
+                gpe01:       0   enable
-                gpe02:0
+                gpe02:     108   enable
-                gpe03:0
+                gpe03:       0  invalid
-                gpe04:0
+                gpe04:       0  invalid
-                gpe05:0
+                gpe05:       0  invalid
-                gpe06:0
+                gpe06:       0   enable
-                gpe07:0
+                gpe07:       0   enable
-                gpe08:0
+                gpe08:       0  invalid
-                gpe09:174
+                gpe09:       0  invalid
-                gpe0A:0
+                gpe0A:       0  invalid
-                gpe0B:0
+                gpe0B:       0  invalid
-                gpe0C:0
+                gpe0C:       0  invalid
-                gpe0D:0
+                gpe0D:       0  invalid
-                gpe0E:0
+                gpe0E:       0  invalid
-                gpe0F:0
+                gpe0F:       0  invalid
-                gpe10:0
+                gpe10:       0  invalid
-                gpe11:60
+                gpe11:       0  invalid
-                gpe12:0
+                gpe12:       0  invalid
-                gpe13:0
+                gpe13:       0  invalid
-                gpe14:0
+                gpe14:       0  invalid
-                gpe15:0
+                gpe15:       0  invalid
-                gpe16:0
+                gpe16:       0  invalid
-                gpe17:0
+                gpe17:    1084   enable
-                gpe18:0
+                gpe18:       0   enable
-                gpe19:7
+                gpe19:       0  invalid
-                gpe1A:0
+                gpe1A:       0  invalid
-                gpe1B:0
+                gpe1B:       0  invalid
-                gpe1C:0
+                gpe1C:       0  invalid
-                gpe1D:0
+                gpe1D:       0  invalid
-                gpe1E:0
+                gpe1E:       0  invalid
-                gpe1F:0
+                gpe1F:       0  invalid
-                gpe_all:241
+                gpe_all:    1192
-                sci:241
+                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
diff --git a/Documentation/ABI/testing/sysfs-firmware-memmap b/Documentation/ABI/testing/sysfs-firmware-memmap
new file mode 100644
index 000000000000..0d99ee6ae02e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-memmap
@@ -0,0 +1,71 @@
+What:           /sys/firmware/memmap/
+Date:           June 2008
+Contact:        Bernhard Walle <bwalle@suse.de>
+Description:
+                On all platforms, the firmware provides a memory map which the
+                kernel reads. The resources from that memory map are registered
+                in the kernel resource tree and exposed to userspace via
+                /proc/iomem (together with other resources).
+                However, on most architectures that firmware-provided memory
+                map is modified afterwards by the kernel itself, either because
+                the kernel merges that memory map with other information or
+                just because the user overwrites that memory map via command
+                line.
+                kexec needs the raw firmware-provided memory map to setup the
+                parameter segment of the kernel that should be booted with
+                kexec. Also, the raw memory map is useful for debugging. For
+                that reason, /sys/firmware/memmap is an interface that provides
+                the raw memory map to userspace.
+                The structure is as follows: Under /sys/firmware/memmap there
+                are subdirectories with the number of the entry as their name:
+                        /sys/firmware/memmap/0
+                        /sys/firmware/memmap/1
+                        /sys/firmware/memmap/2
+                        /sys/firmware/memmap/3
+                        ...
+                The maximum depends on the number of memory map entries provided
+                by the firmware. The order is just the order that the firmware
+                provides.
+                Each directory contains three files:
+                start   : The start address (as hexadecimal number with the
+                          '0x' prefix).
+                end     : The end address, inclusive (regardless whether the
+                          firmware provides inclusive or exclusive ranges).
+                type    : Type of the entry as string. See below for a list of
+                          valid types.
+                So, for example:
+                        /sys/firmware/memmap/0/start
+                        /sys/firmware/memmap/0/end
+                        /sys/firmware/memmap/0/type
+                        /sys/firmware/memmap/1/start
+                        ...
+                Currently following types exist:
+                  - System RAM
+                  - ACPI Tables
+                  - ACPI Non-volatile Storage
+                  - reserved
+                Following shell snippet can be used to display that memory
+                map in a human-readable format:
+                -------------------- 8< ----------------------------------------
+                  #!/bin/bash
+                  cd /sys/firmware/memmap
+                  for dir in * ; do
+                      start=$(cat $dir/start)
+                      end=$(cat $dir/end)
+                      type=$(cat $dir/type)
+                      printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
+                  done
+                -------------------- >8 ----------------------------------------
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm b/Documentation/ABI/testing/sysfs-kernel-mm
new file mode 100644
index 000000000000..190d523ac159
--- /dev/null
+++ b/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/.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
new file mode 100644
index 000000000000..e21c00571cf4
--- /dev/null
+++ b/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.
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 6caa14615578..1875e502f872 100644
--- a/Documentation/CodingStyle
+++ b/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 ()
+(defun c-lineup-arglist-tabs-only (ignored)
-  "C mode with adjusted defaults for use with the Linux kernel."
+  "Line up argument lists by tabs, not spaces"
-  (interactive)
+  (let* ((anchor (c-langelem-pos c-syntactic-element))
-  (c-mode)
+         (column (c-langelem-2nd-pos c-syntactic-element))
-  (c-set-style "K&R")
+         (offset (- (1+ column) anchor))
-  (setq tab-width 8)
+         (steps (floor offset c-basic-offset)))
-  (setq indent-tabs-mode t)
+    (* (max steps 1)
-  (setq c-basic-offset 8))
+       c-basic-offset)))
-This will define the M-x linux-c-mode command.  When hacking on a
+(add-hook 'c-mode-hook
-module, if you put the string -*- linux-c -*- somewhere on the first
+          (lambda ()
-two lines, this mode will be automatically invoked. Also, you may want
+            (let ((filename (buffer-file-name)))
-to add
+              ;; Enable kernel mode for the appropriate files
+              (when (and filename
-(setq auto-mode-alist (cons '("/usr/src/linux.*/.*\\.[ch]$" . linux-c-mode)
+                         (string-match "~/src/linux-trees" filename))
-                        auto-mode-alist))
+                (setq indent-tabs-mode t)
+                (c-set-style "linux")
-to your .emacs file if you want to have linux-c-mode switched on
+                (c-set-offset 'arglist-cont-nonempty
-automagically when you edit source files under /usr/src/linux.
+                              '(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".
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 80d150458c80..d8b63d164e41 100644
--- a/Documentation/DMA-API.txt
+++ b/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
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 6d772f84b477..b768cc0e402b 100644
--- a/Documentation/DMA-attributes.txt
+++ b/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.
diff --git a/Documentation/DocBook/gadget.tmpl b/Documentation/DocBook/gadget.tmpl
index 5a8ffa761e09..ea3bc9565e6a 100644
--- a/Documentation/DocBook/gadget.tmpl
+++ b/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>
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index 77c42f40be5d..084f6ad7b7a0 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/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 
@@ -240,14 +240,6 @@
     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"/>.
   </para>
@@ -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
+       user context, then you can use a simple mutex
-       (<filename>linux/linux/semaphore.h</filename>) to protect it.  This
+       (<filename>include/linux/mutex.h</filename>) to protect it.  This
-       is the most trivial case: you initialize the semaphore to the number 
+       is the most trivial case: you initialize the mutex.  Then you can
-       of resources available (usually 1), and call
+       call <function>mutex_lock_interruptible()</function> to grab the mutex,
-       <function>down_interruptible()</function> to grab the semaphore, and 
+       and <function>mutex_unlock()</function> to release it.  There is also a 
-       <function>up()</function> to release it.  There is also a 
+       <function>mutex_lock()</function>, which should be avoided, because it 
-       <function>down()</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>MLI</entry>
-<entry>down_interruptible</entry>
+<entry>mutex_lock_interruptible</entry>
 </row>
 </tbody>
@@ -703,6 +694,31 @@
 </sect1>
 </chapter>
+<chapter id="trylock-functions">
+ <title>The trylock Functions</title>
+  <para>
+   There are functions that try to acquire a lock only once and immediately
+   return a value telling about success or failure to acquire the lock.
+   They can be used if you need no access to the data protected with the lock
+   when some other thread is holding the lock. You should acquire the lock
+   later if you then need access to the data protected with the lock.
+  </para>
+  <para>
+    <function>spin_trylock()</function> does not spin but returns non-zero if
+    it acquires the spinlock on the first try or 0 if not. This function can
+    be used in all contexts like <function>spin_lock</function>: you must have
+    disabled the contexts that might interrupt you and acquire the spin lock.
+  </para>
+  <para>
+    <function>mutex_trylock()</function> does not suspend your task
+    but returns non-zero if it could lock the mutex on the first try
+    or 0 if not. This function cannot be safely used in hardware or software
+    interrupt contexts despite not sleeping.
+  </para>
+</chapter>
  <chapter id="Examples">
   <title>Common Examples</title>
    <para>
@@ -1285,7 +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.
@@ -1310,7 +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>
@@ -1533,7 +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
@@ -1656,7 +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
@@ -1888,7 +1904,7 @@ machines due to caching.
       </listitem>
       <listitem>
        <para>
-          <function> put_user()</function>
+          <function>put_user()</function>
        </para>
       </listitem>
      </itemizedlist>
@@ -1902,13 +1918,13 @@ machines due to caching.
     <listitem>
      <para>
-      <function>down_interruptible()</function> and
+      <function>mutex_lock_interruptible()</function> and
-      <function>down()</function>
+      <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>
@@ -1998,7 +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
diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl
index 97618bed4d65..e8acd1f03456 100644
--- a/Documentation/DocBook/kgdb.tmpl
+++ b/Documentation/DocBook/kgdb.tmpl
@@ -72,7 +72,7 @@
    kgdb is a source level debugger for linux kernel. It is used along
    with gdb to debug a linux kernel.  The expectation is that gdb can
    be used to "break in" to the kernel to inspect memory, variables
-    and look through a cal stack information similar to what an
+    and look through call stack information similar to what an
    application developer would use gdb for.  It is possible to place
    breakpoints in kernel code and perform some limited execution
    stepping.
@@ -84,17 +84,18 @@
    runs an instance of gdb against the vmlinux file which contains
    the symbols (not boot image such as bzImage, zImage, uImage...).
    In gdb the developer specifies the connection parameters and
-    connects to kgdb.  Depending on which kgdb I/O modules exist in
+    connects to kgdb.  The type of connection a developer makes with
-    the kernel for a given architecture, it may be possible to debug
+    gdb depends on the availability of kgdb I/O modules compiled as
-    the test machine's kernel with the development machine using a
+    builtin's or kernel modules in the test machine's kernel.
-    rs232 or ethernet connection.
    </para>
  </chapter>
  <chapter id="CompilingAKernel">
    <title>Compiling a kernel</title>
    <para>
-    To enable <symbol>CONFIG_KGDB</symbol>, look under the "Kernel debugging"
+    To enable <symbol>CONFIG_KGDB</symbol> you should first turn on
-    and then select "KGDB: kernel debugging with remote gdb".
+    "Prompt for development and/or incomplete code/drivers"
+    (CONFIG_EXPERIMENTAL) in  "General setup", then under the
+    "Kernel debugging" select "KGDB: kernel debugging with remote gdb".
    </para>
    <para>
    Next you should choose one of more I/O drivers to interconnect debugging
@@ -221,7 +222,7 @@
  </para>
  <para>
  IMPORTANT NOTE: Using this option with kgdb over the console
-  (kgdboc) or kgdb over ethernet (kgdboe) is not supported.
+  (kgdboc) is not supported.
  </para>
  </sect1>
  </chapter>
@@ -247,18 +248,11 @@
    (gdb) target remote /dev/ttyS0
    </programlisting>
    <para>
-    Example (kgdb to a terminal server):
+    Example (kgdb to a terminal server on tcp port 2012):
    </para>
    <programlisting>
    % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
+    (gdb) target remote 192.168.2.2:2012
-    </programlisting>
-    <para>
-    Example (kgdb over ethernet):
-    </para>
-    <programlisting>
-    % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
    </programlisting>
    <para>
    Once connected, you can debug a kernel the way you would debug an
diff --git a/Documentation/DocBook/procfs-guide.tmpl b/Documentation/DocBook/procfs-guide.tmpl
index 1fd6a1ec7591..8a5dc6e021ff 100644
--- a/Documentation/DocBook/procfs-guide.tmpl
+++ b/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>
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index fdd7f4f887b7..df87d1b93605 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/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>
@@ -30,6 +42,12 @@
 <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>
        <authorinitials>hjk</authorinitials>
@@ -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>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 0291ade44c17..c2371c5a98f9 100644
--- a/Documentation/HOWTO
+++ b/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>
@@ -377,7 +377,7 @@ Bug Reporting
 bugzilla.kernel.org is where the Linux kernel developers track kernel
 bugs.  Users are encouraged to report all bugs that they find in this
 tool.  For details on how to use the kernel bugzilla, please see:
-        http://test.kernel.org/bugzilla/faq.html
+        http://bugzilla.kernel.org/page.cgi?id=faq.html
 The file REPORTING-BUGS in the main kernel source directory has a good
 template for how to report a possible kernel bug, and details what kind
diff --git a/Documentation/IRQ-affinity.txt b/Documentation/IRQ-affinity.txt
index 938d7dd05490..b4a615b78403 100644
--- a/Documentation/IRQ-affinity.txt
+++ b/Documentation/IRQ-affinity.txt
@@ -1,17 +1,26 @@
+ChangeLog:
+        Started by Ingo Molnar <mingo@redhat.com>
+        Update by Max Krasnyansky <maxk@qualcomm.com>
-SMP IRQ affinity, started by Ingo Molnar <mingo@redhat.com>
+SMP IRQ affinity
 /proc/irq/IRQ#/smp_affinity specifies which target CPUs are permitted
 for a given IRQ source. It's a bitmask of allowed CPUs. It's not allowed
 to turn off all CPUs, and if an IRQ controller does not support IRQ
 affinity then the value will not change from the default 0xffffffff.
+/proc/irq/default_smp_affinity specifies default affinity mask that applies
+to all non-active IRQs. Once IRQ is allocated/activated its affinity bitmask
+will be set to the default mask. It can then be changed as described above.
+Default mask is 0xffffffff.
 Here is an example of restricting IRQ44 (eth1) to CPU0-3 then restricting
-the IRQ to CPU4-7 (this is an 8-CPU SMP box):
+it to CPU4-7 (this is an 8-CPU SMP box):
+[root@moon 44]# cd /proc/irq/44
 [root@moon 44]# cat smp_affinity
 ffffffff
 [root@moon 44]# echo 0f > smp_affinity
 [root@moon 44]# cat smp_affinity
 0000000f
@@ -21,17 +30,27 @@ PING hell (195.4.7.3): 56 data bytes
 --- hell ping statistics ---
 6029 packets transmitted, 6027 packets received, 0% packet loss
 round-trip min/avg/max = 0.1/0.1/0.4 ms
-[root@moon 44]# cat /proc/interrupts | grep 44:
+[root@moon 44]# cat /proc/interrupts | grep 'CPU\|44:'
- 44:          0       1785       1785       1783       1783          1
+           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
-1          0   IO-APIC-level  eth1
+ 44:       1068       1785       1785       1783         0          0           0         0    IO-APIC-level  eth1
+As can be seen from the line above IRQ44 was delivered only to the first four
+processors (0-3).
+Now lets restrict that IRQ to CPU(4-7).
 [root@moon 44]# echo f0 > smp_affinity
+[root@moon 44]# cat smp_affinity
+000000f0
 [root@moon 44]# ping -f h
 PING hell (195.4.7.3): 56 data bytes
 ..
 --- hell ping statistics ---
 2779 packets transmitted, 2777 packets received, 0% packet loss
 round-trip min/avg/max = 0.1/0.5/585.4 ms
-[root@moon 44]# cat /proc/interrupts | grep 44:
+[root@moon 44]# cat /proc/interrupts |  'CPU\|44:'
- 44:       1068       1785       1785       1784       1784       1069       1070       1069   IO-APIC-level  eth1
+           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
-[root@moon 44]#
+ 44:       1068       1785       1785       1783      1784       1069        1070       1069   IO-APIC-level  eth1
+This time around IRQ44 was delivered only to the last four processors.
+i.e counters for the CPU0-3 did not change.
diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt
index c2321903aa09..21bc416d887e 100644
--- a/Documentation/Intel-IOMMU.txt
+++ b/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.
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index c64158ecde43..a6d32e65d222 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/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
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 39ad8f56783a..9f711d2df91b 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/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.
+"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 42b01bc2e1b4..cf5562cbe356 100644
--- a/Documentation/RCU/checklist.txt
+++ b/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,
+        Another exception is where performance is not an issue, and RCU
-        and RCU provides a simpler implementation.  An example of this
+        provides a simpler implementation.  An example of this situation
-        situation is the dynamic NMI code in the Linux 2.6 kernel,
+        is the dynamic NMI code in the Linux 2.6 kernel, at least on
-        at least on architectures where NMIs are rare.
+        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
+        to prevent grace periods from ending prematurely, which
-        rcu_read_lock_bh()) in the read-side critical sections,
+        could result in data being unceremoniously freed out from
-        and are also an excellent aid to readability.
+        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(),
+5.      If call_rcu(), or a related primitive such as call_rcu_bh() or
-        is used, the callback function must be written to be called
+        call_rcu_sched(), is used, the callback function must be
-        from softirq context.  In particular, it cannot block.
+        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
+        rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
-        will result in confusion and broken kernels.
+        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(),
+8.      Although synchronize_rcu() is slower than is call_rcu(), it
-        it usually results in simpler code.  So, unless update
+        usually results in simpler code.  So, unless update performance
-        performance is critically important or the updaters cannot block,
+        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
+        The reason that it is permissible to use RCU list-traversal
-        RCU read-side critical section causes no harm other than
+        primitives when the update-side lock is held is that doing so
-        a slight performance degradation on Alpha CPUs.  It can
+        can be quite helpful in reducing code bloat when common code is
-        also be quite helpful in reducing code bloat when common
+        shared between readers and updaters.
-        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.
+        and you don't hold the appropriate update-side lock, you -must-
-        Failing to do so will break Alpha and confuse people reading
+        use the "_rcu()" variants of the list macros.  Failing to do so
-        your code.
+        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
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 2967a65269d8..a342b6e1cc10 100644
--- a/Documentation/RCU/torture.txt
+++ b/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
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
+result in the tests being loaded into the base kernel.  In this case,
-the test, perhaps using a script similar to the one shown at the end of
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
+whether the RCU torture tests are to be started immediately during
-to be able to end the test.
+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.
+irqreaders      Says to invoke RCU readers from irq level.  This is currently
-                The default is twice the number of CPUs.  Why twice?
+                done via timers.  Defaults to "1" for variants of RCU that
-                To properly exercise RCU implementations with preemptible
+                permit this.  (Or, more accurately, variants of RCU that do
-                read-side critical sections.
+                -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
+stutter         The length of time to run the test before pausing for this
-                The number of seconds to keep the test threads affinitied
+                same period of time.  Defaults to "stutter=5", so as
-                to a particular subset of the CPUs, defaults to 5 seconds.
+                to run and pause for (roughly) five-second intervals.
-                Used in conjunction with test_no_idle_hz.
+                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
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e0d6d99b8f9b..e04d643a9f57 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/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.
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 9c93a03ea33b..f79ad9ff6031 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -327,6 +327,52 @@ Some people also put extra tags at the end.  They'll just be ignored for
 now, but you can do this to mark internal company procedures or just
 point out some special detail about the sign-off. 
+If you are a subsystem or branch maintainer, sometimes you need to slightly
+modify patches you receive in order to merge them, because the code is not
+exactly the same in your tree and the submitters'. If you stick strictly to
+rule (c), you should ask the submitter to rediff, but this is a totally
+counter-productive waste of time and energy. Rule (b) allows you to adjust
+the code, but then it is very impolite to change one submitter's code and
+make him endorse your bugs. To solve this problem, it is recommended that
+you add a line between the last Signed-off-by header and yours, indicating
+the nature of your changes. While there is nothing mandatory about this, it
+seems like prepending the description with your mail and/or name, all
+enclosed in square brackets, is noticeable enough to make it obvious that
+you are responsible for last-minute changes. Example :
+        Signed-off-by: Random J Developer <random@developer.example.org>
+        [lucky@maintainer.example.org: struct foo moved from foo.c to foo.h]
+        Signed-off-by: Lucky K Maintainer <lucky@maintainer.example.org>
+This practise is particularly helpful if you maintain a stable branch and
+want at the same time to credit the author, track changes, merge the fix,
+and protect the submitter from complaints. Note that under no circumstances
+can you change the author's identity (the From header), as it is the one
+which appears in the changelog.
+Special note to back-porters: It seems to be a common and useful practise
+to insert an indication of the origin of a patch at the top of the commit
+message (just after the subject line) to facilitate tracking. For instance,
+here's what we see in 2.6-stable :
+    Date:   Tue May 13 19:10:30 2008 +0000
+        SCSI: libiscsi regression in 2.6.25: fix nop timer handling
+        commit 4cf1043593db6a337f10e006c23c69e5fc93e722 upstream
+And here's what appears in 2.4 :
+    Date:   Tue May 13 22:12:27 2008 +0200
+        wireless, airo: waitbusy() won't delay
+        [backport of 2.6 commit b7acbdfbd1f277c1eb23f344f899cfa4cd0bf36a]
+Whatever the format, this information provides a valuable help to people
+tracking your trees, and to people trying to trouble-shoot bugs in your
+tree.
 13) When to use Acked-by: and Cc:
@@ -482,7 +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
diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt
index 1443cd71d263..8a12f0730c94 100644
--- a/Documentation/accounting/delay-accounting.txt
+++ b/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
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 40121b5cca14..3f7755f3963f 100644
--- a/Documentation/accounting/getdelays.c
+++ b/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)
diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index 8aa7529f8258..e7512c061c15 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/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
@@ -24,6 +24,10 @@ There are three different groups of fields in the struct taskstats:
 4) Per-task and per-thread context switch count statistics
+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.
@@ -164,4 +168,13 @@ struct taskstats {
        __u64   nvcsw;                  /* Context voluntary switch counter */
        __u64   nivcsw;                 /* Context involuntary switch counter */
+5) Time accounting for SMT machines
+        __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;
 }
diff --git a/Documentation/arm/Interrupts b/Documentation/arm/Interrupts
index 0d3dbf1099bc..c202ed35d7d6 100644
--- a/Documentation/arm/Interrupts
+++ b/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:
+                function.  Type should be one of IRQ_TYPE_xxx defined in
+                <linux/irq.h>
-                #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)
 3. set_GPIO_IRQ_edge() is obsolete, and should be replaced by set_irq_type.
diff --git a/Documentation/auxdisplay/cfag12864b b/Documentation/auxdisplay/cfag12864b
index b714183d4125..eb7be393a510 100644
--- a/Documentation/auxdisplay/cfag12864b
+++ b/Documentation/auxdisplay/cfag12864b
@@ -3,7 +3,7 @@
        ===================================
 License:                GPLv2
-Author & Maintainer:    Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:    Miguel Ojeda Sandonis
 Date:                   2006-10-27
@@ -22,7 +22,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
-This driver support one cfag12864b display at time.
+This driver supports a cfag12864b LCD.
 ---------------------
diff --git a/Documentation/auxdisplay/cfag12864b-example.c b/Documentation/auxdisplay/cfag12864b-example.c
index 7bfac354d4c9..2caeea5e4993 100644
--- a/Documentation/auxdisplay/cfag12864b-example.c
+++ b/Documentation/auxdisplay/cfag12864b-example.c
@@ -4,7 +4,7 @@
 * Description: cfag12864b LCD userspace example program
 *     License: GPLv2
 *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
 *        Date: 2006-10-31
 *
 *  This program is free software; you can redistribute it and/or modify
diff --git a/Documentation/auxdisplay/ks0108 b/Documentation/auxdisplay/ks0108
index 92b03b60c613..8ddda0c8ceef 100644
--- a/Documentation/auxdisplay/ks0108
+++ b/Documentation/auxdisplay/ks0108
@@ -3,7 +3,7 @@
        ==========================================
 License:                GPLv2
-Author & Maintainer:    Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:    Miguel Ojeda Sandonis
 Date:                   2006-10-27
@@ -21,7 +21,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
-This driver support the ks0108 LCD controller.
+This driver supports the ks0108 LCD controller.
 ---------------------
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
new file mode 100644
index 000000000000..e9dc8d86adc7
--- /dev/null
+++ b/Documentation/block/data-integrity.txt
@@ -0,0 +1,327 @@
+----------------------------------------------------------------------
+1. INTRODUCTION
+Modern filesystems feature checksumming of data and metadata to
+protect against data corruption.  However, the detection of the
+corruption is done at read time which could potentially be months
+after the data was written.  At that point the original data that the
+application tried to write is most likely lost.
+The solution is to ensure that the disk is actually storing what the
+application meant it to.  Recent additions to both the SCSI family
+protocols (SBC Data Integrity Field, SCC protection proposal) as well
+as SATA/T13 (External Path Protection) try to remedy this by adding
+support for appending integrity metadata to an I/O.  The integrity
+metadata (or protection information in SCSI terminology) includes a
+checksum for each sector as well as an incrementing counter that
+ensures the individual sectors are written in the right order.  And
+for some protection schemes also that the I/O is written to the right
+place on disk.
+Current storage controllers and devices implement various protective
+measures, for instance checksumming and scrubbing.  But these
+technologies are working in their own isolated domains or at best
+between adjacent nodes in the I/O path.  The interesting thing about
+DIF and the other integrity extensions is that the protection format
+is well defined and every node in the I/O path can verify the
+integrity of the I/O and reject it if corruption is detected.  This
+allows not only corruption prevention but also isolation of the point
+of failure.
+----------------------------------------------------------------------
+2. THE DATA INTEGRITY EXTENSIONS
+As written, the protocol extensions only protect the path between
+controller and storage device.  However, many controllers actually
+allow the operating system to interact with the integrity metadata
+(IMD).  We have been working with several FC/SAS HBA vendors to enable
+the protection information to be transferred to and from their
+controllers.
+The SCSI Data Integrity Field works by appending 8 bytes of protection
+information to each sector.  The data + integrity metadata is stored
+in 520 byte sectors on disk.  Data + IMD are interleaved when
+transferred between the controller and target.  The T13 proposal is
+similar.
+Because it is highly inconvenient for operating systems to deal with
+520 (and 4104) byte sectors, we approached several HBA vendors and
+encouraged them to allow separation of the data and integrity metadata
+scatter-gather lists.
+The controller will interleave the buffers on write and split them on
+read.  This means that the Linux can DMA the data buffers to and from
+host memory without changes to the page cache.
+Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs
+is somewhat heavy to compute in software.  Benchmarks found that
+calculating this checksum had a significant impact on system
+performance for a number of workloads.  Some controllers allow a
+lighter-weight checksum to be used when interfacing with the operating
+system.  Emulex, for instance, supports the TCP/IP checksum instead.
+The IP checksum received from the OS is converted to the 16-bit CRC
+when writing and vice versa.  This allows the integrity metadata to be
+generated by Linux or the application at very low cost (comparable to
+software RAID5).
+The IP checksum is weaker than the CRC in terms of detecting bit
+errors.  However, the strength is really in the separation of the data
+buffers and the integrity metadata.  These two distinct buffers much
+match up for an I/O to complete.
+The separation of the data and integrity metadata buffers as well as
+the choice in checksums is referred to as the Data Integrity
+Extensions.  As these extensions are outside the scope of the protocol
+bodies (T10, T13), Oracle and its partners are trying to standardize
+them within the Storage Networking Industry Association.
+----------------------------------------------------------------------
+3. KERNEL CHANGES
+The data integrity framework in Linux enables protection information
+to be pinned to I/Os and sent to/received from controllers that
+support it.
+The advantage to the integrity extensions in SCSI and SATA is that
+they enable us to protect the entire path from application to storage
+device.  However, at the same time this is also the biggest
+disadvantage. It means that the protection information must be in a
+format that can be understood by the disk.
+Generally Linux/POSIX applications are agnostic to the intricacies of
+the storage devices they are accessing.  The virtual filesystem switch
+and the block layer make things like hardware sector size and
+transport protocols completely transparent to the application.
+However, this level of detail is required when preparing the
+protection information to send to a disk.  Consequently, the very
+concept of an end-to-end protection scheme is a layering violation.
+It is completely unreasonable for an application to be aware whether
+it is accessing a SCSI or SATA disk.
+The data integrity support implemented in Linux attempts to hide this
+from the application.  As far as the application (and to some extent
+the kernel) is concerned, the integrity metadata is opaque information
+that's attached to the I/O.
+The current implementation allows the block layer to automatically
+generate the protection information for any I/O.  Eventually the
+intent is to move the integrity metadata calculation to userspace for
+user data.  Metadata and other I/O that originates within the kernel
+will still use the automatic generation interface.
+Some storage devices allow each hardware sector to be tagged with a
+16-bit value.  The owner of this tag space is the owner of the block
+device.  I.e. the filesystem in most cases.  The filesystem can use
+this extra space to tag sectors as they see fit.  Because the tag
+space is limited, the block interface allows tagging bigger chunks by
+way of interleaving.  This way, 8*16 bits of information can be
+attached to a typical 4KB filesystem block.
+This also means that applications such as fsck and mkfs will need
+access to manipulate the tags from user space.  A passthrough
+interface for this is being worked on.
+----------------------------------------------------------------------
+4. BLOCK LAYER IMPLEMENTATION DETAILS
+4.1 BIO
+The data integrity patches add a new field to struct bio when
+CONFIG_BLK_DEV_INTEGRITY is enabled.  bio->bi_integrity is a pointer
+to a struct bip which contains the bio integrity payload.  Essentially
+a bip is a trimmed down struct bio which holds a bio_vec containing
+the integrity metadata and the required housekeeping information (bvec
+pool, vector count, etc.)
+A kernel subsystem can enable data integrity protection on a bio by
+calling bio_integrity_alloc(bio).  This will allocate and attach the
+bip to the bio.
+Individual pages containing integrity metadata can subsequently be
+attached using bio_integrity_add_page().
+bio_free() will automatically free the bip.
+4.2 BLOCK DEVICE
+Because the format of the protection data is tied to the physical
+disk, each block device has been extended with a block integrity
+profile (struct blk_integrity).  This optional profile is registered
+with the block layer using blk_integrity_register().
+The profile contains callback functions for generating and verifying
+the protection data, as well as getting and setting application tags.
+The profile also contains a few constants to aid in completing,
+merging and splitting the integrity metadata.
+Layered block devices will need to pick a profile that's appropriate
+for all subdevices.  blk_integrity_compare() can help with that.  DM
+and MD linear, RAID0 and RAID1 are currently supported.  RAID4/5/6
+will require extra work due to the application tag.
+----------------------------------------------------------------------
+5.0 BLOCK LAYER INTEGRITY API
+5.1 NORMAL FILESYSTEM
+    The normal filesystem is unaware that the underlying block device
+    is capable of sending/receiving integrity metadata.  The IMD will
+    be automatically generated by the block layer at submit_bio() time
+    in case of a WRITE.  A READ request will cause the I/O integrity
+    to be verified upon completion.
+    IMD generation and verification can be toggled using the
+      /sys/block/<bdev>/integrity/write_generate
+    and
+      /sys/block/<bdev>/integrity/read_verify
+    flags.
+5.2 INTEGRITY-AWARE FILESYSTEM
+    A filesystem that is integrity-aware can prepare I/Os with IMD
+    attached.  It can also use the application tag space if this is
+    supported by the block device.
+    int bdev_integrity_enabled(block_device, int rw);
+      bdev_integrity_enabled() will return 1 if the block device
+      supports integrity metadata transfer for the data direction
+      specified in 'rw'.
+      bdev_integrity_enabled() honors the write_generate and
+      read_verify flags in sysfs and will respond accordingly.
+    int bio_integrity_prep(bio);
+      To generate IMD for WRITE and to set up buffers for READ, the
+      filesystem must call bio_integrity_prep(bio).
+      Prior to calling this function, the bio data direction and start
+      sector must be set, and the bio should have all data pages
+      added.  It is up to the caller to ensure that the bio does not
+      change while I/O is in progress.
+      bio_integrity_prep() should only be called if
+      bio_integrity_enabled() returned 1.
+    int bio_integrity_tag_size(bio);
+      If the filesystem wants to use the application tag space it will
+      first have to find out how much storage space is available.
+      Because tag space is generally limited (usually 2 bytes per
+      sector regardless of sector size), the integrity framework
+      supports interleaving the information between the sectors in an
+      I/O.
+      Filesystems can call bio_integrity_tag_size(bio) to find out how
+      many bytes of storage are available for that particular bio.
+      Another option is bdev_get_tag_size(block_device) which will
+      return the number of available bytes per hardware sector.
+    int bio_integrity_set_tag(bio, void *tag_buf, len);
+      After a successful return from bio_integrity_prep(),
+      bio_integrity_set_tag() can be used to attach an opaque tag
+      buffer to a bio.  Obviously this only makes sense if the I/O is
+      a WRITE.
+    int bio_integrity_get_tag(bio, void *tag_buf, len);
+      Similarly, at READ I/O completion time the filesystem can
+      retrieve the tag buffer using bio_integrity_get_tag().
+6.3 PASSING EXISTING INTEGRITY METADATA
+    Filesystems that either generate their own integrity metadata or
+    are capable of transferring IMD from user space can use the
+    following calls:
+    struct bip * bio_integrity_alloc(bio, gfp_mask, nr_pages);
+      Allocates the bio integrity payload and hangs it off of the bio.
+      nr_pages indicate how many pages of protection data need to be
+      stored in the integrity bio_vec list (similar to bio_alloc()).
+      The integrity payload will be freed at bio_free() time.
+    int bio_integrity_add_page(bio, page, len, offset);
+      Attaches a page containing integrity metadata to an existing
+      bio.  The bio must have an existing bip,
+      i.e. bio_integrity_alloc() must have been called.  For a WRITE,
+      the integrity metadata in the pages must be in a format
+      understood by the target device with the notable exception that
+      the sector numbers will be remapped as the request traverses the
+      I/O stack.  This implies that the pages added using this call
+      will be modified during I/O!  The first reference tag in the
+      integrity metadata must have a value of bip->bip_sector.
+      Pages can be added using bio_integrity_add_page() as long as
+      there is room in the bip bio_vec array (nr_pages).
+      Upon completion of a READ operation, the attached pages will
+      contain the integrity metadata received from the storage device.
+      It is up to the receiver to process them and verify data
+      integrity upon completion.
+6.4 REGISTERING A BLOCK DEVICE AS CAPABLE OF EXCHANGING INTEGRITY
+    METADATA
+    To enable integrity exchange on a block device the gendisk must be
+    registered as capable:
+    int blk_integrity_register(gendisk, blk_integrity);
+      The blk_integrity struct is a template and should contain the
+      following:
+        static struct blk_integrity my_profile = {
+            .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
+            .generate_fn            = my_generate_fn,
+            .verify_fn              = my_verify_fn,
+            .get_tag_fn             = my_get_tag_fn,
+            .set_tag_fn             = my_set_tag_fn,
+            .tuple_size             = sizeof(struct my_tuple_size),
+            .tag_size               = <tag bytes per hw sector>,
+        };
+      'name' is a text string which will be visible in sysfs.  This is
+      part of the userland API so chose it carefully and never change
+      it.  The format is standards body-type-variant.
+      E.g. T10-DIF-TYPE1-IP or T13-EPP-0-CRC.
+      'generate_fn' generates appropriate integrity metadata (for WRITE).
+      'verify_fn' verifies that the data buffer matches the integrity
+      metadata.
+      'tuple_size' must be set to match the size of the integrity
+      metadata per sector.  I.e. 8 for DIF and EPP.
+      'tag_size' must be set to identify how many bytes of tag space
+      are available per hardware sector.  For DIF this is either 2 or
+      0 depending on the value of the Control Mode Page ATO bit.
+      See 6.2 for a description of get_tag_fn and set_tag_fn.
+----------------------------------------------------------------------
+2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/Documentation/bt8xxgpio.txt b/Documentation/bt8xxgpio.txt
new file mode 100644
index 000000000000..d8297e4ebd26
--- /dev/null
+++ b/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
diff --git a/Documentation/cciss.txt b/Documentation/cciss.txt
index e65736c6b8bc..63e59b8847c5 100644
--- a/Documentation/cciss.txt
+++ b/Documentation/cciss.txt
@@ -21,6 +21,11 @@ This driver is known to work with the following cards:
        * SA E200
        * SA E200i
        * SA E500
+        * SA P212
+        * SA P410
+        * SA P410i
+        * SA P411
+        * SA P812
 Detecting drive failures:
 -------------------------
diff --git a/Documentation/cgroups.txt b/Documentation/cgroups.txt
index c298a6690e0d..d9014aa0eb68 100644
--- a/Documentation/cgroups.txt
+++ b/Documentation/cgroups.txt
@@ -310,8 +310,8 @@ and then start a subshell 'sh' in that cgroup:
  cd /dev/cgroup
  mkdir Charlie
  cd Charlie
-  /bin/echo 2-3 > cpus
+  /bin/echo 2-3 > cpuset.cpus
-  /bin/echo 1 > mems
+  /bin/echo 1 > cpuset.mems
  /bin/echo $$ > tasks
  sh
  # The subshell 'sh' is now running in cgroup Charlie
@@ -390,6 +390,10 @@ If you have several tasks to attach, you have to do it one after another:
        ...
 # /bin/echo PIDn > tasks
+You can attach the current shell task by echoing 0:
+# echo 0 > tasks
 3. Kernel API
 =============
diff --git a/Documentation/controllers/devices.txt b/Documentation/controllers/devices.txt
index 4dcea42432c2..7cc6e6a60672 100644
--- a/Documentation/controllers/devices.txt
+++ b/Documentation/controllers/devices.txt
@@ -13,7 +13,7 @@ either an integer or * for all.  Access is a composition of r
 The root device cgroup starts with rwm to 'all'.  A child device
 cgroup gets a copy of the parent.  Administrators can then remove
 devices from the whitelist or add new entries.  A child cgroup can
-never receive a device access which is denied its parent.  However
+never receive a device access which is denied by its parent.  However
 when a device access is removed from a parent it will not also be
 removed from the child(ren).
@@ -29,7 +29,11 @@ allows cgroup 1 to read and mknod the device usually known as
        echo a > /cgroups/1/devices.deny
-will remove the default 'a *:* mrw' entry.
+will remove the default 'a *:* rwm' entry. Doing
+        echo a > /cgroups/1/devices.allow
+will add the 'a *:* rwm' entry to the whitelist.
 3. Security
diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
index 866b9cd9a959..9b53d5827361 100644
--- a/Documentation/controllers/memory.txt
+++ b/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
+4. Start reclamation in the background when the limit is
-5. Start reclamation in the background when the limit is
   not yet hit but the usage is getting closer
 Summary
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index 6a9c55bd556b..5b0cfa67aff9 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -122,21 +122,13 @@ 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
 intervals the CPU needs to be on average more than 80% in use to then
 decide that the CPU frequency needs to be increased.  
-sampling_down_factor: this parameter controls the rate that the CPU
-makes a decision on when to decrease the frequency.  When set to its
-default value of '5' it means that at 1/5 the sampling_rate the kernel
-makes a decision to lower the frequency.  Five "lower rate" decisions
-have to be made in a row before the CPU frequency is actually lower.
-If set to '1' then the frequency decreases as quickly as it increases,
-if set to '2' it decreases at half the rate of the increase.
 ignore_nice_load: this parameter takes a value of '0' or '1'. When
 set to '0' (its default), all processes are counted towards the
 'cpu utilisation' value.  When set to '1', the processes that are
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index fb7b361e6eea..1f5a924d1e56 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -154,13 +154,15 @@ browsing and modifying the cpusets presently known to the kernel.  No
 new system calls are added for cpusets - all support for querying and
 modifying cpusets is via this cpuset file system.
-The /proc/<pid>/status file for each task has two added lines,
+The /proc/<pid>/status file for each task has four added lines,
 displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
 and mems_allowed (on which Memory Nodes it may obtain memory),
-in the format seen in the following example:
+in the two formats seen in the following example:
  Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
+  Cpus_allowed_list:      0-127
  Mems_allowed:   ffffffff,ffffffff
+  Mems_allowed_list:      0-63
 Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
@@ -199,7 +201,7 @@ using the sched_setaffinity, mbind and set_mempolicy system calls.
 The following rules apply to each cpuset:
 - Its CPUs and Memory Nodes must be a subset of its parents.
- - It can only be marked exclusive if its parent is.
+ - It can't be marked exclusive unless its parent is.
 - If its cpu or memory is exclusive, they may not overlap any sibling.
 These rules, and the natural hierarchy of cpusets, enable efficient
@@ -345,7 +347,7 @@ is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
-Similarly, setting 'memory_spread_cache' turns on the flag
+Similarly, setting 'memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
@@ -542,7 +544,10 @@ otherwise initial value -1 that indicates the cpuset has no request.
   2  : search cores in a package.
   3  : search cpus in a node [= system wide on non-NUMA system]
 ( 4  : search nodes in a chunk of node [on NUMA system] )
- ( 5~ : search system wide [on NUMA system])
+ ( 5  : search system wide [on NUMA system] )
+The system default is architecture dependent.  The system default
+can be changed using the relax_domain_level= boot parameter.
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
@@ -709,7 +714,10 @@ Now you want to do something with this cpuset.
 In this directory you can find several files:
 # ls
-cpus  cpu_exclusive  mems  mem_exclusive mem_hardwall  tasks
+cpu_exclusive  memory_migrate      mems                      tasks
+cpus           memory_pressure     notify_on_release
+mem_exclusive  memory_spread_page  sched_load_balance
+mem_hardwall   memory_spread_slab  sched_relax_domain_level
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index b61cb9564023..bd699da24666 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,9 +14,8 @@ represent the thread siblings to cpu X in the same physical package;
 To implement it in an architecture-neutral way, a new source file,
 drivers/base/topology.c, is to export the 4 attributes.
-If one architecture wants to support this feature, it just needs to
+For an architecture to support this feature, it must define some of
-implement 4 defines, typically in file include/asm-XXX/topology.h.
+these macros in include/asm-XXX/topology.h:
-The 4 defines are:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_thread_siblings(cpu)
@@ -25,17 +24,10 @@ The 4 defines are:
 The type of **_id is int.
 The type of siblings is cpumask_t.
-To be consistent on all architectures, the 4 attributes should have
+To be consistent on all architectures, include/linux/topology.h
-default values if their values are unavailable. Below is the rule.
+provides default definitions for any of the above macros that are
-1) physical_package_id: If cpu has no physical package id, -1 is the
+not defined by include/asm-XXX/topology.h:
-default value.
+1) physical_package_id: -1
-2) core_id: If cpu doesn't support multi-core, its core id is 0.
+2) core_id: 0
-3) thread_siblings: Just include itself, if the cpu doesn't support
+3) thread_siblings: just the given CPU
-HT/multi-thread.
+4) core_siblings: just the given CPU
-4) core_siblings: Just include itself, if the cpu doesn't support
-multi-core and HT/Multi-thread.
-So be careful when declaring the 4 defines in include/asm-XXX/topology.h.
-If an attribute isn't defined on an architecture, it won't be exported.
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index a5c36842ecef..8eda3fb66416 100644
--- a/Documentation/edac.txt
+++ b/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
+        echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe
-Parity Count:
-        'pci_parity_count'
-        This attribute file will display the number of parity errors that
-        have been detected.
diff --git a/Documentation/fb/sh7760fb.txt b/Documentation/fb/sh7760fb.txt
new file mode 100644
index 000000000000..c87bfe5c630a
--- /dev/null
+++ b/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 ======================================
diff --git a/Documentation/fb/tridentfb.txt b/Documentation/fb/tridentfb.txt
index 8a6c8a43e6a3..45d9de5b13a3 100644
--- a/Documentation/fb/tridentfb.txt
+++ b/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 from the TGUI series 9440/96XX and with Cyber in their names
-those with Blade in their names (Blade3D,CyberBlade...) - accelerated
+those from the Image series and with Cyber in their names
-the newer CyberBladeXP family  - nonaccelerated
+those with Blade in their names (Blade3D,CyberBlade...)
+the newer CyberBladeXP family
-Only PCI/AGP based cards are supported, none of the older Tridents.
+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.
+          configurable size. Otherwise use memsize.
-          If in some modes which barely fit the memory you see garbage at the bottom
+          If in some modes which barely fit the memory you see garbage
-          this might help by not letting change to that mode anymore.
+          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)
+bpp     - bits per pixel (8,16 or 32)
-mode - a mode name like 800x600 (as described in Documentation/fb/modedb.txt)
+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
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 3c35d452b1a9..c23955404bf5 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/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.
@@ -222,13 +228,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 ---------------------------
-What:   i2c-i810, i2c-prosavage and i2c-savage4
-When:   May 2008
-Why:    These drivers are superseded by i810fb, intelfb and savagefb.
-Who:    Jean Delvare <khali@linux-fr.org>
---------------------------
 What (Why):
        - include/linux/netfilter_ipv4/ipt_TOS.h ipt_tos.h header files
          (superseded by xt_TOS/xt_tos target & match)
@@ -289,6 +288,14 @@ Who:	Glauber Costa <gcosta@redhat.com>
 ---------------------------
+What:   old style serial driver for ColdFire (CONFIG_SERIAL_COLDFIRE)
+When:   2.6.28
+Why:    This driver still uses the old interface and has been replaced
+        by CONFIG_SERIAL_MCF.
+Who:    Sebastian Siewior <sebastian@breakpoint.cc>
+---------------------------
 What:   /sys/o2cb symlink
 When:   January 2010
 Why:    /sys/fs/o2cb is the proper location for this information - /sys/o2cb
@@ -299,8 +306,41 @@ Who:	ocfs2-devel@oss.oracle.com
 ---------------------------
-What:   asm/semaphore.h
+What:   SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD,
-When:   2.6.26
+        SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD
-Why:    Implementation became generic; users should now include
+When:   June 2009
-        linux/semaphore.h instead.
+Why:    A newer version of the options have been introduced in 2005 that
-Who:    Matthew Wilcox <willy@linux.intel.com>
+        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>
+---------------------------
+What:   CONFIG_THERMAL_HWMON
+When:   January 2009
+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>
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index c2992bc54f2f..680fb566b928 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -92,7 +92,6 @@ prototypes:
        void (*destroy_inode)(struct inode *);
        void (*dirty_inode) (struct inode *);
        int (*write_inode) (struct inode *, int);
-        void (*put_inode) (struct inode *);
        void (*drop_inode) (struct inode *);
        void (*delete_inode) (struct inode *);
        void (*put_super) (struct super_block *);
@@ -115,7 +114,6 @@ alloc_inode:		no	no	no
 destroy_inode:          no
 dirty_inode:            no                              (must not sleep)
 write_inode:            no
-put_inode:              no
 drop_inode:             no                              !!!inode_lock!!!
 delete_inode:           no
 put_super:              yes     yes     no
@@ -512,6 +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)
@@ -519,6 +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
@@ -527,6 +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
diff --git a/Documentation/filesystems/bfs.txt b/Documentation/filesystems/bfs.txt
index ea825e178e79..78043d5a8fc3 100644
--- a/Documentation/filesystems/bfs.txt
+++ b/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 
+loaded automatically, make sure that you have compiled the module and
-support (CONFIG_KMOD) enabled. Beware that umount will not
+that modprobe is functioning. Beware that umount will not deallocate
-deallocate /dev/loopN device if /etc/mtab file on your system is a
+/dev/loopN device if /etc/mtab file on your system is a symbolic link to
-symbolic link to /proc/mounts. You will need to do it manually using
+/proc/mounts. You will need to do it manually using "-d" switch of
-"-d" switch of losetup(8). Read losetup(8) manpage for more info.
+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:
diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c
index 25151fd5c2c6..039648791701 100644
--- a/Documentation/filesystems/configfs/configfs_example.c
+++ b/Documentation/filesystems/configfs/configfs_example.c
@@ -279,7 +279,7 @@ static struct config_item *simple_children_make_item(struct config_group *group,
        simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
        if (!simple_child)
-                return NULL;
+                return ERR_PTR(-ENOMEM);
        config_item_init_type_name(&simple_child->item, name,
@@ -366,7 +366,7 @@ static struct config_group *group_children_make_group(struct config_group *group
        simple_children = kzalloc(sizeof(struct simple_children),
                                  GFP_KERNEL);
        if (!simple_children)
-                return NULL;
+                return ERR_PTR(-ENOMEM);
        config_group_init_type_name(&simple_children->group, name,
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 560f88dc7090..80e193d82e2e 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -13,72 +13,93 @@ Mailing list: linux-ext4@vger.kernel.org
 1. Quick usage instructions:
 ===========================
-  - Grab updated e2fsprogs from
+  - Compile and install the latest version of e2fsprogs (as of this
-    ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs-interim/
+    writing version 1.41) from:
-    This is a patchset on top of e2fsprogs-1.39, which can be found at
+    http://sourceforge.net/project/showfiles.php?group_id=2406
+        
+        or
    ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
-  - It's still mke2fs -j /dev/hda1
+        or grab the latest git repository from:
+    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
+  - Create a new filesystem using the ext4dev filesystem type:
+        # mke2fs -t ext4dev /dev/hda1
+    Or configure an existing ext3 filesystem to support extents and set
+    the test_fs flag to indicate that it's ok for an in-development
+    filesystem to touch this filesystem:
-  - mount /dev/hda1 /wherever -t ext4dev
+        # tune2fs -O extents -E test_fs /dev/hda1
-  - To enable extents,
+    If the filesystem was created with 128 byte inodes, it can be
+    converted to use 256 byte for greater efficiency via:
-        mount /dev/hda1 /wherever -t ext4dev -o extents
+        # tune2fs -I 256 /dev/hda1
-  - The filesystem is compatible with the ext3 driver until you add a file
+    (Note: we currently do not have tools to convert an ext4dev
-    which has extents (ie: `mount -o extents', then create a file).
+    filesystem back to ext3; so please do not do try this on production
+    filesystems.)
-    NOTE: The "extents" mount flag is temporary.  It will soon go away and
+  - Mounting:
-    extents will be enabled by the "-o extents" flag to mke2fs or tune2fs
+        # mount -t ext4dev /dev/hda1 /wherever
  - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.  So
+    ext3/4 by default offers higher data integrity guarantees than most.
-    when comparing with a metadata-only journalling filesystem, use `mount -o
+    So when comparing with a metadata-only journalling filesystem, such
-    data=writeback'.  And you might as well use `mount -o nobh' too along
+    as ext3, use `mount -o data=writeback'.  And you might as well use
-    with it.  Making the journal larger than the mke2fs default often helps
+    `mount -o nobh' too along with it.  Making the journal larger than
-    performance with metadata-intensive workloads.
+    the mke2fs default often helps performance with metadata-intensive
+    workloads.
 2. Features
 ===========
 2.1 Currently available
-* ability to use filesystems > 16TB
+* ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
 * internal redunancy in tree
+* improved file allocation (multi-block alloc)
-2.1 Previously available, soon to be enabled by default by "mkefs.ext4":
+* fix 32000 subdirectory limit
+* nsec timestamps for mtime, atime, ctime, create time
-* dir_index and resize inode will be on by default
+* inode version field on disk (NFSv4, Lustre)
-* large inodes will be used by default for fast EAs, nsec timestamps, etc
+* reduced e2fsck time via uninit_bg feature
+* journal checksumming for robustness, performance
+* persistent file preallocation (e.g for streaming media, databases)
+* ability to pack bitmaps and inode tables into larger virtual groups via the
+  flex_bg feature
+* large file support
+* Inode allocation using large virtual block groups via flex_bg
+* delayed allocation
+* large block (up to pagesize) support
+* efficent new ordered mode in JBD2 and ext4(avoid using buffer head to force
+  the ordering)
 2.2 Candidate features for future inclusion
-There are several under discussion, whether they all make it in is
+* Online defrag (patches available but not well tested)
-partly a function of how much time everyone has to work on them:
+* reduced mke2fs time via lazy itable initialization in conjuction with
+  the uninit_bg feature (capability to do this is available in e2fsprogs
+  but a kernel thread to do lazy zeroing of unused inode table blocks
+  after filesystem is first mounted is required for safety)
-* improved file allocation (multi-block alloc, delayed alloc; basically done)
+There are several others under discussion, whether they all make it in is
-* fix 32000 subdirectory limit (patch exists, needs some e2fsck work)
+partly a function of how much time everyone has to work on them. Features like
-* nsec timestamps for mtime, atime, ctime, create time (patch exists,
+metadata checksumming have been discussed and planned for a bit but no patches
-  needs some e2fsck work)
+exist yet so I'm not sure they're in the near-term roadmap.
