Merge branch 'linus' into perfcounters/core

Conflicts: arch/x86/kernel/irqinit.c arch/x86/kernel/irqinit_64.c arch/x86/kernel/traps.c arch/x86/mm/fault.c include/linux/sched.h kernel/exit.c
author: Ingo Molnar <mingo@elte.hu> 2009-06-11 17:55:42 +0200
committer: Ingo Molnar <mingo@elte.hu> 2009-06-11 17:55:42 +0200
commit: 940010c5a314a7bd9b498593bc6ba1718ac5aec5 (patch)
tree: d141e08ced08c40c6a8e3ab2cdecde5ff14e560f
parent: 8dc8e5e8bc0ce00b0f656bf972f67cd8a72759e5 (diff)
parent: 991ec02cdca33b03a132a0cacfe6f0aa0be9aa8d (diff)
449 files changed, 17770 insertions, 8480 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
new file mode 100644
index 00000000000..175bb4f7051
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-cache_disable
@@ -0,0 +1,18 @@
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:	2.6.27
+Contact:	mark.langsdorf@amd.com
+Description:	These files exist in every cpu's cache index directories.
+		There are currently 2 cache_disable_# files in each
+		directory.  Reading from these files on a supported
+		processor will return that cache disable index value
+		for that processor and node.  Writing to one of these
+		files will cause the specificed cache index to be disabled.
+
+		Currently, only AMD Family 10h Processors support cache index
+		disable, and only for their L3 caches.  See the BIOS and
+		Kernel Developer's Guide at
+		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+		for formatting information and other details on the
+		cache index disable.
+Users:    joachim.deguara@amd.com
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index d9aa43d78bc..25fb8bcf32a 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -704,12 +704,24 @@ this directory the following files can currently be found:
 				The current number of free dma_debug_entries
 				in the allocator.
 
+	dma-api/driver-filter
+				You can write a name of a driver into this file
+				to limit the debug output to requests from that
+				particular driver. Write an empty string to
+				that file to disable the filter and see
+				all errors again.
+
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
 Notice that you can not enable it again at runtime. You have to reboot to do
 so.
 
+If you want to see debug messages only for a special device driver you can
+specify the dma_debug_driver=<drivername> parameter. This will enable the
+driver filter at boot time. The debug code will only print errors for that
+driver afterwards. This filter can be disabled or changed later using debugfs.
+
 When the code disables itself at runtime this is most likely because it ran
 out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index b1eb661e630..9632444f6c6 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -13,7 +13,8 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
 	    mac80211.xml debugobjects.xml sh.xml regulator.xml \
-	    alsa-driver-api.xml writing-an-alsa-driver.xml
+	    alsa-driver-api.xml writing-an-alsa-driver.xml \
+	    tracepoint.xml
 
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
new file mode 100644
index 00000000000..b0756d0fd57
--- /dev/null
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -0,0 +1,89 @@
+<?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="Tracepoints">
+ <bookinfo>
+  <title>The Linux Kernel Tracepoint API</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Jason</firstname>
+    <surname>Baron</surname>
+    <affiliation>
+     <address>
+      <email>jbaron@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <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>
+     Tracepoints are static probe points that are located in strategic points
+     throughout the kernel. 'Probes' register/unregister with tracepoints
+     via a callback mechanism. The 'probes' are strictly typed functions that
+     are passed a unique set of parameters defined by each tracepoint.
+   </para>
+
+   <para>
+     From this simple callback mechanism, 'probes' can be used to profile, debug,
+     and understand kernel behavior. There are a number of tools that provide a
+     framework for using 'probes'. These tools include Systemtap, ftrace, and
+     LTTng.
+   </para>
+
+   <para>
+     Tracepoints are defined in a number of header files via various macros. Thus,
+     the purpose of this document is to provide a clear accounting of the available
+     tracepoints. The intention is to understand not only what tracepoints are
+     available but also to understand where future tracepoints might be added.
+   </para>
+
+   <para>
+     The API presented has functions of the form:
+     <function>trace_tracepointname(function parameters)</function>. These are the
+     tracepoints callbacks that are found throughout the code. Registering and
+     unregistering probes with these callback sites is covered in the
+     <filename>Documentation/trace/*</filename> directory.
+   </para>
+  </chapter>
+
+  <chapter id="irq">
+   <title>IRQ</title>
+!Iinclude/trace/events/irq.h
+  </chapter>
+
+</book>
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 068848240a8..02cced183b2 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu:
-  0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
-  1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
-  2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
-  3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
-  4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
-  5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
-  6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
-  7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
+rcu:
+  0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
+  1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
+  2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
+  3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
+  4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
+  5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
+  6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
+  7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
 rcu_bh:
-  0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
-  1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
-  2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
-  3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
-  4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
-  6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
+  0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
+  1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
+  2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
+  4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
 
 The first section lists the rcu_data structures for rcu, the second for
 rcu_bh.  Each section has one line per CPU, or eight for this 8-CPU system.
@@ -253,12 +254,6 @@ o	"pqc" indicates which grace period the last-observed quiescent
 o	"qp" indicates that RCU still expects a quiescent state from
 	this CPU.
 
