Merge commit 'v2.6.31-rc6' into core/rcu

Merge reason: the branch was on pre-rc1 .30, update to latest.

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

45 files changed, 2265 insertions, 1735 deletions

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index cbbd3e069945..5f3bedaf8e35 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -94,28 +94,37 @@ What:		/sys/block/<disk>/queue/physical_block_size
 Date:		May 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		This is the smallest unit the storage device can write
-		without resorting to read-modify-write operation.  It is
-		usually the same as the logical block size but may be
-		bigger.  One example is SATA drives with 4KB sectors
-		that expose a 512-byte logical block size to the
-		operating system.
+		This is the smallest unit a physical storage device can
+		write atomically.  It is usually the same as the logical
+		block size but may be bigger.  One example is SATA
+		drives with 4KB sectors that expose a 512-byte logical
+		block size to the operating system.  For stacked block
+		devices the physical_block_size variable contains the
+		maximum physical_block_size of the component devices.
 
 What:		/sys/block/<disk>/queue/minimum_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		Storage devices may report a preferred minimum I/O size,
-		which is the smallest request the device can perform
-		without incurring a read-modify-write penalty.  For disk
-		drives this is often the physical block size.  For RAID
-		arrays it is often the stripe chunk size.
+		Storage devices may report a granularity or preferred
+		minimum I/O size which is the smallest request the
+		device can perform without incurring a performance
+		penalty.  For disk drives this is often the physical
+		block size.  For RAID arrays it is often the stripe
+		chunk size.  A properly aligned multiple of
+		minimum_io_size is the preferred request size for
+		workloads where a high number of I/O operations is
+		desired.
 
 What:		/sys/block/<disk>/queue/optimal_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
 		Storage devices may report an optimal I/O size, which is
-		the device's preferred unit of receiving I/O.  This is
-		rarely reported for disk drives.  For RAID devices it is
-		usually the stripe width or the internal block size.
+		the device's preferred unit for sustained I/O.  This is
+		rarely reported for disk drives.  For RAID arrays it is
+		usually the stripe width or the internal track size.  A
+		properly aligned multiple of optimal_io_size is the
+		preferred request size for workloads where sustained
+		throughput is desired.  If no optimal I/O size is
+		reported this file contains 0.
diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl
index a50d6cd58573..992e67e6be7f 100644
--- a/Documentation/DocBook/kernel-hacking.tmpl
+++ b/Documentation/DocBook/kernel-hacking.tmpl
@@ -449,8 +449,8 @@ printk(KERN_INFO "i = %u\n", i);
    </para>
 
    <programlisting>
-__u32 ipaddress;
-printk(KERN_INFO "my ip: %d.%d.%d.%d\n", NIPQUAD(ipaddress));
+__be32 ipaddress;
+printk(KERN_INFO "my ip: %pI4\n", &amp;ipaddress);
    </programlisting>
 
    <para>
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index e36986663570..f3f37f141dbd 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -184,8 +184,6 @@ usage should require reading the full document.
 !Finclude/net/mac80211.h ieee80211_ctstoself_get
 !Finclude/net/mac80211.h ieee80211_ctstoself_duration
 !Finclude/net/mac80211.h ieee80211_generic_frame_duration
-!Finclude/net/mac80211.h ieee80211_get_hdrlen_from_skb
-!Finclude/net/mac80211.h ieee80211_hdrlen
 !Finclude/net/mac80211.h ieee80211_wake_queue
 !Finclude/net/mac80211.h ieee80211_stop_queue
 !Finclude/net/mac80211.h ieee80211_wake_queues
diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt
index 93cb28d05dcd..18f9651ff23d 100644
--- a/Documentation/RCU/rculist_nulls.txt
+++ b/Documentation/RCU/rculist_nulls.txt
@@ -83,11 +83,12 @@ not detect it missed following items in original chain.
 obj = kmem_cache_alloc(...);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
-atomic_inc(&obj->refcnt);
 /*
  * we need to make sure obj->key is updated before obj->next
+ * or obj->refcnt
  */
 smp_wmb();
+atomic_set(&obj->refcnt, 1);
 hlist_add_head_rcu(&obj->obj_node, list);
 unlock_chain(); // typically a spin_unlock()
 
@@ -159,6 +160,10 @@ out:
 obj = kmem_cache_alloc(cachep);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
+/*
+ * changes to obj->key must be visible before refcnt one
+ */
+smp_wmb();
 atomic_set(&obj->refcnt, 1);
 /*
  * insert obj in RCU way (readers might be traversing chain)
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 43cb1004d35f..9d58c7c5eddd 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -21,6 +21,8 @@ ffff8000	ffffffff	copy_user_page / clear_user_page use.
 				For SA11xx and Xscale, this is used to
 				setup a minicache mapping.
 
+ffff4000	ffffffff	cache aliasing on ARMv6 and later CPUs.
+
 ffff1000	ffff7fff	Reserved.
 				Platforms must not use this address range.
 
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index e8ca040ba2cf..2d735b0ae383 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -50,7 +50,7 @@ encouraged them to allow separation of the data and integrity metadata
 scatter-gather lists.
 
 The controller will interleave the buffers on write and split them on
-read.  This means that the Linux can DMA the data buffers to and from
+read.  This means that Linux can DMA the data buffers to and from
 host memory without changes to the page cache.
 
 Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs
@@ -66,7 +66,7 @@ software RAID5).
 
 The IP checksum is weaker than the CRC in terms of detecting bit
 errors.  However, the strength is really in the separation of the data
-buffers and the integrity metadata.  These two distinct buffers much
+buffers and the integrity metadata.  These two distinct buffers must
 match up for an I/O to complete.
 
 The separation of the data and integrity metadata buffers as well as
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index f9ca389dddf4..1d7e9784439a 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -777,6 +777,18 @@ in cpuset directories:
 # /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
 # /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
 
+To add a CPU to a cpuset, write the new list of CPUs including the
+CPU to be added. To add 6 to the above cpuset:
+
+# /bin/echo 1-4,6 > cpus	-> set cpus list to cpus 1,2,3,4,6
+
+Similarly to remove a CPU from a cpuset, write the new list of CPUs
+without the CPU to be removed.
+
+To remove all the CPUs:
+
+# /bin/echo "" > cpus		-> clear cpus list
+
 2.3 Setting flags
 -----------------
 
diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c
index f688eba87704..6a5be5d5c8e4 100644
--- a/Documentation/connector/cn_test.c
+++ b/Documentation/connector/cn_test.c
@@ -1,7 +1,7 @@
 /*
  * 	cn_test.c
  * 
- * 2004-2005 Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * 2004+ Copyright (c) Evgeniy Polyakov <zbr@ioremap.net>
  * All rights reserved.
  * 
  * This program is free software; you can redistribute it and/or modify
@@ -194,5 +194,5 @@ module_init(cn_test_init);
 module_exit(cn_test_fini);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>");
+MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>");
 MODULE_DESCRIPTION("Connector's test module");
diff --git a/Documentation/connector/ucon.c b/Documentation/connector/ucon.c
index d738cde2a8d5..c5092ad0ce4b 100644
--- a/Documentation/connector/ucon.c
+++ b/Documentation/connector/ucon.c
@@ -1,7 +1,7 @@
 /*
  * 	ucon.c
  *
- * Copyright (c) 2004+ Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * Copyright (c) 2004+ Evgeniy Polyakov <zbr@ioremap.net>
  *
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt
new file mode 100644
index 000000000000..994dd75475a6
--- /dev/null
+++ b/Documentation/device-mapper/dm-log.txt
@@ -0,0 +1,54 @@
+Device-Mapper Logging
+=====================
+The device-mapper logging code is used by some of the device-mapper
+RAID targets to track regions of the disk that are not consistent.
+A region (or portion of the address space) of the disk may be
+inconsistent because a RAID stripe is currently being operated on or
+a machine died while the region was being altered.  In the case of
+mirrors, a region would be considered dirty/inconsistent while you
+are writing to it because the writes need to be replicated for all
+the legs of the mirror and may not reach the legs at the same time.
+Once all writes are complete, the region is considered clean again.
+
+There is a generic logging interface that the device-mapper RAID
+implementations use to perform logging operations (see
+dm_dirty_log_type in include/linux/dm-dirty-log.h).  Various different
+logging implementations are available and provide different
+capabilities.  The list includes:
+
+Type		Files
+====		=====
+disk		drivers/md/dm-log.c
+core		drivers/md/dm-log.c
+userspace	drivers/md/dm-log-userspace* include/linux/dm-log-userspace.h
+
+The "disk" log type
+-------------------
+This log implementation commits the log state to disk.  This way, the
+logging state survives reboots/crashes.
+
+The "core" log type
+-------------------
+This log implementation keeps the log state in memory.  The log state
+will not survive a reboot or crash, but there may be a small boost in
+performance.  This method can also be used if no storage device is
+available for storing log state.
+
+The "userspace" log type
+------------------------
+This log type simply provides a way to export the log API to userspace,
+so log implementations can be done there.  This is done by forwarding most
+logging requests to userspace, where a daemon receives and processes the
+request.
+
+The structure used for communication between kernel and userspace are
+located in include/linux/dm-log-userspace.h.  Due to the frequency,
+diversity, and 2-way communication nature of the exchanges between
+kernel and userspace, 'connector' is used as the interface for
+communication.
+
+There are currently two userspace log implementations that leverage this
+framework - "clustered_disk" and "clustered_core".  These implementations
+provide a cluster-coherent log for shared-storage.  Device-mapper mirroring
+can be used in a shared-storage environment when the cluster log implementations
+are employed.
diff --git a/Documentation/device-mapper/dm-queue-length.txt b/Documentation/device-mapper/dm-queue-length.txt
new file mode 100644
index 000000000000..f4db2562175c
--- /dev/null
+++ b/Documentation/device-mapper/dm-queue-length.txt
@@ -0,0 +1,39 @@
+dm-queue-length
+===============
+
+dm-queue-length is a path selector module for device-mapper targets,
+which selects a path with the least number of in-flight I/Os.
+The path selector name is 'queue-length'.
+
+Table parameters for each path: [<repeat_count>]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used. To check
+			the default value, see the activated table.
+
+Status for each path: <status> <fail-count> <in-flight>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight>: The number of in-flight I/Os on the path.
+
+
+Algorithm
+=========
+
+dm-queue-length increments/decrements 'in-flight' when an I/O is
+dispatched/completed respectively.
+dm-queue-length selects a path with the minimum 'in-flight'.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128.
+
+# echo "0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 1 8:0 A 0 0 8:16 A 0 0
diff --git a/Documentation/device-mapper/dm-service-time.txt b/Documentation/device-mapper/dm-service-time.txt
new file mode 100644
index 000000000000..7d00668e97bb
--- /dev/null
+++ b/Documentation/device-mapper/dm-service-time.txt
@@ -0,0 +1,91 @@
+dm-service-time
+===============
+
+dm-service-time is a path selector module for device-mapper targets,
+which selects a path with the shortest estimated service time for
+the incoming I/O.
+
+The service time for each path is estimated by dividing the total size
+of in-flight I/Os on a path with the performance value of the path.
+The performance value is a relative throughput value among all paths
+in a path-group, and it can be specified as a table argument.
+
+The path selector name is 'service-time'.
+
+Table parameters for each path: [<repeat_count> [<relative_throughput>]]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used.  To check
+			the default value, see the activated table.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+			The valid range is 0-100.
+			If not given, minimum value '1' is used.
+			If '0' is given, the path isn't selected while
+			other paths having a positive value are available.
+
+Status for each path: <status> <fail-count> <in-flight-size> \
+		      <relative_throughput>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight-size>: The size of in-flight I/Os on the path.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+
+
+Algorithm
+=========
+
+dm-service-time adds the I/O size to 'in-flight-size' when the I/O is
+dispatched and substracts when completed.
+Basically, dm-service-time selects a path having minimum service time
+which is calculated by:
+
+	('in-flight-size' + 'size-of-incoming-io') / 'relative_throughput'
+
+However, some optimizations below are used to reduce the calculation
+as much as possible.
+
+	1. If the paths have the same 'relative_throughput', skip
+	   the division and just compare the 'in-flight-size'.
+
+	2. If the paths have the same 'in-flight-size', skip the division
+	   and just compare the 'relative_throughput'.
+
+	3. If some paths have non-zero 'relative_throughput' and others
+	   have zero 'relative_throughput', ignore those paths with zero
+	   'relative_throughput'.
+
+If such optimizations can't be applied, calculate service time, and
+compare service time.
+If calculated service time is equal, the path having maximum
+'relative_throughput' may be better.  So compare 'relative_throughput'
+then.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128
+and sda has an average throughput 1GB/s and sdb has 4GB/s,
+'relative_throughput' value may be '1' for sda and '4' for sdb.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 1 8:16 A 0 0 4
+
+
+Or '2' for sda and '8' for sdb would be also true.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 2 8:16 A 0 0 8
diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt
index 82132169d47a..60120fb3b961 100644
--- a/Documentation/driver-model/driver.txt
+++ b/Documentation/driver-model/driver.txt
@@ -207,8 +207,8 @@ Attributes
 ~~~~~~~~~~
 struct driver_attribute {
         struct attribute        attr;
-        ssize_t (*show)(struct device_driver *, char * buf, size_t count, loff_t off);
-        ssize_t (*store)(struct device_driver *, const char * buf, size_t count, loff_t off);
+        ssize_t (*show)(struct device_driver *driver, char *buf);
+        ssize_t (*store)(struct device_driver *, const char * buf, size_t count);
 };
 
 Device drivers can export attributes via their sysfs directories. 
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index a52adfc9a57f..3d1b0ab70c8e 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -25,7 +25,7 @@ use IO::Handle;
 		"tda10046lifeview", "av7110", "dec2000t", "dec2540t",
 		"dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
 		"or51211", "or51132_qam", "or51132_vsb", "bluebird",
-		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2" );
+		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718" );
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -381,6 +381,57 @@ sub cx18 {
     $allfiles;
 }
 
+sub mpc718 {
+    my $archive = 'Yuan MPC718 TV Tuner Card 2.13.10.1016.zip';
+    my $url = "ftp://ftp.work.acer-euro.com/desktop/aspire_idea510/vista/Drivers/$archive";
+    my $fwfile = "dvb-cx18-mpc718-mt352.fw";
+    my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
+
+    checkstandard();
+    wgetfile($archive, $url);
+    unzip($archive, $tmpdir);
+
+    my $sourcefile = "$tmpdir/Yuan MPC718 TV Tuner Card 2.13.10.1016/mpc718_32bit/yuanrap.sys";
+    my $found = 0;
+
+    open IN, '<', $sourcefile or die "Couldn't open $sourcefile to extract $fwfile data\n";
+    binmode IN;
+    open OUT, '>', $fwfile;
+    binmode OUT;
+    {
+	# Block scope because we change the line terminator variable $/
+	my $prevlen = 0;
+	my $currlen;
+
+	# Buried in the data segment are 3 runs of almost identical
+	# register-value pairs that end in 0x5d 0x01 which is a "TUNER GO"
+	# command for the MT352.
+	# Pull out the middle run (because it's easy) of register-value
+	# pairs to make the "firmware" file.
+
+	local $/ = "\x5d\x01"; # MT352 "TUNER GO"
+
+	while (<IN>) {
+	    $currlen = length($_);
+	    if ($prevlen == $currlen && $currlen <= 64) {
+		chop; chop; # Get rid of "TUNER GO"
+		s/^\0\0//;  # get rid of leading 00 00 if it's there
+		printf OUT "$_";
+		$found = 1;
+		last;
+	    }
+	    $prevlen = $currlen;
+	}
+    }
+    close OUT;
+    close IN;
+    if (!$found) {
+	unlink $fwfile;
+	die "Couldn't find valid register-value sequence in $sourcefile for $fwfile\n";
+    }
+    $fwfile;
+}
+
 sub cx23885 {
     my $url = "http://linuxtv.org/downloads/firmware/";
 
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index f8cd450be9aa..09e031c55887 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -458,3 +458,13 @@ Why:	Remove the old legacy 32bit machine check code. This has been
 	but the old version has been kept around for easier testing. Note this
 	doesn't impact the old P5 and WinChip machine check handlers.
 Who:	Andi Kleen <andi@firstfloor.org>
+
+----------------------------
+
+What:	lock_policy_rwsem_* and unlock_policy_rwsem_* will not be
+	exported interface anymore.
+When:	2.6.33
+Why:	cpu_policy_rwsem has a new cleaner definition making it local to
+	cpufreq core and contained inside cpufreq.c. Other dependent
+	drivers should not use it in order to safely avoid lockdep issues.
+Who:	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 229d7b7c50a3..18b9d0ca0630 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -109,27 +109,28 @@ prototypes:
 
 locking rules:
 	All may block.
-			BKL	s_lock	s_umount
-alloc_inode:		no	no	no
-destroy_inode:		no
-dirty_inode:		no				(must not sleep)
-write_inode:		no
-drop_inode:		no				!!!inode_lock!!!
-delete_inode:		no
-put_super:		yes	yes	no
-write_super:		no	yes	read
-sync_fs:		no	no	read
-freeze_fs:		?
-unfreeze_fs:		?
-statfs:			no	no	no
-remount_fs:		yes	yes	maybe		(see below)
-clear_inode:		no
-umount_begin:		yes	no	no
-show_options:		no				(vfsmount->sem)
-quota_read:		no	no	no		(see below)
-quota_write:		no	no	no		(see below)
-
-->remount_fs() will have the s_umount lock if it's already mounted.
+	None have BKL
+			s_umount
+alloc_inode:
+destroy_inode:
+dirty_inode:				(must not sleep)
+write_inode:
+drop_inode:				!!!inode_lock!!!
+delete_inode:
+put_super:		write
+write_super:		read
+sync_fs:		read
+freeze_fs:		read
+unfreeze_fs:		read
+statfs:			no
+remount_fs:		maybe		(see below)
+clear_inode:
+umount_begin:		no
+show_options:		no		(namespace_sem)
+quota_read:		no		(see below)
+quota_write:		no		(see below)
+
+->remount_fs() will have the s_umount exclusive lock if it's already mounted.
 When called from get_sb_single, it does NOT have the s_umount lock.
 ->quota_read() and ->quota_write() functions are both guaranteed to
 be the only ones operating on the quota file by the quota code (via
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 7e81e37c0b1e..b245d524d568 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -23,7 +23,8 @@ interface.
 Using sysfs
 ~~~~~~~~~~~
 
-sysfs is always compiled in. You can access it by doing:
+sysfs is always compiled in if CONFIG_SYSFS is defined. You can access
+it by doing:
 
     mount -t sysfs sysfs /sys 
 
diff --git a/Documentation/gcov.txt b/Documentation/gcov.txt
index e716aadb3a33..40ec63352760 100644
--- a/Documentation/gcov.txt
+++ b/Documentation/gcov.txt
@@ -188,13 +188,18 @@ Solution: Exclude affected source files from profiling by specifying
           GCOV_PROFILE := n or GCOV_PROFILE_basename.o := n in the
           corresponding Makefile.
 
+Problem:  Files copied from sysfs appear empty or incomplete.
+Cause:    Due to the way seq_file works, some tools such as cp or tar
+          may not correctly copy files from sysfs.
+Solution: Use 'cat' to read .gcda files and 'cp -d' to copy links.
+          Alternatively use the mechanism shown in Appendix B.
+
 
 Appendix A: gather_on_build.sh
 ==============================
 
 Sample script to gather coverage meta files on the build machine
 (see 6a):
-
 #!/bin/bash
 
 KSRC=$1
@@ -226,7 +231,7 @@ Appendix B: gather_on_test.sh
 Sample script to gather coverage data files on the test machine
 (see 6b):
 
-#!/bin/bash
+#!/bin/bash -e
 
 DEST=$1
 GCDA=/sys/kernel/debug/gcov
@@ -236,11 +241,13 @@ if [ -z "$DEST" ] ; then
   exit 1
 fi
 
-find $GCDA -name '*.gcno' -o -name '*.gcda' | tar cfz $DEST -T -
+TEMPDIR=$(mktemp -d)
+echo Collecting data..
+find $GCDA -type d -exec mkdir -p $TEMPDIR/\{\} \;
+find $GCDA -name '*.gcda' -exec sh -c 'cat < $0 > '$TEMPDIR'/$0' {} \;
+find $GCDA -name '*.gcno' -exec sh -c 'cp -d $0 '$TEMPDIR'/$0' {} \;
+tar czf $DEST -C $TEMPDIR sys
+rm -rf $TEMPDIR
 
-if [ $? -eq 0 ] ; then
-  echo "$DEST successfully created, copy to build system and unpack with:"
-  echo "  tar xfz $DEST"
-else
-  echo "Could not create file $DEST"
-fi
+echo "$DEST successfully created, copy to build system and unpack with:"
+echo "  tar xfz $DEST"
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 7bb0d934b6d8..dbea4f95fc85 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -139,6 +139,7 @@ Code	Seq#	Include File		Comments
 'm'	all	linux/synclink.h	conflict!
 'm'	00-1F	net/irda/irmod.h	conflict!
 'n'	00-7F	linux/ncp_fs.h
+'n'	80-8F	linux/nilfs2_fs.h	NILFS2
 'n'	E0-FF	video/matrox.h          matroxfb
 'o'	00-1F	fs/ocfs2/ocfs2_fs.h	OCFS2
 'o'     00-03   include/mtd/ubi-user.h  conflict! (OCFS2 and UBI overlaps)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 92e1ab8178a8..7936b801fe6a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -229,14 +229,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			to assume that this machine's pmtimer latches its value
 			and always returns good values.
 
- 	acpi.power_nocheck=	[HW,ACPI]
- 			Format: 1/0 enable/disable the check of power state.
- 			On some bogus BIOS the _PSC object/_STA object of
- 			power resource can't return the correct device power
- 			state. In such case it is unneccessary to check its
- 			power state again in power transition.
- 			1 : disable the power state check
-
 	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
 
@@ -1123,6 +1115,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			libata.dma=4	  Compact Flash DMA only 
 			Combinations also work, so libata.dma=3 enables DMA
 			for disks and CDROMs, but not CFs.
+	
+	libata.ignore_hpa=	[LIBATA] Ignore HPA limit
+			libata.ignore_hpa=0	  keep BIOS limits (default)
+			libata.ignore_hpa=1	  ignore limits, using full disk
 
 	libata.noacpi	[LIBATA] Disables use of ACPI in libata suspend/resume
 			when set.
@@ -1728,8 +1724,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.cpu_type=	Force an oprofile cpu type
 			This might be useful if you have an older oprofile
 			userland or if you want common events.
-			Format: { archperfmon }
-			archperfmon: [X86] Force use of architectural
+			Format: { arch_perfmon }
+			arch_perfmon: [X86] Force use of architectural
 				perfmon on Intel CPUs instead of the
 				CPU specific event set.
 
@@ -1863,7 +1859,7 @@ and is between 256 and 4096 characters. It is defined in the file
 				IRQ routing is enabled.
 		noacpi		[X86] Do not use ACPI for IRQ routing
 				or for PCI scanning.
-		nocrs		[X86] Don't use _CRS for PCI resource
+		use_crs		[X86] Use _CRS for PCI resource
 				allocation.
 		routeirq	Do IRQ routing for all PCI devices.
 				This is normally done in pci_enable_device(),
@@ -1923,6 +1919,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: { 0 | 1 }
 			See arch/parisc/kernel/pdc_chassis.c
 
+	percpu_alloc=	[X86] Select which percpu first chunk allocator to use.
+			Allowed values are one of "lpage", "embed" and "4k".
+			See comments in arch/x86/kernel/setup_percpu.c for
+			details on each allocator.  This parameter is primarily
+			for debugging and performance comparison.
+
 	pf.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
@@ -2475,7 +2477,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	tp720=		[HW,PS2]
 
-	trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size.
+	trace_buf_size=nn[KMG]
+			[FTRACE] will set tracing buffer size.
 
 	trix=		[HW,OSS] MediaTrix AudioTrix Pro
 			Format:
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
index 0112da3b9ab8..89068030b01b 100644
--- a/Documentation/kmemleak.txt
+++ b/Documentation/kmemleak.txt
@@ -16,13 +16,17 @@ Usage
 -----
 
 CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
-thread scans the memory every 10 minutes (by default) and prints any new
-unreferenced objects found. To trigger an intermediate scan and display
-all the possible memory leaks:
+thread scans the memory every 10 minutes (by default) and prints the
+number of new unreferenced objects found. To display the details of all
+the possible memory leaks:
 
   # mount -t debugfs nodev /sys/kernel/debug/
   # cat /sys/kernel/debug/kmemleak
 
+To trigger an intermediate memory scan:
+
+  # echo scan > /sys/kernel/debug/kmemleak
+
 Note that the orphan objects are listed in the order they were allocated
 and one object at the beginning of the list may cause other subsequent
 objects to be reported as orphan.
@@ -31,16 +35,21 @@ Memory scanning parameters can be modified at run-time by writing to the
 /sys/kernel/debug/kmemleak file. The following parameters are supported:
 
   off		- disable kmemleak (irreversible)
-  stack=on	- enable the task stacks scanning
+  stack=on	- enable the task stacks scanning (default)
   stack=off	- disable the tasks stacks scanning
-  scan=on	- start the automatic memory scanning thread
+  scan=on	- start the automatic memory scanning thread (default)
   scan=off	- stop the automatic memory scanning thread
-  scan=<secs>	- set the automatic memory scanning period in seconds (0
-		  to disable it)
+  scan=<secs>	- set the automatic memory scanning period in seconds
+		  (default 600, 0 to stop the automatic scanning)
+  scan		- trigger a memory scan
 
 Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
 the kernel command line.
 
