Merge branch 'master'

46 files changed, 3501 insertions, 507 deletions

diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index fcbcbc35b122..6221464d1a7e 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -90,16 +90,20 @@ at OLS.  The resulting abundance of RCU patches was presented the
 following year [McKenney02a], and use of RCU in dcache was first
 described that same year [Linder02a].
 
-Also in 2002, Michael [Michael02b,Michael02a] presented techniques
-that defer the destruction of data structures to simplify non-blocking
-synchronization (wait-free synchronization, lock-free synchronization,
-and obstruction-free synchronization are all examples of non-blocking
-synchronization).  In particular, this technique eliminates locking,
-reduces contention, reduces memory latency for readers, and parallelizes
-pipeline stalls and memory latency for writers.  However, these
-techniques still impose significant read-side overhead in the form of
-memory barriers.  Researchers at Sun worked along similar lines in the
-same timeframe [HerlihyLM02,HerlihyLMS03].
+Also in 2002, Michael [Michael02b,Michael02a] presented "hazard-pointer"
+techniques that defer the destruction of data structures to simplify
+non-blocking synchronization (wait-free synchronization, lock-free
+synchronization, and obstruction-free synchronization are all examples of
+non-blocking synchronization).  In particular, this technique eliminates
+locking, reduces contention, reduces memory latency for readers, and
+parallelizes pipeline stalls and memory latency for writers.  However,
+these techniques still impose significant read-side overhead in the
+form of memory barriers.  Researchers at Sun worked along similar lines
+in the same timeframe [HerlihyLM02,HerlihyLMS03].  These techniques
+can be thought of as inside-out reference counts, where the count is
+represented by the number of hazard pointers referencing a given data
+structure (rather than the more conventional counter field within the
+data structure itself).
 
 In 2003, the K42 group described how RCU could be used to create
 hot-pluggable implementations of operating-system functions.  Later that
@@ -113,7 +117,6 @@ number of operating-system kernels [PaulEdwardMcKenneyPhD], a paper
 describing how to make RCU safe for soft-realtime applications [Sarma04c],
 and a paper describing SELinux performance with RCU [JamesMorris04b].
 
-
 2005 has seen further adaptation of RCU to realtime use, permitting
 preemption of RCU realtime critical sections [PaulMcKenney05a,
 PaulMcKenney05b].
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index e118a7c1a092..49e27cc19385 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -177,3 +177,9 @@ over a rather long period of time, but improvements are always welcome!
 
         If you want to wait for some of these other things, you might
         instead need to use synchronize_irq() or synchronize_sched().
+
+12.     Any lock acquired by an RCU callback must be acquired elsewhere
+        with irq disabled, e.g., via spin_lock_irqsave().  Failing to
+        disable irq on a given acquisition of that lock will result in
+        deadlock as soon as the RCU callback happens to interrupt that
+        acquisition's critical section.
diff --git a/Documentation/RCU/listRCU.txt b/Documentation/RCU/listRCU.txt
index f8a54fa0d8ab..1fd175368a87 100644
--- a/Documentation/RCU/listRCU.txt
+++ b/Documentation/RCU/listRCU.txt
@@ -232,7 +232,7 @@ entry does not exist.  For this to be helpful, the search function must
 return holding the per-entry spinlock, as ipc_lock() does in fact do.
 
 Quick Quiz:  Why does the search function need to return holding the
-per-entry lock for this deleted-flag technique to be helpful?
+        per-entry lock for this deleted-flag technique to be helpful?
 
 If the system-call audit module were to ever need to reject stale data,
 one way to accomplish this would be to add a "deleted" flag and a "lock"
@@ -275,8 +275,8 @@ flag under the spinlock as follows:
         {
                 struct audit_entry  *e;
 
-                /* Do not use the _rcu iterator here, since this is the only
-                 * deletion routine. */
+                /* Do not need to use the _rcu iterator here, since this
+                 * is the only deletion routine. */
                 list_for_each_entry(e, list, list) {
                         if (!audit_compare_rule(rule, &e->rule)) {
                                 spin_lock(&e->lock);
@@ -304,9 +304,12 @@ function to reject newly deleted data.
 
 
 Answer to Quick Quiz
-
-If the search function drops the per-entry lock before returning, then
-the caller will be processing stale data in any case.  If it is really
-OK to be processing stale data, then you don't need a "deleted" flag.
-If processing stale data really is a problem, then you need to hold the
-per-entry lock across all of the code that uses the value looked up.
+        Why does the search function need to return holding the per-entry
+        lock for this deleted-flag technique to be helpful?
+
+        If the search function drops the per-entry lock before returning,
+        then the caller will be processing stale data in any case.  If it
+        is really OK to be processing stale data, then you don't need a
+        "deleted" flag.  If processing stale data really is a problem,
+        then you need to hold the per-entry lock across all of the code
+        that uses the value that was returned.
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 6fa092251586..02e27bf1d365 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -111,6 +111,11 @@ o	What are all these files in this directory?
 
                 You are reading it!
 
+        rcuref.txt
+
+                Describes how to combine use of reference counts
+                with RCU.
+
         whatisRCU.txt
 
                 Overview of how the RCU implementation works.  Along
diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt
index 3f60db41b2f0..451de2ad8329 100644
--- a/Documentation/RCU/rcuref.txt
+++ b/Documentation/RCU/rcuref.txt
@@ -1,7 +1,7 @@
-Refcounter design for elements of lists/arrays protected by RCU.
+Reference-count design for elements of lists/arrays protected by RCU.
 
-Refcounting on elements of  lists which are protected by traditional
-reader/writer spinlocks or semaphores are straight forward as in:
+Reference counting on elements of lists which are protected by traditional
+reader/writer spinlocks or semaphores are straightforward:
 
 1.                              2.
 add()                           search_and_reference()
@@ -28,12 +28,12 @@ release_referenced()			delete()
                                             ...
                                         }
 
-If this list/array is made lock free using rcu as in changing the
-write_lock in add() and delete() to spin_lock and changing read_lock
+If this list/array is made lock free using RCU as in changing the
+write_lock() in add() and delete() to spin_lock and changing read_lock
 in search_and_reference to rcu_read_lock(), the atomic_get in
 search_and_reference could potentially hold reference to an element which
-has already been deleted from the list/array.  atomic_inc_not_zero takes
-care of this scenario. search_and_reference should look as;
+has already been deleted from the list/array.  Use atomic_inc_not_zero()
+in this scenario as follows:
 
 1.                                      2.
 add()                                   search_and_reference()
@@ -51,17 +51,16 @@ add()					search_and_reference()
 release_referenced()                    delete()
 {                                       {
     ...                                     write_lock(&list_lock);
-    atomic_dec(&el->rc, relfunc)            ...
-    ...                                     delete_element
-}                                           write_unlock(&list_lock);
-                                            ...
+    if (atomic_dec_and_test(&el->rc))       ...
+        call_rcu(&el->head, el_free);       delete_element
+    ...                                     write_unlock(&list_lock);
+}                                           ...
                                             if (atomic_dec_and_test(&el->rc))
                                                 call_rcu(&el->head, el_free);
                                             ...
                                         }
 
-Sometimes, reference to the element need to be obtained in the
-update (write) stream.  In such cases, atomic_inc_not_zero might be an
-overkill since the spinlock serialising list updates are held. atomic_inc
-is to be used in such cases.
-
+Sometimes, a reference to the element needs to be obtained in the
+update (write) stream.  In such cases, atomic_inc_not_zero() might be
+overkill, since we hold the update-side spinlock.  One might instead
+use atomic_inc() in such cases.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 15da16861fa3..5ed85af88789 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -200,10 +200,11 @@ rcu_assign_pointer()
         the new value, and also executes any memory-barrier instructions
         required for a given CPU architecture.
 
-        Perhaps more important, it serves to document which pointers
-        are protected by RCU.  That said, rcu_assign_pointer() is most
-        frequently used indirectly, via the _rcu list-manipulation
-        primitives such as list_add_rcu().
+        Perhaps just as important, it serves to document (1) which
+        pointers are protected by RCU and (2) the point at which a
+        given structure becomes accessible to other CPUs.  That said,
+        rcu_assign_pointer() is most frequently used indirectly, via
+        the _rcu list-manipulation primitives such as list_add_rcu().
 
 rcu_dereference()
 
@@ -258,9 +259,11 @@ rcu_dereference()
         locking.
 
         As with rcu_assign_pointer(), an important function of
-        rcu_dereference() is to document which pointers are protected
-        by RCU.  And, again like rcu_assign_pointer(), rcu_dereference()
-        is typically used indirectly, via the _rcu list-manipulation
+        rcu_dereference() is to document which pointers are protected by
+        RCU, in particular, flagging a pointer that is subject to changing
+        at any time, including immediately after the rcu_dereference().
+        And, again like rcu_assign_pointer(), rcu_dereference() is
+        typically used indirectly, via the _rcu list-manipulation
         primitives, such as list_for_each_entry_rcu().
 
 The following diagram shows how each API communicates among the
@@ -327,7 +330,7 @@ for specialized uses, but are relatively uncommon.
 3.  WHAT ARE SOME EXAMPLE USES OF CORE RCU API?
 
 This section shows a simple use of the core RCU API to protect a
-global pointer to a dynamically allocated structure.  More typical
+global pointer to a dynamically allocated structure.  More-typical
 uses of RCU may be found in listRCU.txt, arrayRCU.txt, and NMI-RCU.txt.
 
         struct foo {
@@ -410,6 +413,8 @@ o	Use synchronize_rcu() -after- removing a data element from an
         data item.
 
 See checklist.txt for additional rules to follow when using RCU.
+And again, more-typical uses of RCU may be found in listRCU.txt,
+arrayRCU.txt, and NMI-RCU.txt.
 
 
 4.  WHAT IF MY UPDATING THREAD CANNOT BLOCK?
@@ -513,7 +518,7 @@ production-quality implementation, and see:
 
 for papers describing the Linux kernel RCU implementation.  The OLS'01
 and OLS'02 papers are a good introduction, and the dissertation provides
-more details on the current implementation.
+more details on the current implementation as of early 2004.
 
 
 5A.  "TOY" IMPLEMENTATION #1: LOCKING
@@ -768,7 +773,6 @@ RCU pointer/list traversal:
         rcu_dereference
         list_for_each_rcu               (to be deprecated in favor of
                                          list_for_each_entry_rcu)
-        list_for_each_safe_rcu          (deprecated, not used)
         list_for_each_entry_rcu
         list_for_each_continue_rcu      (to be deprecated in favor of new
                                          list_for_each_entry_continue_rcu)
@@ -807,7 +811,8 @@ Quick Quiz #1:	Why is this argument naive?  How could a deadlock
 Answer:         Consider the following sequence of events:
 
                 1.      CPU 0 acquires some unrelated lock, call it
-                        "problematic_lock".
+                        "problematic_lock", disabling irq via
+                        spin_lock_irqsave().
 
                 2.      CPU 1 enters synchronize_rcu(), write-acquiring
                         rcu_gp_mutex.
@@ -894,7 +899,7 @@ Answer:		Just as PREEMPT_RT permits preemption of spinlock
 ACKNOWLEDGEMENTS
 
 My thanks to the people who helped make this human-readable, including
-Jon Walpole, Josh Triplett, Serge Hallyn, and Suzanne Wood.
+Jon Walpole, Josh Triplett, Serge Hallyn, Suzanne Wood, and Alan Stern.
 
 
 For more information, see http://www.rdrop.com/users/paulmck/RCU.
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index 08c5d04f3086..57a09f99ecb0 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -11,6 +11,8 @@
                         Joel Schopp <jschopp@austin.ibm.com>
                 ia64/x86_64:
                         Ashok Raj <ashok.raj@intel.com>
+                s390:
+                        Heiko Carstens <heiko.carstens@de.ibm.com>
 
 Authors: Ashok Raj <ashok.raj@intel.com>
 Lots of feedback: Nathan Lynch <nathanl@austin.ibm.com>,
@@ -44,9 +46,28 @@ maxcpus=n    Restrict boot time cpus to n. Say if you have 4 cpus, using
              maxcpus=2 will only boot 2. You can choose to bring the
              other cpus later online, read FAQ's for more info.
 
-additional_cpus=n       [x86_64 only] use this to limit hotpluggable cpus.
-                        This option sets
-                        cpu_possible_map = cpu_present_map + additional_cpus
+additional_cpus*=n      Use this to limit hotpluggable cpus. This option sets
+                        cpu_possible_map = cpu_present_map + additional_cpus
+
+(*) Option valid only for following architectures
+- x86_64, ia64, s390
+
+ia64 and x86_64 use the number of disabled local apics in ACPI tables MADT
+to determine the number of potentially hot-pluggable cpus. The implementation
+should only rely on this to count the #of cpus, but *MUST* not rely on the
+apicid values in those tables for disabled apics. In the event BIOS doesnt
+mark such hot-pluggable cpus as disabled entries, one could use this
+parameter "additional_cpus=x" to represent those cpus in the cpu_possible_map.
+
+s390 uses the number of cpus it detects at IPL time to also the number of bits
+in cpu_possible_map. If it is desired to add additional cpus at a later time
+the number should be specified using this option or the possible_cpus option.
+
+possible_cpus=n         [s390 only] use this to set hotpluggable cpus.
+                        This option sets possible_cpus bits in
+                        cpu_possible_map. Thus keeping the numbers of bits set
+                        constant even if the machine gets rebooted.
+                        This option overrides additional_cpus.
 
 CPU maps and such
 -----------------
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
new file mode 100644
index 000000000000..ff280e2e1613
--- /dev/null
+++ b/Documentation/cputopology.txt
@@ -0,0 +1,41 @@
+
+Export cpu topology info by sysfs. Items (attributes) are similar
+to /proc/cpuinfo.
+
+1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
+represent the physical package id of  cpu X;
+2) /sys/devices/system/cpu/cpuX/topology/core_id:
+represent the cpu core id to cpu X;
+3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+represent the thread siblings to cpu X in the same core;
+4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+represent the thread siblings to cpu X in the same physical package;
+
+To implement it in an architecture-neutral way, a new source file,
+driver/base/topology.c, is to export the 5 attributes.
+
+If one architecture wants to support this feature, it just needs to
+implement 4 defines, typically in file 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)
+#define topology_core_siblings(cpu)
+
+The type of **_id is int.
+The type of siblings is cpumask_t.
+
+To be consistent on all architectures, the 4 attributes should have
+deafult values if their values are unavailable. Below is the rule.
+1) physical_package_id: If cpu has no physical package id, -1 is the
+default value.
+2) core_id: If cpu doesn't support multi-core, its core id is 0.
+3) thread_siblings: Just include itself, if the cpu doesn't support
+HT/multi-thread.
+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/driver-model/overview.txt b/Documentation/driver-model/overview.txt
index 44662735cf81..ac4a7a737e43 100644
--- a/Documentation/driver-model/overview.txt
+++ b/Documentation/driver-model/overview.txt
@@ -1,50 +1,43 @@
 The Linux Kernel Device Model
 
-Patrick Mochel  <mochel@osdl.org>
+Patrick Mochel  <mochel@digitalimplant.org>
 
-26 August 2002
+Drafted 26 August 2002
+Updated 31 January 2006
 
 
 Overview
 ~~~~~~~~
 
-This driver model is a unification of all the current, disparate driver models
-that are currently in the kernel. It is intended to augment the
+The Linux Kernel Driver Model is a unification of all the disparate driver
+models that were previously used in the kernel. It is intended to augment the
 bus-specific drivers for bridges and devices by consolidating a set of data
 and operations into globally accessible data structures.
 
-Current driver models implement some sort of tree-like structure (sometimes
-just a list) for the devices they control. But, there is no linkage between
-the different bus types.
+Traditional driver models implemented some sort of tree-like structure
+(sometimes just a list) for the devices they control. There wasn't any
+uniformity across the different bus types.
 
-A common data structure can provide this linkage with little overhead: when a
-bus driver discovers a particular device, it can insert it into the global
-tree as well as its local tree. In fact, the local tree becomes just a subset
-of the global tree.
-
-Common data fields can also be moved out of the local bus models into the
-global model. Some of the manipulations of these fields can also be
-consolidated. Most likely, manipulation functions will become a set
-of helper functions, which the bus drivers wrap around to include any
-bus-specific items.
-
-The common device and bridge interface currently reflects the goals of the
-modern PC: namely the ability to do seamless Plug and Play, power management,
-and hot plug. (The model dictated by Intel and Microsoft (read: ACPI) ensures
-us that any device in the system may fit any of these criteria.)
-
-In reality, not every bus will be able to support such operations. But, most
-buses will support a majority of those operations, and all future buses will.
-In other words, a bus that doesn't support an operation is the exception,
-instead of the other way around.
+The current driver model provides a comon, uniform data model for describing
+a bus and the devices that can appear under the bus. The unified bus
+model includes a set of common attributes which all busses carry, and a set
+of common callbacks, such as device discovery during bus probing, bus
+shutdown, bus power management, etc.
 
+The common device and bridge interface reflects the goals of the modern
+computer: namely the ability to do seamless device "plug and play", power
+management, and hot plug. In particular, the model dictated by Intel and
+Microsoft (namely ACPI) ensures that almost every device on almost any bus
+on an x86-compatible system can work within this paradigm.  Of course,
+not every bus is able to support all such operations, although most
+buses support a most of those operations.
 
 
 Downstream Access
 ~~~~~~~~~~~~~~~~~
 
 Common data fields have been moved out of individual bus layers into a common
-data structure. But, these fields must still be accessed by the bus layers,
+data structure. These fields must still be accessed by the bus layers,
 and sometimes by the device-specific drivers.
 
 Other bus layers are encouraged to do what has been done for the PCI layer.
@@ -53,7 +46,7 @@ struct pci_dev now looks like this:
 struct pci_dev {
         ...
 
-        struct device device;
+        struct device dev;
 };
 
 Note first that it is statically allocated. This means only one allocation on
@@ -64,9 +57,9 @@ the two.
 
 The PCI bus layer freely accesses the fields of struct device. It knows about
 the structure of struct pci_dev, and it should know the structure of struct
-device. PCI devices that have been converted generally do not touch the fields
-of struct device. More precisely, device-specific drivers should not touch
-fields of struct device unless there is a strong compelling reason to do so.
+device. Individual PCI device drivers that have been converted the the current
+driver model generally do not and should not touch the fields of struct device,
+unless there is a strong compelling reason to do so.
 
 This abstraction is prevention of unnecessary pain during transitional phases.
 If the name of the field changes or is removed, then every downstream driver
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index b4a1ea762698..be5ae600f533 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -148,3 +148,35 @@ Why:	The 8250 serial driver now has the ability to deal with the differences
         brother on Alchemy SOCs.  The loss of features is not considered an
         issue.
 Who:    Ralf Baechle <ralf@linux-mips.org>
+
+---------------------------
+
+What:   Legacy /proc/pci interface (PCI_LEGACY_PROC)
+When:   March 2006
+Why:    deprecated since 2.5.53 in favor of lspci(8)
+Who:    Adrian Bunk <bunk@stusta.de>
+
+---------------------------
+
+What:   pci_module_init(driver)
+When:   January 2007
+Why:    Is replaced by pci_register_driver(pci_driver).
+Who:    Richard Knutsson <ricknu-0@student.ltu.se> and Greg Kroah-Hartman <gregkh@suse.de>
+
+---------------------------
+
+What:   I2C interface of the it87 driver
+When:   January 2007
+Why:    The ISA interface is faster and should be always available. The I2C
+        probing is also known to cause trouble in at least one case (see
+        bug #5889.)
+Who:    Jean Delvare <khali@linux-fr.org>
+
+---------------------------
+
+What:   mount/umount uevents
+When:   February 2007
+Why:    These events are not correct, and do not properly let userspace know
+        when a file system has been mounted or unmounted.  Userspace should
+        poll the /proc/mounts file instead to detect this properly.
+Who:    Greg Kroah-Hartman <gregkh@suse.de>
diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c
index f3c6e4946f98..3d4713a6c207 100644
--- a/Documentation/filesystems/configfs/configfs_example.c
+++ b/Documentation/filesystems/configfs/configfs_example.c
@@ -320,6 +320,7 @@ static struct config_item_type simple_children_type = {
         .ct_item_ops    = &simple_children_item_ops,
         .ct_group_ops   = &simple_children_group_ops,
         .ct_attrs       = simple_children_attrs,
+        .ct_owner       = THIS_MODULE,
 };
 
 static struct configfs_subsystem simple_children_subsys = {
@@ -403,6 +404,7 @@ static struct config_item_type group_children_type = {
         .ct_item_ops    = &group_children_item_ops,
         .ct_group_ops   = &group_children_group_ops,
         .ct_attrs       = group_children_attrs,
+        .ct_owner       = THIS_MODULE,
 };
 
 static struct configfs_subsystem group_children_subsys = {
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index f2595caf052e..4389c684a80a 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -35,6 +35,7 @@ Features which OCFS2 does not support yet:
           be cluster coherent.
         - quotas
         - cluster aware flock
+        - cluster aware lockf
         - Directory change notification (F_NOTIFY)
         - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
         - POSIX ACLs
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index dbe4d87d2615..8a155418c705 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -79,15 +79,18 @@ that instance in a system with many cpus making intensive use of it.
 
 
 tmpfs has a mount option to set the NUMA memory allocation policy for
-all files in that instance:
-mpol=interleave         prefers to allocate memory from each node in turn
-mpol=default            prefers to allocate memory from the local node
-mpol=bind               prefers to allocate from mpol_nodelist
-mpol=preferred          prefers to allocate from first node in mpol_nodelist
+all files in that instance (if CONFIG_NUMA is enabled) - which can be
+adjusted on the fly via 'mount -o remount ...'
 