-o	"rpfq" is the number of rcu_pending() calls on this CPU required
-	to induce this CPU to invoke force_quiescent_state().
-
-o	"rp" is low-order four hex digits of the count of how many times
-	rcu_pending() has been invoked on this CPU.
-
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
 	scheduler or by irq.  The number after the "/" is the interrupt
@@ -305,6 +300,9 @@ o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
 
+There is also an rcu/rcudata.csv file with the same information in
+comma-separated-variable spreadsheet format.
+
 
 The output of "cat rcu/rcugp" looks as follows:
 
@@ -411,3 +409,63 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 		For example, the first entry at the lowest level shows
 		"^0", indicating that it corresponds to bit zero in
 		the first entry at the middle level.
+
+
+The output of "cat rcu/rcu_pending" looks as follows:
+
+rcu:
+  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+rcu_bh:
+  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+
+As always, this is once again split into "rcu" and "rcu_bh" portions.
+The fields are as follows:
+
+o	"np" is the number of times that __rcu_pending() has been invoked
+	for the corresponding flavor of RCU.
+
+o	"qsp" is the number of times that the RCU was waiting for a
+	quiescent state from this CPU.
+
+o	"cbr" is the number of times that this CPU had RCU callbacks
+	that had passed through a grace period, and were thus ready
+	to be invoked.
+
+o	"cng" is the number of times that this CPU needed another
+	grace period while RCU was idle.
+
+o	"gpc" is the number of times that an old grace period had
+	completed, but this CPU was not yet aware of it.
+
+o	"gps" is the number of times that a new grace period had started,
+	but this CPU was not yet aware of it.
+
+o	"nf" is the number of times that this CPU suspected that the
+	current grace period had run for too long, and thus needed to
+	be forced.
+
+	Please note that "forcing" consists of sending resched IPIs
+	to holdout CPUs.  If that CPU really still is in an old RCU
+	read-side critical section, then we really do have to wait for it.
+	The assumption behing "forcing" is that the CPU is not still in
+	an old RCU read-side critical section, but has not yet responded
+	for some other reason.
+
+o	"nn" is the number of times that this CPU needed nothing.  Alert
+	readers will note that the rcu "nn" number for a given CPU very
+	closely matches the rcu_bh "np" number for that same CPU.  This
+	is due to short-circuit evaluation in rcu_pending().
diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
new file mode 100644
index 00000000000..9dc1ff4fd53
--- /dev/null
+++ b/Documentation/futex-requeue-pi.txt
@@ -0,0 +1,131 @@
+Futex Requeue PI
+----------------
+
+Requeueing of tasks from a non-PI futex to a PI futex requires
+special handling in order to ensure the underlying rt_mutex is never
+left without an owner if it has waiters; doing so would break the PI
+boosting logic [see rt-mutex-desgin.txt] For the purposes of
+brevity, this action will be referred to as "requeue_pi" throughout
+this document.  Priority inheritance is abbreviated throughout as
+"PI".
+
+Motivation
+----------
+
+Without requeue_pi, the glibc implementation of
+pthread_cond_broadcast() must resort to waking all the tasks waiting
+on a pthread_condvar and letting them try to sort out which task
+gets to run first in classic thundering-herd formation.  An ideal
+implementation would wake the highest-priority waiter, and leave the
+rest to the natural wakeup inherent in unlocking the mutex
+associated with the condvar.
+
+Consider the simplified glibc calls:
+
+/* caller must lock mutex */
+pthread_cond_wait(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+	lock(mutex);
+}
+
+pthread_cond_broadcast(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue(cond->data.__futex, cond->mutex);
+}
+
+Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
+has waiters. Note that pthread_cond_wait() attempts to lock the
+mutex only after it has returned to user space.  This will leave the
+underlying rt_mutex with waiters, and no owner, breaking the
+previously mentioned PI-boosting algorithms.
+
+In order to support PI-aware pthread_condvar's, the kernel needs to
+be able to requeue tasks to PI futexes.  This support implies that
+upon a successful futex_wait system call, the caller would return to
+user space already holding the PI futex.  The glibc implementation
+would be modified as follows:
+
+
+/* caller must lock mutex */
+pthread_cond_wait_pi(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait_requeue_pi(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+        /* the kernel acquired the the mutex for us */
+}
+
+pthread_cond_broadcast_pi(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue_pi(cond->data.__futex, cond->mutex);
+}
+
+The actual glibc implementation will likely test for PI and make the
+necessary changes inside the existing calls rather than creating new
+calls for the PI cases.  Similar changes are needed for
+pthread_cond_timedwait() and pthread_cond_signal().
+
+Implementation
+--------------
+
+In order to ensure the rt_mutex has an owner if it has waiters, it
+is necessary for both the requeue code, as well as the waiting code,
+to be able to acquire the rt_mutex before returning to user space.
+The requeue code cannot simply wake the waiter and leave it to
+acquire the rt_mutex as it would open a race window between the
+requeue call returning to user space and the waiter waking and
+starting to run.  This is especially true in the uncontended case.
+
+The solution involves two new rt_mutex helper routines,
+rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
+allow the requeue code to acquire an uncontended rt_mutex on behalf
+of the waiter and to enqueue the waiter on a contended rt_mutex.
+Two new system calls provide the kernel<->user interface to
+requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
+
+FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
+and pthread_cond_timedwait()) to block on the initial futex and wait
+to be requeued to a PI-aware futex.  The implementation is the
+result of a high-speed collision between futex_wait() and
+futex_lock_pi(), with some extra logic to check for the additional
+wake-up scenarios.
+
+FUTEX_REQUEUE_CMP_PI is called by the waker
+(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
+possibly wake the waiting tasks. Internally, this system call is
+still handled by futex_requeue (by passing requeue_pi=1).  Before
+requeueing, futex_requeue() attempts to acquire the requeue target
+PI futex on behalf of the top waiter.  If it can, this waiter is
+woken.  futex_requeue() then proceeds to requeue the remaining
+nr_wake+nr_requeue tasks to the PI futex, calling
+rt_mutex_start_proxy_lock() prior to each requeue to prepare the
+task as a waiter on the underlying rt_mutex.  It is possible that
+the lock can be acquired at this stage as well, if so, the next
+waiter is woken to finish the acquisition of the lock.
+
+FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
+their sum is all that really matters.  futex_requeue() will wake or
+requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
+tasks as it can acquire the lock for, which in the majority of cases
+should be 0 as good programming practice dictates that the caller of
+either pthread_cond_broadcast() or pthread_cond_signal() acquire the
+mutex prior to making the call. FUTEX_REQUEUE_PI requires that
+nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
+signal.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fd5cac01303..4a3c2209a12 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -56,7 +56,6 @@ parameter is applicable:
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
 	JOY	Appropriate joystick support is enabled.
-	KMEMTRACE kmemtrace is enabled.
 	LIBATA  Libata driver is enabled
 	LP	Printer support is enabled.
 	LOOP	Loopback device support is enabled.
@@ -329,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file
 				    flushed before they will be reused, which
 				    is a lot of faster
 