+Memory may be allocated or freed before kmemleak is initialised and
+these actions are stored in an early log buffer. The size of this buffer
+is configured via the CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE option.
+
 Basic Algorithm
 ---------------
 
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 78e354b42f67..e2ddcdeb61b6 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -36,8 +36,6 @@ detailed description):
 	- Bluetooth enable and disable
 	- video output switching, expansion control
 	- ThinkLight on and off
-	- limited docking and undocking
-	- UltraBay eject
 	- CMOS/UCMS control
 	- LED control
 	- ACPI sounds
@@ -729,131 +727,6 @@ cannot be read or if it is unknown, thinkpad-acpi will report it as "off".
 It is impossible to know if the status returned through sysfs is valid.
 
 
-Docking / undocking -- /proc/acpi/ibm/dock
-------------------------------------------
-
-Docking and undocking (e.g. with the X4 UltraBase) requires some
-actions to be taken by the operating system to safely make or break
-the electrical connections with the dock.
-
-The docking feature of this driver generates the following ACPI events:
-
-	ibm/dock GDCK 00000003 00000001 -- eject request
-	ibm/dock GDCK 00000003 00000002 -- undocked
-	ibm/dock GDCK 00000000 00000003 -- docked
-
-NOTE: These events will only be generated if the laptop was docked
-when originally booted. This is due to the current lack of support for
-hot plugging of devices in the Linux ACPI framework. If the laptop was
-booted while not in the dock, the following message is shown in the
-logs:
-
-	Mar 17 01:42:34 aero kernel: thinkpad_acpi: dock device not present
-
-In this case, no dock-related events are generated but the dock and
-undock commands described below still work. They can be executed
-manually or triggered by Fn key combinations (see the example acpid
-configuration files included in the driver tarball package available
-on the web site).
-
-When the eject request button on the dock is pressed, the first event
-above is generated. The handler for this event should issue the
-following command:
-
-	echo undock > /proc/acpi/ibm/dock
-
-After the LED on the dock goes off, it is safe to eject the laptop.
-Note: if you pressed this key by mistake, go ahead and eject the
-laptop, then dock it back in. Otherwise, the dock may not function as
-expected.
-
-When the laptop is docked, the third event above is generated. The
-handler for this event should issue the following command to fully
-enable the dock:
-
-	echo dock > /proc/acpi/ibm/dock
-
-The contents of the /proc/acpi/ibm/dock file shows the current status
-of the dock, as provided by the ACPI framework.
-
-The docking support in this driver does not take care of enabling or
-disabling any other devices you may have attached to the dock. For
-example, a CD drive plugged into the UltraBase needs to be disabled or
-enabled separately. See the provided example acpid configuration files
-for how this can be accomplished.
-
-There is no support yet for PCI devices that may be attached to a
-docking station, e.g. in the ThinkPad Dock II. The driver currently
-does not recognize, enable or disable such devices. This means that
-the only docking stations currently supported are the X-series
-UltraBase docks and "dumb" port replicators like the Mini Dock (the
-latter don't need any ACPI support, actually).
-
-
-UltraBay eject -- /proc/acpi/ibm/bay
-------------------------------------
-
-Inserting or ejecting an UltraBay device requires some actions to be
-taken by the operating system to safely make or break the electrical
-connections with the device.
-
-This feature generates the following ACPI events:
-
-	ibm/bay MSTR 00000003 00000000 -- eject request
-	ibm/bay MSTR 00000001 00000000 -- eject lever inserted
-
-NOTE: These events will only be generated if the UltraBay was present
-when the laptop was originally booted (on the X series, the UltraBay
-is in the dock, so it may not be present if the laptop was undocked).
-This is due to the current lack of support for hot plugging of devices
-in the Linux ACPI framework. If the laptop was booted without the
-UltraBay, the following message is shown in the logs:
-
-	Mar 17 01:42:34 aero kernel: thinkpad_acpi: bay device not present
-
-In this case, no bay-related events are generated but the eject
-command described below still works. It can be executed manually or
-triggered by a hot key combination.
-
-Sliding the eject lever generates the first event shown above. The
-handler for this event should take whatever actions are necessary to
-shut down the device in the UltraBay (e.g. call idectl), then issue
-the following command:
-
-	echo eject > /proc/acpi/ibm/bay
-
-After the LED on the UltraBay goes off, it is safe to pull out the
-device.
-
-When the eject lever is inserted, the second event above is
-generated. The handler for this event should take whatever actions are
-necessary to enable the UltraBay device (e.g. call idectl).
-
-The contents of the /proc/acpi/ibm/bay file shows the current status
-of the UltraBay, as provided by the ACPI framework.
-
-EXPERIMENTAL warm eject support on the 600e/x, A22p and A3x (To use
-this feature, you need to supply the experimental=1 parameter when
-loading the module):
-
-These models do not have a button near the UltraBay device to request
-a hot eject but rather require the laptop to be put to sleep
-(suspend-to-ram) before the bay device is ejected or inserted).
-The sequence of steps to eject the device is as follows:
-
-	echo eject > /proc/acpi/ibm/bay
-	put the ThinkPad to sleep
-	remove the drive
-	resume from sleep
-	cat /proc/acpi/ibm/bay should show that the drive was removed
-
-On the A3x, both the UltraBay 2000 and UltraBay Plus devices are
-supported. Use "eject2" instead of "eject" for the second bay.
-
-Note: the UltraBay eject support on the 600e/x, A22p and A3x is
-EXPERIMENTAL and may not work as expected. USE WITH CAUTION!
-
-
 CMOS/UCMS control
 -----------------
 
@@ -920,7 +793,7 @@ The available commands are:
 	echo '<LED number> off' >/proc/acpi/ibm/led
 	echo '<LED number> blink' >/proc/acpi/ibm/led
 
-The <LED number> range is 0 to 7. The set of LEDs that can be
+The <LED number> range is 0 to 15. The set of LEDs that can be
 controlled varies from model to model. Here is the common ThinkPad
 mapping:
 
@@ -932,6 +805,11 @@ mapping:
 	5 - UltraBase battery slot
 	6 - (unknown)
 	7 - standby
+	8 - dock status 1
+	9 - dock status 2
+	10, 11 - (unknown)
+	12 - thinkvantage
+	13, 14, 15 - (unknown)
 
 All of the above can be turned on and off and can be made to blink.
 
@@ -940,10 +818,12 @@ sysfs notes:
 The ThinkPad LED sysfs interface is described in detail by the LED class
 documentation, in Documentation/leds-class.txt.
 
-The leds are named (in LED ID order, from 0 to 7):
+The LEDs are named (in LED ID order, from 0 to 12):
 "tpacpi::power", "tpacpi:orange:batt", "tpacpi:green:batt",
 "tpacpi::dock_active", "tpacpi::bay_active", "tpacpi::dock_batt",
-"tpacpi::unknown_led", "tpacpi::standby".
+"tpacpi::unknown_led", "tpacpi::standby", "tpacpi::dock_status1",
+"tpacpi::dock_status2", "tpacpi::unknown_led2", "tpacpi::unknown_led3",
+"tpacpi::thinkvantage".
 
 Due to limitations in the sysfs LED class, if the status of the LED
 indicators cannot be read due to an error, thinkpad-acpi will report it as
@@ -958,6 +838,12 @@ ThinkPad indicator LED should blink in hardware accelerated mode, use the
 "timer" trigger, and leave the delay_on and delay_off parameters set to
 zero (to request hardware acceleration autodetection).
 
+LEDs that are known not to exist in a given ThinkPad model are not
+made available through the sysfs interface.  If you have a dock and you
+notice there are LEDs listed for your ThinkPad that do not exist (and
+are not in the dock), or if you notice that there are missing LEDs,
+a report to ibm-acpi-devel@lists.sourceforge.net is appreciated.
+
 
 ACPI sounds -- /proc/acpi/ibm/beep
 ----------------------------------
@@ -1156,17 +1042,19 @@ may not be distinct.  Later Lenovo models that implement the ACPI
 display backlight brightness control methods have 16 levels, ranging
 from 0 to 15.
 
-There are two interfaces to the firmware for direct brightness control,
-EC and UCMS (or CMOS).  To select which one should be used, use the
-brightness_mode module parameter: brightness_mode=1 selects EC mode,
-brightness_mode=2 selects UCMS mode, brightness_mode=3 selects EC
-mode with NVRAM backing (so that brightness changes are remembered
-across shutdown/reboot).
+For IBM ThinkPads, there are two interfaces to the firmware for direct
+brightness control, EC and UCMS (or CMOS).  To select which one should be
+used, use the brightness_mode module parameter: brightness_mode=1 selects
+EC mode, brightness_mode=2 selects UCMS mode, brightness_mode=3 selects EC
+mode with NVRAM backing (so that brightness changes are remembered across
+shutdown/reboot).
 
 The driver tries to select which interface to use from a table of
 defaults for each ThinkPad model.  If it makes a wrong choice, please
 report this as a bug, so that we can fix it.
 
+Lenovo ThinkPads only support brightness_mode=2 (UCMS).
+
 When display backlight brightness controls are available through the
 standard ACPI interface, it is best to use it instead of this direct
 ThinkPad-specific interface.  The driver will disable its native
@@ -1254,7 +1142,7 @@ Fan control and monitoring: fan speed, fan enable/disable
 
 procfs: /proc/acpi/ibm/fan
 sysfs device attributes: (hwmon "thinkpad") fan1_input, pwm1,
-			  pwm1_enable
+			  pwm1_enable, fan2_input
 sysfs hwmon driver attributes: fan_watchdog
 
 NOTE NOTE NOTE: fan control operations are disabled by default for
@@ -1267,6 +1155,9 @@ from the hardware registers of the embedded controller.  This is known
 to work on later R, T, X and Z series ThinkPads but may show a bogus
 value on other models.
 
+Some Lenovo ThinkPads support a secondary fan.  This fan cannot be
+controlled separately, it shares the main fan control.
+
 Fan levels:
 
 Most ThinkPad fans work in "levels" at the firmware interface.  Level 0
@@ -1397,6 +1288,11 @@ hwmon device attribute fan1_input:
 	which can take up to two minutes.  May return rubbish on older
 	ThinkPads.
 
+hwmon device attribute fan2_input:
+	Fan tachometer reading, in RPM, for the secondary fan.
+	Available only on some ThinkPads.  If the secondary fan is
+	not installed, will always read 0.
+
 hwmon driver attribute fan_watchdog:
 	Fan safety watchdog timer interval, in seconds.  Minimum is
 	1 second, maximum is 120 seconds.  0 disables the watchdog.
@@ -1555,3 +1451,7 @@ Sysfs interface changelog:
 0x020300:	hotkey enable/disable support removed, attributes
 		hotkey_bios_enabled and hotkey_enable deprecated and
 		marked for removal.
+
+0x020400:	Marker for 16 LEDs support.  Also, LEDs that are known
+		to not exist in a given model are not registered with
+		the LED sysfs class anymore.
diff --git a/Documentation/leds-lp3944.txt b/Documentation/leds-lp3944.txt
new file mode 100644
index 000000000000..c6eda18b15ef
--- /dev/null
+++ b/Documentation/leds-lp3944.txt
@@ -0,0 +1,50 @@
+Kernel driver lp3944
+====================
+
+  * National Semiconductor LP3944 Fun-light Chip
+    Prefix: 'lp3944'
+    Addresses scanned: None (see the Notes section below)
+    Datasheet: Publicly available at the National Semiconductor website
+               http://www.national.com/pf/LP/LP3944.html
+
+Authors:
+        Antonio Ospite <ospite@studenti.unina.it>
+
+
+Description
+-----------
+The LP3944 is a helper chip that can drive up to 8 leds, with two programmable
+DIM modes; it could even be used as a gpio expander but this driver assumes it
+is used as a led controller.
+
+The DIM modes are used to set _blink_ patterns for leds, the pattern is
+specified supplying two parameters:
+  - period: from 0s to 1.6s
+  - duty cycle: percentage of the period the led is on, from 0 to 100
+
+Setting a led in DIM0 or DIM1 mode makes it blink according to the pattern.
+See the datasheet for details.
+
+LP3944 can be found on Motorola A910 smartphone, where it drives the rgb
+leds, the camera flash light and the lcds power.
+
+
+Notes
+-----
+The chip is used mainly in embedded contexts, so this driver expects it is
+registered using the i2c_board_info mechanism.
+
+To register the chip at address 0x60 on adapter 0, set the platform data
+according to include/linux/leds-lp3944.h, set the i2c board info:
+
+	static struct i2c_board_info __initdata a910_i2c_board_info[] = {
+		{
+			I2C_BOARD_INFO("lp3944", 0x60),
+			.platform_data = &a910_lp3944_leds,
+		},
+	};
+
+and register it in the platform init function
+
+	i2c_register_board_info(0, a910_i2c_board_info,
+			ARRAY_SIZE(a910_i2c_board_info));
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 9ebcd6ef361b..950cde6d6e58 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1,7 +1,9 @@
-/*P:100 This is the Launcher code, a simple program which lays out the
- * "physical" memory for the new Guest by mapping the kernel image and
- * the virtual devices, then opens /dev/lguest to tell the kernel
- * about the Guest and control it. :*/
+/*P:100
+ * This is the Launcher code, a simple program which lays out the "physical"
+ * memory for the new Guest by mapping the kernel image and the virtual
+ * devices, then opens /dev/lguest to tell the kernel about the Guest and
+ * control it.
+:*/
 #define _LARGEFILE64_SOURCE
 #define _GNU_SOURCE
 #include <stdio.h>
@@ -46,13 +48,15 @@
 #include "linux/virtio_rng.h"
 #include "linux/virtio_ring.h"
 #include "asm/bootparam.h"
-/*L:110 We can ignore the 39 include files we need for this program, but I do
- * want to draw attention to the use of kernel-style types.
+/*L:110
+ * We can ignore the 42 include files we need for this program, but I do want
+ * to draw attention to the use of kernel-style types.
  *
  * As Linus said, "C is a Spartan language, and so should your naming be."  I
  * like these abbreviations, so we define them here.  Note that u64 is always
  * unsigned long long, which works on all Linux systems: this means that we can
- * use %llu in printf for any u64. */
+ * use %llu in printf for any u64.
+ */
 typedef unsigned long long u64;
 typedef uint32_t u32;
 typedef uint16_t u16;
@@ -69,8 +73,10 @@ typedef uint8_t u8;
 /* This will occupy 3 pages: it must be a power of 2. */
 #define VIRTQUEUE_NUM 256
 
-/*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
- * this, and although I wouldn't recommend it, it works quite nicely here. */
+/*L:120
+ * verbose is both a global flag and a macro.  The C preprocessor allows
+ * this, and although I wouldn't recommend it, it works quite nicely here.
+ */
 static bool verbose;
 #define verbose(args...) \
 	do { if (verbose) printf(args); } while(0)
@@ -87,8 +93,7 @@ static int lguest_fd;
 static unsigned int __thread cpu_id;
 
 /* This is our list of devices. */
-struct device_list
-{
+struct device_list {
 	/* Counter to assign interrupt numbers. */
 	unsigned int next_irq;
 
@@ -100,8 +105,7 @@ struct device_list
 
 	/* A single linked list of devices. */
 	struct device *dev;
-	/* And a pointer to the last device for easy append and also for
-	 * configuration appending. */
+	/* And a pointer to the last device for easy append. */
 	struct device *lastdev;
 };
 
@@ -109,8 +113,7 @@ struct device_list
 static struct device_list devices;
 
 /* The device structure describes a single device. */
-struct device
-{
+struct device {
 	/* The linked-list pointer. */
 	struct device *next;
 
@@ -135,8 +138,7 @@ struct device
 };
 
 /* The virtqueue structure describes a queue attached to a device. */
-struct virtqueue
-{
+struct virtqueue {
 	struct virtqueue *next;
 
 	/* Which device owns me. */
@@ -168,20 +170,24 @@ static char **main_args;
 /* The original tty settings to restore on exit. */
 static struct termios orig_term;
 
-/* We have to be careful with barriers: our devices are all run in separate
+/*
+ * We have to be careful with barriers: our devices are all run in separate
  * threads and so we need to make sure that changes visible to the Guest happen
- * in precise order. */
+ * in precise order.
+ */
 #define wmb() __asm__ __volatile__("" : : : "memory")
 #define mb() __asm__ __volatile__("" : : : "memory")
 
-/* Convert an iovec element to the given type.
+/*
+ * Convert an iovec element to the given type.
  *
  * This is a fairly ugly trick: we need to know the size of the type and
  * alignment requirement to check the pointer is kosher.  It's also nice to
  * have the name of the type in case we report failure.
  *
  * Typing those three things all the time is cumbersome and error prone, so we
- * have a macro which sets them all up and passes to the real function. */
+ * have a macro which sets them all up and passes to the real function.
+ */
 #define convert(iov, type) \
 	((type *)_convert((iov), sizeof(type), __alignof__(type), #type))
 
@@ -198,8 +204,10 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 /* Wrapper for the last available index.  Makes it easier to change. */
 #define lg_last_avail(vq)	((vq)->last_avail_idx)
 
-/* The virtio configuration space is defined to be little-endian.  x86 is
- * little-endian too, but it's nice to be explicit so we have these helpers. */
+/*
+ * The virtio configuration space is defined to be little-endian.  x86 is
+ * little-endian too, but it's nice to be explicit so we have these helpers.
+ */
 #define cpu_to_le16(v16) (v16)
 #define cpu_to_le32(v32) (v32)
 #define cpu_to_le64(v64) (v64)
@@ -241,11 +249,12 @@ static u8 *get_feature_bits(struct device *dev)
 		+ dev->num_vq * sizeof(struct lguest_vqconfig);
 }
 
-/*L:100 The Launcher code itself takes us out into userspace, that scary place
- * where pointers run wild and free!  Unfortunately, like most userspace
- * programs, it's quite boring (which is why everyone likes to hack on the
- * kernel!).  Perhaps if you make up an Lguest Drinking Game at this point, it
- * will get you through this section.  Or, maybe not.
+/*L:100
+ * The Launcher code itself takes us out into userspace, that scary place where
+ * pointers run wild and free!  Unfortunately, like most userspace programs,
+ * it's quite boring (which is why everyone likes to hack on the kernel!).
+ * Perhaps if you make up an Lguest Drinking Game at this point, it will get
+ * you through this section.  Or, maybe not.
  *
  * The Launcher sets up a big chunk of memory to be the Guest's "physical"
  * memory and stores it in "guest_base".  In other words, Guest physical ==
@@ -253,7 +262,8 @@ static u8 *get_feature_bits(struct device *dev)
  *
  * This can be tough to get your head around, but usually it just means that we
  * use these trivial conversion functions when the Guest gives us it's
- * "physical" addresses: */
+ * "physical" addresses:
+ */
 static void *from_guest_phys(unsigned long addr)
 {
 	return guest_base + addr;
@@ -268,7 +278,8 @@ static unsigned long to_guest_phys(const void *addr)
  * Loading the Kernel.
  *
  * We start with couple of simple helper routines.  open_or_die() avoids
- * error-checking code cluttering the callers: */
+ * error-checking code cluttering the callers:
+ */
 static int open_or_die(const char *name, int flags)
 {
 	int fd = open(name, flags);
@@ -283,12 +294,19 @@ static void *map_zeroed_pages(unsigned int num)
 	int fd = open_or_die("/dev/zero", O_RDONLY);
 	void *addr;
 
-	/* We use a private mapping (ie. if we write to the page, it will be
-	 * copied). */
+	/*
+	 * We use a private mapping (ie. if we write to the page, it will be
+	 * copied).
+	 */
 	addr = mmap(NULL, getpagesize() * num,
 		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
 	if (addr == MAP_FAILED)
 		err(1, "Mmaping %u pages of /dev/zero", num);
+
+	/*
+	 * One neat mmap feature is that you can close the fd, and it
+	 * stays mapped.
+	 */
 	close(fd);
 
 	return addr;
@@ -305,20 +323,24 @@ static void *get_pages(unsigned int num)
 	return addr;
 }
 
-/* This routine is used to load the kernel or initrd.  It tries mmap, but if
+/*
+ * This routine is used to load the kernel or initrd.  It tries mmap, but if
  * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries),
- * it falls back to reading the memory in. */
+ * it falls back to reading the memory in.
+ */
 static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
 {
 	ssize_t r;
 
-	/* We map writable even though for some segments are marked read-only.
+	/*
+	 * We map writable even though for some segments are marked read-only.
 	 * The kernel really wants to be writable: it patches its own
 	 * instructions.
 	 *
 	 * MAP_PRIVATE means that the page won't be copied until a write is
 	 * done to it.  This allows us to share untouched memory between
-	 * Guests. */
+	 * Guests.
+	 */
 	if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
 		 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
 		return;
@@ -329,7 +351,8 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
 		err(1, "Reading offset %lu len %lu gave %zi", offset, len, r);
 }
 
-/* This routine takes an open vmlinux image, which is in ELF, and maps it into
+/*
+ * This routine takes an open vmlinux image, which is in ELF, and maps it into
  * the Guest memory.  ELF = Embedded Linking Format, which is the format used
  * by all modern binaries on Linux including the kernel.
  *
@@ -337,23 +360,28 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
  * address.  We use the physical address; the Guest will map itself to the
  * virtual address.
  *
- * We return the starting address. */
+ * We return the starting address.
+ */
 static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 {
 	Elf32_Phdr phdr[ehdr->e_phnum];
 	unsigned int i;
 
-	/* Sanity checks on the main ELF header: an x86 executable with a
-	 * reasonable number of correctly-sized program headers. */
+	/*
+	 * Sanity checks on the main ELF header: an x86 executable with a
+	 * reasonable number of correctly-sized program headers.
+	 */
 	if (ehdr->e_type != ET_EXEC
 	    || ehdr->e_machine != EM_386
 	    || ehdr->e_phentsize != sizeof(Elf32_Phdr)
 	    || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr))
 		errx(1, "Malformed elf header");
 
-	/* An ELF executable contains an ELF header and a number of "program"
+	/*
+	 * An ELF executable contains an ELF header and a number of "program"
 	 * headers which indicate which parts ("segments") of the program to
-	 * load where. */
+	 * load where.
+	 */
 
 	/* We read in all the program headers at once: */
 	if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
@@ -361,8 +389,10 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 	if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
 		err(1, "Reading program headers");
 
-	/* Try all the headers: there are usually only three.  A read-only one,
-	 * a read-write one, and a "note" section which we don't load. */
+	/*
+	 * Try all the headers: there are usually only three.  A read-only one,
+	 * a read-write one, and a "note" section which we don't load.
+	 */
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		/* If this isn't a loadable segment, we ignore it */
 		if (phdr[i].p_type != PT_LOAD)
@@ -380,13 +410,15 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 	return ehdr->e_entry;
 }
 
-/*L:150 A bzImage, unlike an ELF file, is not meant to be loaded.  You're
- * supposed to jump into it and it will unpack itself.  We used to have to
- * perform some hairy magic because the unpacking code scared me.
+/*L:150
+ * A bzImage, unlike an ELF file, is not meant to be loaded.  You're supposed
+ * to jump into it and it will unpack itself.  We used to have to perform some
+ * hairy magic because the unpacking code scared me.
  *
  * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote
  * a small patch to jump over the tricky bits in the Guest, so now we just read
- * the funky header so we know where in the file to load, and away we go! */
+ * the funky header so we know where in the file to load, and away we go!
+ */
 static unsigned long load_bzimage(int fd)
 {
 	struct boot_params boot;
@@ -394,8 +426,10 @@ static unsigned long load_bzimage(int fd)
 	/* Modern bzImages get loaded at 1M. */
 	void *p = from_guest_phys(0x100000);
 
