1 files changed, 1 insertions, 0 deletions
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index d75788feac6..8538b88eda3 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -24,6 +24,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #define ATOM_DEBUG
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 08687e45e19..1a7f53068ec 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -11,7 +11,7 @@ DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml videobook.xml \
 	    procfs-guide.xml writing_usb_driver.xml \
 	    kernel-api.xml filesystems.xml lsm.xml usb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
-	    genericirq.xml
+	    genericirq.xml s390-drivers.xml
 
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/s390-drivers.tmpl b/Documentation/DocBook/s390-drivers.tmpl
new file mode 100644
index 00000000000..254e769282a
--- /dev/null
+++ b/Documentation/DocBook/s390-drivers.tmpl
@@ -0,0 +1,149 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="s390drivers">
+ <bookinfo>
+  <title>Writing s390 channel device drivers</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Cornelia</firstname>
+    <surname>Huck</surname>
+    <affiliation>
+     <address>
+       <email>cornelia.huck@de.ibm.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <copyright>
+   <year>2007</year>
+   <holder>IBM Corp.</holder>
+  </copyright>
+
+  <legalnotice>
+   <para>
+     This documentation is free software; you can redistribute
+     it and/or modify it under the terms of the GNU General Public
+     License as published by the Free Software Foundation; either
+     version 2 of the License, or (at your option) any later
+     version.
+   </para>
+
+   <para>
+     This program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+     MA 02111-1307 USA
+   </para>
+
+   <para>
+     For more details see the file COPYING in the source
+     distribution of Linux.
+   </para>
+  </legalnotice>
+ </bookinfo>
+
+<toc></toc>
+
+  <chapter id="intro">
+   <title>Introduction</title>
+  <para>
+    This document describes the interfaces available for device drivers that
+    drive s390 based channel attached devices. This includes interfaces for
+    interaction with the hardware and interfaces for interacting with the
+    common driver core. Those interfaces are provided by the s390 common I/O
+    layer.
+  </para>
+  <para>
+    The document assumes a familarity with the technical terms associated
+    with the s390 channel I/O architecture. For a description of this
+    architecture, please refer to the "z/Architecture: Principles of
+    Operation", IBM publication no. SA22-7832.
+  </para>
+  <para>
+    While most I/O devices on a s390 system are typically driven through the
+    channel I/O mechanism described here, there are various other methods
+    (like the diag interface). These are out of the scope of this document.
+  </para>
+  <para>
+    Some additional information can also be found in the kernel source
+    under Documentation/s390/driver-model.txt.
+  </para>
+  </chapter>
+  <chapter id="ccw">
+   <title>The ccw bus</title>
+  <para>
+	The ccw bus typically contains the majority of devices available to
+	a s390 system. Named after the channel command word (ccw), the basic
+	command structure used to address its devices, the ccw bus contains
+	so-called channel attached devices. They are addressed via subchannels,
+	visible on the css bus. A device driver, however, will never interact
+	with the subchannel directly, but only via the device on the ccw bus,
+	the ccw device.
+  </para>
+    <sect1 id="channelIO">
+     <title>I/O functions for channel-attached devices</title>
+    <para>
+      Some hardware structures have been translated into C structures for use
+      by the common I/O layer and device drivers. For more information on
+      the hardware structures represented here, please consult the Principles
+      of Operation.
+    </para>
+!Iinclude/asm-s390/cio.h
+    </sect1>
+    <sect1 id="ccwdev">
+     <title>ccw devices</title>
+    <para>
+      Devices that want to initiate channel I/O need to attach to the ccw bus.
+      Interaction with the driver core is done via the common I/O layer, which
+      provides the abstractions of ccw devices and ccw device drivers.
+    </para>
+    <para>
+      The functions that initiate or terminate channel I/O all act upon a
+      ccw device structure. Device drivers must not bypass those functions
+      or strange side effects may happen.
+    </para>
+!Iinclude/asm-s390/ccwdev.h
+!Edrivers/s390/cio/device.c
+!Edrivers/s390/cio/device_ops.c
+    </sect1>
+    <sect1 id="cmf">
+     <title>The channel-measurement facility</title>
+  <para>
+	The channel-measurement facility provides a means to collect
+	measurement data which is made available by the channel subsystem
+	for each channel attached device.
+  </para>
+!Iinclude/asm-s390/cmb.h
+!Edrivers/s390/cio/cmf.c
+    </sect1>
+  </chapter>
+
+  <chapter id="ccwgroup">
+   <title>The ccwgroup bus</title>
+  <para>
+	The ccwgroup bus only contains artificial devices, created by the user.
+	Many networking devices (e.g. qeth) are in fact composed of several
+	ccw devices (like read, write and data channel for qeth). The
+	ccwgroup bus provides a mechanism to create a meta-device which
+	contains those ccw devices as slave devices and can be associated
+	with the netdevice.
+  </para>
+   <sect1 id="ccwgroupdevices">
+    <title>ccw group devices</title>
+!Iinclude/asm-s390/ccwgroup.h
+!Edrivers/s390/cio/ccwgroup.c
+   </sect1>
+  </chapter>
+
+</book>
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index 8ee10ec8829..e79ee2db183 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -407,7 +407,7 @@ raiddev /dev/md0
 	device		/dev/hda5
 	raid-disk	0
 	device		/dev/hdb1
-	raid-disl	1
+	raid-disk	1
 
 For linear raid, just change the raid-level above to "raid-level linear", for
 mirrors, change it to "raid-level 1", and for stripe sets with parity, change
@@ -457,6 +457,8 @@ ChangeLog
 
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
 
+2.1.29:
+	- Fix a deadlock when mounting read-write.
 2.1.28:
 	- Fix a deadlock.
 2.1.27:
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 9f08dab1e75..d9d832c010e 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -1,4 +1,4 @@
-NOTE:
+NOTE:
 This is a version of Documentation/HOWTO translated into Japanese.
 This document is maintained by Tsugikazu Shibata <tshibata@ab.jp.nec.com>
 and the JF Project team <www.linux.or.jp/JF>.
@@ -11,14 +11,14 @@ for non English (read: Japanese) speakers and is not intended as a
 fork. So if you have any comments or updates for this file, please try
 to update the original English file first.
 
-Last Updated: 2007/07/18
+Last Updated: 2007/09/23
 ==================================
 これは、
-linux-2.6.22/Documentation/HOWTO
+linux-2.6.23/Documentation/HOWTO
 の和訳です。
 
 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2007/07/16
+翻訳日： 2007/09/19
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： 松倉さん <nbh--mats at nifty dot com>
          小林 雅典さん (Masanori Kobayasi) <zap03216 at nifty dot ne dot jp>
@@ -27,6 +27,7 @@ linux-2.6.22/Documentation/HOWTO
          野口さん (Kenji Noguchi) <tokyo246 at gmail dot com>
          河内さん (Takayoshi Kochi) <t-kochi at bq dot jp dot nec dot com>
          岩本さん (iwamoto) <iwamoto.kn at ncos dot nec dot co dot jp>
+         内田さん (Satoshi Uchida) <s-uchida at ap dot jp dot nec dot com>
 ==================================
 
 Linux カーネル開発のやり方
@@ -40,7 +41,7 @@ Linux カーネル開発コミュニティと共に活動するやり方を学�
 手助けになります。
 
 もし、このドキュメントのどこかが古くなっていた場合には、このドキュメン
-トの最後にリストしたメンテナーにパッチを送ってください。
+トの最後にリストしたメンテナにパッチを送ってください。
 
 はじめに
 ---------
@@ -59,7 +60,7 @@ Linux カーネル開発コミュニティと共に活動するやり方を学�
 ネル開発者には必要です。アーキテクチャ向けの低レベル部分の開発をするの
 でなければ、(どんなアーキテクチャでも)アセンブリ(訳注: 言語)は必要あり
 ません。以下の本は、C 言語の十分な知識や何年もの経験に取って代わるもの
-ではありませんが、少なくともリファレンスとしてはいい本です。
+ではありませんが、少なくともリファレンスとしては良い本です。
  - "The C Programming Language" by Kernighan and Ritchie [Prentice Hall]
  -『プログラミング言語Ｃ第2版』(B.W. カーニハン/D.M. リッチー著 石田晴久訳) [共立出版]
  - "Practical C Programming" by Steve Oualline [O'Reilly]
@@ -76,7 +77,7 @@ Linux カーネル開発コミュニティと共に活動するやり方を学�
 ときどき、カーネルがツールチェインや C 言語拡張に置いている前提がどう
 なっているのかわかりにくいことがあり、また、残念なことに決定的なリファ
 レンスは存在しません。情報を得るには、gcc の info ページ( info gcc )を
-みてください。
+見てください。
 
 あなたは既存の開発コミュニティと一緒に作業する方法を学ぼうとしているこ
 とに留意してください。そのコミュニティは、コーディング、スタイル、
@@ -92,7 +93,7 @@ Linux カーネル開発コミュニティと共に活動するやり方を学�
 
 Linux カーネルのソースコードは GPL ライセンスの下でリリースされていま
 す。ライセンスの詳細については、ソースツリーのメインディレクトリに存在
-する、COPYING のファイルをみてください。もしライセンスについてさらに質
+する、COPYING のファイルを見てください。もしライセンスについてさらに質
 問があれば、Linux Kernel メーリングリストに質問するのではなく、どうぞ
 法律家に相談してください。メーリングリストの人達は法律家ではなく、法的
 問題については彼らの声明はあてにするべきではありません。
@@ -109,7 +110,8 @@ Linux カーネルソースツリーは幅広い範囲のドキュメントを�
 新しいドキュメントファイルも追加することを勧めます。
 カーネルの変更が、カーネルがユーザ空間に公開しているインターフェイスの
 変更を引き起こす場合、その変更を説明するマニュアルページのパッチや情報
-をマニュアルページのメンテナ mtk-manpages@gmx.net に送ることを勧めます。
+をマニュアルページのメンテナ mtk-manpages@gmx.net に送ることを勧めま
+す。
 
 以下はカーネルソースツリーに含まれている読んでおくべきファイルの一覧で
 す-
@@ -117,7 +119,7 @@ Linux カーネルソースツリーは幅広い範囲のドキュメントを�
   README
     このファイルは Linuxカーネルの簡単な背景とカーネルを設定(訳注
     configure )し、生成(訳注 build )するために必要なことは何かが書かれ
-    ています。カーネルに関して初めての人はここからスタートするとよいで
+    ています。カーネルに関して初めての人はここからスタートすると良いで
     しょう。
 
   Documentation/Changes
@@ -128,7 +130,7 @@ Linux カーネルソースツリーは幅広い範囲のドキュメントを�
   Documentation/CodingStyle
     これは Linux カーネルのコーディングスタイルと背景にある理由を記述
     しています。全ての新しいコードはこのドキュメントにあるガイドライン
-    に従っていることを期待されています。大部分のメンテナーはこれらのルー
+    に従っていることを期待されています。大部分のメンテナはこれらのルー
     ルに従っているものだけを受け付け、多くの人は正しいスタイルのコード
     だけをレビューします。
 
@@ -168,16 +170,16 @@ Linux カーネルソースツリーは幅広い範囲のドキュメントを�
     支援してください。
 
   Documentation/ManagementStyle
-    このドキュメントは Linux カーネルのメンテナー達がどう行動するか、
+    このドキュメントは Linux カーネルのメンテナ達がどう行動するか、
     彼らの手法の背景にある共有されている精神について記述しています。こ
     れはカーネル開発の初心者なら（もしくは、単に興味があるだけの人でも）
-    重要です。なぜならこのドキュメントは、カーネルメンテナー達の独特な
+    重要です。なぜならこのドキュメントは、カーネルメンテナ達の独特な
     行動についての多くの誤解や混乱を解消するからです。
 
   Documentation/stable_kernel_rules.txt
     このファイルはどのように stable カーネルのリリースが行われるかのルー
     ルが記述されています。そしてこれらのリリースの中のどこかで変更を取
-    り入れてもらいたい場合に何をすればいいかが示されています。
+    り入れてもらいたい場合に何をすれば良いかが示されています。
 
   Documentation/kernel-docs.txt
 　　カーネル開発に付随する外部ドキュメントのリストです。もしあなたが
@@ -218,9 +220,9 @@ web サイトには、コードの構成、サブシステム、現在存在す�
 ここには、また、カーネルのコンパイルのやり方やパッチの当て方などの間接
 的な基本情報も記述されています。
 
-あなたがどこからスタートしてよいかわからないが、Linux カーネル開発コミュ
+あなたがどこからスタートして良いかわからないが、Linux カーネル開発コミュ
 ニティに参加して何かすることをさがしている場合には、Linux kernel
-Janitor's プロジェクトにいけばよいでしょう -
+Janitor's プロジェクトにいけば良いでしょう -
 	http://janitor.kernelnewbies.org/
 ここはそのようなスタートをするのにうってつけの場所です。ここには、
 Linux カーネルソースツリーの中に含まれる、きれいにし、修正しなければな
@@ -243,7 +245,7 @@ Linux カーネルソースツリーの中に含まれる、きれいにし、�
 自己参照方式で、索引がついた web 形式で、ソースコードを参照することが
 できます。この最新の素晴しいカーネルコードのリポジトリは以下で見つかり
 ます-
-	http://sosdg.org/~coywolf/lxr/
+	http://sosdg.org/~qiyong/lxr/
 
 開発プロセス
 -----------------------
@@ -265,9 +267,9 @@ Linux カーネルの開発プロセスは現在幾つかの異なるメイン�
 以下のとおり-
 
   - 新しいカーネルがリリースされた直後に、2週間の特別期間が設けられ、
-    この期間中に、メンテナー達は Linus に大きな差分を送ることができま
-    す。このような差分は通常 -mm カーネルに数週間含まれてきたパッチで
-    す。 大きな変更は git(カーネルのソース管理ツール、詳細は
+    この期間中に、メンテナ達は Linus に大きな差分を送ることができます。
+    このような差分は通常 -mm カーネルに数週間含まれてきたパッチです。
+    大きな変更は git(カーネルのソース管理ツール、詳細は
     http://git.or.cz/  参照) を使って送るのが好ましいやり方ですが、パッ
     チファイルの形式のまま送るのでも十分です。
 
@@ -285,6 +287,10 @@ Linux カーネルの開発プロセスは現在幾つかの異なるメイン�
     に安定した状態にあると判断したときにリリースされます。目標は毎週新
     しい -rc カーネルをリリースすることです。
 
+   - 以下の URL で各 -rc リリースに存在する既知の後戻り問題のリスト
+     が追跡されます-
+     http://kernelnewbies.org/known_regressions
+
   - このプロセスはカーネルが 「準備ができた」と考えられるまで継続しま
     す。このプロセスはだいたい 6週間継続します。
 
@@ -331,8 +337,8 @@ Andrew は個別のサブシステムカーネルツリーとパッチを全て�
 linux-kernel メーリングリストで収集された多数のパッチと同時に一つにま
 とめます。
 このツリーは新機能とパッチが検証される場となります。ある期間の間パッチ
-が -mm に入って価値を証明されたら、Andrew やサブシステムメンテナが、メ
-インラインへ入れるように Linus にプッシュします。
+が -mm に入って価値を証明されたら、Andrew やサブシステムメンテナが、
+メインラインへ入れるように Linus にプッシュします。
 
 メインカーネルツリーに含めるために Linus に送る前に、すべての新しいパッ
 チが -mm ツリーでテストされることが強く推奨されます。
@@ -460,7 +466,7 @@ MAINTAINERS ファイルにリストがありますので参照してくださ�
 せん-
 彼らはあなたのパッチの行毎にコメントを入れたいので、そのためにはそうす
 るしかありません。あなたのメールプログラムが空白やタブを圧縮しないよう
-に確認した方がいいです。最初の良いテストとしては、自分にメールを送って
+に確認した方が良いです。最初の良いテストとしては、自分にメールを送って
 みて、そのパッチを自分で当ててみることです。もしそれがうまく行かないな
 ら、あなたのメールプログラムを直してもらうか、正しく動くように変えるべ
 きです。
@@ -507,14 +513,14 @@ MAINTAINERS ファイルにリストがありますので参照してくださ�
 とも普通のことです。これはあなたのパッチが受け入れられないということで
 は *ありません*、そしてあなた自身に反対することを意味するのでも *ありま
 せん*。単に自分のパッチに対して指摘された問題を全て修正して再送すれば
-いいのです。
+良いのです。
 
 
 カーネルコミュニティと企業組織のちがい
 -----------------------------------------------------------------
 
 カーネルコミュニティは大部分の伝統的な会社の開発環境とは異ったやり方で
-動いています。以下は問題を避けるためにできるとよいことののリストです-
+動いています。以下は問題を避けるためにできると良いことのリストです-
 
   あなたの提案する変更について言うときのうまい言い方：
 
@@ -525,7 +531,7 @@ MAINTAINERS ファイルにリストがありますので参照してくださ�
     - "以下は一連の小さなパッチ群ですが..."
     - "これは典型的なマシンでの性能を向上させます.."
 