-The following mount option is used in conjunction with mpol=interleave,
-mpol=bind or mpol=preferred:
-mpol_nodelist:  nodelist suitable for parsing with nodelist_parse.
+mpol=default             prefers to allocate memory from the local node
+mpol=prefer:Node         prefers to allocate memory from the given Node
+mpol=bind:NodeList       allocates memory only from nodes in NodeList
+mpol=interleave          prefers to allocate from each node in turn
+mpol=interleave:NodeList allocates from each node of NodeList in turn
+
+NodeList format is a comma-separated list of decimal numbers and ranges,
+a range being two hyphen-separated decimal numbers, the smallest and
+largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
 
 
 To specify the initial root directory you can use the following mount
@@ -109,4 +112,4 @@ RAM/SWAP in 10240 inodes and it is only accessible by root.
 Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
-   Hugh Dickins <hugh@veritas.com>, 13 March 2005
+   Hugh Dickins <hugh@veritas.com>, 19 February 2006
diff --git a/Documentation/filesystems/v9fs.txt b/Documentation/filesystems/v9fs.txt
index 4e92feb6b507..24c7a9c41f0d 100644
--- a/Documentation/filesystems/v9fs.txt
+++ b/Documentation/filesystems/v9fs.txt
@@ -57,8 +57,6 @@ OPTIONS
 
   port=n        port to connect to on the remote server
 
-  timeout=n     request timeouts (in ms) (default 60000ms)
-
   noextend      force legacy mode (no 9P2000.u semantics)
 
   uid           attempt to mount as a particular uid
@@ -74,10 +72,16 @@ OPTIONS
 RESOURCES
 =========
 
-The Linux version of the 9P server, along with some client-side utilities
-can be found at http://v9fs.sf.net (along with a CVS repository of the
-development branch of this module).  There are user and developer mailing
-lists here, as well as a bug-tracker.
+The Linux version of the 9P server is now maintained under the npfs project
+on sourceforge (http://sourceforge.net/projects/npfs).
+
+There are user and developer mailing lists available through the v9fs project
+on sourceforge (http://sourceforge.net/projects/v9fs).
+
+News and other information is maintained on SWiK (http://swik.net/v9fs).
+
+Bug reports may be issued through the kernel.org bugzilla 
+(http://bugzilla.kernel.org)
 
 For more information on the Plan 9 Operating System check out
 http://plan9.bell-labs.com/plan9
diff --git a/Documentation/fujitsu/frv/kernel-ABI.txt b/Documentation/fujitsu/frv/kernel-ABI.txt
new file mode 100644
index 000000000000..0ed9b0a779bc
--- /dev/null
+++ b/Documentation/fujitsu/frv/kernel-ABI.txt
@@ -0,0 +1,234 @@
+                                 =================================
+                                 INTERNAL KERNEL ABI FOR FR-V ARCH
+                                 =================================
+
+The internal FRV kernel ABI is not quite the same as the userspace ABI. A number of the registers
+are used for special purposed, and the ABI is not consistent between modules vs core, and MMU vs
+no-MMU.
+
+This partly stems from the fact that FRV CPUs do not have a separate supervisor stack pointer, and
+most of them do not have any scratch registers, thus requiring at least one general purpose
+register to be clobbered in such an event. Also, within the kernel core, it is possible to simply
+jump or call directly between functions using a relative offset. This cannot be extended to modules
+for the displacement is likely to be too far. Thus in modules the address of a function to call
+must be calculated in a register and then used, requiring two extra instructions.
+
+This document has the following sections:
+
+ (*) System call register ABI
+ (*) CPU operating modes
+ (*) Internal kernel-mode register ABI
+ (*) Internal debug-mode register ABI
+ (*) Virtual interrupt handling
+
+
+========================
+SYSTEM CALL REGISTER ABI
+========================
+
+When a system call is made, the following registers are effective:
+
+        REGISTERS       CALL                    RETURN
+        =============== ======================= =======================
+        GR7             System call number      Preserved
+        GR8             Syscall arg #1          Return value
+        GR9-GR13        Syscall arg #2-6        Preserved
+
+
+===================
+CPU OPERATING MODES
+===================
+
+The FR-V CPU has three basic operating modes. In order of increasing capability:
+
+  (1) User mode.
+
+      Basic userspace running mode.
+
+  (2) Kernel mode.
+
+      Normal kernel mode. There are many additional control registers available that may be
+      accessed in this mode, in addition to all the stuff available to user mode. This has two
+      submodes:
+
+      (a) Exceptions enabled (PSR.T == 1).
+
+          Exceptions will invoke the appropriate normal kernel mode handler. On entry to the
+          handler, the PSR.T bit will be cleared.
+
+      (b) Exceptions disabled (PSR.T == 0).
+
+          No exceptions or interrupts may happen. Any mandatory exceptions will cause the CPU to
+          halt unless the CPU is told to jump into debug mode instead.
+
+  (3) Debug mode.
+
+      No exceptions may happen in this mode. Memory protection and management exceptions will be
+      flagged for later consideration, but the exception handler won't be invoked. Debugging traps
+      such as hardware breakpoints and watchpoints will be ignored. This mode is entered only by
+      debugging events obtained from the other two modes.
+
+      All kernel mode registers may be accessed, plus a few extra debugging specific registers.
+
+
+=================================
+INTERNAL KERNEL-MODE REGISTER ABI
+=================================
+
+There are a number of permanent register assignments that are set up by entry.S in the exception
+prologue. Note that there is a complete set of exception prologues for each of user->kernel
+transition and kernel->kernel transition. There are also user->debug and kernel->debug mode
+transition prologues.
+
+
+        REGISTER        FLAVOUR USE
+        =============== ======= ====================================================
+        GR1                     Supervisor stack pointer
+        GR15                    Current thread info pointer
+        GR16                    GP-Rel base register for small data
+        GR28                    Current exception frame pointer (__frame)
+        GR29                    Current task pointer (current)
+        GR30                    Destroyed by kernel mode entry
+        GR31            NOMMU   Destroyed by debug mode entry
+        GR31            MMU     Destroyed by TLB miss kernel mode entry
+        CCR.ICC2                Virtual interrupt disablement tracking
+        CCCR.CC3                Cleared by exception prologue (atomic op emulation)
+        SCR0            MMU     See mmu-layout.txt.
+        SCR1            MMU     See mmu-layout.txt.
+        SCR2            MMU     Save for EAR0 (destroyed by icache insns in debug mode)
+        SCR3            MMU     Save for GR31 during debug exceptions
+        DAMR/IAMR       NOMMU   Fixed memory protection layout.
+        DAMR/IAMR       MMU     See mmu-layout.txt.
+
+
+Certain registers are also used or modified across function calls:
+
+        REGISTER        CALL                            RETURN
+        =============== =============================== ===============================
+        GR0             Fixed Zero                      -
+        GR2             Function call frame pointer
+        GR3             Special                         Preserved
+        GR3-GR7         -                               Clobbered
+        GR8             Function call arg #1            Return value (or clobbered)
+        GR9             Function call arg #2            Return value MSW (or clobbered)
+        GR10-GR13       Function call arg #3-#6         Clobbered
+        GR14            -                               Clobbered
+        GR15-GR16       Special                         Preserved
+        GR17-GR27       -                               Preserved
+        GR28-GR31       Special                         Only accessed explicitly
+        LR              Return address after CALL       Clobbered
+        CCR/CCCR        -                               Mostly Clobbered
+
+
+================================
+INTERNAL DEBUG-MODE REGISTER ABI
+================================
+
+This is the same as the kernel-mode register ABI for functions calls. The difference is that in
+debug-mode there's a different stack and a different exception frame. Almost all the global
+registers from kernel-mode (including the stack pointer) may be changed.
+
+        REGISTER        FLAVOUR USE
+        =============== ======= ====================================================
+        GR1                     Debug stack pointer
+        GR16                    GP-Rel base register for small data
+        GR31                    Current debug exception frame pointer (__debug_frame)
+        SCR3            MMU     Saved value of GR31
+
+
+Note that debug mode is able to interfere with the kernel's emulated atomic ops, so it must be
+exceedingly careful not to do any that would interact with the main kernel in this regard. Hence
+the debug mode code (gdbstub) is almost completely self-contained. The only external code used is
+the sprintf family of functions.
+
+Futhermore, break.S is so complicated because single-step mode does not switch off on entry to an
+exception. That means unless manually disabled, single-stepping will blithely go on stepping into
+things like interrupts. See gdbstub.txt for more information.
+
+
+==========================
+VIRTUAL INTERRUPT HANDLING
+==========================
+
+Because accesses to the PSR is so slow, and to disable interrupts we have to access it twice (once
+to read and once to write), we don't actually disable interrupts at all if we don't have to. What
+we do instead is use the ICC2 condition code flags to note virtual disablement, such that if we
+then do take an interrupt, we note the flag, really disable interrupts, set another flag and resume
+execution at the point the interrupt happened. Setting condition flags as a side effect of an
+arithmetic or logical instruction is really fast. This use of the ICC2 only occurs within the
+kernel - it does not affect userspace.
+
+The flags we use are:
+
+ (*) CCR.ICC2.Z [Zero flag]
+
+     Set to virtually disable interrupts, clear when interrupts are virtually enabled. Can be
+     modified by logical instructions without affecting the Carry flag.
+
+ (*) CCR.ICC2.C [Carry flag]
+
+     Clear to indicate hardware interrupts are really disabled, set otherwise.
+
+
+What happens is this:
+
+ (1) Normal kernel-mode operation.
+
+        ICC2.Z is 0, ICC2.C is 1.
+
+ (2) An interrupt occurs. The exception prologue examines ICC2.Z and determines that nothing needs
+     doing. This is done simply with an unlikely BEQ instruction.
+
+ (3) The interrupts are disabled (local_irq_disable)
+
+        ICC2.Z is set to 1.
+
+ (4) If interrupts were then re-enabled (local_irq_enable):
+
+        ICC2.Z would be set to 0.
+
+     A TIHI #2 instruction (trap #2 if condition HI - Z==0 && C==0) would be used to trap if
+     interrupts were now virtually enabled, but physically disabled - which they're not, so the
+     trap isn't taken. The kernel would then be back to state (1).
+
+ (5) An interrupt occurs. The exception prologue examines ICC2.Z and determines that the interrupt
+     shouldn't actually have happened. It jumps aside, and there disabled interrupts by setting
+     PSR.PIL to 14 and then it clears ICC2.C.
+
+ (6) If interrupts were then saved and disabled again (local_irq_save):
+
+        ICC2.Z would be shifted into the save variable and masked off (giving a 1).
+
+        ICC2.Z would then be set to 1 (thus unchanged), and ICC2.C would be unaffected (ie: 0).
+
+ (7) If interrupts were then restored from state (6) (local_irq_restore):
+
+        ICC2.Z would be set to indicate the result of XOR'ing the saved value (ie: 1) with 1, which
+        gives a result of 0 - thus leaving ICC2.Z set.
+
+        ICC2.C would remain unaffected (ie: 0).
+
+     A TIHI #2 instruction would be used to again assay the current state, but this would do
+     nothing as Z==1.
+
+ (8) If interrupts were then enabled (local_irq_enable):
+
+        ICC2.Z would be cleared. ICC2.C would be left unaffected. Both flags would now be 0.
+
+     A TIHI #2 instruction again issued to assay the current state would then trap as both Z==0
+     [interrupts virtually enabled] and C==0 [interrupts really disabled] would then be true.
+
+ (9) The trap #2 handler would simply enable hardware interrupts (set PSR.PIL to 0), set ICC2.C to
+     1 and return.
+
+(10) Immediately upon returning, the pending interrupt would be taken.
+
+(11) The interrupt handler would take the path of actually processing the interrupt (ICC2.Z is
+     clear, BEQ fails as per step (2)).
+
+(12) The interrupt handler would then set ICC2.C to 1 since hardware interrupts are definitely
+     enabled - or else the kernel wouldn't be here.
+
+(13) On return from the interrupt handler, things would be back to state (1).
+
+This trap (#2) is only available in kernel mode. In user mode it will result in SIGILL.
diff --git a/Documentation/hwmon/f71805f b/Documentation/hwmon/f71805f
new file mode 100644
index 000000000000..28c5b7d1eb90
--- /dev/null
+++ b/Documentation/hwmon/f71805f
@@ -0,0 +1,105 @@
+Kernel driver f71805f
+=====================
+
+Supported chips:
+  * Fintek F71805F/FG
+    Prefix: 'f71805f'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Provided by Fintek on request
+
+Author: Jean Delvare <khali@linux-fr.org>
+
+Thanks to Denis Kieft from Barracuda Networks for the donation of a
+test system (custom Jetway K8M8MS motherboard, with CPU and RAM) and
+for providing initial documentation.
+
+Thanks to Kris Chen from Fintek for answering technical questions and
+providing additional documentation.
+
+Thanks to Chris Lin from Jetway for providing wiring schematics and
+anwsering technical questions.
+
+
+Description
+-----------
+
+The Fintek F71805F/FG Super I/O chip includes complete hardware monitoring
+capabilities. It can monitor up to 9 voltages (counting its own power
+source), 3 fans and 3 temperature sensors.
+
+This chip also has fan controlling features, using either DC or PWM, in
+three different modes (one manual, two automatic). The driver doesn't
+support these features yet.
+
+The driver assumes that no more than one chip is present, which seems
+reasonable.
+
+
+Voltage Monitoring
+------------------
+
+Voltages are sampled by an 8-bit ADC with a LSB of 8 mV. The supported
+range is thus from 0 to 2.040 V. Voltage values outside of this range
+need external resistors. An exception is in0, which is used to monitor
+the chip's own power source (+3.3V), and is divided internally by a
+factor 2.
+
+The two LSB of the voltage limit registers are not used (always 0), so
+you can only set the limits in steps of 32 mV (before scaling).
+
+The wirings and resistor values suggested by Fintek are as follow:
+
+        pin                                           expected
+        name    use           R1      R2     divider  raw val.
+
+in0     VCC     VCC3.3V     int.    int.        2.00    1.65 V
+in1     VIN1    VTT1.2V      10K       -        1.00    1.20 V
+in2     VIN2    VRAM        100K    100K        2.00   ~1.25 V (1)
+in3     VIN3    VCHIPSET     47K    100K        1.47    2.24 V (2)
+in4     VIN4    VCC5V       200K     47K        5.25    0.95 V
+in5     VIN5    +12V        200K     20K       11.00    1.05 V
+in6     VIN6    VCC1.5V      10K       -        1.00    1.50 V
+in7     VIN7    VCORE        10K       -        1.00   ~1.40 V (1)
+in8     VIN8    VSB5V       200K     47K        1.00    0.95 V
+
+(1) Depends on your hardware setup.
+(2) Obviously not correct, swapping R1 and R2 would make more sense.
+
+These values can be used as hints at best, as motherboard manufacturers
+are free to use a completely different setup. As a matter of fact, the
+Jetway K8M8MS uses a significantly different setup. You will have to
+find out documentation about your own motherboard, and edit sensors.conf
+accordingly.
+
+Each voltage measured has associated low and high limits, each of which
+triggers an alarm when crossed.
+
+
+Fan Monitoring
+--------------
+
+Fan rotation speeds are reported as 12-bit values from a gated clock
+signal. Speeds down to 366 RPM can be measured. There is no theoretical
+high limit, but values over 6000 RPM seem to cause problem. The effective
+resolution is much lower than you would expect, the step between different
+register values being 10 rather than 1.
+
+The chip assumes 2 pulse-per-revolution fans.
+
+An alarm is triggered if the rotation speed drops below a programmable
+limit or is too low to be measured.
+
+
+Temperature Monitoring
+----------------------
+
+Temperatures are reported in degrees Celsius. Each temperature measured
+has a high limit, those crossing triggers an alarm. There is an associated
+hysteresis value, below which the temperature has to drop before the
+alarm is cleared.
+
+All temperature channels are external, there is no embedded temperature
+sensor. Each channel can be used for connecting either a thermal diode
+or a thermistor. The driver reports the currently selected mode, but
+doesn't allow changing it. In theory, the BIOS should have configured
+everything properly.
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index 7f42e441c645..9555be1ed999 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -9,7 +9,7 @@ Supported chips:
                http://www.ite.com.tw/
   * IT8712F
     Prefix: 'it8712'
-    Addresses scanned: I2C 0x28 - 0x2f
+    Addresses scanned: I2C 0x2d
                        from Super I/O config space (8 I/O ports)
     Datasheet: Publicly available at the ITE website
                http://www.ite.com.tw/
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 764cdc5480e7..a0d0ab24288e 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -179,11 +179,12 @@ temp[1-*]_auto_point[1-*]_temp_hyst
 ****************
 
 temp[1-3]_type  Sensor type selection.
-                Integers 1, 2, 3 or thermistor Beta value (3435)
+                Integers 1 to 4 or thermistor Beta value (typically 3435)
                 Read/Write.
                 1: PII/Celeron Diode
                 2: 3904 transistor
                 3: thermal diode
+                4: thermistor (default/unknown Beta)
                 Not all types are supported by all chips
 
 temp[1-4]_max   Temperature max value.
@@ -261,6 +262,21 @@ alarms		Alarm bitmask.
                 of individual bits.
                 Bits are defined in kernel/include/sensors.h.
 
+alarms_in       Alarm bitmask relative to in (voltage) channels
+                Read only
+                A '1' bit means an alarm, LSB corresponds to in0 and so on
+                Prefered to 'alarms' for newer chips
+
+alarms_fan      Alarm bitmask relative to fan channels
+                Read only
+                A '1' bit means an alarm, LSB corresponds to fan1 and so on
+                Prefered to 'alarms' for newer chips
+
+alarms_temp     Alarm bitmask relative to temp (temperature) channels
+                Read only
+                A '1' bit means an alarm, LSB corresponds to temp1 and so on
+                Prefered to 'alarms' for newer chips
+
 beep_enable     Beep/interrupt enable
                 0 to disable.
                 1 to enable.
diff --git a/Documentation/hwmon/w83627hf b/Documentation/hwmon/w83627hf
index 5d23776e9907..bbeaba680443 100644
--- a/Documentation/hwmon/w83627hf
+++ b/Documentation/hwmon/w83627hf
@@ -36,6 +36,10 @@ Module Parameters
   (default is 1)
   Use 'init=0' to bypass initializing the chip.
   Try this if your computer crashes when you load the module.
+* reset: int
+  (default is 0)
+  The driver used to reset the chip on load, but does no more. Use
+  'reset=1' to restore the old behavior. Report if you need to do this.
 
 Description
 -----------
diff --git a/Documentation/i2c/busses/i2c-sis69x b/Documentation/i2c/busses/i2c-sis96x
index b88953dfd580..00a009b977e9 100644
--- a/Documentation/i2c/busses/i2c-sis69x
+++ b/Documentation/i2c/busses/i2c-sis96x
@@ -7,7 +7,7 @@ Supported adapters:
     Any combination of these host bridges:
         645, 645DX (aka 646), 648, 650, 651, 655, 735, 745, 746
     and these south bridges:
-        961, 962, 963(L) 
+        961, 962, 963(L)
 
 Author: Mark M. Hoffman <mhoffman@lightlink.com>
 
@@ -29,7 +29,7 @@ The command "lspci" as root should produce something like these lines:
 
 or perhaps this...
 
-00:00.0 Host bridge: Silicon Integrated Systems [SiS]: Unknown device 0645 
+00:00.0 Host bridge: Silicon Integrated Systems [SiS]: Unknown device 0645
 00:02.0 ISA bridge: Silicon Integrated Systems [SiS]: Unknown device 0961
 00:02.1 SMBus: Silicon Integrated Systems [SiS]: Unknown device 0016
 
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index c406ce67edd0..c65233d430f0 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -45,10 +45,10 @@ How to extract the documentation
 
 If you just want to read the ready-made books on the various
 subsystems (see Documentation/DocBook/*.tmpl), just type 'make
-psdocs', or 'make pdfdocs', or 'make htmldocs', depending on your 
-preference.  If you would rather read a different format, you can type 
-'make sgmldocs' and then use DocBook tools to convert 
-Documentation/DocBook/*.sgml to a format of your choice (for example, 
+psdocs', or 'make pdfdocs', or 'make htmldocs', depending on your
+preference.  If you would rather read a different format, you can type
+'make sgmldocs' and then use DocBook tools to convert
+Documentation/DocBook/*.sgml to a format of your choice (for example,
 'db2html ...' if 'make htmldocs' was not defined).
 
 If you want to see man pages instead, you can do this:
@@ -124,6 +124,36 @@ patterns, which are highlighted appropriately.
 Take a look around the source tree for examples.
 
 
+kernel-doc for structs, unions, enums, and typedefs
+---------------------------------------------------
+
+Beside functions you can also write documentation for structs, unions,
+enums and typedefs. Instead of the function name you must write the name
+of the declaration;  the struct/union/enum/typedef must always precede
+the name. Nesting of declarations is not supported.
+Use the argument mechanism to document members or constants.
+
+Inside a struct description, you can use the "private:" and "public:"
+comment tags.  Structure fields that are inside a "private:" area
+are not listed in the generated output documentation.
+
+Example:
+
+/**
+ * struct my_struct - short description
+ * @a: first member
+ * @b: second member
+ *
+ * Longer description
+ */
+struct my_struct {
+    int a;
+    int b;
+/* private: */
+    int c;
+};
+
+
 How to make new SGML template files
 -----------------------------------
 
@@ -147,4 +177,3 @@ documentation, in <filename>, for the functions listed.
 
 Tim.
 */ <twaugh@redhat.com>
-
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1cbcf65b764b..b874771385cd 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -452,6 +452,11 @@ running once the system is up.
 
         eata=           [HW,SCSI]
 
+        ec_intr=        [HW,ACPI] ACPI Embedded Controller interrupt mode
+                        Format: <int>
+                        0: polling mode
+                        non-0: interrupt mode (default)
+
         eda=            [HW,PS2]
 
         edb=            [HW,PS2]
@@ -1128,6 +1133,8 @@ running once the system is up.
                                 Mechanism 1.
                 conf2           [IA-32] Force use of PCI Configuration
                                 Mechanism 2.
+                nommconf        [IA-32,X86_64] Disable use of MMCONFIG for PCI
+                                Configuration
                 nosort          [IA-32] Don't sort PCI devices according to
                                 order given by the PCI BIOS. This sorting is
                                 done to get a device order compatible with
@@ -1631,6 +1638,9 @@ running once the system is up.
                         Format:
                         <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
 
+        norandmaps      Don't use address space randomization
+                        Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space
+
 
 ______________________________________________________________________
 Changelog:
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 0ea5a0c6e827..2c3b1eae4280 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -136,17 +136,20 @@ Kprobes, jprobes, and return probes are implemented on the following
 architectures:
 
 - i386
-- x86_64 (AMD-64, E64MT)
+- x86_64 (AMD-64, EM64T)
 - ppc64
-- ia64 (Support for probes on certain instruction types is still in progress.)
+- ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
 
 3. Configuring Kprobes
 
 When configuring the kernel using make menuconfig/xconfig/oldconfig,
-ensure that CONFIG_KPROBES is set to "y".  Under "Kernel hacking",
-look for "Kprobes".  You may have to enable "Kernel debugging"
-(CONFIG_DEBUG_KERNEL) before you can enable Kprobes.
+ensure that CONFIG_KPROBES is set to "y".  Under "Instrumentation
+Support", look for "Kprobes".
+
+So that you can load and unload Kprobes-based instrumentation modules,
+make sure "Loadable module support" (CONFIG_MODULES) and "Module
+unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
 
 You may also want to ensure that CONFIG_KALLSYMS and perhaps even
 CONFIG_KALLSYMS_ALL are set to "y", since kallsyms_lookup_name()
@@ -262,18 +265,18 @@ at any time after the probe has been registered.
 
 5. Kprobes Features and Limitations
 
-As of Linux v2.6.12, Kprobes allows multiple probes at the same
-address.  Currently, however, there cannot be multiple jprobes on
-the same function at the same time.
+Kprobes allows multiple probes at the same address.  Currently,
+however, there cannot be multiple jprobes on the same function at
+the same time.
 
 In general, you can install a probe anywhere in the kernel.
 In particular, you can probe interrupt handlers.  Known exceptions
 are discussed in this section.
 
-For obvious reasons, it's a bad idea to install a probe in
-the code that implements Kprobes (mostly kernel/kprobes.c and
-arch/*/kernel/kprobes.c).  A patch in the v2.6.13 timeframe instructs
-Kprobes to reject such requests.
+The register_*probe functions will return -EINVAL if you attempt
+to install a probe in the code that implements Kprobes (mostly
+kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such
+as do_page_fault and notifier_call_chain).
 
 If you install a probe in an inline-able function, Kprobes makes
 no attempt to chase down all inline instances of the function and
@@ -290,18 +293,14 @@ from the accidental ones.  Don't drink and probe.
 