-* inode version field on disk (NFSv4, Lustre; prototype exists)
-* reduced mke2fs/e2fsck time via uninitialized groups (prototype exists)
-* journal checksumming for robustness, performance (prototype exists)
-* persistent file preallocation (e.g for streaming media, databases)
-Features like metadata checksumming have been discussed and planned for
+The big performance win will come with mballoc, delalloc and flex_bg
-a bit but no patches exist yet so I'm not sure they're in the near-term
+grouping of bitmaps and inode tables.  Some test results available here:
-roadmap.
-The big performance win will come with mballoc and delalloc.  CFS has
+ - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
-been using mballoc for a few years already with Lustre, and IBM + Bull
+ - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
-did a lot of benchmarking on it.  The reason it isn't in the first set of
-patches is partly a manageability issue, and partly because it doesn't
-directly affect the on-disk format (outside of much better allocation)
-so it isn't critical to get into the first round of changes.  I believe
-Alex is working on a new set of patches right now.
 3. Options
 ==========
@@ -139,8 +160,16 @@ commit=nrsec	(*)	Ext4 can be told to sync all its data and metadata
                        Setting it to very large values will improve
                        performance.
-barrier=1               This enables/disables barriers.  barrier=0 disables
+barrier=<0|1(*)>        This enables/disables the use of write barriers in
-                        it, barrier=1 enables it.
+                        the jbd code.  barrier=0 disables, barrier=1 enables.
+                        This also requires an IO stack which can support
+                        barriers, and if jbd gets an error on a barrier
+                        write, it will disable again with a warning.
+                        Write barriers enforce proper on-disk ordering
+                        of journal commits, making volatile disk write caches
+                        safe to use, at some performance penalty.  If
+                        your disks are battery-backed in one way or another,
+                        disabling barriers may safely improve performance.
 orlov           (*)     This enables the new Orlov block allocator. It is
                        enabled by default.
@@ -214,9 +243,11 @@ stripe=n		Number of filesystem blocks that mballoc will try
                        to use for allocation size and alignment. For RAID5/6
                        systems this should be the number of data
                        disks *  RAID chunk size in file system blocks.
+delalloc        (*)     Deferring block allocation until write-out time.
+nodelalloc              Disable delayed allocation. Blocks are allocation
+                        when data is copied from user to page cache.
 Data Mode
---------
+=========
 There are 3 different data modes:
 * writeback mode
@@ -228,10 +259,10 @@ typically provide the best ext4 performance.
 * ordered mode
 In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata and data blocks into a single unit called a transaction.  When
+groups metadata information related to data changes with the data blocks into a
-it's time to write the new metadata out to disk, the associated data blocks
+single unit called a transaction.  When it's time to write the new metadata
-are written first.  In general, this mode performs slightly slower than
+out to disk, the associated data blocks are written first.  In general,
-writeback but significantly faster than journal mode.
+this mode performs slightly slower than writeback but significantly faster than journal mode.
 * journal mode
 data=journal mode provides full data and metadata journaling.  All new data is
@@ -239,7 +270,8 @@ written to the journal first, and then to its final location.
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.
+outperforms all others modes.  Curently ext4 does not have delayed
+allocation support if this data journalling mode is selected.
 References
 ==========
@@ -248,7 +280,8 @@ kernel source:	<file:fs/ext4/>
                <file:fs/jbd2/>
 programs:       http://e2fsprogs.sourceforge.net/
-                http://ext2resize.sourceforge.net
 useful links:   http://fedoraproject.org/wiki/ext3-devel
                http://www.bullopensource.org/ext4/
+                http://ext4.wiki.kernel.org/index.php/Main_Page
+                http://fedoraproject.org/wiki/Features/Ext4
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
new file mode 100644
index 000000000000..4dae9a3840bf
--- /dev/null
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -0,0 +1,114 @@
+                   Glock internal locking rules
+                  ------------------------------
+This documents the basic principles of the glock state machine
+internals. Each glock (struct gfs2_glock in fs/gfs2/incore.h)
+has two main (internal) locks:
+ 1. A spinlock (gl_spin) which protects the internal state such
+    as gl_state, gl_target and the list of holders (gl_holders)
+ 2. A non-blocking bit lock, GLF_LOCK, which is used to prevent other
+    threads from making calls to the DLM, etc. at the same time. If a
+    thread takes this lock, it must then call run_queue (usually via the
+    workqueue) when it releases it in order to ensure any pending tasks
+    are completed.
+The gl_holders list contains all the queued lock requests (not
+just the holders) associated with the glock. If there are any
+held locks, then they will be contiguous entries at the head
+of the list. Locks are granted in strictly the order that they
+are queued, except for those marked LM_FLAG_PRIORITY which are
+used only during recovery, and even then only for journal locks.
+There are three lock states that users of the glock layer can request,
+namely shared (SH), deferred (DF) and exclusive (EX). Those translate
+to the following DLM lock modes:
+Glock mode    | DLM lock mode
+------------------------------
+    UN        |    IV/NL  Unlocked (no DLM lock associated with glock) or NL
+    SH        |    PR     (Protected read)
+    DF        |    CW     (Concurrent write)
+    EX        |    EX     (Exclusive)
+Thus DF is basically a shared mode which is incompatible with the "normal"
+shared lock mode, SH. In GFS2 the DF mode is used exclusively for direct I/O
+operations. The glocks are basically a lock plus some routines which deal
+with cache management. The following rules apply for the cache:
+Glock mode   |  Cache data | Cache Metadata | Dirty Data | Dirty Metadata
+--------------------------------------------------------------------------
+    UN       |     No      |       No       |     No     |      No
+    SH       |     Yes     |       Yes      |     No     |      No
+    DF       |     No      |       Yes      |     No     |      No
+    EX       |     Yes     |       Yes      |     Yes    |      Yes
+These rules are implemented using the various glock operations which
+are defined for each type of glock. Not all types of glocks use
+all the modes. Only inode glocks use the DF mode for example.
+Table of glock operations and per type constants:
+Field            | Purpose
+----------------------------------------------------------------------------
+go_xmote_th      | Called before remote state change (e.g. to sync dirty data)
+go_xmote_bh      | Called after remote state change (e.g. to refill cache)
+go_inval         | Called if remote state change requires invalidating the cache
+go_demote_ok     | Returns boolean value of whether its ok to demote a glock
+                 | (e.g. checks timeout, and that there is no cached data)
+go_lock          | Called for the first local holder of a lock
+go_unlock        | Called on the final local unlock of a lock
+go_dump          | Called to print content of object for debugfs file, or on
+                 | error to dump glock to the log.
+go_type;         | The type of the glock, LM_TYPE_.....
+go_min_hold_time | The minimum hold time
+The minimum hold time for each lock is the time after a remote lock
+grant for which we ignore remote demote requests. This is in order to
+prevent a situation where locks are being bounced around the cluster
+from node to node with none of the nodes making any progress. This
+tends to show up most with shared mmaped files which are being written
+to by multiple nodes. By delaying the demotion in response to a
+remote callback, that gives the userspace program time to make
+some progress before the pages are unmapped.
+There is a plan to try and remove the go_lock and go_unlock callbacks
+if possible, in order to try and speed up the fast path though the locking.
+Also, eventually we hope to make the glock "EX" mode locally shared
+such that any local locking will be done with the i_mutex as required
+rather than via the glock.
+Locking rules for glock operations:
+Operation     |  GLF_LOCK bit lock held |  gl_spin spinlock held
+-----------------------------------------------------------------
+go_xmote_th   |       Yes               |       No
+go_xmote_bh   |       Yes               |       No
+go_inval      |       Yes               |       No
+go_demote_ok  |       Sometimes         |       Yes
+go_lock       |       Yes               |       No
+go_unlock     |       Yes               |       No
+go_dump       |       Sometimes         |       Yes
+N.B. Operations must not drop either the bit lock or the spinlock
+if its held on entry. go_dump and do_demote_ok must never block.
+Note that go_dump will only be called if the glock's state
+indicates that it is caching uptodate data.
+Glock locking order within GFS2:
+ 1. i_mutex (if required)
+ 2. Rename glock (for rename only)
+ 3. Inode glock(s)
+    (Parents before children, inodes at "same level" with same parent in
+     lock number order)
+ 4. Rgrp glock(s) (for (de)allocation operations)
+ 5. Transaction glock (via gfs2_trans_begin) for non-read operations
+ 6. Page lock  (always last, very important!)
+There are two glocks per inode. One deals with access to the inode
+itself (locking order as above), and the other, known as the iopen
+glock is used in conjunction with the i_nlink field in the inode to
+determine the lifetime of the inode in question. Locking of inodes
+is on a per-inode basis. Locking of rgrps is on a per rgrp basis.
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index d0ec45ae4e7d..44bd766f2e5d 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/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
+    An NFS/RDMA mount point can be obtained by using the mount.nfs command in
-    command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs
+    nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils
-    you are using, type:
+    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,
+    If the version is less than 1.1.2 or the command does not exist,
-    then you will need to install the latest version of nfs-utils.
+    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
+    If you will not need the idmapper and gssd executables (you do not need
-    can be simplified by disabling these features when running configure:
+    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.
+    or v4 mounts. To initiate a v4 mount, the binary must be called
-    The standard technique is to create a symlink called mount.nfs4 to mount.nfs.
+    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_mthca
-    > modprobe ib_ipoib
+    $ 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
+    host1$ ifconfig ib0 a.b.c.x
-    host2> ifconfig ib0 a.b.c.y
+    host2$ ifconfig ib0 a.b.c.y
-    host1> ping a.b.c.y
+    host1$ ping a.b.c.y
-    host2> ping a.b.c.x
+    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
+    The IP address(es) is(are) the client's IPoIB address for an InfiniBand
-    cleint's iWARP address(es) for an RNIC.
+    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
+    NOTE: The "insecure" option must be used because the NFS/RDMA client does
-    use a reserved port.
+    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_mthca
-    > modprobe ib_ipoib
+    $ modprobe ib_ipoib
-    > ifconfig ib0 a.b.c.d
+    $ 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),
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    load the RDMA transport module:
+    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),
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    load the RDMA client module:
+    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
+    To verify that the mount is using RDMA, run "cat /proc/mounts" and check
-    "proto" field for the given mount.
+    the "proto" field for the given mount.
  Congratulations! You're using NFS/RDMA!
diff --git a/Documentation/filesystems/omfs.txt b/Documentation/filesystems/omfs.txt
new file mode 100644
index 000000000000..1d0d41ff5c65
--- /dev/null
+++ b/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.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index dbc3c6a3650f..64557821ee59 100644
--- a/Documentation/filesystems/proc.txt
+++ b/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
@@ -380,28 +381,35 @@ i386 and x86_64 platforms support the new IRQ vector displays.
 Of some interest is the introduction of the /proc/irq directory to 2.4.
 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
-irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask
+irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
+prof_cpu_mask.
 For example 
  > ls /proc/irq/
  0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
-  1  11  13  15  17  19  3  5  7  9
+  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
  > ls /proc/irq/0/
  smp_affinity
-The contents of the prof_cpu_mask file and each smp_affinity file for each IRQ
+smp_affinity is a bitmask, in which you can specify which CPUs can handle the
-is the same by default:
+IRQ, you can set it by doing:
-  > cat /proc/irq/0/smp_affinity 
+  > echo 1 > /proc/irq/10/smp_affinity
-  ffffffff
+This means that only the first CPU will handle the IRQ, but you can also echo
+5 which means that only the first and fourth CPU can handle the IRQ.
+The contents of each smp_affinity file is the same by default:
-It's a bitmask, in which you can specify which CPUs can handle the IRQ, you can
+  > cat /proc/irq/0/smp_affinity
-set it by doing:
+  ffffffff
-  > echo 1 > /proc/irq/prof_cpu_mask
+The default_smp_affinity mask applies to all non-active IRQs, which are the
+IRQs which have not yet been allocated/activated, and hence which lack a
+/proc/irq/[0-9]* directory.
-This means that only the first CPU will handle the IRQ, but you can also echo 5
+prof_cpu_mask specifies which CPUs are to be profiled by the system wide
-which means that only the first and fourth CPU can handle the IRQ.
+profiler. Default value is ffffffff (all cpus).
 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 between all the CPUs which are allowed to handle it. As usual the kernel has
@@ -550,6 +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
 ----------------------------
@@ -880,7 +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.
@@ -1423,7 +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]
diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
index 094f2d2f38b1..510b722667ac 100644
--- a/Documentation/filesystems/relay.txt
+++ b/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'
 ---------------
diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt
index 5daa2aaec2c5..68ef48839c04 100644
--- a/Documentation/filesystems/sysfs-pci.txt
+++ b/Documentation/filesystems/sysfs-pci.txt
@@ -36,6 +36,7 @@ files, each with their own function.
       local_cpus          nearby CPU mask (cpumask, ro)
       resource            PCI resource host addresses (ascii, ro)
       resource0..N        PCI resource N, if present (binary, mmap)
+       resource0_wc..N_wc  PCI WC map resource N, if prefetchable (binary, mmap)
       rom                 PCI ROM resource, if present (binary, ro)
       subsystem_device    PCI subsystem device (ascii, ro)
       subsystem_vendor    PCI subsystem vendor (ascii, ro)
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 7f27b8f840d0..9e9c348275a9 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/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/. 
diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt
new file mode 100644
index 000000000000..540e9e7f59c5
--- /dev/null
+++ b/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
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index 2d5e1e582e13..bbac4f1d9056 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/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
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 81e5be6e6e35..c4d348dabe94 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/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
@@ -205,7 +205,6 @@ struct super_operations {
        void (*dirty_inode) (struct inode *);
        int (*write_inode) (struct inode *, int);
-        void (*put_inode) (struct inode *);
        void (*drop_inode) (struct inode *);
        void (*delete_inode) (struct inode *);
        void (*put_super) (struct super_block *);
@@ -246,9 +245,6 @@ or bottom half).
        inode to disc.  The second parameter indicates whether the write
        should be synchronous or not, not all filesystems check this flag.
-  put_inode: called when the VFS inode is removed from the inode
-        cache.
  drop_inode: called when the last access to the inode is dropped,
        with the inode_lock spinlock held.
@@ -899,9 +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
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
new file mode 100644
index 000000000000..f218f616ff6b
--- /dev/null
+++ b/Documentation/ftrace.txt
@@ -0,0 +1,1360 @@
+                ftrace - Function Tracer
+                ========================
+Copyright 2008 Red Hat Inc.
+   Author:   Steven Rostedt <srostedt@redhat.com>
+  License:   The GNU Free Documentation License, Version 1.2
+Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
+             John Kacur, and David Teigland.
+Written for: 2.6.27-rc1
+Introduction
+------------
+Ftrace is an internal tracer designed to help out developers and
+designers of systems to find what is going on inside the kernel.
+It can be used for debugging or analyzing latencies and performance
+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 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 (ftrace allows for tracer plugins, which means that the list of
+tracers can always grow).
+The File System
+---------------
+Ftrace uses the debugfs file system to hold the control files as well
+as the files to display output.
+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)
+After mounting the debugfs, you can see a directory called
+"tracing".  This directory contains the control and output files
+of ftrace. Here is a list of some of the key files:
+ Note: all time values are in microseconds.
+  current_tracer : This is used to set or display the current tracer
+                that is configured.
+  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 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 to enable it.
+  trace : This file holds the output of the trace in a human readable
+                format (described below).
+  latency_trace : This file shows the same trace but the information
+                is organized more to display possible latencies
+                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.
+                Reads from this file will block until new data
+                is retrieved. Unlike the "trace" and "latency_trace"
+                files, this file is a consumer. This means reading
+                from this file causes sequential reads to display
+                more current data. Once data is read from this
+                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 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
+                that is displayed in one of the above output
+                files.
+  trace_max_latency : Some of the tracers record the max latency.
+                For example, the time interrupts are disabled.
+                This time is saved in this file. The max trace
+                will also be stored, and displayed by either
+                "trace" or "latency_trace".  A new max trace will
+                only be recorded if the latency is greater than
+                the value in this file. (in microseconds)
+  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. 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
+                entries.
+                This can only be updated when the current_tracer
+                is set to "none".
+                NOTE: It is planned on changing the allocated buffers
+                      from being the number of possible CPUS to
+                      the number of online CPUS.
+  tracing_cpumask : This is a mask that lets the user only trace
+                on specified CPUS. The format is a hex string
+                representing the CPUS.
+  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
+                later the call is converted into a nop. This file
+                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. (See the section "dynamic ftrace"
+                below for more details).
+The Tracers
+-----------
+Here is the list of current tracers that may be configured.
+  ftrace - function tracer that uses mcount to trace all functions.
+  sched_switch - traces the context switches between tasks.
+  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 via the latency_trace file.
+  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 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
+                it has been woken up.
+  none - This is not a tracer. To remove all tracers from tracing
+                simply echo "none" into current_tracer.
+Examples of using the tracer
+----------------------------
+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 is an example of the output format of the file "trace"
+                             --------
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4251  [01] 10152.583854: path_put <-path_walk
+            bash-4251  [01] 10152.583855: dput <-path_put
+            bash-4251  [01] 10152.583855: _atomic_dec_and_lock <-dput
+                             --------
+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". The timestamp is the time at which the function was
+entered.
+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
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +    10:115:S
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R ==>    10:115:R
+        events/1-10    [01]  1453.070013:     10:115:S ==>  2916:115:R
+     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 are shown as
+"==>".  The format is:
+ Context switches:
+       Previous task              Next Task
+  <pid>:<prio>:<state>  ==>  <pid>:<prio>:<state>
+ Wake ups:
+       Current task               Task waking up
+  <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
+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
+reserved for the idle task which is the lowest priority thread (pid 0).
+Latency trace format
+--------------------
+For traces that display latency times, the latency_trace file gives
+somewhat more information to see why a latency happened. Here is a typical
+trace.
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: apic_timer_interrupt
+ => ended at:   do_softirq
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+  <idle>-0     0d..1    0us+: trace_hardirqs_off_thunk (apic_timer_interrupt)
+  <idle>-0     0d.s.   97us : __do_softirq (do_softirq)
+  <idle>-0     0d.s1   98us : trace_hardirqs_on (do_softirq)
+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 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 occurred.
+(swapper pid: 0).
+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.
+The next lines after the header are the trace itself. The header
+explains which is which.
+  cmd: The name of the process in the trace.
+  pid: The PID of that process.
+  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 occurred inside a softirq.
+        'h' - hard irq is running
+        's' - soft irq is running
+        '.' - normal context.
+  preempt-depth: The level of preempt_disabled
+The above is mostly meaningful for kernel developers.
+  time: This differs from the trace file output. The trace file output
+        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
+        needs to be fixed to be only relative to the same CPU.
+        The marks are determined by the difference between this
+        current trace and the next trace.
+         '!' - greater than preempt_mark_thresh (default 100)
+         '+' - greater than 1 microsecond
+         ' ' - less than or equal to 1 microsecond.
+  The rest is the same as the 'trace' file.
+iter_ctrl
+---------
+The iter_ctrl file is used to control what gets printed in the trace
+output. To see what is available, simply cat the file:
+  cat /debug/tracing/iter_ctrl
+  print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
+ noblock nostacktrace nosched-tree
+To disable one of the options, echo in the option prepended with "no".
+  echo noprint-parent > /debug/tracing/iter_ctrl
+To enable an option, leave off the "no".
+  echo sym-offset > /debug/tracing/iter_ctrl
+Here are the available options:
+  print-parent - On function traces, display the calling function
+                as well as the function being traced.
+  print-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul <-strict_strtoul
+  noprint-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul
+  sym-offset - Display not only the function name, but also the offset
+                in the function. For example, instead of seeing just
+                "ktime_get", you will see "ktime_get+0xb/0x20".
+  sym-offset:
+   bash-4000  [01]  1477.606694: simple_strtoul+0x6/0xa0
+  sym-addr - this will also display the function address as well as
+                the function name.
+  sym-addr:
+   bash-4000  [01]  1477.606694: simple_strtoul <c0339346>
+  verbose - This deals with the latency_trace file.
+    bash  4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
+    (+0.000ms): simple_strtoul (strict_strtoul)
+  raw - This will display raw numbers. This option is best for use with
+        user applications that can translate the raw numbers better than
+        having it done in the kernel.
+  hex - Similar to raw, but the numbers will be in a hexadecimal format.
+  bin - This will print out the formats in raw binary.
+  block - TBD (needs update)
+  stacktrace - This is one of the options that changes the trace itself.
+                When a trace is recorded, so is the stack of functions.
+                This allows for back traces of trace sites.
+  sched-tree - TBD (any users??)
+sched_switch
+------------
+This tracer simply records schedule switches. Here is an example
+of how to use it.
+ # echo sched_switch > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # sleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: sched_switch
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-3997  [01]   240.132281:   3997:120:R   +  4055:120:R
+            bash-3997  [01]   240.132284:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132371:   4055:120:S ==>  3997:120:R
+            bash-3997  [01]   240.132454:   3997:120:R   +  4055:120:S
+            bash-3997  [01]   240.132457:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132460:   4055:120:D ==>  3997:120:R
+            bash-3997  [01]   240.132463:   3997:120:R   +  4055:120:D
+            bash-3997  [01]   240.132465:   3997:120:R ==>  4055:120:R
+          <idle>-0     [00]   240.132589:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132591:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132595:      4:115:S ==>     0:140:R
+          <idle>-0     [00]   240.132598:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132599:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132603:      4:115:S ==>     0:140:R
+           sleep-4055  [01]   240.133058:   4055:120:S ==>  3997:120:R
+ [...]
+As we have discussed previously about this format, the header shows
+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 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
+priority and the nice values starting at 100 (nice -20). Below is
+a quick chart to map the kernel priority to user land priorities.
+  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
+  Kernel priority: 100 to 139 ==> user nice -20 to 19
+  Kernel priority: 140        ==> idle task priority
+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 - 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
+ X - unknown
+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.
+  sysctl kernel.ftrace_enabled=1
+ or
+  echo 1 > /proc/sys/kernel/ftrace_enabled
+To disable ftrace_enabled simply replace the '1' with '0' in
+the above commands.
+When ftrace_enabled is set the tracers will also record the functions
+that are within the trace. The descriptions of the tracers
+will also show an example with ftrace enabled.
+irqsoff
+-------
+When interrupts are disabled, the CPU can not react to any other
+external event (besides NMIs and SMIs). This prevents the timer
+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 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 is an
+example:
+ # echo irqsoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26
+--------------------------------------------------------------------
+ latency: 12 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: bash-3730 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: sys_setpgid
+ => ended at:   sys_setpgid
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    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)
+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 example had ftrace_enabled not set. If we set the
+ftrace_enabled, we get a much larger output:
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: __alloc_pages_internal
+ => ended at:   __alloc_pages_internal
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4339  0...1    0us+: get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..1    3us : rmqueue_bulk (get_page_from_freelist)
+      ls-4339  0d..1    3us : _spin_lock (rmqueue_bulk)
+      ls-4339  0d..1    4us : add_preempt_count (_spin_lock)
+      ls-4339  0d..2    4us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    5us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    5us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    6us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    6us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    7us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    7us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    8us : __rmqueue_smallest (__rmqueue)
+[...]
+      ls-4339  0d..2   46us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   47us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   47us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2   48us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   48us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   49us : _spin_unlock (rmqueue_bulk)
+      ls-4339  0d..2   49us : sub_preempt_count (_spin_unlock)
+      ls-4339  0d..1   50us : get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..2   51us : trace_hardirqs_on (__alloc_pages_internal)
+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 incur an added overhead. This overhead may
+extend the latency times. But nevertheless, this trace has provided
+some very helpful debugging information.
+preemptoff
+----------
+When preemption is disabled, we may be able to receive interrupts but
+the task cannot be preempted and a higher priority task must wait
+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 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
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: do_IRQ
+ => ended at:   __do_softirq
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d.h.    0us+: irq_enter (do_IRQ)
+    sshd-4261  0d.s.   29us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1   30us : trace_preempt_on (__do_softirq)
+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
+when entering the preempt off section and leaving it (the 'd').
+We do not know if interrupts were enabled in the mean time.
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: remove_wait_queue
+ => ended at:   __do_softirq
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d..1    0us : _spin_lock_irqsave (remove_wait_queue)
+    sshd-4261  0d..1    1us : _spin_unlock_irqrestore (remove_wait_queue)
+    sshd-4261  0d..1    2us : do_IRQ (common_interrupt)
+    sshd-4261  0d..1    2us : irq_enter (do_IRQ)
+    sshd-4261  0d..1    2us : idle_cpu (irq_enter)
+    sshd-4261  0d..1    3us : add_preempt_count (irq_enter)
+    sshd-4261  0d.h1    3us : idle_cpu (irq_enter)
+    sshd-4261  0d.h.    4us : handle_fasteoi_irq (do_IRQ)
+[...]
+    sshd-4261  0d.h.   12us : add_preempt_count (_spin_lock)
+    sshd-4261  0d.h1   12us : ack_ioapic_quirk_irq (handle_fasteoi_irq)
+    sshd-4261  0d.h1   13us : move_native_irq (ack_ioapic_quirk_irq)
+    sshd-4261  0d.h1   13us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   14us : sub_preempt_count (_spin_unlock)
+    sshd-4261  0d.h1   14us : irq_exit (do_IRQ)
+    sshd-4261  0d.h1   15us : sub_preempt_count (irq_exit)
+    sshd-4261  0d..2   15us : do_softirq (irq_exit)
+    sshd-4261  0d...   15us : __do_softirq (do_softirq)
+    sshd-4261  0d...   16us : __local_bh_disable (__do_softirq)
+    sshd-4261  0d...   16us+: add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   20us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   21us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s5   21us : sub_preempt_count (local_bh_enable)
+[...]
+    sshd-4261  0d.s6   41us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s6   42us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s7   42us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s5   43us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s5   43us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s6   44us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s5   44us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s5   45us : sub_preempt_count (local_bh_enable)
+[...]
+    sshd-4261  0d.s.   63us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1   64us : trace_preempt_on (__do_softirq)
+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 from the functions themselves that
+this is not the case.
+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 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
+--------------
+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.
+Consider the following code:
+    local_irq_disable();
+    call_function_with_irqs_off();
+    preempt_disable();
+    call_function_with_irqs_and_preemption_off();
+    local_irq_enable();
+    call_function_with_preemption_off();
+    preempt_enable();
+The irqsoff tracer will record the total length of
+call_function_with_irqs_off() and
+call_function_with_irqs_and_preemption_off().
+The preemptoff tracer will record the total length of
+call_function_with_irqs_and_preemption_off() and
+call_function_with_preemption_off().
+But neither will trace the time that interrupts and/or preemption
+is disabled. This total time is the time that we can not schedule.
+To record this time, use the preemptirqsoff tracer.
+Again, using this trace is much like the irqsoff and preemptoff tracers.
+ # echo preemptirqsoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: preemptirqsoff
+#
+preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 293 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: ls-4860 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: apic_timer_interrupt
+ => ended at:   __do_softirq
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4860  0d...    0us!: trace_hardirqs_off_thunk (apic_timer_interrupt)
+      ls-4860  0d.s.  294us : _local_bh_enable (__do_softirq)
+      ls-4860  0d.s1  294us : trace_preempt_on (__do_softirq)
+The trace_hardirqs_off_thunk is called from assembly on x86 when
+interrupts are disabled in the assembly code. Without the function
+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:
+# tracer: preemptirqsoff
+#
+preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 105 us, #183/183, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: write_chan
+ => ended at:   __do_softirq
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4473  0.N..    0us : preempt_schedule (write_chan)
+      ls-4473  0dN.1    1us : _spin_lock (schedule)
+      ls-4473  0dN.1    2us : add_preempt_count (_spin_lock)
+      ls-4473  0d..2    2us : put_prev_task_fair (schedule)
+[...]
+      ls-4473  0d..2   13us : set_normalized_timespec (ktime_get_ts)
+      ls-4473  0d..2   13us : __switch_to (schedule)
+    sshd-4261  0d..2   14us : finish_task_switch (schedule)
+    sshd-4261  0d..2   14us : _spin_unlock_irq (finish_task_switch)
+    sshd-4261  0d..1   15us : add_preempt_count (_spin_lock_irqsave)
+    sshd-4261  0d..2   16us : _spin_unlock_irqrestore (hrtick_set)
+    sshd-4261  0d..2   16us : do_IRQ (common_interrupt)
+    sshd-4261  0d..2   17us : irq_enter (do_IRQ)
+    sshd-4261  0d..2   17us : idle_cpu (irq_enter)
+    sshd-4261  0d..2   18us : add_preempt_count (irq_enter)
+    sshd-4261  0d.h2   18us : idle_cpu (irq_enter)
+    sshd-4261  0d.h.   18us : handle_fasteoi_irq (do_IRQ)
+    sshd-4261  0d.h.   19us : _spin_lock (handle_fasteoi_irq)
+    sshd-4261  0d.h.   19us : add_preempt_count (_spin_lock)
+    sshd-4261  0d.h1   20us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   20us : sub_preempt_count (_spin_unlock)
+[...]
+    sshd-4261  0d.h1   28us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   29us : sub_preempt_count (_spin_unlock)
+    sshd-4261  0d.h2   29us : irq_exit (do_IRQ)
+    sshd-4261  0d.h2   29us : sub_preempt_count (irq_exit)
+    sshd-4261  0d..3   30us : do_softirq (irq_exit)
+    sshd-4261  0d...   30us : __do_softirq (do_softirq)
+    sshd-4261  0d...   31us : __local_bh_disable (__do_softirq)
+    sshd-4261  0d...   31us+: add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   34us : add_preempt_count (__local_bh_disable)
+[...]
+    sshd-4261  0d.s3   43us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s4   44us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s3   44us : smp_apic_timer_interrupt (apic_timer_interrupt)
+    sshd-4261  0d.s3   45us : irq_enter (smp_apic_timer_interrupt)
+    sshd-4261  0d.s3   45us : idle_cpu (irq_enter)
+    sshd-4261  0d.s3   46us : add_preempt_count (irq_enter)
+    sshd-4261  0d.H3   46us : idle_cpu (irq_enter)
+    sshd-4261  0d.H3   47us : hrtimer_interrupt (smp_apic_timer_interrupt)
+    sshd-4261  0d.H3   47us : ktime_get (hrtimer_interrupt)
+[...]
+    sshd-4261  0d.H3   81us : tick_program_event (hrtimer_interrupt)
+    sshd-4261  0d.H3   82us : ktime_get (tick_program_event)
+    sshd-4261  0d.H3   82us : ktime_get_ts (ktime_get)
+    sshd-4261  0d.H3   83us : getnstimeofday (ktime_get_ts)
+    sshd-4261  0d.H3   83us : set_normalized_timespec (ktime_get_ts)
+    sshd-4261  0d.H3   84us : clockevents_program_event (tick_program_event)
+    sshd-4261  0d.H3   84us : lapic_next_event (clockevents_program_event)
+    sshd-4261  0d.H3   85us : irq_exit (smp_apic_timer_interrupt)
+    sshd-4261  0d.H3   85us : sub_preempt_count (irq_exit)
+    sshd-4261  0d.s4   86us : sub_preempt_count (irq_exit)
+    sshd-4261  0d.s3   86us : add_preempt_count (__local_bh_disable)
+[...]
+    sshd-4261  0d.s1   98us : sub_preempt_count (net_rx_action)
+    sshd-4261  0d.s.   99us : add_preempt_count (_spin_lock_irq)
+    sshd-4261  0d.s1   99us+: _spin_unlock_irq (run_timer_softirq)
+    sshd-4261  0d.s.  104us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s.  104us : sub_preempt_count (_local_bh_enable)
+    sshd-4261  0d.s.  105us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1  105us : trace_preempt_on (__do_softirq)
+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
+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 from the capital 'H'.
+wakeup
+------
+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
+LatencyTop are more appropriate for such measurements.
+Real-Time environments are interested in the worst case latency.
+That is the longest latency it takes for something to happen, and
+not the average. We can have a very fast scheduler that may only
+have a large latency once in a while, but that would not work well
+with Real-Time tasks.  The wakeup tracer was designed to record
+the worst case wakeups of RT tasks. Non-RT tasks are not recorded
+because the tracer only records one worst case and tracing non-RT
+tasks that are unpredictable will overwrite the worst case latency
+of RT tasks.
+Since this tracer only deals with RT tasks, we will run this slightly
+differently than we did with the previous tracers. Instead of performing
+an 'ls', we will run 'sleep 1' under 'chrt' which changes the
+priority of the task.
+ # echo wakeup > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # chrt -f 5 sleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: wakeup
+#
+wakeup latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 4 us, #2/2, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sleep-4901 (uid:0 nice:0 policy:1 rt_prio:5)
+    -----------------
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+  <idle>-0     1d.h4    0us+: try_to_wake_up (wake_up_process)
+  <idle>-0     1d..4    4us : schedule (cpu_idle)
+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
+schedule is before the actual "switch", we stop the tracing when
+the recorded task is about to schedule in. This may change if
+we add a new marker at the end of the scheduler.
+Notice that the recorded task is 'sleep' with the PID of 4901 and it
+has an rt_prio of 5. This priority is user-space priority and not
+the internal kernel priority. The policy is 1 for SCHED_FIFO and 2
+for SCHED_RR.
+Doing the same with chrt -r 5 and ftrace_enabled set.
+# tracer: wakeup
+#
+wakeup latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 50 us, #60/60, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sleep-4068 (uid:0 nice:0 policy:2 rt_prio:5)
+    -----------------
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+ksoftirq-7     1d.H3    0us : try_to_wake_up (wake_up_process)
+ksoftirq-7     1d.H4    1us : sub_preempt_count (marker_probe_cb)
+ksoftirq-7     1d.H3    2us : check_preempt_wakeup (try_to_wake_up)
+ksoftirq-7     1d.H3    3us : update_curr (check_preempt_wakeup)
+ksoftirq-7     1d.H3    4us : calc_delta_mine (update_curr)
+ksoftirq-7     1d.H3    5us : __resched_task (check_preempt_wakeup)
+ksoftirq-7     1d.H3    6us : task_wake_up_rt (try_to_wake_up)
+ksoftirq-7     1d.H3    7us : _spin_unlock_irqrestore (try_to_wake_up)
+[...]
+ksoftirq-7     1d.H2   17us : irq_exit (smp_apic_timer_interrupt)
+ksoftirq-7     1d.H2   18us : sub_preempt_count (irq_exit)
+ksoftirq-7     1d.s3   19us : sub_preempt_count (irq_exit)
+ksoftirq-7     1..s2   20us : rcu_process_callbacks (__do_softirq)
+[...]
+ksoftirq-7     1..s2   26us : __rcu_process_callbacks (rcu_process_callbacks)
+ksoftirq-7     1d.s2   27us : _local_bh_enable (__do_softirq)
+ksoftirq-7     1d.s2   28us : sub_preempt_count (_local_bh_enable)
+ksoftirq-7     1.N.3   29us : sub_preempt_count (ksoftirqd)
+ksoftirq-7     1.N.2   30us : _cond_resched (ksoftirqd)
+ksoftirq-7     1.N.2   31us : __cond_resched (_cond_resched)
+ksoftirq-7     1.N.2   32us : add_preempt_count (__cond_resched)
+ksoftirq-7     1.N.2   33us : schedule (__cond_resched)
+ksoftirq-7     1.N.2   33us : add_preempt_count (schedule)
+ksoftirq-7     1.N.3   34us : hrtick_clear (schedule)
+ksoftirq-7     1dN.3   35us : _spin_lock (schedule)
+ksoftirq-7     1dN.3   36us : add_preempt_count (_spin_lock)
+ksoftirq-7     1d..4   37us : put_prev_task_fair (schedule)
+ksoftirq-7     1d..4   38us : update_curr (put_prev_task_fair)
+[...]
+ksoftirq-7     1d..5   47us : _spin_trylock (tracing_record_cmdline)
+ksoftirq-7     1d..5   48us : add_preempt_count (_spin_trylock)
+ksoftirq-7     1d..6   49us : _spin_unlock (tracing_record_cmdline)
+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 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 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 do not see the 'N' until we switch back to the task's
+assigned stack.
+ftrace
+------
+ftrace is not only the name of the tracing infrastructure, but it
+is also a name of one of the tracers. The tracer is the function
+tracer. Enabling the function tracer can be done from the
+debug file system. Make sure the ftrace_enabled is set otherwise
+this tracer is a nop.
+ # sysctl kernel.ftrace_enabled=1
+ # echo ftrace > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4003  [00]   123.638713: finish_task_switch <-schedule
+            bash-4003  [00]   123.638714: _spin_unlock_irq <-finish_task_switch
+            bash-4003  [00]   123.638714: sub_preempt_count <-_spin_unlock_irq
+            bash-4003  [00]   123.638715: hrtick_set <-schedule
+            bash-4003  [00]   123.638715: _spin_lock_irqsave <-hrtick_set
+            bash-4003  [00]   123.638716: add_preempt_count <-_spin_lock_irqsave
+            bash-4003  [00]   123.638716: _spin_unlock_irqrestore <-hrtick_set
+            bash-4003  [00]   123.638717: sub_preempt_count <-_spin_unlock_irqrestore
+            bash-4003  [00]   123.638717: hrtick_clear <-hrtick_set
+            bash-4003  [00]   123.638718: sub_preempt_count <-schedule
+            bash-4003  [00]   123.638718: sub_preempt_count <-preempt_schedule
+            bash-4003  [00]   123.638719: wait_for_completion <-__stop_machine_run
+            bash-4003  [00]   123.638719: wait_for_common <-wait_for_completion
+            bash-4003  [00]   123.638720: _spin_lock_irq <-wait_for_common
+            bash-4003  [00]   123.638720: add_preempt_count <-_spin_lock_irq
+[...]
+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;
+[...]
+int main(int argc, char *argv[]) {
+        [...]
+        trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY);
+        [...]
+        if (condition_hit()) {
+                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, 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. (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
+without worrying about other processors executing that same code.  At
+initialization, the mcount calls are changed to call a "record_ip"
+function.  After this, the first time a kernel function is called,
+it has the calling address saved in a hash table.
+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 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
+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 specified functions. They are:
+  set_ftrace_filter
+and
+  set_ftrace_notrace
+A list of available functions that you can add to these files is listed
+in:
+   available_filter_functions
+ # cat /debug/tracing/available_filter_functions
+put_prev_task_idle
+kmem_cache_create
+pick_next_task_rt
+get_online_cpus
+pick_next_task_fair
+mutex_lock
+[...]
+If I am only interested in sys_nanosleep and hrtimer_interrupt:
+ # echo sys_nanosleep hrtimer_interrupt \
+                > /debug/tracing/set_ftrace_filter
+ # echo ftrace > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+          usleep-4134  [00]  1317.070017: hrtimer_interrupt <-smp_apic_timer_interrupt
+          usleep-4134  [00]  1317.070111: sys_nanosleep <-syscall_call
+          <idle>-0     [00]  1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt
+To see which functions are being traced, you can cat the file:
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_interrupt
+sys_nanosleep
+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
+These are the only wild cards which are supported.
+  <match>*<match> will not work.
+ # echo hrtimer_* > /debug/tracing/set_ftrace_filter
+Produces:
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4003  [00]  1480.611794: hrtimer_init <-copy_process
+            bash-4003  [00]  1480.611941: hrtimer_start <-hrtick_set
+            bash-4003  [00]  1480.611956: hrtimer_cancel <-hrtick_clear
+            bash-4003  [00]  1480.611956: hrtimer_try_to_cancel <-hrtimer_cancel
+          <idle>-0     [00]  1480.612019: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612025: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612032: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612037: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612382: hrtimer_get_next_event <-get_next_timer_interrupt
+Notice that we lost the sys_nanosleep.
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_run_queues
+hrtimer_run_pending
+hrtimer_init
+hrtimer_cancel
+hrtimer_try_to_cancel
+hrtimer_forward
+hrtimer_start
+hrtimer_reprogram
+hrtimer_force_reprogram
+hrtimer_get_next_event
+hrtimer_interrupt
+hrtimer_nanosleep
+hrtimer_wakeup
+hrtimer_get_remaining
+hrtimer_get_res
+hrtimer_init_sleeper
+This is because the '>' and '>>' act just like they do in bash.
+To rewrite the filters, use '>'
+To append to the filters, use '>>'
+To clear out a filter so that all functions will be recorded again:
+ # echo > /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+ #
+Again, now we want to append.
+ # echo sys_nanosleep > /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+sys_nanosleep
+ # echo hrtimer_* >> /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_run_queues
+hrtimer_run_pending
+hrtimer_init
+hrtimer_cancel
+hrtimer_try_to_cancel
+hrtimer_forward
+hrtimer_start
+hrtimer_reprogram
+hrtimer_force_reprogram
+hrtimer_get_next_event
+hrtimer_interrupt
+sys_nanosleep
+hrtimer_nanosleep
+hrtimer_wakeup
+hrtimer_get_remaining
+hrtimer_get_res
+hrtimer_init_sleeper
+The set_ftrace_notrace prevents those functions from being traced.
+ # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace
+Produces:
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4043  [01]   115.281644: finish_task_switch <-schedule
+            bash-4043  [01]   115.281645: hrtick_set <-schedule
+            bash-4043  [01]   115.281645: hrtick_clear <-hrtick_set
+            bash-4043  [01]   115.281646: wait_for_completion <-__stop_machine_run
+            bash-4043  [01]   115.281647: wait_for_common <-wait_for_completion
+            bash-4043  [01]   115.281647: kthread_stop <-stop_machine_run
+            bash-4043  [01]   115.281648: init_waitqueue_head <-kthread_stop
+            bash-4043  [01]   115.281648: wake_up_process <-kthread_stop
+            bash-4043  [01]   115.281649: try_to_wake_up <-wake_up_process
+We can see that there's no more lock or preempt tracing.
+ftraced
+-------
+As mentioned above, when dynamic ftrace is configured in, a kernel
+thread wakes up once a second and checks to see if there are mcount
+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 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.
+ # echo 0 > /debug/tracing/ftraced_enabled
+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.
+If there are recorded calls to mcount, any write to the ftraced_enabled
+file will cause the kstop_machine to run. This means that a
+user can manually perform the updates when they want to by simply
+echoing a '0' into the ftraced_enabled file.
+The updates are also done at the beginning of enabling a tracer
+that uses ftrace function recording.
+trace_pipe
+----------
+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.
+ # echo ftrace > /debug/tracing/current_tracer
+ # cat /debug/tracing/trace_pipe > /tmp/trace.out &
+[1] 4153
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+ #
+ # cat /tmp/trace.out
+            bash-4043  [00] 41.267106: finish_task_switch <-schedule
+            bash-4043  [00] 41.267106: hrtick_set <-schedule
+            bash-4043  [00] 41.267107: hrtick_clear <-hrtick_set
+            bash-4043  [00] 41.267108: wait_for_completion <-__stop_machine_run
+            bash-4043  [00] 41.267108: wait_for_common <-wait_for_completion
+            bash-4043  [00] 41.267109: kthread_stop <-stop_machine_run
+            bash-4043  [00] 41.267109: init_waitqueue_head <-kthread_stop
+            bash-4043  [00] 41.267110: wake_up_process <-kthread_stop
+            bash-4043  [00] 41.267110: try_to_wake_up <-wake_up_process
+            bash-4043  [00] 41.267111: select_task_rq_rt <-try_to_wake_up
+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.
+trace entries
+-------------
+Having too much or not enough data can be troublesome in diagnosing
+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
+number of entries.
+ # cat /debug/tracing/trace_entries
+65620
+Note, to modify this, you must have tracing completely disabled. To do that,
+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
+ # cat /debug/tracing/trace_entries
+100045
+Notice that we echoed in 100,000 but the size is 100,045. The entries
+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
+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 in a single page.
+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
+ # cat /debug/tracing/trace_entries
+85
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index c35ca9e40d4c..18022e249c53 100644
--- a/Documentation/gpio.txt
+++ b/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.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
index 22d8b19046ab..2126de34c711 100644
--- a/Documentation/hwmon/adt7473
+++ b/Documentation/hwmon/adt7473
@@ -69,7 +69,8 @@ point2: Set the pwm speed at a higher temperature bound.
 The ADT7473 will scale the pwm between the lower and higher pwm speed when
 the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).
+from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
+temperature sensor associated with the PWM control exceeds temp#_max.
 Notes
 -----
diff --git a/Documentation/hwmon/ibmaem b/Documentation/hwmon/ibmaem
new file mode 100644
index 000000000000..2fefaf582a43
--- /dev/null
+++ b/Documentation/hwmon/ibmaem
@@ -0,0 +1,37 @@
+Kernel driver ibmaem
+======================
+Supported systems:
+  * Any recent IBM System X server with Active Energy Manager support.
+    This includes the x3350, x3550, x3650, x3655, x3755, x3850 M2,
+    x3950 M2, and certain HS2x/LS2x/QS2x blades.  The IPMI host interface
+    driver ("ipmi-si") needs to be loaded for this driver to do anything.
+    Prefix: 'ibmaem'
+    Datasheet: Not available
+Author: Darrick J. Wong
+Description
+-----------
+This driver implements sensor reading support for the energy and power
+meters available on various IBM System X hardware through the BMC.  All
+sensor banks will be exported as platform devices; this driver can talk
+to both v1 and v2 interfaces.  This driver is completely separate from the
+older ibmpex driver.
+The v1 AEM interface has a simple set of features to monitor energy use.
+There is a register that displays an estimate of raw energy consumption
+since the last BMC reset, and a power sensor that returns average power
+use over a configurable interval.
+The v2 AEM interface is a bit more sophisticated, being able to present
+a wider range of energy and power use registers, the power cap as
+set by the AEM software, and temperature sensors.
+Special Features
+----------------
+The "power_cap" value displays the current system power cap, as set by
+the Active Energy Manager software.  Setting the power cap from the host
+is not currently supported.
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index f4a8ebc1ef1a..2d845730d4e0 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -2,17 +2,12 @@ Naming and data format standards for sysfs files
 ------------------------------------------------
 The libsensors library offers an interface to the raw sensors data
-through the sysfs interface. See libsensors documentation and source for
+through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
-further information. As of writing this document, libsensors
+completely chip-independent. It assumes that all the kernel drivers
-(from lm_sensors 2.8.3) is heavily chip-dependent. Adding or updating
+implement the standard sysfs interface described in this document.
-support for any given chip requires modifying the library's code.
+This makes adding or updating support for any given chip very easy, as
-This is because libsensors was written for the procfs interface
+libsensors, and applications using it, do not need to be modified.
-older kernel modules were using, which wasn't standardized enough.
+This is a major improvement compared to lm-sensors 2.
-Recent versions of libsensors (from lm_sensors 2.8.2 and later) have
-support for the sysfs interface, though.
-The new sysfs interface was designed to be as chip-independent as
-possible.
 Note that motherboards vary widely in the connections to sensor chips.
 There is no standard that ensures, for example, that the second
@@ -35,19 +30,17 @@ access this data in a simple and consistent way. That said, such programs
 will have to implement conversion, labeling and hiding of inputs. For
 this reason, it is still not recommended to bypass the library.
-If you are developing a userspace application please send us feedback on
-this standard.
-Note that this standard isn't completely established yet, so it is subject
-to changes. If you are writing a new hardware monitoring driver those
-features can't seem to fit in this interface, please contact us with your
-extension proposal. Keep in mind that backward compatibility must be
-preserved.
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
 /sys/class/hwmon/hwmon*.
+Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
+in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
+in the hwmon "class" device directory are also supported. Complex drivers
+(e.g. drivers for multifunction chips) may want to use this possibility to
+avoid namespace pollution. The only drawback will be that older versions of
+libsensors won't support the driver in question.
 All sysfs values are fixed point numbers.
 There is only one value per file, unlike the older /proc specification.
diff --git a/Documentation/i2c/busses/i2c-i810 b/Documentation/i2c/busses/i2c-i810
deleted file mode 100644
index 778210ee1583..000000000000
--- a/Documentation/i2c/busses/i2c-i810
+++ /dev/null
@@ -1,47 +0,0 @@
-Kernel driver i2c-i810
-Supported adapters:
-  * Intel 82810, 82810-DC100, 82810E, and 82815 (GMCH)
-  * Intel 82845G (GMCH)
-Authors: 
-        Frodo Looijaard <frodol@dds.nl>, 
-        Philip Edelbrock <phil@netroedge.com>,
-        Kyösti Mälkki <kmalkki@cc.hut.fi>,
-        Ralph Metzler <rjkm@thp.uni-koeln.de>,
-        Mark D. Studebaker <mdsxyz123@yahoo.com>
-Main contact: Mark Studebaker <mdsxyz123@yahoo.com>
-Description 
----------- 
-WARNING: If you have an '810' or '815' motherboard, your standard I2C
-temperature sensors are most likely on the 801's I2C bus. You want the
-i2c-i801 driver for those, not this driver.
-Now for the i2c-i810...
-The GMCH chip contains two I2C interfaces.
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org .
-The second interface is a general-purpose I2C bus. It may be connected to a
-TV-out chip such as the BT869 or possibly to a digital flat-panel display.
-Features
-------- 
-Both busses use the i2c-algo-bit driver for 'bit banging'
-and support for specific transactions is provided by i2c-algo-bit.
-Issues
------
-If you enable bus testing in i2c-algo-bit (insmod i2c-algo-bit bit_test=1),
-the test may fail; if so, the i2c-i810 driver won't be inserted. However,
-we think this has been fixed.
diff --git a/Documentation/i2c/busses/i2c-prosavage b/Documentation/i2c/busses/i2c-prosavage
deleted file mode 100644
index 703687902511..000000000000
--- a/Documentation/i2c/busses/i2c-prosavage
+++ /dev/null
@@ -1,23 +0,0 @@
-Kernel driver i2c-prosavage
-Supported adapters:
-        
-        S3/VIA KM266/VT8375 aka ProSavage8 
-        S3/VIA KM133/VT8365 aka Savage4 
-Author: Henk Vergonet <henk@god.dyndns.org>
-Description
-----------
-The Savage4 chips contain two I2C interfaces (aka a I2C 'master' or
-'host'). 
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org . The second interface is a general-purpose I2C bus.
-Usefull for gaining access to the TV Encoder chips.
diff --git a/Documentation/i2c/busses/i2c-savage4 b/Documentation/i2c/busses/i2c-savage4
deleted file mode 100644
index 6ecceab618d3..000000000000
--- a/Documentation/i2c/busses/i2c-savage4
+++ /dev/null
@@ -1,26 +0,0 @@
-Kernel driver i2c-savage4
-Supported adapters:
-  * Savage4
-  * Savage2000
-Authors: 
-        Alexander Wold <awold@bigfoot.com>,
-        Mark D. Studebaker <mdsxyz123@yahoo.com> 
-Description
-----------
-The Savage4 chips contain two I2C interfaces (aka a I2C 'master'
-or 'host'). 
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org . The DDC bus is not yet supported because its register
-is not directly memory-mapped.
-The second interface is a general-purpose I2C bus. This is the only
-interface supported by the driver at the moment.
diff --git a/Documentation/i2c/chips/max6875 b/Documentation/i2c/chips/max6875
index a0cd8af2f408..10ca43cd1a72 100644
--- a/Documentation/i2c/chips/max6875
+++ b/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
diff --git a/Documentation/i2c/chips/pca9539 b/Documentation/i2c/chips/pca9539
index 1d81c530c4a5..6aff890088b1 100644
--- a/Documentation/i2c/chips/pca9539
+++ b/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
 -------------
diff --git a/Documentation/i2c/chips/pcf8574 b/Documentation/i2c/chips/pcf8574
index 5c1ad1376b62..235815c075ff 100644
--- a/Documentation/i2c/chips/pcf8574
+++ b/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
+So, you have to pass the I2C bus and address of the installed PCF857A
-detected as PCF8574(A). If you have other chips in this address
+and PCF8574A devices explicitly to the driver at load time via the
-range, the workaround is to load this module after the one
+force=... parameter.
-for your others chips.
 On detection (i.e. insmod, modprobe et al.), directories are being
 created for each detected PCF8574(A):
diff --git a/Documentation/i2c/chips/pcf8575 b/Documentation/i2c/chips/pcf8575
index 25f5698a61cf..40b268eb276f 100644
--- a/Documentation/i2c/chips/pcf8575
+++ b/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
+a PCF8575 or whether it is any other I2C device, so you have to pass the I2C
-to let the driver find the installed PCF8575 devices:
+bus and address of the installed PCF8575 devices explicitly to the driver at
- Load this driver after any other I2C driver for I2C devices with addresses
+load time via the force=... parameter.
-  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.
 /sys interface
 --------------
diff --git a/Documentation/i2c/fault-codes b/Documentation/i2c/fault-codes
new file mode 100644
index 000000000000..045765c0b9b5
--- /dev/null
+++ b/Documentation/i2c/fault-codes
@@ -0,0 +1,127 @@
+This is a summary of the most important conventions for use of fault
+codes in the I2C/SMBus stack.