-	/* Go back to the start of the file and read the header.  It should be
-	 * a Linux boot header (see Documentation/x86/i386/boot.txt) */
+	/*
+	 * Go back to the start of the file and read the header.  It should be
+	 * a Linux boot header (see Documentation/x86/i386/boot.txt)
+	 */
 	lseek(fd, 0, SEEK_SET);
 	read(fd, &boot, sizeof(boot));
 
@@ -414,9 +448,11 @@ static unsigned long load_bzimage(int fd)
 	return boot.hdr.code32_start;
 }
 
-/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels
+/*L:140
+ * Loading the kernel is easy when it's a "vmlinux", but most kernels
  * come wrapped up in the self-decompressing "bzImage" format.  With a little
- * work, we can load those, too. */
+ * work, we can load those, too.
+ */
 static unsigned long load_kernel(int fd)
 {
 	Elf32_Ehdr hdr;
@@ -433,24 +469,28 @@ static unsigned long load_kernel(int fd)
 	return load_bzimage(fd);
 }
 
-/* This is a trivial little helper to align pages.  Andi Kleen hated it because
+/*
+ * This is a trivial little helper to align pages.  Andi Kleen hated it because
  * it calls getpagesize() twice: "it's dumb code."
  *
  * Kernel guys get really het up about optimization, even when it's not
- * necessary.  I leave this code as a reaction against that. */
+ * necessary.  I leave this code as a reaction against that.
+ */
 static inline unsigned long page_align(unsigned long addr)
 {
 	/* Add upwards and truncate downwards. */
 	return ((addr + getpagesize()-1) & ~(getpagesize()-1));
 }
 
-/*L:180 An "initial ram disk" is a disk image loaded into memory along with
- * the kernel which the kernel can use to boot from without needing any
- * drivers.  Most distributions now use this as standard: the initrd contains
- * the code to load the appropriate driver modules for the current machine.
+/*L:180
+ * An "initial ram disk" is a disk image loaded into memory along with the
+ * kernel which the kernel can use to boot from without needing any drivers.
+ * Most distributions now use this as standard: the initrd contains the code to
+ * load the appropriate driver modules for the current machine.
  *
  * Importantly, James Morris works for RedHat, and Fedora uses initrds for its
- * kernels.  He sent me this (and tells me when I break it). */
+ * kernels.  He sent me this (and tells me when I break it).
+ */
 static unsigned long load_initrd(const char *name, unsigned long mem)
 {
 	int ifd;
@@ -462,12 +502,16 @@ static unsigned long load_initrd(const char *name, unsigned long mem)
 	if (fstat(ifd, &st) < 0)
 		err(1, "fstat() on initrd '%s'", name);
 
-	/* We map the initrd at the top of memory, but mmap wants it to be
-	 * page-aligned, so we round the size up for that. */
+	/*
+	 * We map the initrd at the top of memory, but mmap wants it to be
+	 * page-aligned, so we round the size up for that.
+	 */
 	len = page_align(st.st_size);
 	map_at(ifd, from_guest_phys(mem - len), 0, st.st_size);
-	/* Once a file is mapped, you can close the file descriptor.  It's a
-	 * little odd, but quite useful. */
+	/*
+	 * Once a file is mapped, you can close the file descriptor.  It's a
+	 * little odd, but quite useful.
+	 */
 	close(ifd);
 	verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len);
 
@@ -476,8 +520,10 @@ static unsigned long load_initrd(const char *name, unsigned long mem)
 }
 /*:*/
 
-/* Simple routine to roll all the commandline arguments together with spaces
- * between them. */
+/*
+ * Simple routine to roll all the commandline arguments together with spaces
+ * between them.
+ */
 static void concat(char *dst, char *args[])
 {
 	unsigned int i, len = 0;
@@ -494,10 +540,12 @@ static void concat(char *dst, char *args[])
 	dst[len] = '\0';
 }
 
-/*L:185 This is where we actually tell the kernel to initialize the Guest.  We
+/*L:185
+ * This is where we actually tell the kernel to initialize the Guest.  We
  * saw the arguments it expects when we looked at initialize() in lguest_user.c:
  * the base of Guest "physical" memory, the top physical page to allow and the
- * entry point for the Guest. */
+ * entry point for the Guest.
+ */
 static void tell_kernel(unsigned long start)
 {
 	unsigned long args[] = { LHREQ_INITIALIZE,
@@ -511,7 +559,7 @@ static void tell_kernel(unsigned long start)
 }
 /*:*/
 
-/*
+/*L:200
  * Device Handling.
  *
  * When the Guest gives us a buffer, it sends an array of addresses and sizes.
@@ -522,20 +570,26 @@ static void tell_kernel(unsigned long start)
 static void *_check_pointer(unsigned long addr, unsigned int size,
 			    unsigned int line)
 {
-	/* We have to separately check addr and addr+size, because size could
-	 * be huge and addr + size might wrap around. */
+	/*
+	 * We have to separately check addr and addr+size, because size could
+	 * be huge and addr + size might wrap around.
+	 */
 	if (addr >= guest_limit || addr + size >= guest_limit)
 		errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
-	/* We return a pointer for the caller's convenience, now we know it's
-	 * safe to use. */
+	/*
+	 * We return a pointer for the caller's convenience, now we know it's
+	 * safe to use.
+	 */
 	return from_guest_phys(addr);
 }
 /* A macro which transparently hands the line number to the real function. */
 #define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
 
-/* Each buffer in the virtqueues is actually a chain of descriptors.  This
+/*
+ * Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain, or vq->vring.num if we're
- * at the end. */
+ * at the end.
+ */
 static unsigned next_desc(struct vring_desc *desc,
 			  unsigned int i, unsigned int max)
 {
@@ -556,7 +610,10 @@ static unsigned next_desc(struct vring_desc *desc,
 	return next;
 }
 
-/* This actually sends the interrupt for this virtqueue */
+/*
+ * This actually sends the interrupt for this virtqueue, if we've used a
+ * buffer.
+ */
 static void trigger_irq(struct virtqueue *vq)
 {
 	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
@@ -576,12 +633,14 @@ static void trigger_irq(struct virtqueue *vq)
 		err(1, "Triggering irq %i", vq->config.irq);
 }
 
-/* This looks in the virtqueue and for the first available buffer, and converts
+/*
+ * This looks in the virtqueue for the first available buffer, and converts
  * it to an iovec for convenient access.  Since descriptors consist of some
  * number of output then some number of input descriptors, it's actually two
  * iovecs, but we pack them into one and note how many of each there were.
  *
- * This function returns the descriptor number found. */
+ * This function waits if necessary, and returns the descriptor number found.
+ */
 static unsigned wait_for_vq_desc(struct virtqueue *vq,
 				 struct iovec iov[],
 				 unsigned int *out_num, unsigned int *in_num)
@@ -590,17 +649,23 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	struct vring_desc *desc;
 	u16 last_avail = lg_last_avail(vq);
 
+	/* There's nothing available? */
 	while (last_avail == vq->vring.avail->idx) {
 		u64 event;
 
-		/* OK, tell Guest about progress up to now. */
+		/*
+		 * Since we're about to sleep, now is a good time to tell the
+		 * Guest about what we've used up to now.
+		 */
 		trigger_irq(vq);
 
 		/* OK, now we need to know about added descriptors. */
 		vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
 
-		/* They could have slipped one in as we were doing that: make
-		 * sure it's written, then check again. */
+		/*
+		 * They could have slipped one in as we were doing that: make
+		 * sure it's written, then check again.
+		 */
 		mb();
 		if (last_avail != vq->vring.avail->idx) {
 			vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
@@ -620,8 +685,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 		errx(1, "Guest moved used index from %u to %u",
 		     last_avail, vq->vring.avail->idx);
 
-	/* Grab the next descriptor number they're advertising, and increment
-	 * the index we've seen. */
+	/*
+	 * Grab the next descriptor number they're advertising, and increment
+	 * the index we've seen.
+	 */
 	head = vq->vring.avail->ring[last_avail % vq->vring.num];
 	lg_last_avail(vq)++;
 
@@ -636,8 +703,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	desc = vq->vring.desc;
 	i = head;
 
-	/* If this is an indirect entry, then this buffer contains a descriptor
-	 * table which we handle as if it's any normal descriptor chain. */
+	/*
+	 * If this is an indirect entry, then this buffer contains a descriptor
+	 * table which we handle as if it's any normal descriptor chain.
+	 */
 	if (desc[i].flags & VRING_DESC_F_INDIRECT) {
 		if (desc[i].len % sizeof(struct vring_desc))
 			errx(1, "Invalid size for indirect buffer table");
@@ -656,8 +725,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 		if (desc[i].flags & VRING_DESC_F_WRITE)
 			(*in_num)++;
 		else {
-			/* If it's an output descriptor, they're all supposed
-			 * to come before any input descriptors. */
+			/*
+			 * If it's an output descriptor, they're all supposed
+			 * to come before any input descriptors.
+			 */
 			if (*in_num)
 				errx(1, "Descriptor has out after in");
 			(*out_num)++;
@@ -671,14 +742,19 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	return head;
 }
 
-/* After we've used one of their buffers, we tell them about it.  We'll then
- * want to send them an interrupt, using trigger_irq(). */
+/*
+ * After we've used one of their buffers, we tell the Guest about it.  Sometime
+ * later we'll want to send them an interrupt using trigger_irq(); note that
+ * wait_for_vq_desc() does that for us if it has to wait.
+ */
 static void add_used(struct virtqueue *vq, unsigned int head, int len)
 {
 	struct vring_used_elem *used;
 
-	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
-	 * next entry in that used ring. */
+	/*
+	 * The virtqueue contains a ring of used buffers.  Get a pointer to the
+	 * next entry in that used ring.
+	 */
 	used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num];
 	used->id = head;
 	used->len = len;
@@ -698,9 +774,9 @@ static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
 /*
  * The Console
  *
- * We associate some data with the console for our exit hack. */
-struct console_abort
-{
+ * We associate some data with the console for our exit hack.
+ */
+struct console_abort {
 	/* How many times have they hit ^C? */
 	int count;
 	/* When did they start? */
@@ -715,30 +791,35 @@ static void console_input(struct virtqueue *vq)
 	struct console_abort *abort = vq->dev->priv;
 	struct iovec iov[vq->vring.num];
 
-	/* Make sure there's a descriptor waiting. */
+	/* Make sure there's a descriptor available. */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
 		errx(1, "Output buffers in console in queue?");
 
-	/* Read it in. */
+	/* Read into it.  This is where we usually wait. */
 	len = readv(STDIN_FILENO, iov, in_num);
 	if (len <= 0) {
 		/* Ran out of input? */
 		warnx("Failed to get console input, ignoring console.");
-		/* For simplicity, dying threads kill the whole Launcher.  So
-		 * just nap here. */
+		/*
+		 * For simplicity, dying threads kill the whole Launcher.  So
+		 * just nap here.
+		 */
 		for (;;)
 			pause();
 	}
 
+	/* Tell the Guest we used a buffer. */
 	add_used_and_trigger(vq, head, len);
 
-	/* Three ^C within one second?  Exit.
+	/*
+	 * Three ^C within one second?  Exit.
 	 *
 	 * This is such a hack, but works surprisingly well.  Each ^C has to
 	 * be in a buffer by itself, so they can't be too fast.  But we check
 	 * that we get three within about a second, so they can't be too
-	 * slow. */
+	 * slow.
+	 */
 	if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
 		abort->count = 0;
 		return;
@@ -763,15 +844,23 @@ static void console_output(struct virtqueue *vq)
 	unsigned int head, out, in;
 	struct iovec iov[vq->vring.num];
 
+	/* We usually wait in here, for the Guest to give us something. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
 		errx(1, "Input buffers in console output queue?");
+
+	/* writev can return a partial write, so we loop here. */
 	while (!iov_empty(iov, out)) {
 		int len = writev(STDOUT_FILENO, iov, out);
 		if (len <= 0)
 			err(1, "Write to stdout gave %i", len);
 		iov_consume(iov, out, len);
 	}
+
+	/*
+	 * We're finished with that buffer: if we're going to sleep,
+	 * wait_for_vq_desc() will prod the Guest with an interrupt.
+	 */
 	add_used(vq, head, 0);
 }
 
@@ -791,15 +880,30 @@ static void net_output(struct virtqueue *vq)
 	unsigned int head, out, in;
 	struct iovec iov[vq->vring.num];
 
+	/* We usually wait in here for the Guest to give us a packet. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
 		errx(1, "Input buffers in net output queue?");
+	/*
+	 * Send the whole thing through to /dev/net/tun.  It expects the exact
+	 * same format: what a coincidence!
+	 */
 	if (writev(net_info->tunfd, iov, out) < 0)
 		errx(1, "Write to tun failed?");
+
+	/*
+	 * Done with that one; wait_for_vq_desc() will send the interrupt if
+	 * all packets are processed.
+	 */
 	add_used(vq, head, 0);
 }
 
-/* Will reading from this file descriptor block? */
+/*
+ * Handling network input is a bit trickier, because I've tried to optimize it.
+ *
+ * First we have a helper routine which tells is if from this file descriptor
+ * (ie. the /dev/net/tun device) will block:
+ */
 static bool will_block(int fd)
 {
 	fd_set fdset;
@@ -809,8 +913,11 @@ static bool will_block(int fd)
 	return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
 }
 
-/* This is where we handle packets coming in from the tun device to our
- * Guest. */
+/*
+ * This handles packets coming in from the tun device to our Guest.  Like all
+ * service routines, it gets called again as soon as it returns, so you don't
+ * see a while(1) loop here.
+ */
 static void net_input(struct virtqueue *vq)
 {
 	int len;
@@ -818,21 +925,38 @@ static void net_input(struct virtqueue *vq)
 	struct iovec iov[vq->vring.num];
 	struct net_info *net_info = vq->dev->priv;
 
+	/*
+	 * Get a descriptor to write an incoming packet into.  This will also
+	 * send an interrupt if they're out of descriptors.
+	 */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (out)
 		errx(1, "Output buffers in net input queue?");
 
-	/* Deliver interrupt now, since we're about to sleep. */
+	/*
+	 * If it looks like we'll block reading from the tun device, send them
+	 * an interrupt.
+	 */
 	if (vq->pending_used && will_block(net_info->tunfd))
 		trigger_irq(vq);
 
+	/*
+	 * Read in the packet.  This is where we normally wait (when there's no
+	 * incoming network traffic).
+	 */
 	len = readv(net_info->tunfd, iov, in);
 	if (len <= 0)
 		err(1, "Failed to read from tun.");
+
+	/*
+	 * Mark that packet buffer as used, but don't interrupt here.  We want
+	 * to wait until we've done as much work as we can.
+	 */
 	add_used(vq, head, len);
 }
+/*:*/
 
-/* This is the helper to create threads. */
+/* This is the helper to create threads: run the service routine in a loop. */
 static int do_thread(void *_vq)
 {
 	struct virtqueue *vq = _vq;
@@ -842,8 +966,10 @@ static int do_thread(void *_vq)
 	return 0;
 }
 
-/* When a child dies, we kill our entire process group with SIGTERM.  This
- * also has the side effect that the shell restores the console for us! */
+/*
+ * When a child dies, we kill our entire process group with SIGTERM.  This
+ * also has the side effect that the shell restores the console for us!
+ */
 static void kill_launcher(int signal)
 {
 	kill(0, SIGTERM);
@@ -878,11 +1004,15 @@ static void reset_device(struct device *dev)
 	signal(SIGCHLD, (void *)kill_launcher);
 }
 
+/*L:216
+ * This actually creates the thread which services the virtqueue for a device.
+ */
 static void create_thread(struct virtqueue *vq)
 {
-	/* Create stack for thread and run it.  Since stack grows
-	 * upwards, we point the stack pointer to the end of this
-	 * region. */
+	/*
+	 * Create stack for thread.  Since the stack grows upwards, we point
+	 * the stack pointer to the end of this region.
+	 */
 	char *stack = malloc(32768);
 	unsigned long args[] = { LHREQ_EVENTFD,
 				 vq->config.pfn*getpagesize(), 0 };
@@ -893,17 +1023,22 @@ static void create_thread(struct virtqueue *vq)
 		err(1, "Creating eventfd");
 	args[2] = vq->eventfd;
 
-	/* Attach an eventfd to this virtqueue: it will go off
-	 * when the Guest does an LHCALL_NOTIFY for this vq. */
+	/*
+	 * Attach an eventfd to this virtqueue: it will go off when the Guest
+	 * does an LHCALL_NOTIFY for this vq.
+	 */
 	if (write(lguest_fd, &args, sizeof(args)) != 0)
 		err(1, "Attaching eventfd");
 
-	/* CLONE_VM: because it has to access the Guest memory, and
-	 * SIGCHLD so we get a signal if it dies. */
+	/*
+	 * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
+	 * we get a signal if it dies.
+	 */
 	vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
 	if (vq->thread == (pid_t)-1)
 		err(1, "Creating clone");
-	/* We close our local copy, now the child has it. */
+
+	/* We close our local copy now the child has it. */
 	close(vq->eventfd);
 }
 
@@ -955,7 +1090,10 @@ static void update_device_status(struct device *dev)
 	}
 }
 
-/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
+/*L:215
+ * This is the generic routine we call when the Guest uses LHCALL_NOTIFY.  In
+ * particular, it's used to notify us of device status changes during boot.
+ */
 static void handle_output(unsigned long addr)
 {
 	struct device *i;
@@ -964,25 +1102,42 @@ static void handle_output(unsigned long addr)
 	for (i = devices.dev; i; i = i->next) {
 		struct virtqueue *vq;
 
-		/* Notifications to device descriptors update device status. */
+		/*
+		 * Notifications to device descriptors mean they updated the
+		 * device status.
+		 */
 		if (from_guest_phys(addr) == i->desc) {
 			update_device_status(i);
 			return;
 		}
 
-		/* Devices *can* be used before status is set to DRIVER_OK. */
+		/*
+		 * Devices *can* be used before status is set to DRIVER_OK.
+		 * The original plan was that they would never do this: they
+		 * would always finish setting up their status bits before
+		 * actually touching the virtqueues.  In practice, we allowed
+		 * them to, and they do (eg. the disk probes for partition
+		 * tables as part of initialization).
+		 *
+		 * If we see this, we start the device: once it's running, we
+		 * expect the device to catch all the notifications.
+		 */
 		for (vq = i->vq; vq; vq = vq->next) {
 			if (addr != vq->config.pfn*getpagesize())
 				continue;
 			if (i->running)
 				errx(1, "Notification on running %s", i->name);
+			/* This just calls create_thread() for each virtqueue */
 			start_device(i);
 			return;
 		}
 	}
 
-	/* Early console write is done using notify on a nul-terminated string
-	 * in Guest memory. */
+	/*
+	 * Early console write is done using notify on a nul-terminated string
+	 * in Guest memory.  It's also great for hacking debugging messages
+	 * into a Guest.
+	 */
 	if (addr >= guest_limit)
 		errx(1, "Bad NOTIFY %#lx", addr);
 
@@ -998,10 +1153,12 @@ static void handle_output(unsigned long addr)
  * routines to allocate and manage them.
  */
 
-/* The layout of the device page is a "struct lguest_device_desc" followed by a
+/*
+ * The layout of the device page is a "struct lguest_device_desc" followed by a
  * number of virtqueue descriptors, then two sets of feature bits, then an
  * array of configuration bytes.  This routine returns the configuration
- * pointer. */
+ * pointer.
+ */
 static u8 *device_config(const struct device *dev)
 {
 	return (void *)(dev->desc + 1)
@@ -1009,9 +1166,11 @@ static u8 *device_config(const struct device *dev)
 		+ dev->feature_len * 2;
 }
 
-/* This routine allocates a new "struct lguest_device_desc" from descriptor
+/*
+ * This routine allocates a new "struct lguest_device_desc" from descriptor
  * table page just above the Guest's normal memory.  It returns a pointer to
- * that descriptor. */
+ * that descriptor.
+ */
 static struct lguest_device_desc *new_dev_desc(u16 type)
 {
 	struct lguest_device_desc d = { .type = type };
@@ -1032,8 +1191,10 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 	return memcpy(p, &d, sizeof(d));
 }
 
-/* Each device descriptor is followed by the description of its virtqueues.  We
- * specify how many descriptors the virtqueue is to have. */
+/*
+ * Each device descriptor is followed by the description of its virtqueues.  We
+ * specify how many descriptors the virtqueue is to have.
+ */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
 			  void (*service)(struct virtqueue *))
 {
@@ -1050,6 +1211,11 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->next = NULL;
 	vq->last_avail_idx = 0;
 	vq->dev = dev;
+
+	/*
+	 * This is the routine the service thread will run, and its Process ID
+	 * once it's running.
+	 */
 	vq->service = service;
 	vq->thread = (pid_t)-1;
 
@@ -1061,10 +1227,12 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	/* Initialize the vring. */
 	vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
 
-	/* Append virtqueue to this device's descriptor.  We use
+	/*
+	 * Append virtqueue to this device's descriptor.  We use
 	 * device_config() to get the end of the device's current virtqueues;
 	 * we check that we haven't added any config or feature information
-	 * yet, otherwise we'd be overwriting them. */
+	 * yet, otherwise we'd be overwriting them.
+	 */
 	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
 	memcpy(device_config(dev), &vq->config, sizeof(vq->config));
 	dev->num_vq++;
@@ -1072,14 +1240,18 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 
 	verbose("Virtqueue page %#lx\n", to_guest_phys(p));
 
-	/* Add to tail of list, so dev->vq is first vq, dev->vq->next is
-	 * second.  */
+	/*
+	 * Add to tail of list, so dev->vq is first vq, dev->vq->next is
+	 * second.
+	 */
 	for (i = &dev->vq; *i; i = &(*i)->next);
 	*i = vq;
 }
 
-/* The first half of the feature bitmask is for us to advertise features.  The
- * second half is for the Guest to accept features. */
+/*
+ * The first half of the feature bitmask is for us to advertise features.  The
+ * second half is for the Guest to accept features.
+ */
 static void add_feature(struct device *dev, unsigned bit)
 {
 	u8 *features = get_feature_bits(dev);
@@ -1093,9 +1265,11 @@ static void add_feature(struct device *dev, unsigned bit)
 	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
 }
 
-/* This routine sets the configuration fields for an existing device's
+/*
+ * This routine sets the configuration fields for an existing device's
  * descriptor.  It only works for the last device, but that's OK because that's
- * how we use it. */
+ * how we use it.
+ */
 static void set_config(struct device *dev, unsigned len, const void *conf)
 {
 	/* Check we haven't overflowed our single page. */
@@ -1105,12 +1279,18 @@ static void set_config(struct device *dev, unsigned len, const void *conf)
 	/* Copy in the config information, and store the length. */
 	memcpy(device_config(dev), conf, len);
 	dev->desc->config_len = len;
+
+	/* Size must fit in config_len field (8 bits)! */
+	assert(dev->desc->config_len == len);
 }
 
-/* This routine does all the creation and setup of a new device, including
- * calling new_dev_desc() to allocate the descriptor and device memory.
+/*
+ * This routine does all the creation and setup of a new device, including
+ * calling new_dev_desc() to allocate the descriptor and device memory.  We
+ * don't actually start the service threads until later.
  *
- * See what I mean about userspace being boring? */
+ * See what I mean about userspace being boring?
+ */
 static struct device *new_device(const char *name, u16 type)
 {
 	struct device *dev = malloc(sizeof(*dev));
@@ -1123,10 +1303,12 @@ static struct device *new_device(const char *name, u16 type)
 	dev->num_vq = 0;
 	dev->running = false;
 
-	/* Append to device list.  Prepending to a single-linked list is
+	/*
+	 * Append to device list.  Prepending to a single-linked list is
 	 * easier, but the user expects the devices to be arranged on the bus
 	 * in command-line order.  The first network device on the command line
-	 * is eth0, the first block device /dev/vda, etc. */
+	 * is eth0, the first block device /dev/vda, etc.
+	 */
 	if (devices.lastdev)
 		devices.lastdev->next = dev;
 	else
@@ -1136,8 +1318,10 @@ static struct device *new_device(const char *name, u16 type)
 	return dev;
 }
 