 Kprobes makes no attempt to prevent probe handlers from stepping on
 each other -- e.g., probing printk() and then calling printk() from a
-probe handler.  As of Linux v2.6.12, if a probe handler hits a probe,
-that second probe's handlers won't be run in that instance.
-
-In Linux v2.6.12 and previous versions, Kprobes' data structures are
-protected by a single lock that is held during probe registration and
-unregistration and while handlers are run.  Thus, no two handlers
-can run simultaneously.  To improve scalability on SMP systems,
-this restriction will probably be removed soon, in which case
-multiple handlers (or multiple instances of the same handler) may
-run concurrently on different CPUs.  Code your handlers accordingly.
-
-Kprobes does not use semaphores or allocate memory except during
+probe handler.  If a probe handler hits a probe, that second probe's
+handlers won't be run in that instance, and the kprobe.nmissed member
+of the second probe will be incremented.
+
+As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
+the same handler) may run concurrently on different CPUs.
+
+Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
 Probe handlers are run with preemption disabled.  Depending on the
@@ -316,11 +315,18 @@ address instead of the real return address for kretprobed functions.
 (As far as we can tell, __builtin_return_address() is used only
 for instrumentation and error reporting.)
 
-If the number of times a function is called does not match the
-number of times it returns, registering a return probe on that
-function may produce undesirable results.  We have the do_exit()
-and do_execve() cases covered.  do_fork() is not an issue.  We're
-unaware of other specific cases where this could be a problem.
+If the number of times a function is called does not match the number
+of times it returns, registering a return probe on that function may
+produce undesirable results.  We have the do_exit() case covered.
+do_execve() and do_fork() are not an issue.  We're unaware of other
+specific cases where this could be a problem.
+
+If, upon entry to or exit from a function, the CPU is running on
+a stack other than that of the current task, registering a return
+probe on that function may produce undesirable results.  For this
+reason, Kprobes doesn't support return probes (or kprobes or jprobes)
+on the x86_64 version of __switch_to(); the registration functions
+return -EINVAL.
 
 6. Probe Overhead
 
@@ -347,14 +353,12 @@ k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
 
 7. TODO
 
-a. SystemTap (http://sourceware.org/systemtap): Work in progress
-to provide a simplified programming interface for probe-based
-instrumentation.
-b. Improved SMP scalability: Currently, work is in progress to handle
-multiple kprobes in parallel.
-c. Kernel return probes for sparc64.
-d. Support for other architectures.
-e. User-space probes.
+a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
+programming interface for probe-based instrumentation.  Try it out.
+b. Kernel return probes for sparc64.
+c. Support for other architectures.
+d. User-space probes.
+e. Watchpoint probes (which fire on data references).
 
 8. Kprobes Example
 
@@ -411,8 +415,7 @@ int init_module(void)
                 printk("Couldn't find %s to plant kprobe\n", "do_fork");
                 return -1;
         }
-        ret = register_kprobe(&kp);
-        if (ret < 0) {
+        if ((ret = register_kprobe(&kp) < 0)) {
                 printk("register_kprobe failed, returned %d\n", ret);
                 return -1;
         }
diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README
index a7e4c4ea3560..afb31c141d9d 100644
--- a/Documentation/mips/AU1xxx_IDE.README
+++ b/Documentation/mips/AU1xxx_IDE.README
@@ -95,11 +95,13 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
 CONFIG_IDEDMA_PCI_AUTO=y
 CONFIG_BLK_DEV_IDE_AU1XXX=y
 CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y
-CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON=y
 CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
 CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_IDEDMA_AUTO=y
 
+Also define 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to enable
+the burst support on DBDMA controller.
+
 If the used system need the USB support enable the following kernel configs for
 high IDE to USB throughput.
 
@@ -115,6 +117,8 @@ CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
 CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_IDEDMA_AUTO=y
 
+Also undefine 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to
+disable the burst support on DBDMA controller.
 
 ADD NEW HARD DISC TO WHITE OR BLACK LIST
 ----------------------------------------
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 2b7cf19a06ad..26364d06ae92 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -427,6 +427,23 @@ icmp_ignore_bogus_error_responses - BOOLEAN
         will avoid log file clutter.
         Default: FALSE
 
+icmp_errors_use_inbound_ifaddr - BOOLEAN
+
+        If zero, icmp error messages are sent with the primary address of
+        the exiting interface.
+ 
+        If non-zero, the message will be sent with the primary address of
+        the interface that received the packet that caused the icmp error.
+        This is the behaviour network many administrators will expect from
+        a router. And it can make debugging complicated network layouts
+        much easier. 
+
+        Note that if no primary address exists for the interface selected,
+        then the primary address of the first non-loopback interface that
+        has one will be used regarldess of this setting.
+
+        Default: 0
+
 igmp_max_memberships - INTEGER
         Change the maximum number of multicast groups we can subscribe to.
         Default: 20
diff --git a/Documentation/parport-lowlevel.txt b/Documentation/parport-lowlevel.txt
index 1d40008a1926..8f2302415eff 100644
--- a/Documentation/parport-lowlevel.txt
+++ b/Documentation/parport-lowlevel.txt
@@ -1068,7 +1068,7 @@ SYNOPSIS
 
 struct parport_operations {
         ...
-        void (*write_status) (struct parport *port, unsigned char s);
+        void (*write_control) (struct parport *port, unsigned char s);
         ...
 };
 
@@ -1097,9 +1097,9 @@ SYNOPSIS
 
 struct parport_operations {
         ...
-        void (*frob_control) (struct parport *port,
-                              unsigned char mask,
-                              unsigned char val);
+        unsigned char (*frob_control) (struct parport *port,
+                                       unsigned char mask,
+                                       unsigned char val);
         ...
 };
 
diff --git a/Documentation/pci-error-recovery.txt b/Documentation/pci-error-recovery.txt
index d089967e4948..634d3e5b5756 100644
--- a/Documentation/pci-error-recovery.txt
+++ b/Documentation/pci-error-recovery.txt
@@ -1,246 +1,396 @@
 
                        PCI Error Recovery
                        ------------------
-                         May 31, 2005
-
-               Current document maintainer:
-           Linas Vepstas <linas@austin.ibm.com>
-
-
-Some PCI bus controllers are able to detect certain "hard" PCI errors
-on the bus, such as parity errors on the data and address busses, as
-well as SERR and PERR errors.  These chipsets are then able to disable
-I/O to/from the affected device, so that, for example, a bad DMA
-address doesn't end up corrupting system memory.  These same chipsets
-are also able to reset the affected PCI device, and return it to
-working condition.  This document describes a generic API form
-performing error recovery.
-
-The core idea is that after a PCI error has been detected, there must
-be a way for the kernel to coordinate with all affected device drivers
-so that the pci card can be made operational again, possibly after
-performing a full electrical #RST of the PCI card.  The API below
-provides a generic API for device drivers to be notified of PCI
-errors, and to be notified of, and respond to, a reset sequence.
-
-Preliminary sketch of API, cut-n-pasted-n-modified email from
-Ben Herrenschmidt, circa 5 april 2005
+                        February 2, 2006
+
+                 Current document maintainer:
+             Linas Vepstas <linas@austin.ibm.com>
+
+
+Many PCI bus controllers are able to detect a variety of hardware
+PCI errors on the bus, such as parity errors on the data and address
+busses, as well as SERR and PERR errors.  Some of the more advanced
+chipsets are able to deal with these errors; these include PCI-E chipsets,
+and the PCI-host bridges found on IBM Power4 and Power5-based pSeries
+boxes. A typical action taken is to disconnect the affected device,
+halting all I/O to it.  The goal of a disconnection is to avoid system
+corruption; for example, to halt system memory corruption due to DMA's
+to "wild" addresses. Typically, a reconnection mechanism is also
+offered, so that the affected PCI device(s) are reset and put back
+into working condition. The reset phase requires coordination
+between the affected device drivers and the PCI controller chip.
+This document describes a generic API for notifying device drivers
+of a bus disconnection, and then performing error recovery.
+This API is currently implemented in the 2.6.16 and later kernels.
+
+Reporting and recovery is performed in several steps. First, when
+a PCI hardware error has resulted in a bus disconnect, that event
+is reported as soon as possible to all affected device drivers,
+including multiple instances of a device driver on multi-function
+cards. This allows device drivers to avoid deadlocking in spinloops,
+waiting for some i/o-space register to change, when it never will.
+It also gives the drivers a chance to defer incoming I/O as
+needed.
+
+Next, recovery is performed in several stages. Most of the complexity
+is forced by the need to handle multi-function devices, that is,
+devices that have multiple device drivers associated with them.
+In the first stage, each driver is allowed to indicate what type
+of reset it desires, the choices being a simple re-enabling of I/O
+or requesting a hard reset (a full electrical #RST of the PCI card).
+If any driver requests a full reset, that is what will be done.
+
+After a full reset and/or a re-enabling of I/O, all drivers are
+again notified, so that they may then perform any device setup/config
+that may be required.  After these have all completed, a final
+"resume normal operations" event is sent out.
+
+The biggest reason for choosing a kernel-based implementation rather
+than a user-space implementation was the need to deal with bus
+disconnects of PCI devices attached to storage media, and, in particular,
+disconnects from devices holding the root file system.  If the root
+file system is disconnected, a user-space mechanism would have to go
+through a large number of contortions to complete recovery. Almost all
+of the current Linux file systems are not tolerant of disconnection
+from/reconnection to their underlying block device. By contrast,
+bus errors are easy to manage in the device driver. Indeed, most
+device drivers already handle very similar recovery procedures;
+for example, the SCSI-generic layer already provides significant
+mechanisms for dealing with SCSI bus errors and SCSI bus resets.
+
+
+Detailed Design
+---------------
+Design and implementation details below, based on a chain of
+public email discussions with Ben Herrenschmidt, circa 5 April 2005.
 
 The error recovery API support is exposed to the driver in the form of
 a structure of function pointers pointed to by a new field in struct
-pci_driver. The absence of this pointer in pci_driver denotes an
-"non-aware" driver, behaviour on these is platform dependant.
-Platforms like ppc64 can try to simulate pci hotplug remove/add.
-
-The definition of "pci_error_token" is not covered here. It is based on
-Seto's work on the synchronous error detection. We still need to define
-functions for extracting infos out of an opaque error token. This is
-separate from this API.
+pci_driver. A driver that fails to provide the structure is "non-aware",
+and the actual recovery steps taken are platform dependent.  The
+arch/powerpc implementation will simulate a PCI hotplug remove/add.
 
 This structure has the form:
-
 struct pci_error_handlers
 {
-        int (*error_detected)(struct pci_dev *dev, pci_error_token error);
+        int (*error_detected)(struct pci_dev *dev, enum pci_channel_state);
         int (*mmio_enabled)(struct pci_dev *dev);
-        int (*resume)(struct pci_dev *dev);
         int (*link_reset)(struct pci_dev *dev);
         int (*slot_reset)(struct pci_dev *dev);
+        void (*resume)(struct pci_dev *dev);
 };
 
-A driver doesn't have to implement all of these callbacks. The
-only mandatory one is error_detected(). If a callback is not
-implemented, the corresponding feature is considered unsupported.
-For example, if mmio_enabled() and resume() aren't there, then the
-driver is assumed as not doing any direct recovery and requires
+The possible channel states are:
+enum pci_channel_state {
+        pci_channel_io_normal,  /* I/O channel is in normal state */
+        pci_channel_io_frozen,  /* I/O to channel is blocked */
+        pci_channel_io_perm_failure, /* PCI card is dead */
+};
+
+Possible return values are:
+enum pci_ers_result {
+        PCI_ERS_RESULT_NONE,        /* no result/none/not supported in device driver */
+        PCI_ERS_RESULT_CAN_RECOVER, /* Device driver can recover without slot reset */
+        PCI_ERS_RESULT_NEED_RESET,  /* Device driver wants slot to be reset. */
+        PCI_ERS_RESULT_DISCONNECT,  /* Device has completely failed, is unrecoverable */
+        PCI_ERS_RESULT_RECOVERED,   /* Device driver is fully recovered and operational */
+};
+
+A driver does not have to implement all of these callbacks; however,
+if it implements any, it must implement error_detected(). If a callback
+is not implemented, the corresponding feature is considered unsupported.
+For example, if mmio_enabled() and resume() aren't there, then it
+is assumed that the driver is not doing any direct recovery and requires
 a reset. If link_reset() is not implemented, the card is assumed as
-not caring about link resets, in which case, if recover is supported,
-the core can try recover (but not slot_reset() unless it really did
-reset the slot). If slot_reset() is not supported, link_reset() can
-be called instead on a slot reset.
-
-At first, the call will always be :
-
-        1) error_detected()
-
-        Error detected. This is sent once after an error has been detected. At
-this point, the device might not be accessible anymore depending on the
-platform (the slot will be isolated on ppc64). The driver may already
-have "noticed" the error because of a failing IO, but this is the proper
-"synchronisation point", that is, it gives a chance to the driver to
-cleanup, waiting for pending stuff (timers, whatever, etc...) to
-complete; it can take semaphores, schedule, etc... everything but touch
-the device. Within this function and after it returns, the driver
+not care about link resets. Typically a driver will want to know about
+a slot_reset().
+
+The actual steps taken by a platform to recover from a PCI error
+event will be platform-dependent, but will follow the general
+sequence described below.
+
+STEP 0: Error Event
+-------------------
+PCI bus error is detect by the PCI hardware.  On powerpc, the slot
+is isolated, in that all I/O is blocked: all reads return 0xffffffff,
+all writes are ignored.
+
+
+STEP 1: Notification
+--------------------
+Platform calls the error_detected() callback on every instance of
+every driver affected by the error.
+
+At this point, the device might not be accessible anymore, depending on
+the platform (the slot will be isolated on powerpc). The driver may
+already have "noticed" the error because of a failing I/O, but this
+is the proper "synchronization point", that is, it gives the driver
+a chance to cleanup, waiting for pending stuff (timers, whatever, etc...)
+to complete; it can take semaphores, schedule, etc... everything but
+touch the device. Within this function and after it returns, the driver
 shouldn't do any new IOs. Called in task context. This is sort of a
 "quiesce" point. See note about interrupts at the end of this doc.
 
-        Result codes:
-                - PCIERR_RESULT_CAN_RECOVER:
-                  Driever returns this if it thinks it might be able to recover
+All drivers participating in this system must implement this call.
+The driver must return one of the following result codes:
+                - PCI_ERS_RESULT_CAN_RECOVER:
+                  Driver returns this if it thinks it might be able to recover
                   the HW by just banging IOs or if it wants to be given
-                  a chance to extract some diagnostic informations (see
-                  below).
-                - PCIERR_RESULT_NEED_RESET:
-                  Driver returns this if it thinks it can't recover unless the
-                  slot is reset.
-                - PCIERR_RESULT_DISCONNECT:
-                  Return this if driver thinks it won't recover at all,
-                  (this will detach the driver ? or just leave it
-                  dangling ? to be decided)
-
-So at this point, we have called error_detected() for all drivers
-on the segment that had the error. On ppc64, the slot is isolated. What
-happens now typically depends on the result from the drivers. If all
-drivers on the segment/slot return PCIERR_RESULT_CAN_RECOVER, we would
-re-enable IOs on the slot (or do nothing special if the platform doesn't
-isolate slots) and call 2). If not and we can reset slots, we go to 4),
-if neither, we have a dead slot. If it's an hotplug slot, we might
-"simulate" reset by triggering HW unplug/replug though.
-
->>> Current ppc64 implementation assumes that a device driver will
->>> *not* schedule or semaphore in this routine; the current ppc64
+                  a chance to extract some diagnostic information (see
+                  mmio_enable, below).
+                - PCI_ERS_RESULT_NEED_RESET:
+                  Driver returns this if it can't recover without a hard
+                  slot reset.
+                - PCI_ERS_RESULT_DISCONNECT:
+                  Driver returns this if it doesn't want to recover at all.
+
+The next step taken will depend on the result codes returned by the
+drivers.
+
+If all drivers on the segment/slot return PCI_ERS_RESULT_CAN_RECOVER,
+then the platform should re-enable IOs on the slot (or do nothing in
+particular, if the platform doesn't isolate slots), and recovery
+proceeds to STEP 2 (MMIO Enable).
+
+If any driver requested a slot reset (by returning PCI_ERS_RESULT_NEED_RESET),
+then recovery proceeds to STEP 4 (Slot Reset).
+
+If the platform is unable to recover the slot, the next step
+is STEP 6 (Permanent Failure).
+
+>>> The current powerpc implementation assumes that a device driver will
+>>> *not* schedule or semaphore in this routine; the current powerpc
 >>> implementation uses one kernel thread to notify all devices;
->>> thus, of one device sleeps/schedules, all devices are affected.
+>>> thus, if one device sleeps/schedules, all devices are affected.
 >>> Doing better requires complex multi-threaded logic in the error
 >>> recovery implementation (e.g. waiting for all notification threads
 >>> to "join" before proceeding with recovery.)  This seems excessively
 >>> complex and not worth implementing.
 
->>> The current ppc64 implementation doesn't much care if the device
->>> attempts i/o at this point, or not.  I/O's will fail, returning
+>>> The current powerpc implementation doesn't much care if the device
+>>> attempts I/O at this point, or not.  I/O's will fail, returning
 >>> a value of 0xff on read, and writes will be dropped. If the device
 >>> driver attempts more than 10K I/O's to a frozen adapter, it will
 >>> assume that the device driver has gone into an infinite loop, and
->>> it will panic the the kernel.
+>>> it will panic the the kernel. There doesn't seem to be any other
+>>> way of stopping a device driver that insists on spinning on I/O.
 
-        2) mmio_enabled()
+STEP 2: MMIO Enabled
+-------------------
+The platform re-enables MMIO to the device (but typically not the
+DMA), and then calls the mmio_enabled() callback on all affected
+device drivers.
 
-        This is the "early recovery" call. IOs are allowed again, but DMA is
+This is the "early recovery" call. IOs are allowed again, but DMA is
 not (hrm... to be discussed, I prefer not), with some restrictions. This
 is NOT a callback for the driver to start operations again, only to
 peek/poke at the device, extract diagnostic information, if any, and
 eventually do things like trigger a device local reset or some such,
-but not restart operations. This is sent if all drivers on a segment
-agree that they can try to recover and no automatic link reset was
-performed by the HW. If the platform can't just re-enable IOs without
-a slot reset or a link reset, it doesn't call this callback and goes
-directly to 3) or 4). All IOs should be done _synchronously_ from
-within this callback, errors triggered by them will be returned via
-the normal pci_check_whatever() api, no new error_detected() callback
-will be issued due to an error happening here. However, such an error
-might cause IOs to be re-blocked for the whole segment, and thus
-invalidate the recovery that other devices on the same segment might
-have done, forcing the whole segment into one of the next states,
-that is link reset or slot reset.
-
-        Result codes:
-                - PCIERR_RESULT_RECOVERED
+but not restart operations. This is callback is made if all drivers on
+a segment agree that they can try to recover and if no automatic link reset
+was performed by the HW. If the platform can't just re-enable IOs without
+a slot reset or a link reset, it wont call this callback, and instead
+will have gone directly to STEP 3 (Link Reset) or STEP 4 (Slot Reset)
+
+>>> The following is proposed; no platform implements this yet:
+>>> Proposal: All I/O's should be done _synchronously_ from within
+>>> this callback, errors triggered by them will be returned via
+>>> the normal pci_check_whatever() API, no new error_detected()
+>>> callback will be issued due to an error happening here. However,
+>>> such an error might cause IOs to be re-blocked for the whole
+>>> segment, and thus invalidate the recovery that other devices
+>>> on the same segment might have done, forcing the whole segment
+>>> into one of the next states, that is, link reset or slot reset.
+
+The driver should return one of the following result codes:
+                - PCI_ERS_RESULT_RECOVERED
                   Driver returns this if it thinks the device is fully
-                  functionnal and thinks it is ready to start
+                  functional and thinks it is ready to start
                   normal driver operations again. There is no
                   guarantee that the driver will actually be
                   allowed to proceed, as another driver on the
                   same segment might have failed and thus triggered a
                   slot reset on platforms that support it.
 
-                - PCIERR_RESULT_NEED_RESET
+                - PCI_ERS_RESULT_NEED_RESET
                   Driver returns this if it thinks the device is not
                   recoverable in it's current state and it needs a slot
                   reset to proceed.
 
-                - PCIERR_RESULT_DISCONNECT
+                - PCI_ERS_RESULT_DISCONNECT
                   Same as above. Total failure, no recovery even after
                   reset driver dead. (To be defined more precisely)
 
->>> The current ppc64 implementation does not implement this callback.
+The next step taken depends on the results returned by the drivers.
+If all drivers returned PCI_ERS_RESULT_RECOVERED, then the platform
+proceeds to either STEP3 (Link Reset) or to STEP 5 (Resume Operations).
+
+If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform
+proceeds to STEP 4 (Slot Reset)
 
-        3) link_reset()
+>>> The current powerpc implementation does not implement this callback.
 
-        This is called after the link has been reset. This is typically
-a PCI Express specific state at this point and is done whenever a
-non-fatal error has been detected that can be "solved" by resetting
-the link. This call informs the driver of the reset and the driver
-should check if the device appears to be in working condition.
-This function acts a bit like 2) mmio_enabled(), in that the driver
-is not supposed to restart normal driver I/O operations right away.
-Instead, it should just "probe" the device to check it's recoverability
-status. If all is right, then the core will call resume() once all
-drivers have ack'd link_reset().
+
+STEP 3: Link Reset
+------------------
+The platform resets the link, and then calls the link_reset() callback
+on all affected device drivers.  This is a PCI-Express specific state
+and is done whenever a non-fatal error has been detected that can be
+"solved" by resetting the link. This call informs the driver of the
+reset and the driver should check to see if the device appears to be
+in working condition.
+
+The driver is not supposed to restart normal driver I/O operations
+at this point.  It should limit itself to "probing" the device to
+check it's recoverability status. If all is right, then the platform
+will call resume() once all drivers have ack'd link_reset().
 
         Result codes:
-                (identical to mmio_enabled)
+                (identical to STEP 3 (MMIO Enabled)
+
+The platform then proceeds to either STEP 4 (Slot Reset) or STEP 5
+(Resume Operations).
+
+>>> The current powerpc implementation does not implement this callback.
+
+
+STEP 4: Slot Reset
+------------------
+The platform performs a soft or hard reset of the device, and then
+calls the slot_reset() callback.
+
+A soft reset consists of asserting the adapter #RST line and then
+restoring the PCI BAR's and PCI configuration header to a state
+that is equivalent to what it would be after a fresh system
+power-on followed by power-on BIOS/system firmware initialization.
+If the platform supports PCI hotplug, then the reset might be
+performed by toggling the slot electrical power off/on.
 
->>> The current ppc64 implementation does not implement this callback.
+It is important for the platform to restore the PCI config space
+to the "fresh poweron" state, rather than the "last state". After
+a slot reset, the device driver will almost always use its standard
+device initialization routines, and an unusual config space setup
+may result in hung devices, kernel panics, or silent data corruption.
 
-        4) slot_reset()
+This call gives drivers the chance to re-initialize the hardware
+(re-download firmware, etc.).  At this point, the driver may assume
+that he card is in a fresh state and is fully functional. In
+particular, interrupt generation should work normally.
 