-	amd_iommu_size= [HW,X86-64]
-			Define the size of the aperture for the AMD IOMMU
-			driver. Possible values are:
-			'32M', '64M' (default), '128M', '256M', '512M', '1G'
-
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -646,6 +640,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			DMA-API debugging code disables itself because the
 			architectural default is too low.
 
+	dma_debug_driver=<driver_name>
+			With this option the DMA-API debugging driver
+			filter feature can be enabled at boot time. Just
+			pass the driver to filter for as the parameter.
+			The filter can be disabled or changed to another
+			driver later using sysfs.
+
 	dscc4.setup=	[NET]
 
 	dtc3181e=	[HW,SCSI]
@@ -752,12 +753,25 @@ and is between 256 and 4096 characters. It is defined in the file
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
 	ftrace=[tracer]
-			[ftrace] will set and start the specified tracer
+			[FTRACE] will set and start the specified tracer
 			as early as possible in order to facilitate early
 			boot debugging.
 
 	ftrace_dump_on_oops
-			[ftrace] will dump the trace buffers on oops.
+			[FTRACE] will dump the trace buffers on oops.
+
+	ftrace_filter=[function-list]
+			[FTRACE] Limit the functions traced by the function
+			tracer at boot up. function-list is a comma separated
+			list of functions. This list can be changed at run
+			time by the set_ftrace_filter file in the debugfs
+			tracing directory. 
+
+	ftrace_notrace=[function-list]
+			[FTRACE] Do not trace the functions specified in
+			function-list. This list can be changed at run time
+			by the set_ftrace_notrace file in the debugfs
+			tracing directory.
 