-  やめた方がいい悪い言い方：
+  やめた方が良い悪い言い方：
 
     - このやり方で AIX/ptx/Solaris ではできたので、できるはずだ
     - 私はこれを20年もの間やってきた、だから
@@ -575,10 +581,10 @@ Linux カーネルコミュニティは、一度に大量のコードの塊を�
 
 1) 小さいパッチはあなたのパッチが適用される見込みを大きくします、カー
    ネルの人達はパッチが正しいかどうかを確認する時間や労力をかけないか
-   らです。5行のパッチはメンテナがたった1秒見るだけで適用できます。し
-   かし、500行のパッチは、正しいことをレビューするのに数時間かかるかも
-   しれません(時間はパッチのサイズなどにより指数関数に比例してかかりま
-   す)
+   らです。5行のパッチはメンテナがたった1秒見るだけで適用できます。
+   しかし、500行のパッチは、正しいことをレビューするのに数時間かかるか
+   もしれません(時間はパッチのサイズなどにより指数関数に比例してかかり
+   ます)
 
    小さいパッチは何かあったときにデバッグもとても簡単になります。パッ
    チを1個1個取り除くのは、とても大きなパッチを当てた後に(かつ、何かお
@@ -587,23 +593,23 @@ Linux カーネルコミュニティは、一度に大量のコードの塊を�
 2) 小さいパッチを送るだけでなく、送るまえに、書き直して、シンプルにす
    る(もしくは、単に順番を変えるだけでも)ことも、とても重要です。
 
-以下はカーネル開発者の Al Viro のたとえ話しです：
+以下はカーネル開発者の Al Viro のたとえ話です：
 
         "生徒の数学の宿題を採点する先生のことを考えてみてください、先
-        生は生徒が解に到達するまでの試行錯誤をみたいとは思わないでしょ
-        う。先生は簡潔な最高の解をみたいのです。良い生徒はこれを知って
+        生は生徒が解に到達するまでの試行錯誤を見たいとは思わないでしょ
+        う。先生は簡潔な最高の解を見たいのです。良い生徒はこれを知って
         おり、そして最終解の前の中間作業を提出することは決してないので
         す"
 
-        カーネル開発でもこれは同じです。メンテナー達とレビューア達は、
-        問題を解決する解の背後になる思考プロセスをみたいとは思いません。
-        彼らは単純であざやかな解決方法をみたいのです。
+        カーネル開発でもこれは同じです。メンテナ達とレビューア達は、
+        問題を解決する解の背後になる思考プロセスを見たいとは思いません。
+        彼らは単純であざやかな解決方法を見たいのです。
 
 あざやかな解を説明するのと、コミュニティと共に仕事をし、未解決の仕事を
 議論することのバランスをキープするのは難しいかもしれません。
 ですから、開発プロセスの早期段階で改善のためのフィードバックをもらうよ
-うにするのもいいですが、変更点を小さい部分に分割して全体ではまだ完成し
-ていない仕事を(部分的に)取り込んでもらえるようにすることもいいことです。
+うにするのも良いですが、変更点を小さい部分に分割して全体ではまだ完成し
+ていない仕事を(部分的に)取り込んでもらえるようにすることも良いことです。
 
 また、でき上がっていないものや、"将来直す" ようなパッチを、本流に含め
 てもらうように送っても、それは受け付けられないことを理解してください。
@@ -629,7 +635,7 @@ Linux カーネルコミュニティは、一度に大量のコードの塊を�
   - テスト結果
 
 これについて全てがどのようにあるべきかについての詳細は、以下のドキュメ
-ントの ChangeLog セクションをみてください-
+ントの ChangeLog セクションを見てください-
   "The Perfect Patch"
       http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d006e8b66ff..9cbc82e37ed 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1010,6 +1010,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	meye.*=		[HW] Set MotionEye Camera parameters
 			See Documentation/video4linux/meye.txt.
 
+	mfgpt_irq=	[IA-32] Specify the IRQ to use for the
+			Multi-Function General Purpose Timers on AMD Geode
+			platforms.
+
 	mga=		[HW,DRM]
 
 	mousedev.tap_time=
@@ -1161,6 +1165,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nomce		[X86-32] Machine Check Exception
 
+	nomfgpt		[X86-32] Disable Multi-Function General Purpose
+			Timer usage (for AMD Geode machines).
+
 	noreplace-paravirt	[X86-32,PV_OPS] Don't patch paravirt_ops
 
 	noreplace-smp	[X86-32,SMP] Don't replace SMP instructions
@@ -1438,6 +1445,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	pt.		[PARIDE]
 			See Documentation/paride.txt.
 
+	pty.legacy_count=
+			[KNL] Number of legacy pty's. Overwrites compiled-in
+			default number.
+
 	quiet		[KNL] Disable most log messages
 
 	r128=		[HW,DRM]
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index 8ee49ee7c96..ca86a885ad8 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -54,7 +54,6 @@ embedded in larger data structures and replace fields they duplicate.
 
 struct kobject {
 	const char		* k_name;
-	char			name[KOBJ_NAME_LEN];
 	struct kref		kref;
 	struct list_head	entry;
 	struct kobject		* parent;
@@ -223,18 +222,15 @@ decl_subsys(devices, &ktype_device, &device_uevent_ops);
 is equivalent to doing:
 
 struct kset devices_subsys = {
-     .kobj = {
-	   .name = "devices",
-     },
      .ktype = &ktype_devices,
      .uevent_ops = &device_uevent_ops,
 };
-
+kobject_set_name(&devices_subsys, name);
 
 The objects that are registered with a subsystem that use the
 subsystem's default list must have their kset ptr set properly. These
 objects may have embedded kobjects or ksets. The
-following helpers make setting the kset easier:
+following helper makes setting the kset easier:
 
 
 kobj_set_kset_s(obj,subsys)
@@ -242,22 +238,8 @@ kobj_set_kset_s(obj,subsys)
 - Assumes that obj->kobj exists, and is a struct kobject.
 - Sets the kset of that kobject to the kset <subsys>.
 
-
-kset_set_kset_s(obj,subsys)
-
-- Assumes that obj->kset exists, and is a struct kset.
-- Sets the kset of the embedded kobject to the kset <subsys>.
-
-subsys_set_kset(obj,subsys)
-
-- Assumes obj->subsys exists, and is a struct subsystem.
-- Sets obj->subsys.kset.kobj.kset to the subsystem's embedded kset.
-
-void subsystem_init(struct kset *s);
 int subsystem_register(struct kset *s);
 void subsystem_unregister(struct kset *s);
-struct kset *subsys_get(struct kset *s);
-void kset_put(struct kset *s);
 
 These are just wrappers around the respective kset_* functions.
 
diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX
new file mode 100644
index 00000000000..3a2b96302ec
--- /dev/null
+++ b/Documentation/s390/00-INDEX
@@ -0,0 +1,26 @@
+00-INDEX
+	- this file.
+3270.ChangeLog
+	- ChangeLog for the UTS Global 3270-support patch (outdated).
+3270.txt
+	- how to use the IBM 3270 display system support.
+cds.txt
+	- s390 common device support (common I/O layer).
+CommonIO
+	- common I/O layer command line parameters, procfs and debugfs	entries
+config3270.sh
+	- example configuration for 3270 devices.
+DASD
+	- information on the DASD disk device driver.
+Debugging390.txt
+	- hints for debugging on s390 systems.
+driver-model.txt
+	- information on s390 devices and the driver model.
+monreader.txt
+	- information on accessing the z/VM monitor stream from Linux.
+s390dbf.txt
+	- information on using the s390 debug feature.
+TAPE
+	- information on the driver for channel-attached tapes.
+zfcpdump
+	- information on the s390 SCSI dump tool.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index 22f82f21bc6..86320aa3fb0 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -1,5 +1,5 @@
-S/390 common I/O-Layer - command line parameters and /proc entries
-==================================================================
+S/390 common I/O-Layer - command line parameters, procfs and debugfs entries
+============================================================================
 
 Command line parameters
 -----------------------
@@ -7,9 +7,9 @@ Command line parameters
 * cio_msg = yes | no
   
   Determines whether information on found devices and sensed device 
-  characteristics should be shown during startup, i. e. messages of the types 
-  "Detected device 0.0.4711 on subchannel 0.0.0042" and "SenseID: Device
-  0.0.4711 reports: ...".
+  characteristics should be shown during startup or when new devices are
+  found, i. e. messages of the types "Detected device 0.0.4711 on subchannel
+  0.0.0042" and "SenseID: Device 0.0.4711 reports: ...".
 
   Default is off.
 
@@ -26,8 +26,10 @@ Command line parameters
   An ignored device can be un-ignored later; see the "/proc entries"-section for
   details.
 
-  The devices must be given either as bus ids (0.0.abcd) or as hexadecimal
-  device numbers (0xabcd or abcd, for 2.4 backward compatibility).
+  The devices must be given either as bus ids (0.x.abcd) or as hexadecimal
+  device numbers (0xabcd or abcd, for 2.4 backward compatibility). If you
+  give a device number 0xabcd, it will be interpreted as 0.0.abcd.
+
   You can use the 'all' keyword to ignore all devices.
   The '!' operator will cause the I/O-layer to _not_ ignore a device.
   The command line is parsed from left to right.
@@ -81,31 +83,36 @@ Command line parameters
   will add 0.0.a000-0.0.accc and 0.0.af00-0.0.afff to the list of ignored
   devices.
 
-  The devices can be specified either by bus id (0.0.abcd) or, for 2.4 backward
-  compatibility, by the device number in hexadecimal (0xabcd or abcd).
+  The devices can be specified either by bus id (0.x.abcd) or, for 2.4 backward
+  compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
+  numbers given as 0xabcd will be interpreted as 0.0.abcd.
+
+* For some of the information present in the /proc filesystem in 2.4 (namely,
+  /proc/subchannels and /proc/chpids), see driver-model.txt.
+  Information formerly in /proc/irq_count is now in /proc/interrupts.
+
 
+debugfs entries
+---------------
 
-* /proc/s390dbf/cio_*/ (S/390 debug feature)
+* /sys/kernel/debug/s390dbf/cio_*/ (S/390 debug feature)
 
   Some views generated by the debug feature to hold various debug outputs.
 
-  - /proc/s390dbf/cio_crw/sprintf
+  - /sys/kernel/debug/s390dbf/cio_crw/sprintf
     Messages from the processing of pending channel report words (machine check
-    handling), which will also show when CONFIG_DEBUG_CRW is defined.
+    handling).
 
-  - /proc/s390dbf/cio_msg/sprintf
-    Various debug messages from the common I/O-layer; generally, messages which 
-    will also show when CONFIG_DEBUG_IO is defined.
+  - /sys/kernel/debug/s390dbf/cio_msg/sprintf
+    Various debug messages from the common I/O-layer, including messages
+    printed when cio_msg=yes.
 
-  - /proc/s390dbf/cio_trace/hex_ascii
+  - /sys/kernel/debug/s390dbf/cio_trace/hex_ascii
     Logs the calling of functions in the common I/O-layer and, if applicable, 
     which subchannel they were called for, as well as dumps of some data
     structures (like irb in an error case).
 
   The level of logging can be changed to be more or less verbose by piping to 
-  /proc/s390dbf/cio_*/level a number between 0 and 6; see the documentation on
-  the S/390 debug feature (Documentation/s390/s390dbf.txt) for details.
-
-* For some of the information present in the /proc filesystem in 2.4 (namely,
-  /proc/subchannels and /proc/chpids), see driver-model.txt.
-  Information formerly in /proc/irq_count is now in /proc/interrupts.
+  /sys/kernel/debug/s390dbf/cio_*/level a number between 0 and 6; see the
+  documentation on the S/390 debug feature (Documentation/s390/s390dbf.txt)
+  for details.
diff --git a/Documentation/s390/cds.txt b/Documentation/s390/cds.txt
index 58919d6a593..3081927cc2d 100644
--- a/Documentation/s390/cds.txt
+++ b/Documentation/s390/cds.txt
@@ -286,10 +286,10 @@ first:
             timeout value
 -EIO:       the common I/O layer terminated the request due to an error state
 
-If the concurrent sense flag in the extended status word in the irb is set, the
-field irb->scsw.count describes the number of device specific sense bytes
-available in the extended control word irb->scsw.ecw[0]. No device sensing by
-the device driver itself is required.
+If the concurrent sense flag in the extended status word (esw) in the irb is
+set, the field erw.scnt in the esw describes the number of device specific
+sense bytes available in the extended control word irb->scsw.ecw[]. No device
+sensing by the device driver itself is required.
 