-        This is called after the slot has been soft or hard reset by the
-platform.  A soft reset consists of asserting the adapter #RST line
-and then restoring the PCI BARs and PCI configuration header. If the
-platform supports PCI hotplug, then it might instead perform a hard
-reset by toggling power on the slot off/on. This call gives drivers
-the chance to re-initialize the hardware (re-download firmware, etc.),
-but drivers shouldn't restart normal I/O processing operations at
-this point.  (See note about interrupts; interrupts aren't guaranteed
-to be delivered until the resume() callback has been called). If all
-device drivers report success on this callback, the patform will call
-resume() to complete the error handling and let the driver restart
-normal I/O processing.
+Drivers should not yet restart normal I/O processing operations
+at this point.  If all device drivers report success on this
+callback, the platform will call resume() to complete the sequence,
+and let the driver restart normal I/O processing.
 
 A driver can still return a critical failure for this function if
 it can't get the device operational after reset.  If the platform
-previously tried a soft reset, it migh now try a hard reset (power
+previously tried a soft reset, it might now try a hard reset (power
 cycle) and then call slot_reset() again.  It the device still can't
 be recovered, there is nothing more that can be done;  the platform
 will typically report a "permanent failure" in such a case.  The
 device will be considered "dead" in this case.
 
-        Result codes:
-                - PCIERR_RESULT_DISCONNECT
-                Same as above.
+Drivers for multi-function cards will need to coordinate among
+themselves as to which driver instance will perform any "one-shot"
+or global device initialization. For example, the Symbios sym53cxx2
+driver performs device init only from PCI function 0:
 
->>> The current ppc64 implementation does not try a power-cycle reset
->>> if the driver returned PCIERR_RESULT_DISCONNECT. However, it should.
++       if (PCI_FUNC(pdev->devfn) == 0)
++               sym_reset_scsi_bus(np, 0);
 
-        5) resume()
-
-        This is called if all drivers on the segment have returned
-PCIERR_RESULT_RECOVERED from one of the 3 prevous callbacks.
-That basically tells the driver to restart activity, tht everything
-is back and running. No result code is taken into account here. If
-a new error happens, it will restart a new error handling process.
+        Result codes:
+                - PCI_ERS_RESULT_DISCONNECT
+                Same as above.
 
-That's it. I think this covers all the possibilities. The way those
-callbacks are called is platform policy. A platform with no slot reset
-capability for example may want to just "ignore" drivers that can't
+Platform proceeds either to STEP 5 (Resume Operations) or STEP 6 (Permanent
+Failure).
+
+>>> The current powerpc implementation does not currently try a
+>>> power-cycle reset if the driver returned PCI_ERS_RESULT_DISCONNECT.
+>>> However, it probably should.
+
+
+STEP 5: Resume Operations
+-------------------------
+The platform will call the resume() callback on all affected device
+drivers if all drivers on the segment have returned
+PCI_ERS_RESULT_RECOVERED from one of the 3 previous callbacks.
+The goal of this callback is to tell the driver to restart activity,
+that everything is back and running. This callback does not return
+a result code.
+
+At this point, if a new error happens, the platform will restart
+a new error recovery sequence.
+
+STEP 6: Permanent Failure
+-------------------------
+A "permanent failure" has occurred, and the platform cannot recover
+the device.  The platform will call error_detected() with a
+pci_channel_state value of pci_channel_io_perm_failure.
+
+The device driver should, at this point, assume the worst. It should
+cancel all pending I/O, refuse all new I/O, returning -EIO to
+higher layers. The device driver should then clean up all of its
+memory and remove itself from kernel operations, much as it would
+during system shutdown.
+
+The platform will typically notify the system operator of the
+permanent failure in some way.  If the device is hotplug-capable,
+the operator will probably want to remove and replace the device.
+Note, however, not all failures are truly "permanent". Some are
+caused by over-heating, some by a poorly seated card. Many
+PCI error events are caused by software bugs, e.g. DMA's to
+wild addresses or bogus split transactions due to programming
+errors. See the discussion in powerpc/eeh-pci-error-recovery.txt
+for additional detail on real-life experience of the causes of
+software errors.
+
+
+Conclusion; General Remarks
+---------------------------
+The way those callbacks are called is platform policy. A platform with
+no slot reset capability may want to just "ignore" drivers that can't
 recover (disconnect them) and try to let other cards on the same segment
 recover. Keep in mind that in most real life cases, though, there will
 be only one driver per segment.
 
-Now, there is a note about interrupts. If you get an interrupt and your
+Now, a note about interrupts. If you get an interrupt and your
 device is dead or has been isolated, there is a problem :)
-
-After much thinking, I decided to leave that to the platform. That is,
-the recovery API only precies that:
+The current policy is to turn this into a platform policy.
+That is, the recovery API only requires that:
 
  - There is no guarantee that interrupt delivery can proceed from any
 device on the segment starting from the error detection and until the
-restart callback is sent, at which point interrupts are expected to be
+resume callback is sent, at which point interrupts are expected to be
 fully operational.
 
- - There is no guarantee that interrupt delivery is stopped, that is, ad
-river that gets an interrupts after detecting an error, or that detects
-and error within the interrupt handler such that it prevents proper
+ - There is no guarantee that interrupt delivery is stopped, that is,
+a driver that gets an interrupt after detecting an error, or that detects
+an error within the interrupt handler such that it prevents proper
 ack'ing of the interrupt (and thus removal of the source) should just
-return IRQ_NOTHANDLED. It's up to the platform to deal with taht
-condition, typically by masking the irq source during the duration of
+return IRQ_NOTHANDLED. It's up to the platform to deal with that
+condition, typically by masking the IRQ source during the duration of
 the error handling. It is expected that the platform "knows" which
 interrupts are routed to error-management capable slots and can deal
-with temporarily disabling that irq number during error processing (this
+with temporarily disabling that IRQ number during error processing (this
 isn't terribly complex). That means some IRQ latency for other devices
 sharing the interrupt, but there is simply no other way. High end
 platforms aren't supposed to share interrupts between many devices
 anyway :)
 
-
-Revised: 31 May 2005 Linas Vepstas <linas@austin.ibm.com>
+>>> Implementation details for the powerpc platform are discussed in
+>>> the file Documentation/powerpc/eeh-pci-error-recovery.txt
+
+>>> As of this writing, there are six device drivers with patches
+>>> implementing error recovery. Not all of these patches are in
+>>> mainline yet. These may be used as "examples":
+>>>
+>>> drivers/scsi/ipr.c
+>>> drivers/scsi/sym53cxx_2
+>>> drivers/next/e100.c
+>>> drivers/net/e1000
+>>> drivers/net/ixgb
+>>> drivers/net/s2io.c
+
+The End
+-------
diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt
index bd4ffb5bd49a..4117802af0f8 100644
--- a/Documentation/power/interface.txt
+++ b/Documentation/power/interface.txt
@@ -44,7 +44,7 @@ it.
 /sys/power/image_size controls the size of the image created by
 the suspend-to-disk mechanism.  It can be written a string
 representing a non-negative integer that will be used as an upper
-limit of the image size, in megabytes.  The suspend-to-disk mechanism will
+limit of the image size, in bytes.  The suspend-to-disk mechanism will
 do its best to ensure the image size will not exceed that number.  However,
 if this turns out to be impossible, it will try to suspend anyway using the
 smallest image possible.  In particular, if "0" is written to this file, the
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 08c79d4dc540..b28b7f04abb8 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -27,7 +27,7 @@ echo shutdown > /sys/power/disk; echo disk > /sys/power/state
 
 echo platform > /sys/power/disk; echo disk > /sys/power/state
 
-If you want to limit the suspend image size to N megabytes, do
+If you want to limit the suspend image size to N bytes, do
 