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
@@ -1054,15 +1068,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			use the HighMem zone if it exists, and the Normal
 			zone if it does not.
 
-	kmemtrace.enable=	[KNL,KMEMTRACE] Format: { yes | no }
-				Controls whether kmemtrace is enabled
-				at boot-time.
-
-	kmemtrace.subbufs=n	[KNL,KMEMTRACE] Overrides the number of
-			subbufs kmemtrace's relay channel has. Set this
-			higher than default (KMEMTRACE_N_SUBBUFS in code) if
-			you experience buffer overruns.
-
 	kgdboc=		[HW] kgdb over consoles.
 			Requires a tty driver that supports console polling.
 			(only serial suported for now)
@@ -1575,6 +1580,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
+	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+			remapping.
+
 	nointroute	[IA-64]
 
 	nojitter	[IA64] Disables jitter checking for ITC timers.
@@ -1660,6 +1668,14 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.timer=	[HW]
 			Use timer interrupt instead of performance counters
 
+	oprofile.cpu_type=	Force an oprofile cpu type
+			This might be useful if you have an older oprofile
+			userland or if you want common events.
+			Format: { archperfmon }
+			archperfmon: [X86] Force use of architectural
+				perfmon on Intel CPUs instead of the
+				CPU specific event set.
+
 	osst=		[HW,SCSI] SCSI Tape Driver
 			Format: <buffer_size>,<write_threshold>
 			See also Documentation/scsi/st.txt.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f5b7127f54a..7f5809eddee 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -31,6 +31,7 @@ Contents:
 
      - Locking functions.
      - Interrupt disabling functions.
+     - Sleep and wake-up functions.
      - Miscellaneous functions.
 
  (*) Inter-CPU locking barrier effects.
@@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
 other means.
 
 
+SLEEP AND WAKE-UP FUNCTIONS
+---------------------------
+
+Sleeping and waking on an event flagged in global data can be viewed as an
+interaction between two pieces of data: the task state of the task waiting for
+the event and the global data used to indicate the event.  To make sure that
+these appear to happen in the right order, the primitives to begin the process
+of going to sleep, and the primitives to initiate a wake up imply certain
+barriers.
+
+Firstly, the sleeper normally follows something like this sequence of events:
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (event_indicated)
+			break;
+		schedule();
+	}
+
+A general memory barrier is interpolated automatically by set_current_state()
+after it has altered the task state:
+
+	CPU 1
+	===============================
+	set_current_state();
+	  set_mb();
+	    STORE current->state
+	    <general barrier>
+	LOAD event_indicated
+
+set_current_state() may be wrapped by:
+
+	prepare_to_wait();
+	prepare_to_wait_exclusive();
+
+which therefore also imply a general memory barrier after setting the state.
+The whole sequence above is available in various canned forms, all of which
+interpolate the memory barrier in the right place:
+
+	wait_event();
+	wait_event_interruptible();
+	wait_event_interruptible_exclusive();
+	wait_event_interruptible_timeout();
+	wait_event_killable();
+	wait_event_timeout();
+	wait_on_bit();
+	wait_on_bit_lock();
+
+
+Secondly, code that performs a wake up normally follows something like this:
+
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+or:
+
+	event_indicated = 1;
+	wake_up_process(event_daemon);
+
+A write memory barrier is implied by wake_up() and co. if and only if they wake
+something up.  The barrier occurs before the task state is cleared, and so sits
+between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+
+	CPU 1				CPU 2
+	===============================	===============================
+	set_current_state();		STORE event_indicated
+	  set_mb();			wake_up();
+	    STORE current->state	  <write barrier>
+	    <general barrier>		  STORE current->state
+	LOAD event_indicated
+
+The available waker functions include:
+
+	complete();
+	wake_up();
+	wake_up_all();
+	wake_up_bit();
+	wake_up_interruptible();
+	wake_up_interruptible_all();
+	wake_up_interruptible_nr();
+	wake_up_interruptible_poll();
+	wake_up_interruptible_sync();
+	wake_up_interruptible_sync_poll();
+	wake_up_locked();
+	wake_up_locked_poll();
+	wake_up_nr();
+	wake_up_poll();
+	wake_up_process();
+
+
+[!] Note that the memory barriers implied by the sleeper and the waker do _not_
+order multiple stores before the wake-up with respect to loads of those stored
+values after the sleeper has called set_current_state().  For instance, if the
+sleeper does:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated)
+		break;
+	__set_current_state(TASK_RUNNING);
+	do_something(my_data);
+
+and the waker does:
+
+	my_data = value;
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+there's no guarantee that the change to event_indicated will be perceived by
+the sleeper as coming after the change to my_data.  In such a circumstance, the
+code on both sides must interpolate its own memory barriers between the
+separate data accesses.  Thus the above sleeper ought to do:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated) {
+		smp_rmb();
+		do_something(my_data);
+	}
+
+and the waker should do:
+
+	my_data = value;
+	smp_wmb();
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+
 MISCELLANEOUS FUNCTIONS
 -----------------------
 