-/* Our first setup routine is the console.  It's a fairly simple device, but
- * UNIX tty handling makes it uglier than it could be. */
+/*
+ * Our first setup routine is the console.  It's a fairly simple device, but
+ * UNIX tty handling makes it uglier than it could be.
+ */
 static void setup_console(void)
 {
 	struct device *dev;
@@ -1145,8 +1329,10 @@ static void setup_console(void)
 	/* If we can save the initial standard input settings... */
 	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
 		struct termios term = orig_term;
-		/* Then we turn off echo, line buffering and ^C etc.  We want a
-		 * raw input stream to the Guest. */
+		/*
+		 * Then we turn off echo, line buffering and ^C etc: We want a
+		 * raw input stream to the Guest.
+		 */
 		term.c_lflag &= ~(ISIG|ICANON|ECHO);
 		tcsetattr(STDIN_FILENO, TCSANOW, &term);
 	}
@@ -1157,10 +1343,12 @@ static void setup_console(void)
 	dev->priv = malloc(sizeof(struct console_abort));
 	((struct console_abort *)dev->priv)->count = 0;
 
-	/* The console needs two virtqueues: the input then the output.  When
+	/*
+	 * The console needs two virtqueues: the input then the output.  When
 	 * they put something the input queue, we make sure we're listening to
 	 * stdin.  When they put something in the output queue, we write it to
-	 * stdout. */
+	 * stdout.
+	 */
 	add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
 	add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
 
@@ -1168,7 +1356,8 @@ static void setup_console(void)
 }
 /*:*/
 
-/*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
+/*M:010
+ * Inter-guest networking is an interesting area.  Simplest is to have a
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
  *
@@ -1182,7 +1371,8 @@ static void setup_console(void)
  * multiple inter-guest channels behind one interface, although it would
  * require some manner of hotplugging new virtio channels.
  *
- * Finally, we could implement a virtio network switch in the kernel. :*/
+ * Finally, we could implement a virtio network switch in the kernel.
+:*/
 
 static u32 str2ip(const char *ipaddr)
 {
@@ -1207,11 +1397,13 @@ static void str2mac(const char *macaddr, unsigned char mac[6])
 	mac[5] = m[5];
 }
 
-/* This code is "adapted" from libbridge: it attaches the Host end of the
+/*
+ * This code is "adapted" from libbridge: it attaches the Host end of the
  * network device to the bridge device specified by the command line.
  *
  * This is yet another James Morris contribution (I'm an IP-level guy, so I
- * dislike bridging), and I just try not to break it. */
+ * dislike bridging), and I just try not to break it.
+ */
 static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 {
 	int ifidx;
@@ -1231,9 +1423,11 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 		err(1, "can't add %s to bridge %s", if_name, br_name);
 }
 
-/* This sets up the Host end of the network device with an IP address, brings
+/*
+ * This sets up the Host end of the network device with an IP address, brings
  * it up so packets will flow, the copies the MAC address into the hwaddr
- * pointer. */
+ * pointer.
+ */
 static void configure_device(int fd, const char *tapif, u32 ipaddr)
 {
 	struct ifreq ifr;
@@ -1260,10 +1454,12 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 	/* Start with this zeroed.  Messy but sure. */
 	memset(&ifr, 0, sizeof(ifr));
 
-	/* We open the /dev/net/tun device and tell it we want a tap device.  A
+	/*
+	 * We open the /dev/net/tun device and tell it we want a tap device.  A
 	 * tap device is like a tun device, only somehow different.  To tell
 	 * the truth, I completely blundered my way through this code, but it
-	 * works now! */
+	 * works now!
+	 */
 	netfd = open_or_die("/dev/net/tun", O_RDWR);
 	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
 	strcpy(ifr.ifr_name, "tap%d");
@@ -1274,18 +1470,22 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 		  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
 		err(1, "Could not set features for tun device");
 
-	/* We don't need checksums calculated for packets coming in this
-	 * device: trust us! */
+	/*
+	 * We don't need checksums calculated for packets coming in this
+	 * device: trust us!
+	 */
 	ioctl(netfd, TUNSETNOCSUM, 1);
 
 	memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
 	return netfd;
 }
 
-/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
+/*L:195
+ * Our network is a Host<->Guest network.  This can either use bridging or
  * routing, but the principle is the same: it uses the "tun" device to inject
  * packets into the Host as if they came in from a normal network card.  We
- * just shunt packets between the Guest and the tun device. */
+ * just shunt packets between the Guest and the tun device.
+ */
 static void setup_tun_net(char *arg)
 {
 	struct device *dev;
@@ -1302,13 +1502,14 @@ static void setup_tun_net(char *arg)
 	dev = new_device("net", VIRTIO_ID_NET);
 	dev->priv = net_info;
 
-	/* Network devices need a receive and a send queue, just like
-	 * console. */
+	/* Network devices need a recv and a send queue, just like console. */
 	add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
 	add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
 
-	/* We need a socket to perform the magic network ioctls to bring up the
-	 * tap interface, connect to the bridge etc.  Any socket will do! */
+	/*
+	 * We need a socket to perform the magic network ioctls to bring up the
+	 * tap interface, connect to the bridge etc.  Any socket will do!
+	 */
 	ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
 	if (ipfd < 0)
 		err(1, "opening IP socket");
@@ -1362,39 +1563,31 @@ static void setup_tun_net(char *arg)
 		verbose("device %u: tun %s: %s\n",
 			devices.device_num, tapif, arg);
 }
-
-/* Our block (disk) device should be really simple: the Guest asks for a block
- * number and we read or write that position in the file.  Unfortunately, that
- * was amazingly slow: the Guest waits until the read is finished before
- * running anything else, even if it could have been doing useful work.
- *
- * We could use async I/O, except it's reputed to suck so hard that characters
- * actually go missing from your code when you try to use it.
- *
- * So we farm the I/O out to thread, and communicate with it via a pipe. */
+/*:*/
 
 /* This hangs off device->priv. */
-struct vblk_info
-{
+struct vblk_info {
 	/* The size of the file. */
 	off64_t len;
 
 	/* The file descriptor for the file. */
 	int fd;
 
-	/* IO thread listens on this file descriptor [0]. */
-	int workpipe[2];
-
-	/* IO thread writes to this file descriptor to mark it done, then
-	 * Launcher triggers interrupt to Guest. */
-	int done_fd;
 };
 
 /*L:210
  * The Disk
  *
- * Remember that the block device is handled by a separate I/O thread.  We head
- * straight into the core of that thread here:
+ * The disk only has one virtqueue, so it only has one thread.  It is really
+ * simple: the Guest asks for a block number and we read or write that position
+ * in the file.
+ *
+ * Before we serviced each virtqueue in a separate thread, that was unacceptably
+ * slow: the Guest waits until the read is finished before running anything
+ * else, even if it could have been doing useful work.
+ *
+ * We could have used async I/O, except it's reputed to suck so hard that
+ * characters actually go missing from your code when you try to use it.
  */
 static void blk_request(struct virtqueue *vq)
 {
@@ -1406,47 +1599,64 @@ static void blk_request(struct virtqueue *vq)
 	struct iovec iov[vq->vring.num];
 	off64_t off;
 
-	/* Get the next request. */
+	/*
+	 * Get the next request, where we normally wait.  It triggers the
+	 * interrupt to acknowledge previously serviced requests (if any).
+	 */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
-	/* Every block request should contain at least one output buffer
+	/*
+	 * Every block request should contain at least one output buffer
 	 * (detailing the location on disk and the type of request) and one
-	 * input buffer (to hold the result). */
+	 * input buffer (to hold the result).
+	 */
 	if (out_num == 0 || in_num == 0)
 		errx(1, "Bad virtblk cmd %u out=%u in=%u",
 		     head, out_num, in_num);
 
 	out = convert(&iov[0], struct virtio_blk_outhdr);
 	in = convert(&iov[out_num+in_num-1], u8);
+	/*
+	 * For historical reasons, block operations are expressed in 512 byte
+	 * "sectors".
+	 */
 	off = out->sector * 512;
 
-	/* The block device implements "barriers", where the Guest indicates
+	/*
+	 * The block device implements "barriers", where the Guest indicates
 	 * that it wants all previous writes to occur before this write.  We
 	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no? */
+	 * synchronize all the data in the file.  Pretty poor, no?
+	 */
 	if (out->type & VIRTIO_BLK_T_BARRIER)
 		fdatasync(vblk->fd);
 
-	/* In general the virtio block driver is allowed to try SCSI commands.
-	 * It'd be nice if we supported eject, for example, but we don't. */
+	/*
+	 * In general the virtio block driver is allowed to try SCSI commands.
+	 * It'd be nice if we supported eject, for example, but we don't.
+	 */
 	if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
 		fprintf(stderr, "Scsi commands unsupported\n");
 		*in = VIRTIO_BLK_S_UNSUPP;
 		wlen = sizeof(*in);
 	} else if (out->type & VIRTIO_BLK_T_OUT) {
-		/* Write */
-
-		/* Move to the right location in the block file.  This can fail
-		 * if they try to write past end. */
+		/*
+		 * Write
+		 *
+		 * Move to the right location in the block file.  This can fail
+		 * if they try to write past end.
+		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
 			err(1, "Bad seek to sector %llu", out->sector);
 
 		ret = writev(vblk->fd, iov+1, out_num-1);
 		verbose("WRITE to sector %llu: %i\n", out->sector, ret);
 
-		/* Grr... Now we know how long the descriptor they sent was, we
+		/*
+		 * Grr... Now we know how long the descriptor they sent was, we
 		 * make sure they didn't try to write over the end of the block
-		 * file (possibly extending it). */
+		 * file (possibly extending it).
+		 */
 		if (ret > 0 && off + ret > vblk->len) {
 			/* Trim it back to the correct length */
 			ftruncate64(vblk->fd, vblk->len);
@@ -1456,10 +1666,12 @@ static void blk_request(struct virtqueue *vq)
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {
-		/* Read */
-
-		/* Move to the right location in the block file.  This can fail
-		 * if they try to read past end. */
+		/*
+		 * Read
+		 *
+		 * Move to the right location in the block file.  This can fail
+		 * if they try to read past end.
+		 */
 		if (lseek64(vblk->fd, off, SEEK_SET) != off)
 			err(1, "Bad seek to sector %llu", out->sector);
 
@@ -1474,13 +1686,16 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 
-	/* OK, so we noted that it was pretty poor to use an fdatasync as a
+	/*
+	 * OK, so we noted that it was pretty poor to use an fdatasync as a
 	 * barrier.  But Christoph Hellwig points out that we need a sync
 	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are: */
+	 * or the back."  And Jens Axboe confirmed it, so here we are:
+	 */
 	if (out->type & VIRTIO_BLK_T_BARRIER)
 		fdatasync(vblk->fd);
 
+	/* Finished that request. */
 	add_used(vq, head, wlen);
 }
 
@@ -1491,7 +1706,7 @@ static void setup_block_file(const char *filename)
 	struct vblk_info *vblk;
 	struct virtio_blk_config conf;
 
-	/* The device responds to return from I/O thread. */
+	/* Creat the device. */
 	dev = new_device("block", VIRTIO_ID_BLOCK);
 
 	/* The device has one virtqueue, where the Guest places requests. */
@@ -1510,27 +1725,32 @@ static void setup_block_file(const char *filename)
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);
 
-	/* Tell Guest not to put in too many descriptors at once: two are used
-	 * for the in and out elements. */
+	/*
+	 * Tell Guest not to put in too many descriptors at once: two are used
+	 * for the in and out elements.
+	 */
 	add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
 	conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
 
-	set_config(dev, sizeof(conf), &conf);
+	/* Don't try to put whole struct: we have 8 bit limit. */
+	set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf);
 
 	verbose("device %u: virtblock %llu sectors\n",
 		++devices.device_num, le64_to_cpu(conf.capacity));
 }
 
-struct rng_info {
-	int rfd;
-};
-
-/* Our random number generator device reads from /dev/random into the Guest's
+/*L:211
+ * Our random number generator device reads from /dev/random into the Guest's
  * input buffers.  The usual case is that the Guest doesn't want random numbers
  * and so has no buffers although /dev/random is still readable, whereas
  * console is the reverse.
  *
- * The same logic applies, however. */
+ * The same logic applies, however.
+ */
+struct rng_info {
+	int rfd;
+};
+
 static void rng_input(struct virtqueue *vq)
 {
 	int len;
@@ -1543,9 +1763,10 @@ static void rng_input(struct virtqueue *vq)
 	if (out_num)
 		errx(1, "Output buffers in rng?");
 
-	/* This is why we convert to iovecs: the readv() call uses them, and so
-	 * it reads straight into the Guest's buffer.  We loop to make sure we
-	 * fill it. */
+	/*
+	 * Just like the console write, we loop to cover the whole iovec.
+	 * In this case, short reads actually happen quite a bit.
+	 */
 	while (!iov_empty(iov, in_num)) {
 		len = readv(rng_info->rfd, iov, in_num);
 		if (len <= 0)
@@ -1558,15 +1779,18 @@ static void rng_input(struct virtqueue *vq)
 	add_used(vq, head, totlen);
 }
 
-/* And this creates a "hardware" random number device for the Guest. */
+/*L:199
+ * This creates a "hardware" random number device for the Guest.
+ */
 static void setup_rng(void)
 {
 	struct device *dev;
 	struct rng_info *rng_info = malloc(sizeof(*rng_info));
 
+	/* Our device's privat info simply contains the /dev/random fd. */
 	rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
 
-	/* The device responds to return from I/O thread. */
+	/* Create the new device. */
 	dev = new_device("rng", VIRTIO_ID_RNG);
 	dev->priv = rng_info;
 
@@ -1582,8 +1806,10 @@ static void __attribute__((noreturn)) restart_guest(void)
 {
 	unsigned int i;
 
-	/* Since we don't track all open fds, we simply close everything beyond
-	 * stderr. */
+	/*
+	 * Since we don't track all open fds, we simply close everything beyond
+	 * stderr.
+	 */
 	for (i = 3; i < FD_SETSIZE; i++)
 		close(i);
 
@@ -1594,8 +1820,10 @@ static void __attribute__((noreturn)) restart_guest(void)
 	err(1, "Could not exec %s", main_args[0]);
 }
 
-/*L:220 Finally we reach the core of the Launcher which runs the Guest, serves
- * its input and output, and finally, lays it to rest. */
+/*L:220
+ * Finally we reach the core of the Launcher which runs the Guest, serves
+ * its input and output, and finally, lays it to rest.
+ */
 static void __attribute__((noreturn)) run_guest(void)
 {
 	for (;;) {
@@ -1630,7 +1858,7 @@ static void __attribute__((noreturn)) run_guest(void)
  *
  * Are you ready?  Take a deep breath and join me in the core of the Host, in
  * "make Host".
- :*/
+:*/
 
 static struct option opts[] = {
 	{ "verbose", 0, NULL, 'v' },
@@ -1651,8 +1879,7 @@ static void usage(void)
 /*L:105 The main routine is where the real work begins: */
 int main(int argc, char *argv[])
 {
-	/* Memory, top-level pagetable, code startpoint and size of the
-	 * (optional) initrd. */
+	/* Memory, code startpoint and size of the (optional) initrd. */
 	unsigned long mem = 0, start, initrd_size = 0;
 	/* Two temporaries. */
 	int i, c;
@@ -1664,24 +1891,32 @@ int main(int argc, char *argv[])
 	/* Save the args: we "reboot" by execing ourselves again. */
 	main_args = argv;
 
-	/* First we initialize the device list.  We keep a pointer to the last
+	/*
+	 * First we initialize the device list.  We keep a pointer to the last
 	 * device, and the next interrupt number to use for devices (1:
-	 * remember that 0 is used by the timer). */
+	 * remember that 0 is used by the timer).
+	 */
 	devices.lastdev = NULL;
 	devices.next_irq = 1;
 
+	/* We're CPU 0.  In fact, that's the only CPU possible right now. */
 	cpu_id = 0;
-	/* We need to know how much memory so we can set up the device
+
+	/*
+	 * We need to know how much memory so we can set up the device
 	 * descriptor and memory pages for the devices as we parse the command
 	 * line.  So we quickly look through the arguments to find the amount
-	 * of memory now. */
+	 * of memory now.
+	 */
 	for (i = 1; i < argc; i++) {
 		if (argv[i][0] != '-') {
 			mem = atoi(argv[i]) * 1024 * 1024;
-			/* We start by mapping anonymous pages over all of
+			/*
+			 * We start by mapping anonymous pages over all of
 			 * guest-physical memory range.  This fills it with 0,
 			 * and ensures that the Guest won't be killed when it
-			 * tries to access it. */
+			 * tries to access it.
+			 */
 			guest_base = map_zeroed_pages(mem / getpagesize()
 						      + DEVICE_PAGES);
 			guest_limit = mem;
@@ -1714,8 +1949,10 @@ int main(int argc, char *argv[])
 			usage();
 		}
 	}
-	/* After the other arguments we expect memory and kernel image name,
-	 * followed by command line arguments for the kernel. */
+	/*
+	 * After the other arguments we expect memory and kernel image name,
+	 * followed by command line arguments for the kernel.
+	 */
 	if (optind + 2 > argc)
 		usage();
 
@@ -1733,20 +1970,26 @@ int main(int argc, char *argv[])
 	/* Map the initrd image if requested (at top of physical memory) */
 	if (initrd_name) {
 		initrd_size = load_initrd(initrd_name, mem);
-		/* These are the location in the Linux boot header where the
-		 * start and size of the initrd are expected to be found. */
+		/*
+		 * These are the location in the Linux boot header where the
+		 * start and size of the initrd are expected to be found.
+		 */
 		boot->hdr.ramdisk_image = mem - initrd_size;
 		boot->hdr.ramdisk_size = initrd_size;
 		/* The bootloader type 0xFF means "unknown"; that's OK. */
 		boot->hdr.type_of_loader = 0xFF;
 	}
 
-	/* The Linux boot header contains an "E820" memory map: ours is a
-	 * simple, single region. */
+	/*
+	 * The Linux boot header contains an "E820" memory map: ours is a
+	 * simple, single region.
+	 */
 	boot->e820_entries = 1;
 	boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
-	/* The boot header contains a command line pointer: we put the command
-	 * line after the boot header. */
+	/*
+	 * The boot header contains a command line pointer: we put the command
+	 * line after the boot header.
+	 */
 	boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1);
 	/* We use a simple helper to copy the arguments separated by spaces. */
 	concat((char *)(boot + 1), argv+optind+2);
@@ -1760,11 +2003,13 @@ int main(int argc, char *argv[])
 	/* Tell the entry path not to try to reload segment registers. */
 	boot->hdr.loadflags |= KEEP_SEGMENTS;
 
-	/* We tell the kernel to initialize the Guest: this returns the open
-	 * /dev/lguest file descriptor. */
+	/*
+	 * We tell the kernel to initialize the Guest: this returns the open
+	 * /dev/lguest file descriptor.
+	 */
 	tell_kernel(start);
 
-	/* Ensure that we terminate if a child dies. */
+	/* Ensure that we terminate if a device-servicing child dies. */
 	signal(SIGCHLD, kill_launcher);
 
 	/* If we exit via err(), this kills all the threads, restores tty. */
diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt
index e20d913d5914..abf768c681e2 100644
--- a/Documentation/lockdep-design.txt
+++ b/Documentation/lockdep-design.txt
@@ -30,9 +30,9 @@ State
 The validator tracks lock-class usage history into 4n + 1 separate state bits:
 
 - 'ever held in STATE context'
-- 'ever head as readlock in STATE context'
-- 'ever head with STATE enabled'
-- 'ever head as readlock with STATE enabled'
+- 'ever held as readlock in STATE context'
+- 'ever held with STATE enabled'
+- 'ever held as readlock with STATE enabled'
 
 Where STATE can be either one of (kernel/lockdep_states.h)
  - hardirq
diff --git a/Documentation/networking/6pack.txt b/Documentation/networking/6pack.txt
index d0777a1200e1..8f339428fdf4 100644
--- a/Documentation/networking/6pack.txt
+++ b/Documentation/networking/6pack.txt
@@ -1,7 +1,7 @@
 This is the 6pack-mini-HOWTO, written by
 
 Andreas Könsgen DG3KQ
-Internet: ajk@iehk.rwth-aachen.de
+Internet: ajk@comnets.uni-bremen.de
 AMPR-net: dg3kq@db0pra.ampr.org
 AX.25:    dg3kq@db0ach.#nrw.deu.eu
 
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 8d999d862d0e..79f533f38c61 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -1238,1122 +1238,7 @@ descriptions for the SOC devices for which new nodes have been
 defined; this list will expand as more and more SOC-containing
 platforms are moved over to use the flattened-device-tree model.
 