 echo N > /sys/power/image_size
 
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
new file mode 100644
index 000000000000..d02c64953dcd
--- /dev/null
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -0,0 +1,1486 @@
+           Booting the Linux/ppc kernel without Open Firmware
+           --------------------------------------------------
+
+
+(c) 2005 Benjamin Herrenschmidt <benh at kernel.crashing.org>,
+    IBM Corp.
+(c) 2005 Becky Bruce <becky.bruce at freescale.com>,
+    Freescale Semiconductor, FSL SOC and 32-bit additions
+
+   May 18, 2005: Rev 0.1 - Initial draft, no chapter III yet.
+
+   May 19, 2005: Rev 0.2 - Add chapter III and bits & pieces here or
+                           clarifies the fact that a lot of things are
+                           optional, the kernel only requires a very
+                           small device tree, though it is encouraged
+                           to provide an as complete one as possible.
+
+   May 24, 2005: Rev 0.3 - Precise that DT block has to be in RAM
+                         - Misc fixes
+                         - Define version 3 and new format version 16
+                           for the DT block (version 16 needs kernel
+                           patches, will be fwd separately).
+                           String block now has a size, and full path
+                           is replaced by unit name for more
+                           compactness.
+                           linux,phandle is made optional, only nodes
+                           that are referenced by other nodes need it.
+                           "name" property is now automatically
+                           deduced from the unit name
+
+   June 1, 2005: Rev 0.4 - Correct confusion between OF_DT_END and
+                           OF_DT_END_NODE in structure definition.
+                         - Change version 16 format to always align
+                           property data to 4 bytes. Since tokens are
+                           already aligned, that means no specific
+                           required alignement between property size
+                           and property data. The old style variable
+                           alignment would make it impossible to do
+                           "simple" insertion of properties using
+                           memove (thanks Milton for
+                           noticing). Updated kernel patch as well
+                         - Correct a few more alignement constraints
+                         - Add a chapter about the device-tree
+                           compiler and the textural representation of
+                           the tree that can be "compiled" by dtc.
+
+   November 21, 2005: Rev 0.5
+                         - Additions/generalizations for 32-bit
+                         - Changed to reflect the new arch/powerpc
+                           structure
+                         - Added chapter VI
+
+
+ ToDo:
+        - Add some definitions of interrupt tree (simple/complex)
+        - Add some definitions for pci host bridges
+        - Add some common address format examples
+        - Add definitions for standard properties and "compatible"
+          names for cells that are not already defined by the existing
+          OF spec.
+        - Compare FSL SOC use of PCI to standard and make sure no new
+          node definition required.
+        - Add more information about node definitions for SOC devices
+          that currently have no standard, like the FSL CPM.
+
+
+I - Introduction
+================
+
+During the recent development of the Linux/ppc64 kernel, and more
+specifically, the addition of new platform types outside of the old
+IBM pSeries/iSeries pair, it was decided to enforce some strict rules
+regarding the kernel entry and bootloader <-> kernel interfaces, in
+order to avoid the degeneration that had become the ppc32 kernel entry
+point and the way a new platform should be added to the kernel. The
+legacy iSeries platform breaks those rules as it predates this scheme,
+but no new board support will be accepted in the main tree that
+doesn't follows them properly.  In addition, since the advent of the
+arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit
+platforms and 32-bit platforms which move into arch/powerpc will be
+required to use these rules as well.
+
+The main requirement that will be defined in more detail below is
+the presence of a device-tree whose format is defined after Open
+Firmware specification. However, in order to make life easier
+to embedded board vendors, the kernel doesn't require the device-tree
+to represent every device in the system and only requires some nodes
+and properties to be present. This will be described in detail in
+section III, but, for example, the kernel does not require you to
+create a node for every PCI device in the system. It is a requirement
+to have a node for PCI host bridges in order to provide interrupt
+routing informations and memory/IO ranges, among others. It is also
+recommended to define nodes for on chip devices and other busses that
+don't specifically fit in an existing OF specification. This creates a
+great flexibility in the way the kernel can then probe those and match
+drivers to device, without having to hard code all sorts of tables. It
+also makes it more flexible for board vendors to do minor hardware
+upgrades without significantly impacting the kernel code or cluttering
+it with special cases.
+
+
+1) Entry point for arch/powerpc
+-------------------------------
+
+   There is one and one single entry point to the kernel, at the start
+   of the kernel image. That entry point supports two calling
+   conventions:
+
+        a) Boot from Open Firmware. If your firmware is compatible
+        with Open Firmware (IEEE 1275) or provides an OF compatible
+        client interface API (support for "interpret" callback of
+        forth words isn't required), you can enter the kernel with:
+
+              r5 : OF callback pointer as defined by IEEE 1275
+              bindings to powerpc. Only the 32 bit client interface
+              is currently supported
+
+              r3, r4 : address & length of an initrd if any or 0
+
+              The MMU is either on or off; the kernel will run the
+              trampoline located in arch/powerpc/kernel/prom_init.c to
+              extract the device-tree and other information from open
+              firmware and build a flattened device-tree as described
+              in b). prom_init() will then re-enter the kernel using
+              the second method. This trampoline code runs in the
+              context of the firmware, which is supposed to handle all
+              exceptions during that time.
+
+        b) Direct entry with a flattened device-tree block. This entry
+        point is called by a) after the OF trampoline and can also be
+        called directly by a bootloader that does not support the Open
+        Firmware client interface. It is also used by "kexec" to
+        implement "hot" booting of a new kernel from a previous
+        running one. This method is what I will describe in more
+        details in this document, as method a) is simply standard Open
+        Firmware, and thus should be implemented according to the
+        various standard documents defining it and its binding to the
+        PowerPC platform. The entry point definition then becomes:
+
+                r3 : physical pointer to the device-tree block
+                (defined in chapter II) in RAM
+
+                r4 : physical pointer to the kernel itself. This is
+                used by the assembly code to properly disable the MMU
+                in case you are entering the kernel with MMU enabled
+                and a non-1:1 mapping.
+
+                r5 : NULL (as to differenciate with method a)
+
+        Note about SMP entry: Either your firmware puts your other
+        CPUs in some sleep loop or spin loop in ROM where you can get
+        them out via a soft reset or some other means, in which case
+        you don't need to care, or you'll have to enter the kernel
+        with all CPUs. The way to do that with method b) will be
+        described in a later revision of this document.
+
+
+2) Board support
+----------------
+
+64-bit kernels:
+
+   Board supports (platforms) are not exclusive config options. An
+   arbitrary set of board supports can be built in a single kernel
+   image. The kernel will "know" what set of functions to use for a
+   given platform based on the content of the device-tree. Thus, you
+   should:
+
+        a) add your platform support as a _boolean_ option in
+        arch/powerpc/Kconfig, following the example of PPC_PSERIES,
+        PPC_PMAC and PPC_MAPLE. The later is probably a good
+        example of a board support to start from.
+
+        b) create your main platform file as
+        "arch/powerpc/platforms/myplatform/myboard_setup.c" and add it
+        to the Makefile under the condition of your CONFIG_
+        option. This file will define a structure of type "ppc_md"
+        containing the various callbacks that the generic code will
+        use to get to your platform specific code
+
+        c) Add a reference to your "ppc_md" structure in the
+        "machines" table in arch/powerpc/kernel/setup_64.c if you are
+        a 64-bit platform.
+
+        d) request and get assigned a platform number (see PLATFORM_*
+        constants in include/asm-powerpc/processor.h
+
+32-bit embedded kernels:
+
+  Currently, board support is essentially an exclusive config option.
+  The kernel is configured for a single platform.  Part of the reason
+  for this is to keep kernels on embedded systems small and efficient;
+  part of this is due to the fact the code is already that way. In the
+  future, a kernel may support multiple platforms, but only if the
+  platforms feature the same core architectire.  A single kernel build
+  cannot support both configurations with Book E and configurations
+  with classic Powerpc architectures.
+
+  32-bit embedded platforms that are moved into arch/powerpc using a
+  flattened device tree should adopt the merged tree practice of
+  setting ppc_md up dynamically, even though the kernel is currently
+  built with support for only a single platform at a time.  This allows
+  unification of the setup code, and will make it easier to go to a
+  multiple-platform-support model in the future.
+
+NOTE: I believe the above will be true once Ben's done with the merge
+of the boot sequences.... someone speak up if this is wrong!
+
+  To add a 32-bit embedded platform support, follow the instructions
+  for 64-bit platforms above, with the exception that the Kconfig
+  option should be set up such that the kernel builds exclusively for
+  the platform selected.  The processor type for the platform should
+  enable another config option to select the specific board
+  supported.
+
+NOTE: If ben doesn't merge the setup files, may need to change this to
+point to setup_32.c
+
+
+   I will describe later the boot process and various callbacks that
+   your platform should implement.
+
+
+II - The DT block format
+========================
+
+
+This chapter defines the actual format of the flattened device-tree
+passed to the kernel. The actual content of it and kernel requirements
+are described later. You can find example of code manipulating that
+format in various places, including arch/powerpc/kernel/prom_init.c
+which will generate a flattened device-tree from the Open Firmware
+representation, or the fs2dt utility which is part of the kexec tools
+which will generate one from a filesystem representation. It is
+expected that a bootloader like uboot provides a bit more support,
+that will be discussed later as well.
+
+Note: The block has to be in main memory. It has to be accessible in
+both real mode and virtual mode with no mapping other than main
+memory. If you are writing a simple flash bootloader, it should copy
+the block to RAM before passing it to the kernel.
+
+
+1) Header
+---------
+
+   The kernel is entered with r3 pointing to an area of memory that is
+   roughtly described in include/asm-powerpc/prom.h by the structure
+   boot_param_header:
+
+struct boot_param_header {
+        u32     magic;                  /* magic word OF_DT_HEADER */
+        u32     totalsize;              /* total size of DT block */
+        u32     off_dt_struct;          /* offset to structure */
+        u32     off_dt_strings;         /* offset to strings */
+        u32     off_mem_rsvmap;         /* offset to memory reserve map
+*/
+        u32     version;                /* format version */
+        u32     last_comp_version;      /* last compatible version */
+
+        /* version 2 fields below */
+        u32     boot_cpuid_phys;        /* Which physical CPU id we're
+                                           booting on */
+        /* version 3 fields below */
+        u32     size_dt_strings;        /* size of the strings block */
+};
+
+   Along with the constants:
+
+/* Definitions used by the flattened device tree */
+#define OF_DT_HEADER            0xd00dfeed      /* 4: version,
+                                                   4: total size */
+#define OF_DT_BEGIN_NODE        0x1             /* Start node: full name
+*/
+#define OF_DT_END_NODE          0x2             /* End node */
+#define OF_DT_PROP              0x3             /* Property: name off,
+                                                   size, content */
+#define OF_DT_END               0x9
+
+   All values in this header are in big endian format, the various
+   fields in this header are defined more precisely below. All
+   "offset" values are in bytes from the start of the header; that is
+   from the value of r3.
+
+   - magic
+
+     This is a magic value that "marks" the beginning of the
+     device-tree block header. It contains the value 0xd00dfeed and is
+     defined by the constant OF_DT_HEADER
+
+   - totalsize
+
+     This is the total size of the DT block including the header. The
+     "DT" block should enclose all data structures defined in this
+     chapter (who are pointed to by offsets in this header). That is,
+     the device-tree structure, strings, and the memory reserve map.
+
+   - off_dt_struct
+
+     This is an offset from the beginning of the header to the start
+     of the "structure" part the device tree. (see 2) device tree)
+
+   - off_dt_strings
+
+     This is an offset from the beginning of the header to the start
+     of the "strings" part of the device-tree
+
+   - off_mem_rsvmap
+
+     This is an offset from the beginning of the header to the start
+     of the reserved memory map. This map is a list of pairs of 64
+     bit integers. Each pair is a physical address and a size. The
+
+     list is terminated by an entry of size 0. This map provides the
+     kernel with a list of physical memory areas that are "reserved"
+     and thus not to be used for memory allocations, especially during
+     early initialization. The kernel needs to allocate memory during
+     boot for things like un-flattening the device-tree, allocating an
+     MMU hash table, etc... Those allocations must be done in such a
+     way to avoid overriding critical things like, on Open Firmware
+     capable machines, the RTAS instance, or on some pSeries, the TCE
+     tables used for the iommu. Typically, the reserve map should
+     contain _at least_ this DT block itself (header,total_size). If
+     you are passing an initrd to the kernel, you should reserve it as
+     well. You do not need to reserve the kernel image itself. The map
+     should be 64 bit aligned.
+
+   - version
+
+     This is the version of this structure. Version 1 stops
+     here. Version 2 adds an additional field boot_cpuid_phys.
+     Version 3 adds the size of the strings block, allowing the kernel
+     to reallocate it easily at boot and free up the unused flattened
+     structure after expansion. Version 16 introduces a new more
+     "compact" format for the tree itself that is however not backward
+     compatible. You should always generate a structure of the highest
+     version defined at the time of your implementation. Currently
+     that is version 16, unless you explicitely aim at being backward
+     compatible.
+
+   - last_comp_version
+
+     Last compatible version. This indicates down to what version of
+     the DT block you are backward compatible. For example, version 2
+     is backward compatible with version 1 (that is, a kernel build
+     for version 1 will be able to boot with a version 2 format). You
+     should put a 1 in this field if you generate a device tree of
+     version 1 to 3, or 0x10 if you generate a tree of version 0x10
+     using the new unit name format.
+
+   - boot_cpuid_phys
+
+     This field only exist on version 2 headers. It indicate which
+     physical CPU ID is calling the kernel entry point. This is used,
+     among others, by kexec. If you are on an SMP system, this value
+     should match the content of the "reg" property of the CPU node in
+     the device-tree corresponding to the CPU calling the kernel entry
+     point (see further chapters for more informations on the required
+     device-tree contents)
+
+
+   So the typical layout of a DT block (though the various parts don't
+   need to be in that order) looks like this (addresses go from top to
+   bottom):
+
+
+             ------------------------------
+       r3 -> |  struct boot_param_header  |
+             ------------------------------
+             |      (alignment gap) (*)   |
+             ------------------------------
+             |      memory reserve map    |
+             ------------------------------
+             |      (alignment gap)       |
+             ------------------------------
+             |                            |
+             |    device-tree structure   |
+             |                            |
+             ------------------------------
+             |      (alignment gap)       |
+             ------------------------------
+             |                            |
+             |     device-tree strings    |
+             |                            |
+      -----> ------------------------------
+      |
+      |
+      --- (r3 + totalsize)
+
+  (*) The alignment gaps are not necessarily present; their presence
+      and size are dependent on the various alignment requirements of
+      the individual data blocks.
+
+
+2) Device tree generalities
+---------------------------
+
+This device-tree itself is separated in two different blocks, a
+structure block and a strings block. Both need to be aligned to a 4
+byte boundary.
+
+First, let's quickly describe the device-tree concept before detailing
+the storage format. This chapter does _not_ describe the detail of the
+required types of nodes & properties for the kernel, this is done
+later in chapter III.
+
+The device-tree layout is strongly inherited from the definition of
+the Open Firmware IEEE 1275 device-tree. It's basically a tree of
+nodes, each node having two or more named properties. A property can
+have a value or not.
+
+It is a tree, so each node has one and only one parent except for the
+root node who has no parent.
+
+A node has 2 names. The actual node name is generally contained in a
+property of type "name" in the node property list whose value is a
+zero terminated string and is mandatory for version 1 to 3 of the
+format definition (as it is in Open Firmware). Version 0x10 makes it
+optional as it can generate it from the unit name defined below.
+
+There is also a "unit name" that is used to differenciate nodes with
+the same name at the same level, it is usually made of the node
+name's, the "@" sign, and a "unit address", which definition is
+specific to the bus type the node sits on.
+
+The unit name doesn't exist as a property per-se but is included in
+the device-tree structure. It is typically used to represent "path" in
+the device-tree. More details about the actual format of these will be
+below.
+
+The kernel powerpc generic code does not make any formal use of the
+unit address (though some board support code may do) so the only real
+requirement here for the unit address is to ensure uniqueness of
+the node unit name at a given level of the tree. Nodes with no notion
+of address and no possible sibling of the same name (like /memory or
+/cpus) may omit the unit address in the context of this specification,
+or use the "@0" default unit address. The unit name is used to define
+a node "full path", which is the concatenation of all parent node
+unit names separated with "/".
+
+The root node doesn't have a defined name, and isn't required to have
+a name property either if you are using version 3 or earlier of the
+format. It also has no unit address (no @ symbol followed by a unit
+address). The root node unit name is thus an empty string. The full
+path to the root node is "/".
+
+Every node which actually represents an actual device (that is, a node
+which isn't only a virtual "container" for more nodes, like "/cpus"
+is) is also required to have a "device_type" property indicating the
+type of node .
+
+Finally, every node that can be referenced from a property in another
+node is required to have a "linux,phandle" property. Real open
+firmware implementations provide a unique "phandle" value for every
+node that the "prom_init()" trampoline code turns into
+"linux,phandle" properties. However, this is made optional if the
+flattened device tree is used directly. An example of a node
+referencing another node via "phandle" is when laying out the
+interrupt tree which will be described in a further version of this
+document.
+
+This "linux, phandle" property is a 32 bit value that uniquely
+identifies a node. You are free to use whatever values or system of
+values, internal pointers, or whatever to generate these, the only
+requirement is that every node for which you provide that property has
+a unique value for it.
+
+Here is an example of a simple device-tree. In this example, an "o"
+designates a node followed by the node unit name. Properties are
+presented with their name followed by their content. "content"
+represents an ASCII string (zero terminated) value, while <content>
+represents a 32 bit hexadecimal value. The various nodes in this
+example will be discussed in a later chapter. At this point, it is
+only meant to give you a idea of what a device-tree looks like. I have
+purposefully kept the "name" and "linux,phandle" properties which
+aren't necessary in order to give you a better idea of what the tree
+looks like in practice.
+
+  / o device-tree
+      |- name = "device-tree"
+      |- model = "MyBoardName"
+      |- compatible = "MyBoardFamilyName"
+      |- #address-cells = <2>
+      |- #size-cells = <2>
+      |- linux,phandle = <0>
+      |
+      o cpus
+      | | - name = "cpus"
+      | | - linux,phandle = <1>
+      | | - #address-cells = <1>
+      | | - #size-cells = <0>
+      | |
+      | o PowerPC,970@0
+      |   |- name = "PowerPC,970"
+      |   |- device_type = "cpu"
+      |   |- reg = <0>
+      |   |- clock-frequency = <5f5e1000>
+      |   |- linux,boot-cpu
+      |   |- linux,phandle = <2>
+      |
+      o memory@0
+      | |- name = "memory"
+      | |- device_type = "memory"
+      | |- reg = <00000000 00000000 00000000 20000000>
+      | |- linux,phandle = <3>
+      |
+      o chosen
+        |- name = "chosen"
+        |- bootargs = "root=/dev/sda2"
+        |- linux,platform = <00000600>
+        |- linux,phandle = <4>
+
+This tree is almost a minimal tree. It pretty much contains the
+minimal set of required nodes and properties to boot a linux kernel;
+that is, some basic model informations at the root, the CPUs, and the
+physical memory layout.  It also includes misc information passed
+through /chosen, like in this example, the platform type (mandatory)
+and the kernel command line arguments (optional).
+
+The /cpus/PowerPC,970@0/linux,boot-cpu property is an example of a
+property without a value. All other properties have a value. The
+significance of the #address-cells and #size-cells properties will be
+explained in chapter IV which defines precisely the required nodes and
+properties and their content.
+
+
+3) Device tree "structure" block
+
+The structure of the device tree is a linearized tree structure. The
+"OF_DT_BEGIN_NODE" token starts a new node, and the "OF_DT_END_NODE"
+ends that node definition. Child nodes are simply defined before
+"OF_DT_END_NODE" (that is nodes within the node). A 'token' is a 32
+bit value. The tree has to be "finished" with a OF_DT_END token
+
+Here's the basic structure of a single node:
+
+     * token OF_DT_BEGIN_NODE (that is 0x00000001)
+     * for version 1 to 3, this is the node full path as a zero
+       terminated string, starting with "/". For version 16 and later,
+       this is the node unit name only (or an empty string for the
+       root node)
+     * [align gap to next 4 bytes boundary]
+     * for each property:
+        * token OF_DT_PROP (that is 0x00000003)
+        * 32 bit value of property value size in bytes (or 0 of no
+     * value)
+        * 32 bit value of offset in string block of property name
+        * property value data if any
+        * [align gap to next 4 bytes boundary]
+     * [child nodes if any]
+     * token OF_DT_END_NODE (that is 0x00000002)
+
+So the node content can be summmarised as a start token, a full path,
+a list of properties, a list of child node and an end token. Every
+child node is a full node structure itself as defined above.
+
+4) Device tree 'strings" block
+
+In order to save space, property names, which are generally redundant,
+are stored separately in the "strings" block. This block is simply the
+whole bunch of zero terminated strings for all property names
+concatenated together. The device-tree property definitions in the
+structure block will contain offset values from the beginning of the
+strings block.
+
+
+III - Required content of the device tree
+=========================================
+
+WARNING: All "linux,*" properties defined in this document apply only
+to a flattened device-tree. If your platform uses a real
+implementation of Open Firmware or an implementation compatible with
+the Open Firmware client interface, those properties will be created
+by the trampoline code in the kernel's prom_init() file. For example,
+that's where you'll have to add code to detect your board model and
+set the platform number. However, when using the flatenned device-tree
+entry point, there is no prom_init() pass, and thus you have to
+provide those properties yourself.
+
+
+1) Note about cells and address representation
+----------------------------------------------
+
+The general rule is documented in the various Open Firmware
+documentations. If you chose to describe a bus with the device-tree
+and there exist an OF bus binding, then you should follow the
+specification. However, the kernel does not require every single
+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
+property. In the absence of such a property, the parent's parent
+values are used, etc... The kernel requires the root node to have
+those properties defining addresses format for devices directly mapped
+on the processor bus.
+
+Those 2 properties define 'cells' for representing an address and a
+size. A "cell" is a 32 bit number. For example, if both contain 2
+like the example tree given above, then an address and a size are both
+composed of 2 cells, and each is a 64 bit number (cells are
+concatenated and expected to be in big endian format). Another example
+is the way Apple firmware defines them, with 2 cells for an address
+and one cell for a size.  Most 32-bit implementations should define
+#address-cells and #size-cells to 1, which represents a 32-bit value.
+Some 32-bit processors allow for physical addresses greater than 32
+bits; these processors should define #address-cells as 2.
+
+"reg" properties are always a tuple of the type "address size" where
+the number of cells of address and size is specified by the bus
+#address-cells and #size-cells. When a bus supports various address
+spaces and other flags relative to a given address allocation (like
+prefetchable, etc...) those flags are usually added to the top level
+bits of the physical address. For example, a PCI physical address is
+made of 3 cells, the bottom two containing the actual address itself
+while the top cell contains address space indication, flags, and pci
+bus & device numbers.
+
+For busses that support dynamic allocation, it's the accepted practice
+to then not provide the address in "reg" (keep it 0) though while
+providing a flag indicating the address is dynamically allocated, and
+then, to provide a separate "assigned-addresses" property that
+contains the fully allocated addresses. See the PCI OF bindings for
+details.
+
+In general, a simple bus with no address space bits and no dynamic
+allocation is preferred if it reflects your hardware, as the existing
+kernel address parsing functions will work out of the box. If you
+define a bus type with a more complex address format, including things
+like address space bits, you'll have to add a bus translator to the
+prom_parse.c file of the recent kernels for your bus type.
+
+The "reg" property only defines addresses and sizes (if #size-cells
+is
+non-0) within a given bus. In order to translate addresses upward
+(that is into parent bus addresses, and possibly into cpu physical
+addresses), all busses must contain a "ranges" property. If the
+"ranges" property is missing at a given level, it's assumed that
+translation isn't possible. The format of the "ranges" proprety for a
+bus is a list of:
+
+        bus address, parent bus address, size
+
+"bus address" is in the format of the bus this bus node is defining,
+that is, for a PCI bridge, it would be a PCI address. Thus, (bus
+address, size) defines a range of addresses for child devices. "parent
+bus address" is in the format of the parent bus of this bus. For
+example, for a PCI host controller, that would be a CPU address. For a
+PCI<->ISA bridge, that would be a PCI address. It defines the base
+address in the parent bus where the beginning of that range is mapped.
+
+For a new 64 bit powerpc board, I recommend either the 2/2 format or
+Apple's 2/1 format which is slightly more compact since sizes usually
+fit in a single 32 bit word.   New 32 bit powerpc boards should use a
+1/1 format, unless the processor supports physical addresses greater
+than 32-bits, in which case a 2/1 format is recommended.
+
+
+2) Note about "compatible" properties
+-------------------------------------
+
+These properties are optional, but recommended in devices and the root
+node. The format of a "compatible" property is a list of concatenated
+zero terminated strings. They allow a device to express its
+compatibility with a family of similar devices, in some cases,
+allowing a single driver to match against several devices regardless
+of their actual names.
+
+3) Note about "name" properties
+-------------------------------
+
+While earlier users of Open Firmware like OldWorld macintoshes tended
+to use the actual device name for the "name" property, it's nowadays
+considered a good practice to use a name that is closer to the device
+class (often equal to device_type). For example, nowadays, ethernet
+controllers are named "ethernet", an additional "model" property
+defining precisely the chip type/model, and "compatible" property
+defining the family in case a single driver can driver more than one
+of these chips. However, the kernel doesn't generally put any
+restriction on the "name" property; it is simply considered good
+practice to follow the standard and its evolutions as closely as
+possible.
+
+Note also that the new format version 16 makes the "name" property
+optional. If it's absent for a node, then the node's unit name is then
+used to reconstruct the name. That is, the part of the unit name
+before the "@" sign is used (or the entire unit name if no "@" sign
+is present).
+
+4) Note about node and property names and character set
+-------------------------------------------------------
+
+While open firmware provides more flexibe usage of 8859-1, this
+specification enforces more strict rules. Nodes and properties should
+be comprised only of ASCII characters 'a' to 'z', '0' to
+'9', ',', '.', '_', '+', '#', '?', and '-'. Node names additionally
+allow uppercase characters 'A' to 'Z' (property names should be
+lowercase. The fact that vendors like Apple don't respect this rule is
+irrelevant here). Additionally, node and property names should always
+begin with a character in the range 'a' to 'z' (or 'A' to 'Z' for node
+names).
+
+The maximum number of characters for both nodes and property names
+is 31. In the case of node names, this is only the leftmost part of
+a unit name (the pure "name" property), it doesn't include the unit
+address which can extend beyond that limit.
+
+
+5) Required nodes and properties
+--------------------------------
+  These are all that are currently required. However, it is strongly
+  recommended that you expose PCI host bridges as documented in the
+  PCI binding to open firmware, and your interrupt tree as documented
+  in OF interrupt tree specification.
+
+  a) The root node
+
+  The root node requires some properties to be present:
+
+    - model : this is your board name/model
+    - #address-cells : address representation for "root" devices
+    - #size-cells: the size representation for "root" devices
+
+  Additionally, some recommended properties are:
+
+    - compatible : the board "family" generally finds its way here,
+      for example, if you have 2 board models with a similar layout,
+      that typically get driven by the same platform code in the
+      kernel, you would use a different "model" property but put a
+      value in "compatible". The kernel doesn't directly use that
+      value (see /chosen/linux,platform for how the kernel choses a
+      platform type) but it is generally useful.
+
+  The root node is also generally where you add additional properties
+  specific to your board like the serial number if any, that sort of
+  thing. it is recommended that if you add any "custom" property whose
+  name may clash with standard defined ones, you prefix them with your
+  vendor name and a comma.
+
+  b) The /cpus node
+
+  This node is the parent of all individual CPU nodes. It doesn't
+  have any specific requirements, though it's generally good practice
+  to have at least:
+
+               #address-cells = <00000001>
+               #size-cells    = <00000000>
+
+  This defines that the "address" for a CPU is a single cell, and has
+  no meaningful size. This is not necessary but the kernel will assume
+  that format when reading the "reg" properties of a CPU node, see
+  below
+
+  c) The /cpus/* nodes
+
+  So under /cpus, you are supposed to create a node for every CPU on
+  the machine. There is no specific restriction on the name of the
+  CPU, though It's common practice to call it PowerPC,<name>. For
+  example, Apple uses PowerPC,G5 while IBM uses PowerPC,970FX.
+
+  Required properties:
+
+    - device_type : has to be "cpu"
+    - reg : This is the physical cpu number, it's a single 32 bit cell
+      and is also used as-is as the unit number for constructing the
+      unit name in the full path. For example, with 2 CPUs, you would
+      have the full path:
+        /cpus/PowerPC,970FX@0
+        /cpus/PowerPC,970FX@1
+      (unit addresses do not require leading zeroes)
+    - d-cache-line-size : one cell, L1 data cache line size in bytes
+    - i-cache-line-size : one cell, L1 instruction cache line size in
+      bytes
+    - d-cache-size : one cell, size of L1 data cache in bytes
+    - i-cache-size : one cell, size of L1 instruction cache in bytes
+    - linux, boot-cpu : Should be defined if this cpu is the boot cpu.
+
+  Recommended properties:
+
+    - timebase-frequency : a cell indicating the frequency of the
+      timebase in Hz. This is not directly used by the generic code,
+      but you are welcome to copy/paste the pSeries code for setting
+      the kernel timebase/decrementer calibration based on this
+      value.
+    - clock-frequency : a cell indicating the CPU core clock frequency
+      in Hz. A new property will be defined for 64 bit values, but if
+      your frequency is < 4Ghz, one cell is enough. Here as well as
+      for the above, the common code doesn't use that property, but
+      you are welcome to re-use the pSeries or Maple one. A future
+      kernel version might provide a common function for this.
+
+  You are welcome to add any property you find relevant to your board,
+  like some information about the mechanism used to soft-reset the
+  CPUs. For example, Apple puts the GPIO number for CPU soft reset
+  lines in there as a "soft-reset" property since they start secondary
+  CPUs by soft-resetting them.
+
+
+  d) the /memory node(s)
+
+  To define the physical memory layout of your board, you should
+  create one or more memory node(s). You can either create a single
+  node with all memory ranges in its reg property, or you can create
+  several nodes, as you wish. The unit address (@ part) used for the
+  full path is the address of the first range of memory defined by a
+  given node. If you use a single memory node, this will typically be
+  @0.
+
+  Required properties:
+
+    - device_type : has to be "memory"
+    - reg : This property contains all the physical memory ranges of
+      your board. It's a list of addresses/sizes concatenated
+      together, with the number of cells of each defined by the
+      #address-cells and #size-cells of the root node. For example,
+      with both of these properties beeing 2 like in the example given
+      earlier, a 970 based machine with 6Gb of RAM could typically
+      have a "reg" property here that looks like:
+
+      00000000 00000000 00000000 80000000
+      00000001 00000000 00000001 00000000
+
+      That is a range starting at 0 of 0x80000000 bytes and a range
+      starting at 0x100000000 and of 0x100000000 bytes. You can see
+      that there is no memory covering the IO hole between 2Gb and
+      4Gb. Some vendors prefer splitting those ranges into smaller
+      segments, but the kernel doesn't care.
+
+  e) The /chosen node
+
+  This node is a bit "special". Normally, that's where open firmware
+  puts some variable environment information, like the arguments, or
+  phandle pointers to nodes like the main interrupt controller, or the
+  default input/output devices.
+
+  This specification makes a few of these mandatory, but also defines
+  some linux-specific properties that would be normally constructed by
+  the prom_init() trampoline when booting with an OF client interface,
+  but that you have to provide yourself when using the flattened format.
+
+  Required properties:
+
+    - linux,platform : This is your platform number as assigned by the
+      architecture maintainers
+
+  Recommended properties:
+
+    - bootargs : This zero-terminated string is passed as the kernel
+      command line
+    - linux,stdout-path : This is the full path to your standard
+      console device if any. Typically, if you have serial devices on
+      your board, you may want to put the full path to the one set as
+      the default console in the firmware here, for the kernel to pick
+      it up as it's own default console. If you look at the funciton
+      set_preferred_console() in arch/ppc64/kernel/setup.c, you'll see
+      that the kernel tries to find out the default console and has
+      knowledge of various types like 8250 serial ports. You may want
+      to extend this function to add your own.
+    - interrupt-controller : This is one cell containing a phandle
+      value that matches the "linux,phandle" property of your main
+      interrupt controller node. May be used for interrupt routing.
+
+
+  Note that u-boot creates and fills in the chosen node for platforms
+  that use it.
+
+  f) the /soc<SOCname> node
+
+  This node is used to represent a system-on-a-chip (SOC) and must be
+  present if the processor is a SOC. The top-level soc node contains
+  information that is global to all devices on the SOC. The node name
+  should contain a unit address for the SOC, which is the base address
+  of the memory-mapped register set for the SOC. The name of an soc
+  node should start with "soc", and the remainder of the name should
+  represent the part number for the soc.  For example, the MPC8540's
+  soc node would be called "soc8540".
+
+  Required properties:
+
+    - device_type : Should be "soc"
+    - ranges : Should be defined as specified in 1) to describe the
+      translation of SOC addresses for memory mapped SOC registers.
+    - bus-frequency: Contains the bus frequency for the SOC node.
+      Typically, the value of this field is filled in by the boot
+      loader. 
+
+
+  Recommended properties:
+
+    - reg : This property defines the address and size of the
+      memory-mapped registers that are used for the SOC node itself.
+      It does not include the child device registers - these will be
+      defined inside each child node.  The address specified in the
+      "reg" property should match the unit address of the SOC node.
+    - #address-cells : Address representation for "soc" devices.  The
+      format of this field may vary depending on whether or not the
+      device registers are memory mapped.  For memory mapped
+      registers, this field represents the number of cells needed to
+      represent the address of the registers.  For SOCs that do not
+      use MMIO, a special address format should be defined that
+      contains enough cells to represent the required information.
+      See 1) above for more details on defining #address-cells.
+    - #size-cells : Size representation for "soc" devices
+    - #interrupt-cells : Defines the width of cells used to represent
+       interrupts.  Typically this value is <2>, which includes a
+       32-bit number that represents the interrupt number, and a
+       32-bit number that represents the interrupt sense and level.
+       This field is only needed if the SOC contains an interrupt
+       controller.
+
+  The SOC node may contain child nodes for each SOC device that the
+  platform uses.  Nodes should not be created for devices which exist
+  on the SOC but are not used by a particular platform. See chapter VI
+  for more information on how to specify devices that are part of an
+SOC.
+
+  Example SOC node for the MPC8540:
+
+        soc8540@e0000000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                #interrupt-cells = <2>;
+                device_type = "soc";
+                ranges = <00000000 e0000000 00100000>
+                reg = <e0000000 00003000>;
+                bus-frequency = <0>;
+        }
+
+
+
+IV - "dtc", the device tree compiler
+====================================
+
+
+dtc source code can be found at
+<http://ozlabs.org/~dgibson/dtc/dtc.tar.gz>
+
+WARNING: This version is still in early development stage; the
+resulting device-tree "blobs" have not yet been validated with the
+kernel. The current generated bloc lacks a useful reserve map (it will
+be fixed to generate an empty one, it's up to the bootloader to fill
+it up) among others. The error handling needs work, bugs are lurking,
+etc...
+
+dtc basically takes a device-tree in a given format and outputs a
+device-tree in another format. The currently supported formats are:
+
+  Input formats:
+  -------------
+
+     - "dtb": "blob" format, that is a flattened device-tree block
+       with
+        header all in a binary blob.
+     - "dts": "source" format. This is a text file containing a
+       "source" for a device-tree. The format is defined later in this
+        chapter.
+     - "fs" format. This is a representation equivalent to the
+        output of /proc/device-tree, that is nodes are directories and
+        properties are files
+
+ Output formats:
+ ---------------
+
+     - "dtb": "blob" format
+     - "dts": "source" format
+     - "asm": assembly language file. This is a file that can be
+       sourced by gas to generate a device-tree "blob". That file can
+       then simply be added to your Makefile. Additionally, the
+       assembly file exports some symbols that can be use
+
+
+The syntax of the dtc tool is
+
+    dtc [-I <input-format>] [-O <output-format>]
+        [-o output-filename] [-V output_version] input_filename
+
+
+The "output_version" defines what versio of the "blob" format will be
+generated. Supported versions are 1,2,3 and 16. The default is
+currently version 3 but that may change in the future to version 16.
+
+Additionally, dtc performs various sanity checks on the tree, like the
+uniqueness of linux,phandle properties, validity of strings, etc...
+
+The format of the .dts "source" file is "C" like, supports C and C++
+style commments.
+
+/ {
+}
+
+The above is the "device-tree" definition. It's the only statement
+supported currently at the toplevel.
+
+/ {
+  property1 = "string_value";   /* define a property containing a 0
+                                 * terminated string
+                                 */
+
+  property2 = <1234abcd>;       /* define a property containing a
+                                 * numerical 32 bits value (hexadecimal)
+                                 */
+
+  property3 = <12345678 12345678 deadbeef>;
+                                /* define a property containing 3
+                                 * numerical 32 bits values (cells) in
+                                 * hexadecimal
+                                 */
+  property4 = [0a 0b 0c 0d de ea ad be ef];
+                                /* define a property whose content is
+                                 * an arbitrary array of bytes
+                                 */
+
+  childnode@addresss {  /* define a child node named "childnode"
+                                 * whose unit name is "childnode at
+                                 * address"
+                                 */
+
+    childprop = "hello\n";      /* define a property "childprop" of
+                                 * childnode (in this case, a string)
+                                 */
+  };
+};
+
+Nodes can contain other nodes etc... thus defining the hierarchical
+structure of the tree.
+
+Strings support common escape sequences from C: "\n", "\t", "\r",
+"\(octal value)", "\x(hex value)".
+
+It is also suggested that you pipe your source file through cpp (gcc
+preprocessor) so you can use #include's, #define for constants, etc...
+
+Finally, various options are planned but not yet implemented, like
+automatic generation of phandles, labels (exported to the asm file so
+you can point to a property content and change it easily from whatever
+you link the device-tree with), label or path instead of numeric value
+in some cells to "point" to a node (replaced by a phandle at compile
+time), export of reserve map address to the asm file, ability to
+specify reserve map content at compile time, etc...
+
+We may provide a .h include file with common definitions of that
+proves useful for some properties (like building PCI properties or
+interrupt maps) though it may be better to add a notion of struct
+definitions to the compiler...
+
+
+V - Recommendations for a bootloader
+====================================
+
+
+Here are some various ideas/recommendations that have been proposed
+while all this has been defined and implemented.
+
+  - The bootloader may want to be able to use the device-tree itself
+    and may want to manipulate it (to add/edit some properties,
+    like physical memory size or kernel arguments). At this point, 2
+    choices can be made. Either the bootloader works directly on the
+    flattened format, or the bootloader has its own internal tree
+    representation with pointers (similar to the kernel one) and
+    re-flattens the tree when booting the kernel. The former is a bit
+    more difficult to edit/modify, the later requires probably a bit
+    more code to handle the tree structure. Note that the structure
+    format has been designed so it's relatively easy to "insert"
+    properties or nodes or delete them by just memmoving things
+    around. It contains no internal offsets or pointers for this
+    purpose.
+
+  - An example of code for iterating nodes & retreiving properties
+    directly from the flattened tree format can be found in the kernel
+    file arch/ppc64/kernel/prom.c, look at scan_flat_dt() function,
+    it's usage in early_init_devtree(), and the corresponding various
+    early_init_dt_scan_*() callbacks. That code can be re-used in a
+    GPL bootloader, and as the author of that code, I would be happy
+    do discuss possible free licencing to any vendor who wishes to
+    integrate all or part of this code into a non-GPL bootloader.
+
+
+
+VI - System-on-a-chip devices and nodes
+=======================================
+
+Many companies are now starting to develop system-on-a-chip
+processors, where the processor core (cpu) and many peripheral devices
+exist on a single piece of silicon.  For these SOCs, an SOC node
+should be used that defines child nodes for the devices that make
+up the SOC. While platforms are not required to use this model in
+order to boot the kernel, it is highly encouraged that all SOC
+implementations define as complete a flat-device-tree as possible to
+describe the devices on the SOC.  This will allow for the
+genericization of much of the kernel code.
+
+
+1) Defining child nodes of an SOC
+---------------------------------
+
+Each device that is part of an SOC may have its own node entry inside
+the SOC node.  For each device that is included in the SOC, the unit
+address property represents the address offset for this device's
+memory-mapped registers in the parent's address space.  The parent's
+address space is defined by the "ranges" property in the top-level soc
+node. The "reg" property for each node that exists directly under the
+SOC node should contain the address mapping from the child address space
+to the parent SOC address space and the size of the device's
+memory-mapped register file.
+
+For many devices that may exist inside an SOC, there are predefined
+specifications for the format of the device tree node.  All SOC child
+nodes should follow these specifications, except where noted in this
+document.
+
+See appendix A for an example partial SOC node definition for the
+MPC8540.
+
+
+2) Specifying interrupt information for SOC devices
+---------------------------------------------------
+
+Each device that is part of an SOC and which generates interrupts
+should have the following properties:
+
+        - interrupt-parent : contains the phandle of the interrupt
+          controller which handles interrupts for this device
+        - interrupts : a list of tuples representing the interrupt
+          number and the interrupt sense and level for each interupt
+          for this device.
+
+This information is used by the kernel to build the interrupt table
+for the interrupt controllers in the system.
+
+Sense and level information should be encoded as follows:
+
+   Devices connected to openPIC-compatible controllers should encode
+   sense and polarity as follows:
+
+        0 = high to low edge sensitive type enabled
+        1 = active low level sensitive type enabled
+        2 = low to high edge sensitive type enabled
+        3 = active high level sensitive type enabled
+
+   ISA PIC interrupt controllers should adhere to the ISA PIC
+   encodings listed below:
+
+        0 =  active low level sensitive type enabled
+        1 =  active high level sensitive type enabled
+        2 =  high to low edge sensitive type enabled
+        3 =  low to high edge sensitive type enabled
+
+
+
+3) Representing devices without a current OF specification
+----------------------------------------------------------
+
+Currently, there are many devices on SOCs that do not have a standard
+representation pre-defined as part of the open firmware
+specifications, mainly because the boards that contain these SOCs are
+not currently booted using open firmware.   This section contains
+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
+
+  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
+    - device_type : Should be "mdio"
+    - compatible : Should define the compatible device type for the
+      mdio.  Currently, this is most likely to be "gianfar"
+
+  Example:
+
+        mdio@24520 {
+                reg = <24520 20>;
+                device_type = "mdio"; 
+                compatible = "gianfar";
+
+                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
+    - 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.
+
+  Example:
+
+        ethernet@24000 {
+                #size-cells = <0>;
+                device_type = "network";
+                model = "TSEC";
+                compatible = "gianfar";
+                reg = <24000 1000>;
+                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:
+
+    - device_type : Should be "ethernet-phy"
+    - 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.
+    - reg : The ID number for the phy, usually a small integer
+    - linux,phandle :  phandle for this node; likely referenced by an
+      ethernet controller node.
+
+
+   Example:
+
+        ethernet-phy@0 {
+                linux,phandle = <2452000>
+                interrupt-parent = <40000>;
+                interrupts = <35 1>;
+                reg = <0>;
+                device_type = "ethernet-phy";
+        };
+
+
+   d) Interrupt controllers
+
+   Some SOC devices contain interrupt controllers that are different
+   from the standard Open PIC specification.  The SOC device nodes for
+   these types of controllers should be specified just like a standard
+   OpenPIC controller.  Sense and level information should be encoded
+   as specified in section 2) of this chapter for each device that
+   specifies an interrupt.
+
+   Example :
+
+        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;
+        };
+
+
+   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.
+
+   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 {
+                device_type = "usb";
+                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 {
+                device_type = "usb";
+                compatible = "fsl-usb2-dr";
+                reg = <23000 1000>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                interrupt-parent = <700>;
+                interrupts = <26 1>;
+                phy = "ulpi";
+        };
+
+
+   More devices will be defined as this spec matures.
+
+
+Appendix A - Sample SOC node for MPC8540
+========================================
+
+Note that the #address-cells and #size-cells for the SoC node
+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>;
+                device_type = "soc";
+                ranges = <00000000 e0000000 00100000>
+                reg = <e0000000 00003000>;
+                bus-frequency = <0>;
+
+                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>;
+                        device_type = "network";
+                        model = "TSEC";
+                        compatible = "gianfar";
+                        reg = <24000 1000>;
+                        address = [ 00 E0 0C 00 73 00 ];
+                        interrupts = <d 3 e 3 12 3>;
+                        interrupt-parent = <40000>;
+                        phy-handle = <2452000>;
+                };
+
+                ethernet@25000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        device_type = "network";
+                        model = "TSEC";
+                        compatible = "gianfar";
+                        reg = <25000 1000>;
+                        address = [ 00 E0 0C 00 73 01 ];
+                        interrupts = <13 3 14 3 18 3>;
+                        interrupt-parent = <40000>;
+                        phy-handle = <2452001>;
+                };
+
+                ethernet@26000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        device_type = "network";
+                        model = "FEC";
+                        compatible = "gianfar";
+                        reg = <26000 1000>;
+                        address = [ 00 E0 0C 00 73 02 ];
+                        interrupts = <19 3>;
+                        interrupt-parent = <40000>;
+                        phy-handle = <2452002>;
+                };
+
+                serial@4500 {
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <4500 100>;
+                        clock-frequency = <0>;
+                        interrupts = <1a 3>;
+                        interrupt-parent = <40000>;
+                };
+
+                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;
+                };
+
+                i2c@3000 {
+                        interrupt-parent = <40000>;
+                        interrupts = <1b 3>;
+                        reg = <3000 18>;
+                        device_type = "i2c";
+                        compatible  = "fsl-i2c";
+                        dfsrr;
+                };
+
+        };
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
new file mode 100644
index 000000000000..2dafa63bd370
--- /dev/null
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -0,0 +1,47 @@
+1 Release Date    : Wed Feb 03 14:31:44 PST 2006 - Sumant Patro <Sumant.Patro@lsil.com>
+2 Current Version : 00.00.02.04
+3 Older Version   : 00.00.02.04 
+
+i.      Support for 1078 type (ppc IOP) controller, device id : 0x60 added.
+        During initialization, depending on the device id, the template members 
+        are initialized with function pointers specific to the ppc or 
+        xscale controllers.  
+
+                -Sumant Patro <Sumant.Patro@lsil.com>
+                
+1 Release Date    : Fri Feb 03 14:16:25 PST 2006 - Sumant Patro 
+                                                        <Sumant.Patro@lsil.com>
+2 Current Version : 00.00.02.04
+3 Older Version   : 00.00.02.02 
+i.      Register 16 byte CDB capability with scsi midlayer 
+
+        "Ths patch properly registers the 16 byte command length capability of the 
+        megaraid_sas controlled hardware with the scsi midlayer. All megaraid_sas 
+        hardware supports 16 byte CDB's."
+
+                -Joshua Giles <joshua_giles@dell.com> 
+
+1 Release Date    : Mon Jan 23 14:09:01 PST 2006 - Sumant Patro <Sumant.Patro@lsil.com>
+2 Current Version : 00.00.02.02
+3 Older Version   : 00.00.02.01 
+
+i.      New template defined to represent each family of controllers (identified by processor used). 
+        The template will have defintions that will be initialised to appropritae values for a specific family of controllers. The template definition has four function pointers. During driver initialisation the function pointers will be set based on the controller family type. This change is done to support new controllers that has different processors and thus different register set.
+
+                -Sumant Patro <Sumant.Patro@lsil.com>
+
+1 Release Date    : Mon Dec 19 14:36:26 PST 2005 - Sumant Patro <Sumant.Patro@lsil.com>
+2 Current Version : 00.00.02.00-rc4 
+3 Older Version   : 00.00.02.01 
+
+i.      Code reorganized to remove code duplication in megasas_build_cmd. 
+
+        "There's a lot of duplicate code megasas_build_cmd.  Move that out of the different codepathes and merge the reminder of megasas_build_cmd into megasas_queue_command"
+
+                - Christoph Hellwig <hch@lst.de>
+
+ii.     Defined MEGASAS_IOC_FIRMWARE32 for code paths that handles 32 bit applications in 64 bit systems.
+
+        "MEGASAS_IOC_FIRMWARE can't be redefined if CONFIG_COMPAT is set, we need to define a MEGASAS_IOC_FIRMWARE32 define so native binaries continue to work"
+
+                - Christoph Hellwig <hch@lst.de>
diff --git a/Documentation/scsi/aic79xx.txt b/Documentation/scsi/aic79xx.txt
index 0aeef740a95a..382b439b439e 100644
--- a/Documentation/scsi/aic79xx.txt
+++ b/Documentation/scsi/aic79xx.txt
@@ -1,5 +1,5 @@
 ====================================================================
-=             Adaptec Ultra320 Family Manager Set v1.3.11          =
+=             Adaptec Ultra320 Family Manager Set                  =
 =                                                                  =
 =                            README for                            =
 =                    The Linux Operating System                    =
@@ -63,6 +63,11 @@ The following information is available in this file:
                               68-pin)
 2. Version History
 