@@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
 
 Under normal operation, memory operation reordering is generally not going to
 be a problem as a single-threaded linear piece of code will still appear to
-work correctly, even if it's in an SMP kernel.  There are, however, three
+work correctly, even if it's in an SMP kernel.  There are, however, four
 circumstances in which reordering definitely _could_ be a problem:
 
  (*) Interprocessor interaction.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 5ba4d3fc625..1df7f9cdab0 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -4,6 +4,7 @@
 CONTENTS
 ========
 
+0. WARNING
 1. Overview
   1.1 The problem
   1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS
 3. Future plans
 
 
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+   system when the period is smaller than either the available hrtimer
+   resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+   system when the runtime is so small the system has difficulty making
+   forward progress (NOTE: the migration thread and kstopmachine both
+   are real-time processes).
+
 1. Overview
 ===========
 
@@ -169,7 +187,7 @@ get their allocated time.
 
 Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-139. With deadline scheduling you need to
+the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
 deadline delta (deadline - now).
 
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
new file mode 100644
index 00000000000..f157d7594ea
--- /dev/null
+++ b/Documentation/trace/events.txt
@@ -0,0 +1,90 @@
+			     Event Tracing
+
+		Documentation written by Theodore Ts'o
+			Updated by Li Zefan
+
+1. Introduction
+===============
+
+Tracepoints (see Documentation/trace/tracepoints.txt) can be used
+without creating custom kernel modules to register probe functions
+using the event tracing infrastructure.
+
+Not all tracepoints can be traced using the event tracing system;
+the kernel developer must provide code snippets which define how the
+tracing information is saved into the tracing buffer, and how the
+tracing information should be printed.
+
+2. Using Event Tracing
+======================
+
+2.1 Via the 'set_event' interface
+---------------------------------
+
+The events which are available for tracing can be found in the file
+/debug/tracing/available_events.
+
+To enable a particular event, such as 'sched_wakeup', simply echo it
+to /debug/tracing/set_event. For example:
+
+	# echo sched_wakeup >> /debug/tracing/set_event
+
+[ Note: '>>' is necessary, otherwise it will firstly disable
+  all the events. ]
+
+To disable an event, echo the event name to the set_event file prefixed
+with an exclamation point:
+
+	# echo '!sched_wakeup' >> /debug/tracing/set_event
+
+To disable all events, echo an empty line to the set_event file:
+
+	# echo > /debug/tracing/set_event
+
+To enable all events, echo '*:*' or '*:' to the set_event file:
+
+	# echo *:* > /debug/tracing/set_event
+
+The events are organized into subsystems, such as ext4, irq, sched,
+etc., and a full event name looks like this: <subsystem>:<event>.  The
+subsystem name is optional, but it is displayed in the available_events
+file.  All of the events in a subsystem can be specified via the syntax
+"<subsystem>:*"; for example, to enable all irq events, you can use the
+command:
+
+	# echo 'irq:*' > /debug/tracing/set_event
+
+2.2 Via the 'enable' toggle
+---------------------------
+
+The events available are also listed in /debug/tracing/events/ hierarchy
+of directories.
+
+To enable event 'sched_wakeup':
+
+	# echo 1 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To disable it:
+
+	# echo 0 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To enable all events in sched subsystem:
+
+	# echo 1 > /debug/tracing/events/sched/enable
+
+To eanble all events:
+
+	# echo 1 > /debug/tracing/events/enable
+
+When reading one of these enable files, there are four results:
+
+ 0 - all events this file affects are disabled
+ 1 - all events this file affects are enabled
+ X - there is a mixture of events enabled and disabled
+ ? - this file does not affect any event
+
+3. Defining an event-enabled tracepoint
+=======================================
+
+See The example provided in samples/trace_events
+
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index fd9a3e69381..2a82d860294 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured.
 
 	Function call tracer to trace all kernel functions.
 
-  "function_graph_tracer"
+  "function_graph"
 
 	Similar to the function tracer except that the
 	function tracer probes the functions on their entry
@@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice
 values starting at 100 (nice -20). Below is a quick chart to map
 the kernel priority to user land priorities.
 