-   a) 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";
-	};
-
-
-   b) 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>;
-		interrupt-controller;
-		#address-cells = <0>;
-		reg = <40000 40000>;
-		compatible = "chrp,open-pic";
-		device_type = "open-pic";
-	};
-
-    c) 4xx/Axon EMAC ethernet nodes
-
-    The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
-    the Axon bridge.  To operate this needs to interact with a ths
-    special McMAL DMA controller, and sometimes an RGMII or ZMII
-    interface.  In addition to the nodes and properties described
-    below, the node for the OPB bus on which the EMAC sits must have a
-    correct clock-frequency property.
-
-      i) The EMAC node itself
-
-    Required properties:
-    - device_type       : "network"
-
-    - compatible        : compatible list, contains 2 entries, first is
-			  "ibm,emac-CHIP" where CHIP is the host ASIC (440gx,
-			  405gp, Axon) and second is either "ibm,emac" or
-			  "ibm,emac4".  For Axon, thus, we have: "ibm,emac-axon",
-			  "ibm,emac4"
-    - interrupts        : <interrupt mapping for EMAC IRQ and WOL IRQ>
-    - interrupt-parent  : optional, if needed for interrupt mapping
-    - reg               : <registers mapping>
-    - local-mac-address : 6 bytes, MAC address
-    - mal-device        : phandle of the associated McMAL node
-    - mal-tx-channel    : 1 cell, index of the tx channel on McMAL associated
-			  with this EMAC
-    - mal-rx-channel    : 1 cell, index of the rx channel on McMAL associated
-			  with this EMAC
-    - cell-index        : 1 cell, hardware index of the EMAC cell on a given
-			  ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on
-			  each Axon chip)
-    - max-frame-size    : 1 cell, maximum frame size supported in bytes
-    - rx-fifo-size      : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec
-			  operations.
-			  For Axon, 2048
-    - tx-fifo-size      : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec
-			  operations.
-			  For Axon, 2048.
-    - fifo-entry-size   : 1 cell, size of a fifo entry (used to calculate
-			  thresholds).
-			  For Axon, 0x00000010
-    - mal-burst-size    : 1 cell, MAL burst size (used to calculate thresholds)
-			  in bytes.
-			  For Axon, 0x00000100 (I think ...)
-    - phy-mode          : string, mode of operations of the PHY interface.
-			  Supported values are: "mii", "rmii", "smii", "rgmii",
-			  "tbi", "gmii", rtbi", "sgmii".
-			  For Axon on CAB, it is "rgmii"
-    - mdio-device       : 1 cell, required iff using shared MDIO registers
-			  (440EP).  phandle of the EMAC to use to drive the
-			  MDIO lines for the PHY used by this EMAC.
-    - zmii-device       : 1 cell, required iff connected to a ZMII.  phandle of
-			  the ZMII device node
-    - zmii-channel      : 1 cell, required iff connected to a ZMII.  Which ZMII
-			  channel or 0xffffffff if ZMII is only used for MDIO.
-    - rgmii-device      : 1 cell, required iff connected to an RGMII. phandle
-			  of the RGMII device node.
-			  For Axon: phandle of plb5/plb4/opb/rgmii
-    - rgmii-channel     : 1 cell, required iff connected to an RGMII.  Which
-			  RGMII channel is used by this EMAC.
-			  Fox Axon: present, whatever value is appropriate for each
-			  EMAC, that is the content of the current (bogus) "phy-port"
-			  property.
-
-    Optional properties:
-    - phy-address       : 1 cell, optional, MDIO address of the PHY. If absent,
-			  a search is performed.
-    - phy-map           : 1 cell, optional, bitmap of addresses to probe the PHY
-			  for, used if phy-address is absent. bit 0x00000001 is
-			  MDIO address 0.
-			  For Axon it can be absent, though my current driver
-			  doesn't handle phy-address yet so for now, keep
-			  0x00ffffff in it.
-    - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
-			  operations (if absent the value is the same as
-			  rx-fifo-size).  For Axon, either absent or 2048.
-    - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec
-			  operations (if absent the value is the same as
-			  tx-fifo-size). For Axon, either absent or 2048.
-    - tah-device        : 1 cell, optional. If connected to a TAH engine for
-			  offload, phandle of the TAH device node.
-    - tah-channel       : 1 cell, optional. If appropriate, channel used on the
-			  TAH engine.
-
-    Example:
-
-	EMAC0: ethernet@40000800 {
-		device_type = "network";
-		compatible = "ibm,emac-440gp", "ibm,emac";
-		interrupt-parent = <&UIC1>;
-		interrupts = <1c 4 1d 4>;
-		reg = <40000800 70>;
-		local-mac-address = [00 04 AC E3 1B 1E];
-		mal-device = <&MAL0>;
-		mal-tx-channel = <0 1>;
-		mal-rx-channel = <0>;
-		cell-index = <0>;
-		max-frame-size = <5dc>;
-		rx-fifo-size = <1000>;
-		tx-fifo-size = <800>;
-		phy-mode = "rmii";
-		phy-map = <00000001>;
-		zmii-device = <&ZMII0>;
-		zmii-channel = <0>;
-	};
-
-      ii) McMAL node
-
-    Required properties:
-    - device_type        : "dma-controller"
-    - compatible         : compatible list, containing 2 entries, first is
-			   "ibm,mcmal-CHIP" where CHIP is the host ASIC (like
-			   emac) and the second is either "ibm,mcmal" or
-			   "ibm,mcmal2".
-			   For Axon, "ibm,mcmal-axon","ibm,mcmal2"
-    - interrupts         : <interrupt mapping for the MAL interrupts sources:
-                           5 sources: tx_eob, rx_eob, serr, txde, rxde>.
-                           For Axon: This is _different_ from the current
-			   firmware.  We use the "delayed" interrupts for txeob
-			   and rxeob. Thus we end up with mapping those 5 MPIC
-			   interrupts, all level positive sensitive: 10, 11, 32,
-			   33, 34 (in decimal)
-    - dcr-reg            : < DCR registers range >
-    - dcr-parent         : if needed for dcr-reg
-    - num-tx-chans       : 1 cell, number of Tx channels
-    - num-rx-chans       : 1 cell, number of Rx channels
-
-      iii) ZMII node
-
-    Required properties:
-    - compatible         : compatible list, containing 2 entries, first is
-			   "ibm,zmii-CHIP" where CHIP is the host ASIC (like
-			   EMAC) and the second is "ibm,zmii".
-			   For Axon, there is no ZMII node.
-    - reg                : <registers mapping>
-
-      iv) RGMII node
-
-    Required properties:
-    - compatible         : compatible list, containing 2 entries, first is
-			   "ibm,rgmii-CHIP" where CHIP is the host ASIC (like
-			   EMAC) and the second is "ibm,rgmii".
-                           For Axon, "ibm,rgmii-axon","ibm,rgmii"
-    - reg                : <registers mapping>
-    - revision           : as provided by the RGMII new version register if
-			   available.
-			   For Axon: 0x0000012a
-
-   d) Xilinx IP cores
-
-   The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
-   in Xilinx Spartan and Virtex FPGAs.  The devices cover the whole range
-   of standard device types (network, serial, etc.) and miscellaneous
-   devices (gpio, LCD, spi, etc).  Also, since these devices are
-   implemented within the fpga fabric every instance of the device can be
-   synthesised with different options that change the behaviour.
-
-   Each IP-core has a set of parameters which the FPGA designer can use to
-   control how the core is synthesized.  Historically, the EDK tool would
-   extract the device parameters relevant to device drivers and copy them
-   into an 'xparameters.h' in the form of #define symbols.  This tells the
-   device drivers how the IP cores are configured, but it requres the kernel
-   to be recompiled every time the FPGA bitstream is resynthesized.
-
-   The new approach is to export the parameters into the device tree and
-   generate a new device tree each time the FPGA bitstream changes.  The
-   parameters which used to be exported as #defines will now become
-   properties of the device node.  In general, device nodes for IP-cores
-   will take the following form:
-
-	(name): (generic-name)@(base-address) {
-		compatible = "xlnx,(ip-core-name)-(HW_VER)"
-			     [, (list of compatible devices), ...];
-		reg = <(baseaddr) (size)>;
-		interrupt-parent = <&interrupt-controller-phandle>;
-		interrupts = < ... >;
-		xlnx,(parameter1) = "(string-value)";
-		xlnx,(parameter2) = <(int-value)>;
-	};
-
-	(generic-name):   an open firmware-style name that describes the
-			generic class of device.  Preferably, this is one word, such
-			as 'serial' or 'ethernet'.
-	(ip-core-name):	the name of the ip block (given after the BEGIN
-			directive in system.mhs).  Should be in lowercase
-			and all underscores '_' converted to dashes '-'.
-	(name):		is derived from the "PARAMETER INSTANCE" value.
-	(parameter#):	C_* parameters from system.mhs.  The C_ prefix is
-			dropped from the parameter name, the name is converted
-			to lowercase and all underscore '_' characters are
-			converted to dashes '-'.
-	(baseaddr):	the baseaddr parameter value (often named C_BASEADDR).
-	(HW_VER):	from the HW_VER parameter.
-	(size):		the address range size (often C_HIGHADDR - C_BASEADDR + 1).
-
-   Typically, the compatible list will include the exact IP core version
-   followed by an older IP core version which implements the same
-   interface or any other device with the same interface.
-
-   'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
-
-   For example, the following block from system.mhs:
-
-	BEGIN opb_uartlite
-		PARAMETER INSTANCE = opb_uartlite_0
-		PARAMETER HW_VER = 1.00.b
-		PARAMETER C_BAUDRATE = 115200
-		PARAMETER C_DATA_BITS = 8
-		PARAMETER C_ODD_PARITY = 0
-		PARAMETER C_USE_PARITY = 0
-		PARAMETER C_CLK_FREQ = 50000000
-		PARAMETER C_BASEADDR = 0xEC100000
-		PARAMETER C_HIGHADDR = 0xEC10FFFF
-		BUS_INTERFACE SOPB = opb_7
-		PORT OPB_Clk = CLK_50MHz
-		PORT Interrupt = opb_uartlite_0_Interrupt
-		PORT RX = opb_uartlite_0_RX
-		PORT TX = opb_uartlite_0_TX
-		PORT OPB_Rst = sys_bus_reset_0
-	END
-
-   becomes the following device tree node:
-
-	opb_uartlite_0: serial@ec100000 {
-		device_type = "serial";
-		compatible = "xlnx,opb-uartlite-1.00.b";
-		reg = <ec100000 10000>;
-		interrupt-parent = <&opb_intc_0>;
-		interrupts = <1 0>; // got this from the opb_intc parameters
-		current-speed = <d#115200>;	// standard serial device prop
-		clock-frequency = <d#50000000>;	// standard serial device prop
-		xlnx,data-bits = <8>;
-		xlnx,odd-parity = <0>;
-		xlnx,use-parity = <0>;
-	};
-
-   Some IP cores actually implement 2 or more logical devices.  In
-   this case, the device should still describe the whole IP core with
-   a single node and add a child node for each logical device.  The
-   ranges property can be used to translate from parent IP-core to the
-   registers of each device.  In addition, the parent node should be
-   compatible with the bus type 'xlnx,compound', and should contain
-   #address-cells and #size-cells, as with any other bus.  (Note: this
-   makes the assumption that both logical devices have the same bus
-   binding.  If this is not true, then separate nodes should be used
-   for each logical device).  The 'cell-index' property can be used to
-   enumerate logical devices within an IP core.  For example, the
-   following is the system.mhs entry for the dual ps2 controller found
-   on the ml403 reference design.
-
-	BEGIN opb_ps2_dual_ref
-		PARAMETER INSTANCE = opb_ps2_dual_ref_0
-		PARAMETER HW_VER = 1.00.a
-		PARAMETER C_BASEADDR = 0xA9000000
-		PARAMETER C_HIGHADDR = 0xA9001FFF
-		BUS_INTERFACE SOPB = opb_v20_0
-		PORT Sys_Intr1 = ps2_1_intr
-		PORT Sys_Intr2 = ps2_2_intr
-		PORT Clkin1 = ps2_clk_rx_1
-		PORT Clkin2 = ps2_clk_rx_2
-		PORT Clkpd1 = ps2_clk_tx_1
-		PORT Clkpd2 = ps2_clk_tx_2
-		PORT Rx1 = ps2_d_rx_1
-		PORT Rx2 = ps2_d_rx_2
-		PORT Txpd1 = ps2_d_tx_1
-		PORT Txpd2 = ps2_d_tx_2
-	END
-
-   It would result in the following device tree nodes:
-
-	opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "xlnx,compound";
-		ranges = <0 a9000000 2000>;
-		// If this device had extra parameters, then they would
-		// go here.
-		ps2@0 {
-			compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
-			reg = <0 40>;
-			interrupt-parent = <&opb_intc_0>;
-			interrupts = <3 0>;
-			cell-index = <0>;
-		};
-		ps2@1000 {
-			compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
-			reg = <1000 40>;
-			interrupt-parent = <&opb_intc_0>;
-			interrupts = <3 0>;
-			cell-index = <0>;
-		};
-	};
-
-   Also, the system.mhs file defines bus attachments from the processor
-   to the devices.  The device tree structure should reflect the bus
-   attachments.  Again an example; this system.mhs fragment:
-
-	BEGIN ppc405_virtex4
-		PARAMETER INSTANCE = ppc405_0
-		PARAMETER HW_VER = 1.01.a
-		BUS_INTERFACE DPLB = plb_v34_0
-		BUS_INTERFACE IPLB = plb_v34_0
-	END
-
-	BEGIN opb_intc
-		PARAMETER INSTANCE = opb_intc_0
-		PARAMETER HW_VER = 1.00.c
-		PARAMETER C_BASEADDR = 0xD1000FC0
-		PARAMETER C_HIGHADDR = 0xD1000FDF
-		BUS_INTERFACE SOPB = opb_v20_0
-	END
-
-	BEGIN opb_uart16550
-		PARAMETER INSTANCE = opb_uart16550_0
-		PARAMETER HW_VER = 1.00.d
-		PARAMETER C_BASEADDR = 0xa0000000
-		PARAMETER C_HIGHADDR = 0xa0001FFF
-		BUS_INTERFACE SOPB = opb_v20_0
-	END
-
-	BEGIN plb_v34
-		PARAMETER INSTANCE = plb_v34_0
-		PARAMETER HW_VER = 1.02.a
-	END
-
-	BEGIN plb_bram_if_cntlr
-		PARAMETER INSTANCE = plb_bram_if_cntlr_0
-		PARAMETER HW_VER = 1.00.b
-		PARAMETER C_BASEADDR = 0xFFFF0000
-		PARAMETER C_HIGHADDR = 0xFFFFFFFF
-		BUS_INTERFACE SPLB = plb_v34_0
-	END
-
-	BEGIN plb2opb_bridge
-		PARAMETER INSTANCE = plb2opb_bridge_0
-		PARAMETER HW_VER = 1.01.a
-		PARAMETER C_RNG0_BASEADDR = 0x20000000
-		PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF
-		PARAMETER C_RNG1_BASEADDR = 0x60000000
-		PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF
-		PARAMETER C_RNG2_BASEADDR = 0x80000000
-		PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF
-		PARAMETER C_RNG3_BASEADDR = 0xC0000000
-		PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF
-		BUS_INTERFACE SPLB = plb_v34_0
-		BUS_INTERFACE MOPB = opb_v20_0
-	END
-
-   Gives this device tree (some properties removed for clarity):
-
-	plb@0 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "xlnx,plb-v34-1.02.a";
-		device_type = "ibm,plb";
-		ranges; // 1:1 translation
-
-		plb_bram_if_cntrl_0: bram@ffff0000 {
-			reg = <ffff0000 10000>;
-		}
-
-		opb@20000000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <20000000 20000000 20000000
-				  60000000 60000000 20000000
-				  80000000 80000000 40000000
-				  c0000000 c0000000 20000000>;
-
-			opb_uart16550_0: serial@a0000000 {
-				reg = <a00000000 2000>;
-			};
-
-			opb_intc_0: interrupt-controller@d1000fc0 {
-				reg = <d1000fc0 20>;
-			};
-		};
-	};
-
-   That covers the general approach to binding xilinx IP cores into the
-   device tree.  The following are bindings for specific devices:
-
-      i) Xilinx ML300 Framebuffer
-
-      Simple framebuffer device from the ML300 reference design (also on the
-      ML403 reference design as well as others).
-
-      Optional properties:
-       - resolution = <xres yres> : pixel resolution of framebuffer.  Some
-                                    implementations use a different resolution.
-                                    Default is <d#640 d#480>
-       - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory.
-                                           Default is <d#1024 d#480>.
-       - rotate-display (empty) : rotate display 180 degrees.
-
-      ii) Xilinx SystemACE
-
-      The Xilinx SystemACE device is used to program FPGAs from an FPGA
-      bitstream stored on a CF card.  It can also be used as a generic CF
-      interface device.
-
-      Optional properties:
-       - 8-bit (empty) : Set this property for SystemACE in 8 bit mode
-
-      iii) Xilinx EMAC and Xilinx TEMAC
-
-      Xilinx Ethernet devices.  In addition to general xilinx properties
-      listed above, nodes for these devices should include a phy-handle
-      property, and may include other common network device properties
-      like local-mac-address.
-
-      iv) Xilinx Uartlite
-
-      Xilinx uartlite devices are simple fixed speed serial ports.
-
-      Required properties:
-       - current-speed : Baud rate of uartlite
-
-      v) Xilinx hwicap
-
-		Xilinx hwicap devices provide access to the configuration logic
-		of the FPGA through the Internal Configuration Access Port
-		(ICAP).  The ICAP enables partial reconfiguration of the FPGA,
-		readback of the configuration information, and some control over
-		'warm boots' of the FPGA fabric.
-
-		Required properties:
-		- xlnx,family : The family of the FPGA, necessary since the
-                      capabilities of the underlying ICAP hardware
-                      differ between different families.  May be
-                      'virtex2p', 'virtex4', or 'virtex5'.
-
-      vi) Xilinx Uart 16550
-
-      Xilinx UART 16550 devices are very similar to the NS16550 but with
-      different register spacing and an offset from the base address.
-
-      Required properties:
-       - clock-frequency : Frequency of the clock input
-       - reg-offset : A value of 3 is required
-       - reg-shift : A value of 2 is required
-
-    e) USB EHCI controllers
-
-    Required properties:
-      - compatible : should be "usb-ehci".
-      - reg : should contain at least address and length of the standard EHCI
-        register set for the device. Optional platform-dependent registers
-        (debug-port or other) can be also specified here, but only after
-        definition of standard EHCI registers.
-      - interrupts : one EHCI interrupt should be described here.
-    If device registers are implemented in big endian mode, the device
-    node should have "big-endian-regs" property.
-    If controller implementation operates with big endian descriptors,
-    "big-endian-desc" property should be specified.
-    If both big endian registers and descriptors are used by the controller
-    implementation, "big-endian" property can be specified instead of having
-    both "big-endian-regs" and "big-endian-desc".
-
-     Example (Sequoia 440EPx):
-	    ehci@e0000300 {
-		   compatible = "ibm,usb-ehci-440epx", "usb-ehci";
-		   interrupt-parent = <&UIC0>;
-		   interrupts = <1a 4>;
-		   reg = <0 e0000300 90 0 e0000390 70>;
-		   big-endian;
-	   };
-
-   f) MDIO on GPIOs
-
-   Currently defined compatibles:
-   - virtual,gpio-mdio
-
-   MDC and MDIO lines connected to GPIO controllers are listed in the
-   gpios property as described in section VIII.1 in the following order:
-
-   MDC, MDIO.
-
-   Example:
-
-	mdio {
-		compatible = "virtual,mdio-gpio";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		gpios = <&qe_pio_a 11
-			 &qe_pio_c 6>;
-	};
-
-    g) SPI (Serial Peripheral Interface) busses
-
-    SPI busses can be described with a node for the SPI master device
-    and a set of child nodes for each SPI slave on the bus.  For this
-    discussion, it is assumed that the system's SPI controller is in
-    SPI master mode.  This binding does not describe SPI controllers
-    in slave mode.
-
-    The SPI master node requires the following properties:
-    - #address-cells  - number of cells required to define a chip select
-			address on the SPI bus.
-    - #size-cells     - should be zero.
-    - compatible      - name of SPI bus controller following generic names
-			recommended practice.
-    No other properties are required in the SPI bus node.  It is assumed
-    that a driver for an SPI bus device will understand that it is an SPI bus.
-    However, the binding does not attempt to define the specific method for
-    assigning chip select numbers.  Since SPI chip select configuration is
-    flexible and non-standardized, it is left out of this binding with the
-    assumption that board specific platform code will be used to manage
-    chip selects.  Individual drivers can define additional properties to
-    support describing the chip select layout.
-
-    SPI slave nodes must be children of the SPI master node and can
-    contain the following properties.
-    - reg             - (required) chip select address of device.
-    - compatible      - (required) name of SPI device following generic names
-			recommended practice
-    - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
-    - spi-cpol        - (optional) Empty property indicating device requires
-			inverse clock polarity (CPOL) mode
-    - spi-cpha        - (optional) Empty property indicating device requires
-			shifted clock phase (CPHA) mode
-    - spi-cs-high     - (optional) Empty property indicating device requires
-			chip select active high
-
-    SPI example for an MPC5200 SPI bus:
-		spi@f00 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
-			reg = <0xf00 0x20>;
-			interrupts = <2 13 0 2 14 0>;
-			interrupt-parent = <&mpc5200_pic>;
-
-			ethernet-switch@0 {
-				compatible = "micrel,ks8995m";
-				spi-max-frequency = <1000000>;
-				reg = <0>;
-			};
-
-			codec@1 {
-				compatible = "ti,tlv320aic26";
-				spi-max-frequency = <100000>;
-				reg = <1>;
-			};
-		};
-
-VII - Marvell Discovery mv64[345]6x System Controller chips
-===========================================================
-
-The Marvell mv64[345]60 series of system controller chips contain
-many of the peripherals needed to implement a complete computer
-system.  In this section, we define device tree nodes to describe
-the system controller chip itself and each of the peripherals
-which it contains.  Compatible string values for each node are
-prefixed with the string "marvell,", for Marvell Technology Group Ltd.
-
-1) The /system-controller node
-
-  This node is used to represent the system-controller and must be
-  present when the system uses a system controller chip. The top-level
-  system-controller node contains information that is global to all
-  devices within the system controller chip. The node name begins
-  with "system-controller" followed by the unit address, which is
-  the base address of the memory-mapped register set for the system
-  controller chip.
-
-  Required properties:
-
-    - ranges : Describes the translation of system controller addresses
-      for memory mapped registers.
-    - clock-frequency: Contains the main clock frequency for the system
-      controller chip.
-    - reg : This property defines the address and size of the
-      memory-mapped registers contained within the system controller
-      chip.  The address specified in the "reg" property should match
-      the unit address of the system-controller node.
-    - #address-cells : Address representation for system controller
-      devices.  This field represents the number of cells needed to
-      represent the address of the memory-mapped registers of devices
-      within the system controller chip.
-    - #size-cells : Size representation for for the memory-mapped
-      registers within the system controller chip.
-    - #interrupt-cells : Defines the width of cells used to represent
-      interrupts.
-
-  Optional properties:
-
-    - model : The specific model of the system controller chip.  Such
-      as, "mv64360", "mv64460", or "mv64560".
-    - compatible : A string identifying the compatibility identifiers
-      of the system controller chip.
-
-  The system-controller node contains child nodes for each system
-  controller device that the platform uses.  Nodes should not be created
-  for devices which exist on the system controller chip but are not used
-
-  Example Marvell Discovery mv64360 system-controller node:
-
-    system-controller@f1000000 { /* Marvell Discovery mv64360 */
-	    #address-cells = <1>;
-	    #size-cells = <1>;
-	    model = "mv64360";                      /* Default */
-	    compatible = "marvell,mv64360";
-	    clock-frequency = <133333333>;
-	    reg = <0xf1000000 0x10000>;
-	    virtual-reg = <0xf1000000>;
-	    ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */
-		    0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */
-		    0xa0000000 0xa0000000 0x4000000 /* User FLASH */
-		    0x00000000 0xf1000000 0x0010000 /* Bridge's regs */
-		    0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */
-
-	    [ child node definitions... ]
-    }
-
-2) Child nodes of /system-controller
-
-   a) Marvell Discovery MDIO bus
-
-   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:
-     - #address-cells : Should be <1>
-     - #size-cells : Should be <0>
-     - device_type : Should be "mdio"
-     - compatible : Should be "marvell,mv64360-mdio"
-
-   Example:
-
-     mdio {
-	     #address-cells = <1>;
-	     #size-cells = <0>;
-	     device_type = "mdio";
-	     compatible = "marvell,mv64360-mdio";
-
-	     ethernet-phy@0 {
-		     ......
-	     };
-     };
-
-
-   b) Marvell Discovery ethernet controller
-
-   The Discover ethernet controller is described with two levels
-   of nodes.  The first level describes an ethernet silicon block
-   and the second level describes up to 3 ethernet nodes within
-   that block.  The reason for the multiple levels is that the
-   registers for the node are interleaved within a single set
-   of registers.  The "ethernet-block" level describes the
-   shared register set, and the "ethernet" nodes describe ethernet
-   port-specific properties.
-
-   Ethernet block node
-
-   Required properties:
-     - #address-cells : <1>
-     - #size-cells : <0>
-     - compatible : "marvell,mv64360-eth-block"
-     - reg : Offset and length of the register set for this block
-
-   Example Discovery Ethernet block node:
-     ethernet-block@2000 {
-	     #address-cells = <1>;
-	     #size-cells = <0>;
-	     compatible = "marvell,mv64360-eth-block";
-	     reg = <0x2000 0x2000>;
-	     ethernet@0 {
-		     .......
-	     };
-     };
-
-   Ethernet port node
-
-   Required properties:
-     - device_type : Should be "network".
-     - compatible : Should be "marvell,mv64360-eth".
-     - reg : Should be <0>, <1>, or <2>, according to which registers
-       within the silicon block the device uses.
-     - interrupts : <a> where a is the interrupt number for the port.
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-     - phy : the phandle for the PHY connected to this ethernet
-       controller.
-     - local-mac-address : 6 bytes, MAC address
-
-   Example Discovery Ethernet port node:
-     ethernet@0 {
-	     device_type = "network";
-	     compatible = "marvell,mv64360-eth";
-	     reg = <0>;
-	     interrupts = <32>;
-	     interrupt-parent = <&PIC>;
-	     phy = <&PHY0>;
-	     local-mac-address = [ 00 00 00 00 00 00 ];
-     };
-
-
-
-   c) Marvell Discovery PHY nodes
-
-   Required properties:
-     - device_type : Should be "ethernet-phy"
-     - interrupts : <a> where a is the interrupt number for this phy.
-     - 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
-
-   Example Discovery PHY node:
-     ethernet-phy@1 {
-	     device_type = "ethernet-phy";
-	     compatible = "broadcom,bcm5421";
-	     interrupts = <76>;      /* GPP 12 */
-	     interrupt-parent = <&PIC>;
-	     reg = <1>;
-     };
-
-
-   d) Marvell Discovery SDMA nodes
-
-   Represent DMA hardware associated with the MPSC (multiprotocol
-   serial controllers).
-
-   Required properties:
-     - compatible : "marvell,mv64360-sdma"
-     - reg : Offset and length of the register set for this device
-     - interrupts : <a> where a is the interrupt number for the DMA
-       device.
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery SDMA node:
-     sdma@4000 {
-	     compatible = "marvell,mv64360-sdma";
-	     reg = <0x4000 0xc18>;
-	     virtual-reg = <0xf1004000>;
-	     interrupts = <36>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   e) Marvell Discovery BRG nodes
-
-   Represent baud rate generator hardware associated with the MPSC
-   (multiprotocol serial controllers).
-
-   Required properties:
-     - compatible : "marvell,mv64360-brg"
-     - reg : Offset and length of the register set for this device
-     - clock-src : A value from 0 to 15 which selects the clock
-       source for the baud rate generator.  This value corresponds
-       to the CLKS value in the BRGx configuration register.  See
-       the mv64x60 User's Manual.
-     - clock-frequence : The frequency (in Hz) of the baud rate
-       generator's input clock.
-     - current-speed : The current speed setting (presumably by
-       firmware) of the baud rate generator.
-
-   Example Discovery BRG node:
-     brg@b200 {
-	     compatible = "marvell,mv64360-brg";
-	     reg = <0xb200 0x8>;
-	     clock-src = <8>;
-	     clock-frequency = <133333333>;
-	     current-speed = <9600>;
-     };
-
-
-   f) Marvell Discovery CUNIT nodes
-
-   Represent the Serial Communications Unit device hardware.
-
-   Required properties:
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery CUNIT node:
-     cunit@f200 {
-	     reg = <0xf200 0x200>;
-     };
-
-
-   g) Marvell Discovery MPSCROUTING nodes
-
-   Represent the Discovery's MPSC routing hardware
-
-   Required properties:
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery CUNIT node:
-     mpscrouting@b500 {
-	     reg = <0xb400 0xc>;
-     };
-
-
-   h) Marvell Discovery MPSCINTR nodes
-
-   Represent the Discovery's MPSC DMA interrupt hardware registers
-   (SDMA cause and mask registers).
-
-   Required properties:
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery MPSCINTR node:
-     mpsintr@b800 {
-	     reg = <0xb800 0x100>;
-     };
-
-
-   i) Marvell Discovery MPSC nodes
-
-   Represent the Discovery's MPSC (Multiprotocol Serial Controller)
-   serial port.
-
-   Required properties:
-     - device_type : "serial"
-     - compatible : "marvell,mv64360-mpsc"
-     - reg : Offset and length of the register set for this device
-     - sdma : the phandle for the SDMA node used by this port
-     - brg : the phandle for the BRG node used by this port
-     - cunit : the phandle for the CUNIT node used by this port
-     - mpscrouting : the phandle for the MPSCROUTING node used by this port
-     - mpscintr : the phandle for the MPSCINTR node used by this port
-     - cell-index : the hardware index of this cell in the MPSC core
-     - max_idle : value needed for MPSC CHR3 (Maximum Frame Length)
-       register
-     - interrupts : <a> where a is the interrupt number for the MPSC.
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery MPSCINTR node:
-     mpsc@8000 {
-	     device_type = "serial";
-	     compatible = "marvell,mv64360-mpsc";
-	     reg = <0x8000 0x38>;
-	     virtual-reg = <0xf1008000>;
-	     sdma = <&SDMA0>;
-	     brg = <&BRG0>;
-	     cunit = <&CUNIT>;
-	     mpscrouting = <&MPSCROUTING>;
-	     mpscintr = <&MPSCINTR>;
-	     cell-index = <0>;
-	     max_idle = <40>;
-	     interrupts = <40>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   j) Marvell Discovery Watch Dog Timer nodes
-
-   Represent the Discovery's watchdog timer hardware
-
-   Required properties:
-     - compatible : "marvell,mv64360-wdt"
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery Watch Dog Timer node:
-     wdt@b410 {
-	     compatible = "marvell,mv64360-wdt";
-	     reg = <0xb410 0x8>;
-     };
-
-
-   k) Marvell Discovery I2C nodes
-
-   Represent the Discovery's I2C hardware
-
-   Required properties:
-     - device_type : "i2c"
-     - compatible : "marvell,mv64360-i2c"
-     - reg : Offset and length of the register set for this device
-     - interrupts : <a> where a is the interrupt number for the I2C.
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery I2C node:
-	     compatible = "marvell,mv64360-i2c";
-	     reg = <0xc000 0x20>;
-	     virtual-reg = <0xf100c000>;
-	     interrupts = <37>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes
-
-   Represent the Discovery's PIC hardware
-
-   Required properties:
-     - #interrupt-cells : <1>
-     - #address-cells : <0>
-     - compatible : "marvell,mv64360-pic"
-     - reg : Offset and length of the register set for this device
-     - interrupt-controller
-
-   Example Discovery PIC node:
-     pic {
-	     #interrupt-cells = <1>;
-	     #address-cells = <0>;
-	     compatible = "marvell,mv64360-pic";
-	     reg = <0x0 0x88>;
-	     interrupt-controller;
-     };
-
-
-   m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes
-
-   Represent the Discovery's MPP hardware
-
-   Required properties:
-     - compatible : "marvell,mv64360-mpp"
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery MPP node:
-     mpp@f000 {
-	     compatible = "marvell,mv64360-mpp";
-	     reg = <0xf000 0x10>;
-     };
-
-
-   n) Marvell Discovery GPP (General Purpose Pins) nodes
-
-   Represent the Discovery's GPP hardware
-
-   Required properties:
-     - compatible : "marvell,mv64360-gpp"
-     - reg : Offset and length of the register set for this device
-
-   Example Discovery GPP node:
-     gpp@f000 {
-	     compatible = "marvell,mv64360-gpp";
-	     reg = <0xf100 0x20>;
-     };
-
-
-   o) Marvell Discovery PCI host bridge node
-
-   Represents the Discovery's PCI host bridge device.  The properties
-   for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE
-   1275-1994.  A typical value for the compatible property is
-   "marvell,mv64360-pci".
-
-   Example Discovery PCI host bridge node
-     pci@80000000 {
-	     #address-cells = <3>;
-	     #size-cells = <2>;
-	     #interrupt-cells = <1>;
-	     device_type = "pci";
-	     compatible = "marvell,mv64360-pci";
-	     reg = <0xcf8 0x8>;
-	     ranges = <0x01000000 0x0        0x0
-			     0x88000000 0x0 0x01000000
-		       0x02000000 0x0 0x80000000
-			     0x80000000 0x0 0x08000000>;
-	     bus-range = <0 255>;
-	     clock-frequency = <66000000>;
-	     interrupt-parent = <&PIC>;
-	     interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-	     interrupt-map = <
-		     /* IDSEL 0x0a */
-		     0x5000 0 0 1 &PIC 80
-		     0x5000 0 0 2 &PIC 81
-		     0x5000 0 0 3 &PIC 91
-		     0x5000 0 0 4 &PIC 93
-
-		     /* IDSEL 0x0b */
-		     0x5800 0 0 1 &PIC 91
-		     0x5800 0 0 2 &PIC 93
-		     0x5800 0 0 3 &PIC 80
-		     0x5800 0 0 4 &PIC 81
-
-		     /* IDSEL 0x0c */
-		     0x6000 0 0 1 &PIC 91
-		     0x6000 0 0 2 &PIC 93
-		     0x6000 0 0 3 &PIC 80
-		     0x6000 0 0 4 &PIC 81
-
-		     /* IDSEL 0x0d */
-		     0x6800 0 0 1 &PIC 93
-		     0x6800 0 0 2 &PIC 80
-		     0x6800 0 0 3 &PIC 81
-		     0x6800 0 0 4 &PIC 91
-	     >;
-     };
-
-
-   p) Marvell Discovery CPU Error nodes
-
-   Represent the Discovery's CPU error handler device.
-
-   Required properties:
-     - compatible : "marvell,mv64360-cpu-error"
-     - reg : Offset and length of the register set for this device
-     - interrupts : the interrupt number for this device
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery CPU Error node:
-     cpu-error@0070 {
-	     compatible = "marvell,mv64360-cpu-error";
-	     reg = <0x70 0x10 0x128 0x28>;
-	     interrupts = <3>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   q) Marvell Discovery SRAM Controller nodes
-
-   Represent the Discovery's SRAM controller device.
-
-   Required properties:
-     - compatible : "marvell,mv64360-sram-ctrl"
-     - reg : Offset and length of the register set for this device
-     - interrupts : the interrupt number for this device
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery SRAM Controller node:
-     sram-ctrl@0380 {
-	     compatible = "marvell,mv64360-sram-ctrl";
-	     reg = <0x380 0x80>;
-	     interrupts = <13>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   r) Marvell Discovery PCI Error Handler nodes
-
-   Represent the Discovery's PCI error handler device.
-
-   Required properties:
-     - compatible : "marvell,mv64360-pci-error"
-     - reg : Offset and length of the register set for this device
-     - interrupts : the interrupt number for this device
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery PCI Error Handler node:
-     pci-error@1d40 {
-	     compatible = "marvell,mv64360-pci-error";
-	     reg = <0x1d40 0x40 0xc28 0x4>;
-	     interrupts = <12>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-   s) Marvell Discovery Memory Controller nodes
-
-   Represent the Discovery's memory controller device.
-
-   Required properties:
-     - compatible : "marvell,mv64360-mem-ctrl"
-     - reg : Offset and length of the register set for this device
-     - interrupts : the interrupt number for this device
-     - interrupt-parent : the phandle for the interrupt controller
-       that services interrupts for this device.
-
-   Example Discovery Memory Controller node:
-     mem-ctrl@1400 {
-	     compatible = "marvell,mv64360-mem-ctrl";
-	     reg = <0x1400 0x60>;
-	     interrupts = <17>;
-	     interrupt-parent = <&PIC>;
-     };
-
-
-VIII - Specifying interrupt information for devices
+VII - Specifying interrupt information for devices
 ===================================================
 