+   3.0    (December 1st, 2005)
+        - Updated driver to use SCSI transport class infrastructure
+        - Upported sequencer and core fixes from adaptec released
+          version 2.0.15 of the driver.
+
    1.3.11 (July 11, 2003)
         - Fix several deadlock issues.
         - Add 29320ALP and 39320B Id's.
@@ -194,7 +199,7 @@ The following information is available in this file:
           supported)
         - Support for the PCI-X standard up to 133MHz
         - Support for the PCI v2.2 standard
-        - Domain Validation
+        - Domain Validation
 
    2.2. Operating System Support:
         - Redhat Linux 7.2, 7.3, 8.0, Advanced Server 2.1
@@ -411,77 +416,53 @@ The following information is available in this file:
           http://www.adaptec.com.
 
 
-5. Contacting Adaptec
+5. Adaptec Customer Support
 
    A Technical Support Identification (TSID) Number is required for 
    Adaptec technical support.
     - The 12-digit TSID can be found on the white barcode-type label
-      included inside the box with your product. The TSID helps us 
+      included inside the box with your product.  The TSID helps us 
       provide more efficient service by accurately identifying your 
       product and support status.
+
    Support Options
     - Search the Adaptec Support Knowledgebase (ASK) at
       http://ask.adaptec.com for articles, troubleshooting tips, and
-      frequently asked questions for your product.
+      frequently asked questions about your product.
     - For support via Email, submit your question to Adaptec's 
-      Technical Support Specialists at http://ask.adaptec.com.
+      Technical Support Specialists at http://ask.adaptec.com/.
      
    North America
-    - Visit our Web site at http://www.adaptec.com.
-    - To speak with a Fibre Channel/RAID/External Storage Technical
-      Support Specialist, call 1-321-207-2000,
-      Hours: Monday-Friday, 3:00 A.M. to 5:00 P.M., PST.
-      (Not open on holidays)
-    - For Technical Support in all other technologies including 
-      SCSI, call 1-408-934-7274,
-      Hours: Monday-Friday, 6:00 A.M. to 5:00 P.M., PST.
-      (Not open on holidays)
-    - For after hours support, call 1-800-416-8066 ($99/call, 
-      $149/call on holidays)
-    - To order Adaptec products including software and cables, call
-      1-800-442-7274 or 1-408-957-7274. You can also visit our 
-      online store at http://www.adaptecstore.com
+    - Visit our Web site at http://www.adaptec.com/.
+    - For information about Adaptec's support options, call
+      408-957-2550, 24 hours a day, 7 days a week.
+    - To speak with a Technical Support Specialist,
+      * For hardware products, call 408-934-7274,
+        Monday to Friday, 3:00 am to 5:00 pm, PDT.
+      * For RAID and Fibre Channel products, call 321-207-2000,
+        Monday to Friday, 3:00 am to 5:00 pm, PDT.
+      To expedite your service, have your computer with you.
+    - To order Adaptec products, including accessories and cables,
+      call 408-957-7274.  To order cables online go to
+      http://www.adaptec.com/buy-cables/.
 
    Europe
-    - Visit our Web site at http://www.adaptec-europe.com.
-    - English and French: To speak with a Technical Support 
-      Specialist, call one of the following numbers:
-        - English: +32-2-352-3470
-        - French:  +32-2-352-3460
-      Hours: Monday-Thursday, 10:00 to 12:30, 13:30 to 17:30 CET 
-             Friday, 10:00 to 12:30, 13:30 to 16:30 CET
-    - German: To speak with a Technical Support Specialist,
-      call +49-89-456-40660
-      Hours: Monday-Thursday, 09:30 to 12:30, 13:30 to 16:30 CET
-             Friday, 09:30 to 12:30, 13:30 to 15:00 CET
-    - To order Adaptec products, including accessories and cables:
-        - UK: +0800-96-65-26 or fax +0800-731-02-95
-        - Other European countries: +32-11-300-379
-
-   Australia and New Zealand
-    - Visit our Web site at http://www.adaptec.com.au.
-    - To speak with a Technical Support Specialist, call 
-      +612-9416-0698
-      Hours: Monday-Friday, 10:00 A.M. to 4:30 P.M., EAT
-      (Not open on holidays)
+    - Visit our Web site at http://www.adaptec-europe.com/.
+    - To speak with a Technical Support Specialist, call, or email,
+      * German:  +49 89 4366 5522, Monday-Friday, 9:00-17:00 CET,
+        http://ask-de.adaptec.com/.
+      * French:  +49 89 4366 5533, Monday-Friday, 9:00-17:00 CET,
+        http://ask-fr.adaptec.com/.
+      * English: +49 89 4366 5544, Monday-Friday, 9:00-17:00 GMT,
+        http://ask.adaptec.com/.
+    - You can order Adaptec cables online at
+      http://www.adaptec.com/buy-cables/.
 
    Japan
+    - Visit our web site at http://www.adaptec.co.jp/.
     - To speak with a Technical Support Specialist, call 
-      +81-3-5308-6120 
-      Hours: Monday-Friday, 9:00 a.m. to 12:00 p.m., 1:00 p.m. to
-      6:00 p.m. TSC
-
-   Hong Kong and China
-    - To speak with a Technical Support Specialist, call 
-      +852-2869-7200
-      Hours: Monday-Friday, 10:00 to 17:00.
-    - Fax Technical Support at +852-2869-7100.
-
-   Singapore
-    - To speak with a Technical Support Specialist, call 
-      +65-245-7470
-      Hours: Monday-Friday, 10:00 to 17:00.
-    - Fax Technical Support at +852-2869-7100
+      +81 3 5308 6120, Monday-Friday, 9:00 a.m. to 12:00 p.m.,
+      1:00 p.m. to 6:00 p.m.
 
 -------------------------------------------------------------------
 /*
diff --git a/Documentation/scsi/aic7xxx.txt b/Documentation/scsi/aic7xxx.txt
index 47e74ddc4bc9..3481fcded4c2 100644
--- a/Documentation/scsi/aic7xxx.txt
+++ b/Documentation/scsi/aic7xxx.txt
@@ -309,81 +309,57 @@ The following information is available in this file:
    -----------------------------------------------------------------
 
    Example:
-   'options aic7xxx aic7xxx=verbose,no_probe,tag_info:{{},{,,10}},seltime:1"
+   'options aic7xxx aic7xxx=verbose,no_probe,tag_info:{{},{,,10}},seltime:1'
         enables verbose logging, Disable EISA/VLB probing,
         and set tag depth on Controller 1/Target 2 to 10 tags.
 
-3. Contacting Adaptec
+4. Adaptec Customer Support
 
    A Technical Support Identification (TSID) Number is required for 
    Adaptec technical support.
     - The 12-digit TSID can be found on the white barcode-type label
-      included inside the box with your product. The TSID helps us 
+      included inside the box with your product.  The TSID helps us 
       provide more efficient service by accurately identifying your 
       product and support status.
+
    Support Options
     - Search the Adaptec Support Knowledgebase (ASK) at
       http://ask.adaptec.com for articles, troubleshooting tips, and
-      frequently asked questions for your product.
+      frequently asked questions about your product.
     - For support via Email, submit your question to Adaptec's 
-      Technical Support Specialists at http://ask.adaptec.com.
+      Technical Support Specialists at http://ask.adaptec.com/.
      
    North America
-    - Visit our Web site at http://www.adaptec.com.
-    - To speak with a Fibre Channel/RAID/External Storage Technical
-      Support Specialist, call 1-321-207-2000,
-      Hours: Monday-Friday, 3:00 A.M. to 5:00 P.M., PST.
-      (Not open on holidays)
-    - For Technical Support in all other technologies including 
-      SCSI, call 1-408-934-7274,
-      Hours: Monday-Friday, 6:00 A.M. to 5:00 P.M., PST.
-      (Not open on holidays)
-    - For after hours support, call 1-800-416-8066 ($99/call, 
-      $149/call on holidays)
-    - To order Adaptec products including software and cables, call
-      1-800-442-7274 or 1-408-957-7274. You can also visit our 
-      online store at http://www.adaptecstore.com
+    - Visit our Web site at http://www.adaptec.com/.
+    - For information about Adaptec's support options, call
+      408-957-2550, 24 hours a day, 7 days a week.
+    - To speak with a Technical Support Specialist,
+      * For hardware products, call 408-934-7274,
+        Monday to Friday, 3:00 am to 5:00 pm, PDT.
+      * For RAID and Fibre Channel products, call 321-207-2000,
+        Monday to Friday, 3:00 am to 5:00 pm, PDT.
+      To expedite your service, have your computer with you.
+    - To order Adaptec products, including accessories and cables,
+      call 408-957-7274.  To order cables online go to
+      http://www.adaptec.com/buy-cables/.
 
    Europe
-    - Visit our Web site at http://www.adaptec-europe.com.
-    - English and French: To speak with a Technical Support 
-      Specialist, call one of the following numbers:
-        - English: +32-2-352-3470
-        - French:  +32-2-352-3460
-      Hours: Monday-Thursday, 10:00 to 12:30, 13:30 to 17:30 CET 
-             Friday, 10:00 to 12:30, 13:30 to 16:30 CET
-    - German: To speak with a Technical Support Specialist,
-      call +49-89-456-40660
-      Hours: Monday-Thursday, 09:30 to 12:30, 13:30 to 16:30 CET
-             Friday, 09:30 to 12:30, 13:30 to 15:00 CET
-    - To order Adaptec products, including accessories and cables:
-        - UK: +0800-96-65-26 or fax +0800-731-02-95
-        - Other European countries: +32-11-300-379
-
-   Australia and New Zealand
-    - Visit our Web site at http://www.adaptec.com.au.
-    - To speak with a Technical Support Specialist, call 
-      +612-9416-0698
-      Hours: Monday-Friday, 10:00 A.M. to 4:30 P.M., EAT
-      (Not open on holidays)
+    - Visit our Web site at http://www.adaptec-europe.com/.
+    - To speak with a Technical Support Specialist, call, or email,
+      * German:  +49 89 4366 5522, Monday-Friday, 9:00-17:00 CET,
+        http://ask-de.adaptec.com/.
+      * French:  +49 89 4366 5533, Monday-Friday, 9:00-17:00 CET,
+        http://ask-fr.adaptec.com/.
+      * English: +49 89 4366 5544, Monday-Friday, 9:00-17:00 GMT,
+        http://ask.adaptec.com/.
+    - You can order Adaptec cables online at
+      http://www.adaptec.com/buy-cables/.
 
    Japan
+    - Visit our web site at http://www.adaptec.co.jp/.
     - To speak with a Technical Support Specialist, call 
-      +81-3-5308-6120 
-      Hours: Monday-Friday, 9:00 a.m. to 12:00 p.m., 1:00 p.m. to
-      6:00 p.m. TSC
-
-   Hong Kong and China
-    - To speak with a Technical Support Specialist, call 
-      +852-2869-7200
-      Hours: Monday-Friday, 10:00 to 17:00.
-    - Fax Technical Support at +852-2869-7100.
-
-   Singapore
-    - To speak with a Technical Support Specialist, call 
-      +65-245-7470
-      Hours: Monday-Friday, 10:00 to 17:00.
-    - Fax Technical Support at +852-2869-7100
+      +81 3 5308 6120, Monday-Friday, 9:00 a.m. to 12:00 p.m.,
+      1:00 p.m. to 6:00 p.m.
 
 -------------------------------------------------------------------
 /*
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index d2578013e829..36b511c7cade 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -837,8 +837,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     Module for AC'97 motherboards from Intel and compatibles.
                         * Intel i810/810E, i815, i820, i830, i84x, MX440
+                                ICH5, ICH6, ICH7, ESB2
                         * SiS 7012 (SiS 735)
-                        * NVidia NForce, NForce2
+                        * NVidia NForce, NForce2, NForce3, MCP04, CK804
+                                 CK8, CK8S, MCP501
                         * AMD AMD768, AMD8111
                         * ALi m5455
 
@@ -868,6 +870,12 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   --------------------
 
     Module for Intel ICH (i8x0) chipset MC97 modems.
+                        * Intel i810/810E, i815, i820, i830, i84x, MX440
+                                ICH5, ICH6, ICH7
+                        * SiS 7013 (SiS 735)
+                        * NVidia NForce, NForce2, NForce2s, NForce3
+                        * AMD AMD8111
+                        * ALi m5455
 
     ac97_clock    - AC'97 codec clock base (0 = auto-detect)
 
diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
index e651ed8d1e6f..4251085d38d3 100644
--- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
@@ -5206,14 +5206,14 @@ struct _snd_pcm_runtime {
         You need to pass the <function>snd_dma_pci_data(pci)</function>,
         where pci is the struct <structname>pci_dev</structname> pointer
         of the chip as well.
-        The <type>snd_sg_buf_t</type> instance is created as
+        The <type>struct snd_sg_buf</type> instance is created as
         substream-&gt;dma_private. You can cast
         the pointer like: 
 
         <informalexample>
           <programlisting>
 <![CDATA[
-  struct snd_sg_buf *sgbuf = (struct snd_sg_buf_t*)substream->dma_private;
+  struct snd_sg_buf *sgbuf = (struct snd_sg_buf *)substream->dma_private;
 ]]>
           </programlisting>
         </informalexample>
diff --git a/Documentation/spi/butterfly b/Documentation/spi/butterfly
index a2e8c8d90e35..9927af7a629c 100644
--- a/Documentation/spi/butterfly
+++ b/Documentation/spi/butterfly
@@ -12,13 +12,20 @@ You can make this adapter from an old printer cable and solder things
 directly to the Butterfly.  Or (if you have the parts and skills) you
 can come up with something fancier, providing ciruit protection to the
 Butterfly and the printer port, or with a better power supply than two
-signal pins from the printer port.
+signal pins from the printer port.  Or for that matter, you can use
+similar cables to talk to many AVR boards, even a breadboard.
+
+This is more powerful than "ISP programming" cables since it lets kernel
+SPI protocol drivers interact with the AVR, and could even let the AVR
+issue interrupts to them.  Later, your protocol driver should work
+easily with a "real SPI controller", instead of this bitbanger.
 