 The device interrupt handler can use the following definitions to investigate
 the primary unit check source coded in sense byte 0 :
diff --git a/Documentation/usb/authorization.txt b/Documentation/usb/authorization.txt
new file mode 100644
index 00000000000..2af40060949
--- /dev/null
+++ b/Documentation/usb/authorization.txt
@@ -0,0 +1,92 @@
+
+Authorizing (or not) your USB devices to connect to the system
+
+(C) 2007 Inaky Perez-Gonzalez <inaky@linux.intel.com> Intel Corporation
+
+This feature allows you to control if a USB device can be used (or
+not) in a system. This feature will allow you to implement a lock-down
+of USB devices, fully controlled by user space.
+
+As of now, when a USB device is connected it is configured and
+it's interfaces inmediately made available to the users. With this
+modification, only if root authorizes the device to be configured will
+then it be possible to use it.
+
+Usage:
+
+Authorize a device to connect:
+
+$ echo 1 > /sys/usb/devices/DEVICE/authorized
+
+Deauthorize a device:
+
+$ echo 0 > /sys/usb/devices/DEVICE/authorized
+
+Set new devices connected to hostX to be deauthorized by default (ie:
+lock down):
+
+$ echo 0 > /sys/bus/devices/usbX/authorized_default
+
+Remove the lock down:
+
+$ echo 1 > /sys/bus/devices/usbX/authorized_default
+
+By default, Wired USB devices are authorized by default to
+connect. Wireless USB hosts deauthorize by default all new connected
+devices (this is so because we need to do an authentication phase
+before authorizing).
+
+
+Example system lockdown (lame)
+-----------------------
+
+Imagine you want to implement a lockdown so only devices of type XYZ
+can be connected (for example, it is a kiosk machine with a visible
+USB port):
+
+boot up
+rc.local ->
+
+ for host in /sys/bus/devices/usb*
+ do
+    echo 0 > $host/authorized_default
+ done
+
+Hookup an script to udev, for new USB devices
+
+ if device_is_my_type $DEV
+ then
+   echo 1 > $device_path/authorized
+ done
+
+
+Now, device_is_my_type() is where the juice for a lockdown is. Just
+checking if the class, type and protocol match something is the worse
+security verification you can make (or the best, for someone willing
+to break it). If you need something secure, use crypto and Certificate
+Authentication or stuff like that. Something simple for an storage key
+could be:
+
+function device_is_my_type()
+{
+   echo 1 > authorized		# temporarily authorize it
+                                # FIXME: make sure none can mount it
+   mount DEVICENODE /mntpoint
+   sum=$(md5sum /mntpoint/.signature)
+   if [ $sum = $(cat /etc/lockdown/keysum) ]
+   then
+        echo "We are good, connected"
+        umount /mntpoint
+        # Other stuff so others can use it
+   else
+        echo 0 > authorized
+   fi
+}
+
+
+Of course, this is lame, you'd want to do a real certificate
+verification stuff with PKI, so you don't depend on a shared secret,
+etc, but you get the idea. Anybody with access to a device gadget kit
+can fake descriptors and device info. Don't trust that. You are
+welcome.
+
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
new file mode 100644
index 00000000000..97842deec47
--- /dev/null
+++ b/Documentation/usb/power-management.txt
@@ -0,0 +1,517 @@
+			Power Management for USB
+
+		 Alan Stern <stern@rowland.harvard.edu>
+
+			    October 5, 2007
+
+
+
+	What is Power Management?
+	-------------------------
+
+Power Management (PM) is the practice of saving energy by suspending
+parts of a computer system when they aren't being used.  While a
+component is "suspended" it is in a nonfunctional low-power state; it
+might even be turned off completely.  A suspended component can be
+"resumed" (returned to a functional full-power state) when the kernel
+needs to use it.  (There also are forms of PM in which components are
+placed in a less functional but still usable state instead of being
+suspended; an example would be reducing the CPU's clock rate.  This
+document will not discuss those other forms.)
+
+When the parts being suspended include the CPU and most of the rest of
+the system, we speak of it as a "system suspend".  When a particular
+device is turned off while the system as a whole remains running, we
+call it a "dynamic suspend" (also known as a "runtime suspend" or
+"selective suspend").  This document concentrates mostly on how
+dynamic PM is implemented in the USB subsystem, although system PM is
+covered to some extent (see Documentation/power/*.txt for more
+information about system PM).
+
+Note: Dynamic PM support for USB is present only if the kernel was
+built with CONFIG_USB_SUSPEND enabled.  System PM support is present
+only if the kernel was built with CONFIG_SUSPEND or CONFIG_HIBERNATION
+enabled.
+
+
+	What is Remote Wakeup?
+	----------------------
+
+When a device has been suspended, it generally doesn't resume until
+the computer tells it to.  Likewise, if the entire computer has been
+suspended, it generally doesn't resume until the user tells it to, say
+by pressing a power button or opening the cover.
+
+However some devices have the capability of resuming by themselves, or
+asking the kernel to resume them, or even telling the entire computer
+to resume.  This capability goes by several names such as "Wake On
+LAN"; we will refer to it generically as "remote wakeup".  When a
+device is enabled for remote wakeup and it is suspended, it may resume
+itself (or send a request to be resumed) in response to some external
+event.  Examples include a suspended keyboard resuming when a key is
+pressed, or a suspended USB hub resuming when a device is plugged in.
+
+
+	When is a USB device idle?
+	--------------------------
+
+A device is idle whenever the kernel thinks it's not busy doing
+anything important and thus is a candidate for being suspended.  The
+exact definition depends on the device's driver; drivers are allowed
+to declare that a device isn't idle even when there's no actual
+communication taking place.  (For example, a hub isn't considered idle
+unless all the devices plugged into that hub are already suspended.)
+In addition, a device isn't considered idle so long as a program keeps
+its usbfs file open, whether or not any I/O is going on.
+
+If a USB device has no driver, its usbfs file isn't open, and it isn't
+being accessed through sysfs, then it definitely is idle.
+
+
+	Forms of dynamic PM
+	-------------------
+
+Dynamic suspends can occur in two ways: manual and automatic.
+"Manual" means that the user has told the kernel to suspend a device,
+whereas "automatic" means that the kernel has decided all by itself to
+suspend a device.  Automatic suspend is called "autosuspend" for
+short.  In general, a device won't be autosuspended unless it has been
+idle for some minimum period of time, the so-called idle-delay time.
+
+Of course, nothing the kernel does on its own initiative should
+prevent the computer or its devices from working properly.  If a
+device has been autosuspended and a program tries to use it, the
+kernel will automatically resume the device (autoresume).  For the
+same reason, an autosuspended device will usually have remote wakeup
+enabled, if the device supports remote wakeup.
+
+It is worth mentioning that many USB drivers don't support
+autosuspend.  In fact, at the time of this writing (Linux 2.6.23) the
+only drivers which do support it are the hub driver, kaweth, asix,
+usblp, usblcd, and usb-skeleton (which doesn't count).  If a
+non-supporting driver is bound to a device, the device won't be
+autosuspended.  In effect, the kernel pretends the device is never
+idle.
+
+We can categorize power management events in two broad classes:
+external and internal.  External events are those triggered by some
+agent outside the USB stack: system suspend/resume (triggered by
+userspace), manual dynamic suspend/resume (also triggered by
+userspace), and remote wakeup (triggered by the device).  Internal
+events are those triggered within the USB stack: autosuspend and
+autoresume.
+
+
+	The user interface for dynamic PM
+	---------------------------------
+
+The user interface for controlling dynamic PM is located in the power/
+subdirectory of each USB device's sysfs directory, that is, in
+/sys/bus/usb/devices/.../power/ where "..." is the device's ID.  The
+relevant attribute files are: wakeup, level, and autosuspend.
+
+	power/wakeup
+
+		This file is empty if the device does not support
+		remote wakeup.  Otherwise the file contains either the
+		word "enabled" or the word "disabled", and you can
+		write those words to the file.  The setting determines
+		whether or not remote wakeup will be enabled when the
+		device is next suspended.  (If the setting is changed
+		while the device is suspended, the change won't take
+		effect until the following suspend.)
+
+	power/level
+
+		This file contains one of three words: "on", "auto",
+		or "suspend".  You can write those words to the file
+		to change the device's setting.
+
+		"on" means that the device should be resumed and
+		autosuspend is not allowed.  (Of course, system
+		suspends are still allowed.)
+
+		"auto" is the normal state in which the kernel is
+		allowed to autosuspend and autoresume the device.
+
+		"suspend" means that the device should remain
+		suspended, and autoresume is not allowed.  (But remote
+		wakeup may still be allowed, since it is controlled
+		separately by the power/wakeup attribute.)
+
+	power/autosuspend
+
+		This file contains an integer value, which is the
+		number of seconds the device should remain idle before
+		the kernel will autosuspend it (the idle-delay time).
+		The default is 2.  0 means to autosuspend as soon as
+		the device becomes idle, and -1 means never to
+		autosuspend.  You can write a number to the file to
+		change the autosuspend idle-delay time.
+
+Writing "-1" to power/autosuspend and writing "on" to power/level do
+essentially the same thing -- they both prevent the device from being
+autosuspended.  Yes, this is a redundancy in the API.
+
+(In 2.6.21 writing "0" to power/autosuspend would prevent the device
+from being autosuspended; the behavior was changed in 2.6.22.  The
+power/autosuspend attribute did not exist prior to 2.6.21, and the
+power/level attribute did not exist prior to 2.6.22.)
+
+
+	Changing the default idle-delay time
+	------------------------------------
+
+The default autosuspend idle-delay time is controlled by a module
+parameter in usbcore.  You can specify the value when usbcore is
+loaded.  For example, to set it to 5 seconds instead of 2 you would
+do:
+
+	modprobe usbcore autosuspend=5
+
+Equivalently, you could add to /etc/modprobe.conf a line saying:
+
+	options usbcore autosuspend=5
+
+Some distributions load the usbcore module very early during the boot
+process, by means of a program or script running from an initramfs
+image.  To alter the parameter value you would have to rebuild that
+image.
+
+If usbcore is compiled into the kernel rather than built as a loadable
+module, you can add
+
+	usbcore.autosuspend=5
+
+to the kernel's boot command line.
+
+Finally, the parameter value can be changed while the system is
+running.  If you do:
+
+	echo 5 >/sys/module/usbcore/parameters/autosuspend
+
+then each new USB device will have its autosuspend idle-delay
+initialized to 5.  (The idle-delay values for already existing devices
+will not be affected.)
+
+Setting the initial default idle-delay to -1 will prevent any
+autosuspend of any USB device.  This is a simple alternative to
+disabling CONFIG_USB_SUSPEND and rebuilding the kernel, and it has the
+added benefit of allowing you to enable autosuspend for selected
+devices.
+
+
+	Warnings
+	--------
+
+The USB specification states that all USB devices must support power
+management.  Nevertheless, the sad fact is that many devices do not
+support it very well.  You can suspend them all right, but when you
+try to resume them they disconnect themselves from the USB bus or
+they stop working entirely.  This seems to be especially prevalent
+among printers and scanners, but plenty of other types of device have
+the same deficiency.
+
+For this reason, by default the kernel disables autosuspend (the
+power/level attribute is initialized to "on") for all devices other
+than hubs.  Hubs, at least, appear to be reasonably well-behaved in
+this regard.
+
+(In 2.6.21 and 2.6.22 this wasn't the case.  Autosuspend was enabled
+by default for almost all USB devices.  A number of people experienced
+problems as a result.)
+
+This means that non-hub devices won't be autosuspended unless the user
+or a program explicitly enables it.  As of this writing there aren't
+any widespread programs which will do this; we hope that in the near
+future device managers such as HAL will take on this added
+responsibility.  In the meantime you can always carry out the
+necessary operations by hand or add them to a udev script.  You can
+also change the idle-delay time; 2 seconds is not the best choice for
+every device.
+
+Sometimes it turns out that even when a device does work okay with
+autosuspend there are still problems.  For example, there are
+experimental patches adding autosuspend support to the usbhid driver,
+which manages keyboards and mice, among other things.  Tests with a
+number of keyboards showed that typing on a suspended keyboard, while
+causing the keyboard to do a remote wakeup all right, would
+nonetheless frequently result in lost keystrokes.  Tests with mice
+showed that some of them would issue a remote-wakeup request in
+response to button presses but not to motion, and some in response to
+neither.
+
+The kernel will not prevent you from enabling autosuspend on devices
+that can't handle it.  It is even possible in theory to damage a
+device by suspending it at the wrong time -- for example, suspending a
+USB hard disk might cause it to spin down without parking the heads.
+(Highly unlikely, but possible.)  Take care.
+
+
+	The driver interface for Power Management
+	-----------------------------------------
+
+The requirements for a USB driver to support external power management
+are pretty modest; the driver need only define
+
+	.suspend
+	.resume
+	.reset_resume
+
+methods in its usb_driver structure, and the reset_resume method is
+optional.  The methods' jobs are quite simple:
+
+	The suspend method is called to warn the driver that the
+	device is going to be suspended.  If the driver returns a
+	negative error code, the suspend will be aborted.  Normally
+	the driver will return 0, in which case it must cancel all
+	outstanding URBs (usb_kill_urb()) and not submit any more.
+
+	The resume method is called to tell the driver that the
+	device has been resumed and the driver can return to normal
+	operation.  URBs may once more be submitted.
+
+	The reset_resume method is called to tell the driver that
+	the device has been resumed and it also has been reset.
+	The driver should redo any necessary device initialization,
+	since the device has probably lost most or all of its state
+	(although the interfaces will be in the same altsettings as
+	before the suspend).
+
+The reset_resume method is used by the USB Persist facility (see
+Documentation/usb/persist.txt) and it can also be used under certain
+circumstances when CONFIG_USB_PERSIST is not enabled.  Currently, if a
+device is reset during a resume and the driver does not have a
+reset_resume method, the driver won't receive any notification about
+the resume.  Later kernels will call the driver's disconnect method;
+2.6.23 doesn't do this.
+
+USB drivers are bound to interfaces, so their suspend and resume
+methods get called when the interfaces are suspended or resumed.  In
+principle one might want to suspend some interfaces on a device (i.e.,
+force the drivers for those interface to stop all activity) without
+suspending the other interfaces.  The USB core doesn't allow this; all
+interfaces are suspended when the device itself is suspended and all
+interfaces are resumed when the device is resumed.  It isn't possible
+to suspend or resume some but not all of a device's interfaces.  The
+closest you can come is to unbind the interfaces' drivers.
+
+
+	The driver interface for autosuspend and autoresume
+	---------------------------------------------------
+
+To support autosuspend and autoresume, a driver should implement all
+three of the methods listed above.  In addition, a driver indicates
+that it supports autosuspend by setting the .supports_autosuspend flag
+in its usb_driver structure.  It is then responsible for informing the
+USB core whenever one of its interfaces becomes busy or idle.  The
+driver does so by calling these three functions:
+
+	int  usb_autopm_get_interface(struct usb_interface *intf);
+	void usb_autopm_put_interface(struct usb_interface *intf);
+	int  usb_autopm_set_interface(struct usb_interface *intf);
+
+The functions work by maintaining a counter in the usb_interface
+structure.  When intf->pm_usage_count is > 0 then the interface is
+deemed to be busy, and the kernel will not autosuspend the interface's
+device.  When intf->pm_usage_count is <= 0 then the interface is
+considered to be idle, and the kernel may autosuspend the device.
+
+(There is a similar pm_usage_count field in struct usb_device,
+associated with the device itself rather than any of its interfaces.
+This field is used only by the USB core.)
+
+The driver owns intf->pm_usage_count; it can modify the value however
+and whenever it likes.  A nice aspect of the usb_autopm_* routines is
+that the changes they make are protected by the usb_device structure's
+PM mutex (udev->pm_mutex); however drivers may change pm_usage_count
+without holding the mutex.
+
+	usb_autopm_get_interface() increments pm_usage_count and
+	attempts an autoresume if the new value is > 0 and the
+	device is suspended.
+
+	usb_autopm_put_interface() decrements pm_usage_count and
+	attempts an autosuspend if the new value is <= 0 and the
+	device isn't suspended.
+
+	usb_autopm_set_interface() leaves pm_usage_count alone.
+	It attempts an autoresume if the value is > 0 and the device
+	is suspended, and it attempts an autosuspend if the value is
+	<= 0 and the device isn't suspended.
+
+There also are a couple of utility routines drivers can use:
+
+	usb_autopm_enable() sets pm_usage_cnt to 1 and then calls
+	usb_autopm_set_interface(), which will attempt an autoresume.
+
+	usb_autopm_disable() sets pm_usage_cnt to 0 and then calls
+	usb_autopm_set_interface(), which will attempt an autosuspend.
+
+The conventional usage pattern is that a driver calls
+usb_autopm_get_interface() in its open routine and
+usb_autopm_put_interface() in its close or release routine.  But
+other patterns are possible.
+
+The autosuspend attempts mentioned above will often fail for one
+reason or another.  For example, the power/level attribute might be
+set to "on", or another interface in the same device might not be
+idle.  This is perfectly normal.  If the reason for failure was that
+the device hasn't been idle for long enough, a delayed workqueue
+routine is automatically set up to carry out the operation when the
+autosuspend idle-delay has expired.
+
+Autoresume attempts also can fail.  This will happen if power/level is
+set to "suspend" or if the device doesn't manage to resume properly.
+Unlike autosuspend, there's no delay for an autoresume.
+
+
+	Other parts of the driver interface
+	-----------------------------------
+
+Sometimes a driver needs to make sure that remote wakeup is enabled
+during autosuspend.  For example, there's not much point
+autosuspending a keyboard if the user can't cause the keyboard to do a
+remote wakeup by typing on it.  If the driver sets
+intf->needs_remote_wakeup to 1, the kernel won't autosuspend the
+device if remote wakeup isn't available or has been disabled through
+the power/wakeup attribute.  (If the device is already autosuspended,
+though, setting this flag won't cause the kernel to autoresume it.
+Normally a driver would set this flag in its probe method, at which
+time the device is guaranteed not to be autosuspended.)
+
+The usb_autopm_* routines have to run in a sleepable process context;
+they must not be called from an interrupt handler or while holding a
+spinlock.  In fact, the entire autosuspend mechanism is not well geared
+toward interrupt-driven operation.  However there is one thing a
+driver can do in an interrupt handler:
+
+	usb_mark_last_busy(struct usb_device *udev);
+
+This sets udev->last_busy to the current time.  udev->last_busy is the
+field used for idle-delay calculations; updating it will cause any
+pending autosuspend to be moved back.  The usb_autopm_* routines will
+also set the last_busy field to the current time.
+
+Calling urb_mark_last_busy() from within an URB completion handler is
+subject to races: The kernel may have just finished deciding the
+device has been idle for long enough but not yet gotten around to
+calling the driver's suspend method.  The driver would have to be
+responsible for synchronizing its suspend method with its URB
+completion handler and causing the autosuspend to fail with -EBUSY if
+an URB had completed too recently.
+
+External suspend calls should never be allowed to fail in this way,
+only autosuspend calls.  The driver can tell them apart by checking
+udev->auto_pm; this flag will be set to 1 for internal PM events
+(autosuspend or autoresume) and 0 for external PM events.
+
+Many of the ingredients in the autosuspend framework are oriented
+towards interfaces: The usb_interface structure contains the
+pm_usage_cnt field, and the usb_autopm_* routines take an interface
+pointer as their argument.  But somewhat confusingly, a few of the
+pieces (usb_mark_last_busy() and udev->auto_pm) use the usb_device
+structure instead.  Drivers need to keep this straight; they can call
+interface_to_usbdev() to find the device structure for a given
+interface.
+
+
+	Locking requirements
+	--------------------
+
+All three suspend/resume methods are always called while holding the
+usb_device's PM mutex.  For external events -- but not necessarily for
+autosuspend or autoresume -- the device semaphore (udev->dev.sem) will
+also be held.  This implies that external suspend/resume events are
+mutually exclusive with calls to probe, disconnect, pre_reset, and
+post_reset; the USB core guarantees that this is true of internal
+suspend/resume events as well.
+
+If a driver wants to block all suspend/resume calls during some
+critical section, it can simply acquire udev->pm_mutex.
+Alternatively, if the critical section might call some of the
+usb_autopm_* routines, the driver can avoid deadlock by doing:
+
+	down(&udev->dev.sem);
+	rc = usb_autopm_get_interface(intf);
+
+and at the end of the critical section:
+
+	if (!rc)
+		usb_autopm_put_interface(intf);
+	up(&udev->dev.sem);
+
+Holding the device semaphore will block all external PM calls, and the
+usb_autopm_get_interface() will prevent any internal PM calls, even if
+it fails.  (Exercise: Why?)
+
+The rules for locking order are:
+
+	Never acquire any device semaphore while holding any PM mutex.
+
+	Never acquire udev->pm_mutex while holding the PM mutex for
+	a device that isn't a descendant of udev.
+
+In other words, PM mutexes should only be acquired going up the device
+tree, and they should be acquired only after locking all the device
+semaphores you need to hold.  These rules don't matter to drivers very
+much; they usually affect just the USB core.
+
+Still, drivers do need to be careful.  For example, many drivers use a
+private mutex to synchronize their normal I/O activities with their
+disconnect method.  Now if the driver supports autosuspend then it
+must call usb_autopm_put_interface() from somewhere -- maybe from its
+close method.  It should make the call while holding the private mutex,
+since a driver shouldn't call any of the usb_autopm_* functions for an
+interface from which it has been unbound.
+
+But the usb_autpm_* routines always acquire the device's PM mutex, and
+consequently the locking order has to be: private mutex first, PM
+mutex second.  Since the suspend method is always called with the PM
+mutex held, it mustn't try to acquire the private mutex.  It has to
+synchronize with the driver's I/O activities in some other way.
+
+
+	Interaction between dynamic PM and system PM
+	--------------------------------------------
+
+Dynamic power management and system power management can interact in
+a couple of ways.
+
+Firstly, a device may already be manually suspended or autosuspended
+when a system suspend occurs.  Since system suspends are supposed to
+be as transparent as possible, the device should remain suspended
+following the system resume.  The 2.6.23 kernel obeys this principle
+for manually suspended devices but not for autosuspended devices; they
+do get resumed when the system wakes up.  (Presumably they will be
+autosuspended again after their idle-delay time expires.)  In later
+kernels this behavior will be fixed.
+
+(There is an exception.  If a device would undergo a reset-resume
+instead of a normal resume, and the device is enabled for remote
+wakeup, then the reset-resume takes place even if the device was
+already suspended when the system suspend began.  The justification is
+that a reset-resume is a kind of remote-wakeup event.  Or to put it
+another way, a device which needs a reset won't be able to generate
+normal remote-wakeup signals, so it ought to be resumed immediately.)
+
+Secondly, a dynamic power-management event may occur as a system
+suspend is underway.  The window for this is short, since system
+suspends don't take long (a few seconds usually), but it can happen.
+For example, a suspended device may send a remote-wakeup signal while
+the system is suspending.  The remote wakeup may succeed, which would
+cause the system suspend to abort.  If the remote wakeup doesn't
+succeed, it may still remain active and thus cause the system to
+resume as soon as the system suspend is complete.  Or the remote
+wakeup may fail and get lost.  Which outcome occurs depends on timing
+and on the hardware and firmware design.
+
+More interestingly, a device might undergo a manual resume or
+autoresume during system suspend.  With current kernels this shouldn't
+happen, because manual resumes must be initiated by userspace and
+autoresumes happen in response to I/O requests, but all user processes
+and I/O should be quiescent during a system suspend -- thanks to the
+freezer.  However there are plans to do away with the freezer, which
+would mean these things would become possible.  If and when this comes
+about, the USB core will carefully arrange matters so that either type
+of resume will block until the entire system has resumed.
diff --git a/Documentation/usb/usb-serial.txt b/Documentation/usb/usb-serial.txt
index 5b635ae8494..4e0b62b8566 100644
--- a/Documentation/usb/usb-serial.txt
+++ b/Documentation/usb/usb-serial.txt
@@ -428,6 +428,17 @@ Options supported:
   See http://www.uuhaus.de/linux/palmconnect.html for up-to-date
   information on this driver.
 
+Winchiphead CH341 Driver
+
+  This driver is for the Winchiphead CH341 USB-RS232 Converter. This chip
+  also implements an IEEE 1284 parallel port, I2C and SPI, but that is not
+  supported by the driver. The protocol was analyzed from the behaviour
+  of the Windows driver, no datasheet is available at present.
+  The manufacturer's website: http://www.winchiphead.com/.
+  For any questions or problems with this driver, please contact
+  frank@kingswood-consulting.co.uk.
+
+
 Generic Serial driver
 
   If your device is not one of the above listed devices, compatible with
diff --git a/Documentation/usb/usbmon.txt b/Documentation/usb/usbmon.txt
index 53ae866ae37..2917ce4ffdc 100644
--- a/Documentation/usb/usbmon.txt
+++ b/Documentation/usb/usbmon.txt
@@ -34,9 +34,12 @@ if usbmon is built into the kernel.
 Verify that bus sockets are present.
 
 # ls /sys/kernel/debug/usbmon
-1s  1t  1u  2s  2t  2u  3s  3t  3u  4s  4t  4u
+0s  0t  0u  1s  1t  1u  2s  2t  2u  3s  3t  3u  4s  4t  4u
 #
 
+Now you can choose to either use the sockets numbered '0' (to capture packets on
+all buses), and skip to step #3, or find the bus used by your device with step #2.
+
 2. Find which bus connects to the desired device
 
 Run "cat /proc/bus/usb/devices", and find the T-line which corresponds to
@@ -56,6 +59,10 @@ Bus=03 means it's bus 3.
 