 The device tree represents the busses and devices of a hardware
@@ -2439,56 +1324,7 @@ encodings listed below:
 	2 =  high to low edge sensitive type enabled
 	3 =  low to high edge sensitive type enabled
 
-IX - Specifying GPIO information for devices
-============================================
-
-1) gpios property
------------------
-
-Nodes that makes use of GPIOs should define them using `gpios' property,
-format of which is: <&gpio-controller1-phandle gpio1-specifier
-		     &gpio-controller2-phandle gpio2-specifier
-		     0 /* holes are permitted, means no GPIO 3 */
-		     &gpio-controller4-phandle gpio4-specifier
-		     ...>;
-
-Note that gpio-specifier length is controller dependent.
-
-gpio-specifier may encode: bank, pin position inside the bank,
-whether pin is open-drain and whether pin is logically inverted.
-
-Example of the node using GPIOs:
-
-	node {
-		gpios = <&qe_pio_e 18 0>;
-	};
-
-In this example gpio-specifier is "18 0" and encodes GPIO pin number,
-and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller.
-
-2) gpio-controller nodes
-------------------------
-
-Every GPIO controller node must have #gpio-cells property defined,
-this information will be used to translate gpio-specifiers.
-
-Example of two SOC GPIO banks defined as gpio-controller nodes:
-
-	qe_pio_a: gpio-controller@1400 {
-		#gpio-cells = <2>;
-		compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank";
-		reg = <0x1400 0x18>;
-		gpio-controller;
-	};
-
-	qe_pio_e: gpio-controller@1460 {
-		#gpio-cells = <2>;
-		compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
-		reg = <0x1460 0x18>;
-		gpio-controller;
-	};
-
-X - Specifying Device Power Management Information (sleep property)
+VIII - Specifying Device Power Management Information (sleep property)
 ===================================================================
 
 Devices on SOCs often have mechanisms for placing devices into low-power
diff --git a/Documentation/powerpc/dts-bindings/4xx/emac.txt b/Documentation/powerpc/dts-bindings/4xx/emac.txt
new file mode 100644
index 000000000000..2161334a7ca5
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/4xx/emac.txt
@@ -0,0 +1,148 @@
+    4xx/Axon EMAC ethernet nodes
+
+    The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
+    the Axon bridge.  To operate this needs to interact with a ths
+    special McMAL DMA controller, and sometimes an RGMII or ZMII
+    interface.  In addition to the nodes and properties described
+    below, the node for the OPB bus on which the EMAC sits must have a
+    correct clock-frequency property.
+
+      i) The EMAC node itself
+
+    Required properties:
+    - device_type       : "network"
+
+    - compatible        : compatible list, contains 2 entries, first is
+			  "ibm,emac-CHIP" where CHIP is the host ASIC (440gx,
+			  405gp, Axon) and second is either "ibm,emac" or
+			  "ibm,emac4".  For Axon, thus, we have: "ibm,emac-axon",
+			  "ibm,emac4"
+    - interrupts        : <interrupt mapping for EMAC IRQ and WOL IRQ>
+    - interrupt-parent  : optional, if needed for interrupt mapping
+    - reg               : <registers mapping>
+    - local-mac-address : 6 bytes, MAC address
+    - mal-device        : phandle of the associated McMAL node
+    - mal-tx-channel    : 1 cell, index of the tx channel on McMAL associated
+			  with this EMAC
+    - mal-rx-channel    : 1 cell, index of the rx channel on McMAL associated
+			  with this EMAC
+    - cell-index        : 1 cell, hardware index of the EMAC cell on a given
+			  ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on
+			  each Axon chip)
+    - max-frame-size    : 1 cell, maximum frame size supported in bytes
+    - rx-fifo-size      : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec
+			  operations.
+			  For Axon, 2048
+    - tx-fifo-size      : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec
+			  operations.
+			  For Axon, 2048.
+    - fifo-entry-size   : 1 cell, size of a fifo entry (used to calculate
+			  thresholds).
+			  For Axon, 0x00000010
+    - mal-burst-size    : 1 cell, MAL burst size (used to calculate thresholds)
+			  in bytes.
+			  For Axon, 0x00000100 (I think ...)
+    - phy-mode          : string, mode of operations of the PHY interface.
+			  Supported values are: "mii", "rmii", "smii", "rgmii",
+			  "tbi", "gmii", rtbi", "sgmii".
+			  For Axon on CAB, it is "rgmii"
+    - mdio-device       : 1 cell, required iff using shared MDIO registers
+			  (440EP).  phandle of the EMAC to use to drive the
+			  MDIO lines for the PHY used by this EMAC.
+    - zmii-device       : 1 cell, required iff connected to a ZMII.  phandle of
+			  the ZMII device node
+    - zmii-channel      : 1 cell, required iff connected to a ZMII.  Which ZMII
+			  channel or 0xffffffff if ZMII is only used for MDIO.
+    - rgmii-device      : 1 cell, required iff connected to an RGMII. phandle
+			  of the RGMII device node.
+			  For Axon: phandle of plb5/plb4/opb/rgmii
+    - rgmii-channel     : 1 cell, required iff connected to an RGMII.  Which
+			  RGMII channel is used by this EMAC.
+			  Fox Axon: present, whatever value is appropriate for each
+			  EMAC, that is the content of the current (bogus) "phy-port"
+			  property.
+
+    Optional properties:
+    - phy-address       : 1 cell, optional, MDIO address of the PHY. If absent,
+			  a search is performed.
+    - phy-map           : 1 cell, optional, bitmap of addresses to probe the PHY
+			  for, used if phy-address is absent. bit 0x00000001 is
+			  MDIO address 0.
+			  For Axon it can be absent, though my current driver
+			  doesn't handle phy-address yet so for now, keep
+			  0x00ffffff in it.
+    - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
+			  operations (if absent the value is the same as
+			  rx-fifo-size).  For Axon, either absent or 2048.
+    - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec
+			  operations (if absent the value is the same as
+			  tx-fifo-size). For Axon, either absent or 2048.
+    - tah-device        : 1 cell, optional. If connected to a TAH engine for
+			  offload, phandle of the TAH device node.
+    - tah-channel       : 1 cell, optional. If appropriate, channel used on the
+			  TAH engine.
+
+    Example:
+
+	EMAC0: ethernet@40000800 {
+		device_type = "network";
+		compatible = "ibm,emac-440gp", "ibm,emac";
+		interrupt-parent = <&UIC1>;
+		interrupts = <1c 4 1d 4>;
+		reg = <40000800 70>;
+		local-mac-address = [00 04 AC E3 1B 1E];
+		mal-device = <&MAL0>;
+		mal-tx-channel = <0 1>;
+		mal-rx-channel = <0>;
+		cell-index = <0>;
+		max-frame-size = <5dc>;
+		rx-fifo-size = <1000>;
+		tx-fifo-size = <800>;
+		phy-mode = "rmii";
+		phy-map = <00000001>;
+		zmii-device = <&ZMII0>;
+		zmii-channel = <0>;
+	};
+
+      ii) McMAL node
+
+    Required properties:
+    - device_type        : "dma-controller"
+    - compatible         : compatible list, containing 2 entries, first is
+			   "ibm,mcmal-CHIP" where CHIP is the host ASIC (like
+			   emac) and the second is either "ibm,mcmal" or
+			   "ibm,mcmal2".
+			   For Axon, "ibm,mcmal-axon","ibm,mcmal2"
+    - interrupts         : <interrupt mapping for the MAL interrupts sources:
+                           5 sources: tx_eob, rx_eob, serr, txde, rxde>.
+                           For Axon: This is _different_ from the current
+			   firmware.  We use the "delayed" interrupts for txeob
+			   and rxeob. Thus we end up with mapping those 5 MPIC
+			   interrupts, all level positive sensitive: 10, 11, 32,
+			   33, 34 (in decimal)
+    - dcr-reg            : < DCR registers range >
+    - dcr-parent         : if needed for dcr-reg
+    - num-tx-chans       : 1 cell, number of Tx channels
+    - num-rx-chans       : 1 cell, number of Rx channels
+
+      iii) ZMII node
+
+    Required properties:
+    - compatible         : compatible list, containing 2 entries, first is
+			   "ibm,zmii-CHIP" where CHIP is the host ASIC (like
+			   EMAC) and the second is "ibm,zmii".
+			   For Axon, there is no ZMII node.
+    - reg                : <registers mapping>
+
+      iv) RGMII node
+
+    Required properties:
+    - compatible         : compatible list, containing 2 entries, first is
+			   "ibm,rgmii-CHIP" where CHIP is the host ASIC (like
+			   EMAC) and the second is "ibm,rgmii".
+                           For Axon, "ibm,rgmii-axon","ibm,rgmii"
+    - reg                : <registers mapping>
+    - revision           : as provided by the RGMII new version register if
+			   available.
+			   For Axon: 0x0000012a
+
diff --git a/Documentation/powerpc/dts-bindings/gpio/gpio.txt b/Documentation/powerpc/dts-bindings/gpio/gpio.txt
new file mode 100644
index 000000000000..edaa84d288a1
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/gpio/gpio.txt
@@ -0,0 +1,50 @@
+Specifying GPIO information for devices
+============================================
+
+1) gpios property
+-----------------
+
+Nodes that makes use of GPIOs should define them using `gpios' property,
+format of which is: <&gpio-controller1-phandle gpio1-specifier
+		     &gpio-controller2-phandle gpio2-specifier
+		     0 /* holes are permitted, means no GPIO 3 */
+		     &gpio-controller4-phandle gpio4-specifier
+		     ...>;
+
+Note that gpio-specifier length is controller dependent.
+
+gpio-specifier may encode: bank, pin position inside the bank,
+whether pin is open-drain and whether pin is logically inverted.
+
+Example of the node using GPIOs:
+
+	node {
+		gpios = <&qe_pio_e 18 0>;
+	};
+
+In this example gpio-specifier is "18 0" and encodes GPIO pin number,
+and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller.
+
+2) gpio-controller nodes
+------------------------
+
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+
+Example of two SOC GPIO banks defined as gpio-controller nodes:
+
+	qe_pio_a: gpio-controller@1400 {
+		#gpio-cells = <2>;
+		compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank";
+		reg = <0x1400 0x18>;
+		gpio-controller;
+	};
+
+	qe_pio_e: gpio-controller@1460 {
+		#gpio-cells = <2>;
+		compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
+		reg = <0x1460 0x18>;
+		gpio-controller;
+	};
+
+
diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt
index 4fe14deedc0a..064db928c3c1 100644
--- a/Documentation/powerpc/dts-bindings/gpio/led.txt
+++ b/Documentation/powerpc/dts-bindings/gpio/led.txt
@@ -16,10 +16,17 @@ LED sub-node properties:
   string defining the trigger assigned to the LED.  Current triggers are:
     "backlight" - LED will act as a back-light, controlled by the framebuffer
 		  system
-    "default-on" - LED will turn on
+    "default-on" - LED will turn on, but see "default-state" below
     "heartbeat" - LED "double" flashes at a load average based rate
     "ide-disk" - LED indicates disk activity
     "timer" - LED flashes at a fixed, configurable rate
+- default-state:  (optional) The initial state of the LED.  Valid
+  values are "on", "off", and "keep".  If the LED is already on or off
+  and the default-state property is set the to same value, then no
+  glitch should be produced where the LED momentarily turns off (or
+  on).  The "keep" setting will keep the LED at whatever its current
+  state is, without producing a glitch.  The default is off if this
+  property is not present.
 
 Examples:
 
@@ -30,14 +37,22 @@ leds {
 		gpios = <&mcu_pio 0 1>; /* Active low */
 		linux,default-trigger = "ide-disk";
 	};
+
+	fault {
+		gpios = <&mcu_pio 1 0>;
+		/* Keep LED on if BIOS detected hardware fault */
+		default-state = "keep";
+	};
 };
 