+A "Fault" is not always an "Error"
+----------------------------------
+Not all fault reports imply errors; "page faults" should be a familiar
+example.  Software often retries idempotent operations after transient
+faults.  There may be fancier recovery schemes that are appropriate in
+some cases, such as re-initializing (and maybe resetting).  After such
+recovery, triggered by a fault report, there is no error.
+In a similar way, sometimes a "fault" code just reports one defined
+result for an operation ... it doesn't indicate that anything is wrong
+at all, just that the outcome wasn't on the "golden path".
+In short, your I2C driver code may need to know these codes in order
+to respond correctly.  Other code may need to rely on YOUR code reporting
+the right fault code, so that it can (in turn) behave correctly.
+I2C and SMBus fault codes
+-------------------------
+These are returned as negative numbers from most calls, with zero or
+some positive number indicating a non-fault return.  The specific
+numbers associated with these symbols differ between architectures,
+though most Linux systems use <asm-generic/errno*.h> numbering.
+Note that the descriptions here are not exhaustive.  There are other
+codes that may be returned, and other cases where these codes should
+be returned.  However, drivers should not return other codes for these
+cases (unless the hardware doesn't provide unique fault reports).
+Also, codes returned by adapter probe methods follow rules which are
+specific to their host bus (such as PCI, or the platform bus).
+EAGAIN
+        Returned by I2C adapters when they lose arbitration in master
+        transmit mode:  some other master was transmitting different
+        data at the same time.
+        Also returned when trying to invoke an I2C operation in an
+        atomic context, when some task is already using that I2C bus
+        to execute some other operation.
+EBADMSG
+        Returned by SMBus logic when an invalid Packet Error Code byte
+        is received.  This code is a CRC covering all bytes in the
+        transaction, and is sent before the terminating STOP.  This
+        fault is only reported on read transactions; the SMBus slave
+        may have a way to report PEC mismatches on writes from the
+        host.  Note that even if PECs are in use, you should not rely
+        on these as the only way to detect incorrect data transfers.
+EBUSY
+        Returned by SMBus adapters when the bus was busy for longer
+        than allowed.  This usually indicates some device (maybe the
+        SMBus adapter) needs some fault recovery (such as resetting),
+        or that the reset was attempted but failed.
+EINVAL
+        This rather vague error means an invalid parameter has been
+        detected before any I/O operation was started.  Use a more
+        specific fault code when you can.
+        One example would be a driver trying an SMBus Block Write
+        with block size outside the range of 1-32 bytes.
+EIO
+        This rather vague error means something went wrong when
+        performing an I/O operation.  Use a more specific fault
+        code when you can.
+ENODEV
+        Returned by driver probe() methods.  This is a bit more
+        specific than ENXIO, implying the problem isn't with the
+        address, but with the device found there.  Driver probes
+        may verify the device returns *correct* responses, and
+        return this as appropriate.  (The driver core will warn
+        about probe faults other than ENXIO and ENODEV.)
+ENOMEM
+        Returned by any component that can't allocate memory when
+        it needs to do so.
+ENXIO
+        Returned by I2C adapters to indicate that the address phase
+        of a transfer didn't get an ACK.  While it might just mean
+        an I2C device was temporarily not responding, usually it
+        means there's nothing listening at that address.
+        Returned by driver probe() methods to indicate that they
+        found no device to bind to.  (ENODEV may also be used.)
+EOPNOTSUPP
+        Returned by an adapter when asked to perform an operation
+        that it doesn't, or can't, support.
+        For example, this would be returned when an adapter that
+        doesn't support SMBus block transfers is asked to execute
+        one.  In that case, the driver making that request should
+        have verified that functionality was supported before it
+        made that block transfer request.
+        Similarly, if an I2C adapter can't execute all legal I2C
+        messages, it should return this when asked to perform a
+        transaction it can't.  (These limitations can't be seen in
+        the adapter's functionality mask, since the assumption is
+        that if an adapter supports I2C it supports all of I2C.)
+EPROTO
+        Returned when slave does not conform to the relevant I2C
+        or SMBus (or chip-specific) protocol specifications.  One
+        case is when the length of an SMBus block data response
+        (from the SMBus slave) is outside the range 1-32 bytes.
+ETIMEDOUT
+        This is returned by drivers when an operation took too much
+        time, and was aborted before it completed.
+        SMBus adapters may return it when an operation took more
+        time than allowed by the SMBus specification; for example,
+        when a slave stretches clocks too far.  I2C has no such
+        timeouts, but it's normal for I2C adapters to impose some
+        arbitrary limits (much longer than SMBus!) too.
diff --git a/Documentation/i2c/functionality b/Documentation/i2c/functionality
index 60cca249e452..42c17c1fb3cd 100644
--- a/Documentation/i2c/functionality
+++ b/Documentation/i2c/functionality
@@ -51,26 +51,38 @@ A few combinations of the above flags are also defined for your convenience:
                                  the transparent emulation layer)
-ALGORITHM/ADAPTER IMPLEMENTATION
+ADAPTER IMPLEMENTATION
--------------------------------
+----------------------
-When you write a new algorithm driver, you will have to implement a
+When you write a new adapter driver, you will have to implement a
-function callback `functionality', that gets an i2c_adapter structure
+function callback `functionality'. Typical implementations are given
-pointer as its only parameter:
+below.
-  struct i2c_algorithm {
+A typical SMBus-only adapter would list all the SMBus transactions it
-        /* Many other things of course; check <linux/i2c.h>! */
+supports. This example comes from the i2c-piix4 driver:
-        u32 (*functionality) (struct i2c_adapter *);
+  static u32 piix4_func(struct i2c_adapter *adapter)
+  {
+        return I2C_FUNC_SMBUS_QUICK | I2C_FUNC_SMBUS_BYTE |
+               I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA |
+               I2C_FUNC_SMBUS_BLOCK_DATA;
  }
-A typically implementation is given below, from i2c-algo-bit.c:
+A typical full-I2C adapter would use the following (from the i2c-pxa
+driver):
-  static u32 bit_func(struct i2c_adapter *adap)
+  static u32 i2c_pxa_functionality(struct i2c_adapter *adap)
  {
-        return I2C_FUNC_SMBUS_EMUL | I2C_FUNC_10BIT_ADDR | 
+        return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
-               I2C_FUNC_PROTOCOL_MANGLING;
  }
+I2C_FUNC_SMBUS_EMUL includes all the SMBus transactions (with the
+addition of I2C block transactions) which i2c-core can emulate using
+I2C_FUNC_I2C without any help from the adapter driver. The idea is
+to let the client drivers check for the support of SMBus functions
+without having to care whether the said functions are implemented in
+hardware by the adapter, or emulated in software by i2c-core on top
+of an I2C adapter.
 CLIENT CHECKING
@@ -78,36 +90,33 @@ CLIENT CHECKING
 Before a client tries to attach to an adapter, or even do tests to check
 whether one of the devices it supports is present on an adapter, it should
-check whether the needed functionality is present. There are two functions
+check whether the needed functionality is present. The typical way to do
-defined which should be used instead of calling the functionality hook
+this is (from the lm75 driver):
-in the algorithm structure directly:
-  /* Return the functionality mask */
-  extern u32 i2c_get_functionality (struct i2c_adapter *adap);
-  /* Return 1 if adapter supports everything we need, 0 if not. */
-  extern int i2c_check_functionality (struct i2c_adapter *adap, u32 func);
-This is a typical way to use these functions (from the writing-clients
+  static int lm75_detect(...)
-document):
-  int foo_detect_client(struct i2c_adapter *adapter, int address, 
-                          unsigned short flags, int kind)
  {
-        /* Define needed variables */
+        (...)
+        if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
-        /* As the very first action, we check whether the adapter has the
+                                     I2C_FUNC_SMBUS_WORD_DATA))
-           needed functionality: we need the SMBus read_word_data,
+                goto exit;
-           write_word_data and write_byte functions in this example. */
+        (...)
-        if (!i2c_check_functionality(adapter,I2C_FUNC_SMBUS_WORD_DATA |
-                                             I2C_FUNC_SMBUS_WRITE_BYTE))
-                goto ERROR0;
-        /* Now we can do the real detection */
-        ERROR0:
-                /* Return an error */
  }
+Here, the lm75 driver checks if the adapter can do both SMBus byte data
+and SMBus word data transactions. If not, then the driver won't work on
+this adapter and there's no point in going on. If the check above is
+successful, then the driver knows that it can call the following
+functions: i2c_smbus_read_byte_data(), i2c_smbus_write_byte_data(),
+i2c_smbus_read_word_data() and i2c_smbus_write_word_data(). As a rule of
+thumb, the functionality constants you test for with
+i2c_check_functionality() should match exactly the i2c_smbus_* functions
+which you driver is calling.
+Note that the check above doesn't tell whether the functionalities are
+implemented in hardware by the underlying adapter or emulated in
+software by i2c-core. Client drivers don't have to care about this, as
+i2c-core will transparently implement SMBus transactions on top of I2C
+adapters.
 CHECKING THROUGH /DEV
@@ -116,19 +125,19 @@ CHECKING THROUGH /DEV
 If you try to access an adapter from a userspace program, you will have
 to use the /dev interface. You will still have to check whether the
 functionality you need is supported, of course. This is done using
-the I2C_FUNCS ioctl. An example, adapted from the lm_sensors i2cdetect
+the I2C_FUNCS ioctl. An example, adapted from the i2cdetect program, is
-program, is below:
+below:
  int file;
-  if (file = open("/dev/i2c-0",O_RDWR) < 0) {
+  if (file = open("/dev/i2c-0", O_RDWR) < 0) {
        /* Some kind of error handling */
        exit(1);
  }
-  if (ioctl(file,I2C_FUNCS,&funcs) < 0) {
+  if (ioctl(file, I2C_FUNCS, &funcs) < 0) {
        /* Some kind of error handling */
        exit(1);
  }
-  if (! (funcs & I2C_FUNC_SMBUS_QUICK)) {
+  if (!(funcs & I2C_FUNC_SMBUS_QUICK)) {
        /* Oops, the needed functionality (SMBus write_quick function) is
           not available! */
        exit(1);
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 8a653c60d25a..24bfb65da17d 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -1,5 +1,6 @@
 SMBus Protocol Summary
 ======================
 The following is a summary of the SMBus protocol. It applies to
 all revisions of the protocol (1.0, 1.1, and 2.0).
 Certain protocol features which are not supported by
@@ -8,6 +9,7 @@ this package are briefly described at the end of this document.
 Some adapters understand only the SMBus (System Management Bus) protocol,
 which is a subset from the I2C protocol. Fortunately, many devices use
 only the same subset, which makes it possible to put them on an SMBus.
 If you write a driver for some I2C device, please try to use the SMBus
 commands if at all possible (if the device uses only that subset of the
 I2C protocol). This makes it possible to use the device driver on both
@@ -15,7 +17,12 @@ SMBus adapters and I2C adapters (the SMBus command set is automatically
 translated to I2C on I2C adapters, but plain I2C commands can not be
 handled at all on most pure SMBus adapters).
-Below is a list of SMBus commands.
+Below is a list of SMBus protocol operations, and the functions executing
+them.  Note that the names used in the SMBus protocol specifications usually
+don't match these function names.  For some of the operations which pass a
+single data byte, the functions using SMBus protocol operation names execute
+a different protocol operation entirely.
 Key to symbols
 ==============
@@ -35,17 +42,16 @@ Count (8 bits): A data byte containing the length of a block operation.
 [..]: Data sent by I2C device, as opposed to data sent by the host adapter.
-SMBus Write Quick
+SMBus Quick Command
-=================
+===================
 This sends a single bit to the device, at the place of the Rd/Wr bit.
-There is no equivalent Read Quick command.
 A Addr Rd/Wr [A] P
-SMBus Read Byte
+SMBus Receive Byte:  i2c_smbus_read_byte()
-===============
+==========================================
 This reads a single byte from a device, without specifying a device
 register. Some devices are so simple that this interface is enough; for
@@ -55,17 +61,17 @@ the previous SMBus command.
 S Addr Rd [A] [Data] NA P
-SMBus Write Byte
+SMBus Send Byte:  i2c_smbus_write_byte()
-================
+========================================
-This is the reverse of Read Byte: it sends a single byte to a device.
+This operation is the reverse of Receive Byte: it sends a single byte
-See Read Byte for more information.
+to a device.  See Receive Byte for more information.
 S Addr Wr [A] Data [A] P
-SMBus Read Byte Data
+SMBus Read Byte:  i2c_smbus_read_byte_data()
-====================
+============================================
 This reads a single byte from a device, from a designated register.
 The register is specified through the Comm byte.
@@ -73,30 +79,30 @@ The register is specified through the Comm byte.
 S Addr Wr [A] Comm [A] S Addr Rd [A] [Data] NA P
-SMBus Read Word Data
+SMBus Read Word:  i2c_smbus_read_word_data()
-====================
+============================================
-This command is very like Read Byte Data; again, data is read from a
+This operation is very like Read Byte; again, data is read from a
 device, from a designated register that is specified through the Comm
 byte. But this time, the data is a complete word (16 bits).
 S Addr Wr [A] Comm [A] S Addr Rd [A] [DataLow] A [DataHigh] NA P
-SMBus Write Byte Data
+SMBus Write Byte:  i2c_smbus_write_byte_data()
-=====================
+==============================================
 This writes a single byte to a device, to a designated register. The
 register is specified through the Comm byte. This is the opposite of
-the Read Byte Data command.
+the Read Byte operation.
 S Addr Wr [A] Comm [A] Data [A] P
-SMBus Write Word Data
+SMBus Write Word:  i2c_smbus_write_word_data()
-=====================
+==============================================
-This is the opposite operation of the Read Word Data command. 16 bits
+This is the opposite of the Read Word operation. 16 bits
 of data is written to a device, to the designated register that is
 specified through the Comm byte. 
@@ -113,8 +119,8 @@ S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A]
                             S Addr Rd [A] [DataLow] A [DataHigh] NA P
-SMBus Block Read
+SMBus Block Read:  i2c_smbus_read_block_data()
-================
+==============================================
 This command reads a block of up to 32 bytes from a device, from a 
 designated register that is specified through the Comm byte. The amount
@@ -124,8 +130,8 @@ S Addr Wr [A] Comm [A]
           S Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P
-SMBus Block Write
+SMBus Block Write:  i2c_smbus_write_block_data()
-=================
+================================================
 The opposite of the Block Read command, this writes up to 32 bytes to 
 a device, to a designated register that is specified through the
@@ -134,10 +140,11 @@ Comm byte. The amount of data is specified in the Count byte.
 S Addr Wr [A] Comm [A] Count [A] Data [A] Data [A] ... [A] Data [A] P
-SMBus Block Process Call
+SMBus Block Write - Block Read Process Call
-========================
+===========================================
-SMBus Block Process Call was introduced in Revision 2.0 of the specification.
+SMBus Block Write - Block Read Process Call was introduced in
+Revision 2.0 of the specification.
 This command selects a device register (through the Comm byte), sends
 1 to 31 bytes of data to it, and reads 1 to 31 bytes of data in return.
@@ -159,13 +166,16 @@ alerting device's address.
 Packet Error Checking (PEC)
 ===========================
 Packet Error Checking was introduced in Revision 1.1 of the specification.
-PEC adds a CRC-8 error-checking byte to all transfers.
+PEC adds a CRC-8 error-checking byte to transfers using it, immediately
+before the terminating STOP.
 Address Resolution Protocol (ARP)
 =================================
 The Address Resolution Protocol was introduced in Revision 2.0 of
 the specification. It is a higher-layer protocol which uses the
 messages above.
@@ -177,14 +187,17 @@ require PEC checksums.
 I2C Block Transactions
 ======================
 The following I2C block transactions are supported by the
 SMBus layer and are described here for completeness.
+They are *NOT* defined by the SMBus specification.
 I2C block transactions do not limit the number of bytes transferred
 but the SMBus layer places a limit of 32 bytes.
-I2C Block Read
+I2C Block Read:  i2c_smbus_read_i2c_block_data()
-==============
+================================================
 This command reads a block of bytes from a device, from a 
 designated register that is specified through the Comm byte.
@@ -203,8 +216,8 @@ S Addr Wr [A] Comm1 [A] Comm2 [A]
           S Addr Rd [A] [Data] A [Data] A ... A [Data] NA P
-I2C Block Write
+I2C Block Write:  i2c_smbus_write_i2c_block_data()
-===============
+==================================================
 The opposite of the Block Read command, this writes bytes to 
 a device, to a designated register that is specified through the
@@ -212,5 +225,3 @@ Comm byte. Note that command lengths of 0, 2, or more bytes are
 supported as they are indistinguishable from data.
 S Addr Wr [A] Comm [A] Data [A] Data [A] ... [A] Data [A] P
diff --git a/Documentation/i2c/upgrading-clients b/Documentation/i2c/upgrading-clients
new file mode 100644
index 000000000000..9a45f9bb6a25
--- /dev/null
+++ b/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,
+};
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index ee75cbace28d..6b61b3a2e90b 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -25,14 +25,29 @@ routines, and should be zero-initialized except for fields with data you
 provide.  A client structure holds device-specific information like the
 driver model device node, and its I2C address.
+/* iff driver uses driver model ("new style") binding model: */
+static struct i2c_device_id foo_idtable[] = {
+        { "foo", my_id_for_foo },
+        { "bar", my_id_for_bar },
+        { }
+};
+MODULE_DEVICE_TABLE(i2c, foo_idtable);
 static struct i2c_driver foo_driver = {
        .driver = {
                .name   = "foo",
        },
        /* iff driver uses driver model ("new style") binding model: */
+        .id_table       = foo_ids,
        .probe          = foo_probe,
        .remove         = foo_remove,
+        /* if device autodetection is needed: */
+        .class          = I2C_CLASS_SOMETHING,
+        .detect         = foo_detect,
+        .address_data   = &addr_data,
        /* else, driver uses "legacy" binding model: */
        .attach_adapter = foo_attach_adapter,
@@ -173,10 +188,9 @@ handle may be used during foo_probe().  If foo_probe() reports success
 (zero not a negative status code) it may save the handle and use it until
 foo_remove() returns.  That binding model is used by most Linux drivers.
-Drivers match devices when i2c_client.driver_name and the driver name are
+The probe function is called when an entry in the id_table name field
-the same; this approach is used in several other busses that don't have
+matches the device's name. It is passed the entry that was matched so
-device typing support in the hardware.  The driver and module name should
+the driver knows which one in the table matched.
-match, so hotplug/coldplug mechanisms will modprobe the driver.
 Device Creation (Standard driver model)
@@ -207,6 +221,31 @@ in the I2C bus driver. You may want to save the returned i2c_client
 reference for later use.
+Device Detection (Standard driver model)
+----------------------------------------
+Sometimes you do not know in advance which I2C devices are connected to
+a given I2C bus.  This is for example the case of hardware monitoring
+devices on a PC's SMBus.  In that case, you may want to let your driver
+detect supported devices automatically.  This is how the legacy model
+was working, and is now available as an extension to the standard
+driver model (so that we can finally get rid of the legacy model.)
+You simply have to define a detect callback which will attempt to
+identify supported devices (returning 0 for supported ones and -ENODEV
+for unsupported ones), a list of addresses to probe, and a device type
+(or class) so that only I2C buses which may have that type of device
+connected (and not otherwise enumerated) will be probed.  The i2c
+core will then call you back as needed and will instantiate a device
+for you for every successful detection.
+Note that this mechanism is purely optional and not suitable for all
+devices.  You need some reliable way to identify the supported devices
+(typically using device-specific, dedicated identification registers),
+otherwise misdetections are likely to occur and things can get wrong
+quickly.
 Device Deletion (Standard driver model)
 ---------------------------------------
@@ -559,7 +598,6 @@ SMBus communication
  in terms of it. Never use this function directly!
-  extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
  extern s32 i2c_smbus_read_byte(struct i2c_client * client);
  extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value);
  extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command);
@@ -568,30 +606,31 @@ SMBus communication
  extern s32 i2c_smbus_read_word_data(struct i2c_client * client, u8 command);
  extern s32 i2c_smbus_write_word_data(struct i2c_client * client,
                                       u8 command, u16 value);
+  extern s32 i2c_smbus_read_block_data(struct i2c_client * client,
+                                       u8 command, u8 *values);
  extern s32 i2c_smbus_write_block_data(struct i2c_client * client,
                                        u8 command, u8 length,
                                        u8 *values);
  extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client * client,
                                           u8 command, u8 length, u8 *values);
-These ones were removed in Linux 2.6.10 because they had no users, but could
-be added back later if needed:
-  extern s32 i2c_smbus_read_block_data(struct i2c_client * client,
-                                       u8 command, u8 *values);
  extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client,
                                            u8 command, u8 length,
                                            u8 *values);
+These ones were removed from i2c-core because they had no users, but could
+be added back later if needed:
+  extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
  extern s32 i2c_smbus_process_call(struct i2c_client * client,
                                    u8 command, u16 value);
  extern s32 i2c_smbus_block_process_call(struct i2c_client *client,
                                          u8 command, u8 length,
                                          u8 *values)
-All these transactions return -1 on failure. The 'write' transactions 
+All these transactions return a negative errno value on failure. The 'write'
-return 0 on success; the 'read' transactions return the read value, except 
+transactions return 0 on success; the 'read' transactions return the read
-for read_block, which returns the number of values read. The block buffers 
+value, except for block transactions, which return the number of values
-need not be longer than 32 bytes.
+read. The block buffers need not be longer than 32 bytes.
 You can read the file `smbus-protocol' for more information about the
 actual SMBus protocol.
diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt
index bec9d815da33..914d07f49268 100644
--- a/Documentation/ia64/kvm.txt
+++ b/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.d                          // serialize restoration of psr.l
-+       srlz.i                  // seralize restoration of psr.l
+       srlz.i                  // serialize restoration of psr.l
 +       ;;
        br.ret.sptk.many b0
 END(ia64_pal_call_static)
diff --git a/Documentation/ia64/paravirt_ops.txt b/Documentation/ia64/paravirt_ops.txt
new file mode 100644
index 000000000000..39ded02ec33f
--- /dev/null
+++ b/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.
diff --git a/Documentation/input/cs461x.txt b/Documentation/input/cs461x.txt
index afe0d6543e09..202e9dbacec3 100644
--- a/Documentation/input/cs461x.txt
+++ b/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.
diff --git a/Documentation/input/gameport-programming.txt b/Documentation/input/gameport-programming.txt
index 14e0a8b70225..03a74fc3b496 100644
--- a/Documentation/input/gameport-programming.txt
+++ b/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
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/input/input.txt b/Documentation/input/input.txt
index ff8cea0225f9..686ee9932dff 100644
--- a/Documentation/input/input.txt
+++ b/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
diff --git a/Documentation/input/joystick-api.txt b/Documentation/input/joystick-api.txt
index acbd32b88454..c507330740cd 100644
--- a/Documentation/input/joystick-api.txt
+++ b/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
 ~~~~~~~~~~~~~~~~~
diff --git a/Documentation/input/joystick-parport.txt b/Documentation/input/joystick-parport.txt
index ede5f33daad3..1c856f32ff2c 100644
--- a/Documentation/input/joystick-parport.txt
+++ b/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
diff --git a/Documentation/input/joystick.txt b/Documentation/input/joystick.txt
index 389de9bd9878..154d767b2acb 100644
--- a/Documentation/input/joystick.txt
+++ b/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
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index 240ce7a56c40..3bb5f466a90d 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -117,6 +117,7 @@ Code	Seq#	Include File		Comments
                                        <mailto:natalia@nikhefk.nikhef.nl>
 'c'     00-7F   linux/comstats.h        conflict!
 'c'     00-7F   linux/coda.h            conflict!
+'c'     80-9F   asm-s390/chsc.h
 'd'     00-FF   linux/char/drm/drm/h    conflict!
 'd'     00-DF   linux/video_decoder.h   conflict!
 'd'     F0-FF   linux/digi1.h
diff --git a/Documentation/ioctl/hdio.txt b/Documentation/ioctl/hdio.txt
index c19efdeace2c..91a6ecbae0bb 100644
--- a/Documentation/ioctl/hdio.txt
+++ b/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
+          Execute a reset on the device as soon as the current IO
-          queued, execute a reset on the device, and issue BLKRRPART
+          operation has completed.
-          ioctl on the block device.
          Executes an ATAPI soft reset if applicable, otherwise
          executes an ATA soft reset on the controller.
diff --git a/Documentation/ioctl/ioctl-decoding.txt b/Documentation/ioctl/ioctl-decoding.txt
index bfdf7f3ee4f0..e35efb0cec2e 100644
--- a/Documentation/ioctl/ioctl-decoding.txt
+++ b/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])
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 5925c3cd030d..59a69ec67c40 100644
--- a/Documentation/iostats.txt
+++ b/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
 ----------------
diff --git a/Documentation/isdn/README.mISDN b/Documentation/isdn/README.mISDN
new file mode 100644
index 000000000000..cd8bf920e77b
--- /dev/null
+++ b/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.
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index 00b950d1c193..c412c245848f 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -377,27 +377,3 @@ config FOO
 limits FOO to module (=m) or disabled (=n).
-Build limited by a third config symbol which may be =y or =m
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-A common idiom that we see (and sometimes have problems with) is this:
-When option C in B (module or subsystem) uses interfaces from A (module
-or subsystem), and both A and B are tristate (could be =y or =m if they
-were independent of each other, but they aren't), then we need to limit
-C such that it cannot be built statically if A is built as a loadable
-module.  (C already depends on B, so there is no dependency issue to
-take care of here.)
-If A is linked statically into the kernel image, C can be built
-statically or as loadable module(s).  However, if A is built as loadable
-module(s), then C must be restricted to loadable module(s) also.  This
-can be expressed in kconfig language as:
-config C
-        depends on A = y || A = B
-or for real examples, use this command in a kernel tree:
-$ find . -name Kconfig\* | xargs grep -ns "depends on.*=.*||.*=" | grep -v orig
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index b8e52c0355d3..0705040531a5 100644
--- a/Documentation/kdump/kdump.txt
+++ b/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
+This is a symlink to the latest version.
-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/
-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:
@@ -109,7 +109,7 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
   no need to build a separate dump-capture kernel. This is possible
   only with the architecutres which support a relocatable kernel. As
-   of today i386 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 2075c0658bf5..0bd32748a467 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -1,6 +1,105 @@
 kernel-doc nano-HOWTO
 =====================
+How to format kernel-doc comments
+---------------------------------
+In order to provide embedded, 'C' friendly, easy to maintain,
+but consistent and extractable documentation of the functions and
+data structures in the Linux kernel, the Linux kernel has adopted
+a consistent style for documenting functions and their parameters,
+and structures and their members.
+The format for this documentation is called the kernel-doc format.
+It is documented in this Documentation/kernel-doc-nano-HOWTO.txt file.
+This style embeds the documentation within the source files, using
+a few simple conventions.  The scripts/kernel-doc perl script, some
+SGML templates in Documentation/DocBook, and other tools understand
+these conventions, and are used to extract this embedded documentation
+into various documents.
+In order to provide good documentation of kernel functions and data
+structures, please use the following conventions to format your
+kernel-doc comments in Linux kernel source.
+We definitely need kernel-doc formatted documentation for functions
+that are exported to loadable modules using EXPORT_SYMBOL.
+We also look to provide kernel-doc formatted documentation for
+functions externally visible to other kernel files (not marked
+"static").
+We also recommend providing kernel-doc formatted documentation
+for private (file "static") routines, for consistency of kernel
+source code layout.  But this is lower priority and at the
+discretion of the MAINTAINER of that kernel source file.
+Data structures visible in kernel include files should also be
+documented using kernel-doc formatted comments.
+The opening comment mark "/**" is reserved for kernel-doc comments.
+Only comments so marked will be considered by the kernel-doc scripts,
+and any comment so marked must be in kernel-doc format.  Do not use
+"/**" to be begin a comment block unless the comment block contains
+kernel-doc formatted comments.  The closing comment marker for
+kernel-doc comments can be either "*/" or "**/".
+Kernel-doc comments should be placed just before the function
+or data structure being described.
+Example kernel-doc function comment:
+/**
+ * foobar() - short function description of foobar
+ * @arg1:       Describe the first argument to foobar.
+ * @arg2:       Describe the second argument to foobar.
+ *              One can provide multiple line descriptions
+ *              for arguments.
+ *
+ * A longer description, with more discussion of the function foobar()
+ * that might be useful to those using or modifying it.  Begins with
+ * empty comment line, and may include additional embedded empty
+ * comment lines.
+ *
+ * The longer description can have multiple paragraphs.
+ **/
+The first line, with the short description, must be on a single line.
+The @argument descriptions must begin on the very next line following
+this opening short function description line, with no intervening
+empty comment lines.
+Example kernel-doc data structure comment.
+/**
+ * struct blah - the basic blah structure
+ * @mem1:       describe the first member of struct blah
+ * @mem2:       describe the second member of struct blah,
+ *              perhaps with more lines and words.
+ *
+ * Longer description of this structure.
+ **/
+The kernel-doc function comments describe each parameter to the
+function, in order, with the @name lines.
+The kernel-doc data structure comments describe each structure member
+in the data structure, with the @name lines.
+The longer description formatting is "reflowed", losing your line
+breaks.  So presenting carefully formatted lists within these
+descriptions won't work so well; derived documentation will lose
+the formatting.
+See the section below "How to add extractable documentation to your
+source files" for more details and notes on how to format kernel-doc
+comments.
+Components of the kernel-doc system
+-----------------------------------
 Many places in the source tree have extractable documentation in the
 form of block comments above functions.  The components of this system
 are:
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt
index 5a4ef48224ae..28cdc2af2131 100644
--- a/Documentation/kernel-docs.txt
+++ b/Documentation/kernel-docs.txt
@@ -715,14 +715,14 @@
     * Name: "Gary's Encyclopedia - The Linux Kernel"
       Author: Gary (I suppose...).
-       URL: http://www.lisoleg.net/cgi-bin/lisoleg.pl?view=kernel.htm
+       URL: http://slencyclopedia.berlios.de/index.html
-       Keywords: links, not found here?.
+       Keywords: linux, community, everything!
       Description: Gary's Encyclopedia exists to allow the rapid finding
       of documentation and other information of interest to GNU/Linux
       users. It has about 4000 links to external pages in 150 major
       categories. This link is for kernel-specific links, documents,
-       sites... Look there if you could not find here what you were
+       sites...  This list is now hosted by developer.Berlios.de,
-       looking for.
+       but seems not to have been updated since sometime in 1999.
     * Name: "The home page of Linux-MM"
       Author: The Linux-MM team.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a3c35446e755..e7bea3e85304 100644
--- a/Documentation/kernel-parameters.txt
+++ b/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 }
@@ -271,6 +278,17 @@ and is between 256 and 4096 characters. It is defined in the file
        aic79xx=        [HW,SCSI]
                        See Documentation/scsi/aic79xx.txt.
+        amd_iommu=      [HW,X86-84]
+                        Pass parameters to the AMD IOMMU driver in the system.
+                        Possible values are:
+                        isolate - enable device isolation (each device, as far
+                                  as possible, will get its own protection
+                                  domain)
+        amd_iommu_size= [HW,X86-64]
+                        Define the size of the aperture for the AMD IOMMU
+                        driver. Possible values are:
+                        '32M', '64M' (default), '128M', '256M', '512M', '1G'
        amijoy.map=     [HW,JOY] Amiga joystick support
                        Map of devices attached to JOY0DAT and JOY1DAT
                        Format: <a>,<b>
@@ -295,7 +313,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        when initialising the APIC and IO-APIC components.
        apm=            [APM] Advanced Power Management
-                        See header of arch/i386/kernel/apm.c.
+                        See header of arch/x86/kernel/apm_32.c.
        arcrimi=        [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
                        Format: <io>,<irq>,<nodeID>
@@ -398,9 +416,6 @@ and is between 256 and 4096 characters. It is defined in the file
        cio_ignore=     [S390]
                        See Documentation/s390/CommonIO for details.
-        cio_msg=        [S390]
-                        See Documentation/s390/CommonIO for details.
        clock=          [BUGS=X86-32, HW] gettimeofday clocksource override.
                        [Deprecated]
                        Forces specified clocksource (if available) to be used
@@ -563,6 +578,8 @@ and is between 256 and 4096 characters. It is defined in the file
        debug_objects   [KNL] Enable object debugging
+        debugpat        [X86] Enable PAT debugging
        decnet.addr=    [HW,NET]
                        Format: <area>[,<node>]
                        See also Documentation/networking/decnet.txt.
@@ -602,6 +619,29 @@ and is between 256 and 4096 characters. It is defined in the file
                        See drivers/char/README.epca and
                        Documentation/digiepca.txt.
+        disable_mtrr_cleanup [X86]
+        enable_mtrr_cleanup [X86]
+                        The kernel tries to adjust MTRR layout from continuous
+                        to discrete, to make X server driver able to add WB
+                        entry later. This parameter enables/disables that.
+        mtrr_chunk_size=nn[KMG] [X86]
+                        used for mtrr cleanup. It is largest continous chunk
+                        that could hold holes aka. UC entries.
+        mtrr_gran_size=nn[KMG] [X86]
+                        Used for mtrr cleanup. It is granularity of mtrr block.
+                        Default is 1.
+                        Large value could prevent small alignment from
+                        using up MTRRs.
+        mtrr_spare_reg_nr=n [X86]
+                        Format: <integer>
+                        Range: 0,7 : spare reg number
+                        Default : 1
+                        Used for mtrr cleanup. It is spare mtrr entries number.
+                        Set to 2 or more if your graphical card needs more.
        disable_mtrr_trim [X86, Intel and AMD only]
                        By default the kernel will trim any uncacheable
                        memory out of your available memory pool based on
@@ -641,7 +681,7 @@ and is between 256 and 4096 characters. It is defined in the file
        elanfreq=       [X86-32]
                        See comment before function elanfreq_setup() in
-                        arch/i386/kernel/cpu/cpufreq/elanfreq.c.
+                        arch/x86/kernel/cpu/cpufreq/elanfreq.c.
        elevator=       [IOSCHED]
                        Format: {"anticipatory" | "cfq" | "deadline" | "noop"}
@@ -689,6 +729,12 @@ and is between 256 and 4096 characters. It is defined in the file
        floppy=         [HW]
                        See Documentation/floppy.txt.
+        force_pal_cache_flush
+                        [IA-64] Avoid check_sal_cache_flush which may hang on
+                        buggy SAL_CACHE_FLUSH implementations. Using this
+                        parameter will force ia64_sal_cache_flush to call
+                        ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
        gamecon.map[2|3]=
                        [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
                        support via parallel port (up to 5 devices per port)
@@ -719,9 +765,6 @@ and is between 256 and 4096 characters. It is defined in the file
        hd=             [EIDE] (E)IDE hard drive subsystem geometry
                        Format: <cyl>,<head>,<sect>
-        hd?=            [HW] (E)IDE subsystem
-        hd?lun=         See Documentation/ide/ide.txt.
        highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
                        size of <nn>. This works even on boxes that have no
                        highmem otherwise. This also works to reduce highmem
@@ -734,8 +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.
+        hugepages=      [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
-        hugepagesz=     [HW,IA-64,PPC] The size of the HugeTLB pages.
+        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
@@ -782,7 +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.
@@ -790,6 +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.
@@ -1094,9 +1154,6 @@ and is between 256 and 4096 characters. It is defined in the file
        mac5380=        [HW,SCSI] Format:
                        <can_queue>,<cmd_per_lun>,<sg_tablesize>,<hostid>,<use_tags>
-        mac53c9x=       [HW,SCSI] Format:
-                        <num_esps>,<disconnect>,<nosync>,<can_queue>,<cmd_per_lun>,<sg_tablesize>,<hostid>,<use_tags>
        machvec=        [IA64] Force the use of a particular machine-vector
                        (machvec) in a generic kernel.
                        Example: machvec=hpzx1_swiotlb
@@ -1166,7 +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>
@@ -1185,6 +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
@@ -1208,6 +1273,11 @@ and is between 256 and 4096 characters. It is defined in the file
        mtdparts=       [MTD]
                        See drivers/mtd/cmdlinepart.c.
+        mtdset=         [ARM]
+                        ARM/S3C2412 JIVE boot control
+                        See arch/arm/mach-s3c2412/mach-jive.c
        mtouchusb.raw_coordinates=
                        [HW] Make the MicroTouch USB driver use raw coordinates
                        ('y', default) or cooked coordinates ('n')
@@ -1234,6 +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.
@@ -1496,6 +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
@@ -1525,6 +1605,8 @@ and is between 256 and 4096 characters. It is defined in the file
                                This is normally done in pci_enable_device(),
                                so this option is a temporary workaround
                                for broken drivers that don't call it.
+                skip_isa_align  [X86] do not align io start addr, so can
+                                handle more pci cards
                firmware        [ARM] Do not re-enumerate the bus but instead
                                just use the configuration from the
                                bootloader. This is currently used on
@@ -1569,6 +1651,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        Format: { parport<nr> | timid | 0 }
                        See also Documentation/parport.txt.
+        pmtmr=          [X86] Manual setup of pmtmr I/O Port. 
+                        Override pmtimer IOPort with a hex value.
+                        e.g. pmtmr=0x508
        pnpacpi=        [ACPI]
                        { off }
@@ -1677,6 +1763,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        Format: <reboot_mode>[,<reboot_mode2>[,...]]
                        See arch/*/kernel/reboot.c or arch/*/kernel/process.c                   
+        relax_domain_level=
+                        [KNL, SMP] Set scheduler's default relax_domain_level.
+                        See Documentation/cpusets.txt.
        reserve=        [KNL,BUGS] Force the kernel to ignore some iomem area
        reservetop=     [X86-32]
@@ -1969,6 +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
@@ -2033,6 +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
@@ -2060,13 +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.
@@ -2100,6 +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
@@ -2110,6 +2206,9 @@ and is between 256 and 4096 characters. It is defined in the file
        usbhid.mousepoll=
                        [USBHID] The interval which mice are to be polled at.
+        add_efi_memmap  [EFI; x86-32,X86-64] Include EFI memory map in
+                        kernel's map of available physical RAM.
        vdso=           [X86-32,SH,x86-64]
                        vdso=2: enable compat VDSO (default with COMPAT_VDSO)
                        vdso=1: enable VDSO (default)
diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index d5c7a57d1700..b56aacc1fff8 100644
--- a/Documentation/keys.txt
+++ b/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);
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index bf3256e04027..51a8021ee532 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -305,7 +305,7 @@ should not be manipulated by any other user.
 A kset keeps its children in a standard kernel linked list.  Kobjects point
 back to their containing kset via their kset field. In almost all cases,
-the kobjects belonging to a ket have that kset (or, strictly, its embedded
+the kobjects belonging to a kset have that kset (or, strictly, its embedded
 kobject) in their parent.
 As a kset contains a kobject within it, it should always be dynamically
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 6877e7187113..a79633d702bf 100644
--- a/Documentation/kprobes.txt
+++ b/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
diff --git a/Documentation/laptops/acer-wmi.txt b/Documentation/laptops/acer-wmi.txt
index 79b7dbd22141..69b5dd4e5a59 100644
--- a/Documentation/laptops/acer-wmi.txt
+++ b/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
 *********
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 01c6c3d8a7e3..02dc748b76c4 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -1,7 +1,7 @@
                     ThinkPad ACPI Extras Driver
-                            Version 0.20
+                            Version 0.21
-                          April 09th, 2008
+                           May 29th, 2008
               Borislav Deianov <borislav@users.sf.net>
             Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -503,7 +503,7 @@ generate input device EV_KEY events.
 In addition to the EV_KEY events, thinkpad-acpi may also issue EV_SW
 events for switches:
-SW_RADIO        T60 and later hardare rfkill rocker switch
+SW_RFKILL_ALL   T60 and later hardare rfkill rocker switch
 SW_TABLET_MODE  Tablet ThinkPads HKEY events 0x5009 and 0x500A
 Non hot-key ACPI HKEY event map:
@@ -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
+        Note: this interface has been superseded by the generic rfkill
-        generic rfkill class, so it is NOT to be considered stable yet.
+        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
+        Note: this interface has been superseded by the generic rfkill
-        generic rfkill class, so it is NOT to be considered stable yet.
+        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
 ------------------------------------
diff --git a/Documentation/leds-class.txt b/Documentation/leds-class.txt
index 18860ad9935a..6399557cdab3 100644
--- a/Documentation/leds-class.txt
+++ b/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.
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 3be8ab2a886a..b88b0ea54e90 100644
--- a/Documentation/lguest/lguest.c
+++ b/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. */
+/* This will occupy 3 pages: it must be a power of 2. */
-#define VIRTQUEUE_NUM 128
+#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 */
+/* File descriptors for the Waker. */
-static int waker_fd;
+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;
@@ -155,8 +164,14 @@ struct virtqueue
        /* Last available index we saw. */
        u16 last_avail_idx;
-        /* The routine to call when the Guest pings us. */
+        /* The routine to call when the Guest pings us, or timeout. */
-        void (*handle_output)(int fd, struct virtqueue *me);
+        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" */
@@ -187,6 +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)
@@ -196,6 +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)
 {
@@ -251,6 +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;
 }
@@ -537,69 +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
+        /* Close the write end of the pipe: only the Launcher has it open. */
-         * we watch it, too. */
+        close(waker_fds.pipe[1]);
-        add_device_fd(pipefd);
        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);
+                select(maxfd+1, &rfds, NULL, NULL, NULL);
-                /* Is it a message from the Launcher? */
-                if (FD_ISSET(pipefd, &rfds)) {
+                /* Message from Launcher? */
-                        int fd;
+                if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
-                        /* If read() returns 0, it means the Launcher has
+                        char c;
-                         * exited.  We silently follow. */
+                        /* If this fails, then assume Launcher has exited.
-                        if (read(pipefd, &fd, sizeof(fd)) == 0)
+                         * Don't do anything on exit: we're just a thread! */
-                                exit(0);
+                        if (read(waker_fds.pipe[0], &c, 1) != 1)
-                        /* Otherwise it's telling us to change what file
+                                _exit(0);
-                         * descriptors we're to listen to.  Positive means
+                        continue;
-                         * listen to a new one, negative means stop
+                }
-                         * listening. */
-                        if (fd >= 0)
+                /* Send LHREQ_BREAK command to snap the Launcher out of it. */
-                                FD_SET(fd, &devices.infds);
+                pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
-                        else
-                                FD_CLR(-fd - 1, &devices.infds);
-                } else /* Send LHREQ_BREAK command. */
-                        pwrite(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)
+static void setup_waker(int lguest_fd)
-{
+{
-        int pipefd[2], child;
+        /* This pipe is closed when Launcher dies, telling Waker. */
+        if (pipe(waker_fds.pipe) != 0)
-        /* We create a pipe to talk to the Waker, and also so it knows when the
+                err(1, "Creating pipe for Waker");
-         * Launcher dies (and closes pipe). */
-        pipe(pipefd);
+        /* Waker also needs to know the lguest fd */
-        child = fork();
+        waker_fds.lguest_fd = lguest_fd;
-        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]);
-        /* Here is the fd used to talk to the waker. */
+        if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
-        return pipefd[1];
+                err(1, "Creating Waker");
 }
 /*
@@ -658,19 +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)
@@ -702,6 +746,7 @@ static unsigned get_vq_desc(struct virtqueue *vq,
                        errx(1, "Looped descriptor");
        } while ((i = next_desc(vq, i)) != vq->vring.num);
+        vq->inflight++;
        return head;
 }
@@ -719,6 +764,7 @@ static void add_used(struct virtqueue *vq, unsigned int head, int len)
        /* Make sure buffer is written before we update index. */
        wmb();
        vq->vring.used->idx++;
+        vq->inflight--;
 }
 /* This actually sends the interrupt for this virtqueue */
@@ -726,8 +772,9 @@ static void trigger_irq(int fd, struct virtqueue *vq)
 {
        unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
-        /* If they don't want an interrupt, don't send one. */
+        /* If they don't want an interrupt, don't send one, unless empty. */
-        if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
+        if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
+            && vq->inflight)
                return;
        /* Send the Guest an interrupt tell them we used something up. */
@@ -815,8 +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);
+                                close(waker_fds.pipe[1]);
-                                /* Just in case waker is blocked in BREAK, send
+                                /* Just in case Waker is blocked in BREAK, send
                                 * unbreak now. */
                                write(fd, args, sizeof(args));
                                exit(2);
@@ -833,7 +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;
@@ -848,6 +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
 *
@@ -855,22 +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
+                len = writev(vq->dev->fd, iov, out);
-                 * supported no features, so it shouldn't have anything
+                if (len < 0)
-                 * interesting). */
+                        err(1, "Writing network packet to tun");
-                (void)convert(&iov[0], struct virtio_net_hdr);
-                len = writev(vq->dev->fd, iov+1, out-1);
                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;
        }
 }
@@ -881,7 +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);
@@ -890,25 +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],
@@ -921,11 +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 */
+        /* Snap the Waker out of its select loop. */
-        write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+        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. */
@@ -945,7 +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);
@@ -954,10 +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)
@@ -994,7 +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;
                }
        }
@@ -1008,6 +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)
@@ -1018,16 +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;
@@ -1037,13 +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);
        }
 }
@@ -1092,7 +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));
@@ -1107,6 +1211,8 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
        vq->next = NULL;
        vq->last_avail_idx = 0;
        vq->dev = dev;
+        vq->inflight = 0;
+        vq->blocked = false;
        /* Initialize the configuration. */
        vq->config.num = num_descs;
@@ -1239,6 +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.
@@ -1257,10 +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]);
+        if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
-        return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+                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
@@ -1281,6 +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);
@@ -1289,64 +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,
+static void configure_device(int fd, const char *tapif, u32 ipaddr)
-                             unsigned char hwaddr[6])
 {
        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
+static int get_tun_device(char tapif[IFNAMSIZ])
- * 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)
 {
-        struct device *dev;
        struct ifreq ifr;
-        int netfd, ipfd;
+        int netfd;
-        u32 ip;
-        const char *br_name = NULL;
+        /* Start with this zeroed.  Messy but sure. */
-        struct virtio_net_config conf;
+        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 | IFF_VNET_HDR;
-        ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
        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
@@ -1357,27 +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;
+                arg += strlen(BRIDGE_PFX);
-                br_name = arg + strlen(BRIDGE_PFX);
+                bridging = true;
-                add_to_bridge(ipfd, ifr.ifr_name, br_name);
+        }
-        } else /* It is an IP address to set up the device with */
+        /* 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. */
+        /* Set up the tun device. */
-        configure_device(ipfd, ifr.ifr_name, ip, conf.mac);
+        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++;
-                devices.device_num++,
-                (u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
+        if (bridging)
-        if (br_name)
+                verbose("device %u: tun %s attached to bridge: %s\n",
-                verbose("attached to bridge: %s\n", br_name);
+                        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
@@ -1542,7 +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;
@@ -1613,6 +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. */
@@ -1620,11 +1873,12 @@ static void __attribute__((noreturn)) restart_guest(void)
 {
        unsigned int i;
-        /* Closing pipes causes the Waker thread and io_threads to die, and
+        /* Since we don't track all open fds, we simply close everything beyond
-         * closing /dev/lguest cleans up the Guest.  Since we don't track all
+         * stderr. */
-         * 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]);
 }
@@ -1655,7 +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");
@@ -1683,13 +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...]");
 }
@@ -1757,6 +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;
@@ -1775,6 +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));
@@ -1818,10 +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
+        /* We clone off a thread, which wakes the Launcher whenever one of the
-         * of the input file descriptors needs attention.  We call this the
+         * input file descriptors needs attention.  We call this the Waker, and
-         * Waker, and we'll cover it in a moment. */
+         * we'll cover it in a moment. */
-        waker_fd = setup_waker(lguest_fd);
+        setup_waker(lguest_fd);
        /* Finally, run the Guest.  This doesn't return. */
        run_guest(lguest_fd);
diff --git a/Documentation/local_ops.txt b/Documentation/local_ops.txt
index 4269a1105b37..f4f8b1c6c8ba 100644
--- a/Documentation/local_ops.txt
+++ b/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
diff --git a/Documentation/md.txt b/Documentation/md.txt
index a8b430627473..1da9d1b1793f 100644
--- a/Documentation/md.txt
+++ b/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
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index e5a819a4f0c9..f5b7127f54ac 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -994,7 +994,17 @@ The Linux kernel has eight basic CPU memory barriers:
        DATA DEPENDENCY read_barrier_depends()  smp_read_barrier_depends()
-All CPU memory barriers unconditionally imply compiler barriers.
+All memory barriers except the data dependency barriers imply a compiler
+barrier. Data dependencies do not impose any additional compiler ordering.
+Aside: In the case of data dependencies, the compiler would be expected to
+issue the loads in the correct order (eg. `a[b]` would have to load the value
+of b before loading a[b]), however there is no guarantee in the C specification
+that the compiler may not speculate the value of b (eg. is equal to 1) and load
+a before b (eg. tmp = a[1]; if (b != 1) tmp = a[b]; ). There is also the
+problem of a compiler reloading b after having loaded a[b], thus having a newer
+copy of b than a[b]. A consensus has not yet been reached about these problems,
+however the ACCESS_ONCE macro is a good place to start looking.
 SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
 systems because it is assumed that a CPU will appear to be self-consistent,
diff --git a/Documentation/moxa-smartio b/Documentation/moxa-smartio
index fe24ecc6372e..5337e80a5b96 100644
--- a/Documentation/moxa-smartio
+++ b/Documentation/moxa-smartio
@@ -1,14 +1,22 @@
 =============================================================================
+          MOXA Smartio/Industio Family Device Driver Installation Guide
-        MOXA Smartio Family Device Driver Ver 1.1 Installation Guide
+                    for Linux Kernel 2.4.x, 2.6.x
-                    for Linux Kernel 2.2.x and 2.0.3x
+               Copyright (C) 2008, Moxa Inc.
-               Copyright (C) 1999, Moxa Technologies Co, Ltd.
 =============================================================================
+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.
+    - 2 ports multiport board
-    -C168P/H/HS, C168H/PCI 8 port multiport board.
+        CP-102U, CP-102UL, CP-102UF
+        CP-132U-I, CP-132UL,
-   This driver has been modified a little and cleaned up from the Moxa
+        CP-132, CP-132I, CP132S, CP-132IS,
-   contributed driver code and merged into Linux 2.2.14pre. In particular
+        CI-132, CI-132I, CI-132IS,
-   official major/minor numbers have been assigned which are different to
+        (C102H, C102HI, C102HIS, C102P, CP-102, CP-102S)
-   those the original Moxa supplied driver used.
+    - 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
+   2.4.x and 2.6.x. This driver supports Intel x86 hardware platform. In order
-   Alpha hardware platform. In order to maintain compatibility, this version
+   to maintain compatibility, this version has also been properly tested with
-   has also been properly tested with RedHat, OpenLinux, TurboLinux and
+   RedHat, Mandrake, Fedora and S.u.S.E Linux. However, if compatibility problem
-   S.u.S.E Linux. However, if compatibility problem occurs, please contact
+   occurs, please contact Moxa at support@moxa.com.tw.
-   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
+   In Moxa's Web sites, you may always find latest driver at http://web.moxa.com.
-   ftp://ftp.moxa.com  or ftp://ftp.moxa.com.tw.
   This version of driver can be installed as Loadable Module (Module driver)
   or built-in into kernel (Static driver). You may refer to following
@@ -61,8 +89,8 @@ Content
 -----------------------------------------------------------------------------
 2. System Requirement
-   - Hardware platform: Intel x86 or Alpha machine
+   - Hardware platform: Intel x86 machine
-   - Kernel version: 2.0.3x or 2.2.x
+   - Kernel version: 2.4.x or 2.6.x
   - gcc version 2.72 or later
   - Maximum 4 boards can be installed in combination
@@ -70,9 +98,18 @@ Content
 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
+       There are two types of buses, ISA and PCI, for Smartio/Industio
-       board.
+       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
+       4 Moxa Smartio/Industio PCI Family multiport boards can be installed
-       one system and they can share the same IRQ.
+       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.
+       run the driver. If you prefer module driver, please refer to 3.4.
-       If static driver is required, 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
+       Naming convention for each Smartio/Industio multiport board is
-       as below.
+       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
+          # modprobe mxser <argument>
-          if "mxser.o" is activated.
-       2. Create special files by executing "msmknod".
+          will activate the module driver. You may run "lsmod" to check
-          # cd /moxa/mxser/driver
+          if "mxser" is activated. If the MOXA board is ISA board, the
-          # ./msmknod
+          <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
+          But if you use ISA board, please modify the "modprobe ..." command
-          174, 175. Msmknod will delete any special files occupying the same
+          to add the argument (see "3.4.5" section). After modifying the
-          device naming.
+          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
+          Run following command for setting rc files.
-          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.
          # 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
+          Check "rc.serial" is existed or not. If "rc.serial" doesn't exist,
-          parameters for ISA board. Please refer to rc.mxser for more detail.