 # cat /sys/kernel/debug/usbmon/3u > /tmp/1.mon.out
 
+to listen on a single bus, otherwise, to listen on all buses, type:
+
+# cat /sys/kernel/debug/usbmon/0u > /tmp/1.mon.out
+
 This process will be reading until killed. Naturally, the output can be
 redirected to a desirable location. This is preferred, because it is going
 to be quite long.
diff --git a/MAINTAINERS b/MAINTAINERS
index c4eca56ed5b..60e649ff6fd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -677,6 +677,13 @@ P:	Haavard Skinnemoen
 M:	hskinnemoen@atmel.com
 S:	Supported
 
+ATMEL USBA UDC DRIVER
+P:	Haavard Skinnemoen
+M:	hskinnemoen@atmel.com
+L:	kernel@avr32linux.org
+W:	http://avr32linux.org/twiki/bin/view/Main/AtmelUsbDeviceDriver
+S:	Supported
+
 ATMEL WIRELESS DRIVER
 P:	Simon Kelley
 M:	simon@thekelleys.org.uk
diff --git a/arch/arm/mach-imx/cpufreq.c b/arch/arm/mach-imx/cpufreq.c
index 467d899fbe7..e548ba74a4d 100644
--- a/arch/arm/mach-imx/cpufreq.c
+++ b/arch/arm/mach-imx/cpufreq.c
@@ -269,7 +269,6 @@ static int __init imx_cpufreq_driver_init(struct cpufreq_policy *policy)
 		return -EINVAL;
 
 	policy->cur = policy->min = policy->max = imx_get_speed(0);
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.min_freq = 8000;
 	policy->cpuinfo.max_freq = 200000;
 	 /* Manual states, that PLL stabilizes in two CLK32 periods */
diff --git a/arch/arm/mach-sa1100/cpu-sa1110.c b/arch/arm/mach-sa1100/cpu-sa1110.c
index 78f4c134604..36b47ff5af1 100644
--- a/arch/arm/mach-sa1100/cpu-sa1110.c
+++ b/arch/arm/mach-sa1100/cpu-sa1110.c
@@ -331,7 +331,6 @@ static int __init sa1110_cpu_init(struct cpufreq_policy *policy)
 	if (policy->cpu != 0)
 		return -EINVAL;
 	policy->cur = policy->min = policy->max = sa11x0_getspeed(0);
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.min_freq = 59000;
 	policy->cpuinfo.max_freq = 287000;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
diff --git a/arch/arm/plat-omap/cpu-omap.c b/arch/arm/plat-omap/cpu-omap.c
index a0c71dca237..c0d63b0c61c 100644
--- a/arch/arm/plat-omap/cpu-omap.c
+++ b/arch/arm/plat-omap/cpu-omap.c
@@ -108,7 +108,6 @@ static int __init omap_cpu_init(struct cpufreq_policy *policy)
 	if (policy->cpu != 0)
 		return -EINVAL;
 	policy->cur = policy->min = policy->max = omap_getspeed(0);
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.min_freq = clk_round_rate(mpu_clk, 0) / 1000;
 	policy->cpuinfo.max_freq = clk_round_rate(mpu_clk, VERY_HI_RATE) / 1000;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
diff --git a/arch/blackfin/mach-bf533/cpu.c b/arch/blackfin/mach-bf533/cpu.c
index 6fd9cfd0a31..b7a0e0fbd9a 100644
--- a/arch/blackfin/mach-bf533/cpu.c
+++ b/arch/blackfin/mach-bf533/cpu.c
@@ -118,8 +118,6 @@ static int __init __bf533_cpu_init(struct cpufreq_policy *policy)
 	if (policy->cpu != 0)
 		return -EINVAL;
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	/*Now ,only support one cpu */
 	policy->cur = bf533_getfreq(0);
diff --git a/arch/blackfin/mach-bf537/boards/generic_board.c b/arch/blackfin/mach-bf537/boards/generic_board.c
index 5e9d09eb857..6668c8e4a3f 100644
--- a/arch/blackfin/mach-bf537/boards/generic_board.c
+++ b/arch/blackfin/mach-bf537/boards/generic_board.c
@@ -40,7 +40,7 @@
 #include <linux/pata_platform.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <linux/usb_sl811.h>
+#include <linux/usb/sl811.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/reboot.h>
diff --git a/arch/blackfin/mach-bf537/boards/pnav10.c b/arch/blackfin/mach-bf537/boards/pnav10.c
index 20507e92a3a..f83a2544004 100644
--- a/arch/blackfin/mach-bf537/boards/pnav10.c
+++ b/arch/blackfin/mach-bf537/boards/pnav10.c
@@ -40,7 +40,7 @@
 #include <linux/irq.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
-#include <linux/usb_sl811.h>
+#include <linux/usb/sl811.h>
 
 #include <linux/spi/ad7877.h>
 
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index 47d7d4a0e73..f42ba3aa86d 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -40,7 +40,7 @@
 #include <linux/pata_platform.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <linux/usb_sl811.h>
+#include <linux/usb/sl811.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/reboot.h>
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 515abb98d41..f1486f8a3e6 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -1211,6 +1211,16 @@ config SCx200HR_TIMER
 	  processor goes idle (as is done by the scheduler).  The
 	  other workaround is idle=poll boot option.
 
+config GEODE_MFGPT_TIMER
+	bool "Geode Multi-Function General Purpose Timer (MFGPT) events"
+	depends on MGEODE_LX && GENERIC_TIME && GENERIC_CLOCKEVENTS
+	default y
+	help
+	  This driver provides a clock event source based on the MFGPT
+	  timer(s) in the CS5535 and CS5536 companion chip for the geode.
+	  MFGPTs have a better resolution and max interval than the
+	  generic PIT, and are suitable for use as high-res timers.
+
 config K8_NB
 	def_bool y
 	depends on AGP_AMD64
diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
index 8c6ec707084..b8498ea6206 100644
--- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
+++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
@@ -321,8 +321,6 @@ acpi_cpufreq_cpu_init (
 			    data->acpi_data.states[i].transition_latency * 1000;
 		}
 	}
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
 	policy->cur = processor_get_freq(data, policy->cpu);
 
 	/* table init */
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index 5a289e4de83..a88eba3314d 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -66,8 +66,7 @@ static int tiocx_match(struct device *dev, struct device_driver *drv)
 
 }
 
-static int tiocx_uevent(struct device *dev, char **envp, int num_envp,
-			 char *buffer, int buffer_size)
+static int tiocx_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	return -ENODEV;
 }
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index 89b911e83c0..8f3db32fac8 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -57,26 +57,21 @@ ssize_t of_device_get_modalias(struct of_device *ofdev,
 	return tsize;
 }
 
-int of_device_uevent(struct device *dev,
-		char **envp, int num_envp, char *buffer, int buffer_size)
+int of_device_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	struct of_device *ofdev;
 	const char *compat;
-	int i = 0, length = 0, seen = 0, cplen, sl;
+	int seen = 0, cplen, sl;
 
 	if (!dev)
 		return -ENODEV;
 
 	ofdev = to_of_device(dev);
 
-	if (add_uevent_var(envp, num_envp, &i,
-			   buffer, buffer_size, &length,
-			   "OF_NAME=%s", ofdev->node->name))
+	if (add_uevent_var(env, "OF_NAME=%s", ofdev->node->name))
 		return -ENOMEM;
 
-	if (add_uevent_var(envp, num_envp, &i,
-			   buffer, buffer_size, &length,
-			   "OF_TYPE=%s", ofdev->node->type))
+	if (add_uevent_var(env, "OF_TYPE=%s", ofdev->node->type))
 		return -ENOMEM;
 
         /* Since the compatible field can contain pretty much anything
@@ -85,9 +80,7 @@ int of_device_uevent(struct device *dev,
 
 	compat = of_get_property(ofdev->node, "compatible", &cplen);
 	while (compat && *compat && cplen > 0) {
-		if (add_uevent_var(envp, num_envp, &i,
-				   buffer, buffer_size, &length,
-				   "OF_COMPATIBLE_%d=%s", seen, compat))
+		if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat))
 			return -ENOMEM;
 
 		sl = strlen (compat) + 1;
@@ -96,25 +89,17 @@ int of_device_uevent(struct device *dev,
 		seen++;
 	}
 
-	if (add_uevent_var(envp, num_envp, &i,
-			   buffer, buffer_size, &length,
-			   "OF_COMPATIBLE_N=%d", seen))
+	if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen))
 		return -ENOMEM;
 
 	/* modalias is trickier, we add it in 2 steps */
-	if (add_uevent_var(envp, num_envp, &i,
-			   buffer, buffer_size, &length,
-			   "MODALIAS="))
+	if (add_uevent_var(env, "MODALIAS="))
 		return -ENOMEM;
-
-	sl = of_device_get_modalias(ofdev, &buffer[length-1],
-					buffer_size-length);
-	if (sl >= (buffer_size-length))
+	sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1],
+				    sizeof(env->buf) - env->buflen);
+	if (sl >= (sizeof(env->buf) - env->buflen))
 		return -ENOMEM;
-
-	length += sl;
-
-	envp[i] = NULL;
+	env->buflen += sl;
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index cb22a3557c4..19a5656001c 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -317,30 +317,20 @@ static int vio_bus_match(struct device *dev, struct device_driver *drv)
 	return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
 }
 
-static int vio_hotplug(struct device *dev, char **envp, int num_envp,
-			char *buffer, int buffer_size)
+static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env)
 {
 	const struct vio_dev *vio_dev = to_vio_dev(dev);
 	struct device_node *dn;
 	const char *cp;
-	int length;
-
-	if (!num_envp)
-		return -ENOMEM;
 
 	dn = dev->archdata.of_node;
 	if (!dn)
 		return -ENODEV;
-	cp = of_get_property(dn, "compatible", &length);
+	cp = of_get_property(dn, "compatible", NULL);
 	if (!cp)
 		return -ENODEV;
 
-	envp[0] = buffer;
-	length = scnprintf(buffer, buffer_size, "MODALIAS=vio:T%sS%s",
-				vio_dev->type, cp);
-	if ((buffer_size - length) <= 0)
-		return -ENOMEM;
-	envp[1] = NULL;
+	add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c
index 901236fa0f0..5123e9d4164 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c
@@ -107,8 +107,6 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		pr_debug("%d: %d\n", i, cbe_freqs[i].frequency);
 	}
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
 	/* if DEBUG is enabled set_pmode() measures the latency
 	 * of a transition */
 	policy->cpuinfo.transition_latency = 25000;
diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c
index 3ae083851b0..1cfb8b0c8fe 100644
--- a/arch/powerpc/platforms/pasemi/cpufreq.c
+++ b/arch/powerpc/platforms/pasemi/cpufreq.c
@@ -195,8 +195,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		pr_debug("%d: %d\n", i, pas_freqs[i].frequency);
 	}
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
 	policy->cpuinfo.transition_latency = get_gizmo_latency();
 
 	cur_astate = get_cur_astate(policy->cpu);
diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
index 1fe35dab0e9..c04abcc28a7 100644
--- a/arch/powerpc/platforms/powermac/cpufreq_32.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_32.c
@@ -410,7 +410,6 @@ static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (policy->cpu != 0)
 		return -ENODEV;
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency	= CPUFREQ_ETERNAL;
 	policy->cur = cur_freq;
 
diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c
index 00f50298c34..4dfb4bc242b 100644
--- a/arch/powerpc/platforms/powermac/cpufreq_64.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_64.c
@@ -357,7 +357,6 @@ static unsigned int g5_cpufreq_get_speed(unsigned int cpu)
 
 static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	policy->cur = g5_cpu_freqs[g5_query_freq()].frequency;
 	/* secondary CPUs are tied to the primary one by the
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 4bb634a17e4..ea0b2c79041 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -437,18 +437,13 @@ static void ps3_system_bus_shutdown(struct device *_dev)
 	dev_dbg(&dev->core, " <- %s:%d\n", __func__, __LINE__);
 }
 
-static int ps3_system_bus_uevent(struct device *_dev, char **envp,
-				 int num_envp, char *buffer, int buffer_size)
+static int ps3_system_bus_uevent(struct device *_dev, struct kobj_uevent_env *env)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int i = 0, length = 0;
 
-	if (add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
-			   &length, "MODALIAS=ps3:%d",
-			   dev->match_id))
+	if (add_uevent_var(env, "MODALIAS=ps3:%d", dev->match_id))
 		return -ENOMEM;
-
-	envp[i] = NULL;
 	return 0;
 }
 
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 62391fb1f61..ac61cf43a7d 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -547,8 +547,7 @@ static void __cpuinit appldata_online_cpu(int cpu)
 	spin_unlock(&appldata_timer_lock);
 }
 
-static void
-appldata_offline_cpu(int cpu)
+static void __cpuinit appldata_offline_cpu(int cpu)
 {
 	del_virt_timer(&per_cpu(appldata_timer, cpu));
 	if (atomic_dec_and_test(&appldata_expire_count)) {
@@ -560,9 +559,9 @@ appldata_offline_cpu(int cpu)
 	spin_unlock(&appldata_timer_lock);
 }
 
-static int __cpuinit
-appldata_cpu_notify(struct notifier_block *self,
-		    unsigned long action, void *hcpu)
+static int __cpuinit appldata_cpu_notify(struct notifier_block *self,
+					 unsigned long action,
+					 void *hcpu)
 {
 	switch (action) {
 	case CPU_ONLINE:
@@ -608,63 +607,15 @@ static int __init appldata_init(void)
 	register_hotcpu_notifier(&appldata_nb);
 
 	appldata_sysctl_header = register_sysctl_table(appldata_dir_table);
-#ifdef MODULE
-	appldata_dir_table[0].de->owner = THIS_MODULE;
-	appldata_table[0].de->owner = THIS_MODULE;
-	appldata_table[1].de->owner = THIS_MODULE;
-#endif
 
 	P_DEBUG("Base interface initialized.\n");
 	return 0;
 }
 
-/*
- * appldata_exit()
- *
- * stop timer, unregister /proc entries
- */
-static void __exit appldata_exit(void)
-{
-	struct list_head *lh;
-	struct appldata_ops *ops;
-	int rc, i;
+__initcall(appldata_init);
 
-	P_DEBUG("Unloading module ...\n");
-	/*
-	 * ops list should be empty, but just in case something went wrong...
-	 */
-	spin_lock(&appldata_ops_lock);
-	list_for_each(lh, &appldata_ops_list) {
-		ops = list_entry(lh, struct appldata_ops, list);
-		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
-				(unsigned long) ops->data, ops->size,
-				ops->mod_lvl);
-		if (rc != 0) {
-			P_ERROR("STOP DIAG 0xDC for %s failed, "
-				"return code: %d\n", ops->name, rc);
-		}
-	}
-	spin_unlock(&appldata_ops_lock);
-
-	for_each_online_cpu(i)
-		appldata_offline_cpu(i);
-
-	appldata_timer_active = 0;
-
-	unregister_sysctl_table(appldata_sysctl_header);
-
-	destroy_workqueue(appldata_wq);
-	P_DEBUG("... module unloaded!\n");
-}
 /**************************** init / exit <END> ******************************/
 
-
-module_init(appldata_init);
-module_exit(appldata_exit);
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Gerald Schaefer");
-MODULE_DESCRIPTION("Linux-VM Monitor Stream, base infrastructure");
-
 EXPORT_SYMBOL_GPL(appldata_register_ops);
 EXPORT_SYMBOL_GPL(appldata_unregister_ops);
 EXPORT_SYMBOL_GPL(appldata_diag);
diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c
index d1c76fe10f2..f4932c22ebe 100644
--- a/arch/s390/kernel/audit.c
+++ b/arch/s390/kernel/audit.c
@@ -2,6 +2,7 @@
 #include <linux/types.h>
 #include <linux/audit.h>
 #include <asm/unistd.h>
+#include "audit.h"
 
 static unsigned dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
@@ -40,7 +41,6 @@ int audit_classify_arch(int arch)
 int audit_classify_syscall(int abi, unsigned syscall)
 {
 #ifdef CONFIG_COMPAT
-	extern int s390_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_S390)
 		return s390_classify_syscall(syscall);
 #endif
@@ -61,11 +61,6 @@ int audit_classify_syscall(int abi, unsigned syscall)
 static int __init audit_classes_init(void)
 {
 #ifdef CONFIG_COMPAT
-	extern __u32 s390_dir_class[];
-	extern __u32 s390_write_class[];
-	extern __u32 s390_read_class[];
-	extern __u32 s390_chattr_class[];
-	extern __u32 s390_signal_class[];
 	audit_register_class(AUDIT_CLASS_WRITE_32, s390_write_class);
 	audit_register_class(AUDIT_CLASS_READ_32, s390_read_class);
 	audit_register_class(AUDIT_CLASS_DIR_WRITE_32, s390_dir_class);
diff --git a/arch/s390/kernel/audit.h b/arch/s390/kernel/audit.h
new file mode 100644
index 00000000000..12b56f4b5a7
--- /dev/null
+++ b/arch/s390/kernel/audit.h
@@ -0,0 +1,15 @@
+#ifndef __ARCH_S390_KERNEL_AUDIT_H
+#define __ARCH_S390_KERNEL_AUDIT_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_COMPAT
+extern int s390_classify_syscall(unsigned);
+extern __u32 s390_dir_class[];
+extern __u32 s390_write_class[];
+extern __u32 s390_read_class[];
+extern __u32 s390_chattr_class[];
+extern __u32 s390_signal_class[];
+#endif /* CONFIG_COMPAT */
+
+#endif /* __ARCH_S390_KERNEL_AUDIT_H */
diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c
index 0569f5126e4..d6487bf879e 100644
--- a/arch/s390/kernel/compat_audit.c
+++ b/arch/s390/kernel/compat_audit.c
@@ -1,5 +1,6 @@
 #undef __s390x__
 #include <asm/unistd.h>
+#include "audit.h"
 
 unsigned s390_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 6c89f30c8e3..d8c1131e081 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/cpcmd.c
  *
  *  S390 version
- *    Copyright (C) 1999,2005 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Copyright IBM Corp. 1999,2007
  *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
  *               Christian Borntraeger (cborntra@de.ibm.com),
  */
@@ -21,6 +21,49 @@
 static DEFINE_SPINLOCK(cpcmd_lock);
 static char cpcmd_buf[241];
 
+static int diag8_noresponse(int cmdlen)
+{
+	register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
+	register unsigned long reg3 asm ("3") = cmdlen;
+
+	asm volatile(
+#ifndef CONFIG_64BIT
+		"	diag	%1,%0,0x8\n"
+#else /* CONFIG_64BIT */
+		"	sam31\n"
+		"	diag	%1,%0,0x8\n"
+		"	sam64\n"
+#endif /* CONFIG_64BIT */
+		: "+d" (reg3) : "d" (reg2) : "cc");
+	return reg3;
+}
+
+static int diag8_response(int cmdlen, char *response, int *rlen)
+{
+	register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
+	register unsigned long reg3 asm ("3") = (addr_t) response;
+	register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
+	register unsigned long reg5 asm ("5") = *rlen;
+
+	asm volatile(
+#ifndef CONFIG_64BIT
+		"	diag	%2,%0,0x8\n"
+		"	brc	8,1f\n"
+		"	ar	%1,%4\n"
+#else /* CONFIG_64BIT */
+		"	sam31\n"
+		"	diag	%2,%0,0x8\n"
+		"	sam64\n"
+		"	brc	8,1f\n"
+		"	agr	%1,%4\n"
+#endif /* CONFIG_64BIT */
+		"1:\n"
+		: "+d" (reg4), "+d" (reg5)
+		: "d" (reg2), "d" (reg3), "d" (*rlen) : "cc");
+	*rlen = reg5;
+	return reg4;
+}
+
 /*
  * __cpcmd has some restrictions over cpcmd
  *  - the response buffer must reside below 2GB (if any)
@@ -28,59 +71,27 @@ static char cpcmd_buf[241];
  */
 int  __cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 {
-	unsigned cmdlen;
-	int return_code, return_len;
+	int cmdlen;
+	int rc;
+	int response_len;
 
 	cmdlen = strlen(cmd);
 	BUG_ON(cmdlen > 240);
 	memcpy(cpcmd_buf, cmd, cmdlen);
 	ASCEBC(cpcmd_buf, cmdlen);
 