 
 The first cable connections will hook Linux up to one SPI bus, with the
 AVR and a DataFlash chip; and to the AVR reset line.  This is all you
 need to reflash the firmware, and the pins are the standard Atmel "ISP"
-connector pins (used also on non-Butterfly AVR boards).
+connector pins (used also on non-Butterfly AVR boards).  On the parport
+side this is like "sp12" programming cables.
 
         Signal    Butterfly       Parport (DB-25)
         ------    ---------       ---------------
@@ -40,10 +47,14 @@ by clearing PORTB.[0-3]); (b) configure the mtd_dataflash driver; and
         SELECT  = J400.PB0/nSS  = pin 17/C3,nSELECT
         GND     = J400.GND      = pin 24/GND
 
-The "USI" controller, using J405, can be used for a second SPI bus.  That
-would let you talk to the AVR over SPI, running firmware that makes it act
-as an SPI slave, while letting either Linux or the AVR use the DataFlash.
-There are plenty of spare parport pins to wire this one up, such as:
+Or you could flash firmware making the AVR into an SPI slave (keeping the
+DataFlash in reset) and tweak the spi_butterfly driver to make it bind to
+the driver for your custom SPI-based protocol.
+
+The "USI" controller, using J405, can also be used for a second SPI bus.
+That would let you talk to the AVR using custom SPI-with-USI firmware,
+while letting either Linux or the AVR use the DataFlash.  There are plenty
+of spare parport pins to wire this one up, such as:
 
         Signal    Butterfly       Parport (DB-25)
         ------    ---------       ---------------
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 9f11d36a8c10..b0c7ab93dcb9 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -16,6 +16,7 @@ before actually making adjustments.
 
 Currently, these files might (depending on your configuration)
 show up in /proc/sys/kernel:
+- acpi_video_flags
 - acct
 - core_pattern
 - core_uses_pid
@@ -57,6 +58,15 @@ show up in /proc/sys/kernel:
 
 ==============================================================
 
+acpi_video_flags:
+
+flags
+
+See Doc*/kernel/power/video.txt, it allows mode of video boot to be
+set during run time.
+
+==============================================================
+
 acct:
 
 highwater lowwater frequency
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 391dd64363e7..a46c10fcddfc 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -28,6 +28,7 @@ Currently, these files are in /proc/sys/vm:
 - block_dump
 - drop-caches
 - zone_reclaim_mode
+- zone_reclaim_interval
 
 ==============================================================
 
@@ -126,15 +127,54 @@ the high water marks for each per cpu page list.
 
 zone_reclaim_mode:
 
-This is set during bootup to 1 if it is determined that pages from
-remote zones will cause a significant performance reduction. The
+Zone_reclaim_mode allows to set more or less agressive approaches to
+reclaim memory when a zone runs out of memory. If it is set to zero then no
+zone reclaim occurs. Allocations will be satisfied from other zones / nodes
+in the system.
+
+This is value ORed together of
+
+1       = Zone reclaim on
+2       = Zone reclaim writes dirty pages out
+4       = Zone reclaim swaps pages
+8       = Also do a global slab reclaim pass
+
+zone_reclaim_mode is set during bootup to 1 if it is determined that pages
+from remote zones will cause a measurable performance reduction. The
 page allocator will then reclaim easily reusable pages (those page
-cache pages that are currently not used) before going off node.
+cache pages that are currently not used) before allocating off node pages.
+
+It may be beneficial to switch off zone reclaim if the system is
+used for a file server and all of memory should be used for caching files
+from disk. In that case the caching effect is more important than
+data locality.
+
+Allowing zone reclaim to write out pages stops processes that are
+writing large amounts of data from dirtying pages on other nodes. Zone
+reclaim will write out dirty pages if a zone fills up and so effectively
+throttle the process. This may decrease the performance of a single process
+since it cannot use all of system memory to buffer the outgoing writes
+anymore but it preserve the memory on other nodes so that the performance
+of other processes running on other nodes will not be affected.
+
+Allowing regular swap effectively restricts allocations to the local
+node unless explicitly overridden by memory policies or cpuset
+configurations.
+
+It may be advisable to allow slab reclaim if the system makes heavy
+use of files and builds up large slab caches. However, the slab
+shrink operation is global, may take a long time and free slabs
+in all nodes of the system.
+
+================================================================
+
+zone_reclaim_interval:
+
+The time allowed for off node allocations after zone reclaim
+has failed to reclaim enough pages to allow a local allocation.
 
-The user can override this setting. It may be beneficial to switch
-off zone reclaim if the system is used for a file server and all
-of memory should be used for caching files from disk.
+Time is set in seconds and set by default to 30 seconds.
 
-It may be beneficial to switch this on if one wants to do zone
-reclaim regardless of the numa distances in the system.
+Reduce the interval if undesired off node allocations occur. However, too
+frequent scans will have a negative impact onoff node allocation performance.
 
diff --git a/Documentation/unshare.txt b/Documentation/unshare.txt
new file mode 100644
index 000000000000..90a5e9e5bef1
--- /dev/null
+++ b/Documentation/unshare.txt
@@ -0,0 +1,295 @@
+
+unshare system call:
+--------------------
+This document describes the new system call, unshare. The document
+provides an overview of the feature, why it is needed, how it can
+be used, its interface specification, design, implementation and
+how it can be tested.
+
+Change Log:
+-----------
+version 0.1  Initial document, Janak Desai (janak@us.ibm.com), Jan 11, 2006
+
+Contents:
+---------
+        1) Overview
+        2) Benefits
+        3) Cost
+        4) Requirements
+        5) Functional Specification
+        6) High Level Design
+        7) Low Level Design
+        8) Test Specification
+        9) Future Work
+
+1) Overview
+-----------
+Most legacy operating system kernels support an abstraction of threads
+as multiple execution contexts within a process. These kernels provide
+special resources and mechanisms to maintain these "threads". The Linux
+kernel, in a clever and simple manner, does not make distinction
+between processes and "threads". The kernel allows processes to share
+resources and thus they can achieve legacy "threads" behavior without
+requiring additional data structures and mechanisms in the kernel. The
+power of implementing threads in this manner comes not only from
+its simplicity but also from allowing application programmers to work
+outside the confinement of all-or-nothing shared resources of legacy
+threads. On Linux, at the time of thread creation using the clone system
+call, applications can selectively choose which resources to share
+between threads.
+
+unshare system call adds a primitive to the Linux thread model that
+allows threads to selectively 'unshare' any resources that were being
+shared at the time of their creation. unshare was conceptualized by
+Al Viro in the August of 2000, on the Linux-Kernel mailing list, as part
+of the discussion on POSIX threads on Linux.  unshare augments the
+usefulness of Linux threads for applications that would like to control
+shared resources without creating a new process. unshare is a natural
+addition to the set of available primitives on Linux that implement
+the concept of process/thread as a virtual machine.
+
+2) Benefits
+-----------
+unshare would be useful to large application frameworks such as PAM
+where creating a new process to control sharing/unsharing of process
+resources is not possible. Since namespaces are shared by default
+when creating a new process using fork or clone, unshare can benefit
+even non-threaded applications if they have a need to disassociate
+from default shared namespace. The following lists two use-cases
+where unshare can be used.
+
+2.1 Per-security context namespaces
+-----------------------------------
+unshare can be used to implement polyinstantiated directories using
+the kernel's per-process namespace mechanism. Polyinstantiated directories,
+such as per-user and/or per-security context instance of /tmp, /var/tmp or
+per-security context instance of a user's home directory, isolate user
+processes when working with these directories. Using unshare, a PAM
+module can easily setup a private namespace for a user at login.
+Polyinstantiated directories are required for Common Criteria certification
+with Labeled System Protection Profile, however, with the availability
+of shared-tree feature in the Linux kernel, even regular Linux systems
+can benefit from setting up private namespaces at login and
+polyinstantiating /tmp, /var/tmp and other directories deemed
+appropriate by system administrators.
+
+2.2 unsharing of virtual memory and/or open files
+-------------------------------------------------
+Consider a client/server application where the server is processing
+client requests by creating processes that share resources such as
+virtual memory and open files. Without unshare, the server has to
+decide what needs to be shared at the time of creating the process
+which services the request. unshare allows the server an ability to
+disassociate parts of the context during the servicing of the
+request. For large and complex middleware application frameworks, this
+ability to unshare after the process was created can be very
+useful.
+
+3) Cost
+-------
+In order to not duplicate code and to handle the fact that unshare
+works on an active task (as opposed to clone/fork working on a newly
+allocated inactive task) unshare had to make minor reorganizational
+changes to copy_* functions utilized by clone/fork system call.
+There is a cost associated with altering existing, well tested and
+stable code to implement a new feature that may not get exercised
+extensively in the beginning. However, with proper design and code
+review of the changes and creation of an unshare test for the LTP
+the benefits of this new feature can exceed its cost.
+
+4) Requirements
+---------------
+unshare reverses sharing that was done using clone(2) system call,
+so unshare should have a similar interface as clone(2). That is,
+since flags in clone(int flags, void *stack) specifies what should
+be shared, similar flags in unshare(int flags) should specify
+what should be unshared. Unfortunately, this may appear to invert
+the meaning of the flags from the way they are used in clone(2).
+However, there was no easy solution that was less confusing and that
+allowed incremental context unsharing in future without an ABI change.
+
+unshare interface should accommodate possible future addition of
+new context flags without requiring a rebuild of old applications.
+If and when new context flags are added, unshare design should allow
+incremental unsharing of those resources on an as needed basis.
+
+5) Functional Specification
+---------------------------
+NAME
+        unshare - disassociate parts of the process execution context
+
+SYNOPSIS
+        #include <sched.h>
+
+        int unshare(int flags);
+
+DESCRIPTION
+        unshare allows a process to disassociate parts of its execution
+        context that are currently being shared with other processes. Part
+        of execution context, such as the namespace, is shared by default
+        when a new process is created using fork(2), while other parts,
+        such as the virtual memory, open file descriptors, etc, may be
+        shared by explicit request to share them when creating a process
+        using clone(2).
+
+        The main use of unshare is to allow a process to control its
+        shared execution context without creating a new process.
+
+        The flags argument specifies one or bitwise-or'ed of several of
+        the following constants.
+
+        CLONE_FS
+                If CLONE_FS is set, file system information of the caller
+                is disassociated from the shared file system information.
+
+        CLONE_FILES
+                If CLONE_FILES is set, the file descriptor table of the
+                caller is disassociated from the shared file descriptor
+                table.
+
+        CLONE_NEWNS
+                If CLONE_NEWNS is set, the namespace of the caller is
+                disassociated from the shared namespace.
+
+        CLONE_VM
+                If CLONE_VM is set, the virtual memory of the caller is
+                disassociated from the shared virtual memory.
+
+RETURN VALUE
+        On success, zero returned. On failure, -1 is returned and errno is
+
+ERRORS
+        EPERM   CLONE_NEWNS was specified by a non-root process (process
+                without CAP_SYS_ADMIN).
+
+        ENOMEM  Cannot allocate sufficient memory to copy parts of caller's
+                context that need to be unshared.
+
+        EINVAL  Invalid flag was specified as an argument.
+
+CONFORMING TO
+        The unshare() call is Linux-specific and  should  not be used
+        in programs intended to be portable.
+
+SEE ALSO
+        clone(2), fork(2)
+
+6) High Level Design
+--------------------
+Depending on the flags argument, the unshare system call allocates
+appropriate process context structures, populates it with values from
+the current shared version, associates newly duplicated structures
+with the current task structure and releases corresponding shared
+versions. Helper functions of clone (copy_*) could not be used
+directly by unshare because of the following two reasons.
+  1) clone operates on a newly allocated not-yet-active task
+     structure, where as unshare operates on the current active
+     task. Therefore unshare has to take appropriate task_lock()
+     before associating newly duplicated context structures
+  2) unshare has to allocate and duplicate all context structures
+     that are being unshared, before associating them with the
+     current task and releasing older shared structures. Failure
+     do so will create race conditions and/or oops when trying
+     to backout due to an error. Consider the case of unsharing
+     both virtual memory and namespace. After successfully unsharing
+     vm, if the system call encounters an error while allocating
+     new namespace structure, the error return code will have to
+     reverse the unsharing of vm. As part of the reversal the
+     system call will have to go back to older, shared, vm
+     structure, which may not exist anymore.
+
+Therefore code from copy_* functions that allocated and duplicated
+current context structure was moved into new dup_* functions. Now,
+copy_* functions call dup_* functions to allocate and duplicate
+appropriate context structures and then associate them with the
+task structure that is being constructed. unshare system call on
+the other hand performs the following:
+  1) Check flags to force missing, but implied, flags
+  2) For each context structure, call the corresponding unshare
+     helper function to allocate and duplicate a new context
+     structure, if the appropriate bit is set in the flags argument.
+  3) If there is no error in allocation and duplication and there
+     are new context structures then lock the current task structure,
+     associate new context structures with the current task structure,
+     and release the lock on the current task structure.
+  4) Appropriately release older, shared, context structures.
+
+7) Low Level Design
+-------------------
+Implementation of unshare can be grouped in the following 4 different
+items:
+  a) Reorganization of existing copy_* functions
+  b) unshare system call service function
+  c) unshare helper functions for each different process context
+  d) Registration of system call number for different architectures
+
+  7.1) Reorganization of copy_* functions
+       Each copy function such as copy_mm, copy_namespace, copy_files,
+       etc, had roughly two components. The first component allocated
+       and duplicated the appropriate structure and the second component
+       linked it to the task structure passed in as an argument to the copy
+       function. The first component was split into its own function.
+       These dup_* functions allocated and duplicated the appropriate
+       context structure. The reorganized copy_* functions invoked
+       their corresponding dup_* functions and then linked the newly
+       duplicated structures to the task structure with which the
+       copy function was called.
+
+  7.2) unshare system call service function
+       * Check flags
+         Force implied flags. If CLONE_THREAD is set force CLONE_VM.
+         If CLONE_VM is set, force CLONE_SIGHAND. If CLONE_SIGHAND is
+         set and signals are also being shared, force CLONE_THREAD. If
+         CLONE_NEWNS is set, force CLONE_FS.
+       * For each context flag, invoke the corresponding unshare_*
+         helper routine with flags passed into the system call and a
+         reference to pointer pointing the new unshared structure
+       * If any new structures are created by unshare_* helper
+         functions, take the task_lock() on the current task,
+         modify appropriate context pointers, and release the
+         task lock.
+       * For all newly unshared structures, release the corresponding
+         older, shared, structures.
+
+  7.3) unshare_* helper functions
+       For unshare_* helpers corresponding to CLONE_SYSVSEM, CLONE_SIGHAND,
+       and CLONE_THREAD, return -EINVAL since they are not implemented yet.
+       For others, check the flag value to see if the unsharing is
+       required for that structure. If it is, invoke the corresponding
+       dup_* function to allocate and duplicate the structure and return
+       a pointer to it.
+
+  7.4) Appropriately modify architecture specific code to register the
+       the new system call.
+
+8) Test Specification
+---------------------
+The test for unshare should test the following:
+  1) Valid flags: Test to check that clone flags for signal and
+        signal handlers, for which unsharing is not implemented
+        yet, return -EINVAL.
+  2) Missing/implied flags: Test to make sure that if unsharing
+        namespace without specifying unsharing of filesystem, correctly
+        unshares both namespace and filesystem information.
+  3) For each of the four (namespace, filesystem, files and vm)
+        supported unsharing, verify that the system call correctly
+        unshares the appropriate structure. Verify that unsharing
+        them individually as well as in combination with each
+        other works as expected.
+  4) Concurrent execution: Use shared memory segments and futex on
+        an address in the shm segment to synchronize execution of
+        about 10 threads. Have a couple of threads execute execve,
+        a couple _exit and the rest unshare with different combination
+        of flags. Verify that unsharing is performed as expected and
+        that there are no oops or hangs.
+
+9) Future Work
+--------------
+The current implementation of unshare does not allow unsharing of
+signals and signal handlers. Signals are complex to begin with and
+to unshare signals and/or signal handlers of a currently running
+process is even more complex. If in the future there is a specific
+need to allow unsharing of signals and/or signal handlers, it can
+be incrementally added to unshare without affecting legacy
+applications using unshare.
+
diff --git a/Documentation/usb/et61x251.txt b/Documentation/usb/et61x251.txt
new file mode 100644
index 000000000000..b44dda407ce2
--- /dev/null
+++ b/Documentation/usb/et61x251.txt
@@ -0,0 +1,306 @@
+
+                       ET61X[12]51 PC Camera Controllers
+                                Driver for Linux
+                       =================================
+
+                               - Documentation -
+
+
+Index
+=====
+1.  Copyright
+2.  Disclaimer
+3.  License
+4.  Overview and features
+5.  Module dependencies
+6.  Module loading
+7.  Module parameters
+8.  Optional device control through "sysfs"
+9.  Supported devices
+10. Notes for V4L2 application developers
+11. Contact information
+
+
+1. Copyright
+============
+Copyright (C) 2006 by Luca Risolia <luca.risolia@studio.unibo.it>
+
+
+2. Disclaimer
+=============
+Etoms is a trademark of Etoms Electronics Corp.
+This software is not developed or sponsored by Etoms Electronics.
+
+
+3. License
+==========
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; if not, write to the Free Software
+Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+4. Overview and features
+========================
+This driver supports the video interface of the devices mounting the ET61X151
+or ET61X251 PC Camera Controllers.
+
+It's worth to note that Etoms Electronics has never collaborated with the
+author during the development of this project; despite several requests,
+Etoms Electronics also refused to release enough detailed specifications of
+the video compression engine.
+
+The driver relies on the Video4Linux2 and USB core modules. It has been
+designed to run properly on SMP systems as well.
+
+The latest version of the ET61X[12]51 driver can be found at the following URL:
+http://www.linux-projects.org/
+
+Some of the features of the driver are:
+
+- full compliance with the Video4Linux2 API (see also "Notes for V4L2
+  application developers" paragraph);
+- available mmap or read/poll methods for video streaming through isochronous
+  data transfers;
+- automatic detection of image sensor;
+- support for any window resolutions and optional panning within the maximum
+  pixel area of image sensor;
+- image downscaling with arbitrary scaling factors from 1 and 2 in both
+  directions (see "Notes for V4L2 application developers" paragraph);
+- two different video formats for uncompressed or compressed data in low or
+  high compression quality (see also "Notes for V4L2 application developers"
+  paragraph);
+- full support for the capabilities of every possible image sensors that can
+  be connected to the ET61X[12]51 bridges, including, for istance, red, green,
+  blue and global gain adjustments and exposure control (see "Supported
+  devices" paragraph for details);
+- use of default color settings for sunlight conditions;
+- dynamic I/O interface for both ET61X[12]51 and image sensor control (see
+  "Optional device control through 'sysfs'" paragraph);
+- dynamic driver control thanks to various module parameters (see "Module
+  parameters" paragraph);
+- up to 64 cameras can be handled at the same time; they can be connected and
+  disconnected from the host many times without turning off the computer, if
+  the system supports hotplugging;
+- no known bugs.
+
+
+5. Module dependencies
+======================
+For it to work properly, the driver needs kernel support for Video4Linux and
+USB.
+
+The following options of the kernel configuration file must be enabled and
+corresponding modules must be compiled:
+
+        # Multimedia devices
+        #
+        CONFIG_VIDEO_DEV=m
+
+To enable advanced debugging functionality on the device through /sysfs:
+
+        # Multimedia devices
+        #
+        CONFIG_VIDEO_ADV_DEBUG=y
+
+        # USB support
+        #
+        CONFIG_USB=m
+
+In addition, depending on the hardware being used, the modules below are
+necessary:
+
+        # USB Host Controller Drivers
+        #
+        CONFIG_USB_EHCI_HCD=m
+        CONFIG_USB_UHCI_HCD=m
+        CONFIG_USB_OHCI_HCD=m
+
+And finally:
+
+        # USB Multimedia devices
+        #
+        CONFIG_USB_ET61X251=m
+
+
+6. Module loading
+=================
+To use the driver, it is necessary to load the "et61x251" module into memory
+after every other module required: "videodev", "usbcore" and, depending on
+the USB host controller you have, "ehci-hcd", "uhci-hcd" or "ohci-hcd".
+
+Loading can be done as shown below:
+
+        [root@localhost home]# modprobe et61x251
+
+At this point the devices should be recognized. You can invoke "dmesg" to
+analyze kernel messages and verify that the loading process has gone well:
+
+        [user@localhost home]$ dmesg
+
+
+7. Module parameters
+====================
+Module parameters are listed below:
+-------------------------------------------------------------------------------
+Name:           video_nr
+Type:           short array (min = 0, max = 64)
+Syntax:         <-1|n[,...]>
+Description:    Specify V4L2 minor mode number:
+                -1 = use next available
+                 n = use minor number n
+                You can specify up to 64 cameras this way.
+                For example:
+                video_nr=-1,2,-1 would assign minor number 2 to the second
+                registered camera and use auto for the first one and for every
+                other camera.
+Default:        -1
+-------------------------------------------------------------------------------
+Name:           force_munmap
+Type:           bool array (min = 0, max = 64)
+Syntax:         <0|1[,...]>
+Description:    Force the application to unmap previously mapped buffer memory
+                before calling any VIDIOC_S_CROP or VIDIOC_S_FMT ioctl's. Not
+                all the applications support this feature. This parameter is
+                specific for each detected camera.
+                0 = do not force memory unmapping
+                1 = force memory unmapping (save memory)
+Default:        0
+-------------------------------------------------------------------------------
+Name:           debug
+Type:           ushort
+Syntax:         <n>
+Description:    Debugging information level, from 0 to 3:
+                0 = none (use carefully)
+                1 = critical errors
+                2 = significant informations
+                3 = more verbose messages
+                Level 3 is useful for testing only, when only one device
+                is used at the same time. It also shows some more informations
+                about the hardware being detected. This module parameter can be
+                changed at runtime thanks to the /sys filesystem interface.
+Default:        2
+-------------------------------------------------------------------------------
+
+
+8. Optional device control through "sysfs"
+==========================================
+If the kernel has been compiled with the CONFIG_VIDEO_ADV_DEBUG option enabled,
+it is possible to read and write both the ET61X[12]51 and the image sensor
+registers by using the "sysfs" filesystem interface.
+
+There are four files in the /sys/class/video4linux/videoX directory for each
+registered camera: "reg", "val", "i2c_reg" and "i2c_val". The first two files
+control the ET61X[12]51 bridge, while the other two control the sensor chip.
+"reg" and "i2c_reg" hold the values of the current register index where the
+following reading/writing operations are addressed at through "val" and
+"i2c_val". Their use is not intended for end-users, unless you know what you
+are doing. Remember that you must be logged in as root before writing to them.
+
+As an example, suppose we were to want to read the value contained in the
+register number 1 of the sensor register table - which is usually the product
+identifier - of the camera registered as "/dev/video0":
+
+        [root@localhost #] cd /sys/class/video4linux/video0
+        [root@localhost #] echo 1 > i2c_reg
+        [root@localhost #] cat i2c_val
+
+Note that if the sensor registers can not be read, "cat" will fail.
+To avoid race conditions, all the I/O accesses to the files are serialized.
+
+
+9. Supported devices
+====================
+None of the names of the companies as well as their products will be mentioned
+here. They have never collaborated with the author, so no advertising.
+
+From the point of view of a driver, what unambiguously identify a device are
+its vendor and product USB identifiers. Below is a list of known identifiers of
+devices mounting the ET61X[12]51 PC camera controllers:
+
+Vendor ID  Product ID
+---------  ----------
+0x102c     0x6151
+0x102c     0x6251
+0x102c     0x6253
+0x102c     0x6254
+0x102c     0x6255
+0x102c     0x6256
+0x102c     0x6257
+0x102c     0x6258
+0x102c     0x6259
+0x102c     0x625a
+0x102c     0x625b
+0x102c     0x625c
+0x102c     0x625d
+0x102c     0x625e
+0x102c     0x625f
+0x102c     0x6260
+0x102c     0x6261
+0x102c     0x6262
+0x102c     0x6263
+0x102c     0x6264
+0x102c     0x6265
+0x102c     0x6266
+0x102c     0x6267
+0x102c     0x6268
+0x102c     0x6269
+
+The following image sensors are supported:
+
+Model       Manufacturer
+-----       ------------
+TAS5130D1B  Taiwan Advanced Sensor Corporation
+
+All the available control settings of each image sensor are supported through
+the V4L2 interface.
+
+
+10. Notes for V4L2 application developers
+========================================
+This driver follows the V4L2 API specifications. In particular, it enforces two
+rules:
+
+- exactly one I/O method, either "mmap" or "read", is associated with each
+file descriptor. Once it is selected, the application must close and reopen the
+device to switch to the other I/O method;
+
+- although it is not mandatory, previously mapped buffer memory should always
+be unmapped before calling any "VIDIOC_S_CROP" or "VIDIOC_S_FMT" ioctl's.
+The same number of buffers as before will be allocated again to match the size
+of the new video frames, so you have to map the buffers again before any I/O
+attempts on them.
+
+Consistently with the hardware limits, this driver also supports image
+downscaling with arbitrary scaling factors from 1 and 2 in both directions.
+However, the V4L2 API specifications don't correctly define how the scaling
+factor can be chosen arbitrarily by the "negotiation" of the "source" and
+"target" rectangles. To work around this flaw, we have added the convention
+that, during the negotiation, whenever the "VIDIOC_S_CROP" ioctl is issued, the
+scaling factor is restored to 1.
+
+This driver supports two different video formats: the first one is the "8-bit
+Sequential Bayer" format and can be used to obtain uncompressed video data
+from the device through the current I/O method, while the second one provides
+"raw" compressed video data (without frame headers not related to the
+compressed data). The current compression quality may vary from 0 to 1 and can
+be selected or queried thanks to the VIDIOC_S_JPEGCOMP and VIDIOC_G_JPEGCOMP
+V4L2 ioctl's.
+
+
+11. Contact information
+=======================
+The author may be contacted by e-mail at <luca.risolia@studio.unibo.it>.
+
+GPG/PGP encrypted e-mail's are accepted. The GPG key ID of the author is
+'FCE635A4'; the public 1024-bit key should be available at any keyserver;
+the fingerprint is: '88E8 F32F 7244 68BA 3958  5D40 99DA 5D2A FCE6 35A4'.
diff --git a/Documentation/usb/sn9c102.txt b/Documentation/usb/sn9c102.txt
index 3f8a119db31b..c6b76414172c 100644
--- a/Documentation/usb/sn9c102.txt
+++ b/Documentation/usb/sn9c102.txt
@@ -17,16 +17,15 @@ Index
 7.  Module parameters
 8.  Optional device control through "sysfs"
 9.  Supported devices
-10. How to add plug-in's for new image sensors
-11. Notes for V4L2 application developers
-12. Video frame formats
-13. Contact information
-14. Credits
+10. Notes for V4L2 application developers
+11. Video frame formats
+12. Contact information
+13. Credits
 