+          create it by vi, run "chmod 755 rc.serial" to change the permission.
-          Find "rc.serial". If "rc.serial" doesn't exist, create it by vi.
+          Add "/etc/rc.d/rc.mxser" in last line,
-          Add "rc.mxser" in last line. Next, open rc.local by vi
-          and append following content.
-          if [ -f /etc/rc.d/rc.serial ]; then
+          Reboot and check if moxa.o activated by "lsmod" command.
-             sh /etc/rc.d/rc.serial
-          fi
-       4. Reboot and check if mxser.o activated by "lsmod" command.
+       3.4.5. If you'd like to drive Smartio/Industio ISA boards in the system,
-       5. If you'd like to drive Smartio ISA boards in the system, you'll
+          you'll have to add parameter to specify CAP address of given
-          have to add parameter to specify CAP address of given board while
+          board while activating "mxser.o". The format for parameters are
-          activating "mxser.o". The format for parameters are as follows.
+          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
+       3.5.4 Setup kernel configuration
-          # cd /usr/src/linux/drivers/char/
-          # vi tty_io.c
-            Find pty_init(), insert "mxser_init()" as
-            pty_init();
+          Configure the kernel:
-            mxser_init();
-       4. Modify tty.h
+            # cd /usr/src/linux
-          # cd /usr/src/linux/include/linux
+            # make menuconfig
-          # vi tty.h
-            Find extern int tty_init(void), insert "mxser_init()" as
-            extern int tty_init(void);
+          You will go into a menu-driven system. Please select [Character
-            extern int mxser_init(void);
+          devices][Non-standard serial port support], enable the [Moxa
-     
+          SmartIO support] driver with "[*]" for built-in (not "[M]"), then
-       5. Modify Makefile
+          select [Exit] to exit this program.
-          # 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
-       6. Rebuild kernel
+       3.5.5 Rebuild kernel
-          The following are for Linux kernel rebuilding,for your reference only.
+          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 */
+           b. make clean             /* take a few minutes */
-           c. make bzImage                 /* take probably 10-20 minutes */
+           c. make dep               /* take a few minutes */
-           d. Backup original boot kernel.                /* optional step */
+           d. make bzImage           /* take probably 10-20 minutes */
-           e. cp /usr/src/linux/arch/i386/boot/bzImage /boot/vmlinuz
+           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
+              correct position.
-              check /etc/lilo.conf 'image' item specified the path
+           g. If you use 'lilo' utility, you should check /etc/lilo.conf
-              which is the 'vmlinuz' path, or you will load wrong
+              'image' item specified the path which is the 'vmlinuz' path,
-              (or old) boot kernel image (vmlinuz).
+              or you will load wrong (or old) boot kernel image (vmlinuz).
-           g. chmod 400 /vmlinuz
+              After checking /etc/lilo.conf, please run "lilo".
-           h. lilo
-           i. rdev -R /vmlinuz 1
+          Note that if the result of "make bzImage" is ERROR, then you have to
-           j. sync
+          go back to Linux configuration Setup. Type "make menuconfig" in
+          directory /usr/src/linux.
-          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".
+       3.5.6 Make tty device and special file
-          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
          # 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
+   This utility provides the function to display what Moxa Smartio/Industio
-   board exists in the system.
+   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.
 -----------------------------------------------------------------------------
diff --git a/Documentation/networking/arcnet.txt b/Documentation/networking/arcnet.txt
index 770fc41a78e8..796012540386 100644
--- a/Documentation/networking/arcnet.txt
+++ b/Documentation/networking/arcnet.txt
@@ -46,7 +46,7 @@ These are the ARCnet drivers for Linux.
 This new release (2.91) has been put together by David Woodhouse 
-<dwmw2@cam.ac.uk>, in an attempt to tidy up the driver after adding support 
+<dwmw2@infradead.org>, in an attempt to tidy up the driver after adding support
 for yet another chipset. Now the generic support has been separated from the
 individual chipset drivers, and the source files aren't quite so packed with
 #ifdefs! I've changed this file a bit, but kept it in the first person from
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index a0cda062bc33..688dfe1e6b70 100644
--- a/Documentation/networking/bonding.txt
+++ b/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
+        the same MAC address at enslavement (the traditional
-        enabled, change the bond's MAC address when changing the
+        behavior), or, when enabled, perform special handling of the
-        active interface (i.e., fail over the MAC address itself).
+        bond's MAC address in accordance with the selected policy.
-        Fail over MAC is useful for devices that cannot ever alter
+        Possible values are:
-        their MAC address, or for devices that refuse incoming
-        broadcasts with their own source MAC (which interferes with
+        none or 0
-        the ARP monitor).
+                This setting disables fail_over_mac, and causes
-        The down side of fail over MAC is that every device on the
+                bonding to set all slaves of an active-backup bond to
-        network must be updated via gratuitous ARP, vs. just updating
+                the same MAC address at enslavement time.  This is the
-        a switch or set of switches (which often takes place for any
+                default.
-        traffic, not just ARP traffic, if the switch snoops incoming
-        traffic to update its tables) for the traditional method.  If
+        active or 1
-        the gratuitous ARP is lost, communication may be disrupted.
+                The "active" fail_over_mac policy indicates that the
-        When fail over MAC is used in conjuction with the mii monitor,
+                MAC address of the bond should always be the MAC
-        devices which assert link up prior to being able to actually
+                address of the currently active slave.  The MAC
-        transmit and receive are particularly susecptible to loss of
+                address of the slaves is not changed; instead, the MAC
-        the gratuitous ARP, and an appropriate updelay setting may be
+                address of the bond changes during a failover.
-        required.
+                This policy is useful for devices that cannot ever
-        A value of 0 disables fail over MAC, and is the default.  A
+                alter their MAC address, or for devices that refuse
-        value of 1 enables fail over MAC.  This option is enabled
+                incoming broadcasts with their own source MAC (which
-        automatically if the first slave added cannot change its MAC
+                interferes with the ARP monitor).
-        address.  This option may be modified via sysfs only when no
-        slaves are present in the bond.
+                The down side of this policy is that every device on
+                the network must be updated via gratuitous ARP,
-        This option was added in bonding version 3.2.0.
+                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
diff --git a/Documentation/networking/bridge.txt b/Documentation/networking/bridge.txt
index bdae2db4119c..bec69a8a1697 100644
--- a/Documentation/networking/bridge.txt
+++ b/Documentation/networking/bridge.txt
@@ -1,6 +1,6 @@
 In order to use the Ethernet bridging functionality, you'll need the
 userspace tools. These programs and documentation are available
-at http://bridge.sourceforge.net.  The download page is
+at http://www.linux-foundation.org/en/Net:Bridge.  The download page is
 http://prdownloads.sourceforge.net/bridge.
 If you still have questions, don't hesitate to post to the mailing list 
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 641d2afacffa..297ba7b1ccaf 100644
--- a/Documentation/networking/can.txt
+++ b/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)
diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/dm9000.txt
new file mode 100644
index 000000000000..65df3dea5561
--- /dev/null
+++ b/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.
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 61b171cf5313..2df71861e578 100644
--- a/Documentation/networking/e1000.txt
+++ b/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
+  NAPI (Rx polling mode) is enabled in the e1000 driver.
-  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
  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 17a6e46fbd43..d84932650fd3 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -81,23 +81,23 @@ inet_peer_minttl - INTEGER
        Minimum time-to-live of entries.  Should be enough to cover fragment
        time-to-live on the reassembling side.  This minimum time-to-live  is
        guaranteed if the pool size is less than inet_peer_threshold.
-        Measured in jiffies(1).
+        Measured in seconds.
 inet_peer_maxttl - INTEGER
        Maximum time-to-live of entries.  Unused entries will expire after
        this period of time if there is no memory pressure on the pool (i.e.
        when the number of entries in the pool is very small).
-        Measured in jiffies(1).
+        Measured in seconds.
 inet_peer_gc_mintime - INTEGER
        Minimum interval between garbage collection passes.  This interval is
        in effect under high memory pressure on the pool.
-        Measured in jiffies(1).
+        Measured in seconds.
 inet_peer_gc_maxtime - INTEGER
        Minimum interval between garbage collection passes.  This interval is
        in effect under low (or absent) memory pressure on the pool.
-        Measured in jiffies(1).
+        Measured in seconds.
 TCP variables: 
@@ -148,9 +148,9 @@ tcp_available_congestion_control - STRING
        but not loaded.
 tcp_base_mss - INTEGER
-        The initial value of search_low to be used by Packetization Layer
+        The initial value of search_low to be used by the packetization layer
-        Path MTU Discovery (MTU probing).  If MTU probing is enabled,
+        Path MTU discovery (MTU probing).  If MTU probing is enabled,
-        this is the inital MSS used by the connection.
+        this is the initial MSS used by the connection.
 tcp_congestion_control - STRING
        Set the congestion control algorithm to be used for new
@@ -185,10 +185,9 @@ tcp_frto - INTEGER
        timeouts.  It is particularly beneficial in wireless environments
        where packet loss is typically due to random radio interference
        rather than intermediate router congestion.  F-RTO is sender-side
-        only modification.  Therefore it does not require any support from
+        only modification. Therefore it does not require any support from
-        the peer, but in a typical case, however, where wireless link is
+        the peer.
-        the local access link and most of the data flows downlink, the
-        faraway servers should have F-RTO enabled to take advantage of it.
        If set to 1, basic version is enabled.  2 enables SACK enhanced
        F-RTO if flow uses SACK.  The basic version can be used also when
        SACK is in use though scenario(s) with it exists where F-RTO
@@ -276,7 +275,7 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max
        memory.
 tcp_moderate_rcvbuf - BOOLEAN
-        If set, TCP performs receive buffer autotuning, attempting to
+        If set, TCP performs receive buffer auto-tuning, attempting to
        automatically size the buffer (no greater than tcp_rmem[2]) to
        match the size required by the path for full throughput.  Enabled by
        default.
@@ -336,7 +335,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
        pressure.
        Default: 8K
-        default: default size of receive buffer used by TCP sockets.
+        default: initial size of receive buffer used by TCP sockets.
        This value overrides net.core.rmem_default used by other protocols.
        Default: 87380 bytes. This value results in window of 65535 with
        default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
@@ -344,8 +343,10 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
        max: maximal size of receive buffer allowed for automatically
        selected receiver buffers for TCP socket. This value does not override
-        net.core.rmem_max, "static" selection via SO_RCVBUF does not use this.
+        net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
-        Default: 87380*2 bytes.
+        automatic tuning of that socket's receive buffer size, in which
+        case this value is ignored.
+        Default: between 87380B and 4MB, depending on RAM size.
 tcp_sack - BOOLEAN
        Enable select acknowledgments (SACKS).
@@ -358,7 +359,7 @@ tcp_slow_start_after_idle - BOOLEAN
        Default: 1
 tcp_stdurg - BOOLEAN
-        Use the Host requirements interpretation of the TCP urg pointer field.
+        Use the Host requirements interpretation of the TCP urgent pointer field.
        Most hosts use the older BSD interpretation, so if you turn this on
        Linux might not communicate correctly with them.
        Default: FALSE
@@ -371,12 +372,12 @@ tcp_synack_retries - INTEGER
 tcp_syncookies - BOOLEAN
        Only valid when the kernel was compiled with CONFIG_SYNCOOKIES
        Send out syncookies when the syn backlog queue of a socket
-        overflows. This is to prevent against the common 'syn flood attack'
+        overflows. This is to prevent against the common 'SYN flood attack'
        Default: FALSE
        Note, that syncookies is fallback facility.
        It MUST NOT be used to help highly loaded servers to stand
-        against legal connection rate. If you see synflood warnings
+        against legal connection rate. If you see SYN flood warnings
        in your logs, but investigation shows that they occur
        because of overload with legal connections, you should tune
        another parameters until this warning disappear.
@@ -386,7 +387,7 @@ tcp_syncookies - BOOLEAN
        to use TCP extensions, can result in serious degradation
        of some services (f.e. SMTP relaying), visible not by you,
        but your clients and relays, contacting you. While you see
-        synflood warnings in logs not being really flooded, your server
+        SYN flood warnings in logs not being really flooded, your server
        is seriously misconfigured.
 tcp_syn_retries - INTEGER
@@ -419,19 +420,21 @@ tcp_window_scaling - BOOLEAN
        Enable window scaling as defined in RFC1323.
 tcp_wmem - vector of 3 INTEGERs: min, default, max
-        min: Amount of memory reserved for send buffers for TCP socket.
+        min: Amount of memory reserved for send buffers for TCP sockets.
        Each TCP socket has rights to use it due to fact of its birth.
        Default: 4K
-        default: Amount of memory allowed for send buffers for TCP socket
+        default: initial size of send buffer used by TCP sockets.  This
-        by default. This value overrides net.core.wmem_default used
+        value overrides net.core.wmem_default used by other protocols.
-        by other protocols, it is usually lower than net.core.wmem_default.
+        It is usually lower than net.core.wmem_default.
        Default: 16K
-        max: Maximal amount of memory allowed for automatically selected
+        max: Maximal amount of memory allowed for automatically tuned
-        send buffers for TCP socket. This value does not override
+        send buffers for TCP sockets. This value does not override
-        net.core.wmem_max, "static" selection via SO_SNDBUF does not use this.
+        net.core.wmem_max.  Calling setsockopt() with SO_SNDBUF disables
-        Default: 128K
+        automatic tuning of that socket's send buffer size, in which case
+        this value is ignored.
+        Default: between 64K and 4MB, depending on RAM size.
 tcp_workaround_signed_windows - BOOLEAN
        If set, assume no receipt of a window scaling option means the
@@ -548,8 +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)
+        0 to disable any limiting,
-        Default: 100
+        otherwise the minimal space between responses in milliseconds.
+        Default: 1000
 icmp_ratemask - INTEGER
        Mask made of ICMP types for which rates are being limited.
@@ -794,10 +798,6 @@ tag - INTEGER
        Allows you to write a number, which can be used as required.
        Default value is 0.
-(1) Jiffie: internal timeunit for the kernel. On the i386 1/100s, on the
-Alpha 1/1024s. See the HZ define in /usr/include/asm/param.h for the exact
-value on your system. 
 Alexey Kuznetsov.
 kuznet@ms2.inr.ac.ru
@@ -1024,11 +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)
+        0 to disable any limiting,
-        Default: 100
+        otherwise the minimal space between responses in milliseconds.
+        Default: 1000
 IPv6 Update by:
@@ -1064,24 +1076,193 @@ bridge-nf-filter-pppoe-tagged - BOOLEAN
        Default: 1
-UNDOCUMENTED:
+proc/sys/net/sctp/* Variables:
+addip_enable - BOOLEAN
+        Enable or disable extension of  Dynamic Address Reconfiguration
+        (ADD-IP) functionality specified in RFC5061.  This extension provides
+        the ability to dynamically add and remove new addresses for the SCTP
+        associations.
+        1: Enable extension.
+        0: Disable extension.
+        Default: 0
+addip_noauth_enable - BOOLEAN
+        Dynamic Address Reconfiguration (ADD-IP) requires the use of
+        authentication to protect the operations of adding or removing new
+        addresses.  This requirement is mandated so that unauthorized hosts
+        would not be able to hijack associations.  However, older
+        implementations may not have implemented this requirement while
+        allowing the ADD-IP extension.  For reasons of interoperability,
+        we provide this variable to control the enforcement of the
+        authentication requirement.
+        1: Allow ADD-IP extension to be used without authentication.  This
+           should only be set in a closed environment for interoperability
+           with older implementations.
+        0: Enforce the authentication requirement
+        Default: 0
+auth_enable - BOOLEAN
+        Enable or disable Authenticated Chunks extension.  This extension
+        provides the ability to send and receive authenticated chunks and is
+        required for secure operation of Dynamic Address Reconfiguration
+        (ADD-IP) extension.
+        1: Enable this extension.
+        0: Disable this extension.
+        Default: 0
+prsctp_enable - BOOLEAN
+        Enable or disable the Partial Reliability extension (RFC3758) which
+        is used to notify peers that a given DATA should no longer be expected.
+        1: Enable extension
+        0: Disable
+        Default: 1
+max_burst - INTEGER
+        The limit of the number of new packets that can be initially sent.  It
+        controls how bursty the generated traffic can be.
+        Default: 4
+association_max_retrans - INTEGER
+        Set the maximum number for retransmissions that an association can
+        attempt deciding that the remote end is unreachable.  If this value
+        is exceeded, the association is terminated.
+        Default: 10
+max_init_retransmits - INTEGER
+        The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
+        that an association will attempt before declaring the destination
+        unreachable and terminating.
+        Default: 8
+path_max_retrans - INTEGER
+        The maximum number of retransmissions that will be attempted on a given
+        path.  Once this threshold is exceeded, the path is considered
+        unreachable, and new traffic will use a different path when the
+        association is multihomed.
+        Default: 5
-dev_weight FIXME
+rto_initial - INTEGER
-discovery_slots FIXME
+        The initial round trip timeout value in milliseconds that will be used
-discovery_timeout FIXME
+        in calculating round trip times.  This is the initial time interval
-fast_poll_increase FIXME
+        for retransmissions.
-ip6_queue_maxlen FIXME
-lap_keepalive_time FIXME
+        Default: 3000
-lo_cong FIXME
-max_baud_rate FIXME
+rto_max - INTEGER
-max_dgram_qlen FIXME
+        The maximum value (in milliseconds) of the round trip timeout.  This
-max_noreply_time FIXME
+        is the largest time interval that can elapse between retransmissions.
-max_tx_data_size FIXME
-max_tx_window FIXME
+        Default: 60000
-min_tx_turn_time FIXME
-mod_cong FIXME
+rto_min - INTEGER
-no_cong FIXME
+        The minimum value (in milliseconds) of the round trip timeout.  This
-no_cong_thresh FIXME
+        is the smallest time interval the can elapse between retransmissions.
-slot_timeout FIXME
-warn_noreply_time FIXME
+        Default: 1000
+hb_interval - INTEGER
+        The interval (in milliseconds) between HEARTBEAT chunks.  These chunks
+        are sent at the specified interval on idle paths to probe the state of
+        a given path between 2 associations.
+        Default: 30000
+sack_timeout - INTEGER
+        The amount of time (in milliseconds) that the implementation will wait
+        to send a SACK.
+        Default: 200
+valid_cookie_life - INTEGER
+        The default lifetime of the SCTP cookie (in milliseconds).  The cookie
+        is used during association establishment.
+        Default: 60000
+cookie_preserve_enable - BOOLEAN
+        Enable or disable the ability to extend the lifetime of the SCTP cookie
+        that is used during the establishment phase of SCTP association
+        1: Enable cookie lifetime extension.
+        0: Disable
+        Default: 1
+rcvbuf_policy - INTEGER
+        Determines if the receive buffer is attributed to the socket or to
+        association.   SCTP supports the capability to create multiple
+        associations on a single socket.  When using this capability, it is
+        possible that a single stalled association that's buffering a lot
+        of data may block other associations from delivering their data by
+        consuming all of the receive buffer space.  To work around this,
+        the rcvbuf_policy could be set to attribute the receiver buffer space
+        to each association instead of the socket.  This prevents the described
+        blocking.
+        1: rcvbuf space is per association
+        0: recbuf space is per socket
+        Default: 0
+sndbuf_policy - INTEGER
+        Similar to rcvbuf_policy above, this applies to send buffer space.
+        1: Send buffer is tracked per association
+        0: Send buffer is tracked per socket.
+        Default: 0
+sctp_mem - vector of 3 INTEGERs: min, pressure, max
+        Number of pages allowed for queueing by all SCTP sockets.
+        min: Below this number of pages SCTP is not bothered about its
+        memory appetite. When amount of memory allocated by SCTP exceeds
+        this number, SCTP starts to moderate memory usage.
+        pressure: This value was introduced to follow format of tcp_mem.
+        max: Number of pages allowed for queueing by all SCTP sockets.
+        Default is calculated at boot time from amount of available memory.
+sctp_rmem - vector of 3 INTEGERs: min, default, max
+        See tcp_rmem for a description.
+sctp_wmem  - vector of 3 INTEGERs: min, default, max
+        See tcp_wmem for a description.
+UNDOCUMENTED:
+/proc/sys/net/core/*
+        dev_weight FIXME
+/proc/sys/net/unix/*
+        max_dgram_qlen FIXME
+/proc/sys/net/irda/*
+        fast_poll_increase FIXME
+        warn_noreply_time FIXME
+        discovery_slots FIXME
+        slot_timeout FIXME
+        max_baud_rate FIXME
+        discovery_timeout FIXME
+        lap_keepalive_time FIXME
+        max_noreply_time FIXME
+        max_tx_data_size FIXME
+        max_tx_window FIXME
+        min_tx_turn_time FIXME
diff --git a/Documentation/networking/ixgb.txt b/Documentation/networking/ixgb.txt
index 7c98277777eb..a0d0ffb5e584 100644
--- a/Documentation/networking/ixgb.txt
+++ b/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 
+This file describes the ixgb Linux Base Driver for the 10 Gigabit Intel(R)
-of Adapters, version 1.0.x.  
+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 
+The following Intel network adapters are compatible with the drivers in this
-adapter. Look for a label that has a barcode and a number in the format  
+release:
-A12345-001. 
+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 
+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
+used by entering them on the command line with the modprobe command using
-using this syntax:
+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
+unless otherwise noted.
-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.
 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
+         If EEPROM is not detected, default is 1
-    This parameter controls the automatic generation(Tx) and response(Rx) to 
+    This parameter controls the automatic generation(Tx) and response(Rx) to
-    Ethernet PAUSE frames.
+    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. 
+    This value is the number of receive descriptors allocated by the driver.
-    Increasing this value allows the driver to buffer more incoming packets. 
+    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 is 16 bytes.  A receive buffer is also allocated for
-    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes, 
+    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 
+    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
+Default Value: 72
-    This value delays the generation of receive interrupts in units of 
+    This value delays the generation of receive interrupts in units of
-    0.8192 microseconds.  Receive interrupt reduction can improve CPU 
+    0.8192 microseconds.  Receive interrupt reduction can improve CPU
-    efficiency if properly tuned for specific network traffic. Increasing 
+    efficiency if properly tuned for specific network traffic.  Increasing
-    this value adds extra latency to frame reception and can end up 
+    this value adds extra latency to frame reception and can end up
-    decreasing the throughput of TCP traffic. If the system is reporting 
+    decreasing the throughput of TCP traffic.  If the system is reporting
-    dropped receives, this value may be set too high, causing the driver to 
+    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 
+With the 10 Gigabit server adapters, the default Linux configuration will
-likely limit the total available throughput artificially.  There is a set of 
+very likely limit the total available throughput artificially.  There is a set
-things that when applied together increase the ability of Linux to transmit 
+of configuration changes that, when applied together, will increase the ability
-and receive data.  The following enhancements were originally acquired from
+of Linux to transmit and receive data.  The following enhancements were
-settings published at http://www.spec.org/web99 for various submitted results 
+originally acquired from settings published at http://www.spec.org/web99/ for
-using Linux.
+various submitted results using Linux.
-NOTE: These changes are only suggestions, and serve as a starting point for 
+NOTE: These changes are only suggestions, and serve as a starting point for
-tuning your network performance.
+      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 
+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 
+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 
+behavior after modifying this register may be undefined (possibly errors of
-kind). A power-cycle, hard reset or explicitly setting the e6 register back to 
+some kind).  A power-cycle, hard reset or explicitly setting the e6 register
-22 (setpci -d 8086:1048 e6.b=22) may be required to get back to a stable 
+back to 22 (setpci -d 8086:1a48 e6.b=22) may be required to get back to a
-configuration.
+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
+# replace 1a48 with appropriate 10GbE device's ID installed on the system,
-# set the MTU (max transmission unit) - it requires your switch and clients to change too!
+# 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 
+# call the sysctl utility to modify /proc/sys entries
-sysctl -p ./sysctl_ixgb.conf 
+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
+# turn TCP timestamp support off, default 1, reduces CPU use
-net.ipv4.tcp_sack = 0 # turn SACK support off, default on
+net.ipv4.tcp_timestamps = 0
-# on systems with a VERY fast bus -> memory interface this is the big gainer 
+# turn SACK support off, default on
-net.ipv4.tcp_rmem = 10000000 10000000 10000000 # sets min/default/max TCP read buffer, default 4096 87380 174760
+# on systems with a VERY fast bus -> memory interface this is the big gainer
-net.ipv4.tcp_wmem = 10000000 10000000 10000000 # sets min/pressure/max TCP write buffer, default 4096 16384 131072
+net.ipv4.tcp_sack = 0
-net.ipv4.tcp_mem = 10000000 10000000 10000000 # sets min/pressure/max TCP buffer space, default 31744 32256 32768
+# 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
+# set maximum receive socket buffer size, default 131071
-net.core.wmem_max = 524287 # maximum send socket buffer size, default 131071
+net.core.rmem_max = 524287
-net.core.rmem_default = 524287 # default receive socket buffer size, default 65535
+# set maximum send socket buffer size, default 131071
-net.core.wmem_default = 524287 # default send socket buffer size, default 65535
+net.core.wmem_max = 524287
-net.core.optmem_max = 524287 # maximum amount of option memory buffers, default 10240
+# set default receive socket buffer size, default 65535
-net.core.netdev_max_backlog = 300000 # number of unprocessed input packets before kernel starts dropping them, default 300
+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 
+Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface
-your ixgb driver is using.
+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 
+NOTE: Unless these scripts are added to the boot process, these changes will
-only last only until the next system reboot.
+      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 
+For instance, use the commands:
-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: 
    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 
+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 
+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 
+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 
+kernel with a supported adapter, email the specific information related
-the issue to linux.nics@intel.com.
+to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/mac80211_hwsim/README b/Documentation/networking/mac80211_hwsim/README
new file mode 100644
index 000000000000..2ff8ccb8dc37
--- /dev/null
+++ b/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
diff --git a/Documentation/networking/mac80211_hwsim/hostapd.conf b/Documentation/networking/mac80211_hwsim/hostapd.conf
new file mode 100644
index 000000000000..08cde7e35f2e
--- /dev/null
+++ b/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
diff --git a/Documentation/networking/mac80211_hwsim/wpa_supplicant.conf b/Documentation/networking/mac80211_hwsim/wpa_supplicant.conf
new file mode 100644
index 000000000000..299128cff035
--- /dev/null
+++ b/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
+}
diff --git a/Documentation/networking/multiqueue.txt b/Documentation/networking/multiqueue.txt
index ea5a42e8f79f..d391ea631141 100644
--- a/Documentation/networking/multiqueue.txt
+++ b/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
+Kernel support for multiqueue devices is always present.
-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.
 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>
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index db0cd5169581..07c53d596035 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -326,7 +326,7 @@ just one call to mmap is needed:
    mmap(0, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
 If tp_frame_size is a divisor of tp_block_size frames will be 
-contiguosly spaced by tp_frame_size bytes. If not, each 
+contiguously spaced by tp_frame_size bytes. If not, each
 tp_block_size/tp_frame_size frames there will be a gap between 
 the frames. This is because a frame cannot be spawn across two
 blocks. 
diff --git a/Documentation/networking/s2io.txt b/Documentation/networking/s2io.txt
index 4bde53e85f3f..c3d6b4d5d014 100644
--- a/Documentation/networking/s2io.txt
+++ b/Documentation/networking/s2io.txt
@@ -52,13 +52,10 @@ d. MSI/MSI-X. Can be enabled on platforms which support this feature
 (IA64, Xeon) resulting in noticeable performance improvement(upto 7%
 on certain platforms).
-e. NAPI. Compile-time option(CONFIG_S2IO_NAPI) for better Rx interrupt 
+e. Statistics. Comprehensive MAC-level and software statistics displayed
-moderation.
-f. Statistics. Comprehensive MAC-level and software statistics displayed
 using "ethtool -S" option.
-g. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings, 
+f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
 with multiple steering options.
 4.  Command line parameters
@@ -83,9 +80,9 @@ Valid range: Limited by memory on system
 Default: 30 
 e. intr_type
-Specifies interrupt type. Possible values 1(INTA), 2(MSI), 3(MSI-X)
+Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
-Valid range: 1-3
+Valid values: 0, 2
-Default: 1 
+Default: 2
 5.  Performance suggestions
 General:
diff --git a/Documentation/networking/tc-actions-env-rules.txt b/Documentation/networking/tc-actions-env-rules.txt
index 01e716d185f4..dcadf6f88e34 100644
--- a/Documentation/networking/tc-actions-env-rules.txt
+++ b/Documentation/networking/tc-actions-env-rules.txt
@@ -4,26 +4,27 @@ The "enviromental" rules for authors of any new tc actions are:
 1) If you stealeth or borroweth any packet thou shalt be branching
 from the righteous path and thou shalt cloneth.
-For example if your action queues a packet to be processed later
+For example if your action queues a packet to be processed later,
-or intentionaly branches by redirecting a packet then you need to
+or intentionally branches by redirecting a packet, then you need to
 clone the packet.
 There are certain fields in the skb tc_verd that need to be reset so we
-avoid loops etc. A few are generic enough so much so that skb_act_clone()
+avoid loops, etc.  A few are generic enough that skb_act_clone()
-resets them for you. So invoke skb_act_clone() rather than skb_clone()
+resets them for you, so invoke skb_act_clone() rather than skb_clone().
 2) If you munge any packet thou shalt call pskb_expand_head in the case
 someone else is referencing the skb. After that you "own" the skb.
 You must also tell us if it is ok to munge the packet (TC_OK2MUNGE),
 this way any action downstream can stomp on the packet.
-3) dropping packets you dont own is a nono. You simply return
+3) Dropping packets you don't own is a no-no. You simply return
 TC_ACT_SHOT to the caller and they will drop it.
 The "enviromental" rules for callers of actions (qdiscs etc) are:
-*) thou art responsible for freeing anything returned as being
+*) Thou art responsible for freeing anything returned as being
 TC_ACT_SHOT/STOLEN/QUEUED. If none of TC_ACT_SHOT/STOLEN/QUEUED is
-returned then all is great and you dont need to do anything.
+returned, then all is great and you don't need to do anything.
 Post on netdev if something is unclear.
diff --git a/Documentation/networking/udplite.txt b/Documentation/networking/udplite.txt
index 3870f280280b..855d8da57a23 100644
--- a/Documentation/networking/udplite.txt
+++ b/Documentation/networking/udplite.txt
@@ -148,7 +148,7 @@
        getsockopt(sockfd, SOL_SOCKET, SO_NO_CHECK, &value, ...);
  is meaningless (as in TCP). Packets with a zero checksum field are
-  illegal (cf. RFC 3828, sec. 3.1) will be silently discarded.
+  illegal (cf. RFC 3828, sec. 3.1) and will be silently discarded.
  4) Fragmentation
diff --git a/Documentation/nmi_watchdog.txt b/Documentation/nmi_watchdog.txt
index 757c729ee42e..90aa4531cb67 100644
--- a/Documentation/nmi_watchdog.txt
+++ b/Documentation/nmi_watchdog.txt
@@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'.  (NMI: Non Maskable Interrupt
 which get executed even if the system is otherwise locked up hard).
 This can be used to debug hard kernel lockups.  By executing periodic
 NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.  
+and print out debugging messages if so.
 In order to use the NMI watchdog, you need to have APIC support in your
 kernel. For SMP kernels, APIC support gets compiled in automatically. For
@@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor with an IO-APIC. [Note: certain
 kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
 may implicitly disable the NMI watchdog.]
-For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
+For x86-64, the needed APIC is always compiled in.
-always enabled with I/O-APIC mode (nmi_watchdog=1).
 Using local APIC (nmi_watchdog=2) needs the first performance register, so
 you can't use it for other purposes (such as high precision performance
@@ -63,16 +62,15 @@ when the system is idle), but if your system locks up on anything but the
 "hlt", then you are out of luck -- the event will not happen at all and the
 watchdog won't trigger. This is a shortcoming of the local APIC watchdog
 -- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.  
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
 But its NMI frequency is much higher, resulting in a more significant hit
 to the overall system performance.
-NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
+On x86 nmi_watchdog is disabled by default so you have to enable it with
-you have to enable it with a boot time parameter.  Prior to 2.4.2-ac18
+a boot time parameter.
-the NMI-oopser is enabled unconditionally on x86 SMP boxes.
-On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
+NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
-it uses IO-APIC by default and on AMD it uses local APIC.
+on x86 SMP boxes.
 [ feel free to send bug reports, suggestions and patches to
  Ingo Molnar <mingo@redhat.com> or the Linux SMP mailing
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index a55d7f1c836d..fb742c213c9e 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
        - This file
+apm-acpi.txt
+        - basic info about the APM and ACPI support.
 basic-pm-debugging.txt
        - Debugging suspend and resume
 devices.txt
@@ -14,8 +16,6 @@ notifiers.txt
        - Registering suspend notifiers in device drivers
 pci.txt
        - How the PCI Subsystem Does Power Management
-pm.txt
-        - info on Linux power management support.
 pm_qos_interface.txt
        - info on Linux PM Quality of Service interface
 power_supply_class.txt
diff --git a/Documentation/power/apm-acpi.txt b/Documentation/power/apm-acpi.txt
new file mode 100644
index 000000000000..1bd799dc17e8
--- /dev/null
+++ b/Documentation/power/apm-acpi.txt
@@ -0,0 +1,32 @@
+APM or ACPI?
+------------
+If you have a relatively recent x86 mobile, desktop, or server system,
+odds are it supports either Advanced Power Management (APM) or
+Advanced Configuration and Power Interface (ACPI).  ACPI is the newer
+of the two technologies and puts power management in the hands of the
+operating system, allowing for more intelligent power management than
+is possible with BIOS controlled APM.
+The best way to determine which, if either, your system supports is to
+build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is
+enabled by default).  If a working ACPI implementation is found, the
+ACPI driver will override and disable APM, otherwise the APM driver
+will be used.
+No, sorry, you cannot have both ACPI and APM enabled and running at
+once.  Some people with broken ACPI or broken APM implementations
+would like to use both to get a full set of working features, but you
+simply cannot mix and match the two.  Only one power management
+interface can be in control of the machine at once.  Think about it..
+User-space Daemons
+------------------
+Both APM and ACPI rely on user-space daemons, apmd and acpid
+respectively, to be completely functional.  Obtain both of these
+daemons from your Linux distribution or from the Internet (see below)
+and be sure that they are started sometime in the system boot process.
+Go ahead and start both.  If ACPI or APM is not available on your
+system the associated daemon will exit gracefully.
+  apmd:   http://worldvisions.ca/~apenwarr/apmd/
+  acpid:  http://acpid.sf.net/
diff --git a/Documentation/power/pm.txt b/Documentation/power/pm.txt
deleted file mode 100644
index be841507e43f..000000000000
--- a/Documentation/power/pm.txt
+++ /dev/null
@@ -1,257 +0,0 @@
-               Linux Power Management Support
-This document briefly describes how to use power management with your
-Linux system and how to add power management support to Linux drivers.
-APM or ACPI?
------------
-If you have a relatively recent x86 mobile, desktop, or server system,
-odds are it supports either Advanced Power Management (APM) or
-Advanced Configuration and Power Interface (ACPI).  ACPI is the newer
-of the two technologies and puts power management in the hands of the
-operating system, allowing for more intelligent power management than
-is possible with BIOS controlled APM.
-The best way to determine which, if either, your system supports is to
-build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is
-enabled by default).  If a working ACPI implementation is found, the
-ACPI driver will override and disable APM, otherwise the APM driver
-will be used.
-No, sorry, you cannot have both ACPI and APM enabled and running at
-once.  Some people with broken ACPI or broken APM implementations
-would like to use both to get a full set of working features, but you
-simply cannot mix and match the two.  Only one power management
-interface can be in control of the machine at once.  Think about it..
-User-space Daemons
------------------
-Both APM and ACPI rely on user-space daemons, apmd and acpid
-respectively, to be completely functional.  Obtain both of these
-daemons from your Linux distribution or from the Internet (see below)
-and be sure that they are started sometime in the system boot process.
-Go ahead and start both.  If ACPI or APM is not available on your
-system the associated daemon will exit gracefully.
-  apmd:   http://worldvisions.ca/~apenwarr/apmd/
-  acpid:  http://acpid.sf.net/
-Driver Interface -- OBSOLETE, DO NOT USE!
----------------*************************
-Note: pm_register(), pm_access(), pm_dev_idle() and friends are
-obsolete. Please do not use them. Instead you should properly hook
-your driver into the driver model, and use its suspend()/resume()
-callbacks to do this kind of stuff.
-If you are writing a new driver or maintaining an old driver, it
-should include power management support.  Without power management
-support, a single driver may prevent a system with power management
-capabilities from ever being able to suspend (safely).
-Overview:
-1) Register each instance of a device with "pm_register"
-2) Call "pm_access" before accessing the hardware.
-   (this will ensure that the hardware is awake and ready)
-3) Your "pm_callback" is called before going into a
-   suspend state (ACPI D1-D3) or after resuming (ACPI D0)
-   from a suspend.
-4) Call "pm_dev_idle" when the device is not being used
-   (optional but will improve device idle detection)
-5) When unloaded, unregister the device with "pm_unregister"
-/*
- * Description: Register a device with the power-management subsystem
- *
- * Parameters:
- *   type - device type (PCI device, system device, ...)
- *   id - instance number or unique identifier
- *   cback - request handler callback (suspend, resume, ...)
- *
- * Returns: Registered PM device or NULL on error
- *
- * Examples:
- *   dev = pm_register(PM_SYS_DEV, PM_SYS_VGA, vga_callback);
- *
- *   struct pci_dev *pci_dev = pci_find_dev(...);
- *   dev = pm_register(PM_PCI_DEV, PM_PCI_ID(pci_dev), callback);
- */
-struct pm_dev *pm_register(pm_dev_t type, unsigned long id, pm_callback cback);
-/*
- * Description: Unregister a device with the power management subsystem
- *
- * Parameters:
- *   dev - PM device previously returned from pm_register
- */
-void pm_unregister(struct pm_dev *dev);
-/*
- * Description: Unregister all devices with a matching callback function
- *
- * Parameters:
- *   cback - previously registered request callback
- *
- * Notes: Provided for easier porting from old APM interface
- */
-void pm_unregister_all(pm_callback cback);
-/*
- * Power management request callback
- *
- * Parameters:
- *   dev - PM device previously returned from pm_register
- *   rqst - request type
- *   data - data, if any, associated with the request
- *
- * Returns: 0 if the request is successful
- *          EINVAL if the request is not supported
- *          EBUSY if the device is now busy and cannot handle the request
- *          ENOMEM if the device was unable to handle the request due to memory
- *
- * Details: The device request callback will be called before the
- *          device/system enters a suspend state (ACPI D1-D3) or
- *          or after the device/system resumes from suspend (ACPI D0).
- *          For PM_SUSPEND, the ACPI D-state being entered is passed
- *          as the "data" argument to the callback.  The device
- *          driver should save (PM_SUSPEND) or restore (PM_RESUME)
- *          device context when the request callback is called.
- *
- *          Once a driver returns 0 (success) from a suspend
- *          request, it should not process any further requests or
- *          access the device hardware until a call to "pm_access" is made.
- */
-typedef int (*pm_callback)(struct pm_dev *dev, pm_request_t rqst, void *data);
-Driver Details
--------------
-This is just a quick Q&A as a stopgap until a real driver writers'
-power management guide is available.
-Q: When is a device suspended?
-Devices can be suspended based on direct user request (eg. laptop lid
-closes), system power policy (eg.  sleep after 30 minutes of console
-inactivity), or device power policy (eg. power down device after 5
-minutes of inactivity)
-Q: Must a driver honor a suspend request?
-No, a driver can return -EBUSY from a suspend request and this
-will stop the system from suspending.  When a suspend request
-fails, all suspended devices are resumed and the system continues
-to run.  Suspend can be retried at a later time.
-Q: Can the driver block suspend/resume requests?
-Yes, a driver can delay its return from a suspend or resume
-request until the device is ready to handle requests.  It
-is advantageous to return as quickly as possible from a
-request as suspend/resume are done serially.
-Q: What context is a suspend/resume initiated from?
-A suspend or resume is initiated from a kernel thread context.
-It is safe to block, allocate memory, initiate requests
-or anything else you can do within the kernel.
-Q: Will requests continue to arrive after a suspend?
-Possibly.  It is the driver's responsibility to queue(*),
-fail, or drop any requests that arrive after returning
-success to a suspend request.  It is important that the
-driver not access its device until after it receives
-a resume request as the device's bus may no longer
-be active.
-(*) If a driver queues requests for processing after
-    resume be aware that the device, network, etc.
-    might be in a different state than at suspend time.
-    It's probably better to drop requests unless
-    the driver is a storage device.
-Q: Do I have to manage bus-specific power management registers
-No.  It is the responsibility of the bus driver to manage
-PCI, USB, etc. power management registers.  The bus driver
-or the power management subsystem will also enable any
-wake-on functionality that the device has.
-Q: So, really, what do I need to do to support suspend/resume?
-You need to save any device context that would
-be lost if the device was powered off and then restore
-it at resume time.  When ACPI is active, there are
-three levels of device suspend states; D1, D2, and D3.
-(The suspend state is passed as the "data" argument
-to the device callback.)  With D3, the device is powered
-off and loses all context, D1 and D2 are shallower power
-states and require less device context to be saved.  To
-play it safe, just save everything at suspend and restore
-everything at resume.
-Q: Where do I store device context for suspend?
-Anywhere in memory, kmalloc a buffer or store it
-in the device descriptor.  You are guaranteed that the
-contents of memory will be restored and accessible
-before resume, even when the system suspends to disk.
-Q: What do I need to do for ACPI vs. APM vs. etc?
-Drivers need not be aware of the specific power management
-technology that is active.  They just need to be aware
-of when the overlying power management system requests
-that they suspend or resume.
-Q: What about device dependencies?
-When a driver registers a device, the power management
-subsystem uses the information provided to build a
-tree of device dependencies (eg. USB device X is on
-USB controller Y which is on PCI bus Z)  When power
-management wants to suspend a device, it first sends
-a suspend request to its driver, then the bus driver,
-and so on up to the system bus.  Device resumes
-proceed in the opposite direction.
-Q: Who do I contact for additional information about
-   enabling power management for my specific driver/device?
-ACPI Development mailing list: linux-acpi@vger.kernel.org
-System Interface -- OBSOLETE, DO NOT USE!
----------------*************************
-If you are providing new power management support to Linux (ie.
-adding support for something like APM or ACPI), you should
-communicate with drivers through the existing generic power
-management interface.
-/*
- * Send a request to all devices
- *
- * Parameters:
- *   rqst - request type
- *   data - data, if any, associated with the request
- *
- * Returns: 0 if the request is successful
- *          See "pm_callback" return for errors
- *
- * Details: Walk list of registered devices and call pm_send
- *          for each until complete or an error is encountered.
- *          If an error is encountered for a suspend request,
- *          return all devices to the state they were in before
- *          the suspend request.
- */
-int pm_send_all(pm_request_t rqst, void *data);
-/*
- * Find a matching device
- *
- * Parameters:
- *   type - device type (PCI device, system device, or 0 to match all devices)
- *   from - previous match or NULL to start from the beginning
- *
- * Returns: Matching device or NULL if none found
- */
-struct pm_dev *pm_find(pm_dev_t type, struct pm_dev *from);
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 1d2a772506cf..928a79ceb7aa 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -58,6 +58,8 @@ Table of Contents
      o) Xilinx IP cores
      p) Freescale Synchronous Serial Interface
          q) USB EHCI controllers
+      r) MDIO on GPIOs
+      s) SPI busses
  VII - Marvell Discovery mv64[345]6x System Controller chips
    1) The /system-controller node
@@ -88,10 +90,12 @@ Table of Contents
    3) OpenPIC Interrupt Controllers
    4) ISA Interrupt Controllers
-  VIII - Specifying GPIO information for devices
+  IX - Specifying GPIO information for devices
    1) gpios property
    2) gpio-controller nodes
+  X - Specifying device power management information (sleep property)
  Appendix A - Sample SOC node for MPC8540
@@ -704,7 +708,7 @@ device or bus to be described by the device tree.
 In general, the format of an address for a device is defined by the
 parent bus type, based on the #address-cells and #size-cells
 properties.  Note that the parent's parent definitions of #address-cells
-and #size-cells are not inhereted so every node with children must specify
+and #size-cells are not inherited so every node with children must specify
 them.  The kernel requires the root node to have those properties defining
 addresses format for devices directly mapped on the processor bus.
@@ -1246,80 +1250,7 @@ descriptions for the SOC devices for which new nodes have been
 defined; this list will expand as more and more SOC-containing
 platforms are moved over to use the flattened-device-tree model.
-  a) MDIO IO device
+   a) PHY nodes
-  The MDIO is a bus to which the PHY devices are connected.  For each
-  device that exists on this bus, a child node should be created.  See
-  the definition of the PHY node below for an example of how to define
-  a PHY.
-  Required properties:
-    - reg : Offset and length of the register set for the device
-    - compatible : Should define the compatible device type for the
-      mdio.  Currently, this is most likely to be "fsl,gianfar-mdio"
-  Example:
-        mdio@24520 {
-                reg = <24520 20>;
-                compatible = "fsl,gianfar-mdio";
-                ethernet-phy@0 {
-                        ......
-                };
-        };
-  b) Gianfar-compatible ethernet nodes
-  Required properties:
-    - device_type : Should be "network"
-    - model : Model of the device.  Can be "TSEC", "eTSEC", or "FEC"
-    - compatible : Should be "gianfar"
-    - reg : Offset and length of the register set for the device
-    - mac-address : List of bytes representing the ethernet address of
-      this controller
-    - interrupts : <a b> where a is the interrupt number and b is a
-      field that represents an encoding of the sense and level
-      information for the interrupt.  This should be encoded based on
-      the information in section 2) depending on the type of interrupt
-      controller you have.
-    - interrupt-parent : the phandle for the interrupt controller that
-      services interrupts for this device.
-    - phy-handle : The phandle for the PHY connected to this ethernet
-      controller.
-    - fixed-link : <a b c d e> where a is emulated phy id - choose any,
-      but unique to the all specified fixed-links, b is duplex - 0 half,
-      1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
-      pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
-  Recommended properties:
-    - phy-connection-type : a string naming the controller/PHY interface type,
-      i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
-      "tbi", or "rtbi".  This property is only really needed if the connection
-      is of type "rgmii-id", as all other connection types are detected by
-      hardware.
-  Example:
-        ethernet@24000 {
-                #size-cells = <0>;
-                device_type = "network";
-                model = "TSEC";
-                compatible = "gianfar";
-                reg = <24000 1000>;
-                mac-address = [ 00 E0 0C 00 73 00 ];
-                interrupts = <d 3 e 3 12 3>;
-                interrupt-parent = <40000>;
-                phy-handle = <2452000>
-        };
-   c) PHY nodes
   Required properties:
@@ -1347,7 +1278,7 @@ platforms are moved over to use the flattened-device-tree model.
        };
-   d) Interrupt controllers
+   b) Interrupt controllers
   Some SOC devices contain interrupt controllers that are different
   from the standard Open PIC specification.  The SOC device nodes for
@@ -1360,491 +1291,14 @@ platforms are moved over to use the flattened-device-tree model.
        pic@40000 {
                linux,phandle = <40000>;
-                clock-frequency = <0>;
                interrupt-controller;
                #address-cells = <0>;
                reg = <40000 40000>;
-                built-in;
                compatible = "chrp,open-pic";
                device_type = "open-pic";
-                big-endian;
        };
+   c) CFI or JEDEC memory-mapped NOR flash
-   e) I2C
-   Required properties :
-    - device_type : Should be "i2c"
-    - reg : Offset and length of the register set for the device
-   Recommended properties :
-    - compatible : Should be "fsl-i2c" for parts compatible with
-      Freescale I2C specifications.
-    - interrupts : <a b> where a is the interrupt number and b is a
-      field that represents an encoding of the sense and level
-      information for the interrupt.  This should be encoded based on
-      the information in section 2) depending on the type of interrupt
-      controller you have.
-    - interrupt-parent : the phandle for the interrupt controller that
-      services interrupts for this device.
-    - dfsrr : boolean; if defined, indicates that this I2C device has
-      a digital filter sampling rate register
-    - fsl5200-clocking : boolean; if defined, indicated that this device
-      uses the FSL 5200 clocking mechanism.
-   Example :
-        i2c@3000 {
-                interrupt-parent = <40000>;
-                interrupts = <1b 3>;
-                reg = <3000 18>;
-                device_type = "i2c";
-                compatible  = "fsl-i2c";
-                dfsrr;
-        };
-   f) Freescale SOC USB controllers
-   The device node for a USB controller that is part of a Freescale
-   SOC is as described in the document "Open Firmware Recommended
-   Practice : Universal Serial Bus" with the following modifications
-   and additions :  
-   Required properties :
-    - compatible : Should be "fsl-usb2-mph" for multi port host USB
-      controllers, or "fsl-usb2-dr" for dual role USB controllers
-    - phy_type : For multi port host USB controllers, should be one of
-      "ulpi", or "serial". For dual role USB controllers, should be
-      one of "ulpi", "utmi", "utmi_wide", or "serial".
-    - reg : Offset and length of the register set for the device
-    - port0 : boolean; if defined, indicates port0 is connected for
-      fsl-usb2-mph compatible controllers.  Either this property or
-      "port1" (or both) must be defined for "fsl-usb2-mph" compatible 
-      controllers.
-    - port1 : boolean; if defined, indicates port1 is connected for
-      fsl-usb2-mph compatible controllers.  Either this property or
-      "port0" (or both) must be defined for "fsl-usb2-mph" compatible 
-      controllers.
-    - dr_mode : indicates the working mode for "fsl-usb2-dr" compatible
-      controllers.  Can be "host", "peripheral", or "otg".  Default to
-      "host" if not defined for backward compatibility.
-   Recommended properties :
-    - interrupts : <a b> where a is the interrupt number and b is a
-      field that represents an encoding of the sense and level
-      information for the interrupt.  This should be encoded based on
-      the information in section 2) depending on the type of interrupt
-      controller you have.
-    - interrupt-parent : the phandle for the interrupt controller that
-      services interrupts for this device.
-   Example multi port host USB controller device node :
-        usb@22000 {
-                compatible = "fsl-usb2-mph";
-                reg = <22000 1000>;
-                #address-cells = <1>;
-                #size-cells = <0>;
-                interrupt-parent = <700>;
-                interrupts = <27 1>;
-                phy_type = "ulpi";
-                port0;
-                port1;
-        };
-   Example dual role USB controller device node :
-        usb@23000 {
-                compatible = "fsl-usb2-dr";
-                reg = <23000 1000>;
-                #address-cells = <1>;
-                #size-cells = <0>;
-                interrupt-parent = <700>;
-                interrupts = <26 1>;
-                dr_mode = "otg";
-                phy = "ulpi";
-        };
-   g) Freescale SOC SEC Security Engines
-   Required properties:
-    - device_type : Should be "crypto"
-    - model : Model of the device.  Should be "SEC1" or "SEC2"
-    - compatible : Should be "talitos"
-    - reg : Offset and length of the register set for the device
-    - interrupts : <a b> where a is the interrupt number and b is a
-      field that represents an encoding of the sense and level
-      information for the interrupt.  This should be encoded based on
-      the information in section 2) depending on the type of interrupt
-      controller you have.
-    - interrupt-parent : the phandle for the interrupt controller that
-      services interrupts for this device.
-    - num-channels : An integer representing the number of channels
-      available.
-    - channel-fifo-len : An integer representing the number of
-      descriptor pointers each channel fetch fifo can hold.
-    - exec-units-mask : The bitmask representing what execution units
-      (EUs) are available. It's a single 32-bit cell. EU information
-      should be encoded following the SEC's Descriptor Header Dword
-      EU_SEL0 field documentation, i.e. as follows:
-        bit 0 = reserved - should be 0
-        bit 1 = set if SEC has the ARC4 EU (AFEU)
-        bit 2 = set if SEC has the DES/3DES EU (DEU)
-        bit 3 = set if SEC has the message digest EU (MDEU)
-        bit 4 = set if SEC has the random number generator EU (RNG)
-        bit 5 = set if SEC has the public key EU (PKEU)
-        bit 6 = set if SEC has the AES EU (AESU)
-        bit 7 = set if SEC has the Kasumi EU (KEU)
-      bits 8 through 31 are reserved for future SEC EUs.