-	if (response != NULL && rlen > 0) {
-		register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
-		register unsigned long reg3 asm ("3") = (addr_t) response;
-		register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
-		register unsigned long reg5 asm ("5") = rlen;
-
+	if (response) {
 		memset(response, 0, rlen);
-		asm volatile(
-#ifndef CONFIG_64BIT
-			"	diag	%2,%0,0x8\n"
-			"	brc	8,1f\n"
-			"	ar	%1,%4\n"
-#else /* CONFIG_64BIT */
-			"	sam31\n"
-			"	diag	%2,%0,0x8\n"
-			"	sam64\n"
-			"	brc	8,1f\n"
-			"	agr	%1,%4\n"
-#endif /* CONFIG_64BIT */
-			"1:\n"
-			: "+d" (reg4), "+d" (reg5)
-			: "d" (reg2), "d" (reg3), "d" (rlen) : "cc");
-		return_code = (int) reg4;
-		return_len = (int) reg5;
-                EBCASC(response, rlen);
+		response_len = rlen;
+		rc = diag8_response(cmdlen, response, &rlen);
+		EBCASC(response, response_len);
         } else {
-		register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
-		register unsigned long reg3 asm ("3") = cmdlen;
-		return_len = 0;
-		asm volatile(
-#ifndef CONFIG_64BIT
-			"	diag	%1,%0,0x8\n"
-#else /* CONFIG_64BIT */
-			"	sam31\n"
-			"	diag	%1,%0,0x8\n"
-			"	sam64\n"
-#endif /* CONFIG_64BIT */
-			: "+d" (reg3) : "d" (reg2) : "cc");
-		return_code = (int) reg3;
+		rc = diag8_noresponse(cmdlen);
         }
-	if (response_code != NULL)
-		*response_code = return_code;
-	return return_len;
+	if (response_code)
+		*response_code = rc;
+	return rlen;
 }
-
 EXPORT_SYMBOL(__cpcmd);
 
 int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
@@ -109,5 +120,4 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 	}
 	return len;
 }
-
 EXPORT_SYMBOL(cpcmd);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 50d2235df73..c14a336f630 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1162,6 +1162,7 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 	unsigned int value;
 	char separator;
 	char *ptr;
+	int i;
 
 	ptr = buffer;
 	insn = find_insn(code);
@@ -1169,7 +1170,8 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 		ptr += sprintf(ptr, "%.5s\t", insn->name);
 		/* Extract the operands. */
 		separator = 0;
-		for (ops = formats[insn->format] + 1; *ops != 0; ops++) {
+		for (ops = formats[insn->format] + 1, i = 0;
+		     *ops != 0 && i < 6; ops++, i++) {
 			operand = operands + *ops;
 			value = extract_operand(code, operand);
 			if ((operand->flags & OPERAND_INDEX)  && value == 0)
@@ -1241,7 +1243,6 @@ void show_code(struct pt_regs *regs)
 	}
 	/* Find a starting point for the disassembly. */
 	while (start < 32) {
-		hops = 0;
 		for (i = 0, hops = 0; start + i < 32 && hops < 3; hops++) {
 			if (!find_insn(code + start + i))
 				break;
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 8b8f136d9cc..66b51901c87 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -735,10 +735,10 @@ void do_reipl(void)
 	case REIPL_METHOD_CCW_VM:
 		reipl_get_ascii_loadparm(loadparm);
 		if (strlen(loadparm) == 0)
-			sprintf(buf, "IPL %X",
+			sprintf(buf, "IPL %X CLEAR",
 				reipl_block_ccw->ipl_info.ccw.devno);
 		else
-			sprintf(buf, "IPL %X LOADPARM '%s'",
+			sprintf(buf, "IPL %X CLEAR LOADPARM '%s'",
 				reipl_block_ccw->ipl_info.ccw.devno, loadparm);
 		__cpcmd(buf, NULL, 0, NULL);
 		break;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index b4622a3889b..849120e3e28 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -2,6 +2,7 @@
  * Written by Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
+#include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
 
 #ifndef CONFIG_64BIT
@@ -18,121 +19,142 @@ jiffies = jiffies_64;
 
 SECTIONS
 {
-  . = 0x00000000;
-  _text = .;			/* Text and read-only data */
-  .text : {
-	*(.text.head)
+	. = 0x00000000;
+	.text : {
+	_text = .;		/* Text and read-only data */
+		*(.text.head)
 	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	KPROBES_TEXT
-	*(.fixup)
-	*(.gnu.warning)
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		*(.fixup)
+		*(.gnu.warning)
 	} = 0x0700
 
-  _etext = .;			/* End of text section */
+	_etext = .;		/* End of text section */
 
-  RODATA
+	RODATA
 
 #ifdef CONFIG_SHARED_KERNEL
-  . = ALIGN(1048576);		/* VM shared segments are 1MB aligned */
+	. = ALIGN(0x100000);	/* VM shared segments are 1MB aligned */
 #endif
 
-  . = ALIGN(4096);
-  _eshared = .;			/* End of shareable data */
-
-  . = ALIGN(16);		/* Exception table */
-  __start___ex_table = .;
-  __ex_table : { *(__ex_table) }
-  __stop___ex_table = .;
-
-  NOTES
-
-  BUG_TABLE
-
-  .data : {			/* Data */
-	DATA_DATA
-	CONSTRUCTORS
-	}
-
-  . = ALIGN(4096);
-  __nosave_begin = .;
-  .data_nosave : { *(.data.nosave) }
-  . = ALIGN(4096);
-  __nosave_end = .;
-
-  . = ALIGN(4096);
-  .data.page_aligned : { *(.data.idt) }
-
-  . = ALIGN(256);
-  .data.cacheline_aligned : { *(.data.cacheline_aligned) }
-
-  . = ALIGN(256);
-  .data.read_mostly : { *(.data.read_mostly) }
-  _edata = .;			/* End of data section */
-
-  . = ALIGN(8192);		/* init_task */
-  .data.init_task : { *(.data.init_task) }
-
-  /* will be freed after init */
-  . = ALIGN(4096);		/* Init code and data */
-  __init_begin = .;
-  .init.text : { 
-	_sinittext = .;
-	*(.init.text)
-	_einittext = .;
-  }
-  /*
-   * .exit.text is discarded at runtime, not link time,
-   * to deal with references from __bug_table
-   */
-  .exit.text :	 { *(.exit.text) }
-
-  .init.data : { *(.init.data) }
-  . = ALIGN(256);
-  __setup_start = .;
-  .init.setup : { *(.init.setup) }
-  __setup_end = .;
-  __initcall_start = .;
-  .initcall.init : {
-	INITCALLS
-  }
-  __initcall_end = .;
-  __con_initcall_start = .;
-  .con_initcall.init : { *(.con_initcall.init) }
-  __con_initcall_end = .;
-  SECURITY_INIT
+	. = ALIGN(PAGE_SIZE);
+	_eshared = .;		/* End of shareable data */
+
+	. = ALIGN(16);		/* Exception table */
+	__ex_table : {
+		__start___ex_table = .;
+		*(__ex_table)
+		__stop___ex_table = .;
+	}
+
+	NOTES
+	BUG_TABLE
+
+	.data : {		/* Data */
+		DATA_DATA
+		CONSTRUCTORS
+	}
+
+	. = ALIGN(PAGE_SIZE);
+	.data_nosave : {
+	__nosave_begin = .;
+		*(.data.nosave)
+	}
+	. = ALIGN(PAGE_SIZE);
+	__nosave_end = .;
+
+	. = ALIGN(PAGE_SIZE);
+	.data.page_aligned : {
+		*(.data.idt)
+	}
+
+	. = ALIGN(0x100);
+	.data.cacheline_aligned : {
+		*(.data.cacheline_aligned)
+	}
+
+	. = ALIGN(0x100);
+	.data.read_mostly : {
+		*(.data.read_mostly)
+	}
+	_edata = .;		/* End of data section */
+
+	. = ALIGN(2 * PAGE_SIZE);	/* init_task */
+	.data.init_task : {
+		*(.data.init_task)
+	}
+
+	/* will be freed after init */
+	. = ALIGN(PAGE_SIZE);	/* Init code and data */
+	__init_begin = .;
+	.init.text : {
+		_sinittext = .;
+		*(.init.text)
+		_einittext = .;
+	}
+	/*
+	 * .exit.text is discarded at runtime, not link time,
+	 * to deal with references from __bug_table
+	*/
+	.exit.text : {
+		*(.exit.text)
+	}
+
+	.init.data : {
+		*(.init.data)
+	}
+	. = ALIGN(0x100);
+	.init.setup : {
+		__setup_start = .;
+		*(.init.setup)
+		__setup_end = .;
+	}
+	.initcall.init : {
+		__initcall_start = .;
+		INITCALLS
+		__initcall_end = .;
+	}
+
+	.con_initcall.init : {
+		__con_initcall_start = .;
+		*(.con_initcall.init)
+		__con_initcall_end = .;
+	}
+	SECURITY_INIT
 
 #ifdef CONFIG_BLK_DEV_INITRD
-  . = ALIGN(256);
-  __initramfs_start = .;
-  .init.ramfs : { *(.init.initramfs) }
-  . = ALIGN(2);
-  __initramfs_end = .;
+	. = ALIGN(0x100);
+	.init.ramfs : {
+		__initramfs_start = .;
+		*(.init.ramfs)
+		. = ALIGN(2);
+		__initramfs_end = .;
+	}
 #endif
-  PERCPU(4096)
-  . = ALIGN(4096);
-  __init_end = .;
-  /* freed after init ends here */
-
-  __bss_start = .;		/* BSS */
-  .bss : { *(.bss) }
-  . = ALIGN(2);
-  __bss_stop = .;
-
-  _end = . ;
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	*(.exit.data) *(.exitcall.exit)
-	}
-
-  /* Stabs debugging sections.  */
-  .stab 0 : { *(.stab) }
-  .stabstr 0 : { *(.stabstr) }
-  .stab.excl 0 : { *(.stab.excl) }
-  .stab.exclstr 0 : { *(.stab.exclstr) }
-  .stab.index 0 : { *(.stab.index) }
-  .stab.indexstr 0 : { *(.stab.indexstr) }
-  .comment 0 : { *(.comment) }
+
+	PERCPU(PAGE_SIZE)
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;		/* freed after init ends here */
+
+	/* BSS */
+	.bss : {
+		__bss_start = .;
+		*(.bss)
+		. = ALIGN(2);
+		__bss_stop = .;
+	}
+
+	_end = . ;
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.exit.data)
+		*(.exitcall.exit)
+	}
+
+	/* Debugging sections.	*/
+	STABS_DEBUG
+	DWARF_DEBUG
 }
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 54055194e9a..4c1ac341ec8 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -468,7 +468,7 @@ typedef struct {
 	__u64 refselmk;
 	__u64 refcmpmk;
 	__u64 reserved;
-} __attribute__ ((packed)) pfault_refbk_t;
+} __attribute__ ((packed, aligned(8))) pfault_refbk_t;
 
 int pfault_init(void)
 {
diff --git a/arch/sh/kernel/cpufreq.c b/arch/sh/kernel/cpufreq.c
index e61890217c5..71d1c427b90 100644
--- a/arch/sh/kernel/cpufreq.c
+++ b/arch/sh/kernel/cpufreq.c
@@ -93,7 +93,6 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.max_freq = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 
-	policy->governor	= CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cur		= sh_cpufreq_get(policy->cpu);
 	policy->min		= policy->cpuinfo.min_freq;
 	policy->max		= policy->cpuinfo.max_freq;
diff --git a/arch/sparc64/kernel/us2e_cpufreq.c b/arch/sparc64/kernel/us2e_cpufreq.c
index 1f83fe6a82d..791c15138f3 100644
--- a/arch/sparc64/kernel/us2e_cpufreq.c
+++ b/arch/sparc64/kernel/us2e_cpufreq.c
@@ -326,7 +326,6 @@ static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy)
 	table[2].index = 5;
 	table[3].frequency = CPUFREQ_TABLE_END;
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 0;
 	policy->cur = clock_tick;
 
diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32
index c624193740f..7ff02063b85 100644
--- a/arch/x86/kernel/Makefile_32
+++ b/arch/x86/kernel/Makefile_32
@@ -7,7 +7,7 @@ extra-y := head_32.o init_task_32.o vmlinux.lds
 obj-y	:= process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \
 		ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \
 		pci-dma_32.o i386_ksyms_32.o i387_32.o bootflag.o e820_32.o\
-		quirks.o i8237.o topology.o alternative.o i8253_32.o tsc_32.o
+		quirks.o i8237.o topology.o alternative.o i8253.o tsc_32.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-y				+= cpu/
@@ -37,9 +37,9 @@ obj-$(CONFIG_EFI) 		+= efi_32.o efi_stub_32.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_HPET_TIMER) 	+= hpet_32.o
+obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
-obj-$(CONFIG_MGEODE_LX)		+= geode_32.o
+obj-$(CONFIG_MGEODE_LX)		+= geode_32.o mfgpt_32.o
 
 obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt_32.o
diff --git a/arch/x86/kernel/Makefile_64 b/arch/x86/kernel/Makefile_64
index 3ab017a0a3b..43da66213a4 100644
--- a/arch/x86/kernel/Makefile_64
+++ b/arch/x86/kernel/Makefile_64
@@ -8,8 +8,8 @@ obj-y	:= process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \
 		ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \
 		x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \
 		setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \
-		pci-dma_64.o pci-nommu_64.o alternative.o hpet_64.o tsc_64.o bugs_64.o \
-		perfctr-watchdog.o
+		pci-dma_64.o pci-nommu_64.o alternative.o hpet.o tsc_64.o bugs_64.o \
+		perfctr-watchdog.o i8253.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_X86_MCE)		+= mce_64.o therm_throt.o
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 925758dbca0..395928de28e 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -25,6 +25,7 @@
 #include <linux/sysdev.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
+#include <linux/clockchips.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -39,12 +40,9 @@
 #include <asm/hpet.h>
 #include <asm/apic.h>
 
-int apic_mapped;
 int apic_verbosity;
-int apic_runs_main_timer;
-int apic_calibrate_pmtmr __initdata;
-
-int disable_apic_timer __initdata;
+int disable_apic_timer __cpuinitdata;
+static int apic_calibrate_pmtmr __initdata;
 
 /* Local APIC timer works in C2? */
 int local_apic_timer_c2_ok;
@@ -56,14 +54,78 @@ static struct resource lapic_resource = {
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
 };
 
+static unsigned int calibration_result;
+
+static int lapic_next_event(unsigned long delta,
+			    struct clock_event_device *evt);
+static void lapic_timer_setup(enum clock_event_mode mode,
+			      struct clock_event_device *evt);
+
+static void lapic_timer_broadcast(cpumask_t mask);
+
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen);
+
+static struct clock_event_device lapic_clockevent = {
+	.name		= "lapic",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
+			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
+	.shift		= 32,
+	.set_mode	= lapic_timer_setup,
+	.set_next_event	= lapic_next_event,
+	.broadcast	= lapic_timer_broadcast,
+	.rating		= 100,
+	.irq		= -1,
+};
+static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
+
+static int lapic_next_event(unsigned long delta,
+			    struct clock_event_device *evt)
+{
+	apic_write(APIC_TMICT, delta);
+	return 0;
+}
+
+static void lapic_timer_setup(enum clock_event_mode mode,
+			      struct clock_event_device *evt)
+{
+	unsigned long flags;
+	unsigned int v;
+
+	/* Lapic used as dummy for broadcast ? */
+	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+		return;
+
+	local_irq_save(flags);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+	case CLOCK_EVT_MODE_ONESHOT:
+		__setup_APIC_LVTT(calibration_result,
+				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		v = apic_read(APIC_LVTT);
+		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+		apic_write(APIC_LVTT, v);
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		/* Nothing to do here */
+		break;
+	}
+
+	local_irq_restore(flags);
+}
+
 /*
- * cpu_mask that denotes the CPUs that needs timer interrupt coming in as
- * IPIs in place of local APIC timers
+ * Local APIC timer broadcast function
  */
-static cpumask_t timer_interrupt_broadcast_ipi_mask;
-
-/* Using APIC to generate smp_local_timer_interrupt? */
-int using_apic_timer __read_mostly = 0;
+static void lapic_timer_broadcast(cpumask_t mask)
+{
+#ifdef CONFIG_SMP
+	send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+#endif
+}
 
 static void apic_pm_activate(void);
 
@@ -184,7 +246,10 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	apic_write(APIC_SPIV, value);
 
 	if (!virt_wire_setup) {
-		/* For LVT0 make it edge triggered, active high, external and enabled */
+		/*
+		 * For LVT0 make it edge triggered, active high,
+		 * external and enabled
+		 */
 		value = apic_read(APIC_LVT0);
 		value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
 			APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
@@ -420,10 +485,12 @@ void __cpuinit setup_local_APIC (void)
 	value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
 	if (!smp_processor_id() && !value) {
 		value = APIC_DM_EXTINT;
-		apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", smp_processor_id());
+		apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n",
+			    smp_processor_id());
 	} else {
 		value = APIC_DM_EXTINT | APIC_LVT_MASKED;
-		apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n", smp_processor_id());
+		apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
+			    smp_processor_id());
 	}
 	apic_write(APIC_LVT0, value);
 
@@ -706,8 +773,8 @@ void __init init_apic_mappings(void)
 		apic_phys = mp_lapic_addr;
 
 	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-	apic_mapped = 1;
-	apic_printk(APIC_VERBOSE,"mapped APIC to %16lx (%16lx)\n", APIC_BASE, apic_phys);
+	apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
+				APIC_BASE, apic_phys);
 
 	/* Put local APIC into the resource map. */
 	lapic_resource.start = apic_phys;
@@ -730,12 +797,14 @@ void __init init_apic_mappings(void)
 			if (smp_found_config) {
 				ioapic_phys = mp_ioapics[i].mpc_apicaddr;
 			} else {
-				ioapic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
+				ioapic_phys = (unsigned long)
+					alloc_bootmem_pages(PAGE_SIZE);
 				ioapic_phys = __pa(ioapic_phys);
 			}
 			set_fixmap_nocache(idx, ioapic_phys);
-			apic_printk(APIC_VERBOSE,"mapped IOAPIC to %016lx (%016lx)\n",
-					__fix_to_virt(idx), ioapic_phys);
+			apic_printk(APIC_VERBOSE,
+				    "mapped IOAPIC to %016lx (%016lx)\n",
+				    __fix_to_virt(idx), ioapic_phys);
 			idx++;
 
 			if (ioapic_res != NULL) {
@@ -758,16 +827,14 @@ void __init init_apic_mappings(void)
  * P5 APIC double write bug.
  */
 