 
 1. Copyright
 ============
-Copyright (C) 2004-2005 by Luca Risolia <luca.risolia@studio.unibo.it>
+Copyright (C) 2004-2006 by Luca Risolia <luca.risolia@studio.unibo.it>
 
 
 2. Disclaimer
@@ -54,9 +53,8 @@ Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 
 4. Overview and features
 ========================
-This driver attempts to support the video and audio streaming capabilities of
-the devices mounting the SONiX SN9C101, SN9C102 and SN9C103 PC Camera
-Controllers.
+This driver attempts to support the video interface of the devices mounting the
+SONiX SN9C101, SN9C102 and SN9C103 PC Camera Controllers.
 
 It's worth to note that SONiX has never collaborated with the author during the
 development of this project, despite several requests for enough detailed
@@ -78,6 +76,7 @@ Some of the features of the driver are:
 - available mmap or read/poll methods for video streaming through isochronous
   data transfers;
 - automatic detection of image sensor;
+- support for built-in microphone interface;
 - support for any window resolutions and optional panning within the maximum
   pixel area of image sensor;
 - image downscaling with arbitrary scaling factors from 1, 2 and 4 in both
@@ -96,7 +95,7 @@ Some of the features of the driver are:
   parameters" paragraph);
 - up to 64 cameras can be handled at the same time; they can be connected and
   disconnected from the host many times without turning off the computer, if
-  your system supports hotplugging;
+  the system supports hotplugging;
 - no known bugs.
 
 
@@ -112,6 +111,12 @@ corresponding modules must be compiled:
         #
         CONFIG_VIDEO_DEV=m
 
+To enable advanced debugging functionality on the device through /sysfs:
+
+        # Multimedia devices
+        #
+        CONFIG_VIDEO_ADV_DEBUG=y
+
         # USB support
         #
         CONFIG_USB=m
@@ -125,6 +130,21 @@ necessary:
         CONFIG_USB_UHCI_HCD=m
         CONFIG_USB_OHCI_HCD=m
 
+The SN9C103 controller also provides a built-in microphone interface. It is
+supported by the USB Audio driver thanks to the ALSA API:
+
+        # Sound
+        #
+        CONFIG_SOUND=y
+
+        # Advanced Linux Sound Architecture
+        #
+        CONFIG_SND=m
+
+        # USB devices
+        #
+        CONFIG_SND_USB_AUDIO=m
+
 And finally:
 
         # USB Multimedia devices
@@ -153,7 +173,7 @@ analyze kernel messages and verify that the loading process has gone well:
 Module parameters are listed below:
 -------------------------------------------------------------------------------
 Name:           video_nr
-Type:           int array (min = 0, max = 64)
+Type:           short array (min = 0, max = 64)
 Syntax:         <-1|n[,...]> 
 Description:    Specify V4L2 minor mode number:
                 -1 = use next available
@@ -165,19 +185,19 @@ Description:    Specify V4L2 minor mode number:
                 other camera.
 Default:        -1
 -------------------------------------------------------------------------------
-Name:           force_munmap;
+Name:           force_munmap
 Type:           bool array (min = 0, max = 64)
 Syntax:         <0|1[,...]> 
 Description:    Force the application to unmap previously mapped buffer memory
                 before calling any VIDIOC_S_CROP or VIDIOC_S_FMT ioctl's. Not
                 all the applications support this feature. This parameter is
                 specific for each detected camera.
-                0 = do not force memory unmapping"
-                1 = force memory unmapping (save memory)"
+                0 = do not force memory unmapping
+                1 = force memory unmapping (save memory)
 Default:        0
 -------------------------------------------------------------------------------
 Name:           debug
-Type:           int
+Type:           ushort
 Syntax:         <n> 
 Description:    Debugging information level, from 0 to 3:
                 0 = none (use carefully)
@@ -187,14 +207,15 @@ Description:    Debugging information level, from 0 to 3:
                 Level 3 is useful for testing only, when only one device
                 is used. It also shows some more informations about the
                 hardware being detected. This parameter can be changed at
-                runtime thanks to the /sys filesystem.
+                runtime thanks to the /sys filesystem interface.
 Default:        2
 -------------------------------------------------------------------------------
 
 
 8. Optional device control through "sysfs" [1]
 ==========================================
-It is possible to read and write both the SN9C10x and the image sensor
+If the kernel has been compiled with the CONFIG_VIDEO_ADV_DEBUG option enabled,
+it is possible to read and write both the SN9C10x and the image sensor
 registers by using the "sysfs" filesystem interface.
 
 Every time a supported device is recognized, a write-only file named "green" is
@@ -236,7 +257,7 @@ serialized.
 
 The sysfs interface also provides the "frame_header" entry, which exports the
 frame header of the most recent requested and captured video frame. The header
-is 12-bytes long and is appended to every video frame by the SN9C10x
+is always 18-bytes long and is appended to every video frame by the SN9C10x
 controllers. As an example, this additional information can be used by the user
 application for implementing auto-exposure features via software. 
 
@@ -250,7 +271,8 @@ Byte #  Value         Description
 0x03    0xC4          Frame synchronisation pattern.
 0x04    0xC4          Frame synchronisation pattern.
 0x05    0x96          Frame synchronisation pattern.
-0x06    0x00 or 0x01  Unknown meaning. The exact value depends on the chip.
+0x06    0xXX          Unknown meaning. The exact value depends on the chip;
+                      possible values are 0x00, 0x01 and 0x20.
 0x07    0xXX          Variable value, whose bits are ff00uzzc, where ff is a
                       frame counter, u is unknown, zz is a size indicator
                       (00 = VGA, 01 = SIF, 10 = QSIF) and c stands for
@@ -267,12 +289,23 @@ Byte #  Value         Description
                       times the area outside of the specified AE area. For
                       images that are not pure white, the value scales down
                       according to relative whiteness.
+                      according to relative whiteness.
+
+The following bytes are used by the SN9C103 bridge only:
+
+0x0C    0xXX          Unknown meaning
+0x0D    0xXX          Unknown meaning
+0x0E    0xXX          Unknown meaning
+0x0F    0xXX          Unknown meaning
+0x10    0xXX          Unknown meaning
+0x11    0xXX          Unknown meaning
 
 The AE area (sx, sy, ex, ey) in the active window can be set by programming the
 registers 0x1c, 0x1d, 0x1e and 0x1f of the SN9C10x controllers, where one unit
 corresponds to 32 pixels.
 
-[1] The frame header has been documented by Bertrik Sikken.
+[1] Part of the meaning of the frame header has been documented by Bertrik
+    Sikken.
 
 
 9. Supported devices
@@ -298,6 +331,7 @@ Vendor ID  Product ID
 0x0c45     0x602b
 0x0c45     0x602c
 0x0c45     0x602d
+0x0c45     0x602e
 0x0c45     0x6030
 0x0c45     0x6080
 0x0c45     0x6082
@@ -348,18 +382,7 @@ appreciated. Non-available hardware will not be supported by the author of this
 driver.
 
 
-10. How to add plug-in's for new image sensors
-==============================================
-It should be easy to write plug-in's for new sensors by using the small API
-that has been created for this purpose, which is present in "sn9c102_sensor.h"
-(documentation is included there). As an example, have a look at the code in
-"sn9c102_pas106b.c", which uses the mentioned interface.
-
-At the moment, possible unsupported image sensors are: CIS-VF10 (VGA),
-OV7620 (VGA), OV7630 (VGA).
-
-
-11. Notes for V4L2 application developers
+10. Notes for V4L2 application developers
 =========================================
 This driver follows the V4L2 API specifications. In particular, it enforces two
 rules:
@@ -394,7 +417,7 @@ initialized (as described in the documentation of the API for the image sensors
 supplied by this driver).
 
 
-12. Video frame formats [1]
+11. Video frame formats [1]
 =======================
 The SN9C10x PC Camera Controllers can send images in two possible video
 formats over the USB: either native "Sequential RGB Bayer" or Huffman
@@ -455,7 +478,7 @@ The following Huffman codes have been found:
     documented by Bertrik Sikken.
 
 
-13. Contact information
+12. Contact information
 =======================
 The author may be contacted by e-mail at <luca.risolia@studio.unibo.it>.
 
@@ -464,7 +487,7 @@ GPG/PGP encrypted e-mail's are accepted. The GPG key ID of the author is
 the fingerprint is: '88E8 F32F 7244 68BA 3958  5D40 99DA 5D2A FCE6 35A4'.
 
 
-14. Credits
+13. Credits
 ===========
 Many thanks to following persons for their contribute (listed in alphabetical
 order):
@@ -480,5 +503,5 @@ order):
 - Bertrik Sikken, who reverse-engineered and documented the Huffman compression
   algorithm used in the SN9C10x controllers and implemented the first decoder;
 - Mizuno Takafumi for the donation of a webcam;
-- An "anonymous" donator (who didn't want his name to be revealed) for the
+- an "anonymous" donator (who didn't want his name to be revealed) for the
   donation of a webcam.
diff --git a/Documentation/usb/w9968cf.txt b/Documentation/usb/w9968cf.txt
index 18a47738d56c..9d46cd0b19e3 100644
--- a/Documentation/usb/w9968cf.txt
+++ b/Documentation/usb/w9968cf.txt
@@ -57,16 +57,12 @@ based cameras should be supported as well.
 The driver is divided into two modules: the basic one, "w9968cf", is needed for
 the supported devices to work; the second one, "w9968cf-vpp", is an optional
 module, which provides some useful video post-processing functions like video
-decoding, up-scaling and colour conversions. Once the driver is installed,
-every time an application tries to open a recognized device, "w9968cf" checks
-the presence of the "w9968cf-vpp" module and loads it automatically by default.
+decoding, up-scaling and colour conversions.
 
-Please keep in mind that official kernels do not include the second module for
-performance purposes. However it is always recommended to download and install
-the latest and complete release of the driver, replacing the existing one, if
-present: it will be still even possible not to load the "w9968cf-vpp" module at
-all, if you ever want to. Another important missing feature of the version in
-the official Linux 2.4 kernels is the writeable /proc filesystem interface.
+Note that the official kernels do neither include nor support the second
+module for performance purposes. Therefore, it is always recommended to
+download and install the latest and complete release of the driver,
+replacing the existing one, if present.
 
 The latest and full-featured version of the W996[87]CF driver can be found at:
 http://www.linux-projects.org. Please refer to the documentation included in
@@ -201,22 +197,6 @@ 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:           vppmod_load
-Type:           bool
-Syntax:         <0|1>
-Description:    Automatic 'w9968cf-vpp' module loading: 0 disabled, 1 enabled.
-                If enabled, every time an application attempts to open a
-                camera, 'insmod' searches for the video post-processing module
-                in the system and loads it automatically (if present).
-                The optional 'w9968cf-vpp' module adds extra image manipulation
-                capabilities to the 'w9968cf' module,like software up-scaling,
-                colour conversions and video decompression for very high frame
-                rates.
-Default:        1
-Note:           The kernel must be compiled with the CONFIG_KMOD option
-                enabled for the 'w9968cf-vpp' module to be loaded and for
-                this parameter to be present.
--------------------------------------------------------------------------------
 Name:           simcams 
 Type:           int 
 Syntax:         <n> 
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index 56e194f1a0b0..8bea3fbd0548 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -42,4 +42,4 @@
  41 -> Hauppauge WinTV-HVR1100 DVB-T/Hybrid (Low Profile)  [0070:9800,0070:9802]
  42 -> digitalnow DNTV Live! DVB-T Pro                     [1822:0025]
  43 -> KWorld/VStream XPert DVB-T with cx22702             [17de:08a1]
- 44 -> DViCO FusionHDTV DVB-T Dual Digital                 [18ac:db50]
+ 44 -> DViCO FusionHDTV DVB-T Dual Digital                 [18ac:db50,18ac:db54]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index cb3a59bbeb17..8a352597830f 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -1,7 +1,7 @@
   0 -> UNKNOWN/GENERIC
   1 -> Proteus Pro [philips reference design]   [1131:2001,1131:2001]
   2 -> LifeView FlyVIDEO3000                    [5168:0138,4e42:0138]
-  3 -> LifeView FlyVIDEO2000                    [5168:0138]
+  3 -> LifeView/Typhoon FlyVIDEO2000            [5168:0138,4e42:0138]
   4 -> EMPRESS                                  [1131:6752]
   5 -> SKNet Monster TV                         [1131:4e85]
   6 -> Tevion MD 9717
@@ -53,12 +53,12 @@
  52 -> AverMedia AverTV/305                     [1461:2108]
  53 -> ASUS TV-FM 7135                          [1043:4845]
  54 -> LifeView FlyTV Platinum FM               [5168:0214,1489:0214]
- 55 -> LifeView FlyDVB-T DUO                    [5168:0502,5168:0306]
+ 55 -> LifeView FlyDVB-T DUO                    [5168:0306]
  56 -> Avermedia AVerTV 307                     [1461:a70a]
  57 -> Avermedia AVerTV GO 007 FM               [1461:f31f]
  58 -> ADS Tech Instant TV (saa7135)            [1421:0350,1421:0351,1421:0370,1421:1370]
  59 -> Kworld/Tevion V-Stream Xpert TV PVR7134
- 60 -> Typhoon DVB-T Duo Digital/Analog Cardbus [4e42:0502]
+ 60 -> LifeView/Typhoon FlyDVB-T Duo Cardbus    [5168:0502,4e42:0502]
  61 -> Philips TOUGH DVB-T reference design     [1131:2004]
  62 -> Compro VideoMate TV Gold+II
  63 -> Kworld Xpert TV PVR7134
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration
new file mode 100644
index 000000000000..c52820fcf500
--- /dev/null
+++ b/Documentation/vm/page_migration
@@ -0,0 +1,129 @@
+Page migration
+--------------
+
+Page migration allows the moving of the physical location of pages between
+nodes in a numa system while the process is running. This means that the
+virtual addresses that the process sees do not change. However, the
+system rearranges the physical location of those pages.
+
+The main intend of page migration is to reduce the latency of memory access
+by moving pages near to the processor where the process accessing that memory
+is running.
+
+Page migration allows a process to manually relocate the node on which its
+pages are located through the MF_MOVE and MF_MOVE_ALL options while setting
+a new memory policy. The pages of process can also be relocated
+from another process using the sys_migrate_pages() function call. The
+migrate_pages function call takes two sets of nodes and moves pages of a
+process that are located on the from nodes to the destination nodes.
+
+Manual migration is very useful if for example the scheduler has relocated
+a process to a processor on a distant node. A batch scheduler or an
+administrator may detect the situation and move the pages of the process
+nearer to the new processor. At some point in the future we may have
+some mechanism in the scheduler that will automatically move the pages.
+
+Larger installations usually partition the system using cpusets into
+sections of nodes. Paul Jackson has equipped cpusets with the ability to
+move pages when a task is moved to another cpuset. This allows automatic
+control over locality of a process. If a task is moved to a new cpuset
+then also all its pages are moved with it so that the performance of the
+process does not sink dramatically (as is the case today).
+
+Page migration allows the preservation of the relative location of pages
+within a group of nodes for all migration techniques which will preserve a
+particular memory allocation pattern generated even after migrating a
+process. This is necessary in order to preserve the memory latencies.
+Processes will run with similar performance after migration.
+
+Page migration occurs in several steps. First a high level
+description for those trying to use migrate_pages() and then
+a low level description of how the low level details work.
+
+A. Use of migrate_pages()
+-------------------------
+
+1. Remove pages from the LRU.
+
+   Lists of pages to be migrated are generated by scanning over
+   pages and moving them into lists. This is done by
+   calling isolate_lru_page() or __isolate_lru_page().
+   Calling isolate_lru_page increases the references to the page
+   so that it cannot vanish under us.
+
+2. Generate a list of newly allocates page to move the contents
+   of the first list to.
+
+3. The migrate_pages() function is called which attempts
+   to do the migration. It returns the moved pages in the
+   list specified as the third parameter and the failed
+   migrations in the fourth parameter. The first parameter
+   will contain the pages that could still be retried.
+
+4. The leftover pages of various types are returned
+   to the LRU using putback_to_lru_pages() or otherwise
+   disposed of. The pages will still have the refcount as
+   increased by isolate_lru_pages()!
+
+B. Operation of migrate_pages()
+--------------------------------
+
+migrate_pages does several passes over its list of pages. A page is moved
+if all references to a page are removable at the time.
+
+Steps:
+
+1. Lock the page to be migrated
+
+2. Insure that writeback is complete.
+
+3. Make sure that the page has assigned swap cache entry if
+   it is an anonyous page. The swap cache reference is necessary
+   to preserve the information contain in the page table maps.
+
+4. Prep the new page that we want to move to. It is locked
+   and set to not being uptodate so that all accesses to the new
+   page immediately lock while we are moving references.
+
+5. All the page table references to the page are either dropped (file backed)
+   or converted to swap references (anonymous pages). This should decrease the
+   reference count.
+
+6. The radix tree lock is taken
+
+7. The refcount of the page is examined and we back out if references remain
+   otherwise we know that we are the only one referencing this page.
+
+8. The radix tree is checked and if it does not contain the pointer to this
+   page then we back out.
+
+9. The mapping is checked. If the mapping is gone then a truncate action may
+   be in progress and we back out.
+
+10. The new page is prepped with some settings from the old page so that accesses
+   to the new page will be discovered to have the correct settings.
+
+11. The radix tree is changed to point to the new page.
+
+12. The reference count of the old page is dropped because the reference has now
+    been removed.
+
+13. The radix tree lock is dropped.
+
+14. The page contents are copied to the new page.
+
+15. The remaining page flags are copied to the new page.
+
+16. The old page flags are cleared to indicate that the page does
+    not use any information anymore.
+
+17. Queued up writeback on the new page is triggered.
+
+18. If swap pte's were generated for the page then remove them again.
+
+19. The locks are dropped from the old and new page.
+
+20. The new page is moved to the LRU.
+
+Christoph Lameter, December 19, 2005.
+
diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt
index 9c5fc15d03d1..153740f460a6 100644
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -40,6 +40,18 @@ APICs
    no_timer_check Don't check the IO-APIC timer. This can work around
                  problems with incorrect timer initialization on some boards.
 
+   apicmaintimer Run time keeping from the local APIC timer instead
+                 of using the PIT/HPET interrupt for this. This is useful
+                 when the PIT/HPET interrupts are unreliable.
+
+   noapicmaintimer  Don't do time keeping using the APIC timer.
+                 Useful when this option was auto selected, but doesn't work.
+
+   apicpmtimer
+                 Do APIC timer calibration using the pmtimer. Implies
+                 apicmaintimer. Useful when your PIT timer is totally
+                 broken.
+
 Early Console
 
    syntax: earlyprintk=vga