-    - descriptor-types-mask : The bitmask representing what descriptors
-      are available. It's a single 32-bit cell. Descriptor type
-      information should be encoded following the SEC's Descriptor
-      Header Dword DESC_TYPE field documentation, i.e. as follows:
-        bit 0  = set if SEC supports the aesu_ctr_nonsnoop desc. type
-        bit 1  = set if SEC supports the ipsec_esp descriptor type
-        bit 2  = set if SEC supports the common_nonsnoop desc. type
-        bit 3  = set if SEC supports the 802.11i AES ccmp desc. type
-        bit 4  = set if SEC supports the hmac_snoop_no_afeu desc. type
-        bit 5  = set if SEC supports the srtp descriptor type
-        bit 6  = set if SEC supports the non_hmac_snoop_no_afeu desc.type
-        bit 7  = set if SEC supports the pkeu_assemble descriptor type
-        bit 8  = set if SEC supports the aesu_key_expand_output desc.type
-        bit 9  = set if SEC supports the pkeu_ptmul descriptor type
-        bit 10 = set if SEC supports the common_nonsnoop_afeu desc. type
-        bit 11 = set if SEC supports the pkeu_ptadd_dbl descriptor type
-      ..and so on and so forth.
-   Example:
-       /* MPC8548E */
-       crypto@30000 {
-               device_type = "crypto";
-               model = "SEC2";
-               compatible = "talitos";
-               reg = <30000 10000>;
-               interrupts = <1d 3>;
-               interrupt-parent = <40000>;
-               num-channels = <4>;
-               channel-fifo-len = <18>;
-               exec-units-mask = <000000fe>;
-               descriptor-types-mask = <012b0ebf>;
-       };
-   h) Board Control and Status (BCSR)
-   Required properties:
-    - device_type : Should be "board-control"
-    - reg : Offset and length of the register set for the device
-    Example:
-        bcsr@f8000000 {
-                device_type = "board-control";
-                reg = <f8000000 8000>;
-        };
-   i) Freescale QUICC Engine module (QE)
-   This represents qe module that is installed on PowerQUICC II Pro.
-   NOTE:  This is an interim binding; it should be updated to fit
-   in with the CPM binding later in this document.
-   Basically, it is a bus of devices, that could act more or less
-   as a complete entity (UCC, USB etc ). All of them should be siblings on
-   the "root" qe node, using the common properties from there.
-   The description below applies to the qe of MPC8360 and
-   more nodes and properties would be extended in the future.
-   i) Root QE device
-   Required properties:
-   - compatible : should be "fsl,qe";
-   - model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
-   - reg : offset and length of the device registers.
-   - bus-frequency : the clock frequency for QUICC Engine.
-   Recommended properties
-   - brg-frequency : the internal clock source frequency for baud-rate
-     generators in Hz.
-   Example:
-        qe@e0100000 {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                #interrupt-cells = <2>;
-                compatible = "fsl,qe";
-                ranges = <0 e0100000 00100000>;
-                reg = <e0100000 480>;
-                brg-frequency = <0>;
-                bus-frequency = <179A7B00>;
-        }
-   ii) SPI (Serial Peripheral Interface)
-   Required properties:
-   - cell-index : SPI controller index.
-   - compatible : should be "fsl,spi".
-   - mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
-   - reg : Offset and length of the register set for the device
-   - interrupts : <a b> where a is the interrupt number and b is a
-     field that represents an encoding of the sense and level
-     information for the interrupt.  This should be encoded based on
-     the information in section 2) depending on the type of interrupt
-     controller you have.
-   - interrupt-parent : the phandle for the interrupt controller that
-     services interrupts for this device.
-   Example:
-        spi@4c0 {
-                cell-index = <0>;
-                compatible = "fsl,spi";
-                reg = <4c0 40>;
-                interrupts = <82 0>;
-                interrupt-parent = <700>;
-                mode = "cpu";
-        };
-   iii) USB (Universal Serial Bus Controller)
-   Required properties:
-   - compatible : could be "qe_udc" or "fhci-hcd".
-   - mode : the could be "host" or "slave".
-   - reg : Offset and length of the register set for the device
-   - interrupts : <a b> where a is the interrupt number and b is a
-     field that represents an encoding of the sense and level
-     information for the interrupt.  This should be encoded based on
-     the information in section 2) depending on the type of interrupt
-     controller you have.
-   - interrupt-parent : the phandle for the interrupt controller that
-     services interrupts for this device.
-   Example(slave):
-        usb@6c0 {
-                compatible = "qe_udc";
-                reg = <6c0 40>;
-                interrupts = <8b 0>;
-                interrupt-parent = <700>;
-                mode = "slave";
-        };
-   iv) UCC (Unified Communications Controllers)
-   Required properties:
-   - device_type : should be "network", "hldc", "uart", "transparent"
-     "bisync", "atm", or "serial".
-   - compatible : could be "ucc_geth" or "fsl_atm" and so on.
-   - cell-index : the ucc number(1-8), corresponding to UCCx in UM.
-   - reg : Offset and length of the register set for the device
-   - interrupts : <a b> where a is the interrupt number and b is a
-     field that represents an encoding of the sense and level
-     information for the interrupt.  This should be encoded based on
-     the information in section 2) depending on the type of interrupt
-     controller you have.
-   - interrupt-parent : the phandle for the interrupt controller that
-     services interrupts for this device.
-   - pio-handle : The phandle for the Parallel I/O port configuration.
-   - port-number : for UART drivers, the port number to use, between 0 and 3.
-     This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
-     The port number is added to the minor number of the device.  Unlike the
-     CPM UART driver, the port-number is required for the QE UART driver.
-   - soft-uart : for UART drivers, if specified this means the QE UART device
-     driver should use "Soft-UART" mode, which is needed on some SOCs that have
-     broken UART hardware.  Soft-UART is provided via a microcode upload.
-   - rx-clock-name: the UCC receive clock source
-     "none": clock source is disabled
-     "brg1" through "brg16": clock source is BRG1-BRG16, respectively
-     "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-   - tx-clock-name: the UCC transmit clock source
-     "none": clock source is disabled
-     "brg1" through "brg16": clock source is BRG1-BRG16, respectively
-     "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-   The following two properties are deprecated.  rx-clock has been replaced
-   with rx-clock-name, and tx-clock has been replaced with tx-clock-name.
-   Drivers that currently use the deprecated properties should continue to
-   do so, in order to support older device trees, but they should be updated
-   to check for the new properties first.
-   - rx-clock : represents the UCC receive clock source.
-     0x00 : clock source is disabled;
-     0x1~0x10 : clock source is BRG1~BRG16 respectively;
-     0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
-   - tx-clock: represents the UCC transmit clock source;
-     0x00 : clock source is disabled;
-     0x1~0x10 : clock source is BRG1~BRG16 respectively;
-     0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
-   Required properties for network device_type:
-   - mac-address : list of bytes representing the ethernet address.
-   - phy-handle : The phandle for the PHY connected to this controller.
-   Recommended properties:
-   - phy-connection-type : a string naming the controller/PHY interface type,
-     i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id" (Internal
-     Delay), "rgmii-txid" (delay on TX only), "rgmii-rxid" (delay on RX only),
-     "tbi", or "rtbi".
-   Example:
-        ucc@2000 {
-                device_type = "network";
-                compatible = "ucc_geth";
-                cell-index = <1>;
-                reg = <2000 200>;
-                interrupts = <a0 0>;
-                interrupt-parent = <700>;
-                mac-address = [ 00 04 9f 00 23 23 ];
-                rx-clock = "none";
-                tx-clock = "clk9";
-                phy-handle = <212000>;
-                phy-connection-type = "gmii";
-                pio-handle = <140001>;
-        };
-   v) Parallel I/O Ports
-   This node configures Parallel I/O ports for CPUs with QE support.
-   The node should reside in the "soc" node of the tree.  For each
-   device that using parallel I/O ports, a child node should be created.
-   See the definition of the Pin configuration nodes below for more
-   information.
-   Required properties:
-   - device_type : should be "par_io".
-   - reg : offset to the register set and its length.
-   - num-ports : number of Parallel I/O ports
-   Example:
-        par_io@1400 {
-                reg = <1400 100>;
-                #address-cells = <1>;
-                #size-cells = <0>;
-                device_type = "par_io";
-                num-ports = <7>;
-                ucc_pin@01 {
-                        ......
-                };
-   vi) Pin configuration nodes
-   Required properties:
-   - linux,phandle : phandle of this node; likely referenced by a QE
-     device.
-   - pio-map : array of pin configurations.  Each pin is defined by 6
-     integers.  The six numbers are respectively: port, pin, dir,
-     open_drain, assignment, has_irq.
-     - port : port number of the pin; 0-6 represent port A-G in UM.
-     - pin : pin number in the port.
-     - dir : direction of the pin, should encode as follows:
-        0 = The pin is disabled
-        1 = The pin is an output
-        2 = The pin is an input
-        3 = The pin is I/O
-     - open_drain : indicates the pin is normal or wired-OR:
-        0 = The pin is actively driven as an output
-        1 = The pin is an open-drain driver. As an output, the pin is
-            driven active-low, otherwise it is three-stated.
-     - assignment : function number of the pin according to the Pin Assignment
-       tables in User Manual.  Each pin can have up to 4 possible functions in
-       QE and two options for CPM.
-     - has_irq : indicates if the pin is used as source of external
-       interrupts.
-   Example:
-        ucc_pin@01 {
-                linux,phandle = <140001>;
-                pio-map = <
-                /* port  pin  dir  open_drain  assignment  has_irq */
-                        0  3  1  0  1  0        /* TxD0 */
-                        0  4  1  0  1  0        /* TxD1 */
-                        0  5  1  0  1  0        /* TxD2 */
-                        0  6  1  0  1  0        /* TxD3 */
-                        1  6  1  0  3  0        /* TxD4 */
-                        1  7  1  0  1  0        /* TxD5 */
-                        1  9  1  0  2  0        /* TxD6 */
-                        1  a  1  0  2  0        /* TxD7 */
-                        0  9  2  0  1  0        /* RxD0 */
-                        0  a  2  0  1  0        /* RxD1 */
-                        0  b  2  0  1  0        /* RxD2 */
-                        0  c  2  0  1  0        /* RxD3 */
-                        0  d  2  0  1  0        /* RxD4 */
-                        1  1  2  0  2  0        /* RxD5 */
-                        1  0  2  0  2  0        /* RxD6 */
-                        1  4  2  0  2  0        /* RxD7 */
-                        0  7  1  0  1  0        /* TX_EN */
-                        0  8  1  0  1  0        /* TX_ER */
-                        0  f  2  0  1  0        /* RX_DV */
-                        0  10 2  0  1  0        /* RX_ER */
-                        0  0  2  0  1  0        /* RX_CLK */
-                        2  9  1  0  3  0        /* GTX_CLK - CLK10 */
-                        2  8  2  0  1  0>;      /* GTX125 - CLK9 */
-        };
-   vii) Multi-User RAM (MURAM)
-   Required properties:
-   - compatible : should be "fsl,qe-muram", "fsl,cpm-muram".
-   - mode : the could be "host" or "slave".
-   - ranges : Should be defined as specified in 1) to describe the
-      translation of MURAM addresses.
-   - data-only : sub-node which defines the address area under MURAM
-      bus that can be allocated as data/parameter
-   Example:
-        muram@10000 {
-                compatible = "fsl,qe-muram", "fsl,cpm-muram";
-                ranges = <0 00010000 0000c000>;
-                data-only@0{
-                        compatible = "fsl,qe-muram-data",
-                                     "fsl,cpm-muram-data";
-                        reg = <0 c000>;
-                };
-        };
-   viii) Uploaded QE firmware
-         If a new firwmare has been uploaded to the QE (usually by the
-         boot loader), then a 'firmware' child node should be added to the QE
-         node.  This node provides information on the uploaded firmware that
-         device drivers may need.
-         Required properties:
-         - id: The string name of the firmware.  This is taken from the 'id'
-               member of the qe_firmware structure of the uploaded firmware.
-               Device drivers can search this string to determine if the
-               firmware they want is already present.
-         - extended-modes: The Extended Modes bitfield, taken from the
-                           firmware binary.  It is a 64-bit number represented
-                           as an array of two 32-bit numbers.
-         - virtual-traps: The virtual traps, taken from the firmware binary.
-                          It is an array of 8 32-bit numbers.
-         Example:
-                firmware {
-                        id = "Soft-UART";
-                        extended-modes = <0 0>;
-                        virtual-traps = <0 0 0 0 0 0 0 0>;
-                }
-   j) CFI or JEDEC memory-mapped NOR flash
    Flash chips (Memory Technology Devices) are often used for solid state
    file systems on embedded devices.
@@ -1908,268 +1362,7 @@ platforms are moved over to use the flattened-device-tree model.
                };
        };
-   k) Global Utilities Block
+    d) 4xx/Axon EMAC ethernet nodes
-   The global utilities block controls power management, I/O device
-   enabling, power-on-reset configuration monitoring, general-purpose
-   I/O signal configuration, alternate function selection for multiplexed
-   signals, and clock control.
-   Required properties:
-    - compatible : Should define the compatible device type for
-      global-utilities.
-    - reg : Offset and length of the register set for the device.
-  Recommended properties:
-    - fsl,has-rstcr : Indicates that the global utilities register set
-      contains a functioning "reset control register" (i.e. the board
-      is wired to reset upon setting the HRESET_REQ bit in this register).
-    Example:
-        global-utilities@e0000 {        /* global utilities block */
-                compatible = "fsl,mpc8548-guts";
-                reg = <e0000 1000>;
-                fsl,has-rstcr;
-        };
-   l) Freescale Communications Processor Module
-   NOTE: This is an interim binding, and will likely change slightly,
-   as more devices are supported.  The QE bindings especially are
-   incomplete.
-   i) Root CPM node
-   Properties:
-   - compatible : "fsl,cpm1", "fsl,cpm2", or "fsl,qe".
-   - reg : A 48-byte region beginning with CPCR.
-   Example:
-        cpm@119c0 {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                #interrupt-cells = <2>;
-                compatible = "fsl,mpc8272-cpm", "fsl,cpm2";
-                reg = <119c0 30>;
-        }
-   ii) Properties common to mulitple CPM/QE devices
-   - fsl,cpm-command : This value is ORed with the opcode and command flag
-                       to specify the device on which a CPM command operates.
-   - fsl,cpm-brg : Indicates which baud rate generator the device
-                   is associated with.  If absent, an unused BRG
-                   should be dynamically allocated.  If zero, the
-                   device uses an external clock rather than a BRG.
-   - reg : Unless otherwise specified, the first resource represents the
-           scc/fcc/ucc registers, and the second represents the device's
-           parameter RAM region (if it has one).
-   iii) Serial
-   Currently defined compatibles:
-   - fsl,cpm1-smc-uart
-   - fsl,cpm2-smc-uart
-   - fsl,cpm1-scc-uart
-   - fsl,cpm2-scc-uart
-   - fsl,qe-uart
-   Example:
-        serial@11a00 {
-                device_type = "serial";
-                compatible = "fsl,mpc8272-scc-uart",
-                             "fsl,cpm2-scc-uart";
-                reg = <11a00 20 8000 100>;
-                interrupts = <28 8>;
-                interrupt-parent = <&PIC>;
-                fsl,cpm-brg = <1>;
-                fsl,cpm-command = <00800000>;
-        };
-   iii) Network
-   Currently defined compatibles:
-   - fsl,cpm1-scc-enet
-   - fsl,cpm2-scc-enet
-   - fsl,cpm1-fec-enet
-   - fsl,cpm2-fcc-enet (third resource is GFEMR)
-   - fsl,qe-enet
-   Example:
-        ethernet@11300 {
-                device_type = "network";
-                compatible = "fsl,mpc8272-fcc-enet",
-                             "fsl,cpm2-fcc-enet";
-                reg = <11300 20 8400 100 11390 1>;
-                local-mac-address = [ 00 00 00 00 00 00 ];
-                interrupts = <20 8>;
-                interrupt-parent = <&PIC>;
-                phy-handle = <&PHY0>;
-                fsl,cpm-command = <12000300>;
-        };
-   iv) MDIO
-   Currently defined compatibles:
-   fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
-   fsl,cpm2-mdio-bitbang (reg is port C registers)
-   Properties for fsl,cpm2-mdio-bitbang:
-   fsl,mdio-pin : pin of port C controlling mdio data
-   fsl,mdc-pin : pin of port C controlling mdio clock
-   Example:
-        mdio@10d40 {
-                device_type = "mdio";
-                compatible = "fsl,mpc8272ads-mdio-bitbang",
-                             "fsl,mpc8272-mdio-bitbang",
-                             "fsl,cpm2-mdio-bitbang";
-                reg = <10d40 14>;
-                #address-cells = <1>;
-                #size-cells = <0>;
-                fsl,mdio-pin = <12>;
-                fsl,mdc-pin = <13>;
-        };
-   v) Baud Rate Generators
-   Currently defined compatibles:
-   fsl,cpm-brg
-   fsl,cpm1-brg
-   fsl,cpm2-brg
-   Properties:
-   - reg : There may be an arbitrary number of reg resources; BRG
-     numbers are assigned to these in order.
-   - clock-frequency : Specifies the base frequency driving
-     the BRG.
-   Example:
-        brg@119f0 {
-                compatible = "fsl,mpc8272-brg",
-                             "fsl,cpm2-brg",
-                             "fsl,cpm-brg";
-                reg = <119f0 10 115f0 10>;
-                clock-frequency = <d#25000000>;
-        };
-   vi) Interrupt Controllers
-   Currently defined compatibles:
-   - fsl,cpm1-pic
-     - only one interrupt cell
-   - fsl,pq1-pic
-   - fsl,cpm2-pic
-     - second interrupt cell is level/sense:
-       - 2 is falling edge
-       - 8 is active low
-   Example:
-        interrupt-controller@10c00 {
-                #interrupt-cells = <2>;
-                interrupt-controller;
-                reg = <10c00 80>;
-                compatible = "mpc8272-pic", "fsl,cpm2-pic";
-        };
-   vii) USB (Universal Serial Bus Controller)
-   Properties:
-   - compatible : "fsl,cpm1-usb", "fsl,cpm2-usb", "fsl,qe-usb"
-   Example:
-        usb@11bc0 {
-                #address-cells = <1>;
-                #size-cells = <0>;
-                compatible = "fsl,cpm2-usb";
-                reg = <11b60 18 8b00 100>;
-                interrupts = <b 8>;
-                interrupt-parent = <&PIC>;
-                fsl,cpm-command = <2e600000>;
-        };
-   viii) Multi-User RAM (MURAM)
-   The multi-user/dual-ported RAM is expressed as a bus under the CPM node.
-   Ranges must be set up subject to the following restrictions:
-   - Children's reg nodes must be offsets from the start of all muram, even
-     if the user-data area does not begin at zero.
-   - If multiple range entries are used, the difference between the parent
-     address and the child address must be the same in all, so that a single
-     mapping can cover them all while maintaining the ability to determine
-     CPM-side offsets with pointer subtraction.  It is recommended that
-     multiple range entries not be used.
-   - A child address of zero must be translatable, even if no reg resources
-     contain it.
-   A child "data" node must exist, compatible with "fsl,cpm-muram-data", to
-   indicate the portion of muram that is usable by the OS for arbitrary
-   purposes.  The data node may have an arbitrary number of reg resources,
-   all of which contribute to the allocatable muram pool.
-   Example, based on mpc8272:
-        muram@0 {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges = <0 0 10000>;
-                data@0 {
-                        compatible = "fsl,cpm-muram-data";
-                        reg = <0 2000 9800 800>;
-                };
-        };
-   m) Chipselect/Local Bus
-   Properties:
-   - name : Should be localbus
-   - #address-cells : Should be either two or three.  The first cell is the
-                      chipselect number, and the remaining cells are the
-                      offset into the chipselect.
-   - #size-cells : Either one or two, depending on how large each chipselect
-                   can be.
-   - ranges : Each range corresponds to a single chipselect, and cover
-              the entire access window as configured.
-   Example:
-        localbus@f0010100 {
-                compatible = "fsl,mpc8272-localbus",
-                             "fsl,pq2-localbus";
-                #address-cells = <2>;
-                #size-cells = <1>;
-                reg = <f0010100 40>;
-                ranges = <0 0 fe000000 02000000
-                          1 0 f4500000 00008000>;
-                flash@0,0 {
-                        compatible = "jedec-flash";
-                        reg = <0 0 2000000>;
-                        bank-width = <4>;
-                        device-width = <1>;
-                };
-                board-control@1,0 {
-                        reg = <1 0 20>;
-                        compatible = "fsl,mpc8272ads-bcsr";
-                };
-        };
-    n) 4xx/Axon EMAC ethernet nodes
    The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
    the Axon bridge.  To operate this needs to interact with a ths
@@ -2317,7 +1510,7 @@ platforms are moved over to use the flattened-device-tree model.
                           available.
                           For Axon: 0x0000012a
-   o) Xilinx IP cores
+   e) Xilinx IP cores
   The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
   in Xilinx Spartan and Virtex FPGAs.  The devices cover the whole range
@@ -2584,7 +1777,7 @@ platforms are moved over to use the flattened-device-tree model.
      Xilinx uartlite devices are simple fixed speed serial ports.
-      Requred properties:
+      Required properties:
       - current-speed : Baud rate of uartlite
      v) Xilinx hwicap
@@ -2606,211 +1799,12 @@ platforms are moved over to use the flattened-device-tree model.
      Xilinx UART 16550 devices are very similar to the NS16550 but with
      different register spacing and an offset from the base address.
-      Requred properties:
+      Required properties:
       - clock-frequency : Frequency of the clock input
       - reg-offset : A value of 3 is required
       - reg-shift : A value of 2 is required
+    f) USB EHCI controllers
-    p) Freescale Synchronous Serial Interface
-       The SSI is a serial device that communicates with audio codecs.  It can
-       be programmed in AC97, I2S, left-justified, or right-justified modes.
-       Required properties:
-       - compatible       : compatible list, containing "fsl,ssi"
-       - cell-index       : the SSI, <0> = SSI1, <1> = SSI2, and so on
-       - reg              : offset and length of the register set for the device
-       - interrupts       : <a b> where a is the interrupt number and b is a
-                            field that represents an encoding of the sense and
-                            level information for the interrupt.  This should be
-                            encoded based on the information in section 2)
-                            depending on the type of interrupt controller you
-                            have.
-       - interrupt-parent : the phandle for the interrupt controller that
-                            services interrupts for this device.
-       - fsl,mode         : the operating mode for the SSI interface
-                            "i2s-slave" - I2S mode, SSI is clock slave
-                            "i2s-master" - I2S mode, SSI is clock master
-                            "lj-slave" - left-justified mode, SSI is clock slave
-                            "lj-master" - l.j. mode, SSI is clock master
-                            "rj-slave" - right-justified mode, SSI is clock slave
-                            "rj-master" - r.j., SSI is clock master
-                            "ac97-slave" - AC97 mode, SSI is clock slave
-                            "ac97-master" - AC97 mode, SSI is clock master
-       Optional properties:
-       - codec-handle     : phandle to a 'codec' node that defines an audio
-                            codec connected to this SSI.  This node is typically
-                            a child of an I2C or other control node.
-       Child 'codec' node required properties:
-       - compatible       : compatible list, contains the name of the codec
-       Child 'codec' node optional properties:
-       - clock-frequency  : The frequency of the input clock, which typically
-                            comes from an on-board dedicated oscillator.
-    * Freescale 83xx DMA Controller
-    Freescale PowerPC 83xx have on chip general purpose DMA controllers.
-    Required properties:
-    - compatible        : compatible list, contains 2 entries, first is
-                         "fsl,CHIP-dma", where CHIP is the processor
-                         (mpc8349, mpc8360, etc.) and the second is
-                         "fsl,elo-dma"
-    - reg               : <registers mapping for DMA general status reg>
-    - ranges            : Should be defined as specified in 1) to describe the
-                          DMA controller channels.
-    - cell-index        : controller index.  0 for controller @ 0x8100
-    - interrupts        : <interrupt mapping for DMA IRQ>
-    - interrupt-parent  : optional, if needed for interrupt mapping
-    - DMA channel nodes:
-            - compatible        : compatible list, contains 2 entries, first is
-                                 "fsl,CHIP-dma-channel", where CHIP is the processor
-                                 (mpc8349, mpc8350, etc.) and the second is
-                                 "fsl,elo-dma-channel"
-            - reg               : <registers mapping for channel>
-            - cell-index        : dma channel index starts at 0.
-    Optional properties:
-            - interrupts        : <interrupt mapping for DMA channel IRQ>
-                                  (on 83xx this is expected to be identical to
-                                   the interrupts property of the parent node)
-            - interrupt-parent  : optional, if needed for interrupt mapping
-  Example:
-        dma@82a8 {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
-                reg = <82a8 4>;
-                ranges = <0 8100 1a4>;
-                interrupt-parent = <&ipic>;
-                interrupts = <47 8>;
-                cell-index = <0>;
-                dma-channel@0 {
-                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
-                        cell-index = <0>;
-                        reg = <0 80>;
-                };
-                dma-channel@80 {
-                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
-                        cell-index = <1>;
-                        reg = <80 80>;
-                };
-                dma-channel@100 {
-                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
-                        cell-index = <2>;
-                        reg = <100 80>;
-                };
-                dma-channel@180 {
-                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
-                        cell-index = <3>;
-                        reg = <180 80>;
-                };
-        };
-   * Freescale 85xx/86xx DMA Controller
-    Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
-    Required properties:
-    - compatible        : compatible list, contains 2 entries, first is
-                         "fsl,CHIP-dma", where CHIP is the processor
-                         (mpc8540, mpc8540, etc.) and the second is
-                         "fsl,eloplus-dma"
-    - reg               : <registers mapping for DMA general status reg>
-    - cell-index        : controller index.  0 for controller @ 0x21000,
-                                             1 for controller @ 0xc000
-    - ranges            : Should be defined as specified in 1) to describe the
-                          DMA controller channels.
-    - DMA channel nodes:
-            - compatible        : compatible list, contains 2 entries, first is
-                                 "fsl,CHIP-dma-channel", where CHIP is the processor
-                                 (mpc8540, mpc8560, etc.) and the second is
-                                 "fsl,eloplus-dma-channel"
-            - cell-index        : dma channel index starts at 0.
-            - reg               : <registers mapping for channel>
-            - interrupts        : <interrupt mapping for DMA channel IRQ>
-            - interrupt-parent  : optional, if needed for interrupt mapping
-  Example:
-        dma@21300 {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
-                reg = <21300 4>;
-                ranges = <0 21100 200>;
-                cell-index = <0>;
-                dma-channel@0 {
-                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
-                        reg = <0 80>;
-                        cell-index = <0>;
-                        interrupt-parent = <&mpic>;
-                        interrupts = <14 2>;
-                };
-                dma-channel@80 {
-                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
-                        reg = <80 80>;
-                        cell-index = <1>;
-                        interrupt-parent = <&mpic>;
-                        interrupts = <15 2>;
-                };
-                dma-channel@100 {
-                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
-                        reg = <100 80>;
-                        cell-index = <2>;
-                        interrupt-parent = <&mpic>;
-                        interrupts = <16 2>;
-                };
-                dma-channel@180 {
-                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
-                        reg = <180 80>;
-                        cell-index = <3>;
-                        interrupt-parent = <&mpic>;
-                        interrupts = <17 2>;
-                };
-        };
-    * Freescale 8xxx/3.0 Gb/s SATA nodes
-    SATA nodes are defined to describe on-chip Serial ATA controllers.
-    Each SATA port should have its own node.
-    Required properties:
-    - compatible        : compatible list, contains 2 entries, first is
-                         "fsl,CHIP-sata", where CHIP is the processor
-                         (mpc8315, mpc8379, etc.) and the second is
-                         "fsl,pq-sata"
-    - interrupts        : <interrupt mapping for SATA IRQ>
-    - cell-index        : controller index.
-                              1 for controller @ 0x18000
-                              2 for controller @ 0x19000
-                              3 for controller @ 0x1a000
-                              4 for controller @ 0x1b000
-    Optional properties:
-    - interrupt-parent  : optional, if needed for interrupt mapping
-    - reg               : <registers mapping>
-   Example:
-        sata@18000 {
-                compatible = "fsl,mpc8379-sata", "fsl,pq-sata";
-                reg = <0x18000 0x1000>;
-                cell-index = <1>;
-                interrupts = <2c 8>;
-                interrupt-parent = < &ipic >;
-        };
-    q) USB EHCI controllers
    Required properties:
      - compatible : should be "usb-ehci".
@@ -2870,6 +1864,82 @@ platforms are moved over to use the flattened-device-tree model.
                reg = <0xe8000000 32>;
        };
+   r) MDIO on GPIOs
+   Currently defined compatibles:
+   - virtual,gpio-mdio
+   MDC and MDIO lines connected to GPIO controllers are listed in the
+   gpios property as described in section VIII.1 in the following order:
+   MDC, MDIO.
+   Example:
+        mdio {
+                compatible = "virtual,mdio-gpio";
+                #address-cells = <1>;
+                #size-cells = <0>;
+                gpios = <&qe_pio_a 11
+                         &qe_pio_c 6>;
+        };
+    s) SPI (Serial Peripheral Interface) busses
+    SPI busses can be described with a node for the SPI master device
+    and a set of child nodes for each SPI slave on the bus.  For this
+    discussion, it is assumed that the system's SPI controller is in
+    SPI master mode.  This binding does not describe SPI controllers
+    in slave mode.
+    The SPI master node requires the following properties:
+    - #address-cells  - number of cells required to define a chip select
+                        address on the SPI bus.
+    - #size-cells     - should be zero.
+    - compatible      - name of SPI bus controller following generic names
+                        recommended practice.
+    No other properties are required in the SPI bus node.  It is assumed
+    that a driver for an SPI bus device will understand that it is an SPI bus.
+    However, the binding does not attempt to define the specific method for
+    assigning chip select numbers.  Since SPI chip select configuration is
+    flexible and non-standardized, it is left out of this binding with the
+    assumption that board specific platform code will be used to manage
+    chip selects.  Individual drivers can define additional properties to
+    support describing the chip select layout.
+    SPI slave nodes must be children of the SPI master node and can
+    contain the following properties.
+    - reg             - (required) chip select address of device.
+    - compatible      - (required) name of SPI device following generic names
+                        recommended practice
+    - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
+    - spi-cpol        - (optional) Empty property indicating device requires
+                        inverse clock polarity (CPOL) mode
+    - spi-cpha        - (optional) Empty property indicating device requires
+                        shifted clock phase (CPHA) mode
+    SPI example for an MPC5200 SPI bus:
+                spi@f00 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
+                        reg = <0xf00 0x20>;
+                        interrupts = <2 13 0 2 14 0>;
+                        interrupt-parent = <&mpc5200_pic>;
+                        ethernet-switch@0 {
+                                compatible = "micrel,ks8995m";
+                                spi-max-frequency = <1000000>;
+                                reg = <0>;
+                        };
+                        codec@1 {
+                                compatible = "ti,tlv320aic26";
+                                spi-max-frequency = <100000>;
+                                reg = <1>;
+                        };
+                };
 VII - Marvell Discovery mv64[345]6x System Controller chips
 ===========================================================
@@ -2883,7 +1953,7 @@ prefixed with the string "marvell,", for Marvell Technology Group Ltd.
 1) The /system-controller node
  This node is used to represent the system-controller and must be
-  present when the system uses a system contller chip. The top-level
+  present when the system uses a system controller chip. The top-level
  system-controller node contains information that is global to all
  devices within the system controller chip. The node name begins
  with "system-controller" followed by the unit address, which is
@@ -3477,8 +2547,8 @@ encodings listed below:
        2 =  high to low edge sensitive type enabled
        3 =  low to high edge sensitive type enabled
-VIII - Specifying GPIO information for devices
+IX - Specifying GPIO information for devices
-==============================================
+============================================
 1) gpios property
 -----------------
@@ -3526,119 +2596,151 @@ Example of two SOC GPIO banks defined as gpio-controller nodes:
                gpio-controller;
        };
+X - Specifying Device Power Management Information (sleep property)
+===================================================================
+Devices on SOCs often have mechanisms for placing devices into low-power
+states that are decoupled from the devices' own register blocks.  Sometimes,
+this information is more complicated than a cell-index property can
+reasonably describe.  Thus, each device controlled in such a manner
+may contain a "sleep" property which describes these connections.
+The sleep property consists of one or more sleep resources, each of
+which consists of a phandle to a sleep controller, followed by a
+controller-specific sleep specifier of zero or more cells.
+The semantics of what type of low power modes are possible are defined
+by the sleep controller.  Some examples of the types of low power modes
+that may be supported are:
+ - Dynamic: The device may be disabled or enabled at any time.
+ - System Suspend: The device may request to be disabled or remain
+   awake during system suspend, but will not be disabled until then.
+ - Permanent: The device is disabled permanently (until the next hard
+   reset).
+Some devices may share a clock domain with each other, such that they should
+only be suspended when none of the devices are in use.  Where reasonable,
+such nodes should be placed on a virtual bus, where the bus has the sleep
+property.  If the clock domain is shared among devices that cannot be
+reasonably grouped in this manner, then create a virtual sleep controller
+(similar to an interrupt nexus, except that defining a standardized
+sleep-map should wait until its necessity is demonstrated).
 Appendix A - Sample SOC node for MPC8540
 ========================================
-Note that the #address-cells and #size-cells for the SoC node
+        soc@e0000000 {
-in this example have been explicitly listed; these are likely
-not necessary as they are usually the same as the root node.
-        soc8540@e0000000 {
                #address-cells = <1>;
                #size-cells = <1>;
-                #interrupt-cells = <2>;
+                compatible = "fsl,mpc8540-ccsr", "simple-bus";
                device_type = "soc";
-                ranges = <00000000 e0000000 00100000>
+                ranges = <0x00000000 0xe0000000 0x00100000>
-                reg = <e0000000 00003000>;
                bus-frequency = <0>;
+                interrupt-parent = <&pic>;
-                mdio@24520 {
-                        reg = <24520 20>;
-                        device_type = "mdio";
-                        compatible = "gianfar";
-                        ethernet-phy@0 {
-                                linux,phandle = <2452000>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <0>;
-                                device_type = "ethernet-phy";
-                        };
-                        ethernet-phy@1 {
-                                linux,phandle = <2452001>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <1>;
-                                device_type = "ethernet-phy";
-                        };
-                        ethernet-phy@3 {
-                                linux,phandle = <2452002>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <3>;
-                                device_type = "ethernet-phy";
-                        };
-                };
                ethernet@24000 {
-                        #size-cells = <0>;
+                        #address-cells = <1>;
+                        #size-cells = <1>;
                        device_type = "network";
                        model = "TSEC";
-                        compatible = "gianfar";
+                        compatible = "gianfar", "simple-bus";
-                        reg = <24000 1000>;
+                        reg = <0x24000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 00 ];
+                        local-mac-address = [ 00 E0 0C 00 73 00 ];
-                        interrupts = <d 3 e 3 12 3>;
+                        interrupts = <29 2 30 2 34 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy0>;
-                        phy-handle = <2452000>;
+                        sleep = <&pmc 00000080>;
+                        ranges;
+                        mdio@24520 {
+                                reg = <0x24520 0x20>;
+                                compatible = "fsl,gianfar-mdio";
+                                phy0: ethernet-phy@0 {
+                                        interrupts = <5 1>;
+                                        reg = <0>;
+                                        device_type = "ethernet-phy";
+                                };
+                                phy1: ethernet-phy@1 {
+                                        interrupts = <5 1>;
+                                        reg = <1>;
+                                        device_type = "ethernet-phy";
+                                };
+                                phy3: ethernet-phy@3 {
+                                        interrupts = <7 1>;
+                                        reg = <3>;
+                                        device_type = "ethernet-phy";
+                                };
+                        };
                };
                ethernet@25000 {
-                        #address-cells = <1>;
-                        #size-cells = <0>;
                        device_type = "network";
                        model = "TSEC";
                        compatible = "gianfar";
-                        reg = <25000 1000>;
+                        reg = <0x25000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 01 ];
+                        local-mac-address = [ 00 E0 0C 00 73 01 ];
-                        interrupts = <13 3 14 3 18 3>;
+                        interrupts = <13 2 14 2 18 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy1>;
-                        phy-handle = <2452001>;
+                        sleep = <&pmc 00000040>;
                };
                ethernet@26000 {
-                        #address-cells = <1>;
-                        #size-cells = <0>;
                        device_type = "network";
                        model = "FEC";
                        compatible = "gianfar";
-                        reg = <26000 1000>;
+                        reg = <0x26000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 02 ];
+                        local-mac-address = [ 00 E0 0C 00 73 02 ];
-                        interrupts = <19 3>;
+                        interrupts = <41 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy3>;
-                        phy-handle = <2452002>;
+                        sleep = <&pmc 00000020>;
                };
                serial@4500 {
-                        device_type = "serial";
+                        #address-cells = <1>;
-                        compatible = "ns16550";
+                        #size-cells = <1>;
-                        reg = <4500 100>;
+                        compatible = "fsl,mpc8540-duart", "simple-bus";
-                        clock-frequency = <0>;
+                        sleep = <&pmc 00000002>;
-                        interrupts = <1a 3>;
+                        ranges;
-                        interrupt-parent = <40000>;
+                        serial@4500 {
+                                device_type = "serial";
+                                compatible = "ns16550";
+                                reg = <0x4500 0x100>;
+                                clock-frequency = <0>;
+                                interrupts = <42 2>;
+                        };
+                        serial@4600 {
+                                device_type = "serial";
+                                compatible = "ns16550";
+                                reg = <0x4600 0x100>;
+                                clock-frequency = <0>;
+                                interrupts = <42 2>;
+                        };
                };
-                pic@40000 {
+                pic: pic@40000 {
-                        linux,phandle = <40000>;
-                        clock-frequency = <0>;
                        interrupt-controller;
                        #address-cells = <0>;
-                        reg = <40000 40000>;
+                        #interrupt-cells = <2>;
-                        built-in;
+                        reg = <0x40000 0x40000>;
                        compatible = "chrp,open-pic";
                        device_type = "open-pic";
-                        big-endian;
                };
                i2c@3000 {
-                        interrupt-parent = <40000>;
+                        interrupts = <43 2>;
-                        interrupts = <1b 3>;
+                        reg = <0x3000 0x100>;
-                        reg = <3000 18>;
-                        device_type = "i2c";
                        compatible  = "fsl-i2c";
                        dfsrr;
+                        sleep = <&pmc 00000004>;
                };
+                pmc: power@e0070 {
+                        compatible = "fsl,mpc8540-pmc", "fsl,mpc8548-pmc";
+                        reg = <0xe0070 0x20>;
+                };
        };
diff --git a/Documentation/powerpc/bootwrapper.txt b/Documentation/powerpc/bootwrapper.txt
new file mode 100644
index 000000000000..d60fced5e1cc
--- /dev/null
+++ b/Documentation/powerpc/bootwrapper.txt
@@ -0,0 +1,141 @@
+The PowerPC boot wrapper
+------------------------
+Copyright (C) Secret Lab Technologies Ltd.
+PowerPC image targets compresses and wraps the kernel image (vmlinux) with
+a boot wrapper to make it usable by the system firmware.  There is no
+standard PowerPC firmware interface, so the boot wrapper is designed to
+be adaptable for each kind of image that needs to be built.
+The boot wrapper can be found in the arch/powerpc/boot/ directory.  The
+Makefile in that directory has targets for all the available image types.
+The different image types are used to support all of the various firmware
+interfaces found on PowerPC platforms.  OpenFirmware is the most commonly
+used firmware type on general purpose PowerPC systems from Apple, IBM and
+others.  U-Boot is typically found on embedded PowerPC hardware, but there
+are a handful of other firmware implementations which are also popular.  Each
+firmware interface requires a different image format.
+The boot wrapper is built from the makefile in arch/powerpc/boot/Makefile and
+it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target
+image.  The details of the build system is discussed in the next section.
+Currently, the following image format targets exist:
+   cuImage.%:           Backwards compatible uImage for older version of
+                        U-Boot (for versions that don't understand the device
+                        tree).  This image embeds a device tree blob inside
+                        the image.  The boot wrapper, kernel and device tree
+                        are all embedded inside the U-Boot uImage file format
+                        with boot wrapper code that extracts data from the old
+                        bd_info structure and loads the data into the device
+                        tree before jumping into the kernel.
+                          Because of the series of #ifdefs found in the
+                        bd_info structure used in the old U-Boot interfaces,
+                        cuImages are platform specific.  Each specific
+                        U-Boot platform has a different platform init file
+                        which populates the embedded device tree with data
+                        from the platform specific bd_info file.  The platform
+                        specific cuImage platform init code can be found in
+                        arch/powerpc/boot/cuboot.*.c.  Selection of the correct
+                        cuImage init code for a specific board can be found in
+                        the wrapper structure.
+   dtbImage.%:          Similar to zImage, except device tree blob is embedded
+                        inside the image instead of provided by firmware.  The
+                        output image file can be either an elf file or a flat
+                        binary depending on the platform.
+                          dtbImages are used on systems which do not have an
+                        interface for passing a device tree directly.
+                        dtbImages are similar to simpleImages except that
+                        dtbImages have platform specific code for extracting
+                        data from the board firmware, but simpleImages do not
+                        talk to the firmware at all.
+                          PlayStation 3 support uses dtbImage.  So do Embedded
+                        Planet boards using the PlanetCore firmware.  Board
+                        specific initialization code is typically found in a
+                        file named arch/powerpc/boot/<platform>.c; but this
+                        can be overridden by the wrapper script.
+   simpleImage.%:       Firmware independent compressed image that does not
+                        depend on any particular firmware interface and embeds
+                        a device tree blob.  This image is a flat binary that
+                        can be loaded to any location in RAM and jumped to.
+                        Firmware cannot pass any configuration data to the
+                        kernel with this image type and it depends entirely on
+                        the embedded device tree for all information.
+                          The simpleImage is useful for booting systems with
+                        an unknown firmware interface or for booting from
+                        a debugger when no firmware is present (such as on
+                        the Xilinx Virtex platform).  The only assumption that
+                        simpleImage makes is that RAM is correctly initialized
+                        and that the MMU is either off or has RAM mapped to
+                        base address 0.
+                          simpleImage also supports inserting special platform
+                        specific initialization code to the start of the bootup
+                        sequence.  The virtex405 platform uses this feature to
+                        ensure that the cache is invalidated before caching
+                        is enabled.  Platform specific initialization code is
+                        added as part of the wrapper script and is keyed on
+                        the image target name.  For example, all
+                        simpleImage.virtex405-* targets will add the
+                        virtex405-head.S initialization code (This also means
+                        that the dts file for virtex405 targets should be
+                        named (virtex405-<board>.dts).  Search the wrapper
+                        script for 'virtex405' and see the file
+                        arch/powerpc/boot/virtex405-head.S for details.
+   treeImage.%;         Image format for used with OpenBIOS firmware found
+                        on some ppc4xx hardware.  This image embeds a device
+                        tree blob inside the image.
+   uImage:              Native image format used by U-Boot.  The uImage target
+                        does not add any boot code.  It just wraps a compressed
+                        vmlinux in the uImage data structure.  This image
+                        requires a version of U-Boot that is able to pass
+                        a device tree to the kernel at boot.  If using an older
+                        version of U-Boot, then you need to use a cuImage
+                        instead.
+   zImage.%:            Image format which does not embed a device tree.
+                        Used by OpenFirmware and other firmware interfaces
+                        which are able to supply a device tree.  This image
+                        expects firmware to provide the device tree at boot.
+                        Typically, if you have general purpose PowerPC
+                        hardware then you want this image format.
+Image types which embed a device tree blob (simpleImage, dtbImage, treeImage,
+and cuImage) all generate the device tree blob from a file in the
+arch/powerpc/boot/dts/ directory.  The Makefile selects the correct device
+tree source based on the name of the target.  Therefore, if the kernel is
+built with 'make treeImage.walnut simpleImage.virtex405-ml403', then the
+build system will use arch/powerpc/boot/dts/walnut.dts to build
+treeImage.walnut and arch/powerpc/boot/dts/virtex405-ml403.dts to build
+the simpleImage.virtex405-ml403.
+Two special targets called 'zImage' and 'zImage.initrd' also exist.  These
+targets build all the default images as selected by the kernel configuration.
+Default images are selected by the boot wrapper Makefile
+(arch/powerpc/boot/Makefile) by adding targets to the $image-y variable.  Look
+at the Makefile to see which default image targets are available.
+How it is built
+---------------
+arch/powerpc is designed to support multiplatform kernels, which means
+that a single vmlinux image can be booted on many different target boards.
+It also means that the boot wrapper must be able to wrap for many kinds of
+images on a single build.  The design decision was made to not use any
+conditional compilation code (#ifdef, etc) in the boot wrapper source code.
+All of the boot wrapper pieces are buildable at any time regardless of the
+kernel configuration.  Building all the wrapper bits on every kernel build
+also ensures that obscure parts of the wrapper are at the very least compile
+tested in a large variety of environments.
+The wrapper is adapted for different image types at link time by linking in
+just the wrapper bits that are appropriate for the image type.  The 'wrapper
+script' (found in arch/powerpc/boot/wrapper) is called by the Makefile and
+is responsible for selecting the correct wrapper bits for the image type.
+The arguments are well documented in the script's comment block, so they
+are not repeated here.  However, it is worth mentioning that the script
+uses the -p (platform) argument as the main method of deciding which wrapper
+bits to compile in.  Look for the large 'case "$platform" in' block in the
+middle of the script.  This is also the place where platform specific fixups
+can be selected by changing the link order.
+In particular, care should be taken when working with cuImages.  cuImage
+wrapper bits are very board specific and care should be taken to make sure
+the target you are trying to build is supported by the wrapper bits.
diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt
new file mode 100644
index 000000000000..74ae6f1cd2d6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/board.txt
@@ -0,0 +1,29 @@
+* Board Control and Status (BCSR)
+Required properties:
+ - device_type : Should be "board-control"
+ - reg : Offset and length of the register set for the device
+Example:
+        bcsr@f8000000 {
+                device_type = "board-control";
+                reg = <f8000000 8000>;
+        };
+* Freescale on board FPGA
+This is the memory-mapped registers for on board FPGA.
+Required properities:
+- compatible : should be "fsl,fpga-pixis".
+- reg : should contain the address and the lenght of the FPPGA register
+  set.
+Example (MPC8610HPCD):
+        board-control@e8000000 {
+                compatible = "fsl,fpga-pixis";
+                reg = <0xe8000000 32>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt
new file mode 100644
index 000000000000..088fc471e03a
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt
@@ -0,0 +1,67 @@
+* Freescale Communications Processor Module
+NOTE: This is an interim binding, and will likely change slightly,
+as more devices are supported.  The QE bindings especially are
+incomplete.
+* Root CPM node
+Properties:
+- compatible : "fsl,cpm1", "fsl,cpm2", or "fsl,qe".
+- reg : A 48-byte region beginning with CPCR.
+Example:
+     cpm@119c0 {
+        #address-cells = <1>;
+        #size-cells = <1>;
+        #interrupt-cells = <2>;
+        compatible = "fsl,mpc8272-cpm", "fsl,cpm2";
+        reg = <119c0 30>;
+     }
+* Properties common to mulitple CPM/QE devices
+- fsl,cpm-command : This value is ORed with the opcode and command flag
+                    to specify the device on which a CPM command operates.
+- fsl,cpm-brg : Indicates which baud rate generator the device
+                is associated with.  If absent, an unused BRG
+                should be dynamically allocated.  If zero, the
+                device uses an external clock rather than a BRG.
+- reg : Unless otherwise specified, the first resource represents the
+        scc/fcc/ucc registers, and the second represents the device's
+        parameter RAM region (if it has one).
+* Multi-User RAM (MURAM)
+The multi-user/dual-ported RAM is expressed as a bus under the CPM node.
+Ranges must be set up subject to the following restrictions:
+- Children's reg nodes must be offsets from the start of all muram, even
+  if the user-data area does not begin at zero.
+- If multiple range entries are used, the difference between the parent
+  address and the child address must be the same in all, so that a single
+  mapping can cover them all while maintaining the ability to determine
+  CPM-side offsets with pointer subtraction.  It is recommended that
+  multiple range entries not be used.
+- A child address of zero must be translatable, even if no reg resources
+  contain it.
+A child "data" node must exist, compatible with "fsl,cpm-muram-data", to
+indicate the portion of muram that is usable by the OS for arbitrary
+purposes.  The data node may have an arbitrary number of reg resources,
+all of which contribute to the allocatable muram pool.
+Example, based on mpc8272:
+        muram@0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                ranges = <0 0 10000>;
+                data@0 {
+                        compatible = "fsl,cpm-muram-data";
+                        reg = <0 2000 9800 800>;
+                };
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt
new file mode 100644
index 000000000000..4c7d45eaf025
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt
@@ -0,0 +1,21 @@
+* Baud Rate Generators
+Currently defined compatibles:
+fsl,cpm-brg
+fsl,cpm1-brg
+fsl,cpm2-brg
+Properties:
+- reg : There may be an arbitrary number of reg resources; BRG
+  numbers are assigned to these in order.
+- clock-frequency : Specifies the base frequency driving
+  the BRG.
+Example:
+        brg@119f0 {
+                compatible = "fsl,mpc8272-brg",
+                             "fsl,cpm2-brg",
+                             "fsl,cpm-brg";
+                reg = <119f0 10 115f0 10>;
+                clock-frequency = <d#25000000>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt
new file mode 100644
index 000000000000..87bc6048667e
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt
@@ -0,0 +1,41 @@
+* I2C
+The I2C controller is expressed as a bus under the CPM node.
+Properties:
+- compatible : "fsl,cpm1-i2c", "fsl,cpm2-i2c"
+- reg : On CPM2 devices, the second resource doesn't specify the I2C
+  Parameter RAM itself, but the I2C_BASE field of the CPM2 Parameter RAM
+  (typically 0x8afc 0x2).
+- #address-cells : Should be one. The cell is the i2c device address with
+  the r/w bit set to zero.
+- #size-cells : Should be zero.
+- clock-frequency : Can be used to set the i2c clock frequency. If
+  unspecified, a default frequency of 60kHz is being used.
+The following two properties are deprecated. They are only used by legacy
+i2c drivers to find the bus to probe:
+- linux,i2c-index : Can be used to hard code an i2c bus number. By default,
+  the bus number is dynamically assigned by the i2c core.
+- linux,i2c-class : Can be used to override the i2c class. The class is used
+  by legacy i2c device drivers to find a bus in a specific context like
+  system management, video or sound. By default, I2C_CLASS_HWMON (1) is
+  being used. The definition of the classes can be found in
+  include/i2c/i2c.h
+Example, based on mpc823:
+        i2c@860 {
+                compatible = "fsl,mpc823-i2c",
+                             "fsl,cpm1-i2c";
+                reg = <0x860 0x20 0x3c80 0x30>;
+                interrupts = <16>;
+                interrupt-parent = <&CPM_PIC>;
+                fsl,cpm-command = <0x10>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                rtc@68 {
+                        compatible = "dallas,ds1307";
+                        reg = <0x68>;
+                };
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt
new file mode 100644
index 000000000000..8e3ee1681618
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt
@@ -0,0 +1,18 @@
+* Interrupt Controllers
+Currently defined compatibles:
+- fsl,cpm1-pic
+  - only one interrupt cell
+- fsl,pq1-pic
+- fsl,cpm2-pic
+  - second interrupt cell is level/sense:
+    - 2 is falling edge
+    - 8 is active low
+Example:
+        interrupt-controller@10c00 {
+                #interrupt-cells = <2>;
+                interrupt-controller;
+                reg = <10c00 80>;
+                compatible = "mpc8272-pic", "fsl,cpm2-pic";
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt
new file mode 100644
index 000000000000..74bfda4bb824
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt
@@ -0,0 +1,15 @@
+* USB (Universal Serial Bus Controller)
+Properties:
+- compatible : "fsl,cpm1-usb", "fsl,cpm2-usb", "fsl,qe-usb"
+Example:
+        usb@11bc0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "fsl,cpm2-usb";
+                reg = <11b60 18 8b00 100>;
+                interrupts = <b 8>;
+                interrupt-parent = <&PIC>;
+                fsl,cpm-command = <2e600000>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
new file mode 100644
index 000000000000..1815dfede1bc
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
@@ -0,0 +1,38 @@
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+On CPM1 devices, all ports are using slightly different register layouts.
+Ports A, C and D are 16bit ports and Ports B and E are 32bit ports.
+On CPM2 devices, all ports are 32bit ports and use a common register layout.
+Required properties:
+- compatible : "fsl,cpm1-pario-bank-a", "fsl,cpm1-pario-bank-b",
+  "fsl,cpm1-pario-bank-c", "fsl,cpm1-pario-bank-d",
+  "fsl,cpm1-pario-bank-e", "fsl,cpm2-pario-bank"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional paramters (currently unused).
+- gpio-controller : Marks the port as GPIO controller.