-  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
-  Kernel priority: 100 to 139 ==> user nice -20 to 19
-  Kernel priority: 140        ==> idle task priority
+   Kernel Space                     User Space
+ ===============================================================
+   0(high) to  98(low)     user RT priority 99(high) to 1(low)
+                           with SCHED_RR or SCHED_FIFO
+ ---------------------------------------------------------------
+  99                       sched_priority is not used in scheduling
+                           decisions(it must be specified as 0)
+ ---------------------------------------------------------------
+ 100(high) to 139(low)     user nice -20(high) to 19(low)
+ ---------------------------------------------------------------
+ 140                       idle task priority
+ ---------------------------------------------------------------
 
 The task states are:
 
diff --git a/Documentation/trace/power.txt b/Documentation/trace/power.txt
new file mode 100644
index 00000000000..cd805e16dc2
--- /dev/null
+++ b/Documentation/trace/power.txt
@@ -0,0 +1,17 @@
+The power tracer collects detailed information about C-state and P-state
+transitions, instead of just looking at the high-level "average"
+information.
+
+There is a helper script found in scrips/tracing/power.pl in the kernel
+sources which can be used to parse this information and create a
+Scalable Vector Graphics (SVG) picture from the trace data.
+
+To use this tracer:
+
+	echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+	echo power > /sys/kernel/debug/tracing/current_tracer
+	echo 1 > /sys/kernel/debug/tracing/tracing_enabled
+	sleep 1
+	echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+	cat /sys/kernel/debug/tracing/trace | \
+		perl scripts/tracing/power.pl > out.sv
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index e0203662f9e..8da3a795083 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -50,6 +50,10 @@ Protocol 2.08:	(Kernel 2.6.26) Added crc32 checksum and ELF format
 Protocol 2.09:	(Kernel 2.6.26) Added a field of 64-bit physical
 		pointer to single linked list of struct	setup_data.
 
+Protocol 2.10:	(Kernel 2.6.31) Added a protocol for relaxed alignment
+		beyond the kernel_alignment added, new init_size and
+		pref_address fields.  Added extended boot loader IDs.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -168,12 +172,13 @@ Offset	Proto	Name		Meaning
 021C/4	2.00+	ramdisk_size	initrd size (set by boot loader)
 0220/4	2.00+	bootsect_kludge	DO NOT USE - for bootsect.S use only
 0224/2	2.01+	heap_end_ptr	Free memory after setup end
-0226/2	N/A	pad1		Unused
+0226/1	2.02+(3 ext_loader_ver	Extended boot loader version
+0227/1	2.02+(3	ext_loader_type	Extended boot loader ID
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
 022C/4	2.03+	ramdisk_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
-0235/1	N/A	pad2		Unused
+0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
 0236/2	N/A	pad3		Unused
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
@@ -182,6 +187,8 @@ Offset	Proto	Name		Meaning
 024C/4	2.08+	payload_length	Length of kernel payload
 0250/8	2.09+	setup_data	64-bit physical pointer to linked list
 				of struct setup_data
+0258/8	2.10+	pref_address	Preferred loading address
+0260/4	2.10+	init_size	Linear memory required during initialization
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -190,6 +197,8 @@ Offset	Proto	Name		Meaning
     field are unusable, which means the size of a bzImage kernel
     cannot be determined.
 
+(3) Ignored, but safe to set, for boot protocols 2.02-2.09.
+
 If the "HdrS" (0x53726448) magic number is not found at offset 0x202,
 the boot protocol version is "old".  Loading an old kernel, the
 following parameters should be assumed:
@@ -343,18 +352,32 @@ Protocol:	2.00+
   0xTV here, where T is an identifier for the boot loader and V is
   a version number.  Otherwise, enter 0xFF here.
 
+  For boot loader IDs above T = 0xD, write T = 0xE to this field and
+  write the extended ID minus 0x10 to the ext_loader_type field.
+  Similarly, the ext_loader_ver field can be used to provide more than
+  four bits for the bootloader version.
+
+  For example, for T = 0x15, V = 0x234, write:
+
+  type_of_loader  <- 0xE4
+  ext_loader_type <- 0x05
+  ext_loader_ver  <- 0x23
+
   Assigned boot loader ids:
 	0  LILO			(0x00 reserved for pre-2.00 bootloader)
 	1  Loadlin
 	2  bootsect-loader	(0x20, all other values reserved)
-	3  SYSLINUX
-	4  EtherBoot
+	3  Syslinux
+	4  Etherboot/gPXE
 	5  ELILO
 	7  GRUB
-	8  U-BOOT
+	8  U-Boot
 	9  Xen
 	A  Gujin
 	B  Qemu
+	C  Arcturus Networks uCbootloader
+	E  Extended		(see ext_loader_type)
+	F  Special		(0xFF = undefined)
 
   Please contact <hpa@zytor.com> if you need a bootloader ID
   value assigned.
@@ -453,6 +476,35 @@ Protocol:	2.01+
   Set this field to the offset (from the beginning of the real-mode
   code) of the end of the setup stack/heap, minus 0x0200.
 