 run-control {
 	compatible = "gpio-leds";
 	red {
 		gpios = <&mpc8572 6 0>;
+		default-state = "off";
 	};
 	green {
 		gpios = <&mpc8572 7 0>;
+		default-state = "on";
 	};
 }
diff --git a/Documentation/powerpc/dts-bindings/gpio/mdio.txt b/Documentation/powerpc/dts-bindings/gpio/mdio.txt
new file mode 100644
index 000000000000..bc9549529014
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/gpio/mdio.txt
@@ -0,0 +1,19 @@
+MDIO on GPIOs
+
+Currently defined compatibles:
+- virtual,gpio-mdio
+
+MDC and MDIO lines connected to GPIO controllers are listed in the
+gpios property as described in section VIII.1 in the following order:
+
+MDC, MDIO.
+
+Example:
+
+mdio {
+	compatible = "virtual,mdio-gpio";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	gpios = <&qe_pio_a 11
+		 &qe_pio_c 6>;
+};
diff --git a/Documentation/powerpc/dts-bindings/marvell.txt b/Documentation/powerpc/dts-bindings/marvell.txt
new file mode 100644
index 000000000000..3708a2fd4747
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/marvell.txt
@@ -0,0 +1,521 @@
+Marvell Discovery mv64[345]6x System Controller chips
+===========================================================
+
+The Marvell mv64[345]60 series of system controller chips contain
+many of the peripherals needed to implement a complete computer
+system.  In this section, we define device tree nodes to describe
+the system controller chip itself and each of the peripherals
+which it contains.  Compatible string values for each node are
+prefixed with the string "marvell,", for Marvell Technology Group Ltd.
+
+1) The /system-controller node
+
+  This node is used to represent the system-controller and must be
+  present when the system uses a system controller chip. The top-level
+  system-controller node contains information that is global to all
+  devices within the system controller chip. The node name begins
+  with "system-controller" followed by the unit address, which is
+  the base address of the memory-mapped register set for the system
+  controller chip.
+
+  Required properties:
+
+    - ranges : Describes the translation of system controller addresses
+      for memory mapped registers.
+    - clock-frequency: Contains the main clock frequency for the system
+      controller chip.
+    - reg : This property defines the address and size of the
+      memory-mapped registers contained within the system controller
+      chip.  The address specified in the "reg" property should match
+      the unit address of the system-controller node.
+    - #address-cells : Address representation for system controller
+      devices.  This field represents the number of cells needed to
+      represent the address of the memory-mapped registers of devices
+      within the system controller chip.
+    - #size-cells : Size representation for for the memory-mapped
+      registers within the system controller chip.
+    - #interrupt-cells : Defines the width of cells used to represent
+      interrupts.
+
+  Optional properties:
+
+    - model : The specific model of the system controller chip.  Such
+      as, "mv64360", "mv64460", or "mv64560".
+    - compatible : A string identifying the compatibility identifiers
+      of the system controller chip.
+
+  The system-controller node contains child nodes for each system
+  controller device that the platform uses.  Nodes should not be created
+  for devices which exist on the system controller chip but are not used
+
+  Example Marvell Discovery mv64360 system-controller node:
+
+    system-controller@f1000000 { /* Marvell Discovery mv64360 */
+	    #address-cells = <1>;
+	    #size-cells = <1>;
+	    model = "mv64360";                      /* Default */
+	    compatible = "marvell,mv64360";
+	    clock-frequency = <133333333>;
+	    reg = <0xf1000000 0x10000>;
+	    virtual-reg = <0xf1000000>;
+	    ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */
+		    0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */
+		    0xa0000000 0xa0000000 0x4000000 /* User FLASH */
+		    0x00000000 0xf1000000 0x0010000 /* Bridge's regs */
+		    0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */
+
+	    [ child node definitions... ]
+    }
+
+2) Child nodes of /system-controller
+
+   a) Marvell Discovery MDIO bus
+
+   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:
+     - #address-cells : Should be <1>
+     - #size-cells : Should be <0>
+     - device_type : Should be "mdio"
+     - compatible : Should be "marvell,mv64360-mdio"
+
+   Example:
+
+     mdio {
+	     #address-cells = <1>;
+	     #size-cells = <0>;
+	     device_type = "mdio";
+	     compatible = "marvell,mv64360-mdio";
+
+	     ethernet-phy@0 {
+		     ......
+	     };
+     };
+
+
+   b) Marvell Discovery ethernet controller
+
+   The Discover ethernet controller is described with two levels
+   of nodes.  The first level describes an ethernet silicon block
+   and the second level describes up to 3 ethernet nodes within
+   that block.  The reason for the multiple levels is that the
+   registers for the node are interleaved within a single set
+   of registers.  The "ethernet-block" level describes the
+   shared register set, and the "ethernet" nodes describe ethernet
+   port-specific properties.
+
+   Ethernet block node
+
+   Required properties:
+     - #address-cells : <1>
+     - #size-cells : <0>
+     - compatible : "marvell,mv64360-eth-block"
+     - reg : Offset and length of the register set for this block
+
+   Example Discovery Ethernet block node:
+     ethernet-block@2000 {
+	     #address-cells = <1>;
+	     #size-cells = <0>;
+	     compatible = "marvell,mv64360-eth-block";
+	     reg = <0x2000 0x2000>;
+	     ethernet@0 {
+		     .......
+	     };
+     };
+
+   Ethernet port node
+
+   Required properties:
+     - device_type : Should be "network".
+     - compatible : Should be "marvell,mv64360-eth".
+     - reg : Should be <0>, <1>, or <2>, according to which registers
+       within the silicon block the device uses.
+     - interrupts : <a> where a is the interrupt number for the port.
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+     - phy : the phandle for the PHY connected to this ethernet
+       controller.
+     - local-mac-address : 6 bytes, MAC address
+
+   Example Discovery Ethernet port node:
+     ethernet@0 {
+	     device_type = "network";
+	     compatible = "marvell,mv64360-eth";
+	     reg = <0>;
+	     interrupts = <32>;
+	     interrupt-parent = <&PIC>;
+	     phy = <&PHY0>;
+	     local-mac-address = [ 00 00 00 00 00 00 ];
+     };
+
+
+
+   c) Marvell Discovery PHY nodes
+
+   Required properties:
+     - device_type : Should be "ethernet-phy"
+     - interrupts : <a> where a is the interrupt number for this phy.
+     - 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
+
+   Example Discovery PHY node:
+     ethernet-phy@1 {
+	     device_type = "ethernet-phy";
+	     compatible = "broadcom,bcm5421";
+	     interrupts = <76>;      /* GPP 12 */
+	     interrupt-parent = <&PIC>;
+	     reg = <1>;
+     };
+
+
+   d) Marvell Discovery SDMA nodes
+
+   Represent DMA hardware associated with the MPSC (multiprotocol
+   serial controllers).
+
+   Required properties:
+     - compatible : "marvell,mv64360-sdma"
+     - reg : Offset and length of the register set for this device
+     - interrupts : <a> where a is the interrupt number for the DMA
+       device.
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery SDMA node:
+     sdma@4000 {
+	     compatible = "marvell,mv64360-sdma";
+	     reg = <0x4000 0xc18>;
+	     virtual-reg = <0xf1004000>;
+	     interrupts = <36>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   e) Marvell Discovery BRG nodes
+
+   Represent baud rate generator hardware associated with the MPSC
+   (multiprotocol serial controllers).
+
+   Required properties:
+     - compatible : "marvell,mv64360-brg"
+     - reg : Offset and length of the register set for this device
+     - clock-src : A value from 0 to 15 which selects the clock
+       source for the baud rate generator.  This value corresponds
+       to the CLKS value in the BRGx configuration register.  See
+       the mv64x60 User's Manual.
+     - clock-frequence : The frequency (in Hz) of the baud rate
+       generator's input clock.
+     - current-speed : The current speed setting (presumably by
+       firmware) of the baud rate generator.
+
+   Example Discovery BRG node:
+     brg@b200 {
+	     compatible = "marvell,mv64360-brg";
+	     reg = <0xb200 0x8>;
+	     clock-src = <8>;
+	     clock-frequency = <133333333>;
+	     current-speed = <9600>;
+     };
+
+
+   f) Marvell Discovery CUNIT nodes
+
+   Represent the Serial Communications Unit device hardware.
+
+   Required properties:
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery CUNIT node:
+     cunit@f200 {
+	     reg = <0xf200 0x200>;
+     };
+
+
+   g) Marvell Discovery MPSCROUTING nodes
+
+   Represent the Discovery's MPSC routing hardware
+
+   Required properties:
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery CUNIT node:
+     mpscrouting@b500 {
+	     reg = <0xb400 0xc>;
+     };
+
+
+   h) Marvell Discovery MPSCINTR nodes
+
+   Represent the Discovery's MPSC DMA interrupt hardware registers
+   (SDMA cause and mask registers).
+
+   Required properties:
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery MPSCINTR node:
+     mpsintr@b800 {
+	     reg = <0xb800 0x100>;
+     };
+
+
+   i) Marvell Discovery MPSC nodes
+
+   Represent the Discovery's MPSC (Multiprotocol Serial Controller)
+   serial port.
+
+   Required properties:
+     - device_type : "serial"
+     - compatible : "marvell,mv64360-mpsc"
+     - reg : Offset and length of the register set for this device
+     - sdma : the phandle for the SDMA node used by this port
+     - brg : the phandle for the BRG node used by this port
+     - cunit : the phandle for the CUNIT node used by this port
+     - mpscrouting : the phandle for the MPSCROUTING node used by this port
+     - mpscintr : the phandle for the MPSCINTR node used by this port
+     - cell-index : the hardware index of this cell in the MPSC core
+     - max_idle : value needed for MPSC CHR3 (Maximum Frame Length)
+       register
+     - interrupts : <a> where a is the interrupt number for the MPSC.
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery MPSCINTR node:
+     mpsc@8000 {
+	     device_type = "serial";
+	     compatible = "marvell,mv64360-mpsc";
+	     reg = <0x8000 0x38>;
+	     virtual-reg = <0xf1008000>;
+	     sdma = <&SDMA0>;
+	     brg = <&BRG0>;
+	     cunit = <&CUNIT>;
+	     mpscrouting = <&MPSCROUTING>;
+	     mpscintr = <&MPSCINTR>;
+	     cell-index = <0>;
+	     max_idle = <40>;
+	     interrupts = <40>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   j) Marvell Discovery Watch Dog Timer nodes
+
+   Represent the Discovery's watchdog timer hardware
+
+   Required properties:
+     - compatible : "marvell,mv64360-wdt"
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery Watch Dog Timer node:
+     wdt@b410 {
+	     compatible = "marvell,mv64360-wdt";
+	     reg = <0xb410 0x8>;
+     };
+
+
+   k) Marvell Discovery I2C nodes
+
+   Represent the Discovery's I2C hardware
+
+   Required properties:
+     - device_type : "i2c"
+     - compatible : "marvell,mv64360-i2c"
+     - reg : Offset and length of the register set for this device
+     - interrupts : <a> where a is the interrupt number for the I2C.
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery I2C node:
+	     compatible = "marvell,mv64360-i2c";
+	     reg = <0xc000 0x20>;
+	     virtual-reg = <0xf100c000>;
+	     interrupts = <37>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes
+
+   Represent the Discovery's PIC hardware
+
+   Required properties:
+     - #interrupt-cells : <1>
+     - #address-cells : <0>
+     - compatible : "marvell,mv64360-pic"
+     - reg : Offset and length of the register set for this device
+     - interrupt-controller
+
+   Example Discovery PIC node:
+     pic {
+	     #interrupt-cells = <1>;
+	     #address-cells = <0>;
+	     compatible = "marvell,mv64360-pic";
+	     reg = <0x0 0x88>;
+	     interrupt-controller;
+     };
+
+
+   m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes
+
+   Represent the Discovery's MPP hardware
+
+   Required properties:
+     - compatible : "marvell,mv64360-mpp"
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery MPP node:
+     mpp@f000 {
+	     compatible = "marvell,mv64360-mpp";
+	     reg = <0xf000 0x10>;
+     };
+
+
+   n) Marvell Discovery GPP (General Purpose Pins) nodes
+
+   Represent the Discovery's GPP hardware
+
+   Required properties:
+     - compatible : "marvell,mv64360-gpp"
+     - reg : Offset and length of the register set for this device
+
+   Example Discovery GPP node:
+     gpp@f000 {
+	     compatible = "marvell,mv64360-gpp";
+	     reg = <0xf100 0x20>;
+     };
+
+
+   o) Marvell Discovery PCI host bridge node
+
+   Represents the Discovery's PCI host bridge device.  The properties
+   for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE
+   1275-1994.  A typical value for the compatible property is
+   "marvell,mv64360-pci".
+
+   Example Discovery PCI host bridge node
+     pci@80000000 {
+	     #address-cells = <3>;
+	     #size-cells = <2>;
+	     #interrupt-cells = <1>;
+	     device_type = "pci";
+	     compatible = "marvell,mv64360-pci";
+	     reg = <0xcf8 0x8>;
+	     ranges = <0x01000000 0x0        0x0
+			     0x88000000 0x0 0x01000000
+		       0x02000000 0x0 0x80000000
+			     0x80000000 0x0 0x08000000>;
+	     bus-range = <0 255>;
+	     clock-frequency = <66000000>;
+	     interrupt-parent = <&PIC>;
+	     interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+	     interrupt-map = <
+		     /* IDSEL 0x0a */
+		     0x5000 0 0 1 &PIC 80
+		     0x5000 0 0 2 &PIC 81
+		     0x5000 0 0 3 &PIC 91
+		     0x5000 0 0 4 &PIC 93
+
+		     /* IDSEL 0x0b */
+		     0x5800 0 0 1 &PIC 91
+		     0x5800 0 0 2 &PIC 93
+		     0x5800 0 0 3 &PIC 80
+		     0x5800 0 0 4 &PIC 81
+
+		     /* IDSEL 0x0c */
+		     0x6000 0 0 1 &PIC 91
+		     0x6000 0 0 2 &PIC 93
+		     0x6000 0 0 3 &PIC 80
+		     0x6000 0 0 4 &PIC 81
+
+		     /* IDSEL 0x0d */
+		     0x6800 0 0 1 &PIC 93
+		     0x6800 0 0 2 &PIC 80
+		     0x6800 0 0 3 &PIC 81
+		     0x6800 0 0 4 &PIC 91
+	     >;
+     };
+
+
+   p) Marvell Discovery CPU Error nodes
+
+   Represent the Discovery's CPU error handler device.
+
+   Required properties:
+     - compatible : "marvell,mv64360-cpu-error"
+     - reg : Offset and length of the register set for this device
+     - interrupts : the interrupt number for this device
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery CPU Error node:
+     cpu-error@0070 {
+	     compatible = "marvell,mv64360-cpu-error";
+	     reg = <0x70 0x10 0x128 0x28>;
+	     interrupts = <3>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   q) Marvell Discovery SRAM Controller nodes
+
+   Represent the Discovery's SRAM controller device.
+
+   Required properties:
+     - compatible : "marvell,mv64360-sram-ctrl"
+     - reg : Offset and length of the register set for this device
+     - interrupts : the interrupt number for this device
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery SRAM Controller node:
+     sram-ctrl@0380 {
+	     compatible = "marvell,mv64360-sram-ctrl";
+	     reg = <0x380 0x80>;
+	     interrupts = <13>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   r) Marvell Discovery PCI Error Handler nodes
+
+   Represent the Discovery's PCI error handler device.
+
+   Required properties:
+     - compatible : "marvell,mv64360-pci-error"
+     - reg : Offset and length of the register set for this device
+     - interrupts : the interrupt number for this device
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery PCI Error Handler node:
+     pci-error@1d40 {
+	     compatible = "marvell,mv64360-pci-error";
+	     reg = <0x1d40 0x40 0xc28 0x4>;
+	     interrupts = <12>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
+   s) Marvell Discovery Memory Controller nodes
+
+   Represent the Discovery's memory controller device.
+
+   Required properties:
+     - compatible : "marvell,mv64360-mem-ctrl"
+     - reg : Offset and length of the register set for this device
+     - interrupts : the interrupt number for this device
+     - interrupt-parent : the phandle for the interrupt controller
+       that services interrupts for this device.
+
+   Example Discovery Memory Controller node:
+     mem-ctrl@1400 {
+	     compatible = "marvell,mv64360-mem-ctrl";
+	     reg = <0x1400 0x60>;
+	     interrupts = <17>;
+	     interrupt-parent = <&PIC>;
+     };
+
+
diff --git a/Documentation/powerpc/dts-bindings/phy.txt b/Documentation/powerpc/dts-bindings/phy.txt
new file mode 100644
index 000000000000..bb8c742eb8c5
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/phy.txt
@@ -0,0 +1,25 @@
+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";
+};
diff --git a/Documentation/powerpc/dts-bindings/spi-bus.txt b/Documentation/powerpc/dts-bindings/spi-bus.txt
new file mode 100644
index 000000000000..e782add2e457
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/spi-bus.txt
@@ -0,0 +1,57 @@
+SPI (Serial Peripheral Interface) busses
+
+SPI busses can be described with a node for the SPI master device
+and a set of child nodes for each SPI slave on the bus.  For this
+discussion, it is assumed that the system's SPI controller is in
+SPI master mode.  This binding does not describe SPI controllers
+in slave mode.
+
+The SPI master node requires the following properties:
+- #address-cells  - number of cells required to define a chip select
+    		address on the SPI bus.
+- #size-cells     - should be zero.
+- compatible      - name of SPI bus controller following generic names
+    		recommended practice.
+No other properties are required in the SPI bus node.  It is assumed
+that a driver for an SPI bus device will understand that it is an SPI bus.
+However, the binding does not attempt to define the specific method for
+assigning chip select numbers.  Since SPI chip select configuration is
+flexible and non-standardized, it is left out of this binding with the
+assumption that board specific platform code will be used to manage
+chip selects.  Individual drivers can define additional properties to
+support describing the chip select layout.
+
+SPI slave nodes must be children of the SPI master node and can
+contain the following properties.
+- reg             - (required) chip select address of device.
+- compatible      - (required) name of SPI device following generic names
+    		recommended practice
+- spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
+- spi-cpol        - (optional) Empty property indicating device requires
+    		inverse clock polarity (CPOL) mode
+- spi-cpha        - (optional) Empty property indicating device requires
+    		shifted clock phase (CPHA) mode
+- spi-cs-high     - (optional) Empty property indicating device requires
+    		chip select active high
+
+SPI example for an MPC5200 SPI bus:
+	spi@f00 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
+		reg = <0xf00 0x20>;
+		interrupts = <2 13 0 2 14 0>;
+		interrupt-parent = <&mpc5200_pic>;
+
+		ethernet-switch@0 {
+			compatible = "micrel,ks8995m";
+			spi-max-frequency = <1000000>;
+			reg = <0>;
+		};
+
+		codec@1 {
+			compatible = "ti,tlv320aic26";
+			spi-max-frequency = <100000>;
+			reg = <1>;
+		};
+	};
diff --git a/Documentation/powerpc/dts-bindings/usb-ehci.txt b/Documentation/powerpc/dts-bindings/usb-ehci.txt
new file mode 100644
index 000000000000..fa18612f757b
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/usb-ehci.txt
@@ -0,0 +1,25 @@
+USB EHCI controllers
+
+Required properties:
+  - compatible : should be "usb-ehci".
+  - reg : should contain at least address and length of the standard EHCI
+    register set for the device. Optional platform-dependent registers
+    (debug-port or other) can be also specified here, but only after
+    definition of standard EHCI registers.
+  - interrupts : one EHCI interrupt should be described here.
+If device registers are implemented in big endian mode, the device
+node should have "big-endian-regs" property.
+If controller implementation operates with big endian descriptors,
+"big-endian-desc" property should be specified.
+If both big endian registers and descriptors are used by the controller
+implementation, "big-endian" property can be specified instead of having
+both "big-endian-regs" and "big-endian-desc".
+
+Example (Sequoia 440EPx):
+    ehci@e0000300 {
+	   compatible = "ibm,usb-ehci-440epx", "usb-ehci";
+	   interrupt-parent = <&UIC0>;
+	   interrupts = <1a 4>;
+	   reg = <0 e0000300 90 0 e0000390 70>;
+	   big-endian;
+   };
diff --git a/Documentation/powerpc/dts-bindings/xilinx.txt b/Documentation/powerpc/dts-bindings/xilinx.txt
new file mode 100644
index 000000000000..80339fe4300b
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/xilinx.txt
@@ -0,0 +1,295 @@
+   d) Xilinx IP cores
+
+   The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
+   in Xilinx Spartan and Virtex FPGAs.  The devices cover the whole range
+   of standard device types (network, serial, etc.) and miscellaneous
+   devices (gpio, LCD, spi, etc).  Also, since these devices are
+   implemented within the fpga fabric every instance of the device can be
+   synthesised with different options that change the behaviour.
+
+   Each IP-core has a set of parameters which the FPGA designer can use to
+   control how the core is synthesized.  Historically, the EDK tool would
+   extract the device parameters relevant to device drivers and copy them
+   into an 'xparameters.h' in the form of #define symbols.  This tells the
+   device drivers how the IP cores are configured, but it requres the kernel
+   to be recompiled every time the FPGA bitstream is resynthesized.
+
+   The new approach is to export the parameters into the device tree and
+   generate a new device tree each time the FPGA bitstream changes.  The
+   parameters which used to be exported as #defines will now become
+   properties of the device node.  In general, device nodes for IP-cores
+   will take the following form:
+
+	(name): (generic-name)@(base-address) {
+		compatible = "xlnx,(ip-core-name)-(HW_VER)"
+			     [, (list of compatible devices), ...];
+		reg = <(baseaddr) (size)>;
+		interrupt-parent = <&interrupt-controller-phandle>;
+		interrupts = < ... >;
+		xlnx,(parameter1) = "(string-value)";
+		xlnx,(parameter2) = <(int-value)>;
+	};
+
+	(generic-name):   an open firmware-style name that describes the
+			generic class of device.  Preferably, this is one word, such
+			as 'serial' or 'ethernet'.
+	(ip-core-name):	the name of the ip block (given after the BEGIN
+			directive in system.mhs).  Should be in lowercase
+			and all underscores '_' converted to dashes '-'.
+	(name):		is derived from the "PARAMETER INSTANCE" value.
+	(parameter#):	C_* parameters from system.mhs.  The C_ prefix is
+			dropped from the parameter name, the name is converted
+			to lowercase and all underscore '_' characters are
+			converted to dashes '-'.
+	(baseaddr):	the baseaddr parameter value (often named C_BASEADDR).
+	(HW_VER):	from the HW_VER parameter.
+	(size):		the address range size (often C_HIGHADDR - C_BASEADDR + 1).
+
+   Typically, the compatible list will include the exact IP core version
+   followed by an older IP core version which implements the same
+   interface or any other device with the same interface.
+
+   'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
+
+   For example, the following block from system.mhs:
+
+	BEGIN opb_uartlite
+		PARAMETER INSTANCE = opb_uartlite_0
+		PARAMETER HW_VER = 1.00.b
+		PARAMETER C_BAUDRATE = 115200
+		PARAMETER C_DATA_BITS = 8
+		PARAMETER C_ODD_PARITY = 0
+		PARAMETER C_USE_PARITY = 0
+		PARAMETER C_CLK_FREQ = 50000000
+		PARAMETER C_BASEADDR = 0xEC100000
+		PARAMETER C_HIGHADDR = 0xEC10FFFF
+		BUS_INTERFACE SOPB = opb_7
+		PORT OPB_Clk = CLK_50MHz
+		PORT Interrupt = opb_uartlite_0_Interrupt
+		PORT RX = opb_uartlite_0_RX
+		PORT TX = opb_uartlite_0_TX
+		PORT OPB_Rst = sys_bus_reset_0
+	END
+
+   becomes the following device tree node:
+
+	opb_uartlite_0: serial@ec100000 {
+		device_type = "serial";
+		compatible = "xlnx,opb-uartlite-1.00.b";
+		reg = <ec100000 10000>;
+		interrupt-parent = <&opb_intc_0>;
+		interrupts = <1 0>; // got this from the opb_intc parameters
+		current-speed = <d#115200>;	// standard serial device prop
+		clock-frequency = <d#50000000>;	// standard serial device prop
+		xlnx,data-bits = <8>;
+		xlnx,odd-parity = <0>;
+		xlnx,use-parity = <0>;
+	};
+
+   Some IP cores actually implement 2 or more logical devices.  In
+   this case, the device should still describe the whole IP core with
+   a single node and add a child node for each logical device.  The
+   ranges property can be used to translate from parent IP-core to the
+   registers of each device.  In addition, the parent node should be
+   compatible with the bus type 'xlnx,compound', and should contain
+   #address-cells and #size-cells, as with any other bus.  (Note: this
+   makes the assumption that both logical devices have the same bus
+   binding.  If this is not true, then separate nodes should be used
+   for each logical device).  The 'cell-index' property can be used to
+   enumerate logical devices within an IP core.  For example, the
+   following is the system.mhs entry for the dual ps2 controller found
+   on the ml403 reference design.
+
+	BEGIN opb_ps2_dual_ref
+		PARAMETER INSTANCE = opb_ps2_dual_ref_0
+		PARAMETER HW_VER = 1.00.a
+		PARAMETER C_BASEADDR = 0xA9000000
+		PARAMETER C_HIGHADDR = 0xA9001FFF
+		BUS_INTERFACE SOPB = opb_v20_0
+		PORT Sys_Intr1 = ps2_1_intr
+		PORT Sys_Intr2 = ps2_2_intr
+		PORT Clkin1 = ps2_clk_rx_1
+		PORT Clkin2 = ps2_clk_rx_2
+		PORT Clkpd1 = ps2_clk_tx_1
+		PORT Clkpd2 = ps2_clk_tx_2
+		PORT Rx1 = ps2_d_rx_1
+		PORT Rx2 = ps2_d_rx_2
+		PORT Txpd1 = ps2_d_tx_1
+		PORT Txpd2 = ps2_d_tx_2
+	END
+
+   It would result in the following device tree nodes:
+
+	opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "xlnx,compound";
+		ranges = <0 a9000000 2000>;
+		// If this device had extra parameters, then they would
+		// go here.
+		ps2@0 {
+			compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
+			reg = <0 40>;
+			interrupt-parent = <&opb_intc_0>;
+			interrupts = <3 0>;
+			cell-index = <0>;
+		};
+		ps2@1000 {
+			compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
+			reg = <1000 40>;
+			interrupt-parent = <&opb_intc_0>;
+			interrupts = <3 0>;
+			cell-index = <0>;
+		};
+	};
+
+   Also, the system.mhs file defines bus attachments from the processor
+   to the devices.  The device tree structure should reflect the bus
+   attachments.  Again an example; this system.mhs fragment:
+
+	BEGIN ppc405_virtex4
+		PARAMETER INSTANCE = ppc405_0
+		PARAMETER HW_VER = 1.01.a
+		BUS_INTERFACE DPLB = plb_v34_0
+		BUS_INTERFACE IPLB = plb_v34_0
+	END
+
+	BEGIN opb_intc
+		PARAMETER INSTANCE = opb_intc_0
+		PARAMETER HW_VER = 1.00.c
+		PARAMETER C_BASEADDR = 0xD1000FC0
+		PARAMETER C_HIGHADDR = 0xD1000FDF
+		BUS_INTERFACE SOPB = opb_v20_0
+	END
+
+	BEGIN opb_uart16550
+		PARAMETER INSTANCE = opb_uart16550_0
+		PARAMETER HW_VER = 1.00.d
+		PARAMETER C_BASEADDR = 0xa0000000
+		PARAMETER C_HIGHADDR = 0xa0001FFF
+		BUS_INTERFACE SOPB = opb_v20_0
+	END
+
+	BEGIN plb_v34
+		PARAMETER INSTANCE = plb_v34_0
+		PARAMETER HW_VER = 1.02.a
+	END
+
+	BEGIN plb_bram_if_cntlr
+		PARAMETER INSTANCE = plb_bram_if_cntlr_0
+		PARAMETER HW_VER = 1.00.b
+		PARAMETER C_BASEADDR = 0xFFFF0000
+		PARAMETER C_HIGHADDR = 0xFFFFFFFF
+		BUS_INTERFACE SPLB = plb_v34_0
+	END
+
+	BEGIN plb2opb_bridge
+		PARAMETER INSTANCE = plb2opb_bridge_0
+		PARAMETER HW_VER = 1.01.a
+		PARAMETER C_RNG0_BASEADDR = 0x20000000
+		PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF
+		PARAMETER C_RNG1_BASEADDR = 0x60000000
+		PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF
+		PARAMETER C_RNG2_BASEADDR = 0x80000000
+		PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF
+		PARAMETER C_RNG3_BASEADDR = 0xC0000000
+		PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF
+		BUS_INTERFACE SPLB = plb_v34_0
+		BUS_INTERFACE MOPB = opb_v20_0
+	END
+
+   Gives this device tree (some properties removed for clarity):
+
+	plb@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "xlnx,plb-v34-1.02.a";
+		device_type = "ibm,plb";
+		ranges; // 1:1 translation
+
+		plb_bram_if_cntrl_0: bram@ffff0000 {
+			reg = <ffff0000 10000>;
+		}
+
+		opb@20000000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <20000000 20000000 20000000
+				  60000000 60000000 20000000
+				  80000000 80000000 40000000
+				  c0000000 c0000000 20000000>;
+
+			opb_uart16550_0: serial@a0000000 {
+				reg = <a00000000 2000>;
+			};
+
+			opb_intc_0: interrupt-controller@d1000fc0 {
+				reg = <d1000fc0 20>;
+			};
+		};
+	};
+
+   That covers the general approach to binding xilinx IP cores into the
+   device tree.  The following are bindings for specific devices:
+
+      i) Xilinx ML300 Framebuffer
+
+      Simple framebuffer device from the ML300 reference design (also on the
+      ML403 reference design as well as others).
+
+      Optional properties:
+       - resolution = <xres yres> : pixel resolution of framebuffer.  Some
+                                    implementations use a different resolution.
+                                    Default is <d#640 d#480>
+       - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory.
+                                           Default is <d#1024 d#480>.
+       - rotate-display (empty) : rotate display 180 degrees.
+
+      ii) Xilinx SystemACE
+
+      The Xilinx SystemACE device is used to program FPGAs from an FPGA
+      bitstream stored on a CF card.  It can also be used as a generic CF
+      interface device.
+
+      Optional properties:
+       - 8-bit (empty) : Set this property for SystemACE in 8 bit mode
+
+      iii) Xilinx EMAC and Xilinx TEMAC
+
+      Xilinx Ethernet devices.  In addition to general xilinx properties
+      listed above, nodes for these devices should include a phy-handle
+      property, and may include other common network device properties
+      like local-mac-address.
+
+      iv) Xilinx Uartlite
+
+      Xilinx uartlite devices are simple fixed speed serial ports.
+
+      Required properties:
+       - current-speed : Baud rate of uartlite
+
+      v) Xilinx hwicap
+
+		Xilinx hwicap devices provide access to the configuration logic
+		of the FPGA through the Internal Configuration Access Port
+		(ICAP).  The ICAP enables partial reconfiguration of the FPGA,
+		readback of the configuration information, and some control over
+		'warm boots' of the FPGA fabric.
+
+		Required properties:
+		- xlnx,family : The family of the FPGA, necessary since the
+                      capabilities of the underlying ICAP hardware
+                      differ between different families.  May be
+                      'virtex2p', 'virtex4', or 'virtex5'.
+
+      vi) Xilinx Uart 16550
+
+      Xilinx UART 16550 devices are very similar to the NS16550 but with
+      different register spacing and an offset from the base address.
+
+      Required properties:
+       - clock-frequency : Frequency of the clock input
+       - reg-offset : A value of 3 is required
+       - reg-shift : A value of 2 is required
+
+
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 1df7f9cdab05..86eabe6c3419 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -73,7 +73,7 @@ The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
 their tasks, buffer underruns in the graphics or audio can be eliminated.
 