+Example of three SOC GPIO banks defined as gpio-controller nodes:
+        CPM1_PIO_A: gpio-controller@950 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-a";
+                reg = <0x950 0x10>;
+                gpio-controller;
+        };
+        CPM1_PIO_B: gpio-controller@ab8 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-b";
+                reg = <0xab8 0x10>;
+                gpio-controller;
+        };
+        CPM1_PIO_E: gpio-controller@ac8 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-e";
+                reg = <0xac8 0x18>;
+                gpio-controller;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt
new file mode 100644
index 000000000000..0e4269446580
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt
@@ -0,0 +1,45 @@
+* Network
+Currently defined compatibles:
+- fsl,cpm1-scc-enet
+- fsl,cpm2-scc-enet
+- fsl,cpm1-fec-enet
+- fsl,cpm2-fcc-enet (third resource is GFEMR)
+- fsl,qe-enet
+Example:
+        ethernet@11300 {
+                device_type = "network";
+                compatible = "fsl,mpc8272-fcc-enet",
+                             "fsl,cpm2-fcc-enet";
+                reg = <11300 20 8400 100 11390 1>;
+                local-mac-address = [ 00 00 00 00 00 00 ];
+                interrupts = <20 8>;
+                interrupt-parent = <&PIC>;
+                phy-handle = <&PHY0>;
+                fsl,cpm-command = <12000300>;
+        };
+* MDIO
+Currently defined compatibles:
+fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
+fsl,cpm2-mdio-bitbang (reg is port C registers)
+Properties for fsl,cpm2-mdio-bitbang:
+fsl,mdio-pin : pin of port C controlling mdio data
+fsl,mdc-pin : pin of port C controlling mdio clock
+Example:
+        mdio@10d40 {
+                device_type = "mdio";
+                compatible = "fsl,mpc8272ads-mdio-bitbang",
+                             "fsl,mpc8272-mdio-bitbang",
+                             "fsl,cpm2-mdio-bitbang";
+                reg = <10d40 14>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                fsl,mdio-pin = <12>;
+                fsl,mdc-pin = <13>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
new file mode 100644
index 000000000000..78790d58dc2c
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
@@ -0,0 +1,58 @@
+* Freescale QUICC Engine module (QE)
+This represents qe module that is installed on PowerQUICC II Pro.
+NOTE:  This is an interim binding; it should be updated to fit
+in with the CPM binding later in this document.
+Basically, it is a bus of devices, that could act more or less
+as a complete entity (UCC, USB etc ). All of them should be siblings on
+the "root" qe node, using the common properties from there.
+The description below applies to the qe of MPC8360 and
+more nodes and properties would be extended in the future.
+i) Root QE device
+Required properties:
+- compatible : should be "fsl,qe";
+- model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
+- reg : offset and length of the device registers.
+- bus-frequency : the clock frequency for QUICC Engine.
+Recommended properties
+- brg-frequency : the internal clock source frequency for baud-rate
+  generators in Hz.
+Example:
+     qe@e0100000 {
+        #address-cells = <1>;
+        #size-cells = <1>;
+        #interrupt-cells = <2>;
+        compatible = "fsl,qe";
+        ranges = <0 e0100000 00100000>;
+        reg = <e0100000 480>;
+        brg-frequency = <0>;
+        bus-frequency = <179A7B00>;
+     }
+* Multi-User RAM (MURAM)
+Required properties:
+- compatible : should be "fsl,qe-muram", "fsl,cpm-muram".
+- mode : the could be "host" or "slave".
+- ranges : Should be defined as specified in 1) to describe the
+   translation of MURAM addresses.
+- data-only : sub-node which defines the address area under MURAM
+   bus that can be allocated as data/parameter
+Example:
+     muram@10000 {
+        compatible = "fsl,qe-muram", "fsl,cpm-muram";
+        ranges = <0 00010000 0000c000>;
+        data-only@0{
+                compatible = "fsl,qe-muram-data",
+                             "fsl,cpm-muram-data";
+                reg = <0 c000>;
+        };
+     };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt
new file mode 100644
index 000000000000..6c238f59b2a9
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt
@@ -0,0 +1,24 @@
+* Uploaded QE firmware
+      If a new firwmare has been uploaded to the QE (usually by the
+      boot loader), then a 'firmware' child node should be added to the QE
+      node.  This node provides information on the uploaded firmware that
+      device drivers may need.
+      Required properties:
+      - id: The string name of the firmware.  This is taken from the 'id'
+            member of the qe_firmware structure of the uploaded firmware.
+            Device drivers can search this string to determine if the
+            firmware they want is already present.
+      - extended-modes: The Extended Modes bitfield, taken from the
+                   firmware binary.  It is a 64-bit number represented
+                   as an array of two 32-bit numbers.
+      - virtual-traps: The virtual traps, taken from the firmware binary.
+                  It is an array of 8 32-bit numbers.
+Example:
+        firmware {
+                id = "Soft-UART";
+                extended-modes = <0 0>;
+                virtual-traps = <0 0 0 0 0 0 0 0>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt
new file mode 100644
index 000000000000..60984260207b
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt
@@ -0,0 +1,51 @@
+* Parallel I/O Ports
+This node configures Parallel I/O ports for CPUs with QE support.
+The node should reside in the "soc" node of the tree.  For each
+device that using parallel I/O ports, a child node should be created.
+See the definition of the Pin configuration nodes below for more
+information.
+Required properties:
+- device_type : should be "par_io".
+- reg : offset to the register set and its length.
+- num-ports : number of Parallel I/O ports
+Example:
+par_io@1400 {
+        reg = <1400 100>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        device_type = "par_io";
+        num-ports = <7>;
+        ucc_pin@01 {
+                ......
+        };
+Note that "par_io" nodes are obsolete, and should not be used for
+the new device trees. Instead, each Par I/O bank should be represented
+via its own gpio-controller node:
+Required properties:
+- #gpio-cells : should be "2".
+- compatible : should be "fsl,<chip>-qe-pario-bank",
+  "fsl,mpc8323-qe-pario-bank".
+- reg : offset to the register set and its length.
+- gpio-controller : node to identify gpio controllers.
+Example:
+        qe_pio_a: gpio-controller@1400 {
+                #gpio-cells = <2>;
+                compatible = "fsl,mpc8360-qe-pario-bank",
+                "fsl,mpc8323-qe-pario-bank";
+                reg = <0x1400 0x18>;
+                gpio-controller;
+          };
+        qe_pio_e: gpio-controller@1460 {
+                #gpio-cells = <2>;
+                compatible = "fsl,mpc8360-qe-pario-bank",
+                             "fsl,mpc8323-qe-pario-bank";
+                reg = <0x1460 0x18>;
+                gpio-controller;
+          };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt
new file mode 100644
index 000000000000..c5b43061db3a
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt
@@ -0,0 +1,60 @@
+* Pin configuration nodes
+Required properties:
+- linux,phandle : phandle of this node; likely referenced by a QE
+  device.
+- pio-map : array of pin configurations.  Each pin is defined by 6
+  integers.  The six numbers are respectively: port, pin, dir,
+  open_drain, assignment, has_irq.
+  - port : port number of the pin; 0-6 represent port A-G in UM.
+  - pin : pin number in the port.
+  - dir : direction of the pin, should encode as follows:
+     0 = The pin is disabled
+     1 = The pin is an output
+     2 = The pin is an input
+     3 = The pin is I/O
+  - open_drain : indicates the pin is normal or wired-OR:
+     0 = The pin is actively driven as an output
+     1 = The pin is an open-drain driver. As an output, the pin is
+         driven active-low, otherwise it is three-stated.
+  - assignment : function number of the pin according to the Pin Assignment
+    tables in User Manual.  Each pin can have up to 4 possible functions in
+    QE and two options for CPM.
+  - has_irq : indicates if the pin is used as source of external
+    interrupts.
+Example:
+     ucc_pin@01 {
+        linux,phandle = <140001>;
+        pio-map = <
+        /* port  pin  dir  open_drain  assignment  has_irq */
+                0  3  1  0  1  0        /* TxD0 */
+                0  4  1  0  1  0        /* TxD1 */
+                0  5  1  0  1  0        /* TxD2 */
+                0  6  1  0  1  0        /* TxD3 */
+                1  6  1  0  3  0        /* TxD4 */
+                1  7  1  0  1  0        /* TxD5 */
+                1  9  1  0  2  0        /* TxD6 */
+                1  a  1  0  2  0        /* TxD7 */
+                0  9  2  0  1  0        /* RxD0 */
+                0  a  2  0  1  0        /* RxD1 */
+                0  b  2  0  1  0        /* RxD2 */
+                0  c  2  0  1  0        /* RxD3 */
+                0  d  2  0  1  0        /* RxD4 */
+                1  1  2  0  2  0        /* RxD5 */
+                1  0  2  0  2  0        /* RxD6 */
+                1  4  2  0  2  0        /* RxD7 */
+                0  7  1  0  1  0        /* TX_EN */
+                0  8  1  0  1  0        /* TX_ER */
+                0  f  2  0  1  0        /* RX_DV */
+                0  10 2  0  1  0        /* RX_ER */
+                0  0  2  0  1  0        /* RX_CLK */
+                2  9  1  0  3  0        /* GTX_CLK - CLK10 */
+                2  8  2  0  1  0>;      /* GTX125 - CLK9 */
+     };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt
new file mode 100644
index 000000000000..e47734bee3f0
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt
@@ -0,0 +1,70 @@
+* UCC (Unified Communications Controllers)
+Required properties:
+- device_type : should be "network", "hldc", "uart", "transparent"
+  "bisync", "atm", or "serial".
+- compatible : could be "ucc_geth" or "fsl_atm" and so on.
+- cell-index : the ucc number(1-8), corresponding to UCCx in UM.
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+  field that represents an encoding of the sense and level
+  information for the interrupt.  This should be encoded based on
+  the information in section 2) depending on the type of interrupt
+  controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+  services interrupts for this device.
+- pio-handle : The phandle for the Parallel I/O port configuration.
+- port-number : for UART drivers, the port number to use, between 0 and 3.
+  This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
+  The port number is added to the minor number of the device.  Unlike the
+  CPM UART driver, the port-number is required for the QE UART driver.
+- soft-uart : for UART drivers, if specified this means the QE UART device
+  driver should use "Soft-UART" mode, which is needed on some SOCs that have
+  broken UART hardware.  Soft-UART is provided via a microcode upload.
+- rx-clock-name: the UCC receive clock source
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- tx-clock-name: the UCC transmit clock source
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+The following two properties are deprecated.  rx-clock has been replaced
+with rx-clock-name, and tx-clock has been replaced with tx-clock-name.
+Drivers that currently use the deprecated properties should continue to
+do so, in order to support older device trees, but they should be updated
+to check for the new properties first.
+- rx-clock : represents the UCC receive clock source.
+  0x00 : clock source is disabled;
+  0x1~0x10 : clock source is BRG1~BRG16 respectively;
+  0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+- tx-clock: represents the UCC transmit clock source;
+  0x00 : clock source is disabled;
+  0x1~0x10 : clock source is BRG1~BRG16 respectively;
+  0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+Required properties for network device_type:
+- mac-address : list of bytes representing the ethernet address.
+- phy-handle : The phandle for the PHY connected to this controller.
+Recommended properties:
+- phy-connection-type : a string naming the controller/PHY interface type,
+  i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id" (Internal
+  Delay), "rgmii-txid" (delay on TX only), "rgmii-rxid" (delay on RX only),
+  "tbi", or "rtbi".
+Example:
+        ucc@2000 {
+                device_type = "network";
+                compatible = "ucc_geth";
+                cell-index = <1>;
+                reg = <2000 200>;
+                interrupts = <a0 0>;
+                interrupt-parent = <700>;
+                mac-address = [ 00 04 9f 00 23 23 ];
+                rx-clock = "none";
+                tx-clock = "clk9";
+                phy-handle = <212000>;
+                phy-connection-type = "gmii";
+                pio-handle = <140001>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt
new file mode 100644
index 000000000000..9ccd5f30405b
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt
@@ -0,0 +1,37 @@
+Freescale QUICC Engine USB Controller
+Required properties:
+- compatible : should be "fsl,<chip>-qe-usb", "fsl,mpc8323-qe-usb".
+- reg : the first two cells should contain usb registers location and
+  length, the next two two cells should contain PRAM location and
+  length.
+- interrupts : should contain USB interrupt.
+- interrupt-parent : interrupt source phandle.
+- fsl,fullspeed-clock : specifies the full speed USB clock source:
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- fsl,lowspeed-clock : specifies the low speed USB clock source:
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- hub-power-budget : USB power budget for the root hub, in mA.
+- gpios : should specify GPIOs in this order: USBOE, USBTP, USBTN, USBRP,
+  USBRN, SPEED (optional), and POWER (optional).
+Example:
+usb@6c0 {
+        compatible = "fsl,mpc8360-qe-usb", "fsl,mpc8323-qe-usb";
+        reg = <0x6c0 0x40 0x8b00 0x100>;
+        interrupts = <11>;
+        interrupt-parent = <&qeic>;
+        fsl,fullspeed-clock = "clk21";
+        gpios = <&qe_pio_b  2 0 /* USBOE */
+                 &qe_pio_b  3 0 /* USBTP */
+                 &qe_pio_b  8 0 /* USBTN */
+                 &qe_pio_b  9 0 /* USBRP */
+                 &qe_pio_b 11 0 /* USBRN */
+                 &qe_pio_e 20 0 /* SPEED */
+                 &qe_pio_e 21 0 /* POWER */>;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt
new file mode 100644
index 000000000000..b35f3482e3e4
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt
@@ -0,0 +1,21 @@
+* Serial
+Currently defined compatibles:
+- fsl,cpm1-smc-uart
+- fsl,cpm2-smc-uart
+- fsl,cpm1-scc-uart
+- fsl,cpm2-scc-uart
+- fsl,qe-uart
+Example:
+        serial@11a00 {
+                device_type = "serial";
+                compatible = "fsl,mpc8272-scc-uart",
+                             "fsl,cpm2-scc-uart";
+                reg = <11a00 20 8000 100>;
+                interrupts = <28 8>;
+                interrupt-parent = <&PIC>;
+                fsl,cpm-brg = <1>;
+                fsl,cpm-command = <00800000>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/diu.txt b/Documentation/powerpc/dts-bindings/fsl/diu.txt
new file mode 100644
index 000000000000..deb35de70988
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/diu.txt
@@ -0,0 +1,18 @@
+* Freescale Display Interface Unit
+The Freescale DIU is a LCD controller, with proper hardware, it can also
+drive DVI monitors.
+Required properties:
+- compatible : should be "fsl-diu".
+- reg : should contain at least address and length of the DIU register
+  set.
+- Interrupts : one DIU interrupt should be describe here.
+Example (MPC8610HPCD):
+        display@2c000 {
+                compatible = "fsl,diu";
+                reg = <0x2c000 100>;
+                interrupts = <72 2>;
+                interrupt-parent = <&mpic>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
new file mode 100644
index 000000000000..86826df00e64
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -0,0 +1,127 @@
+* Freescale 83xx DMA Controller
+Freescale PowerPC 83xx have on chip general purpose DMA controllers.
+Required properties:
+- compatible        : compatible list, contains 2 entries, first is
+                 "fsl,CHIP-dma", where CHIP is the processor
+                 (mpc8349, mpc8360, etc.) and the second is
+                 "fsl,elo-dma"
+- reg               : <registers mapping for DMA general status reg>
+- ranges                : Should be defined as specified in 1) to describe the
+                  DMA controller channels.
+- cell-index        : controller index.  0 for controller @ 0x8100
+- interrupts        : <interrupt mapping for DMA IRQ>
+- interrupt-parent  : optional, if needed for interrupt mapping
+- DMA channel nodes:
+        - compatible        : compatible list, contains 2 entries, first is
+                         "fsl,CHIP-dma-channel", where CHIP is the processor
+                         (mpc8349, mpc8350, etc.) and the second is
+                         "fsl,elo-dma-channel"
+        - reg               : <registers mapping for channel>
+        - cell-index        : dma channel index starts at 0.
+Optional properties:
+        - interrupts        : <interrupt mapping for DMA channel IRQ>
+                          (on 83xx this is expected to be identical to
+                           the interrupts property of the parent node)
+        - interrupt-parent  : optional, if needed for interrupt mapping
+Example:
+        dma@82a8 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
+                reg = <82a8 4>;
+                ranges = <0 8100 1a4>;
+                interrupt-parent = <&ipic>;
+                interrupts = <47 8>;
+                cell-index = <0>;
+                dma-channel@0 {
+                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+                        cell-index = <0>;
+                        reg = <0 80>;
+                };
+                dma-channel@80 {
+                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+                        cell-index = <1>;
+                        reg = <80 80>;
+                };
+                dma-channel@100 {
+                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+                        cell-index = <2>;
+                        reg = <100 80>;
+                };
+                dma-channel@180 {
+                        compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+                        cell-index = <3>;
+                        reg = <180 80>;
+                };
+        };
+* Freescale 85xx/86xx DMA Controller
+Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
+Required properties:
+- compatible        : compatible list, contains 2 entries, first is
+                 "fsl,CHIP-dma", where CHIP is the processor
+                 (mpc8540, mpc8540, etc.) and the second is
+                 "fsl,eloplus-dma"
+- reg               : <registers mapping for DMA general status reg>
+- cell-index        : controller index.  0 for controller @ 0x21000,
+                                         1 for controller @ 0xc000
+- ranges                : Should be defined as specified in 1) to describe the
+                  DMA controller channels.
+- DMA channel nodes:
+        - compatible        : compatible list, contains 2 entries, first is
+                         "fsl,CHIP-dma-channel", where CHIP is the processor
+                         (mpc8540, mpc8560, etc.) and the second is
+                         "fsl,eloplus-dma-channel"
+        - cell-index        : dma channel index starts at 0.
+        - reg               : <registers mapping for channel>
+        - interrupts        : <interrupt mapping for DMA channel IRQ>
+        - interrupt-parent  : optional, if needed for interrupt mapping
+Example:
+        dma@21300 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
+                reg = <21300 4>;
+                ranges = <0 21100 200>;
+                cell-index = <0>;
+                dma-channel@0 {
+                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+                        reg = <0 80>;
+                        cell-index = <0>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <14 2>;
+                };
+                dma-channel@80 {
+                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+                        reg = <80 80>;
+                        cell-index = <1>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <15 2>;
+                };
+                dma-channel@100 {
+                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+                        reg = <100 80>;
+                        cell-index = <2>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <16 2>;
+                };
+                dma-channel@180 {
+                        compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+                        reg = <180 80>;
+                        cell-index = <3>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <17 2>;
+                };
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/gtm.txt b/Documentation/powerpc/dts-bindings/fsl/gtm.txt
new file mode 100644
index 000000000000..9a33efded4bc
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/gtm.txt
@@ -0,0 +1,31 @@
+* Freescale General-purpose Timers Module
+Required properties:
+  - compatible : should be
+    "fsl,<chip>-gtm", "fsl,gtm" for SOC GTMs
+    "fsl,<chip>-qe-gtm", "fsl,qe-gtm", "fsl,gtm" for QE GTMs
+    "fsl,<chip>-cpm2-gtm", "fsl,cpm2-gtm", "fsl,gtm" for CPM2 GTMs
+  - reg : should contain gtm registers location and length (0x40).
+  - interrupts : should contain four interrupts.
+  - interrupt-parent : interrupt source phandle.
+  - clock-frequency : specifies the frequency driving the timer.
+Example:
+timer@500 {
+        compatible = "fsl,mpc8360-gtm", "fsl,gtm";
+        reg = <0x500 0x40>;
+        interrupts = <90 8 78 8 84 8 72 8>;
+        interrupt-parent = <&ipic>;
+        /* filled by u-boot */
+        clock-frequency = <0>;
+};
+timer@440 {
+        compatible = "fsl,mpc8360-qe-gtm", "fsl,qe-gtm", "fsl,gtm";
+        reg = <0x440 0x40>;
+        interrupts = <12 13 14 15>;
+        interrupt-parent = <&qeic>;
+        /* filled by u-boot */
+        clock-frequency = <0>;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/guts.txt b/Documentation/powerpc/dts-bindings/fsl/guts.txt
new file mode 100644
index 000000000000..9e7a2417dac5
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/guts.txt
@@ -0,0 +1,25 @@
+* Global Utilities Block
+The global utilities block controls power management, I/O device
+enabling, power-on-reset configuration monitoring, general-purpose
+I/O signal configuration, alternate function selection for multiplexed
+signals, and clock control.
+Required properties:
+ - compatible : Should define the compatible device type for
+   global-utilities.
+ - reg : Offset and length of the register set for the device.
+Recommended properties:
+ - fsl,has-rstcr : Indicates that the global utilities register set
+   contains a functioning "reset control register" (i.e. the board
+   is wired to reset upon setting the HRESET_REQ bit in this register).
+Example:
+        global-utilities@e0000 {        /* global utilities block */
+                compatible = "fsl,mpc8548-guts";
+                reg = <e0000 1000>;
+                fsl,has-rstcr;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
new file mode 100644
index 000000000000..d0ab33e21fe6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
@@ -0,0 +1,32 @@
+* I2C
+Required properties :
+ - device_type : Should be "i2c"
+ - reg : Offset and length of the register set for the device
+Recommended properties :
+ - compatible : Should be "fsl-i2c" for parts compatible with
+   Freescale I2C specifications.
+ - interrupts : <a b> where a is the interrupt number and b is a
+   field that represents an encoding of the sense and level
+   information for the interrupt.  This should be encoded based on
+   the information in section 2) depending on the type of interrupt
+   controller you have.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+ - dfsrr : boolean; if defined, indicates that this I2C device has
+   a digital filter sampling rate register
+ - fsl5200-clocking : boolean; if defined, indicated that this device
+   uses the FSL 5200 clocking mechanism.
+Example :
+        i2c@3000 {
+                interrupt-parent = <40000>;
+                interrupts = <1b 3>;
+                reg = <3000 18>;
+                device_type = "i2c";
+                compatible  = "fsl-i2c";
+                dfsrr;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/lbc.txt b/Documentation/powerpc/dts-bindings/fsl/lbc.txt
new file mode 100644
index 000000000000..3300fec501c5
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/lbc.txt
@@ -0,0 +1,35 @@
+* Chipselect/Local Bus
+Properties:
+- name : Should be localbus
+- #address-cells : Should be either two or three.  The first cell is the
+                   chipselect number, and the remaining cells are the
+                   offset into the chipselect.
+- #size-cells : Either one or two, depending on how large each chipselect
+                can be.
+- ranges : Each range corresponds to a single chipselect, and cover
+           the entire access window as configured.
+Example:
+        localbus@f0010100 {
+                compatible = "fsl,mpc8272-localbus",
+                           "fsl,pq2-localbus";
+                #address-cells = <2>;
+                #size-cells = <1>;
+                reg = <f0010100 40>;
+                ranges = <0 0 fe000000 02000000
+                          1 0 f4500000 00008000>;
+                flash@0,0 {
+                        compatible = "jedec-flash";
+                        reg = <0 0 2000000>;
+                        bank-width = <4>;
+                        device-width = <1>;
+                };
+                board-control@1,0 {
+                        reg = <1 0 20>;
+                        compatible = "fsl,mpc8272ads-bcsr";
+                };
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt b/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt
new file mode 100644
index 000000000000..0f766333b6eb
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt
@@ -0,0 +1,17 @@
+Freescale MPC8349E-mITX-compatible Power Management Micro Controller Unit (MCU)
+Required properties:
+- compatible : "fsl,<mcu-chip>-<board>", "fsl,mcu-mpc8349emitx".
+- reg : should specify I2C address (0x0a).
+- #gpio-cells : should be 2.
+- gpio-controller : should be present.
+Example:
+mcu@0a {
+        #gpio-cells = <2>;
+        compatible = "fsl,mc9s08qg8-mpc8349emitx",
+                     "fsl,mcu-mpc8349emitx";
+        reg = <0x0a>;
+        gpio-controller;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt b/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt
new file mode 100644
index 000000000000..b26b91992c55
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt
@@ -0,0 +1,36 @@
+* Freescale MSI interrupt controller
+Reguired properities:
+- compatible : compatible list, contains 2 entries,
+  first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
+  etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" depending on
+  the parent type.
+- reg : should contain the address and the length of the shared message
+  interrupt register set.
+- msi-available-ranges: use <start count> style section to define which
+  msi interrupt can be used in the 256 msi interrupts. This property is
+  optional, without this, all the 256 MSI interrupts can be used.
+- interrupts : each one of the interrupts here is one entry per 32 MSIs,
+  and routed to the host interrupt controller. the interrupts should
+  be set as edge sensitive.
+- interrupt-parent: the phandle for the interrupt controller
+  that services interrupts for this device. for 83xx cpu, the interrupts
+  are routed to IPIC, and for 85xx/86xx cpu the interrupts are routed
+  to MPIC.
+Example:
+        msi@41600 {
+                compatible = "fsl,mpc8610-msi", "fsl,mpic-msi";
+                reg = <0x41600 0x80>;
+                msi-available-ranges = <0 0x100>;
+                interrupts = <
+                        0xe0 0
+                        0xe1 0
+                        0xe2 0
+                        0xe3 0
+                        0xe4 0
+                        0xe5 0
+                        0xe6 0
+                        0xe7 0>;
+                interrupt-parent = <&mpic>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/pmc.txt b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
new file mode 100644
index 000000000000..02f6f43ee1b7
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
@@ -0,0 +1,63 @@
+* Power Management Controller
+Properties:
+- compatible: "fsl,<chip>-pmc".
+  "fsl,mpc8349-pmc" should be listed for any chip whose PMC is
+  compatible.  "fsl,mpc8313-pmc" should also be listed for any chip
+  whose PMC is compatible, and implies deep-sleep capability.
+  "fsl,mpc8548-pmc" should be listed for any chip whose PMC is
+  compatible.  "fsl,mpc8536-pmc" should also be listed for any chip
+  whose PMC is compatible, and implies deep-sleep capability.
+  "fsl,mpc8641d-pmc" should be listed for any chip whose PMC is
+  compatible; all statements below that apply to "fsl,mpc8548-pmc" also
+  apply to "fsl,mpc8641d-pmc".
+  Compatibility does not include bit assigments in SCCR/PMCDR/DEVDISR; these
+  bit assigments are indicated via the sleep specifier in each device's
+  sleep property.
+- reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
+  is the PMC block, and the second resource is the Clock Configuration
+  block.
+  For devices compatible with "fsl,mpc8548-pmc", the first resource
+  is a 32-byte block beginning with DEVDISR.
+- interrupts: For "fsl,mpc8349-pmc"-compatible devices, the first
+  resource is the PMC block interrupt.
+- fsl,mpc8313-wakeup-timer: For "fsl,mpc8313-pmc"-compatible devices,
+  this is a phandle to an "fsl,gtm" node on which timer 4 can be used as
+  a wakeup source from deep sleep.
+Sleep specifiers:
+  fsl,mpc8349-pmc: Sleep specifiers consist of one cell.  For each bit
+  that is set in the cell, the corresponding bit in SCCR will be saved
+  and cleared on suspend, and restored on resume.  This sleep controller
+  supports disabling and resuming devices at any time.
+  fsl,mpc8536-pmc: Sleep specifiers consist of three cells, the third of
+  which will be ORed into PMCDR upon suspend, and cleared from PMCDR
+  upon resume.  The first two cells are as described for fsl,mpc8578-pmc.
+  This sleep controller only supports disabling devices during system
+  sleep, or permanently.
+  fsl,mpc8548-pmc: Sleep specifiers consist of one or two cells, the
+  first of which will be ORed into DEVDISR (and the second into
+  DEVDISR2, if present -- this cell should be zero or absent if the
+  hardware does not have DEVDISR2) upon a request for permanent device
+  disabling.  This sleep controller does not support configuring devices
+  to disable during system sleep (unless supported by another compatible
+  match), or dynamically.
+Example:
+        power@b00 {
+                compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
+                reg = <0xb00 0x100 0xa00 0x100>;
+                interrupts = <80 8>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/sata.txt b/Documentation/powerpc/dts-bindings/fsl/sata.txt
new file mode 100644
index 000000000000..b46bcf46c3d8
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/sata.txt
@@ -0,0 +1,29 @@
+* Freescale 8xxx/3.0 Gb/s SATA nodes
+SATA nodes are defined to describe on-chip Serial ATA controllers.
+Each SATA port should have its own node.
+Required properties:
+- compatible        : compatible list, contains 2 entries, first is
+                 "fsl,CHIP-sata", where CHIP is the processor
+                 (mpc8315, mpc8379, etc.) and the second is
+                 "fsl,pq-sata"
+- interrupts        : <interrupt mapping for SATA IRQ>
+- cell-index        : controller index.
+                          1 for controller @ 0x18000
+                          2 for controller @ 0x19000
+                          3 for controller @ 0x1a000
+                          4 for controller @ 0x1b000
+Optional properties:
+- interrupt-parent  : optional, if needed for interrupt mapping
+- reg               : <registers mapping>
+Example:
+        sata@18000 {
+                compatible = "fsl,mpc8379-sata", "fsl,pq-sata";
+                reg = <0x18000 0x1000>;
+                cell-index = <1>;
+                interrupts = <2c 8>;
+                interrupt-parent = < &ipic >;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/sec.txt b/Documentation/powerpc/dts-bindings/fsl/sec.txt
new file mode 100644
index 000000000000..2b6f2d45c45a
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/sec.txt
@@ -0,0 +1,68 @@
+Freescale SoC SEC Security Engines
+Required properties:
+- compatible : Should contain entries for this and backward compatible
+  SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0"
+- reg : Offset and length of the register set for the device
+- interrupts : the SEC's interrupt number
+- fsl,num-channels : An integer representing the number of channels
+  available.
+- fsl,channel-fifo-len : An integer representing the number of
+  descriptor pointers each channel fetch fifo can hold.
+- fsl,exec-units-mask : The bitmask representing what execution units
+  (EUs) are available. It's a single 32-bit cell. EU information
+  should be encoded following the SEC's Descriptor Header Dword
+  EU_SEL0 field documentation, i.e. as follows:
+        bit 0  = reserved - should be 0
+        bit 1  = set if SEC has the ARC4 EU (AFEU)
+        bit 2  = set if SEC has the DES/3DES EU (DEU)
+        bit 3  = set if SEC has the message digest EU (MDEU/MDEU-A)
+        bit 4  = set if SEC has the random number generator EU (RNG)
+        bit 5  = set if SEC has the public key EU (PKEU)
+        bit 6  = set if SEC has the AES EU (AESU)
+        bit 7  = set if SEC has the Kasumi EU (KEU)
+        bit 8  = set if SEC has the CRC EU (CRCU)
+        bit 11 = set if SEC has the message digest EU extended alg set (MDEU-B)
+remaining bits are reserved for future SEC EUs.
+- fsl,descriptor-types-mask : The bitmask representing what descriptors
+  are available. It's a single 32-bit cell. Descriptor type information
+  should be encoded following the SEC's Descriptor Header Dword DESC_TYPE
+  field documentation, i.e. as follows:
+        bit 0  = set if SEC supports the aesu_ctr_nonsnoop desc. type
+        bit 1  = set if SEC supports the ipsec_esp descriptor type
+        bit 2  = set if SEC supports the common_nonsnoop desc. type
+        bit 3  = set if SEC supports the 802.11i AES ccmp desc. type
+        bit 4  = set if SEC supports the hmac_snoop_no_afeu desc. type
+        bit 5  = set if SEC supports the srtp descriptor type
+        bit 6  = set if SEC supports the non_hmac_snoop_no_afeu desc.type
+        bit 7  = set if SEC supports the pkeu_assemble descriptor type
+        bit 8  = set if SEC supports the aesu_key_expand_output desc.type
+        bit 9  = set if SEC supports the pkeu_ptmul descriptor type
+        bit 10 = set if SEC supports the common_nonsnoop_afeu desc. type
+        bit 11 = set if SEC supports the pkeu_ptadd_dbl descriptor type
+  ..and so on and so forth.
+Optional properties:
+- interrupt-parent : the phandle for the interrupt controller that
+  services interrupts for this device.
+Example:
+        /* MPC8548E */
+        crypto@30000 {
+                compatible = "fsl,sec2.1", "fsl,sec2.0";
+                reg = <0x30000 0x10000>;
+                interrupts = <29 2>;
+                interrupt-parent = <&mpic>;
+                fsl,num-channels = <4>;
+                fsl,channel-fifo-len = <24>;
+                fsl,exec-units-mask = <0xfe>;
+                fsl,descriptor-types-mask = <0x12b0ebf>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
new file mode 100644
index 000000000000..e7d9a344c4f4
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -0,0 +1,24 @@
+* SPI (Serial Peripheral Interface)
+Required properties:
+- cell-index : SPI controller index.
+- compatible : should be "fsl,spi".
+- mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+  field that represents an encoding of the sense and level
+  information for the interrupt.  This should be encoded based on
+  the information in section 2) depending on the type of interrupt
+  controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+  services interrupts for this device.
+Example:
+        spi@4c0 {
+                cell-index = <0>;
+                compatible = "fsl,spi";
+                reg = <4c0 40>;
+                interrupts = <82 0>;
+                interrupt-parent = <700>;
+                mode = "cpu";
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/ssi.txt b/Documentation/powerpc/dts-bindings/fsl/ssi.txt
new file mode 100644
index 000000000000..d100555d488a
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/ssi.txt
@@ -0,0 +1,38 @@
+Freescale Synchronous Serial Interface
+The SSI is a serial device that communicates with audio codecs.  It can
+be programmed in AC97, I2S, left-justified, or right-justified modes.
+Required properties:
+- compatible      : compatible list, containing "fsl,ssi"
+- cell-index      : the SSI, <0> = SSI1, <1> = SSI2, and so on
+- reg             : offset and length of the register set for the device
+- interrupts      : <a b> where a is the interrupt number and b is a
+                     field that represents an encoding of the sense and
+                    level information for the interrupt.  This should be
+                    encoded based on the information in section 2)
+                    depending on the type of interrupt controller you
+                    have.
+- interrupt-parent : the phandle for the interrupt controller that
+                     services interrupts for this device.
+- fsl,mode        : the operating mode for the SSI interface
+                    "i2s-slave" - I2S mode, SSI is clock slave
+                    "i2s-master" - I2S mode, SSI is clock master
+                    "lj-slave" - left-justified mode, SSI is clock slave
+                    "lj-master" - l.j. mode, SSI is clock master
+                    "rj-slave" - right-justified mode, SSI is clock slave
+                    "rj-master" - r.j., SSI is clock master
+                    "ac97-slave" - AC97 mode, SSI is clock slave
+                    "ac97-master" - AC97 mode, SSI is clock master
+Optional properties:
+- codec-handle    : phandle to a 'codec' node that defines an audio
+                    codec connected to this SSI.  This node is typically
+                    a child of an I2C or other control node.
+Child 'codec' node required properties:
+- compatible      : compatible list, contains the name of the codec
+Child 'codec' node optional properties:
+- clock-frequency  : The frequency of the input clock, which typically
+                     comes from an on-board dedicated oscillator.
diff --git a/Documentation/powerpc/dts-bindings/fsl/tsec.txt b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
new file mode 100644
index 000000000000..cf55fa4112d2
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
@@ -0,0 +1,62 @@
+* MDIO IO device
+The MDIO is a bus to which the PHY devices are connected.  For each
+device that exists on this bus, a child node should be created.  See
+the definition of the PHY node below for an example of how to define
+a PHY.
+Required properties:
+  - reg : Offset and length of the register set for the device
+  - compatible : Should define the compatible device type for the
+    mdio.  Currently, this is most likely to be "fsl,gianfar-mdio"
+Example:
+        mdio@24520 {
+                reg = <24520 20>;
+                compatible = "fsl,gianfar-mdio";
+                ethernet-phy@0 {
+                        ......
+                };
+        };
+* Gianfar-compatible ethernet nodes
+Properties:
+  - device_type : Should be "network"
+  - model : Model of the device.  Can be "TSEC", "eTSEC", or "FEC"
+  - compatible : Should be "gianfar"
+  - reg : Offset and length of the register set for the device
+  - local-mac-address : List of bytes representing the ethernet address of
+    this controller
+  - interrupts : For FEC devices, the first interrupt is the device's
+    interrupt.  For TSEC and eTSEC devices, the first interrupt is
+    transmit, the second is receive, and the third is error.
+  - phy-handle : The phandle for the PHY connected to this ethernet
+    controller.
+  - fixed-link : <a b c d e> where a is emulated phy id - choose any,
+    but unique to the all specified fixed-links, b is duplex - 0 half,
+    1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
+    pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
+  - phy-connection-type : a string naming the controller/PHY interface type,
+    i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
+    "tbi", or "rtbi".  This property is only really needed if the connection
+    is of type "rgmii-id", as all other connection types are detected by
+    hardware.
+  - fsl,magic-packet : If present, indicates that the hardware supports
+    waking up via magic packet.
+Example:
+        ethernet@24000 {
+                device_type = "network";
+                model = "TSEC";
+                compatible = "gianfar";
+                reg = <0x24000 0x1000>;
+                local-mac-address = [ 00 E0 0C 00 73 00 ];
+                interrupts = <29 2 30 2 34 2>;
+                interrupt-parent = <&mpic>;
+                phy-handle = <&phy0>
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
new file mode 100644
index 000000000000..84a04d5eb8e6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
@@ -0,0 +1,28 @@
+Freescale Localbus UPM programmed to work with NAND flash
+Required properties:
+- compatible : "fsl,upm-nand".
+- reg : should specify localbus chip select and size used for the chip.
+- fsl,upm-addr-offset : UPM pattern offset for the address latch.
+- fsl,upm-cmd-offset : UPM pattern offset for the command latch.
+- gpios : may specify optional GPIO connected to the Ready-Not-Busy pin.
+Example:
+upm@1,0 {
+        compatible = "fsl,upm-nand";
+        reg = <1 0 1>;
+        fsl,upm-addr-offset = <16>;
+        fsl,upm-cmd-offset = <8>;
+        gpios = <&qe_pio_e 18 0>;
+        flash {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "...";
+                partition@0 {
+                        ...
+                };
+        };
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/usb.txt b/Documentation/powerpc/dts-bindings/fsl/usb.txt
new file mode 100644
index 000000000000..b00152402694
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/usb.txt
@@ -0,0 +1,59 @@
+Freescale SOC USB controllers
+The device node for a USB controller that is part of a Freescale
+SOC is as described in the document "Open Firmware Recommended
+Practice : Universal Serial Bus" with the following modifications
+and additions :
+Required properties :
+ - compatible : Should be "fsl-usb2-mph" for multi port host USB
+   controllers, or "fsl-usb2-dr" for dual role USB controllers
+ - phy_type : For multi port host USB controllers, should be one of
+   "ulpi", or "serial". For dual role USB controllers, should be
+   one of "ulpi", "utmi", "utmi_wide", or "serial".
+ - reg : Offset and length of the register set for the device
+ - port0 : boolean; if defined, indicates port0 is connected for
+   fsl-usb2-mph compatible controllers.  Either this property or
+   "port1" (or both) must be defined for "fsl-usb2-mph" compatible
+   controllers.
+ - port1 : boolean; if defined, indicates port1 is connected for
+   fsl-usb2-mph compatible controllers.  Either this property or
+   "port0" (or both) must be defined for "fsl-usb2-mph" compatible
+   controllers.
+ - dr_mode : indicates the working mode for "fsl-usb2-dr" compatible
+   controllers.  Can be "host", "peripheral", or "otg".  Default to
+   "host" if not defined for backward compatibility.
+Recommended properties :
+ - interrupts : <a b> where a is the interrupt number and b is a
+   field that represents an encoding of the sense and level
+   information for the interrupt.  This should be encoded based on
+   the information in section 2) depending on the type of interrupt
+   controller you have.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+Example multi port host USB controller device node :
+        usb@22000 {
+                compatible = "fsl-usb2-mph";
+                reg = <22000 1000>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                interrupt-parent = <700>;
+                interrupts = <27 1>;
+                phy_type = "ulpi";
+                port0;
+                port1;
+        };
+Example dual role USB controller device node :
+        usb@23000 {
+                compatible = "fsl-usb2-dr";
+                reg = <23000 1000>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                interrupt-parent = <700>;
+                interrupts = <26 1>;
+                dr_mode = "otg";
+                phy = "ulpi";
+        };
diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt
new file mode 100644
index 000000000000..ff51f4c0fa9d
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/gpio/led.txt
@@ -0,0 +1,15 @@
+LED connected to GPIO
+Required properties:
+- compatible : should be "gpio-led".
+- label : (optional) the label for this LED. If omitted, the label is
+  taken from the node name (excluding the unit address).
+- gpios : should specify LED GPIO.
+Example:
+led@0 {
+        compatible = "gpio-led";
+        label = "hdd";
+        gpios = <&mcu_pio 0 1>;
+};
diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.txt
index 896266432d33..06da4d4b44f9 100644
--- a/Documentation/powerpc/qe_firmware.txt
+++ b/Documentation/powerpc/qe_firmware.txt
@@ -217,7 +217,7 @@ Although it is not recommended, you can specify '0' in the soc.model
 field to skip matching SOCs altogether.
 The 'model' field is a 16-bit number that matches the actual SOC. The
-'major' and 'minor' fields are the major and minor revision numbrs,
+'major' and 'minor' fields are the major and minor revision numbers,
 respectively, of the SOC.
 For example, to match the 8323, revision 1.0:
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index a83ff23cd68c..0843ed0163a5 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -1,89 +1,528 @@
 rfkill - RF switch subsystem support
 ====================================
-1 Implementation details
+1 Introduction
-2 Driver support
+2 Implementation details
-3 Userspace support
+3 Kernel driver guidelines
+3.1 wireless device drivers
+3.2 platform/switch drivers
+3.3 input device drivers
+4 Kernel API
+5 Userspace support
-===============================================================================
-1: Implementation details
-The rfkill switch subsystem offers support for keys often found on laptops
+1. Introduction:
-to enable wireless devices like WiFi and Bluetooth.
+The rfkill switch subsystem exists to add a generic interface to circuitry that
+can enable or disable the signal output of a wireless *transmitter* of any
+type.  By far, the most common use is to disable radio-frequency transmitters.
-This is done by providing the user 3 possibilities:
+Note that disabling the signal output means that the the transmitter is to be
- 1 - The rfkill system handles all events; userspace is not aware of events.
+made to not emit any energy when "blocked".  rfkill is not about blocking data
- 2 - The rfkill system handles all events; userspace is informed about the events.
+transmissions, it is about blocking energy emission.
- 3 - The rfkill system does not handle events; userspace handles all events.
-The buttons to enable and disable the wireless radios are important in
+The rfkill subsystem offers support for keys and switches often found on
+laptops to enable wireless devices like WiFi and Bluetooth, so that these keys
+and switches actually perform an action in all wireless devices of a given type
+attached to the system.
+The buttons to enable and disable the wireless transmitters are important in
 situations where the user is for example using his laptop on a location where
-wireless radios _must_ be disabled (e.g. airplanes).
+radio-frequency transmitters _must_ be disabled (e.g. airplanes).
-Because of this requirement, userspace support for the keys should not be
-made mandatory. Because userspace might want to perform some additional smarter
+Because of this requirement, userspace support for the keys should not be made
-tasks when the key is pressed, rfkill still provides userspace the possibility
+mandatory.  Because userspace might want to perform some additional smarter
-to take over the task to handle the key events.
+tasks when the key is pressed, rfkill provides userspace the possibility to
+take over the task to handle the key events.
+===============================================================================
+2: Implementation details
+The rfkill subsystem is composed of various components: the rfkill class, the
+rfkill-input module (an input layer handler), and some specific input layer
+events.
+The rfkill class provides kernel drivers with an interface that allows them to
+know when they should enable or disable a wireless network device transmitter.
+This is enabled by the CONFIG_RFKILL Kconfig option.
+The rfkill class support makes sure userspace will be notified of all state
+changes on rfkill devices through uevents.  It provides a notification chain
+for interested parties in the kernel to also get notified of rfkill state
+changes in other drivers.  It creates several sysfs entries which can be used
+by userspace.  See section "Userspace support".
+The rfkill-input module provides the kernel with the ability to implement a
+basic response when the user presses a key or button (or toggles a switch)
+related to rfkill functionality.  It is an in-kernel implementation of default
+policy of reacting to rfkill-related input events and neither mandatory nor
+required for wireless drivers to operate.  It is enabled by the
+CONFIG_RFKILL_INPUT Kconfig option.
+rfkill-input is a rfkill-related events input layer handler.  This handler will
+listen to all rfkill key events and will change the rfkill state of the
+wireless devices accordingly.  With this option enabled userspace could either
+do nothing or simply perform monitoring tasks.
+The rfkill-input module also provides EPO (emergency power-off) functionality
+for all wireless transmitters.  This function cannot be overridden, and it is
+always active.  rfkill EPO is related to *_RFKILL_ALL input layer events.
+Important terms for the rfkill subsystem:
+In order to avoid confusion, we avoid the term "switch" in rfkill when it is
+referring to an electronic control circuit that enables or disables a
+transmitter.  We reserve it for the physical device a human manipulates
+(which is an input device, by the way):
+rfkill switch:
+        A physical device a human manipulates.  Its state can be perceived by
+        the kernel either directly (through a GPIO pin, ACPI GPE) or by its
+        effect on a rfkill line of a wireless device.
+rfkill controller:
+        A hardware circuit that controls the state of a rfkill line, which a
+        kernel driver can interact with *to modify* that state (i.e. it has
+        either write-only or read/write access).
+rfkill line:
+        An input channel (hardware or software) of a wireless device, which
+        causes a wireless transmitter to stop emitting energy (BLOCK) when it
+        is active.  Point of view is extremely important here: rfkill lines are
+        always seen from the PoV of a wireless device (and its driver).
+soft rfkill line/software rfkill line:
+        A rfkill line the wireless device driver can directly change the state
+        of.  Related to rfkill_state RFKILL_STATE_SOFT_BLOCKED.
+hard rfkill line/hardware rfkill line:
+        A rfkill line that works fully in hardware or firmware, and that cannot
+        be overridden by the kernel driver.  The hardware device or the
+        firmware just exports its status to the driver, but it is read-only.
+        Related to rfkill_state RFKILL_STATE_HARD_BLOCKED.
+The enum rfkill_state describes the rfkill state of a transmitter:
+When a rfkill line or rfkill controller is in the RFKILL_STATE_UNBLOCKED state,
+the wireless transmitter (radio TX circuit for example) is *enabled*.  When the
+it is in the RFKILL_STATE_SOFT_BLOCKED or RFKILL_STATE_HARD_BLOCKED, the
+wireless transmitter is to be *blocked* from operating.
+RFKILL_STATE_SOFT_BLOCKED indicates that a call to toggle_radio() can change
+that state.  RFKILL_STATE_HARD_BLOCKED indicates that a call to toggle_radio()
+will not be able to change the state and will return with a suitable error if
+attempts are made to set the state to RFKILL_STATE_UNBLOCKED.
+RFKILL_STATE_HARD_BLOCKED is used by drivers to signal that the device is
+locked in the BLOCKED state by a hardwire rfkill line (typically an input pin
+that, when active, forces the transmitter to be disabled) which the driver
+CANNOT override.
+Full rfkill functionality requires two different subsystems to cooperate: the
+input layer and the rfkill class.  The input layer issues *commands* to the
+entire system requesting that devices registered to the rfkill class change
+state.  The way this interaction happens is not complex, but it is not obvious
+either:
+Kernel Input layer:
+        * Generates KEY_WWAN, KEY_WLAN, KEY_BLUETOOTH, SW_RFKILL_ALL, and
+          other such events when the user presses certain keys, buttons, or
+          toggles certain physical switches.
+        THE INPUT LAYER IS NEVER USED TO PROPAGATE STATUS, NOTIFICATIONS OR THE
+        KIND OF STUFF AN ON-SCREEN-DISPLAY APPLICATION WOULD REPORT.  It is
+        used to issue *commands* for the system to change behaviour, and these
+        commands may or may not be carried out by some kernel driver or
+        userspace application.  It follows that doing user feedback based only
+        on input events is broken, as there is no guarantee that an input event
+        will be acted upon.
+        Most wireless communication device drivers implementing rfkill
+        functionality MUST NOT generate these events, and have no reason to
+        register themselves with the input layer.  Doing otherwise is a common
+        misconception.  There is an API to propagate rfkill status change
+        information, and it is NOT the input layer.
+rfkill class:
+        * Calls a hook in a driver to effectively change the wireless
+          transmitter state;
+        * Keeps track of the wireless transmitter state (with help from
+          the driver);
+        * Generates userspace notifications (uevents) and a call to a
+          notification chain (kernel) when there is a wireless transmitter
+          state change;
+        * Connects a wireless communications driver with the common rfkill
+          control system, which, for example, allows actions such as
+          "switch all bluetooth devices offline" to be carried out by
+          userspace or by rfkill-input.
+        THE RFKILL CLASS NEVER ISSUES INPUT EVENTS.  THE RFKILL CLASS DOES
+        NOT LISTEN TO INPUT EVENTS.  NO DRIVER USING THE RFKILL CLASS SHALL
+        EVER LISTEN TO, OR ACT ON RFKILL INPUT EVENTS.  Doing otherwise is
+        a layering violation.
+        Most wireless data communication drivers in the kernel have just to
+        implement the rfkill class API to work properly.  Interfacing to the
+        input layer is not often required (and is very often a *bug*) on
+        wireless drivers.
+        Platform drivers often have to attach to the input layer to *issue*
+        (but never to listen to) rfkill events for rfkill switches, and also to
+        the rfkill class to export a control interface for the platform rfkill
+        controllers to the rfkill subsystem.  This does NOT mean the rfkill
+        switch is attached to a rfkill class (doing so is almost always wrong).
+        It just means the same kernel module is the driver for different
+        devices (rfkill switches and rfkill controllers).
+Userspace input handlers (uevents) or kernel input handlers (rfkill-input):
+        * Implements the policy of what should happen when one of the input
+          layer events related to rfkill operation is received.
+        * Uses the sysfs interface (userspace) or private rfkill API calls
+          to tell the devices registered with the rfkill class to change
+          their state (i.e. translates the input layer event into real
+          action).
+        * rfkill-input implements EPO by handling EV_SW SW_RFKILL_ALL 0
+          (power off all transmitters) in a special way: it ignores any
+          overrides and local state cache and forces all transmitters to the
+          RFKILL_STATE_SOFT_BLOCKED state (including those which are already
+          supposed to be BLOCKED).  Note that the opposite event (power on all
+          transmitters) is handled normally.
+Userspace uevent handler or kernel platform-specific drivers hooked to the
+rfkill notifier chain:
+        * Taps into the rfkill notifier chain or to KOBJ_CHANGE uevents,
+          in order to know when a device that is registered with the rfkill
+          class changes state;
+        * Issues feedback notifications to the user;
+        * In the rare platforms where this is required, synthesizes an input
+          event to command all *OTHER* rfkill devices to also change their
+          statues when a specific rfkill device changes state.
+===============================================================================
+3: Kernel driver guidelines
+Remember: point-of-view is everything for a driver that connects to the rfkill
+subsystem.  All the details below must be measured/perceived from the point of
+view of the specific driver being modified.
+The first thing one needs to know is whether his driver should be talking to
+the rfkill class or to the input layer.  In rare cases (platform drivers), it
+could happen that you need to do both, as platform drivers often handle a
+variety of devices in the same driver.
+Do not mistake input devices for rfkill controllers.  The only type of "rfkill
+switch" device that is to be registered with the rfkill class are those
+directly controlling the circuits that cause a wireless transmitter to stop
+working (or the software equivalent of them), i.e. what we call a rfkill
+controller.  Every other kind of "rfkill switch" is just an input device and
+MUST NOT be registered with the rfkill class.
+A driver should register a device with the rfkill class when ALL of the
+following conditions are met (they define a rfkill controller):
+1. The device is/controls a data communications wireless transmitter;
+2. The kernel can interact with the hardware/firmware to CHANGE the wireless
+   transmitter state (block/unblock TX operation);
+3. The transmitter can be made to not emit any energy when "blocked":
+   rfkill is not about blocking data transmissions, it is about blocking
+   energy emission;
+A driver should register a device with the input subsystem to issue
+rfkill-related events (KEY_WLAN, KEY_BLUETOOTH, KEY_WWAN, KEY_WIMAX,
+SW_RFKILL_ALL, etc) when ALL of the folowing conditions are met:
+1. It is directly related to some physical device the user interacts with, to
+   command the O.S./firmware/hardware to enable/disable a data communications
+   wireless transmitter.
+   Examples of the physical device are: buttons, keys and switches the user
+   will press/touch/slide/switch to enable or disable the wireless
+   communication device.
+2. It is NOT slaved to another device, i.e. there is no other device that
+   issues rfkill-related input events in preference to this one.
-The system inside the kernel has been split into 2 separate sections:
+   Please refer to the corner cases and examples section for more details.