-#define APIC_DIVISOR 16
-
-static void __setup_APIC_LVTT(unsigned int clocks)
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 {
 	unsigned int lvtt_value, tmp_value;
-	int cpu = smp_processor_id();
 
-	lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;
-
-	if (cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask))
+	lvtt_value = LOCAL_TIMER_VECTOR;
+	if (!oneshot)
+		lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+	if (!irqen)
 		lvtt_value |= APIC_LVT_MASKED;
 
 	apic_write(APIC_LVTT, lvtt_value);
@@ -780,44 +847,18 @@ static void __setup_APIC_LVTT(unsigned int clocks)
 				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
 				| APIC_TDR_DIV_16);
 
-	apic_write(APIC_TMICT, clocks/APIC_DIVISOR);
+	if (!oneshot)
+		apic_write(APIC_TMICT, clocks);
 }
 
-static void setup_APIC_timer(unsigned int clocks)
+static void setup_APIC_timer(void)
 {
-	unsigned long flags;
+	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-	local_irq_save(flags);
+	memcpy(levt, &lapic_clockevent, sizeof(*levt));
+	levt->cpumask = cpumask_of_cpu(smp_processor_id());
 
-	/* wait for irq slice */
-	if (hpet_address && hpet_use_timer) {
-		u32 trigger = hpet_readl(HPET_T0_CMP);
-		while (hpet_readl(HPET_T0_CMP) == trigger)
-			/* do nothing */ ;
-	} else {
-		int c1, c2;
-		outb_p(0x00, 0x43);
-		c2 = inb_p(0x40);
-		c2 |= inb_p(0x40) << 8;
-		do {
-			c1 = c2;
-			outb_p(0x00, 0x43);
-			c2 = inb_p(0x40);
-			c2 |= inb_p(0x40) << 8;
-		} while (c2 - c1 < 300);
-	}
-	__setup_APIC_LVTT(clocks);
-	/* Turn off PIT interrupt if we use APIC timer as main timer.
-	   Only works with the PM timer right now
-	   TBD fix it for HPET too. */
-	if ((pmtmr_ioport != 0) &&
-		smp_processor_id() == boot_cpu_id &&
-		apic_runs_main_timer == 1 &&
-		!cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) {
-		stop_timer_interrupt();
-		apic_runs_main_timer++;
-	}
-	local_irq_restore(flags);
+	clockevents_register_device(levt);
 }
 
 /*
@@ -835,17 +876,22 @@ static void setup_APIC_timer(unsigned int clocks)
 
 #define TICK_COUNT 100000000
 
-static int __init calibrate_APIC_clock(void)
+static void __init calibrate_APIC_clock(void)
 {
 	unsigned apic, apic_start;
 	unsigned long tsc, tsc_start;
 	int result;
+
+	local_irq_disable();
+
 	/*
 	 * Put whatever arbitrary (but long enough) timeout
 	 * value into the APIC clock, we just want to get the
 	 * counter running for calibration.
+	 *
+	 * No interrupt enable !
 	 */
-	__setup_APIC_LVTT(4000000000);
+	__setup_APIC_LVTT(250000000, 0, 0);
 
 	apic_start = apic_read(APIC_TMCCT);
 #ifdef CONFIG_X86_PM_TIMER
@@ -867,123 +913,62 @@ static int __init calibrate_APIC_clock(void)
 		result = (apic_start - apic) * 1000L * tsc_khz /
 					(tsc - tsc_start);
 	}
-	printk("result %d\n", result);
 
+	local_irq_enable();
+
+	printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
 
 	printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
 		result / 1000 / 1000, result / 1000 % 1000);
 
-	return result * APIC_DIVISOR / HZ;
-}
+	/* Calculate the scaled math multiplication factor */
+	lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
+	lapic_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &lapic_clockevent);
 
-static unsigned int calibration_result;
+	calibration_result = result / HZ;
+}
 
 void __init setup_boot_APIC_clock (void)
 {
+	/*
+	 * The local apic timer can be disabled via the kernel commandline.
+	 * Register the lapic timer as a dummy clock event source on SMP
+	 * systems, so the broadcast mechanism is used. On UP systems simply
+	 * ignore it.
+	 */
 	if (disable_apic_timer) {
 		printk(KERN_INFO "Disabling APIC timer\n");
+		/* No broadcast on UP ! */
+		if (num_possible_cpus() > 1)
+			setup_APIC_timer();
 		return;
 	}
 
 	printk(KERN_INFO "Using local APIC timer interrupts.\n");
-	using_apic_timer = 1;
-
-	local_irq_disable();
+	calibrate_APIC_clock();
 
-	calibration_result = calibrate_APIC_clock();
 	/*
-	 * Now set up the timer for real.
+	 * If nmi_watchdog is set to IO_APIC, we need the
+	 * PIT/HPET going.  Otherwise register lapic as a dummy
+	 * device.
 	 */
-	setup_APIC_timer(calibration_result);
+	if (nmi_watchdog != NMI_IO_APIC)
+		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+	else
+		printk(KERN_WARNING "APIC timer registered as dummy,"
+		       " due to nmi_watchdog=1!\n");
 
-	local_irq_enable();
+	setup_APIC_timer();
 }
 
 void __cpuinit setup_secondary_APIC_clock(void)
 {
-	local_irq_disable(); /* FIXME: Do we need this? --RR */
-	setup_APIC_timer(calibration_result);
-	local_irq_enable();
+	setup_APIC_timer();
 }
 
-void disable_APIC_timer(void)
-{
-	if (using_apic_timer) {
-		unsigned long v;
-
-		v = apic_read(APIC_LVTT);
-		/*
-		 * When an illegal vector value (0-15) is written to an LVT
-		 * entry and delivery mode is Fixed, the APIC may signal an
-		 * illegal vector error, with out regard to whether the mask
-		 * bit is set or whether an interrupt is actually seen on input.
-		 *
-		 * Boot sequence might call this function when the LVTT has
-		 * '0' vector value. So make sure vector field is set to
-		 * valid value.
-		 */
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write(APIC_LVTT, v);
-	}
-}
-
-void enable_APIC_timer(void)
-{
-	int cpu = smp_processor_id();
-
-	if (using_apic_timer &&
-	    !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
-		unsigned long v;
-
-		v = apic_read(APIC_LVTT);
-		apic_write(APIC_LVTT, v & ~APIC_LVT_MASKED);
-	}
-}
-
-void switch_APIC_timer_to_ipi(void *cpumask)
-{
-	cpumask_t mask = *(cpumask_t *)cpumask;
-	int cpu = smp_processor_id();
-
-	if (cpu_isset(cpu, mask) &&
-	    !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
-		disable_APIC_timer();
-		cpu_set(cpu, timer_interrupt_broadcast_ipi_mask);
-	}
-}
-EXPORT_SYMBOL(switch_APIC_timer_to_ipi);
-
-void smp_send_timer_broadcast_ipi(void)
-{
-	int cpu = smp_processor_id();
-	cpumask_t mask;
-
-	cpus_and(mask, cpu_online_map, timer_interrupt_broadcast_ipi_mask);
-
-	if (cpu_isset(cpu, mask)) {
-		cpu_clear(cpu, mask);
-		add_pda(apic_timer_irqs, 1);
-		smp_local_timer_interrupt();
-	}
-
-	if (!cpus_empty(mask)) {
-		send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
-	}
-}
-
-void switch_ipi_to_APIC_timer(void *cpumask)
-{
-	cpumask_t mask = *(cpumask_t *)cpumask;
-	int cpu = smp_processor_id();
-
-	if (cpu_isset(cpu, mask) &&
-	    cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
-		cpu_clear(cpu, timer_interrupt_broadcast_ipi_mask);
-		enable_APIC_timer();
-	}
-}
-EXPORT_SYMBOL(switch_ipi_to_APIC_timer);
-
 int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
@@ -997,8 +982,6 @@ void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
 	apic_write(reg, v);
 }
 
-#undef APIC_DIVISOR
-
 /*
  * Local timer interrupt handler. It does both profiling and
  * process statistics/rescheduling.
@@ -1011,22 +994,34 @@ void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
 
 void smp_local_timer_interrupt(void)
 {
-	profile_tick(CPU_PROFILING);
-#ifdef CONFIG_SMP
-	update_process_times(user_mode(get_irq_regs()));
-#endif
-	if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id)
-		main_timer_handler();
+	int cpu = smp_processor_id();
+	struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
+
 	/*
-	 * We take the 'long' return path, and there every subsystem
-	 * grabs the appropriate locks (kernel lock/ irq lock).
+	 * Normally we should not be here till LAPIC has been initialized but
+	 * in some cases like kdump, its possible that there is a pending LAPIC
+	 * timer interrupt from previous kernel's context and is delivered in
+	 * new kernel the moment interrupts are enabled.
 	 *
-	 * We might want to decouple profiling from the 'long path',
-	 * and do the profiling totally in assembly.
-	 *
-	 * Currently this isn't too much of an issue (performance wise),
-	 * we can take more than 100K local irqs per second on a 100 MHz P5.
+	 * Interrupts are enabled early and LAPIC is setup much later, hence
+	 * its possible that when we get here evt->event_handler is NULL.
+	 * Check for event_handler being NULL and discard the interrupt as
+	 * spurious.
+	 */
+	if (!evt->event_handler) {
+		printk(KERN_WARNING
+		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+		/* Switch it off */
+		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		return;
+	}
+
+	/*
+	 * the NMI deadlock-detector uses this.
 	 */
+	add_pda(apic_timer_irqs, 1);
+
+	evt->event_handler(evt);
 }
 
 /*
@@ -1042,11 +1037,6 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	/*
-	 * the NMI deadlock-detector uses this.
-	 */
-	add_pda(apic_timer_irqs, 1);
-
-	/*
 	 * NOTE! We'd better ACK the irq immediately,
 	 * because timer handling can be slow.
 	 */
@@ -1225,29 +1215,13 @@ static __init int setup_noapictimer(char *str)
 	disable_apic_timer = 1;
 	return 1;
 }
-
-static __init int setup_apicmaintimer(char *str)
-{
-	apic_runs_main_timer = 1;
-	nohpet = 1;
-	return 1;
-}
-__setup("apicmaintimer", setup_apicmaintimer);
-
-static __init int setup_noapicmaintimer(char *str)
-{
-	apic_runs_main_timer = -1;
-	return 1;
-}
-__setup("noapicmaintimer", setup_noapicmaintimer);
+__setup("noapictimer", setup_noapictimer);
 
 static __init int setup_apicpmtimer(char *s)
 {
 	apic_calibrate_pmtmr = 1;
 	notsc_setup(NULL);
-	return setup_apicmaintimer(NULL);
+	return 0;
 }
 __setup("apicpmtimer", setup_apicpmtimer);
 
-__setup("noapictimer", setup_noapictimer);
-
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index b6434a7ef8b..ffd01e5dcb5 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -646,7 +646,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 			policy->cpuinfo.transition_latency =
 			    perf->states[i].transition_latency * 1000;
 	}
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 
 	data->max_freq = perf->states[0].core_frequency * 1000;
 	/* table init */
diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
index 66acd503991..32f0bda3fc9 100644
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
@@ -363,7 +363,6 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 	policy->cur = nforce2_get(policy->cpu);
 	policy->min = policy->cpuinfo.min_freq;
 	policy->max = policy->cpuinfo.max_freq;
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
index f43d98e11cc..c11baaf9f2b 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
@@ -253,7 +253,6 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		f_table[k].frequency = CPUFREQ_TABLE_END;
 	}
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */
 	policy->cur = fsb * current_multiplier;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index f317276afa7..1e7ae7dafcf 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -219,7 +219,6 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	policy->cur = elanfreq_get_cpu_frequency(0);
 
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
index 461dabc4e49..ed2bda127c4 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
@@ -420,7 +420,6 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy)
 		policy->min = maxfreq / POLICY_MIN_DIV;
 	policy->max = maxfreq;
 	policy->cur = curfreq;
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.min_freq = maxfreq / max_duration;
 	policy->cpuinfo.max_freq = maxfreq;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index f0cce3c2dc3..5045f5d583c 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -710,6 +710,10 @@ static int enable_arbiter_disable(void)
 	reg = 0x78;
 	dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0,
 			     NULL);
+	/* Find PM133/VT8605 host bridge */
+	if (dev == NULL)
+		dev = pci_get_device(PCI_VENDOR_ID_VIA,
+				     PCI_DEVICE_ID_VIA_8605_0, NULL);
 	/* Find CLE266 host bridge */
 	if (dev == NULL) {
 		reg = 0x76;
@@ -918,7 +922,6 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	if ((longhaul_version != TYPE_LONGHAUL_V1) && (scale_voltage != 0))
 		longhaul_setup_voltagescaling();
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 200000;	/* nsec */
 	policy->cur = calc_speed(longhaul_get_cpu_mult());
 
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 4c76b511e19..8eb414b906d 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -229,7 +229,6 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	cpufreq_frequency_table_get_attr(p4clockmod_table, policy->cpu);
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 1000000; /* assumed */
 	policy->cur = stock_freq;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
index f89524051e4..6d028533931 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
@@ -160,7 +160,6 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	policy->cur = busfreq * max_multiplier;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index ca3e1d34188..7decd6a50ff 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -637,8 +637,6 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy)
 	printk (KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n",
 				minimum_speed/1000, maximum_speed/1000);
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
 	policy->cpuinfo.transition_latency = cpufreq_scale(2000000UL, fsb, latency);
 
 	policy->cur = powernow_get(0);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 34ed53a0673..b273b69cfdd 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -76,7 +76,10 @@ static u32 find_khz_freq_from_fid(u32 fid)
 /* Return a frequency in MHz, given an input fid and did */
 static u32 find_freq_from_fiddid(u32 fid, u32 did)
 {
-	return 100 * (fid + 0x10) >> did;
+	if (current_cpu_data.x86 == 0x10)
+		return 100 * (fid + 0x10) >> did;
+	else
+		return 100 * (fid + 0x8) >> did;
 }
 
 static u32 find_khz_freq_from_fiddid(u32 fid, u32 did)
@@ -1208,7 +1211,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	/* run on any CPU again */
 	set_cpus_allowed(current, oldmask);
 
-	pol->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cpus = cpumask_of_cpu(pol->cpu);
 	else
@@ -1325,21 +1327,16 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
 static int __cpuinit powernowk8_init(void)
 {
 	unsigned int i, supported_cpus = 0;
-	unsigned int booted_cores = 1;
 
 	for_each_online_cpu(i) {
 		if (check_supported_cpu(i))
 			supported_cpus++;
 	}
 
-#ifdef CONFIG_SMP
-	booted_cores = cpu_data[0].booted_cores;
-#endif
-
 	if (supported_cpus == num_online_cpus()) {
 		printk(KERN_INFO PFX "Found %d %s "
 			"processors (%d cpu cores) (" VERSION ")\n",
-			supported_cpus/booted_cores,
+			num_online_nodes(),
 			boot_cpu_data.x86_model_id, supported_cpus);
 		return cpufreq_register_driver(&cpufreq_amd64_driver);
 	}
diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
index b8fb4b521c6..d9f3e90a7ae 100644
--- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
+++ b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
@@ -111,7 +111,6 @@ static int sc520_freq_cpu_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 1000000; /* 1ms */
 	policy->cur = sc520_freq_get_cpu_frequency(0);
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 6c5dc2c85ae..811d4743854 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -393,7 +393,6 @@ static int centrino_cpu_init(struct cpufreq_policy *policy)
 
 	freq = get_cur_freq(policy->cpu);
 
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = 10000; /* 10uS transition latency */
 	policy->cur = freq;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index a5b2346faf1..36685e8f7be 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -348,7 +348,6 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 		(speed / 1000));
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cur = speed;
 
 	result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index e1c509aa305..f2b5a621d27 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -290,7 +290,6 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 		(speed / 1000));
 
 	/* cpuinfo and default policy values */
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	policy->cur = speed;
 
diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c
index 41e8aec4c61..f12d8c5d980 100644
--- a/arch/x86/kernel/geode_32.c
+++ b/arch/x86/kernel/geode_32.c
@@ -145,10 +145,14 @@ EXPORT_SYMBOL_GPL(geode_gpio_setup_event);
 
 static int __init geode_southbridge_init(void)
 {
+	int timers;
+
 	if (!is_geode())
 		return -ENODEV;
 
 	init_lbars();
+	timers = geode_mfgpt_detect();
+	printk(KERN_INFO "geode:  %d MFGPT timers available.\n", timers);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/hpet_32.c b/arch/x86/kernel/hpet.c
index 533d4932bc7..f8367074da0 100644
--- a/arch/x86/kernel/hpet_32.c
+++ b/arch/x86/kernel/hpet.c
@@ -1,5 +1,6 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
@@ -7,11 +8,11 @@
 #include <linux/pm.h>
 #include <linux/delay.h>
 
+#include <asm/fixmap.h>
 #include <asm/hpet.h>
+#include <asm/i8253.h>
 #include <asm/io.h>
 
-extern struct clock_event_device *global_clock_event;
-
 #define HPET_MASK	CLOCKSOURCE_MASK(32)
 #define HPET_SHIFT	22
 
@@ -22,9 +23,9 @@ extern struct clock_event_device *global_clock_event;
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
  */
 unsigned long hpet_address;
-static void __iomem * hpet_virt_address;
+static void __iomem *hpet_virt_address;
 
-static inline unsigned long hpet_readl(unsigned long a)
+unsigned long hpet_readl(unsigned long a)
 {
 	return readl(hpet_virt_address + a);
 }
@@ -34,6 +35,36 @@ static inline void hpet_writel(unsigned long d, unsigned long a)
 	writel(d, hpet_virt_address + a);
 }
 
+#ifdef CONFIG_X86_64
+
+#include <asm/pgtable.h>
+
+static inline void hpet_set_mapping(void)
+{
+	set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
+	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+	hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
+}
+
+static inline void hpet_clear_mapping(void)
+{
+	hpet_virt_address = NULL;
+}
+
+#else
+
+static inline void hpet_set_mapping(void)
+{
+	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+}
+
+static inline void hpet_clear_mapping(void)
+{
+	iounmap(hpet_virt_address);
+	hpet_virt_address = NULL;
+}
+#endif
+
 /*
  * HPET command line enable / disable
  */
@@ -49,6 +80,13 @@ static int __init hpet_setup(char* str)
 }
 __setup("hpet=", hpet_setup);
 