-NOTE: the above example is not fully implemented as of yet (2.6.25). We still
+NOTE: the above example is not fully implemented yet. We still
 lack an EDF scheduler to make non-uniform periods usable.
 
 
@@ -140,14 +140,15 @@ The other option is:
 
 .o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
 
-This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us"
-to control the CPU time reserved for each control group instead.
+This uses the /cgroup virtual file system and
+"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
+control group instead.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
 
-Group settings are checked against the following limits in order to keep the configuration
-schedulable:
+Group settings are checked against the following limits in order to keep the
+configuration schedulable:
 
    \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period
 
@@ -189,7 +190,7 @@ Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
 the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
-deadline delta (deadline - now).
+deadline delta (deadline - now)).
 
 This means the whole PI machinery will have to be reworked - and that is one of
 the most complex pieces of code we have.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 0d8d23581c44..939a3dd58148 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -240,6 +240,7 @@ AD1986A
   laptop-automute 2-channel with EAPD and HP-automute (Lenovo N100)
   ultra		2-channel with EAPD (Samsung Ultra tablet PC)
   samsung	2-channel with EAPD (Samsung R65)
+  samsung-p50	2-channel with HP-automute (Samsung P50)
 
 AD1988/AD1988B/AD1989A/AD1989B
 ==============================
diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index 381908d8ca42..719a819f8cc2 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -101,6 +101,8 @@ card*/pcm*/xrun_debug
 	  bit 0 = Enable XRUN/jiffies debug messages
 	  bit 1 = Show stack trace at XRUN / jiffies check
 	  bit 2 = Enable additional jiffies check
+	  bit 3 = Log hwptr update at each period interrupt
+	  bit 4 = Log hwptr update at each snd_pcm_update_hw_ptr()
 
 	When the bit 0 is set, the driver will show the messages to
 	kernel log when an xrun is detected.  The debug message is
@@ -117,6 +119,9 @@ card*/pcm*/xrun_debug
 	buggy) hardware that doesn't give smooth pointer updates.
 	This feature is enabled via the bit 2.
 
+	Bits 3 and 4 are for logging the hwptr records.  Note that
+	these will give flood of kernel messages.
+
 card*/pcm*/sub*/info
 	The general information of this PCM sub-stream.
 
diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index cf0e3ce0d526..c1a5aad3c75a 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -99,11 +99,13 @@ void parse_opts(int argc, char *argv[])
 			{ "lsb",     0, 0, 'L' },
 			{ "cs-high", 0, 0, 'C' },
 			{ "3wire",   0, 0, '3' },
+			{ "no-cs",   0, 0, 'N' },
+			{ "ready",   0, 0, 'R' },
 			{ NULL, 0, 0, 0 },
 		};
 		int c;
 
-		c = getopt_long(argc, argv, "D:s:d:b:lHOLC3", lopts, NULL);
+		c = getopt_long(argc, argv, "D:s:d:b:lHOLC3NR", lopts, NULL);
 
 		if (c == -1)
 			break;
@@ -139,6 +141,12 @@ void parse_opts(int argc, char *argv[])
 		case '3':
 			mode |= SPI_3WIRE;
 			break;
+		case 'N':
+			mode |= SPI_NO_CS;
+			break;
+		case 'R':
+			mode |= SPI_READY;
+			break;
 		default:
 			print_usage(argv[0]);
 			break;
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index cf42b820ff9d..d56a01775423 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -66,7 +66,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'b'     - Will immediately reboot the system without syncing or unmounting
           your disks.
 
-'c'	- Will perform a kexec reboot in order to take a crashdump.
+'c'	- Will perform a system crash by a NULL pointer dereference.
+          A crashdump will be taken if configured.
 
 'd'	- Shows all locks that are held.
 
@@ -141,8 +142,8 @@ useful when you want to exit a program that will not let you switch consoles.
 re'B'oot is good when you're unable to shut down. But you should also 'S'ync
 and 'U'mount first.
 
-'C'rashdump can be used to manually trigger a crashdump when the system is hung.
-The kernel needs to have been built with CONFIG_KEXEC enabled.
+'C'rash can be used to manually trigger a crashdump when the system is hung.
+Note that this just triggers a crash if there is no dump mechanism available.
 
 'S'ync is great when your system is locked up, it allows you to sync your
 disks and will certainly lessen the chance of data loss and fscking. Note
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 873630e7e53e..68c236c01846 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -20,7 +20,7 @@
  19 -> EM2860/SAA711X Reference Design          (em2860)
  20 -> AMD ATI TV Wonder HD 600                 (em2880)        [0438:b002]
  21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800)        [eb1a:2801]
- 22 -> Unknown EM2750/EM2751 webcam grabber     (em2750)        [eb1a:2750,eb1a:2751]
+ 22 -> EM2710/EM2750/EM2751 webcam grabber      (em2750)        [eb1a:2750,eb1a:2751]
  23 -> Huaqi DLCW-130                           (em2750)
  24 -> D-Link DUB-T210 TV Tuner                 (em2820/em2840) [2001:f112]
  25 -> Gadmei UTV310                            (em2820/em2840)
@@ -66,3 +66,4 @@
  68 -> Terratec AV350                           (em2860)        [0ccd:0084]
  69 -> KWorld ATSC 315U HDTV TV Box             (em2882)        [eb1a:a313]
  70 -> Evga inDtube                             (em2882)
+ 71 -> Silvercrest Webcam 1.3mpix               (em2820/em2840)
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 2bcf78896e22..573f95b58807 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -44,7 +44,9 @@ zc3xx		0458:7007	Genius VideoCam V2
 zc3xx		0458:700c	Genius VideoCam V3
 zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
+sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)
 sonixj		045e:00f5	MicroSoft VX3000
 sonixj		045e:00f7	MicroSoft VX1000
 ov519		045e:028c	Micro$oft xbox cam
@@ -282,6 +284,28 @@ sonixj		0c45:613a	Microdia Sonix PC Camera
 sonixj		0c45:613b	Surfer SN-206
 sonixj		0c45:613c	Sonix Pccam168
 sonixj		0c45:6143	Sonix Pccam168
+sn9c20x		0c45:6240	PC Camera (SN9C201 + MT9M001)
+sn9c20x		0c45:6242	PC Camera (SN9C201 + MT9M111)
+sn9c20x		0c45:6248	PC Camera (SN9C201 + OV9655)
+sn9c20x		0c45:624e	PC Camera (SN9C201 + SOI968)
+sn9c20x		0c45:624f	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6251	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6253	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6260	PC Camera (SN9C201 + OV7670)
+sn9c20x		0c45:6270	PC Camera (SN9C201 + MT9V011/MT9V111/MT9V112)
+sn9c20x		0c45:627b	PC Camera (SN9C201 + OV7660)
+sn9c20x		0c45:627c	PC Camera (SN9C201 + HV7131R)
+sn9c20x		0c45:627f	PC Camera (SN9C201 + OV9650)
+sn9c20x		0c45:6280	PC Camera (SN9C202 + MT9M001)
+sn9c20x		0c45:6282	PC Camera (SN9C202 + MT9M111)
+sn9c20x		0c45:6288	PC Camera (SN9C202 + OV9655)
+sn9c20x		0c45:628e	PC Camera (SN9C202 + SOI968)
+sn9c20x		0c45:628f	PC Camera (SN9C202 + OV9650)
+sn9c20x		0c45:62a0	PC Camera (SN9C202 + OV7670)
+sn9c20x		0c45:62b0	PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112)
+sn9c20x		0c45:62b3	PC Camera (SN9C202 + OV9655)
+sn9c20x		0c45:62bb	PC Camera (SN9C202 + OV7660)
+sn9c20x		0c45:62bc	PC Camera (SN9C202 + HV7131R)
 sunplus		0d64:0303	Sunplus FashionCam DXG
 etoms		102c:6151	Qcam Sangha CIF
 etoms		102c:6251	Qcam xxxxxx VGA
@@ -290,6 +314,7 @@ spca561		10fd:7e50	FlyCam Usb 100
 zc3xx		10fd:8050	Typhoon Webshot II USB 300k
 ov534		1415:2000	Sony HD Eye for PS3 (SLEH 00201)
 pac207		145f:013a	Trust WB-1300N
+sn9c20x		145f:013d	Trust WB-3600R
 vc032x		15b8:6001	HP 2.0 Megapixel
 vc032x		15b8:6002	HP 2.0 Megapixel rz406aa
 spca501		1776:501c	Arowana 300K CMOS Camera
@@ -300,4 +325,11 @@ spca500		2899:012c	Toptro Industrial
 spca508		8086:0110	Intel Easy PC Camera
 spca500		8086:0630	Intel Pocket PC Camera
 spca506		99fa:8988	Grandtec V.cap
+sn9c20x		a168:0610	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0611	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0613	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0618	Dino-Lite Digital Microscope (SN9C201 + HV7131R)
+sn9c20x		a168:0614	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
+sn9c20x		a168:0615	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
+sn9c20x		a168:0617	Dino-Lite Digital Microscope (SN9C201 + MT9M111)
 spca561		abcd:cdee	Petcam
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
index dbe3377754af..f37b46d34861 100644
--- a/Documentation/x86/00-INDEX
+++ b/Documentation/x86/00-INDEX
@@ -2,3 +2,5 @@
 	- this file
 mtrr.txt
 	- how to use x86 Memory Type Range Registers to increase performance
+exception-tables.txt
+	- why and how Linux kernel uses exception tables on x86
diff --git a/Documentation/exception.txt b/Documentation/x86/exception-tables.txt
index 2d5aded64247..32901aa36f0a 100644
--- a/Documentation/exception.txt
+++ b/Documentation/x86/exception-tables.txt
@@ -1,123 +1,123 @@
-     Kernel level exception handling in Linux 2.1.8
+     Kernel level exception handling in Linux
   Commentary by Joerg Pommnitz <joerg@raleigh.ibm.com>
 
-When a process runs in kernel mode, it often has to access user 
-mode memory whose address has been passed by an untrusted program. 
+When a process runs in kernel mode, it often has to access user
+mode memory whose address has been passed by an untrusted program.
 To protect itself the kernel has to verify this address.
 
-In older versions of Linux this was done with the 
-int verify_area(int type, const void * addr, unsigned long size) 
+In older versions of Linux this was done with the
+int verify_area(int type, const void * addr, unsigned long size)
 function (which has since been replaced by access_ok()).
 
-This function verified that the memory area starting at address 
+This function verified that the memory area starting at address
 'addr' and of size 'size' was accessible for the operation specified
-in type (read or write). To do this, verify_read had to look up the 
-virtual memory area (vma) that contained the address addr. In the 
-normal case (correctly working program), this test was successful. 
+in type (read or write). To do this, verify_read had to look up the
+virtual memory area (vma) that contained the address addr. In the
+normal case (correctly working program), this test was successful.
 It only failed for a few buggy programs. In some kernel profiling
 tests, this normally unneeded verification used up a considerable
 amount of time.
 
-To overcome this situation, Linus decided to let the virtual memory 
+To overcome this situation, Linus decided to let the virtual memory
 hardware present in every Linux-capable CPU handle this test.
 
 How does this work?
 
-Whenever the kernel tries to access an address that is currently not 
-accessible, the CPU generates a page fault exception and calls the 
-page fault handler 
+Whenever the kernel tries to access an address that is currently not
+accessible, the CPU generates a page fault exception and calls the
+page fault handler
 
 void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
-in arch/i386/mm/fault.c. The parameters on the stack are set up by 
-the low level assembly glue in arch/i386/kernel/entry.S. The parameter
-regs is a pointer to the saved registers on the stack, error_code 
+in arch/x86/mm/fault.c. The parameters on the stack are set up by
+the low level assembly glue in arch/x86/kernel/entry_32.S. The parameter
+regs is a pointer to the saved registers on the stack, error_code
 contains a reason code for the exception.
 
-do_page_fault first obtains the unaccessible address from the CPU 
-control register CR2. If the address is within the virtual address 
-space of the process, the fault probably occurred, because the page 
-was not swapped in, write protected or something similar. However, 
-we are interested in the other case: the address is not valid, there 
-is no vma that contains this address. In this case, the kernel jumps 
-to the bad_area label. 
-
-There it uses the address of the instruction that caused the exception 
-(i.e. regs->eip) to find an address where the execution can continue 
-(fixup). If this search is successful, the fault handler modifies the 
-return address (again regs->eip) and returns. The execution will 
+do_page_fault first obtains the unaccessible address from the CPU
+control register CR2. If the address is within the virtual address
+space of the process, the fault probably occurred, because the page
+was not swapped in, write protected or something similar. However,
+we are interested in the other case: the address is not valid, there
+is no vma that contains this address. In this case, the kernel jumps
+to the bad_area label.
+
+There it uses the address of the instruction that caused the exception
+(i.e. regs->eip) to find an address where the execution can continue
+(fixup). If this search is successful, the fault handler modifies the
+return address (again regs->eip) and returns. The execution will
 continue at the address in fixup.
 
 Where does fixup point to?
 
-Since we jump to the contents of fixup, fixup obviously points 
-to executable code. This code is hidden inside the user access macros. 
-I have picked the get_user macro defined in include/asm/uaccess.h as an
-example. The definition is somewhat hard to follow, so let's peek at 
+Since we jump to the contents of fixup, fixup obviously points
+to executable code. This code is hidden inside the user access macros.
+I have picked the get_user macro defined in arch/x86/include/asm/uaccess.h
+as an example. The definition is somewhat hard to follow, so let's peek at
 the code generated by the preprocessor and the compiler. I selected
-the get_user call in drivers/char/console.c for a detailed examination.
+the get_user call in drivers/char/sysrq.c for a detailed examination.
 
-The original code in console.c line 1405:
+The original code in sysrq.c line 587:
         get_user(c, buf);
 
 The preprocessor output (edited to become somewhat readable):
 
 (
-  {        
-    long __gu_err = - 14 , __gu_val = 0;        
-    const __typeof__(*( (  buf ) )) *__gu_addr = ((buf));        
-    if (((((0 + current_set[0])->tss.segment) == 0x18 )  || 
-       (((sizeof(*(buf))) <= 0xC0000000UL) && 
-       ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf)))))))        
+  {
+    long __gu_err = - 14 , __gu_val = 0;
+    const __typeof__(*( (  buf ) )) *__gu_addr = ((buf));
+    if (((((0 + current_set[0])->tss.segment) == 0x18 )  ||
+       (((sizeof(*(buf))) <= 0xC0000000UL) &&
+       ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf)))))))
       do {
-        __gu_err  = 0;        
-        switch ((sizeof(*(buf)))) {        
-          case 1: 
-            __asm__ __volatile__(        
-              "1:      mov" "b" " %2,%" "b" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "b" " %" "b" "1,%" "b" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        
-              "        .long 1b,3b\n"        
+        __gu_err  = 0;
+        switch ((sizeof(*(buf)))) {
+          case 1:
+            __asm__ __volatile__(
+              "1:      mov" "b" " %2,%" "b" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "b" " %" "b" "1,%" "b" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"
+              "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=q" (__gu_val): "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )) ; 
-              break;        
-          case 2: 
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )) ;
+              break;
+          case 2:
             __asm__ __volatile__(
-              "1:      mov" "w" " %2,%" "w" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "w" " %" "w" "1,%" "w" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        
-              "        .long 1b,3b\n"        
+              "1:      mov" "w" " %2,%" "w" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "w" " %" "w" "1,%" "w" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"
+              "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  )); 
-              break;        
-          case 4: 
-            __asm__ __volatile__(        
-              "1:      mov" "l" " %2,%" "" "1\n"        
-              "2:\n"        
-              ".section .fixup,\"ax\"\n"        
-              "3:      movl %3,%0\n"        
-              "        xor" "l" " %" "" "1,%" "" "1\n"        
-              "        jmp 2b\n"        
-              ".section __ex_table,\"a\"\n"        
-              "        .align 4\n"        "        .long 1b,3b\n"        
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(  __gu_err  ));
+              break;
+          case 4:
+            __asm__ __volatile__(
+              "1:      mov" "l" " %2,%" "" "1\n"
+              "2:\n"
+              ".section .fixup,\"ax\"\n"
+              "3:      movl %3,%0\n"
+              "        xor" "l" " %" "" "1,%" "" "1\n"
+              "        jmp 2b\n"
+              ".section __ex_table,\"a\"\n"
+              "        .align 4\n"        "        .long 1b,3b\n"
               ".text"        : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *)
-                            (   __gu_addr   )) ), "i"(- 14 ), "0"(__gu_err)); 
-              break;        
-          default: 
-            (__gu_val) = __get_user_bad();        
-        }        
-      } while (0) ;        
-    ((c)) = (__typeof__(*((buf))))__gu_val;        
+                            (   __gu_addr   )) ), "i"(- 14 ), "0"(__gu_err));
+              break;
+          default:
+            (__gu_val) = __get_user_bad();
+        }
+      } while (0) ;
+    ((c)) = (__typeof__(*((buf))))__gu_val;
     __gu_err;
   }
 );
@@ -127,12 +127,12 @@ see what code gcc generates:
 
  >         xorl %edx,%edx
  >         movl current_set,%eax
- >         cmpl $24,788(%eax)        
- >         je .L1424        
+ >         cmpl $24,788(%eax)
+ >         je .L1424
  >         cmpl $-1073741825,64(%esp)
- >         ja .L1423                
+ >         ja .L1423
  > .L1424:
- >         movl %edx,%eax                        
+ >         movl %edx,%eax
  >         movl 64(%esp),%ebx
  > #APP
  > 1:      movb (%ebx),%dl                /* this is the actual user access */
@@ -149,17 +149,17 @@ see what code gcc generates:
  > .L1423:
  >         movzbl %dl,%esi
 
-The optimizer does a good job and gives us something we can actually 
-understand. Can we? The actual user access is quite obvious. Thanks 
-to the unified address space we can just access the address in user 
+The optimizer does a good job and gives us something we can actually
+understand. Can we? The actual user access is quite obvious. Thanks
+to the unified address space we can just access the address in user
 memory. But what does the .section stuff do?????
 
 To understand this we have to look at the final kernel:
 
  > objdump --section-headers vmlinux
- > 
+ >
  > vmlinux:     file format elf32-i386
- > 
+ >
  > Sections:
  > Idx Name          Size      VMA       LMA       File off  Algn
  >   0 .text         00098f40  c0100000  c0100000  00001000  2**4
@@ -198,18 +198,18 @@ final kernel executable:
 
 The whole user memory access is reduced to 10 x86 machine instructions.
 The instructions bracketed in the .section directives are no longer
-in the normal execution path. They are located in a different section 
+in the normal execution path. They are located in a different section
 of the executable file:
 
  > objdump --disassemble --section=.fixup vmlinux
- > 
+ >
  > c0199ff5 <.fixup+10b5> movl   $0xfffffff2,%eax
  > c0199ffa <.fixup+10ba> xorb   %dl,%dl
  > c0199ffc <.fixup+10bc> jmp    c017e7a7 <do_con_write+e3>
 
 And finally:
  > objdump --full-contents --section=__ex_table vmlinux
- > 
+ >
  >  c01aa7c4 93c017c0 e09f19c0 97c017c0 99c017c0  ................
  >  c01aa7d4 f6c217c0 e99f19c0 a5e717c0 f59f19c0  ................
  >  c01aa7e4 080a18c0 01a019c0 0a0a18c0 04a019c0  ................
@@ -235,8 +235,8 @@ sections in the ELF object file. So the instructions
 ended up in the .fixup section of the object file and the addresses
         .long 1b,3b
 ended up in the __ex_table section of the object file. 1b and 3b
-are local labels. The local label 1b (1b stands for next label 1 
-backward) is the address of the instruction that might fault, i.e. 
+are local labels. The local label 1b (1b stands for next label 1
+backward) is the address of the instruction that might fault, i.e.
 in our case the address of the label 1 is c017e7a5:
 the original assembly code: > 1:      movb (%ebx),%dl
 and linked in vmlinux     : > c017e7a5 <do_con_write+e1> movb   (%ebx),%dl
@@ -254,7 +254,7 @@ The assembly code
 becomes the value pair
  >  c01aa7d4 c017c2f6 c0199fe9 c017e7a5 c0199ff5  ................
                                ^this is ^this is
-                               1b       3b 
+                               1b       3b
 c017e7a5,c0199ff5 in the exception table of the kernel.
 
 So, what actually happens if a fault from kernel mode with no suitable
@@ -266,9 +266,9 @@ vma occurs?
 3.) CPU calls do_page_fault
 4.) do page fault calls search_exception_table (regs->eip == c017e7a5);
 5.) search_exception_table looks up the address c017e7a5 in the
-    exception table (i.e. the contents of the ELF section __ex_table) 
+    exception table (i.e. the contents of the ELF section __ex_table)
     and returns the address of the associated fault handle code c0199ff5.
-6.) do_page_fault modifies its own return address to point to the fault 
+6.) do_page_fault modifies its own return address to point to the fault
     handle code and returns.
 7.) execution continues in the fault handling code.
 8.) 8a) EAX becomes -EFAULT (== -14)