+Field name:	ext_loader_ver
+Type:		write (optional)
+Offset/size:	0x226/1
+Protocol:	2.02+
+
+  This field is used as an extension of the version number in the
+  type_of_loader field.  The total version number is considered to be
+  (type_of_loader & 0x0f) + (ext_loader_ver << 4).
+
+  The use of this field is boot loader specific.  If not written, it
+  is zero.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
+Field name:	ext_loader_type
+Type:		write (obligatory if (type_of_loader & 0xf0) == 0xe0)
+Offset/size:	0x227/1
+Protocol:	2.02+
+
+  This field is used as an extension of the type number in
+  type_of_loader field.  If the type in type_of_loader is 0xE, then
+  the actual type is (ext_loader_type + 0x10).
+
+  This field is ignored if the type in type_of_loader is not 0xE.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
 Field name:	cmd_line_ptr
 Type:		write (obligatory)
 Offset/size:	0x228/4
@@ -482,11 +534,19 @@ Protocol:	2.03+
   0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
 
 Field name:	kernel_alignment
-Type:		read (reloc)
+Type:		read/modify (reloc)
 Offset/size:	0x230/4
-Protocol:	2.05+
+Protocol:	2.05+ (read), 2.10+ (modify)
+
+  Alignment unit required by the kernel (if relocatable_kernel is
+  true.)  A relocatable kernel that is loaded at an alignment
+  incompatible with the value in this field will be realigned during
+  kernel initialization.
 
-  Alignment unit required by the kernel (if relocatable_kernel is true.)
+  Starting with protocol version 2.10, this reflects the kernel
+  alignment preferred for optimal performance; it is possible for the
+  loader to modify this field to permit a lesser alignment.  See the
+  min_alignment and pref_address field below.
 
 Field name:	relocatable_kernel
 Type:		read (reloc)
@@ -498,6 +558,22 @@ Protocol:	2.05+
   After loading, the boot loader must set the code32_start field to
   point to the loaded code, or to a boot loader hook.
 
+Field name:	min_alignment
+Type:		read (reloc)
+Offset/size:	0x235/1
+Protocol:	2.10+
+
+  This field, if nonzero, indicates as a power of two the minimum
+  alignment required, as opposed to preferred, by the kernel to boot.
+  If a boot loader makes use of this field, it should update the
+  kernel_alignment field with the alignment unit desired; typically:
+
+	kernel_alignment = 1 << min_alignment
+
+  There may be a considerable performance cost with an excessively
+  misaligned kernel.  Therefore, a loader should typically try each
+  power-of-two alignment from kernel_alignment down to this alignment.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
@@ -582,6 +658,36 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+Field name:	pref_address
+Type:		read (reloc)
+Offset/size:	0x258/8
+Protocol:	2.10+
+
+  This field, if nonzero, represents a preferred load address for the
+  kernel.  A relocating bootloader should attempt to load at this
+  address if possible.
+
+  A non-relocatable kernel will unconditionally move itself and to run
+  at this address.
+
+Field name:	init_size
+Type:		read
+Offset/size:	0x25c/4
+
+  This field indicates the amount of linear contiguous memory starting
+  at the kernel runtime start address that the kernel needs before it
+  is capable of examining its memory map.  This is not the same thing
+  as the total amount of memory the kernel needs to boot, but it can
+  be used by a relocating boot loader to help select a safe load
+  address for the kernel.
+
+  The kernel runtime start address is determined by the following algorithm:
+
+  if (relocatable_kernel)
+	runtime_start = align_up(load_address, kernel_alignment)
+  else
+	runtime_start = pref_address
+
 
 **** THE IMAGE CHECKSUM
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 34c13040a71..2db5893d6c9 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -150,11 +150,6 @@ NUMA
 		Otherwise, the remaining system RAM is allocated to an
 		additional node.
 