+static int __init disable_hpet(char *str)
+{
+	boot_hpet_disable = 1;
+	return 1;
+}
+__setup("nohpet", disable_hpet);
+
 static inline int is_hpet_capable(void)
 {
 	return (!boot_hpet_disable && hpet_address);
@@ -83,7 +121,7 @@ static void hpet_reserve_platform_timers(unsigned long id)
 
 	memset(&hd, 0, sizeof (hd));
 	hd.hd_phys_address = hpet_address;
-	hd.hd_address = hpet_virt_address;
+	hd.hd_address = hpet;
 	hd.hd_nirqs = nrtimers;
 	hd.hd_flags = HPET_DATA_PLATFORM;
 	hpet_reserve_timer(&hd, 0);
@@ -111,9 +149,9 @@ static void hpet_reserve_platform_timers(unsigned long id) { }
  */
 static unsigned long hpet_period;
 
-static void hpet_set_mode(enum clock_event_mode mode,
+static void hpet_legacy_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt);
-static int hpet_next_event(unsigned long delta,
+static int hpet_legacy_next_event(unsigned long delta,
 			   struct clock_event_device *evt);
 
 /*
@@ -122,10 +160,11 @@ static int hpet_next_event(unsigned long delta,
 static struct clock_event_device hpet_clockevent = {
 	.name		= "hpet",
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= hpet_set_mode,
-	.set_next_event = hpet_next_event,
+	.set_mode	= hpet_legacy_set_mode,
+	.set_next_event = hpet_legacy_next_event,
 	.shift		= 32,
 	.irq		= 0,
+	.rating		= 50,
 };
 
 static void hpet_start_counter(void)
@@ -140,7 +179,18 @@ static void hpet_start_counter(void)
 	hpet_writel(cfg, HPET_CFG);
 }
 
-static void hpet_enable_int(void)
+static void hpet_resume_device(void)
+{
+	force_hpet_resume();
+}
+
+static void hpet_restart_counter(void)
+{
+	hpet_resume_device();
+	hpet_start_counter();
+}
+
+static void hpet_enable_legacy_int(void)
 {
 	unsigned long cfg = hpet_readl(HPET_CFG);
 
@@ -149,7 +199,39 @@ static void hpet_enable_int(void)
 	hpet_legacy_int_enabled = 1;
 }
 
-static void hpet_set_mode(enum clock_event_mode mode,
+static void hpet_legacy_clockevent_register(void)
+{
+	uint64_t hpet_freq;
+
+	/* Start HPET legacy interrupts */
+	hpet_enable_legacy_int();
+
+	/*
+	 * The period is a femto seconds value. We need to calculate the
+	 * scaled math multiplication factor for nanosecond to hpet tick
+	 * conversion.
+	 */
+	hpet_freq = 1000000000000000ULL;
+	do_div(hpet_freq, hpet_period);
+	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
+				      NSEC_PER_SEC, 32);
+	/* Calculate the min / max delta */
+	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
+							   &hpet_clockevent);
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
+							   &hpet_clockevent);
+
+	/*
+	 * Start hpet with the boot cpu mask and make it
+	 * global after the IO_APIC has been initialized.
+	 */
+	hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
+	clockevents_register_device(&hpet_clockevent);
+	global_clock_event = &hpet_clockevent;
+	printk(KERN_DEBUG "hpet clockevent registered\n");
+}
+
+static void hpet_legacy_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt)
 {
 	unsigned long cfg, cmp, now;
@@ -190,12 +272,12 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		break;
 
 	case CLOCK_EVT_MODE_RESUME:
-		hpet_enable_int();
+		hpet_enable_legacy_int();
 		break;
 	}
 }
 
-static int hpet_next_event(unsigned long delta,
+static int hpet_legacy_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
 	unsigned long cnt;
@@ -215,6 +297,13 @@ static cycle_t read_hpet(void)
 	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
 
+#ifdef CONFIG_X86_64
+static cycle_t __vsyscall_fn vread_hpet(void)
+{
+	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
+}
+#endif
+
 static struct clocksource clocksource_hpet = {
 	.name		= "hpet",
 	.rating		= 250,
@@ -222,61 +311,17 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.shift		= HPET_SHIFT,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.resume		= hpet_start_counter,
+	.resume		= hpet_restart_counter,
+#ifdef CONFIG_X86_64
+	.vread		= vread_hpet,
+#endif
 };
 
-/*
- * Try to setup the HPET timer
- */
-int __init hpet_enable(void)
+static int hpet_clocksource_register(void)
 {
-	unsigned long id;
-	uint64_t hpet_freq;
 	u64 tmp, start, now;
 	cycle_t t1;
 
-	if (!is_hpet_capable())
-		return 0;
-
-	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-
-	/*
-	 * Read the period and check for a sane value:
-	 */
-	hpet_period = hpet_readl(HPET_PERIOD);
-	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
-		goto out_nohpet;
-
-	/*
-	 * The period is a femto seconds value. We need to calculate the
-	 * scaled math multiplication factor for nanosecond to hpet tick
-	 * conversion.
-	 */
-	hpet_freq = 1000000000000000ULL;
-	do_div(hpet_freq, hpet_period);
-	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
-				      NSEC_PER_SEC, 32);
-	/* Calculate the min / max delta */
-	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
-							   &hpet_clockevent);
-	hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
-							   &hpet_clockevent);
-
-	/*
-	 * Read the HPET ID register to retrieve the IRQ routing
-	 * information and the number of channels
-	 */
-	id = hpet_readl(HPET_ID);
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-	/*
-	 * The legacy routing mode needs at least two channels, tick timer
-	 * and the rtc emulation channel.
-	 */
-	if (!(id & HPET_ID_NUMBER))
-		goto out_nohpet;
-#endif
-
 	/* Start the counter */
 	hpet_start_counter();
 
@@ -298,7 +343,7 @@ int __init hpet_enable(void)
 	if (t1 == read_hpet()) {
 		printk(KERN_WARNING
 		       "HPET counter not counting. HPET disabled\n");
-		goto out_nohpet;
+		return -ENODEV;
 	}
 
 	/* Initialize and register HPET clocksource
@@ -319,27 +364,84 @@ int __init hpet_enable(void)
 
 	clocksource_register(&clocksource_hpet);
 
+	return 0;
+}
+
+/*
+ * Try to setup the HPET timer
+ */
+int __init hpet_enable(void)
+{
+	unsigned long id;
+
+	if (!is_hpet_capable())
+		return 0;
+
+	hpet_set_mapping();
+
+	/*
+	 * Read the period and check for a sane value:
+	 */
+	hpet_period = hpet_readl(HPET_PERIOD);
+	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
+		goto out_nohpet;
+
+	/*
+	 * Read the HPET ID register to retrieve the IRQ routing
+	 * information and the number of channels
+	 */
+	id = hpet_readl(HPET_ID);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+	/*
+	 * The legacy routing mode needs at least two channels, tick timer
+	 * and the rtc emulation channel.
+	 */
+	if (!(id & HPET_ID_NUMBER))
+		goto out_nohpet;
+#endif
+
+	if (hpet_clocksource_register())
+		goto out_nohpet;
+
 	if (id & HPET_ID_LEGSUP) {
-		hpet_enable_int();
-		hpet_reserve_platform_timers(id);
-		/*
-		 * Start hpet with the boot cpu mask and make it
-		 * global after the IO_APIC has been initialized.
-		 */
-		hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
-		clockevents_register_device(&hpet_clockevent);
-		global_clock_event = &hpet_clockevent;
+		hpet_legacy_clockevent_register();
 		return 1;
 	}
 	return 0;
 
 out_nohpet:
-	iounmap(hpet_virt_address);
-	hpet_virt_address = NULL;
+	hpet_clear_mapping();
 	boot_hpet_disable = 1;
 	return 0;
 }
 
+/*
+ * Needs to be late, as the reserve_timer code calls kalloc !
+ *
+ * Not a problem on i386 as hpet_enable is called from late_time_init,
+ * but on x86_64 it is necessary !
+ */
+static __init int hpet_late_init(void)
+{
+	if (boot_hpet_disable)
+		return -ENODEV;
+
+	if (!hpet_address) {
+		if (!force_hpet_address)
+			return -ENODEV;
+
+		hpet_address = force_hpet_address;
+		hpet_enable();
+		if (!hpet_virt_address)
+			return -ENODEV;
+	}
+
+	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
+
+	return 0;
+}
+fs_initcall(hpet_late_init);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 
diff --git a/arch/x86/kernel/hpet_64.c b/arch/x86/kernel/hpet_64.c
deleted file mode 100644
index e2d1b912e15..00000000000
--- a/arch/x86/kernel/hpet_64.c
+++ /dev/null
@@ -1,493 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/mc146818rtc.h>
-#include <linux/time.h>
-#include <linux/clocksource.h>
-#include <linux/ioport.h>
-#include <linux/acpi.h>
-#include <linux/hpet.h>
-#include <asm/pgtable.h>
-#include <asm/vsyscall.h>
-#include <asm/timex.h>
-#include <asm/hpet.h>
-
-#define HPET_MASK	0xFFFFFFFF
-#define HPET_SHIFT	22
-
-/* FSEC = 10^-15 NSEC = 10^-9 */
-#define FSEC_PER_NSEC	1000000
-
-int nohpet __initdata;
-
-unsigned long hpet_address;
-unsigned long hpet_period;	/* fsecs / HPET clock */
-unsigned long hpet_tick;	/* HPET clocks / interrupt */
-
-int hpet_use_timer;		/* Use counter of hpet for time keeping,
-				 * otherwise PIT
-				 */
-
-#ifdef	CONFIG_HPET
-static __init int late_hpet_init(void)
-{
-	struct hpet_data	hd;
-	unsigned int 		ntimer;
-
-	if (!hpet_address)
-        	return 0;
-
-	memset(&hd, 0, sizeof(hd));
-
-	ntimer = hpet_readl(HPET_ID);
-	ntimer = (ntimer & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT;
-	ntimer++;
-
-	/*
-	 * Register with driver.
-	 * Timer0 and Timer1 is used by platform.
-	 */
-	hd.hd_phys_address = hpet_address;
-	hd.hd_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
-	hd.hd_nirqs = ntimer;
-	hd.hd_flags = HPET_DATA_PLATFORM;
-	hpet_reserve_timer(&hd, 0);
-#ifdef	CONFIG_HPET_EMULATE_RTC
-	hpet_reserve_timer(&hd, 1);
-#endif
-	hd.hd_irq[0] = HPET_LEGACY_8254;
-	hd.hd_irq[1] = HPET_LEGACY_RTC;
-	if (ntimer > 2) {
-		struct hpet		*hpet;
-		struct hpet_timer	*timer;
-		int			i;
-
-		hpet = (struct hpet *) fix_to_virt(FIX_HPET_BASE);
-		timer = &hpet->hpet_timers[2];
-		for (i = 2; i < ntimer; timer++, i++)
-			hd.hd_irq[i] = (timer->hpet_config &
-					Tn_INT_ROUTE_CNF_MASK) >>
-				Tn_INT_ROUTE_CNF_SHIFT;
-
-	}
-
-	hpet_alloc(&hd);
-	return 0;
-}
-fs_initcall(late_hpet_init);
-#endif
-
-int hpet_timer_stop_set_go(unsigned long tick)
-{
-	unsigned int cfg;
-
-/*
- * Stop the timers and reset the main counter.
- */
-
-	cfg = hpet_readl(HPET_CFG);
-	cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
-	hpet_writel(cfg, HPET_CFG);
-	hpet_writel(0, HPET_COUNTER);
-	hpet_writel(0, HPET_COUNTER + 4);
-
-/*
- * Set up timer 0, as periodic with first interrupt to happen at hpet_tick,
- * and period also hpet_tick.
- */
-	if (hpet_use_timer) {
-		hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
-		    HPET_TN_32BIT, HPET_T0_CFG);
-		hpet_writel(hpet_tick, HPET_T0_CMP); /* next interrupt */
-		hpet_writel(hpet_tick, HPET_T0_CMP); /* period */
-		cfg |= HPET_CFG_LEGACY;
-	}
-/*
- * Go!
- */
-
-	cfg |= HPET_CFG_ENABLE;
-	hpet_writel(cfg, HPET_CFG);
-
-	return 0;
-}
-
-static cycle_t read_hpet(void)
-{
-	return (cycle_t)hpet_readl(HPET_COUNTER);
-}
-
-static cycle_t __vsyscall_fn vread_hpet(void)
-{
-	return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
-}
-
-struct clocksource clocksource_hpet = {
-	.name		= "hpet",
-	.rating		= 250,
-	.read		= read_hpet,
-	.mask		= (cycle_t)HPET_MASK,
-	.mult		= 0, /* set below */
-	.shift		= HPET_SHIFT,
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.vread		= vread_hpet,
-};
-
-int __init hpet_arch_init(void)
-{
-	unsigned int id;
-	u64 tmp;
-
-	if (!hpet_address)
-		return -1;
-	set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
-	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
-
-/*
- * Read the period, compute tick and quotient.
- */
-
-	id = hpet_readl(HPET_ID);
-
-	if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER))
-		return -1;
-
-	hpet_period = hpet_readl(HPET_PERIOD);
-	if (hpet_period < 100000 || hpet_period > 100000000)
-		return -1;
-
-	hpet_tick = (FSEC_PER_TICK + hpet_period / 2) / hpet_period;
-
-	hpet_use_timer = (id & HPET_ID_LEGSUP);
-
-	/*
-	 * hpet period is in femto seconds per cycle
-	 * so we need to convert this to ns/cyc units
-	 * aproximated by mult/2^shift
-	 *
-	 *  fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
-	 *  fsec/cyc * 1ns/1000000fsec * 2^shift = mult
-	 *  fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
-	 *  (fsec/cyc << shift)/1000000 = mult
-	 *  (hpet_period << shift)/FSEC_PER_NSEC = mult
-	 */
-	tmp = (u64)hpet_period << HPET_SHIFT;
-	do_div(tmp, FSEC_PER_NSEC);
-	clocksource_hpet.mult = (u32)tmp;
-	clocksource_register(&clocksource_hpet);
-
-	return hpet_timer_stop_set_go(hpet_tick);
-}
-
-int hpet_reenable(void)
-{
-	return hpet_timer_stop_set_go(hpet_tick);
-}
-
-/*
- * calibrate_tsc() calibrates the processor TSC in a very simple way, comparing
- * it to the HPET timer of known frequency.
- */
-
-#define TICK_COUNT 100000000
-#define SMI_THRESHOLD 50000
-#define MAX_TRIES  5
-
-/*
- * Some platforms take periodic SMI interrupts with 5ms duration. Make sure none
- * occurs between the reads of the hpet & TSC.
- */
-static void __init read_hpet_tsc(int *hpet, int *tsc)
-{
-	int tsc1, tsc2, hpet1, i;
-
-	for (i = 0; i < MAX_TRIES; i++) {
-		tsc1 = get_cycles_sync();
-		hpet1 = hpet_readl(HPET_COUNTER);
-		tsc2 = get_cycles_sync();
-		if ((tsc2 - tsc1) < SMI_THRESHOLD)
-			break;
-	}
-	*hpet = hpet1;
-	*tsc = tsc2;
-}
-
-unsigned int __init hpet_calibrate_tsc(void)
-{
-	int tsc_start, hpet_start;
-	int tsc_now, hpet_now;
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	read_hpet_tsc(&hpet_start, &tsc_start);
-
-	do {
-		local_irq_disable();
-		read_hpet_tsc(&hpet_now, &tsc_now);
-		local_irq_restore(flags);
-	} while ((tsc_now - tsc_start) < TICK_COUNT &&
-		(hpet_now - hpet_start) < TICK_COUNT);
-
-	return (tsc_now - tsc_start) * 1000000000L
-		/ ((hpet_now - hpet_start) * hpet_period / 1000);
-}
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
- * is enabled, we support RTC interrupt functionality in software.
- * RTC has 3 kinds of interrupts:
- * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
- *    is updated
- * 2) Alarm Interrupt - generate an interrupt at a specific time of day
- * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
- *    2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
- * (1) and (2) above are implemented using polling at a frequency of
- * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
- * overhead. (DEFAULT_RTC_INT_FREQ)
- * For (3), we use interrupts at 64Hz or user specified periodic
- * frequency, whichever is higher.
- */
-#include <linux/rtc.h>
-
-#define DEFAULT_RTC_INT_FREQ 	64
-#define RTC_NUM_INTS 		1
-
-static unsigned long UIE_on;
-static unsigned long prev_update_sec;
-
-static unsigned long AIE_on;
-static struct rtc_time alarm_time;
-
-static unsigned long PIE_on;
-static unsigned long PIE_freq = DEFAULT_RTC_INT_FREQ;
-static unsigned long PIE_count;
-
-static unsigned long hpet_rtc_int_freq; /* RTC interrupt frequency */
-static unsigned int hpet_t1_cmp; /* cached comparator register */
-
-int is_hpet_enabled(void)
-{
-	return hpet_address != 0;
-}
-
-/*
- * Timer 1 for RTC, we do not use periodic interrupt feature,
- * even if HPET supports periodic interrupts on Timer 1.
- * The reason being, to set up a periodic interrupt in HPET, we need to
- * stop the main counter. And if we do that everytime someone diables/enables
- * RTC, we will have adverse effect on main kernel timer running on Timer 0.
- * So, for the time being, simulate the periodic interrupt in software.
- *
- * hpet_rtc_timer_init() is called for the first time and during subsequent
- * interuppts reinit happens through hpet_rtc_timer_reinit().
- */
-int hpet_rtc_timer_init(void)
-{
-	unsigned int cfg, cnt;
-	unsigned long flags;
-
-	if (!is_hpet_enabled())
-		return 0;
-	/*
-	 * Set the counter 1 and enable the interrupts.
-	 */
-	if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
-		hpet_rtc_int_freq = PIE_freq;
-	else
-		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
-
-	local_irq_save(flags);
-
-	cnt = hpet_readl(HPET_COUNTER);
-	cnt += ((hpet_tick*HZ)/hpet_rtc_int_freq);
-	hpet_writel(cnt, HPET_T1_CMP);
-	hpet_t1_cmp = cnt;
-
-	cfg = hpet_readl(HPET_T1_CFG);
-	cfg &= ~HPET_TN_PERIODIC;
-	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
-	hpet_writel(cfg, HPET_T1_CFG);
-
-	local_irq_restore(flags);
-
-	return 1;
-}
-
-static void hpet_rtc_timer_reinit(void)
-{
-	unsigned int cfg, cnt, ticks_per_int, lost_ints;
-
-	if (unlikely(!(PIE_on | AIE_on | UIE_on))) {
-		cfg = hpet_readl(HPET_T1_CFG);
-		cfg &= ~HPET_TN_ENABLE;
-		hpet_writel(cfg, HPET_T1_CFG);
-		return;
-	}
-
-	if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
-		hpet_rtc_int_freq = PIE_freq;
-	else
-		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
-
-	/* It is more accurate to use the comparator value than current count.*/
-	ticks_per_int = hpet_tick * HZ / hpet_rtc_int_freq;
-	hpet_t1_cmp += ticks_per_int;
-	hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
-
-	/*
-	 * If the interrupt handler was delayed too long, the write above tries
-	 * to schedule the next interrupt in the past and the hardware would
-	 * not interrupt until the counter had wrapped around.
-	 * So we have to check that the comparator wasn't set to a past time.
-	 */
-	cnt = hpet_readl(HPET_COUNTER);
-	if (unlikely((int)(cnt - hpet_t1_cmp) > 0)) {
-		lost_ints = (cnt - hpet_t1_cmp) / ticks_per_int + 1;
-		/* Make sure that, even with the time needed to execute
-		 * this code, the next scheduled interrupt has been moved
-		 * back to the future: */
-		lost_ints++;
-
-		hpet_t1_cmp += lost_ints * ticks_per_int;
-		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
-
-		if (PIE_on)
-			PIE_count += lost_ints;
-
-		if (printk_ratelimit())
-			printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
-			       hpet_rtc_int_freq);
-	}
-}
-
-/*
- * The functions below are called from rtc driver.
- * Return 0 if HPET is not being used.
- * Otherwise do the necessary changes and return 1.
- */
-int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
-{
-	if (!is_hpet_enabled())
-		return 0;
-
-	if (bit_mask & RTC_UIE)
-		UIE_on = 0;
-	if (bit_mask & RTC_PIE)
-		PIE_on = 0;
-	if (bit_mask & RTC_AIE)
-		AIE_on = 0;
-
-	return 1;
-}
-
-int hpet_set_rtc_irq_bit(unsigned long bit_mask)
-{
-	int timer_init_reqd = 0;
-
-	if (!is_hpet_enabled())
-		return 0;
-
-	if (!(PIE_on | AIE_on | UIE_on))
-		timer_init_reqd = 1;
-
-	if (bit_mask & RTC_UIE) {
-		UIE_on = 1;
-	}
-	if (bit_mask & RTC_PIE) {
-		PIE_on = 1;
-		PIE_count = 0;
-	}
-	if (bit_mask & RTC_AIE) {
-		AIE_on = 1;
-	}
-
-	if (timer_init_reqd)
-		hpet_rtc_timer_init();
-
-	return 1;
-}
-
-int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec)
-{
-	if (!is_hpet_enabled())
-		return 0;
-
-	alarm_time.tm_hour = hrs;
-	alarm_time.tm_min = min;
-	alarm_time.tm_sec = sec;
-
-	return 1;
-}
-
-int hpet_set_periodic_freq(unsigned long freq)
-{
-	if (!is_hpet_enabled())
-		return 0;
-
-	PIE_freq = freq;
-	PIE_count = 0;
-
-	return 1;
-}
-
-int hpet_rtc_dropped_irq(void)
-{
-	if (!is_hpet_enabled())
-		return 0;
-
-	return 1;
-}
-
-irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
-{
-	struct rtc_time curr_time;
-	unsigned long rtc_int_flag = 0;
-	int call_rtc_interrupt = 0;
-
-	hpet_rtc_timer_reinit();
-
-	if (UIE_on | AIE_on) {
-		rtc_get_rtc_time(&curr_time);
-	}
-	if (UIE_on) {
-		if (curr_time.tm_sec != prev_update_sec) {
-			/* Set update int info, call real rtc int routine */
-			call_rtc_interrupt = 1;
-			rtc_int_flag = RTC_UF;
-			prev_update_sec = curr_time.tm_sec;
-		}
-	}
-	if (PIE_on) {
-		PIE_count++;
-		if (PIE_count >= hpet_rtc_int_freq/PIE_freq) {
-			/* Set periodic int info, call real rtc int routine */
-			call_rtc_interrupt = 1;
-			rtc_int_flag |= RTC_PF;
-			PIE_count = 0;
-		}
-	}
-	if (AIE_on) {
-		if ((curr_time.tm_sec == alarm_time.tm_sec) &&
-		    (curr_time.tm_min == alarm_time.tm_min) &&
-		    (curr_time.tm_hour == alarm_time.tm_hour)) {
-			/* Set alarm int info, call real rtc int routine */
-			call_rtc_interrupt = 1;
-			rtc_int_flag |= RTC_AF;
-		}
-	}
-	if (call_rtc_interrupt) {
-		rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));
-		rtc_interrupt(rtc_int_flag, dev_id);
-	}
-	return IRQ_HANDLED;
-}
-#endif
-
-static int __init nohpet_setup(char *s)
-{
-	nohpet = 1;
-	return 1;
-}
-
-__setup("nohpet", nohpet_setup);
diff --git a/arch/x86/kernel/i8253_32.c b/arch/x86/kernel/i8253.c
index 6d839f2f1b1..ac15e4cbd9c 100644
--- a/arch/x86/kernel/i8253_32.c
+++ b/arch/x86/kernel/i8253.c
@@ -13,7 +13,6 @@
 #include <asm/delay.h>
 #include <asm/i8253.h>
 #include <asm/io.h>
-#include <asm/timer.h>
 