-        1 - RFKILL
-        2 - RFKILL_INPUT
-The first option enables rfkill support and will make sure userspace will
+When in doubt, do not issue input events.  For drivers that should generate
-be notified of any events through the input device. It also creates several
+input events in some platforms, but not in others (e.g. b43), the best solution
-sysfs entries which can be used by userspace. See section "Userspace support".
+is to NEVER generate input events in the first place.  That work should be
+deferred to a platform-specific kernel module (which will know when to generate
+events through the rfkill notifier chain) or to userspace.  This avoids the
+usual maintenance problems with DMI whitelisting.
-The second option provides an rfkill input handler. This handler will
-listen to all rfkill key events and will toggle the radio accordingly.
-With this option enabled userspace could either do nothing or simply
-perform monitoring tasks.
+Corner cases and examples:
 ====================================
-2: Driver support
-To build a driver with rfkill subsystem support, the driver should
+1. If the device is an input device that, because of hardware or firmware,
-depend on the Kconfig symbol RFKILL; it should _not_ depend on
+causes wireless transmitters to be blocked regardless of the kernel's will, it
-RKFILL_INPUT.
+is still just an input device, and NOT to be registered with the rfkill class.
-Unless key events trigger an interrupt to which the driver listens, polling
+2. If the wireless transmitter switch control is read-only, it is an input
-will be required to determine the key state changes. For this the input
+device and not to be registered with the rfkill class (and maybe not to be made
-layer providers the input-polldev handler.
+an input layer event source either, see below).
-A driver should implement a few steps to correctly make use of the
+3. If there is some other device driver *closer* to the actual hardware the
-rfkill subsystem. First for non-polling drivers:
+user interacted with (the button/switch/key) to issue an input event, THAT is
+the device driver that should be issuing input events.
-        - rfkill_allocate()
+E.g:
-        - input_allocate_device()
+  [RFKILL slider switch] -- [GPIO hardware] -- [WLAN card rf-kill input]
-        - rfkill_register()
+                           (platform driver)    (wireless card driver)
-        - input_register_device()
+The user is closer to the RFKILL slide switch plaform driver, so the driver
+which must issue input events is the platform driver looking at the GPIO
+hardware, and NEVER the wireless card driver (which is just a slave).  It is
+very likely that there are other leaves than just the WLAN card rf-kill input
+(e.g. a bluetooth card, etc)...
+On the other hand, some embedded devices do this:
+  [RFKILL slider switch] -- [WLAN card rf-kill input]
+                             (wireless card driver)
+In this situation, the wireless card driver *could* register itself as an input
+device and issue rf-kill related input events... but in order to AVOID the need
+for DMI whitelisting, the wireless card driver does NOT do it.  Userspace (HAL)
+or a platform driver (that exists only on these embedded devices) will do the
+dirty job of issuing the input events.
+COMMON MISTAKES in kernel drivers, related to rfkill:
+====================================
+1. NEVER confuse input device keys and buttons with input device switches.
+  1a. Switches are always set or reset.  They report the current state
+      (on position or off position).
+  1b. Keys and buttons are either in the pressed or not-pressed state, and
+      that's it.  A "button" that latches down when you press it, and
+      unlatches when you press it again is in fact a switch as far as input
+      devices go.
+Add the SW_* events you need for switches, do NOT try to emulate a button using
+KEY_* events just because there is no such SW_* event yet.  Do NOT try to use,
+for example, KEY_BLUETOOTH when you should be using SW_BLUETOOTH instead.
+2. Input device switches (sources of EV_SW events) DO store their current state
+(so you *must* initialize it by issuing a gratuitous input layer event on
+driver start-up and also when resuming from sleep), and that state CAN be
+queried from userspace through IOCTLs.  There is no sysfs interface for this,
+but that doesn't mean you should break things trying to hook it to the rfkill
+class to get a sysfs interface :-)
+3. Do not issue *_RFKILL_ALL events by default, unless you are sure it is the
+correct event for your switch/button.  These events are emergency power-off
+events when they are trying to turn the transmitters off.  An example of an
+input device which SHOULD generate *_RFKILL_ALL events is the wireless-kill
+switch in a laptop which is NOT a hotkey, but a real switch that kills radios
+in hardware, even if the O.S. has gone to lunch.  An example of an input device
+which SHOULD NOT generate *_RFKILL_ALL events by default, is any sort of hot
+key that does nothing by itself, as well as any hot key that is type-specific
+(e.g. the one for WLAN).
+3.1 Guidelines for wireless device drivers
+------------------------------------------
+1. Each independent transmitter in a wireless device (usually there is only one
+transmitter per device) should have a SINGLE rfkill class attached to it.
+2. If the device does not have any sort of hardware assistance to allow the
+driver to rfkill the device, the driver should emulate it by taking all actions
+required to silence the transmitter.
+3. If it is impossible to silence the transmitter (i.e. it still emits energy,
+even if it is just in brief pulses, when there is no data to transmit and there
+is no hardware support to turn it off) do NOT lie to the users.  Do not attach
+it to a rfkill class.  The rfkill subsystem does not deal with data
+transmission, it deals with energy emission.  If the transmitter is emitting
+energy, it is not blocked in rfkill terms.
+4. It doesn't matter if the device has multiple rfkill input lines affecting
+the same transmitter, their combined state is to be exported as a single state
+per transmitter (see rule 1).
+This rule exists because users of the rfkill subsystem expect to get (and set,
+when possible) the overall transmitter rfkill state, not of a particular rfkill
+line.
+Example of a WLAN wireless driver connected to the rfkill subsystem:
+--------------------------------------------------------------------
+A certain WLAN card has one input pin that causes it to block the transmitter
+and makes the status of that input pin available (only for reading!) to the
+kernel driver.  This is a hard rfkill input line (it cannot be overridden by
+the kernel driver).
+The card also has one PCI register that, if manipulated by the driver, causes
+it to block the transmitter.  This is a soft rfkill input line.
+It has also a thermal protection circuitry that shuts down its transmitter if
+the card overheats, and makes the status of that protection available (only for
+reading!) to the kernel driver.  This is also a hard rfkill input line.
+If either one of these rfkill lines are active, the transmitter is blocked by
+the hardware and forced offline.
+The driver should allocate and attach to its struct device *ONE* instance of
+the rfkill class (there is only one transmitter).
+It can implement the get_state() hook, and return RFKILL_STATE_HARD_BLOCKED if
+either one of its two hard rfkill input lines are active.  If the two hard
+rfkill lines are inactive, it must return RFKILL_STATE_SOFT_BLOCKED if its soft
+rfkill input line is active.  Only if none of the rfkill input lines are
+active, will it return RFKILL_STATE_UNBLOCKED.
-For polling drivers:
+If it doesn't implement the get_state() hook, it must make sure that its calls
+to rfkill_force_state() are enough to keep the status always up-to-date, and it
+must do a rfkill_force_state() on resume from sleep.
+Every time the driver gets a notification from the card that one of its rfkill
+lines changed state (polling might be needed on badly designed cards that don't
+generate interrupts for such events), it recomputes the rfkill state as per
+above, and calls rfkill_force_state() to update it.
+The driver should implement the toggle_radio() hook, that:
+1. Returns an error if one of the hardware rfkill lines are active, and the
+caller asked for RFKILL_STATE_UNBLOCKED.
+2. Activates the soft rfkill line if the caller asked for state
+RFKILL_STATE_SOFT_BLOCKED.  It should do this even if one of the hard rfkill
+lines are active, effectively double-blocking the transmitter.
+3. Deactivates the soft rfkill line if none of the hardware rfkill lines are
+active and the caller asked for RFKILL_STATE_UNBLOCKED.
+===============================================================================
+4: Kernel API
+To build a driver with rfkill subsystem support, the driver should depend on
+(or select) the Kconfig symbol RFKILL; it should _not_ depend on RKFILL_INPUT.
+The hardware the driver talks to may be write-only (where the current state
+of the hardware is unknown), or read-write (where the hardware can be queried
+about its current state).
+The rfkill class will call the get_state hook of a device every time it needs
+to know the *real* current state of the hardware.  This can happen often.
+Some hardware provides events when its status changes.  In these cases, it is
+best for the driver to not provide a get_state hook, and instead register the
+rfkill class *already* with the correct status, and keep it updated using
+rfkill_force_state() when it gets an event from the hardware.
+There is no provision for a statically-allocated rfkill struct.  You must
+use rfkill_allocate() to allocate one.
+You should:
        - rfkill_allocate()
-        - input_allocate_polled_device()
+        - modify rfkill fields (flags, name)
+        - modify state to the current hardware state (THIS IS THE ONLY TIME
+          YOU CAN ACCESS state DIRECTLY)
        - rfkill_register()
-        - input_register_polled_device()
-When a key event has been detected, the correct event should be
+The only way to set a device to the RFKILL_STATE_HARD_BLOCKED state is through
-sent over the input device which has been registered by the driver.
+a suitable return of get_state() or through rfkill_force_state().
-====================================
+When a device is in the RFKILL_STATE_HARD_BLOCKED state, the only way to switch
-3: Userspace support
+it to a different state is through a suitable return of get_state() or through
+rfkill_force_state().
+If toggle_radio() is called to set a device to state RFKILL_STATE_SOFT_BLOCKED
+when that device is already at the RFKILL_STATE_HARD_BLOCKED state, it should
+not return an error.  Instead, it should try to double-block the transmitter,
+so that its state will change from RFKILL_STATE_HARD_BLOCKED to
+RFKILL_STATE_SOFT_BLOCKED should the hardware blocking cease.
-For each key an input device will be created which will send out the correct
+Please refer to the source for more documentation.
-key event when the rfkill key has been pressed.
+===============================================================================
+5: Userspace support
+rfkill devices issue uevents (with an action of "change"), with the following
+environment variables set:
+RFKILL_NAME
+RFKILL_STATE
+RFKILL_TYPE
+The ABI for these variables is defined by the sysfs attributes.  It is best
+to take a quick look at the source to make sure of the possible values.
+It is expected that HAL will trap those, and bridge them to DBUS, etc.  These
+events CAN and SHOULD be used to give feedback to the user about the rfkill
+status of the system.
+Input devices may issue events that are related to rfkill.  These are the
+various KEY_* events and SW_* events supported by rfkill-input.c.
+******IMPORTANT******
+When rfkill-input is ACTIVE, userspace is NOT TO CHANGE THE STATE OF AN RFKILL
+SWITCH IN RESPONSE TO AN INPUT EVENT also handled by rfkill-input, unless it
+has set to true the user_claim attribute for that particular switch.  This rule
+is *absolute*; do NOT violate it.
+******IMPORTANT******
+Userspace must not assume it is the only source of control for rfkill switches.
+Their state CAN and WILL change due to firmware actions, direct user actions,
+and the rfkill-input EPO override for *_RFKILL_ALL.
+When rfkill-input is not active, userspace must initiate a rfkill status
+change by writing to the "state" attribute in order for anything to happen.
+Take particular care to implement EV_SW SW_RFKILL_ALL properly.  When that
+switch is set to OFF, *every* rfkill device *MUST* be immediately put into the
+RFKILL_STATE_SOFT_BLOCKED state, no questions asked.
 The following sysfs entries will be created:
        name: Name assigned by driver to this key (interface or driver name).
        type: Name of the key type ("wlan", "bluetooth", etc).
-        state: Current state of the key. 1: On, 0: Off.
+        state: Current state of the transmitter
+                0: RFKILL_STATE_SOFT_BLOCKED
+                        transmitter is forced off, but one can override it
+                        by a write to the state attribute;
+                1: RFKILL_STATE_UNBLOCKED
+                        transmiter is NOT forced off, and may operate if
+                        all other conditions for such operation are met
+                        (such as interface is up and configured, etc);
+                2: RFKILL_STATE_HARD_BLOCKED
+                        transmitter is forced off by something outside of
+                        the driver's control.  One cannot set a device to
+                        this state through writes to the state attribute;
        claim: 1: Userspace handles events, 0: Kernel handles events
 Both the "state" and "claim" entries are also writable. For the "state" entry
-this means that when 1 or 0 is written all radios, not yet in the requested
+this means that when 1 or 0 is written, the device rfkill state (if not yet in
-state, will be will be toggled accordingly.
+the requested state), will be will be toggled accordingly.
 For the "claim" entry writing 1 to it means that the kernel no longer handles
 key events even though RFKILL_INPUT input was enabled. When "claim" has been
 set to 0, userspace should make sure that it listens for the input events or
-check the sysfs "state" entry regularly to correctly perform the required
+check the sysfs "state" entry regularly to correctly perform the required tasks
-tasks when the rkfill key is pressed.
+when the rkfill key is pressed.
+A note about input devices and EV_SW events:
+In order to know the current state of an input device switch (like
+SW_RFKILL_ALL), you will need to use an IOCTL.  That information is not
+available through sysfs in a generic way at this time, and it is not available
+through the rfkill class AT ALL.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index 8fbc0a852870..bf0baa19ec24 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -8,17 +8,6 @@ Command line parameters
  Enable logging of debug information in case of ccw device timeouts.
-* cio_msg = yes | no
-  
-  Determines whether information on found devices and sensed device 
-  characteristics should be shown during startup or when new devices are
-  found, i. e. messages of the types "Detected device 0.0.4711 on subchannel
-  0.0.0042" and "SenseID: Device 0.0.4711 reports: ...".
-  Default is off.
 * cio_ignore = {all} |
               {<device> | <range of devices>} |
               {!<device> | !<range of devices>}
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index e938c442277d..bde473df748d 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -25,7 +25,7 @@ device 4711 via subchannel 1 in subchannel set 0, and subchannel 2 is a non-I/O
 subchannel. Device 1234 is accessed via subchannel 0 in subchannel set 1.
 The subchannel named 'defunct' does not represent any real subchannel on the
-system; it is a pseudo subchannel where disconnnected ccw devices are moved to
+system; it is a pseudo subchannel where disconnected ccw devices are moved to
 if they are displaced by another ccw device becoming operational on their
 former subchannel. The ccw devices will be moved again to a proper subchannel
 if they become operational again on that subchannel.
diff --git a/Documentation/scheduler/sched-design.txt b/Documentation/scheduler/sched-design.txt
deleted file mode 100644
index 1605bf0cba8b..000000000000
--- a/Documentation/scheduler/sched-design.txt
+++ /dev/null
@@ -1,165 +0,0 @@
-                   Goals, Design and Implementation of the
-                      new ultra-scalable O(1) scheduler
-  This is an edited version of an email Ingo Molnar sent to
-  lkml on 4 Jan 2002.  It describes the goals, design, and
-  implementation of Ingo's new ultra-scalable O(1) scheduler.
-  Last Updated: 18 April 2002.
-Goal
-====
-The main goal of the new scheduler is to keep all the good things we know
-and love about the current Linux scheduler:
- - good interactive performance even during high load: if the user
-   types or clicks then the system must react instantly and must execute
-   the user tasks smoothly, even during considerable background load.
- - good scheduling/wakeup performance with 1-2 runnable processes.
- - fairness: no process should stay without any timeslice for any
-   unreasonable amount of time. No process should get an unjustly high
-   amount of CPU time.
- - priorities: less important tasks can be started with lower priority,
-   more important tasks with higher priority.
- - SMP efficiency: no CPU should stay idle if there is work to do.
- - SMP affinity: processes which run on one CPU should stay affine to
-   that CPU. Processes should not bounce between CPUs too frequently.
- - plus additional scheduler features: RT scheduling, CPU binding.
-and the goal is also to add a few new things:
- - fully O(1) scheduling. Are you tired of the recalculation loop
-   blowing the L1 cache away every now and then? Do you think the goodness
-   loop is taking a bit too long to finish if there are lots of runnable
-   processes? This new scheduler takes no prisoners: wakeup(), schedule(),
-   the timer interrupt are all O(1) algorithms. There is no recalculation
-   loop. There is no goodness loop either.
- - 'perfect' SMP scalability. With the new scheduler there is no 'big'
-   runqueue_lock anymore - it's all per-CPU runqueues and locks - two
-   tasks on two separate CPUs can wake up, schedule and context-switch
-   completely in parallel, without any interlocking. All
-   scheduling-relevant data is structured for maximum scalability.
- - better SMP affinity. The old scheduler has a particular weakness that
-   causes the random bouncing of tasks between CPUs if/when higher
-   priority/interactive tasks, this was observed and reported by many
-   people. The reason is that the timeslice recalculation loop first needs
-   every currently running task to consume its timeslice. But when this
-   happens on eg. an 8-way system, then this property starves an
-   increasing number of CPUs from executing any process. Once the last
-   task that has a timeslice left has finished using up that timeslice,
-   the recalculation loop is triggered and other CPUs can start executing
-   tasks again - after having idled around for a number of timer ticks.
-   The more CPUs, the worse this effect.
-   Furthermore, this same effect causes the bouncing effect as well:
-   whenever there is such a 'timeslice squeeze' of the global runqueue,
-   idle processors start executing tasks which are not affine to that CPU.
-   (because the affine tasks have finished off their timeslices already.)
-   The new scheduler solves this problem by distributing timeslices on a
-   per-CPU basis, without having any global synchronization or
-   recalculation.
- - batch scheduling. A significant proportion of computing-intensive tasks
-   benefit from batch-scheduling, where timeslices are long and processes
-   are roundrobin scheduled. The new scheduler does such batch-scheduling
-   of the lowest priority tasks - so nice +19 jobs will get
-   'batch-scheduled' automatically. With this scheduler, nice +19 jobs are
-   in essence SCHED_IDLE, from an interactiveness point of view.
- - handle extreme loads more smoothly, without breakdown and scheduling
-   storms.
- - O(1) RT scheduling. For those RT folks who are paranoid about the
-   O(nr_running) property of the goodness loop and the recalculation loop.
- - run fork()ed children before the parent. Andrea has pointed out the
-   advantages of this a few months ago, but patches for this feature
-   do not work with the old scheduler as well as they should,
-   because idle processes often steal the new child before the fork()ing
-   CPU gets to execute it.
-Design
-======
-The core of the new scheduler contains the following mechanisms:
- - *two* priority-ordered 'priority arrays' per CPU. There is an 'active'
-   array and an 'expired' array. The active array contains all tasks that
-   are affine to this CPU and have timeslices left. The expired array
-   contains all tasks which have used up their timeslices - but this array
-   is kept sorted as well. The active and expired array is not accessed
-   directly, it's accessed through two pointers in the per-CPU runqueue
-   structure. If all active tasks are used up then we 'switch' the two
-   pointers and from now on the ready-to-go (former-) expired array is the
-   active array - and the empty active array serves as the new collector
-   for expired tasks.
- - there is a 64-bit bitmap cache for array indices. Finding the highest
-   priority task is thus a matter of two x86 BSFL bit-search instructions.
-the split-array solution enables us to have an arbitrary number of active
-and expired tasks, and the recalculation of timeslices can be done
-immediately when the timeslice expires. Because the arrays are always
-access through the pointers in the runqueue, switching the two arrays can
-be done very quickly.
-this is a hybride priority-list approach coupled with roundrobin
-scheduling and the array-switch method of distributing timeslices.
- - there is a per-task 'load estimator'.
-one of the toughest things to get right is good interactive feel during
-heavy system load. While playing with various scheduler variants i found
-that the best interactive feel is achieved not by 'boosting' interactive
-tasks, but by 'punishing' tasks that want to use more CPU time than there
-is available. This method is also much easier to do in an O(1) fashion.
-to establish the actual 'load' the task contributes to the system, a
-complex-looking but pretty accurate method is used: there is a 4-entry
-'history' ringbuffer of the task's activities during the last 4 seconds.
-This ringbuffer is operated without much overhead. The entries tell the
-scheduler a pretty accurate load-history of the task: has it used up more
-CPU time or less during the past N seconds. [the size '4' and the interval
-of 4x 1 seconds was found by lots of experimentation - this part is
-flexible and can be changed in both directions.]
-the penalty a task gets for generating more load than the CPU can handle
-is a priority decrease - there is a maximum amount to this penalty
-relative to their static priority, so even fully CPU-bound tasks will
-observe each other's priorities, and will share the CPU accordingly.
-the SMP load-balancer can be extended/switched with additional parallel
-computing and cache hierarchy concepts: NUMA scheduling, multi-core CPUs
-can be supported easily by changing the load-balancer. Right now it's
-tuned for my SMP systems.
-i skipped the prev->mm == next->mm advantage - no workload i know of shows
-any sensitivity to this. It can be added back by sacrificing O(1)
-schedule() [the current and one-lower priority list can be searched for a
-that->mm == current->mm condition], but costs a fair number of cycles
-during a number of important workloads, so i wanted to avoid this as much
-as possible.
- the SMP idle-task startup code was still racy and the new scheduler
-triggered this. So i streamlined the idle-setup code a bit. We do not call
-into schedule() before all processors have started up fully and all idle
-threads are in place.
- the patch also cleans up a number of aspects of sched.c - moves code
-into other areas of the kernel where it's appropriate, and simplifies
-certain code paths and data constructs. As a result, the new scheduler's
-code is smaller than the old one.
-        Ingo
diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt
index a9e990ab980f..373ceacc367e 100644
--- a/Documentation/scheduler/sched-domains.txt
+++ b/Documentation/scheduler/sched-domains.txt
@@ -61,10 +61,7 @@ builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your
 arch_init_sched_domains function. This function will attach domains to all
 CPUs using cpu_attach_domain.
-Implementors should change the line
+The sched-domains debugging infrastructure can be enabled by enabling
-#undef SCHED_DOMAIN_DEBUG
+CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains
-to
-#define SCHED_DOMAIN_DEBUG
-in kernel/sched.c as this enables an error checking parse of the sched domains
 which should catch most possible errors (described above). It also prints out
 the domain structure in a visual format.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 14f901f639ee..3ef339f491e0 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -51,9 +51,9 @@ needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s =
 0.00015s. So this group can be scheduled with a period of 0.005s and a run time
 of 0.00015s.
-The remaining CPU time will be used for user input and other tass. Because
+The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
-their tasks, buffer underruns in the graphocs or audio can be eliminated.
+their tasks, buffer underruns in the graphics or audio can be eliminated.
 NOTE: the above example is not fully implemented as of yet (2.6.25). We still
 lack an EDF scheduler to make non-uniform periods usable.
diff --git a/Documentation/scsi/aacraid.txt b/Documentation/scsi/aacraid.txt
index d16011a8618e..709ca991a451 100644
--- a/Documentation/scsi/aacraid.txt
+++ b/Documentation/scsi/aacraid.txt
@@ -56,19 +56,33 @@ Supported Cards/Chipsets
        9005:0285:9005:02d1     Adaptec 5405 (Voodoo40)
        9005:0285:15d9:02d2     SMC     AOC-USAS-S8i-LP
        9005:0285:15d9:02d3     SMC     AOC-USAS-S8iR-LP
-        9005:0285:9005:02d4     Adaptec 2045 (Voodoo04 Lite)
+        9005:0285:9005:02d4     Adaptec ASR-2045 (Voodoo04 Lite)
-        9005:0285:9005:02d5     Adaptec 2405 (Voodoo40 Lite)
+        9005:0285:9005:02d5     Adaptec ASR-2405 (Voodoo40 Lite)
-        9005:0285:9005:02d6     Adaptec 2445 (Voodoo44 Lite)
+        9005:0285:9005:02d6     Adaptec ASR-2445 (Voodoo44 Lite)
-        9005:0285:9005:02d7     Adaptec 2805 (Voodoo80 Lite)
+        9005:0285:9005:02d7     Adaptec ASR-2805 (Voodoo80 Lite)
+        9005:0285:9005:02d8     Adaptec 5405G (Voodoo40 PM)
+        9005:0285:9005:02d9     Adaptec 5445G (Voodoo44 PM)
+        9005:0285:9005:02da     Adaptec 5805G (Voodoo80 PM)
+        9005:0285:9005:02db     Adaptec 5085G (Voodoo08 PM)
+        9005:0285:9005:02dc     Adaptec 51245G (Voodoo124 PM)
+        9005:0285:9005:02dd     Adaptec 51645G (Voodoo164 PM)
+        9005:0285:9005:02de     Adaptec 52445G (Voodoo244 PM)
+        9005:0285:9005:02df     Adaptec ASR-2045G (Voodoo04 Lite PM)
+        9005:0285:9005:02e0     Adaptec ASR-2405G (Voodoo40 Lite PM)
+        9005:0285:9005:02e1     Adaptec ASR-2445G (Voodoo44 Lite PM)
+        9005:0285:9005:02e2     Adaptec ASR-2805G (Voodoo80 Lite PM)
        1011:0046:9005:0364     Adaptec 5400S (Mustang)
+        1011:0046:9005:0365     Adaptec 5400S (Mustang)
        9005:0287:9005:0800     Adaptec Themisto (Jupiter)
        9005:0200:9005:0200     Adaptec Themisto (Jupiter)
        9005:0286:9005:0800     Adaptec Callisto (Jupiter)
        1011:0046:9005:1364     Dell    PERC 2/QC (Quad Channel, Mustang)
+        1011:0046:9005:1365     Dell    PERC 2/QC (Quad Channel, Mustang)
        1028:0001:1028:0001     Dell    PERC 2/Si (Iguana)
        1028:0003:1028:0003     Dell    PERC 3/Si (SlimFast)
        1028:0002:1028:0002     Dell    PERC 3/Di (Opal)
-        1028:0004:1028:0004     Dell    PERC 3/DiF (Iguana)
+        1028:0004:1028:0004     Dell    PERC 3/SiF (Iguana)
+        1028:0004:1028:00d0     Dell    PERC 3/DiF (Iguana)
        1028:0002:1028:00d1     Dell    PERC 3/DiV (Viper)
        1028:0002:1028:00d9     Dell    PERC 3/DiL (Lexus)
        1028:000a:1028:0106     Dell    PERC 3/DiJ (Jaguar)
diff --git a/Documentation/scsi/ibmmca.txt b/Documentation/scsi/ibmmca.txt
index a810421f1fb3..3920f28710c4 100644
--- a/Documentation/scsi/ibmmca.txt
+++ b/Documentation/scsi/ibmmca.txt
@@ -524,7 +524,7 @@
   - Michael Lang
 
   June 25 1997: (v1.8b)
-   1) Some cosmetical changes for the handling of SCSI-device-types.
+   1) Some cosmetic changes for the handling of SCSI-device-types.
      Now, also CD-Burners / WORMs and SCSI-scanners should work. For
      MO-drives I have no experience, therefore not yet supported.
      In logical_devices I changed from different type-variables to one
@@ -914,7 +914,7 @@
      in version 4.0. This was never really necessary, as all troubles were
      based on non-command related reasons up to now, so bypassing commands
      did not help to avoid any bugs. It is kept in 3.2X for debugging reasons.
-   5) Dynamical reassignment of ldns was again verified and analyzed to be
+   5) Dynamic reassignment of ldns was again verified and analyzed to be
      completely inoperational. This is corrected and should work now.
   6) All commands that get sent to the SCSI adapter were verified and
      completed in such a way, that they are now completely conform to the
@@ -1386,7 +1386,7 @@
   concerning the Linux-kernel in special, this SCSI-driver comes without any
   warranty. Its functionality is tested as good as possible on certain 
   machines and combinations of computer hardware, which does not exclude,
-   that dataloss or severe damage of hardware is possible while using this
+   that data loss or severe damage of hardware is possible while using this
   part of software on some arbitrary computer hardware or in combination 
   with other software packages. It is highly recommended to make backup
   copies of your data before using this software. Furthermore, personal
diff --git a/Documentation/scsi/lpfc.txt b/Documentation/scsi/lpfc.txt
index 4dbe41370a6d..5741ea8aa88a 100644
--- a/Documentation/scsi/lpfc.txt
+++ b/Documentation/scsi/lpfc.txt
@@ -36,7 +36,7 @@ Cable pull and temporary device Loss:
  being removed, a switch rebooting, or a device reboot), the driver could
  hide the disappearance of the device from the midlayer. I/O's issued to
  the LLDD would simply be queued for a short duration, allowing the device
-  to reappear or link come back alive, with no inadvertant side effects
+  to reappear or link come back alive, with no inadvertent side effects
  to the system. If the driver did not hide these conditions, i/o would be
  errored by the driver, the mid-layer would exhaust its retries, and the
  device would be taken offline. Manual intervention would be required to
diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt
index d403e46d8463..75143f0c23b6 100644
--- a/Documentation/scsi/scsi_fc_transport.txt
+++ b/Documentation/scsi/scsi_fc_transport.txt
@@ -65,7 +65,7 @@ Overview:
    discussion will concentrate on NPIV.
  Note: World Wide Name assignment (and uniqueness guarantees) are left
-    up to an administrative entity controling the vport. For example,
+    up to an administrative entity controlling the vport. For example,
    if vports are to be associated with virtual machines, a XEN mgmt
    utility would be responsible for creating wwpn/wwnn's for the vport,
    using it's own naming authority and OUI. (Note: it already does this
@@ -91,7 +91,7 @@ Device Trees and Vport Objects:
  Here's what to expect in the device tree :
   The typical Physical Port's Scsi_Host:
     /sys/devices/.../host17/
-   and it has the typical decendent tree:
+   and it has the typical descendant tree:
     /sys/devices/.../host17/rport-17:0-0/target17:0:0/17:0:0:0:
   and then the vport is created on the Physical Port:
     /sys/devices/.../host17/vport-17:0-0
@@ -192,7 +192,7 @@ Vport States:
      independent of the adapter's link state.
    - Instantiation of the vport on the FC link via ELS traffic, etc.
      This is equivalent to a "link up" and successfull link initialization.
-  Futher information can be found in the interfaces section below for
+  Further information can be found in the interfaces section below for
  Vport Creation.
  Once a vport has been instantiated with the kernel/LLDD, a vport state
diff --git a/Documentation/serial/driver b/Documentation/serial/driver
index 88ad615dd338..77ba0afbe4db 100644
--- a/Documentation/serial/driver
+++ b/Documentation/serial/driver
@@ -186,6 +186,17 @@ hardware.
        Locking: port_sem taken.
        Interrupts: caller dependent.
+  flush_buffer(port)
+        Flush any write buffers, reset any DMA state and stop any
+        ongoing DMA transfers.
+        This will be called whenever the port->info->xmit circular
+        buffer is cleared.
+        Locking: port->lock taken.
+        Interrupts: locally disabled.
+        This call must not sleep
  set_termios(port,termios,oldtermios)
        Change the port parameters, including word length, parity, stop
        bits.  Update read_status_mask and ignore_status_mask to indicate
diff --git a/Documentation/sh/clk.txt b/Documentation/sh/clk.txt
index 9aef710e9a4b..114b595cfa97 100644
--- a/Documentation/sh/clk.txt
+++ b/Documentation/sh/clk.txt
@@ -12,7 +12,7 @@ means no changes to adjanced clock
 Internally, the clk_set_rate_ex forwards request to clk->ops->set_rate method,
 if it is present in ops structure. The method should set the clock rate and adjust
 all needed clocks according to the passed algo_id.
-Exact values for algo_id are machine-dependend. For the sh7722, the following
+Exact values for algo_id are machine-dependent. For the sh7722, the following
 values are defined:
        NO_CHANGE       = 0,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 0bbee38acd26..6f6d117ac7e2 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -753,8 +753,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    [Multiple options for each card instance]
    model       - force the model name
-    position_fix - Fix DMA pointer (0 = auto, 1 = none, 2 = POSBUF, 3 = FIFO size)
+    position_fix - Fix DMA pointer (0 = auto, 1 = use LPIB, 2 = POSBUF)
    probe_mask  - Bitmask to probe codecs (default = -1, meaning all slots)
+    bdl_pos_adj - Specifies the DMA IRQ timing delay in samples.
+                Passing -1 will make the driver to choose the appropriate
+                value based on the controller chip.
    
    [Single (global) options]
    single_cmd  - Use single immediate commands to communicate with
@@ -845,7 +848,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
        ALC269
          basic         Basic preset
-        ALC662
+        ALC662/663
          3stack-dig    3-stack (2-channel) with SPDIF
          3stack-6ch     3-stack (6-channel)
          3stack-6ch-dig 3-stack (6-channel) with SPDIF
@@ -853,6 +856,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          lenovo-101e    Lenovo laptop
          eeepc-p701    ASUS Eeepc P701
          eeepc-ep20    ASUS Eeepc EP20
+          m51va         ASUS M51VA
+          g71v          ASUS G71V
+          h13           ASUS H13
+          g50v          ASUS G50V
          auto          auto-config reading BIOS (default)
        ALC882/885
@@ -1017,6 +1024,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          intel-mac-v3  Intel Mac Type 3
          intel-mac-v4  Intel Mac Type 4
          intel-mac-v5  Intel Mac Type 5
+          intel-mac-auto Intel Mac (detect type according to subsystem id)
          macmini       Intel Mac Mini (equivalent with type 3)
          macbook       Intel Mac Book (eq. type 5)
          macbook-pro-v1 Intel Mac Book Pro 1st generation (eq. type 3)
@@ -1091,7 +1099,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    This occurs when the access to non-existing or non-working codec slot
    (likely a modem one) causes a stall of the communication via HD-audio
    bus.  You can see which codec slots are probed by enabling
-    CONFIG_SND_DEBUG_DETECT, or simply from the file name of the codec
+    CONFIG_SND_DEBUG_VERBOSE, or simply from the file name of the codec
    proc files.  Then limit the slots to probe by probe_mask option.
    For example, probe_mask=1 means to probe only the first slot, and
    probe_mask=4 means only the third slot.
@@ -2267,6 +2275,10 @@ case above again, the first two slots are already reserved.  If any
 other driver (e.g. snd-usb-audio) is loaded before snd-interwave or
 snd-ens1371, it will be assigned to the third or later slot.
+When a module name is given with '!', the slot will be given for any
+modules but that name.  For example, "slots=!snd-pcsp" will reserve
+the first slot for any modules but snd-pcsp. 
 ALSA PCM devices to OSS devices mapping
 =======================================
diff --git a/Documentation/sound/alsa/Audiophile-Usb.txt b/Documentation/sound/alsa/Audiophile-Usb.txt
index 2ad5e6306c44..a4c53d8961e1 100644
--- a/Documentation/sound/alsa/Audiophile-Usb.txt
+++ b/Documentation/sound/alsa/Audiophile-Usb.txt
@@ -236,15 +236,15 @@ The parameter can be given:
       alias snd-card-1 snd-usb-audio
       options snd-usb-audio index=1 device_setup=0x09
-CAUTION when initializaing the device
+CAUTION when initializing the device
 -------------------------------------
 * Correct initialization on the device requires that device_setup is given to
   the module BEFORE the device is turned on. So, if you use the "manual probing"
   method described above, take care to power-on the device AFTER this initialization.
- * Failing to respect this will lead in a misconfiguration of the device. In this case
+ * Failing to respect this will lead to a misconfiguration of the device. In this case
-   turn off the device, unproble the snd-usb-audio module, then probe it again with 
+   turn off the device, unprobe the snd-usb-audio module, then probe it again with
   correct device_setup parameter and then (and only then) turn on the device again.
 * If you've correctly initialized the device in a valid mode and then want to switch
@@ -388,9 +388,9 @@ There are 2 main potential issues when using Jackd with the device:
 Jack supports big endian devices only in recent versions (thanks to
 Andreas Steinmetz for his first big-endian patch). I can't remember 
-extacly when this support was released into jackd, let's just say that 
+exactly when this support was released into jackd, let's just say that
 with jackd version 0.103.0 it's almost ok (just a small bug is affecting 
-16bits Big-Endian devices, but since you've read  carefully the above 
+16bits Big-Endian devices, but since you've read carefully the above
 paragraphs, you're now using kernel >= 2.6.23 and your 16bits devices 
 are now Little Endians ;-) ).
diff --git a/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl b/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
index c4d2e3507af9..9d644f7e241e 100644
--- a/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
+++ b/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
@@ -42,7 +42,7 @@
     <sect1><title>Device Components</title>
 !Esound/core/device.c
     </sect1>
-     <sect1><title>KMOD and Device File Entries</title>
+     <sect1><title>Module requests and Device File Entries</title>
 !Esound/core/sound.c
     </sect1>
     <sect1><title>Memory Management Helpers</title>
diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
index b03df4d4795c..e13c4e67029f 100644
--- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
@@ -6127,8 +6127,8 @@ struct _snd_pcm_runtime {
      <para>
        <function>snd_printdd()</function> is compiled in only when
-      <constant>CONFIG_SND_DEBUG_DETECT</constant> is set. Please note
+      <constant>CONFIG_SND_DEBUG_VERBOSE</constant> is set. Please note
-      that <constant>DEBUG_DETECT</constant> is not set as default
+      that <constant>CONFIG_SND_DEBUG_VERBOSE</constant> is not set as default
      even if you configure the alsa-driver with
      <option>--with-debug=full</option> option. You need to give
      explicitly <option>--with-debug=detect</option> option instead. 
diff --git a/Documentation/sound/alsa/hda_codec.txt b/Documentation/sound/alsa/hda_codec.txt
index 8e1b02526698..34e87ec1379c 100644
--- a/Documentation/sound/alsa/hda_codec.txt
+++ b/Documentation/sound/alsa/hda_codec.txt
@@ -67,7 +67,7 @@ CONFIG_SND_HDA_POWER_SAVE kconfig.  It's called when the codec needs
 to power up or may power down.  The controller should check the all
 belonging codecs on the bus whether they are actually powered off
 (check codec->power_on), and optionally the driver may power down the
-contoller side, too.
+controller side, too.
 The bus instance is created via snd_hda_bus_new().  You need to pass
 the card instance, the template, and the pointer to store the
diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt
index c784a18b94dc..b2ed6983f40d 100644
--- a/Documentation/sound/alsa/soc/dapm.txt
+++ b/Documentation/sound/alsa/soc/dapm.txt
@@ -68,7 +68,7 @@ Audio DAPM widgets fall into a number of types:-
 (Widgets are defined in include/sound/soc-dapm.h)
 Widgets are usually added in the codec driver and the machine driver. There are
-convience macros defined in soc-dapm.h that can be used to quickly build a
+convenience macros defined in soc-dapm.h that can be used to quickly build a
 list of widgets of the codecs and machines DAPM widgets.
 Most widgets have a name, register, shift and invert. Some widgets have extra
diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt
index 1a3bdc27d95e..42f43fa59f24 100644
--- a/Documentation/sparse.txt
+++ b/Documentation/sparse.txt
@@ -73,10 +73,10 @@ recompiled, or use "make C=2" to run sparse on the files whether they need to
 be recompiled or not.  The latter is a fast way to check the whole tree if you
 have already built it.
-The optional make variable CHECKFLAGS can be used to pass arguments to sparse.
+The optional make variable CF can be used to pass arguments to sparse.  The
-The build system passes -Wbitwise to sparse automatically.  To perform
+build system passes -Wbitwise to sparse automatically.  To perform endianness
-endianness checks, you may define __CHECK_ENDIAN__:
+checks, you may define __CHECK_ENDIAN__:
-        make C=2 CHECKFLAGS="-D__CHECK_ENDIAN__"
+        make C=2 CF="-D__CHECK_ENDIAN__"
 These checks are disabled by default as they generate a host of warnings.
diff --git a/Documentation/specialix.txt b/Documentation/specialix.txt
index 4a4b428ce8f6..6eb6f3a3331c 100644
--- a/Documentation/specialix.txt
+++ b/Documentation/specialix.txt
@@ -270,8 +270,8 @@ The pinout of the connectors on the IO8+ is:
 Hardware handshaking issues.
 ============================
-The driver can be compiled in two different ways. The default
+The driver can be told to operate in two different ways. The default
-("Specialix DTR/RTS pin is RTS" is off) the pin behaves as DTR when
+behaviour is specialix.sx_rtscts = 0 where the pin behaves as DTR when
 hardware handshaking is off. It behaves as the RTS hardware
 handshaking signal when hardware handshaking is selected.
@@ -280,7 +280,7 @@ cable will either be compatible with hardware handshaking or with
 software handshaking. So switching on the fly is not really an
 option.
-I actually prefer to use the "Specialix DTR/RTS pin is RTS" option.
+I actually prefer to use the "specialix.sx_rtscts=1" option.
 This makes the DTR/RTS pin always an RTS pin, and ioctls to
 change DTR are always ignored. I have a cable that is configured
 for this. 
@@ -379,7 +379,5 @@ it doesn't fit in your computer, bring back the card.
            You have to WRITE to the address register to even 
            read-probe a CD186x register. Disable autodetection?
         -- Specialix: any suggestions?
-       - Arbitrary baud rates are not implemented yet. 
-            If you need this, bug me about it. 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 8a4863c4edd4..d79eeda7a699 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -116,7 +116,7 @@ of kilobytes free.  The VM uses this number to compute a pages_min
 value for each lowmem zone in the system.  Each lowmem zone gets 
 a number of reserved free pages based proportionally on its size.
-Some minimal ammount of memory is needed to satisfy PF_MEMALLOC
+Some minimal amount of memory is needed to satisfy PF_MEMALLOC
 allocations; if you set this to lower than 1024KB, your system will
 become subtly broken, and prone to deadlock under high loads.
diff --git a/Documentation/sysfs-rules.txt b/Documentation/sysfs-rules.txt
index 80ef562160bb..6049a2a84dda 100644
--- a/Documentation/sysfs-rules.txt
+++ b/Documentation/sysfs-rules.txt
@@ -3,9 +3,8 @@ Rules on how to access information in the Linux kernel sysfs
 The kernel-exported sysfs exports internal kernel implementation details
 and depends on internal kernel structures and layout. It is agreed upon
 by the kernel developers that the Linux kernel does not provide a stable
-internal API. As sysfs is a direct export of kernel internal
+internal API. Therefore, there are aspects of the sysfs interface that
-structures, the sysfs interface cannot provide a stable interface either;
+may not be stable across kernel releases.
-it may always change along with internal kernel changes.
 To minimize the risk of breaking users of sysfs, which are in most cases
 low-level userspace applications, with a new kernel release, the users
diff --git a/Documentation/telephony/ixj.txt b/Documentation/telephony/ixj.txt
index 621024fd3a18..44d124005bad 100644
--- a/Documentation/telephony/ixj.txt
+++ b/Documentation/telephony/ixj.txt
@@ -305,21 +305,14 @@ driver, like this:
 which will result in the needed drivers getting loaded automatically.
-   g.  if you are planning on using kerneld to automatically load the 
+   g.  if you are planning on having the kernel automatically request
-module for you, then you need to edit /etc/conf.modules and add the 
+the module for you, then you need to edit /etc/conf.modules and add the
 following lines:
        options ixj dspio=0x340 xio=0x330 ixjdebug=0
 If you do this, then when you execute an application that uses the
-module kerneld will load the module for you.  Note that to do this,
+module the kernel will request that it is loaded.
-you need to have your kernel set to support kerneld.  You can check
-for this by looking at /usr/src/linux/.config and you should see this:
-        # Loadable module support
-        #
-        <snip>
-        CONFIG_KMOD=y
  h.  if you want non-root users to be able to read and write to the 
 ixj devices (this is a good idea!) you should do the following:
diff --git a/Documentation/timers/highres.txt b/Documentation/timers/highres.txt
index a73ecf5b4bdb..21332233cef1 100644
--- a/Documentation/timers/highres.txt
+++ b/Documentation/timers/highres.txt
@@ -125,7 +125,7 @@ increase of flexibility and the avoidance of duplicated code across
 architectures justifies the slight increase of the binary size.
 The conversion of an architecture has no functional impact, but allows to
-utilize the high resolution and dynamic tick functionalites without any change
+utilize the high resolution and dynamic tick functionalities without any change
 to the clock event device and timer interrupt code. After the conversion the
 enabling of high resolution timers and dynamic ticks is simply provided by
 adding the kernel/time/Kconfig file to the architecture specific Kconfig and
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt
new file mode 100644
index 000000000000..a4afb560a45b
--- /dev/null
+++ b/Documentation/tracers/mmiotrace.txt
@@ -0,0 +1,164 @@
+                In-kernel memory-mapped I/O tracing
+Home page and links to optional user space tools:
+        http://nouveau.freedesktop.org/wiki/MmioTrace
+MMIO tracing was originally developed by Intel around 2003 for their Fault
+Injection Test Harness. In Dec 2006 - Jan 2007, using the code from Intel,
+Jeff Muizelaar created a tool for tracing MMIO accesses with the Nouveau
+project in mind. Since then many people have contributed.
+Mmiotrace was built for reverse engineering any memory-mapped IO device with
+the Nouveau project as the first real user. Only x86 and x86_64 architectures
+are supported.
+Out-of-tree mmiotrace was originally modified for mainline inclusion and
+ftrace framework by Pekka Paalanen <pq@iki.fi>.
+Preparation
+-----------
+Mmiotrace feature is compiled in by the CONFIG_MMIOTRACE option. Tracing is
+disabled by default, so it is safe to have this set to yes. SMP systems are
+supported, but tracing is unreliable and may miss events if more than one CPU
+is on-line, therefore mmiotrace takes all but one CPU off-line during run-time
+activation. You can re-enable CPUs by hand, but you have been warned, there
+is no way to automatically detect if you are losing events due to CPUs racing.
+Usage Quick Reference
+---------------------
+$ mount -t debugfs debugfs /debug
+$ echo mmiotrace > /debug/tracing/current_tracer
+$ cat /debug/tracing/trace_pipe > mydump.txt &
+Start X or whatever.
+$ echo "X is up" > /debug/tracing/marker
+$ echo none > /debug/tracing/current_tracer
+Check for lost events.
+Usage
+-----
+Make sure debugfs is mounted to /debug. If not, (requires root privileges)
+$ mount -t debugfs debugfs /debug
+Check that the driver you are about to trace is not loaded.
+Activate mmiotrace (requires root privileges):
+$ echo mmiotrace > /debug/tracing/current_tracer
+Start storing the trace:
+$ cat /debug/tracing/trace_pipe > mydump.txt &
+The 'cat' process should stay running (sleeping) in the background.
+Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
+accesses to areas that are ioremapped while mmiotrace is active.
+[Unimplemented feature:]
+During tracing you can place comments (markers) into the trace by
+$ echo "X is up" > /debug/tracing/marker
+This makes it easier to see which part of the (huge) trace corresponds to
+which action. It is recommended to place descriptive markers about what you
+do.
+Shut down mmiotrace (requires root privileges):
+$ echo none > /debug/tracing/current_tracer
+The 'cat' process exits. If it does not, kill it by issuing 'fg' command and
+pressing ctrl+c.
+Check that mmiotrace did not lose events due to a buffer filling up. Either
+$ grep -i lost mydump.txt
+which tells you exactly how many events were lost, or use
+$ dmesg
+to view your kernel log and look for "mmiotrace has lost events" warning. If
+events were lost, the trace is incomplete. You should enlarge the buffers and
+try again. Buffers are enlarged by first seeing how large the current buffers
+are:
+$ cat /debug/tracing/trace_entries
+gives you a number. Approximately double this number and write it back, for
+instance:
+$ echo 128000 > /debug/tracing/trace_entries
+Then start again from the top.
+If you are doing a trace for a driver project, e.g. Nouveau, you should also
+do the following before sending your results:
+$ lspci -vvv > lspci.txt
+$ dmesg > dmesg.txt
+$ tar zcf pciid-nick-mmiotrace.tar.gz mydump.txt lspci.txt dmesg.txt
+and then send the .tar.gz file. The trace compresses considerably. Replace
+"pciid" and "nick" with the PCI ID or model name of your piece of hardware
+under investigation and your nick name.
+How Mmiotrace Works
+-------------------
+Access to hardware IO-memory is gained by mapping addresses from PCI bus by
+calling one of the ioremap_*() functions. Mmiotrace is hooked into the
+__ioremap() function and gets called whenever a mapping is created. Mapping is
+an event that is recorded into the trace log. Note, that ISA range mappings
+are not caught, since the mapping always exists and is returned directly.
+MMIO accesses are recorded via page faults. Just before __ioremap() returns,
+the mapped pages are marked as not present. Any access to the pages causes a
+fault. The page fault handler calls mmiotrace to handle the fault. Mmiotrace
+marks the page present, sets TF flag to achieve single stepping and exits the
+fault handler. The instruction that faulted is executed and debug trap is
+entered. Here mmiotrace again marks the page as not present. The instruction
+is decoded to get the type of operation (read/write), data width and the value
+read or written. These are stored to the trace log.
+Setting the page present in the page fault handler has a race condition on SMP
+machines. During the single stepping other CPUs may run freely on that page
+and events can be missed without a notice. Re-enabling other CPUs during
+tracing is discouraged.
+Trace Log Format
+----------------
+The raw log is text and easily filtered with e.g. grep and awk. One record is
+one line in the log. A record starts with a keyword, followed by keyword
+dependant arguments. Arguments are separated by a space, or continue until the
+end of line. The format for version 20070824 is as follows:
+Explanation     Keyword Space separated arguments
+---------------------------------------------------------------------------
+read event      R       width, timestamp, map id, physical, value, PC, PID
+write event     W       width, timestamp, map id, physical, value, PC, PID
+ioremap event   MAP     timestamp, map id, physical, virtual, length, PC, PID
+iounmap event   UNMAP   timestamp, map id, PC, PID
+marker          MARK    timestamp, text
+version         VERSION the string "20070824"
+info for reader LSPCI   one line from lspci -v
+PCI address map PCIDEV  space separated /proc/bus/pci/devices data
+unk. opcode     UNKNOWN timestamp, map id, physical, data, PC, PID
+Timestamp is in seconds with decimals. Physical is a PCI bus address, virtual
+is a kernel virtual address. Width is the data width in bytes and value is the
+data value. Map id is an arbitrary id number identifying the mapping that was
+used in an operation. PC is the program counter and PID is process id. PC is
+zero if it is not recorded. PID is always zero as tracing MMIO accesses
+originating in user space memory is not yet supported.
+For instance, the following awk filter will pass all 32-bit writes that target
+physical addresses in the range [0xfb73ce40, 0xfb800000[
+$ awk '/W 4 / { adr=strtonum($5); if (adr >= 0xfb73ce40 &&
+adr < 0xfb800000) print; }'
+Tools for Developers
+--------------------
+The user space tools include utilities for:
+- replacing numeric addresses and values with hardware register names
+- replaying MMIO logs, i.e., re-executing the recorded writes
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index b0472ac5226a..f866c72291bf 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -218,9 +218,35 @@ If use of such macros is not convenient, another option is to use memcpy(),
 where the source or destination (or both) are of type u8* or unsigned char*.
 Due to the byte-wise nature of this operation, unaligned accesses are avoided.
+Alignment vs. Networking
+========================
+On architectures that require aligned loads, networking requires that the IP
+header is aligned on a four-byte boundary to optimise the IP stack. For
+regular ethernet hardware, the constant NET_IP_ALIGN is used. On most
+architectures this constant has the value 2 because the normal ethernet
+header is 14 bytes long, so in order to get proper alignment one needs to
+DMA to an address which can be expressed as 4*n + 2. One notable exception
+here is powerpc which defines NET_IP_ALIGN to 0 because DMA to unaligned
+addresses can be very expensive and dwarf the cost of unaligned loads.
+For some ethernet hardware that cannot DMA to unaligned addresses like
+4*n+2 or non-ethernet hardware, this can be a problem, and it is then
+required to copy the incoming frame into an aligned buffer. Because this is
+unnecessary on architectures that can do unaligned accesses, the code can be
+made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so:
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+        skb = original skb
+#else
+        skb = copy skb
+#endif
 --
-Author: Daniel Drake <dsd@gentoo.org>
+Authors: Daniel Drake <dsd@gentoo.org>,
+         Johannes Berg <johannes@sipsolutions.net>
 With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt,
-Johannes Berg, Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock,
+Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz,
-Uli Kunitz, Vadim Lobanov
+Vadim Lobanov
diff --git a/Documentation/usb/authorization.txt b/Documentation/usb/authorization.txt
index 2af400609498..381b22ee7834 100644
--- a/Documentation/usb/authorization.txt
+++ b/Documentation/usb/authorization.txt
@@ -8,7 +8,7 @@ not) in a system. This feature will allow you to implement a lock-down
 of USB devices, fully controlled by user space.
 As of now, when a USB device is connected it is configured and
-it's interfaces inmediately made available to the users. With this
+its interfaces are immediately made available to the users.  With this
 modification, only if root authorizes the device to be configured will
 then it be possible to use it.
diff --git a/Documentation/usb/gadget_serial.txt b/Documentation/usb/gadget_serial.txt
index 815f5c2301ff..9b22bd14c348 100644
--- a/Documentation/usb/gadget_serial.txt
+++ b/Documentation/usb/gadget_serial.txt
@@ -1,6 +1,7 @@
                 Linux Gadget Serial Driver v2.0
                           11/20/2004
+                  (updated 8-May-2008 for v2.3)
 License and Disclaimer
@@ -31,7 +32,7 @@ Prerequisites
 -------------
 Versions of the gadget serial driver are available for the
 2.4 Linux kernels, but this document assumes you are using
-version 2.0 or later of the gadget serial driver in a 2.6
+version 2.3 or later of the gadget serial driver in a 2.6
 Linux kernel.