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
@@ -120,6 +119,7 @@ void __init setup_pit_timer(void)
 	global_clock_event = &pit_clockevent;
 }
 
+#ifndef CONFIG_X86_64
 /*
  * Since the PIT overflows every tick, its not very useful
  * to just read by itself. So use jiffies to emulate a free
@@ -204,3 +204,5 @@ static int __init init_pit_clocksource(void)
 	return clocksource_register(&clocksource_pit);
 }
 arch_initcall(init_pit_clocksource);
+
+#endif
diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c
index 0499cbe9871..679bb33acbf 100644
--- a/arch/x86/kernel/i8259_32.c
+++ b/arch/x86/kernel/i8259_32.c
@@ -10,7 +10,6 @@
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
 
-#include <asm/8253pit.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
index 948cae64609..eb72976cc13 100644
--- a/arch/x86/kernel/i8259_64.c
+++ b/arch/x86/kernel/i8259_64.c
@@ -444,46 +444,6 @@ void __init init_ISA_irqs (void)
 	}
 }
 
-static void setup_timer_hardware(void)
-{
-	outb_p(0x34,0x43);		/* binary, mode 2, LSB/MSB, ch 0 */
-	udelay(10);
-	outb_p(LATCH & 0xff , 0x40);	/* LSB */
-	udelay(10);
-	outb(LATCH >> 8 , 0x40);	/* MSB */
-}
-
-static int timer_resume(struct sys_device *dev)
-{
-	setup_timer_hardware();
-	return 0;
-}
-
-void i8254_timer_resume(void)
-{
-	setup_timer_hardware();
-}
-
-static struct sysdev_class timer_sysclass = {
-	set_kset_name("timer_pit"),
-	.resume		= timer_resume,
-};
-
-static struct sys_device device_timer = {
-	.id		= 0,
-	.cls		= &timer_sysclass,
-};
-
-static int __init init_timer_sysfs(void)
-{
-	int error = sysdev_class_register(&timer_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
-}
-
-device_initcall(init_timer_sysfs);
-
 void __init init_IRQ(void)
 {
 	int i;
@@ -533,12 +493,6 @@ void __init init_IRQ(void)
 	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
-	/*
-	 * Set the clock to HZ Hz, we already have a valid
-	 * vector now:
-	 */
-	setup_timer_hardware();
-
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);
 }
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
new file mode 100644
index 00000000000..0ab680f2d9d
--- /dev/null
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -0,0 +1,362 @@
+/*
+ * Driver/API for AMD Geode Multi-Function General Purpose Timers (MFGPT)
+ *
+ * Copyright (C) 2006, Advanced Micro Devices, Inc.
+ * Copyright (C) 2007, Andres Salomon <dilinger@debian.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * The MFGPTs are documented in AMD Geode CS5536 Companion Device Data Book.
+ */
+
+/*
+ * We are using the 32Khz input clock - its the only one that has the
+ * ranges we find desirable.  The following table lists the suitable
+ * divisors and the associated hz, minimum interval
+ * and the maximum interval:
+ *
+ *  Divisor   Hz      Min Delta (S) Max Delta (S)
+ *   1        32000     .0005          2.048
+ *   2        16000      .001          4.096
+ *   4         8000      .002          8.192
+ *   8         4000      .004         16.384
+ *   16        2000      .008         32.768
+ *   32        1000      .016         65.536
+ *   64         500      .032        131.072
+ *  128         250      .064        262.144
+ *  256         125      .128        524.288
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <asm/geode.h>
+
+#define F_AVAIL    0x01
+
+static struct mfgpt_timer_t {
+	int flags;
+	struct module *owner;
+} mfgpt_timers[MFGPT_MAX_TIMERS];
+
+/* Selected from the table above */
+
+#define MFGPT_DIVISOR 16
+#define MFGPT_SCALE  4     /* divisor = 2^(scale) */
+#define MFGPT_HZ  (32000 / MFGPT_DIVISOR)
+#define MFGPT_PERIODIC (MFGPT_HZ / HZ)
+
+#ifdef CONFIG_GEODE_MFGPT_TIMER
+static int __init mfgpt_timer_setup(void);
+#else
+#define mfgpt_timer_setup() (0)
+#endif
+
+/* Allow for disabling of MFGPTs */
+static int disable;
+static int __init mfgpt_disable(char *s)
+{
+	disable = 1;
+	return 1;
+}
+__setup("nomfgpt", mfgpt_disable);
+
+/*
+ * Check whether any MFGPTs are available for the kernel to use.  In most
+ * cases, firmware that uses AMD's VSA code will claim all timers during
+ * bootup; we certainly don't want to take them if they're already in use.
+ * In other cases (such as with VSAless OpenFirmware), the system firmware
+ * leaves timers available for us to use.
+ */
+int __init geode_mfgpt_detect(void)
+{
+	int count = 0, i;
+	u16 val;
+
+	if (disable) {
+		printk(KERN_INFO "geode-mfgpt:  Skipping MFGPT setup\n");
+		return 0;
+	}
+
+	for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
+		val = geode_mfgpt_read(i, MFGPT_REG_SETUP);
+		if (!(val & MFGPT_SETUP_SETUP)) {
+			mfgpt_timers[i].flags = F_AVAIL;
+			count++;
+		}
+	}
+
+	/* set up clock event device, if desired */
+	i = mfgpt_timer_setup();
+
+	return count;
+}
+
+int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
+{
+	u32 msr, mask, value, dummy;
+	int shift = (cmp == MFGPT_CMP1) ? 0 : 8;
+
+	if (timer < 0 || timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	/*
+	 * The register maps for these are described in sections 6.17.1.x of
+	 * the AMD Geode CS5536 Companion Device Data Book.
+	 */
+	switch (event) {
+	case MFGPT_EVENT_RESET:
+		/*
+		 * XXX: According to the docs, we cannot reset timers above
+		 * 6; that is, resets for 7 and 8 will be ignored.  Is this
+		 * a problem?   -dilinger
+		 */
+		msr = MFGPT_NR_MSR;
+		mask = 1 << (timer + 24);
+		break;
+
+	case MFGPT_EVENT_NMI:
+		msr = MFGPT_NR_MSR;
+		mask = 1 << (timer + shift);
+		break;
+
+	case MFGPT_EVENT_IRQ:
+		msr = MFGPT_IRQ_MSR;
+		mask = 1 << (timer + shift);
+		break;
+
+	default:
+		return -EIO;
+	}
+
+	rdmsr(msr, value, dummy);
+
+	if (enable)
+		value |= mask;
+	else
+		value &= ~mask;
+
+	wrmsr(msr, value, dummy);
+	return 0;
+}
+
+int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
+{
+	u32 val, dummy;
+	int offset;
+
+	if (timer < 0 || timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable))
+		return -EIO;
+
+	rdmsr(MSR_PIC_ZSEL_LOW, val, dummy);
+
+	offset = (timer % 4) * 4;
+
+	val &= ~((0xF << offset) | (0xF << (offset + 16)));
+
+	if (enable) {
+		val |= (irq & 0x0F) << (offset);
+		val |= (irq & 0x0F) << (offset + 16);
+	}
+
+	wrmsr(MSR_PIC_ZSEL_LOW, val, dummy);
+	return 0;
+}
+
+static int mfgpt_get(int timer, struct module *owner)
+{
+	mfgpt_timers[timer].flags &= ~F_AVAIL;
+	mfgpt_timers[timer].owner = owner;
+	printk(KERN_INFO "geode-mfgpt:  Registered timer %d\n", timer);
+	return timer;
+}
+
+int geode_mfgpt_alloc_timer(int timer, int domain, struct module *owner)
+{
+	int i;
+
+	if (!geode_get_dev_base(GEODE_DEV_MFGPT))
+		return -ENODEV;
+	if (timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	if (timer < 0) {
+		/* Try to find an available timer */
+		for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
+			if (mfgpt_timers[i].flags & F_AVAIL)
+				return mfgpt_get(i, owner);
+
+			if (i == 5 && domain == MFGPT_DOMAIN_WORKING)
+				break;
+		}
+	} else {
+		/* If they requested a specific timer, try to honor that */
+		if (mfgpt_timers[timer].flags & F_AVAIL)
+			return mfgpt_get(timer, owner);
+	}
+
+	/* No timers available - too bad */
+	return -1;
+}
+
+
+#ifdef CONFIG_GEODE_MFGPT_TIMER
+
+/*
+ * The MFPGT timers on the CS5536 provide us with suitable timers to use
+ * as clock event sources - not as good as a HPET or APIC, but certainly
+ * better then the PIT.  This isn't a general purpose MFGPT driver, but
+ * a simplified one designed specifically to act as a clock event source.
+ * For full details about the MFGPT, please consult the CS5536 data sheet.
+ */
+
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+
+static unsigned int mfgpt_tick_mode = CLOCK_EVT_MODE_SHUTDOWN;
+static u16 mfgpt_event_clock;
+
+static int irq = 7;
+static int __init mfgpt_setup(char *str)
+{
+	get_option(&str, &irq);
+	return 1;
+}
+__setup("mfgpt_irq=", mfgpt_setup);
+
+static inline void mfgpt_disable_timer(u16 clock)
+{
+	u16 val = geode_mfgpt_read(clock, MFGPT_REG_SETUP);
+	geode_mfgpt_write(clock, MFGPT_REG_SETUP, val & ~MFGPT_SETUP_CNTEN);
+}
+
+static int mfgpt_next_event(unsigned long, struct clock_event_device *);
+static void mfgpt_set_mode(enum clock_event_mode, struct clock_event_device *);
+
+static struct clock_event_device mfgpt_clockevent = {
+	.name = "mfgpt-timer",
+	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode = mfgpt_set_mode,
+	.set_next_event = mfgpt_next_event,
+	.rating = 250,
+	.cpumask = CPU_MASK_ALL,
+	.shift = 32
+};
+
+static inline void mfgpt_start_timer(u16 clock, u16 delta)
+{
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_CMP2, (u16) delta);
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0);
+
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP,
+			  MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
+}
+
+static void mfgpt_set_mode(enum clock_event_mode mode,
+			   struct clock_event_device *evt)
+{
+	mfgpt_disable_timer(mfgpt_event_clock);
+
+	if (mode == CLOCK_EVT_MODE_PERIODIC)
+		mfgpt_start_timer(mfgpt_event_clock, MFGPT_PERIODIC);
+
+	mfgpt_tick_mode = mode;
+}
+
+static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt)
+{
+	mfgpt_start_timer(mfgpt_event_clock, delta);
+	return 0;
+}
+
+/* Assume (foolishly?), that this interrupt was due to our tick */
+
+static irqreturn_t mfgpt_tick(int irq, void *dev_id)
+{
+	if (mfgpt_tick_mode == CLOCK_EVT_MODE_SHUTDOWN)
+		return IRQ_HANDLED;
+
+	/* Turn off the clock */
+	mfgpt_disable_timer(mfgpt_event_clock);
+
+	/* Clear the counter */
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0);
+
+	/* Restart the clock in periodic mode */
+
+	if (mfgpt_tick_mode == CLOCK_EVT_MODE_PERIODIC) {
+		geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP,
+				  MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
+	}
+
+	mfgpt_clockevent.event_handler(&mfgpt_clockevent);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction mfgptirq  = {
+	.handler = mfgpt_tick,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING,
+	.mask = CPU_MASK_NONE,
+	.name = "mfgpt-timer"
+};
+
+static int __init mfgpt_timer_setup(void)
+{
+	int timer, ret;
+	u16 val;
+
+	timer = geode_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING,
+			THIS_MODULE);
+	if (timer < 0) {
+		printk(KERN_ERR
+		       "mfgpt-timer:  Could not allocate a MFPGT timer\n");
+		return -ENODEV;
+	}
+
+	mfgpt_event_clock = timer;
+	/* Set the clock scale and enable the event mode for CMP2 */
+	val = MFGPT_SCALE | (3 << 8);
+
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, val);
+
+	/* Set up the IRQ on the MFGPT side */
+	if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, irq)) {
+		printk(KERN_ERR "mfgpt-timer:  Could not set up IRQ %d\n", irq);
+		return -EIO;
+	}
+
+	/* And register it with the kernel */
+	ret = setup_irq(irq, &mfgptirq);
+
+	if (ret) {
+		printk(KERN_ERR
+		       "mfgpt-timer:  Unable to set up the interrupt.\n");
+		goto err;
+	}
+
+	/* Set up the clock event */
+	mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, 32);
+	mfgpt_clockevent.min_delta_ns = clockevent_delta2ns(0xF,
+			&mfgpt_clockevent);
+	mfgpt_clockevent.max_delta_ns = clockevent_delta2ns(0xFFFE,
+			&mfgpt_clockevent);
+
+	printk(KERN_INFO
+	       "mfgpt-timer:  registering the MFGT timer as a clock event.\n");
+	clockevents_register_device(&mfgpt_clockevent);
+
+	return 0;
+
+err:
+	geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, irq);
+	printk(KERN_ERR
+	       "mfgpt-timer:  Unable to set up the MFGPT clock source\n");
+	return -EIO;
+}
+
+#endif
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index c7227e2180f..95d3fc203cf 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -353,7 +353,8 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 	 * Take the local apic timer and PIT/HPET into account. We don't
 	 * know which one is active, when we have highres/dyntick on
 	 */
-	sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0];
+	sum = per_cpu(irq_stat, cpu).apic_timer_irqs +
+		per_cpu(irq_stat, cpu).irq0_irqs;
 
 	/* if the none of the timers isn't firing, this cpu isn't doing much */
 	if (!touched && last_irq_sums[cpu] == sum) {
diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c
index 0ec6d2ddb93..e60ac0da528 100644
--- a/arch/x86/kernel/nmi_64.c
+++ b/arch/x86/kernel/nmi_64.c
@@ -329,7 +329,7 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 		touched = 1;
 	}
 
-	sum = read_pda(apic_timer_irqs);
+	sum = read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
 	if (__get_cpu_var(nmi_touch)) {
 		__get_cpu_var(nmi_touch) = 0;
 		touched = 1;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c