 This document assumes that you are familiar with Linux and
@@ -40,6 +41,12 @@ standard utilities, use minicom and HyperTerminal, and work with
 USB and serial devices.  It also assumes you configure the Linux
 gadget and usb drivers as modules.
+With version 2.3 of the driver, major and minor device nodes are
+no longer statically defined.  Your Linux based system should mount
+sysfs in /sys, and use "mdev" (in Busybox) or "udev" to make the
+/dev nodes matching the sysfs /sys/class/tty files.
 Overview
 --------
@@ -104,15 +111,8 @@ driver.  All this are listed under "USB Gadget Support" when
 configuring the kernel.  Then rebuild and install the kernel or
 modules.
-The gadget serial driver uses major number 127, for now.  So you
-will need to create a device node for it, like this:
-  mknod /dev/ttygserial c 127 0
-You only need to do this once.
 Then you must load the gadget serial driver.  To load it as an
-ACM device, do this:
+ACM device (recommended for interoperability), do this:
  modprobe g_serial use_acm=1
@@ -125,6 +125,23 @@ controller driver.  This must be done each time you reboot the gadget
 side Linux system.  You can add this to the start up scripts, if
 desired.
+Your system should use mdev (from busybox) or udev to make the
+device nodes.  After this gadget driver has been set up you should
+then see a /dev/ttyGS0 node:
+  # ls -l /dev/ttyGS0 | cat
+  crw-rw----    1 root     root     253,   0 May  8 14:10 /dev/ttyGS0
+  #
+Note that the major number (253, above) is system-specific.  If
+you need to create /dev nodes by hand, the right numbers to use
+will be in the /sys/class/tty/ttyGS0/dev file.
+When you link this gadget driver early, perhaps even statically,
+you may want to set up an /etc/inittab entry to run "getty" on it.
+The /dev/ttyGS0 line should work like most any other serial port.
 If gadget serial is loaded as an ACM device you will want to use
 either the Windows or Linux ACM driver on the host side.  If gadget
 serial is loaded as a bulk in/out device, you will want to use the
diff --git a/Documentation/usb/persist.txt b/Documentation/usb/persist.txt
index d56cb1a11550..074b159b77c2 100644
--- a/Documentation/usb/persist.txt
+++ b/Documentation/usb/persist.txt
@@ -81,8 +81,11 @@ re-enumeration shows that the device now attached to that port has the
 same descriptors as before, including the Vendor and Product IDs, then
 the kernel continues to use the same device structure.  In effect, the
 kernel treats the device as though it had merely been reset instead of
-unplugged.  The same thing happens if the host controller is in the
+unplugged.
-expected state but a USB device was unplugged and then replugged.
+The same thing happens if the host controller is in the expected state
+but a USB device was unplugged and then replugged, or if a USB device
+fails to carry out a normal resume.
 If no device is now attached to the port, or if the descriptors are
 different from what the kernel remembers, then the treatment is what
diff --git a/Documentation/usb/uhci.txt b/Documentation/usb/uhci.txt
deleted file mode 100644
index 2f25952c86c6..000000000000
--- a/Documentation/usb/uhci.txt
+++ /dev/null
@@ -1,165 +0,0 @@
-Specification and Internals for the New UHCI Driver (Whitepaper...)
-        brought to you by
-        Georg Acher, acher@in.tum.de (executive slave) (base guitar)
-        Deti Fliegl, deti@fliegl.de (executive slave) (lead voice)
-        Thomas Sailer, sailer@ife.ee.ethz.ch (chief consultant) (cheer leader)
- 
-        $Id: README.uhci,v 1.1 1999/12/14 14:03:02 fliegl Exp $
-This document and the new uhci sources can be found on
-                http://hotswap.in.tum.de/usb
-1. General issues
-1.1 Why a new UHCI driver, we already have one?!?
-Correct, but its internal structure got more and more mixed up by the (still
-ongoing) efforts to get isochronous transfers (ISO) to work.
-Since there is an increasing need for reliable ISO-transfers (especially 
-for USB-audio needed by TS and for a DAB-USB-Receiver build by GA and DF), 
-this state was a bit unsatisfying in our opinion, so we've decided (based
-on knowledge and experiences with the old UHCI driver) to start 
-from scratch with a new approach, much simpler but at the same time more 
-powerful.
-It is inspired by the way Win98/Win2000 handles USB requests via URBs,
-but it's definitely 100% free of MS-code and doesn't crash while 
-unplugging an used ISO-device like Win98 ;-)
-Some code for HW setup and root hub management was taken from the 
-original UHCI driver, but heavily modified to fit into the new code.
-The invention of the basic concept, and major coding were completed in two 
-days (and nights) on the 16th and 17th of October 1999, now known as the
-great USB-October-Revolution started by GA, DF, and TS ;-)
-Since the concept is in no way UHCI dependent, we hope that it will also be 
-transferred to the OHCI-driver, so both drivers share a common API.
-1.2. Advantages and disadvantages
-+ All USB transfer types work now!
-+ Asynchronous operation
-+ Simple, but powerful interface (only two calls for start and cancel)
-+ Easy migration to the new API, simplified by a compatibility API
-+ Simple usage of ISO transfers
-+ Automatic linking of requests
-+ ISO transfers allow variable length for each frame and striping
-+ No CPU dependent and non-portable atomic memory access, no asm()-inlines
-+ Tested on x86 and Alpha
- Rewriting for ISO transfers needed
-1.3. Is there some compatibility to the old API?
-Yes, but only for control, bulk and interrupt transfers. We've implemented 
-some wrapper calls for these transfer types. The usbcore works fine with 
-these wrappers. For ISO there's no compatibility, because the old ISO-API 
-and its semantics were unnecessary complicated in our opinion.
-1.4. What's really working?
-As said above, CTRL and BULK already work fine even with the wrappers,
-so legacy code wouldn't notice the change.
-Regarding to Thomas, ISO transfers now run stable with USB audio.
-INT transfers (e.g. mouse driver) work fine, too.
-1.5. Are there any bugs?
-No ;-)
-Hm...
-Well, of course this implementation needs extensive testing on all available
-hardware, but we believe that any fixes shouldn't harm the overall concept.
-1.6. What should be done next?
-A large part of the request handling seems to be identical for UHCI and 
-OHCI, so it would be a good idea to extract the common parts and have only 
-the HW specific stuff in uhci.c. Furthermore, all other USB device drivers
-should need URBification, if they use isochronous or interrupt transfers.
-One thing missing in the current implementation (and the old UHCI driver) 
-is fair queueing for BULK transfers. Since this would need (in principle) 
-the alteration of already constructed TD chains (to switch from depth to 
-breadth execution), another way has to be found. Maybe some simple 
-heuristics work with the same effect.
---------------------------------------------------------------------------
-2. Internal structure and mechanisms
-To get quickly familiar with the internal structures, here's a short
-description how the new UHCI driver works. However, the ultimate source of
-truth is only uhci.c!
-2.1. Descriptor structure (QHs and TDs)
-During initialization, the following skeleton is allocated in init_skel:
-         framespecific           |           common chain     
-framelist[]
-[  0 ]-----> TD --> TD -------\
-[  1 ]-----> TD --> TD --------> TD ----> QH -------> QH -------> QH ---> NULL
-  ...        TD --> TD -------/
-[1023]-----> TD --> TD ------/
-             
-             ^^     ^^           ^^       ^^          ^^          ^^
-   1024 TDs for   7 TDs for    1 TD for   Start of    Start of    End Chain
-            ISO  INT (2-128ms) 1ms-INT    CTRL Chain  BULK Chain
-For each CTRL or BULK transfer a new QH is allocated and the containing data
-transfers are appended as (vertical) TDs. After building the whole QH with its
-dangling TDs, the QH is inserted before the BULK Chain QH (for CTRL) or
-before the End Chain QH (for BULK). Since only the QH->next pointers are
-affected, no atomic memory operation is required. The three QHs in the
-common chain are never equipped with TDs!
-For ISO or INT, the TD for each frame is simply inserted into the appropriate
-ISO/INT-TD-chain for the desired frame. The 7 skeleton INT-TDs are scattered
-among the 1024 frames similar to the old UHCI driver.
-For CTRL/BULK/ISO, the last TD in the transfer has the IOC-bit set. For INT,
-every TD (there is only one...) has the IOC-bit set.
-Besides the data for the UHCI controller (2 or 4 32bit words), the descriptors
-are double-linked through the .vertical and .horizontal elements in the 
-SW data of the descriptor (using the double-linked list structures and 
-operations), but SW-linking occurs only in closed domains, i.e. for each of
-the 1024 ISO-chains and the 8 INT-chains there is a closed cycle. This 
-simplifies all insertions and unlinking operations and avoids costly 
-bus_to_virt()-calls.
-2.2. URB structure and linking to QH/TDs
-During assembly of the QH and TDs of the requested action, these descriptors
-are stored in urb->urb_list, so the allocated QH/TD descriptors are bound to
-this URB.
-If the assembly was successful and the descriptors were added to the HW chain,
-the corresponding URB is inserted into a global URB list for this controller.
-This list stores all pending URBs.
-2.3. Interrupt processing
-Since UHCI provides no means to directly detect completed transactions, the
-following is done in each UHCI interrupt (uhci_interrupt()):
-For each URB in the pending queue (process_urb()), the ACTIVE-flag of the 
-associated TDs are processed (depending on the transfer type 
-process_{transfer|interrupt|iso}()). If the TDs are not active anymore, 
-they indicate the completion of the transaction and the status is calculated. 
-Inactive QH/TDs are removed from the HW chain (since the host controller
-already removed the TDs from the QH, no atomic access is needed) and 
-eventually the URB is marked as completed (OK or errors) and removed from the 
-pending queue. Then the next linked URB is submitted. After (or immediately 
-before) that, the completion handler is called.
-2.4. Unlinking URBs
-First, all QH/TDs stored in the URB are unlinked from the HW chain. 
-To ensure that the host controller really left a vertical TD chain, we 
-wait for one frame. After that, the TDs are physically destroyed.
-2.5. URB linking and the consequences
-Since URBs can be linked and the corresponding submit_urb is called in
-the UHCI-interrupt, all work associated with URB/QH/TD assembly has to be
-interrupt save. This forces kmalloc to use GFP_ATOMIC in the interrupt.
diff --git a/Documentation/video4linux/CARDLIST.au0828 b/Documentation/video4linux/CARDLIST.au0828
index aaae360312e4..eedc399e8deb 100644
--- a/Documentation/video4linux/CARDLIST.au0828
+++ b/Documentation/video4linux/CARDLIST.au0828
@@ -1,4 +1,5 @@
  0 -> Unknown board                            (au0828)
-  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200]
+  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200,2040:7210,2040:7217,2040:721b,2040:721f,2040:7280,0fd9:0008]
  2 -> Hauppauge HVR850                         (au0828)        [2040:7240]
  3 -> DViCO FusionHDTV USB                     (au0828)        [0fe9:d620]
+  4 -> Hauppauge HVR950Q rev xxF8               (au0828)        [2040:7201,2040:7211,2040:7281]
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 929b90c8387f..f0e613ba55b8 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -5,6 +5,7 @@
  4 -> DViCO FusionHDTV5 Express                           [18ac:d500]
  5 -> Hauppauge WinTV-HVR1500Q                            [0070:7790,0070:7797]
  6 -> Hauppauge WinTV-HVR1500                             [0070:7710,0070:7717]
-  7 -> Hauppauge WinTV-HVR1200                             [0070:71d1]
+  7 -> Hauppauge WinTV-HVR1200                             [0070:71d1,0070:71d3]
  8 -> Hauppauge WinTV-HVR1700                             [0070:8101]
  9 -> Hauppauge WinTV-HVR1400                             [0070:8010]
+ 10 -> DViCO FusionHDTV7 Dual Express                      [18ac:d618]
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index 543957346469..7cf5685d3645 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -60,7 +60,7 @@
 59 -> DViCO FusionHDTV 5 PCI nano                         [18ac:d530]
 60 -> Pinnacle Hybrid PCTV                                [12ab:1788]
 61 -> Winfast TV2000 XP Global                            [107d:6f18]
- 62 -> PowerColor Real Angel 330                           [14f1:ea3d]
+ 62 -> PowerColor RA330                                    [14f1:ea3d]
 63 -> Geniatech X8000-MT DVBT                             [14f1:8852]
 64 -> DViCO FusionHDTV DVB-T PRO                          [18ac:db30]
 65 -> DViCO FusionHDTV 7 Gold                             [18ac:d610]
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index f40e09296f30..89c7f32abf9f 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -1,17 +1,59 @@
  0 -> Unknown EM2800 video grabber             (em2800)        [eb1a:2800]
-  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2750,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
+  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
  2 -> Terratec Cinergy 250 USB                 (em2820/em2840) [0ccd:0036]
  3 -> Pinnacle PCTV USB 2                      (em2820/em2840) [2304:0208]
  4 -> Hauppauge WinTV USB 2                    (em2820/em2840) [2040:4200,2040:4201]
  5 -> MSI VOX USB 2.0                          (em2820/em2840)
  6 -> Terratec Cinergy 200 USB                 (em2800)
-  7 -> Leadtek Winfast USB II                   (em2800)
+  7 -> Leadtek Winfast USB II                   (em2800)        [0413:6023]
  8 -> Kworld USB2800                           (em2800)
  9 -> Pinnacle Dazzle DVC 90/DVC 100           (em2820/em2840) [2304:0207,2304:021a]
- 10 -> Hauppauge WinTV HVR 900                  (em2880)        [2040:6500,2040:6502]
+ 10 -> Hauppauge WinTV HVR 900                  (em2880)        [2040:6500]
 11 -> Terratec Hybrid XS                       (em2880)        [0ccd:0042]
 12 -> Kworld PVR TV 2800 RF                    (em2820/em2840)
 13 -> Terratec Prodigy XS                      (em2880)        [0ccd:0047]
 14 -> Pixelview Prolink PlayTV USB 2.0         (em2820/em2840)
 15 -> V-Gear PocketTV                          (em2800)
- 16 -> Hauppauge WinTV HVR 950                  (em2880)        [2040:6513]
+ 16 -> Hauppauge WinTV HVR 950                  (em2883)        [2040:6513,2040:6517,2040:651b,2040:651f]
+ 17 -> Pinnacle PCTV HD Pro Stick               (em2880)        [2304:0227]
+ 18 -> Hauppauge WinTV HVR 900 (R2)             (em2880)        [2040:6502]
+ 19 -> PointNix Intra-Oral Camera               (em2860)
+ 20 -> AMD ATI TV Wonder HD 600                 (em2880)        [0438:b002]
+ 21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800)        [eb1a:2801]
+ 22 -> Unknown EM2750/EM2751 webcam grabber     (em2750)        [eb1a:2750,eb1a:2751]
+ 23 -> Huaqi DLCW-130                           (em2750)
+ 24 -> D-Link DUB-T210 TV Tuner                 (em2820/em2840) [2001:f112]
+ 25 -> Gadmei UTV310                            (em2820/em2840)
+ 26 -> Hercules Smart TV USB 2.0                (em2820/em2840)
+ 27 -> Pinnacle PCTV USB 2 (Philips FM1216ME)   (em2820/em2840)
+ 28 -> Leadtek Winfast USB II Deluxe            (em2820/em2840)
+ 29 -> Pinnacle Dazzle DVC 100                  (em2820/em2840)
+ 30 -> Videology 20K14XUSB USB2.0               (em2820/em2840)
+ 31 -> Usbgear VD204v9                          (em2821)
+ 32 -> Supercomp USB 2.0 TV                     (em2821)
+ 33 -> SIIG AVTuner-PVR/Prolink PlayTV USB 2.0  (em2821)
+ 34 -> Terratec Cinergy A Hybrid XS             (em2860)        [0ccd:004f]
+ 35 -> Typhoon DVD Maker                        (em2860)
+ 36 -> NetGMBH Cam                              (em2860)
+ 37 -> Gadmei UTV330                            (em2860)
+ 38 -> Yakumo MovieMixer                        (em2861)
+ 39 -> KWorld PVRTV 300U                        (em2861)        [eb1a:e300]
+ 40 -> Plextor ConvertX PX-TV100U               (em2861)        [093b:a005]
+ 41 -> Kworld 350 U DVB-T                       (em2870)        [eb1a:e350]
+ 42 -> Kworld 355 U DVB-T                       (em2870)        [eb1a:e355,eb1a:e357]
+ 43 -> Terratec Cinergy T XS                    (em2870)        [0ccd:0043]
+ 44 -> Terratec Cinergy T XS (MT2060)           (em2870)
+ 45 -> Pinnacle PCTV DVB-T                      (em2870)
+ 46 -> Compro, VideoMate U3                     (em2870)        [185b:2870]
+ 47 -> KWorld DVB-T 305U                        (em2880)        [eb1a:e305]
+ 48 -> KWorld DVB-T 310U                        (em2880)
+ 49 -> MSI DigiVox A/D                          (em2880)        [eb1a:e310]
+ 50 -> MSI DigiVox A/D II                       (em2880)        [eb1a:e320]
+ 51 -> Terratec Hybrid XS Secam                 (em2880)        [0ccd:004c]
+ 52 -> DNT DA2 Hybrid                           (em2881)
+ 53 -> Pinnacle Hybrid Pro                      (em2881)
+ 54 -> Kworld VS-DVB-T 323UR                    (em2882)        [eb1a:e323]
+ 55 -> Terratec Hybrid XS (em2882)              (em2882)        [0ccd:005e]
+ 56 -> Pinnacle Hybrid Pro (2)                  (em2882)        [2304:0226]
+ 57 -> Kworld PlusTV HD Hybrid 330              (em2883)        [eb1a:a316]
+ 58 -> Compro VideoMate ForYou/Stereo           (em2820/em2840) [185b:2041]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 67937df1e974..39868af9cf9f 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -37,7 +37,7 @@
 36 -> UPMOST PURPLE TV                         [12ab:0800]
 37 -> Items MuchTV Plus / IT-005
 38 -> Terratec Cinergy 200 TV                  [153b:1152]
- 39 -> LifeView FlyTV Platinum Mini             [5168:0212,4e42:0212]
+ 39 -> LifeView FlyTV Platinum Mini             [5168:0212,4e42:0212,5169:1502]
 40 -> Compro VideoMate TV PVR/FM               [185b:c100]
 41 -> Compro VideoMate TV Gold+                [185b:c100]
 42 -> Sabrent SBT-TVFM (saa7130)
@@ -128,7 +128,7 @@
 127 -> Beholder BeholdTV 507 FM/RDS / BeholdTV 509 FM [0000:5071,0000:507B,5ace:5070,5ace:5090]
 128 -> Beholder BeholdTV Columbus TVFM          [0000:5201]
 129 -> Beholder BeholdTV 607 / BeholdTV 609     [5ace:6070,5ace:6071,5ace:6072,5ace:6073,5ace:6090,5ace:6091,5ace:6092,5ace:6093]
-130 -> Beholder BeholdTV M6 / BeholdTV M6 Extra [5ace:6190,5ace:6193,5ace:6191]
+130 -> Beholder BeholdTV M6                     [5ace:6190]
 131 -> Twinhan Hybrid DTV-DVB 3056 PCI          [1822:0022]
 132 -> Genius TVGO AM11MCE
 133 -> NXP Snake DVB-S reference design
@@ -141,3 +141,7 @@
 140 -> Avermedia DVB-S Pro A700                 [1461:a7a1]
 141 -> Avermedia DVB-S Hybrid+FM A700           [1461:a7a2]
 142 -> Beholder BeholdTV H6                     [5ace:6290]
+143 -> Beholder BeholdTV M63                    [5ace:6191]
+144 -> Beholder BeholdTV M6 Extra               [5ace:6193]
+145 -> AVerMedia MiniPCI DVB-T Hybrid M103      [1461:f636]
+146 -> ASUSTeK P7131 Analog
diff --git a/Documentation/video4linux/cx18.txt b/Documentation/video4linux/cx18.txt
index 077d56ec3f3d..914cb7e734a2 100644
--- a/Documentation/video4linux/cx18.txt
+++ b/Documentation/video4linux/cx18.txt
@@ -1,34 +1,30 @@
 Some notes regarding the cx18 driver for the Conexant CX23418 MPEG
 encoder chip:
-1) The only hardware currently supported is the Hauppauge HVR-1600.
+1) Currently supported are:
-2) Some people have problems getting the i2c bus to work. Cause unknown.
+        - Hauppauge HVR-1600
-   The symptom is that the eeprom cannot be read and the card is
+        - Compro VideoMate H900
-   unusable.
+        - Yuan MPC718
+        - Conexant Raptor PAL/SECAM devkit
-3) The audio from the analog tuner is mono only. Probably caused by
+2) Some people have problems getting the i2c bus to work.
-   incorrect audio register information in the datasheet. We are
+   The symptom is that the eeprom cannot be read and the card is
-   waiting for updated information from Conexant.
+   unusable. This is probably fixed, but if you have problems
+   then post to the video4linux or ivtv-users mailinglist.
-4) VBI (raw or sliced) has not yet been implemented.
+3) VBI (raw or sliced) has not yet been implemented.
-5) MPEG indexing is not yet implemented.
+4) MPEG indexing is not yet implemented.
-6) The driver is still a bit rough around the edges, this should
+5) The driver is still a bit rough around the edges, this should
   improve over time.
 Firmware:
-The firmware needs to be extracted from the Windows Hauppauge HVR-1600
+You can obtain the firmware files here:
-driver, available here:
-http://hauppauge.lightpath.net/software/install_cd/hauppauge_cd_3.4d1.zip
-Unzip, then copy the following files to the firmware directory
+http://dl.ivtvdriver.org/ivtv/firmware/cx18-firmware.tar.gz
-and rename them as follows:
-Drivers/Driver18/hcw18apu.rom -> v4l-cx23418-apu.fw
+Untar and copy the .fw files to your firmware directory.
-Drivers/Driver18/hcw18enc.rom -> v4l-cx23418-cpu.fw
-Drivers/Driver18/hcw18mlC.rom -> v4l-cx23418-dig.fw
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
new file mode 100644
index 000000000000..bcaf4ab383be
--- /dev/null
+++ b/Documentation/video4linux/gspca.txt
@@ -0,0 +1,243 @@
+List of the webcams known by gspca.
+The modules are:
+        gspca_main      main driver
+        gspca_xxxx      subdriver module with xxxx as follows
+xxxx            vend:prod
+----
+spca501         0000:0000       MystFromOri Unknow Camera
+spca501         040a:0002       Kodak DVC-325
+spca500         040a:0300       Kodak EZ200
+zc3xx           041e:041e       Creative WebCam Live!
+spca500         041e:400a       Creative PC-CAM 300
+sunplus         041e:400b       Creative PC-CAM 600
+sunplus         041e:4012       PC-Cam350
+sunplus         041e:4013       Creative Pccam750
+zc3xx           041e:4017       Creative Webcam Mobile PD1090
+spca508         041e:4018       Creative Webcam Vista (PD1100)
+spca561         041e:401a       Creative Webcam Vista (PD1100)
+zc3xx           041e:401c       Creative NX
+spca505         041e:401d       Creative Webcam NX ULTRA
+zc3xx           041e:401e       Creative Nx Pro
+zc3xx           041e:401f       Creative Webcam Notebook PD1171
+pac207          041e:4028       Creative Webcam Vista Plus
+zc3xx           041e:4029       Creative WebCam Vista Pro
+zc3xx           041e:4034       Creative Instant P0620
+zc3xx           041e:4035       Creative Instant P0620D
+zc3xx           041e:4036       Creative Live !
+zc3xx           041e:403a       Creative Nx Pro 2
+spca561         041e:403b       Creative Webcam Vista (VF0010)
+zc3xx           041e:4051       Creative Live!Cam Notebook Pro (VF0250)
+ov519           041e:4052       Creative Live! VISTA IM
+zc3xx           041e:4053       Creative Live!Cam Video IM
+ov519           041e:405f       Creative Live! VISTA VF0330
+ov519           041e:4060       Creative Live! VISTA VF0350
+ov519           041e:4061       Creative Live! VISTA VF0400
+ov519           041e:4064       Creative Live! VISTA VF0420
+ov519           041e:4068       Creative Live! VISTA VF0470
+spca561         0458:7004       Genius VideoCAM Express V2
+sunplus         0458:7006       Genius Dsc 1.3 Smart
+zc3xx           0458:7007       Genius VideoCam V2
+zc3xx           0458:700c       Genius VideoCam V3
+zc3xx           0458:700f       Genius VideoCam Web V2
+sonixj          0458:7025       Genius Eye 311Q
+sonixj          045e:00f5       MicroSoft VX3000
+sonixj          045e:00f7       MicroSoft VX1000
+ov519           045e:028c       Micro$oft xbox cam
+spca508         0461:0815       Micro Innovation IC200
+sunplus         0461:0821       Fujifilm MV-1
+zc3xx           0461:0a00       MicroInnovation WebCam320
+spca500         046d:0890       Logitech QuickCam traveler
+vc032x          046d:0892       Logitech Orbicam
+vc032x          046d:0896       Logitech Orbicam
+zc3xx           046d:08a0       Logitech QC IM
+zc3xx           046d:08a1       Logitech QC IM 0x08A1 +sound
+zc3xx           046d:08a2       Labtec Webcam Pro
+zc3xx           046d:08a3       Logitech QC Chat
+zc3xx           046d:08a6       Logitech QCim
+zc3xx           046d:08a7       Logitech QuickCam Image
+zc3xx           046d:08a9       Logitech Notebook Deluxe
+zc3xx           046d:08aa       Labtec Webcam  Notebook
+zc3xx           046d:08ac       Logitech QuickCam Cool
+zc3xx           046d:08ad       Logitech QCCommunicate STX
+zc3xx           046d:08ae       Logitech QuickCam for Notebooks
+zc3xx           046d:08af       Logitech QuickCam Cool
+zc3xx           046d:08b9       Logitech QC IM ???
+zc3xx           046d:08d7       Logitech QCam STX
+zc3xx           046d:08d9       Logitech QuickCam IM/Connect
+zc3xx           046d:08d8       Logitech Notebook Deluxe
+zc3xx           046d:08da       Logitech QuickCam Messenger
+zc3xx           046d:08dd       Logitech QuickCam for Notebooks
+spca500         046d:0900       Logitech Inc. ClickSmart 310
+spca500         046d:0901       Logitech Inc. ClickSmart 510
+sunplus         046d:0905       Logitech ClickSmart 820
+tv8532          046d:0920       QC Express
+tv8532          046d:0921       Labtec Webcam
+spca561         046d:0928       Logitech QC Express Etch2
+spca561         046d:0929       Labtec Webcam Elch2
+spca561         046d:092a       Logitech QC for Notebook
+spca561         046d:092b       Labtec Webcam Plus
+spca561         046d:092c       Logitech QC chat Elch2
+spca561         046d:092d       Logitech QC Elch2
+spca561         046d:092e       Logitech QC Elch2
+spca561         046d:092f       Logitech QC Elch2
+sunplus         046d:0960       Logitech ClickSmart 420
+sunplus         0471:0322       Philips DMVC1300K
+zc3xx           0471:0325       Philips SPC 200 NC
+zc3xx           0471:0326       Philips SPC 300 NC
+sonixj          0471:0327       Philips SPC 600 NC
+sonixj          0471:0328       Philips SPC 700 NC
+zc3xx           0471:032d       Philips spc210nc
+zc3xx           0471:032e       Philips spc315nc
+sonixj          0471:0330       Philips SPC 710NC
+spca501         0497:c001       Smile International
+sunplus         04a5:3003       Benq DC 1300
+sunplus         04a5:3008       Benq DC 1500
+sunplus         04a5:300a       Benq DC3410
+spca500         04a5:300c       Benq DC1016
+sunplus         04f1:1001       JVC GC A50
+spca561         04fc:0561       Flexcam 100
+sunplus         04fc:500c       Sunplus CA500C
+sunplus         04fc:504a       Aiptek Mini PenCam 1.3
+sunplus         04fc:504b       Maxell MaxPocket LE 1.3
+sunplus         04fc:5330       Digitrex 2110
+sunplus         04fc:5360       Sunplus Generic
+spca500         04fc:7333       PalmPixDC85
+sunplus         04fc:ffff       Pure DigitalDakota
+spca501         0506:00df       3Com HomeConnect Lite
+sunplus         052b:1513       Megapix V4
+tv8532          0545:808b       Veo Stingray
+tv8532          0545:8333       Veo Stingray
+sunplus         0546:3155       Polaroid PDC3070
+sunplus         0546:3191       Polaroid Ion 80
+sunplus         0546:3273       Polaroid PDC2030
+ov519           054c:0154       Sonny toy4
+ov519           054c:0155       Sonny toy5
+zc3xx           055f:c005       Mustek Wcam300A
+spca500         055f:c200       Mustek Gsmart 300
+sunplus         055f:c211       Kowa Bs888e Microcamera
+spca500         055f:c220       Gsmart Mini
+sunplus         055f:c230       Mustek Digicam 330K
+sunplus         055f:c232       Mustek MDC3500
+sunplus         055f:c360       Mustek DV4000 Mpeg4
+sunplus         055f:c420       Mustek gSmart Mini 2
+sunplus         055f:c430       Mustek Gsmart LCD 2
+sunplus         055f:c440       Mustek DV 3000
+sunplus         055f:c520       Mustek gSmart Mini 3
+sunplus         055f:c530       Mustek Gsmart LCD 3
+sunplus         055f:c540       Gsmart D30
+sunplus         055f:c630       Mustek MDC4000
+sunplus         055f:c650       Mustek MDC5500Z
+zc3xx           055f:d003       Mustek WCam300A
+zc3xx           055f:d004       Mustek WCam300 AN
+conex           0572:0041       Creative Notebook cx11646
+ov519           05a9:0519       OmniVision
+ov519           05a9:0530       OmniVision
+ov519           05a9:4519       OmniVision
+ov519           05a9:8519       OmniVision
+sunplus         05da:1018       Digital Dream Enigma 1.3
+stk014          05e1:0893       Syntek DV4000
+spca561         060b:a001       Maxell Compact Pc PM3
+zc3xx           0698:2003       CTX M730V built in
+spca500         06bd:0404       Agfa CL20
+spca500         06be:0800       Optimedia
+sunplus         06d6:0031       Trust 610 LCD PowerC@m Zoom
+spca506         06e1:a190       ADS Instant VCD
+spca508         0733:0110       ViewQuest VQ110
+spca508         0130:0130       Clone Digital Webcam 11043
+spca501         0733:0401       Intel Create and Share
+spca501         0733:0402       ViewQuest M318B
+spca505         0733:0430       Intel PC Camera Pro
+sunplus         0733:1311       Digital Dream Epsilon 1.3
+sunplus         0733:1314       Mercury 2.1MEG Deluxe Classic Cam
+sunplus         0733:2211       Jenoptik jdc 21 LCD
+sunplus         0733:2221       Mercury Digital Pro 3.1p
+sunplus         0733:3261       Concord 3045 spca536a
+sunplus         0733:3281       Cyberpix S550V
+spca506         0734:043b       3DeMon USB Capture aka
+spca500         084d:0003       D-Link DSC-350
+spca500         08ca:0103       Aiptek PocketDV
+sunplus         08ca:0104       Aiptek PocketDVII 1.3
+sunplus         08ca:0106       Aiptek Pocket DV3100+
+sunplus         08ca:2008       Aiptek Mini PenCam 2 M
+sunplus         08ca:2010       Aiptek PocketCam 3M
+sunplus         08ca:2016       Aiptek PocketCam 2 Mega
+sunplus         08ca:2018       Aiptek Pencam SD 2M
+sunplus         08ca:2020       Aiptek Slim 3000F
+sunplus         08ca:2022       Aiptek Slim 3200
+sunplus         08ca:2024       Aiptek DV3500 Mpeg4
+sunplus         08ca:2028       Aiptek PocketCam4M
+sunplus         08ca:2040       Aiptek PocketDV4100M
+sunplus         08ca:2042       Aiptek PocketDV5100
+sunplus         08ca:2050       Medion MD 41437
+sunplus         08ca:2060       Aiptek PocketDV5300
+tv8532          0923:010f       ICM532 cams
+mars            093a:050f       Mars-Semi Pc-Camera
+pac207          093a:2460       PAC207 Qtec Webcam 100
+pac207          093a:2463       Philips spc200nc pac207
+pac207          093a:2464       Labtec Webcam 1200
+pac207          093a:2468       PAC207
+pac207          093a:2470       Genius GF112
+pac207          093a:2471       PAC207 Genius VideoCam ge111
+pac207          093a:2472       PAC207 Genius VideoCam ge110
+pac7311         093a:2600       PAC7311 Typhoon
+pac7311         093a:2601       PAC7311 Phillips SPC610NC
+pac7311         093a:2603       PAC7312
+pac7311         093a:2608       PAC7311 Trust WB-3300p
+pac7311         093a:260e       PAC7311 Gigaware VGA PC Camera, Trust WB-3350p, SIGMA cam 2350
+pac7311         093a:260f       PAC7311 SnakeCam
+pac7311         093a:2621       PAC731x
+zc3xx           0ac8:0302       Z-star Vimicro zc0302
+vc032x          0ac8:0321       Vimicro generic vc0321
+vc032x          0ac8:0323       Vimicro Vc0323
+vc032x          0ac8:0328       A4Tech PK-130MG
+zc3xx           0ac8:301b       Z-Star zc301b
+zc3xx           0ac8:303b       Vimicro 0x303b
+zc3xx           0ac8:305b       Z-star Vimicro zc0305b
+zc3xx           0ac8:307b       Ldlc VC302+Ov7620
+vc032x          0ac8:c001       Sony embedded vimicro
+vc032x          0ac8:c002       Sony embedded vimicro
+spca508         0af9:0010       Hama USB Sightcam 100
+spca508         0af9:0011       Hama USB Sightcam 100
+sonixb          0c45:6001       Genius VideoCAM NB
+sonixb          0c45:6005       Microdia Sweex Mini Webcam
+sonixb          0c45:6007       Sonix sn9c101 + Tas5110D
+sonixb          0c45:6009       spcaCam@120
+sonixb          0c45:600d       spcaCam@120
+sonixb          0c45:6011       Microdia PC Camera (SN9C102)
+sonixb          0c45:6019       Generic Sonix OV7630
+sonixb          0c45:6024       Generic Sonix Tas5130c
+sonixb          0c45:6025       Xcam Shanga
+sonixb          0c45:6028       Sonix Btc Pc380
+sonixb          0c45:6029       spcaCam@150
+sonixb          0c45:602c       Generic Sonix OV7630
+sonixb          0c45:602d       LIC-200 LG
+sonixb          0c45:602e       Genius VideoCam Messenger
+sonixj          0c45:6040       Speed NVC 350K
+sonixj          0c45:607c       Sonix sn9c102p Hv7131R
+sonixj          0c45:60c0       Sangha Sn535
+sonixj          0c45:60ec       SN9C105+MO4000
+sonixj          0c45:60fb       Surfer NoName
+sonixj          0c45:60fc       LG-LIC300
+sonixj          0c45:612a       Avant Camera
+sonixj          0c45:612c       Typhoon Rasy Cam 1.3MPix
+sonixj          0c45:6130       Sonix Pccam
+sonixj          0c45:6138       Sn9c120 Mo4000
+sonixj          0c45:613b       Surfer SN-206
+sonixj          0c45:613c       Sonix Pccam168
+sunplus         0d64:0303       Sunplus FashionCam DXG
+etoms           102c:6151       Qcam Sangha CIF
+etoms           102c:6251       Qcam xxxxxx VGA
+zc3xx           10fd:0128       Typhoon Webshot II USB 300k 0x0128
+spca561         10fd:7e50       FlyCam Usb 100
+zc3xx           10fd:8050       Typhoon Webshot II USB 300k
+spca501         1776:501c       Arowana 300K CMOS Camera
+t613            17a1:0128       T613/TAS5130A
+vc032x          17ef:4802       Lenovo Vc0323+MI1310_SOC
+pac207          2001:f115       D-Link DSB-C120
+spca500         2899:012c       Toptro Industrial
+spca508         8086:0110       Intel Easy PC Camera
+spca500         8086:0630       Intel Pocket PC Camera
+spca506         99fa:8988       Grandtec V.cap
+spca561         abcd:cdee       Petcam
diff --git a/Documentation/video4linux/sn9c102.txt b/Documentation/video4linux/sn9c102.txt
index b26f5195af51..73de4050d637 100644
--- a/Documentation/video4linux/sn9c102.txt
+++ b/Documentation/video4linux/sn9c102.txt
@@ -157,7 +157,7 @@ Loading can be done as shown below:
        [root@localhost home]# modprobe sn9c102
-Note that the module is called "sn9c102" for historic reasons, althought it
+Note that the module is called "sn9c102" for historic reasons, although it
 does not just support the SN9C102.
 At this point all the devices supported by the driver and connected to the USB
diff --git a/Documentation/video4linux/w9968cf.txt b/Documentation/video4linux/w9968cf.txt
index e0bba8393c77..05138e8aea07 100644
--- a/Documentation/video4linux/w9968cf.txt
+++ b/Documentation/video4linux/w9968cf.txt
@@ -193,9 +193,6 @@ Description:     Automatic 'ovcamchip' module loading: 0 disabled, 1 enabled.
                 loads that module automatically. This action is performed as
                 once soon as the 'w9968cf' module is loaded into memory.
 Default:         1
-Note:            The kernel must be compiled with the CONFIG_KMOD option
-                 enabled for the 'ovcamchip' module to be loaded and for
-                 this parameter to be present.
 -------------------------------------------------------------------------------
 Name:           simcams
 Type:           int
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 3102b81bef88..ea8714fcc3ad 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -77,7 +77,7 @@ memory that is preset in system at this time.  System administrators may want
 to put this command in one of the local rc init files.  This will enable the
 kernel to request huge pages early in the boot process (when the possibility
 of getting physical contiguous pages is still very high). In either
-case, adminstrators will want to verify the number of hugepages actually
+case, administrators will want to verify the number of hugepages actually
 allocated by checking the sysctl or meminfo.
 /proc/sys/vm/nr_overcommit_hugepages indicates how large the pool of
@@ -95,6 +95,29 @@ this condition holds, however, no more surplus huge pages will be
 allowed on the system until one of the two sysctls are increased
 sufficiently, or the surplus huge pages go out of use and are freed.
+With support for multiple hugepage pools at run-time available, much of
+the hugepage userspace interface has been duplicated in sysfs. The above
+information applies to the default hugepage size (which will be
+controlled by the proc interfaces for backwards compatibility). The root
+hugepage control directory is
+        /sys/kernel/mm/hugepages
+For each hugepage size supported by the running kernel, a subdirectory
+will exist, of the form
+        hugepages-${size}kB
+Inside each of these directories, the same set of files will exist:
+        nr_hugepages
+        nr_overcommit_hugepages
+        free_hugepages
+        resv_hugepages
+        surplus_hugepages
+which function as described above for the default hugepage-sized case.
 If the user applications are going to request hugepages using mmap system
 call, then it is required that system administrator mount a file system of
 type hugetlbfs:
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index bad16d3f6a47..6aaaeb38730c 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -58,7 +58,7 @@ most general to most specific:
        the policy at the time they were allocated.
    VMA Policy:  A "VMA" or "Virtual Memory Area" refers to a range of a task's
-    virtual adddress space.  A task may define a specific policy for a range
+    virtual address space.  A task may define a specific policy for a range
    of its virtual address space.   See the MEMORY POLICIES APIS section,
    below, for an overview of the mbind() system call used to set a VMA
    policy.
@@ -353,7 +353,7 @@ follows:
   Because of this extra reference counting, and because we must lookup
   shared policies in a tree structure under spinlock, shared policies are
-   more expensive to use in the page allocation path.  This is expecially
+   more expensive to use in the page allocation path.  This is especially
   true for shared policies on shared memory regions shared by tasks running
   on different NUMA nodes.  This extra overhead can be avoided by always
   falling back to task or system default policy for shared memory regions,
diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
new file mode 100644
index 000000000000..ce72c0fe6177
--- /dev/null
+++ b/Documentation/vm/pagemap.txt
@@ -0,0 +1,77 @@
+pagemap, from the userspace perspective
+---------------------------------------
+pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
+userspace programs to examine the page tables and related information by
+reading files in /proc.
+There are three components to pagemap:
+ * /proc/pid/pagemap.  This file lets a userspace process find out which
+   physical frame each virtual page is mapped to.  It contains one 64-bit
+   value for each virtual page, containing the following data (from
+   fs/proc/task_mmu.c, above pagemap_read):
+    * Bits 0-55  page frame number (PFN) if present
+    * Bits 0-4   swap type if swapped
+    * Bits 5-55  swap offset if swapped
+    * Bits 55-60 page shift (page size = 1<<page shift)
+    * Bit  61    reserved for future use
+    * Bit  62    page swapped
+    * Bit  63    page present
+   If the page is not present but in swap, then the PFN contains an
+   encoding of the swap file number and the page's offset into the
+   swap. Unmapped pages return a null PFN. This allows determining
+   precisely which pages are mapped (or in swap) and comparing mapped
+   pages between processes.
+   Efficient users of this interface will use /proc/pid/maps to
+   determine which areas of memory are actually mapped and llseek to
+   skip over unmapped regions.
+ * /proc/kpagecount.  This file contains a 64-bit count of the number of
+   times each page is mapped, indexed by PFN.
+ * /proc/kpageflags.  This file contains a 64-bit set of flags for each
+   page, indexed by PFN.
+   The flags are (from fs/proc/proc_misc, above kpageflags_read):
+     0. LOCKED
+     1. ERROR
+     2. REFERENCED
+     3. UPTODATE
+     4. DIRTY
+     5. LRU
+     6. ACTIVE
+     7. SLAB
+     8. WRITEBACK
+     9. RECLAIM
+    10. BUDDY
+Using pagemap to do something useful:
+The general procedure for using pagemap to find out about a process' memory
+usage goes like this:
+ 1. Read /proc/pid/maps to determine which parts of the memory space are
+    mapped to what.
+ 2. Select the maps you are interested in -- all of them, or a particular
+    library, or the stack or the heap, etc.
+ 3. Open /proc/pid/pagemap and seek to the pages you would like to examine.
+ 4. Read a u64 for each page from pagemap.
+ 5. Open /proc/kpagecount and/or /proc/kpageflags.  For each PFN you just
+    read, seek to that entry in the file, and read the data you want.
+For example, to find the "unique set size" (USS), which is the amount of
+memory that a process is using that is not shared with any other process,
+you can go through every map in the process, find the PFNs, look those up
+in kpagecount, and tally up the number of pages that are only referenced
+once.
+Other notes:
+Reading from any of the files will return -EINVAL if you are not starting
+the read on an 8-byte boundary (e.g., if you seeked an odd number of bytes
+into the file), or if the size of the read is not a multiple of 8 bytes.
diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c
index e4230ed16ee7..df3227605d59 100644
--- a/Documentation/vm/slabinfo.c
+++ b/Documentation/vm/slabinfo.c
@@ -1,7 +1,7 @@
 /*
 * Slabinfo: Tool to get reports about slabs
 *
- * (C) 2007 sgi, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 sgi, Christoph Lameter
 *
 * Compile by:
 *
@@ -99,7 +99,7 @@ void fatal(const char *x, ...)
 void usage(void)
 {
-        printf("slabinfo 5/7/2007. (c) 2007 sgi. clameter@sgi.com\n\n"
+        printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n"
                "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
                "-a|--aliases           Show aliases\n"
                "-A|--activity          Most active slabs first\n"
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index 7c13f22a0c9e..bb1f5c6e28b3 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -266,4 +266,4 @@ of other objects.
        slub_debug=FZ,dentry
-Christoph Lameter, <clameter@sgi.com>, May 30, 2007
+Christoph Lameter, May 30, 2007
diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt
index 10c2e411cca8..991c26a6ef64 100644
--- a/Documentation/volatile-considered-harmful.txt
+++ b/Documentation/volatile-considered-harmful.txt
@@ -114,6 +114,6 @@ CREDITS
 Original impetus and research by Randy Dunlap
 Written by Jonathan Corbet
-Improvements via coments from Satyam Sharma, Johannes Stezenbach, Jesper
+Improvements via comments from Satyam Sharma, Johannes Stezenbach, Jesper
        Juhl, Heikki Orsila, H. Peter Anvin, Philipp Hahn, and Stefan
        Richter.
diff --git a/Documentation/i386/IO-APIC.txt b/Documentation/x86/i386/IO-APIC.txt
index 30b4c714fbe1..30b4c714fbe1 100644
--- a/Documentation/i386/IO-APIC.txt
+++ b/Documentation/x86/i386/IO-APIC.txt
diff --git a/Documentation/i386/boot.txt b/Documentation/x86/i386/boot.txt
index 95ad15c3b01f..147bfe511cdd 100644
--- a/Documentation/i386/boot.txt
+++ b/Documentation/x86/i386/boot.txt
@@ -1,17 +1,14 @@
-                     THE LINUX/I386 BOOT PROTOCOL
+                     THE LINUX/x86 BOOT PROTOCOL
-                     ----------------------------
+                     ---------------------------
-                    H. Peter Anvin <hpa@zytor.com>
+On the x86 platform, the Linux kernel uses a rather complicated boot
-                        Last update 2007-05-23
-On the i386 platform, the Linux kernel uses a rather complicated boot
 convention.  This has evolved partially due to historical aspects, as
 well as the desire in the early days to have the kernel itself be a
 bootable image, the complicated PC memory model and due to changed
 expectations in the PC industry caused by the effective demise of
 real-mode DOS as a mainstream operating system.
-Currently, the following versions of the Linux/i386 boot protocol exist.
+Currently, the following versions of the Linux/x86 boot protocol exist.
 Old kernels:    zImage/Image support only.  Some very early kernels
                may not even support a command line.
@@ -372,10 +369,17 @@ Protocol:	2.00+
        - If 0, the protected-mode code is loaded at 0x10000.
        - If 1, the protected-mode code is loaded at 0x100000.
+  Bit 5 (write): QUIET_FLAG
+        - If 0, print early messages.
+        - If 1, suppress early messages.
+                This requests to the kernel (decompressor and early
+                kernel) to not write early messages that require
+                accessing the display hardware directly.
  Bit 6 (write): KEEP_SEGMENTS
        Protocol: 2.07+
-        - if 0, reload the segment registers in the 32bit entry point.
+        - If 0, reload the segment registers in the 32bit entry point.
-        - if 1, do not reload the segment registers in the 32bit entry point.
+        - If 1, do not reload the segment registers in the 32bit entry point.
                Assume that %cs %ds %ss %es are all set to flat segments with
                a base of 0 (or the equivalent for their environment).
@@ -504,7 +508,7 @@ Protocol:	2.06+
  maximum size was 255.
 Field name:     hardware_subarch
-Type:           write
+Type:           write (optional, defaults to x86/PC)
 Offset/size:    0x23c/4
 Protocol:       2.07+
@@ -520,11 +524,13 @@ Protocol:	2.07+
  0x00000002    Xen
 Field name:     hardware_subarch_data
-Type:           write
+Type:           write (subarch-dependent)
 Offset/size:    0x240/8
 Protocol:       2.07+
  A pointer to data that is specific to hardware subarch
+  This field is currently unused for the default x86/PC environment,
+  do not modify.
 Field name:     payload_offset
 Type:           read
@@ -545,6 +551,34 @@ Protocol:	2.08+
  The length of the payload.
+Field name:     setup_data
+Type:           write (special)
+Offset/size:    0x250/8
+Protocol:       2.09+
+  The 64-bit physical pointer to NULL terminated single linked list of
+  struct setup_data. This is used to define a more extensible boot
+  parameters passing mechanism. The definition of struct setup_data is
+  as follow:
+  struct setup_data {
+          u64 next;
+          u32 type;
+          u32 len;
+          u8  data[0];
+  };
+  Where, the next is a 64-bit physical pointer to the next node of
+  linked list, the next field of the last node is 0; the type is used
+  to identify the contents of data; the len is the length of data
+  field; the data holds the real payload.
+  This list may be modified at a number of points during the bootup
+  process.  Therefore, when modifying this list one should always make
+  sure to consider the case where the linked list already contains
+  entries.
 **** THE IMAGE CHECKSUM
 From boot protocol version 2.08 onwards the CRC-32 is calculated over
@@ -553,6 +587,7 @@ initial remainder of 0xffffffff.  The checksum is appended to the
 file; therefore the CRC of the file up to the limit specified in the
 syssize field of the header is always 0.
 **** THE KERNEL COMMAND LINE
 The kernel command line has become an important way for the boot
@@ -584,28 +619,6 @@ command line is entered using the following protocol:
        covered by setup_move_size, so you may need to adjust this
        field.
-Field name:     setup_data
-Type:           write (obligatory)
-Offset/size:    0x250/8
-Protocol:       2.09+
-  The 64-bit physical pointer to NULL terminated single linked list of
-  struct setup_data. This is used to define a more extensible boot
-  parameters passing mechanism. The definition of struct setup_data is
-  as follow:
-  struct setup_data {
-          u64 next;
-          u32 type;
-          u32 len;
-          u8  data[0];
-  };
-  Where, the next is a 64-bit physical pointer to the next node of
-  linked list, the next field of the last node is 0; the type is used
-  to identify the contents of data; the len is the length of data
-  field; the data holds the real payload.
 **** MEMORY LAYOUT OF THE REAL-MODE CODE
diff --git a/Documentation/i386/usb-legacy-support.txt b/Documentation/x86/i386/usb-legacy-support.txt
index 1894cdfc69d9..1894cdfc69d9 100644
--- a/Documentation/i386/usb-legacy-support.txt
+++ b/Documentation/x86/i386/usb-legacy-support.txt
diff --git a/Documentation/i386/zero-page.txt b/Documentation/x86/i386/zero-page.txt
index 169ad423a3d1..169ad423a3d1 100644
--- a/Documentation/i386/zero-page.txt
+++ b/Documentation/x86/i386/zero-page.txt
diff --git a/Documentation/x86_64/00-INDEX b/Documentation/x86/x86_64/00-INDEX
index 92fc20ab5f0e..92fc20ab5f0e 100644
--- a/Documentation/x86_64/00-INDEX
+++ b/Documentation/x86/x86_64/00-INDEX
diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b0c7b6c4abda..b0c7b6c4abda 100644
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
diff --git a/Documentation/x86_64/cpu-hotplug-spec b/Documentation/x86/x86_64/cpu-hotplug-spec
index 3c23e0587db3..3c23e0587db3 100644
--- a/Documentation/x86_64/cpu-hotplug-spec
+++ b/Documentation/x86/x86_64/cpu-hotplug-spec
diff --git a/Documentation/x86_64/fake-numa-for-cpusets b/Documentation/x86/x86_64/fake-numa-for-cpusets
index d1a985c5b00a..d1a985c5b00a 100644
--- a/Documentation/x86_64/fake-numa-for-cpusets
+++ b/Documentation/x86/x86_64/fake-numa-for-cpusets
diff --git a/Documentation/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d51fb95..5ad65d51fb95 100644
--- a/Documentation/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
diff --git a/Documentation/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index a05e58e7b159..a05e58e7b159 100644
--- a/Documentation/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
diff --git a/Documentation/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index b89b6d2bebfa..efce75097369 100644
--- a/Documentation/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -11,9 +11,8 @@ ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
-ffffffff80000000 - ffffffff82800000 (=40 MB)   kernel text mapping, from phys 0
+ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
-... unused hole ...
+ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
-ffffffff88000000 - fffffffffff00000 (=1919 MB) module mapping space
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
diff --git a/Documentation/x86_64/uefi.txt b/Documentation/x86/x86_64/uefi.txt
index 7d77120a5184..a5e2b4fdb170 100644
--- a/Documentation/x86_64/uefi.txt
+++ b/Documentation/x86/x86_64/uefi.txt
@@ -36,3 +36,7 @@ Mechanics:
  services.
        noefi           turn off all EFI runtime services
        reboot_type=k   turn off EFI reboot runtime service
+- If the EFI memory map has additional entries not in the E820 map,
+  you can include those entries in the kernels memory map of available
+  physical RAM by using the following kernel command line parameter.
+        add_efi_memmap  include EFI memory map of available physical RAM
author	Anton Vorontsov <cbouatmailru@gmail.com>	2008-07-29 18:05:23 -0400
committer	Anton Vorontsov <cbouatmailru@gmail.com>	2008-07-29 18:05:23 -0400
commit	9fec6060d9e48ed7db0dac0e16d0f0f0e615b7f6 (patch)
tree	74b41f31a08f6500ff3dfcf64ba21e2d9a8e87e5 /Documentation
parent	fece418418f51e92dd7e67e17c5e3fe5a28d3279 (diff)
parent	6e86841d05f371b5b9b86ce76c02aaee83352298 (diff)