-  numa=hotadd=percent
-		Only allow hotadd memory to preallocate page structures upto
-		percent of already available memory.
-		numa=hotadd=0 will disable hotadd memory.
-
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 29b52b14d0b..d6498e3cd71 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
-ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
+ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
+ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
+ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
+ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
+ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
diff --git a/Makefile b/Makefile
index 610d1c332c4..03373bb703c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 30
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Man-Eating Seals of Antiquity
 
 # *DOCUMENTATION*
@@ -533,7 +533,7 @@ endif
 
 include $(srctree)/arch/$(SRCARCH)/Makefile
 
-ifneq (CONFIG_FRAME_WARN,0)
+ifneq ($(CONFIG_FRAME_WARN),0)
 KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 9c9d1fd4155..5bd5259324b 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 	}
 }
 
-static void
+static int
 dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
-static void
+static int
 clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq - 16, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
 static struct hw_interrupt_type dp264_irq_type = {
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index 27f840a4ad3..8dd239ebdb9 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 
 }
 
-static void
+static int
 titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&titan_irq_lock);
 	titan_cpu_set_irq_affinity(irq - 16, *affinity);
 	titan_update_irq_hw(titan_cached_irq_mask);
 	spin_unlock(&titan_irq_lock);
+
+	return 0;
 }
 
 static void
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 3e1714c6523..664c7b8b1ba 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
+static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 {
 	void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
 	unsigned int shift = (irq % 4) * 8;
@@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 	val |= 1 << (cpu + shift);
 	writel(val, reg);
 	spin_unlock(&irq_controller_lock);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index cb7a9e97fd7..feaa75f0013 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -7,4 +7,20 @@
 #define L1_CACHE_SHIFT		5
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+/*
+ * Memory returned by kmalloc() may be used for DMA, so we must make
+ * sure that all such allocations are cache aligned. Otherwise,
+ * unrelated code may cause parts of the buffer to be read into the
+ * cache before the transfer is done, causing old data to be seen by
+ * the CPU.
+ */
+#define ARCH_KMALLOC_MINALIGN	L1_CACHE_BYTES
+
+/*
+ * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
+ */
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+#define ARCH_SLAB_MINALIGN 8
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index e6eb8a67b80..7b522770f29 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -202,13 +202,6 @@ typedef struct page *pgtable_t;
 	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
 	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-/*
- * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
- */
-#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
-#define ARCH_SLAB_MINALIGN 8
-#endif
-
 #include <asm-generic/page.h>
 
 #endif
diff --git a/arch/arm/mach-mx2/clock_imx21.c b/arch/arm/mach-mx2/clock_imx21.c
index 999d013e06e..e4b08ca804e 100644
--- a/arch/arm/mach-mx2/clock_imx21.c
+++ b/arch/arm/mach-mx2/clock_imx21.c
@@ -890,7 +890,7 @@ static struct clk clko_clk = {
 		.con_id = n, \
 		.clk = &c, \
 	},
-static struct clk_lookup lookups[] __initdata = {
+static struct clk_lookup lookups[] = {
 /* It's unlikely that any driver wants one of them directly:
 	_REGISTER_CLOCK(NULL, "ckih", ckih_clk)
 	_REGISTER_CLOCK(NULL, "ckil", ckil_clk)
diff --git a/arch/arm/mach-mx2/clock_imx27.c b/arch/arm/mach-mx2/clock_imx27.c
index 3f7280c490f..2c971442f3f 100644
--- a/arch/arm/mach-mx2/clock_imx27.c
+++ b/arch/arm/mach-mx2/clock_imx27.c
@@ -621,7 +621,7 @@ DEFINE_CLOCK1(csi_clk,     0, 0,      0, parent, &csi_clk1, &per4_clk);
 		.clk = &c, \
 	},
 
-static struct clk_lookup lookups[] __initdata = {
+static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK("imx-uart.0", NULL, uart1_clk)
 	_REGISTER_CLOCK("imx-uart.1", NULL, uart2_clk)
 	_REGISTER_CLOCK("imx-uart.2", NULL, uart3_clk)
diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c
index 53a112d4e04..3c1e06f56dd 100644
--- a/arch/arm/mach-mx3/clock-imx35.c
+++ b/arch/arm/mach-mx3/clock-imx35.c
@@ -404,7 +404,7 @@ DEFINE_CLOCK(gpu2d_clk,  0, CCM_CGR3,  4, NULL, NULL);
 		.clk = &c,		\
 	},
 
-static struct clk_lookup lookups[] __initdata = {
+static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "asrc", asrc_clk)
 	_REGISTER_CLOCK(NULL, "ata", ata_clk)
 	_REGISTER_CLOCK(NULL, "audmux", audmux_clk)
diff --git a/arch/arm/mach-mx3/clock.c b/arch/arm/mach-mx3/clock.c
index 9957a11533a..a68fcf981ed 100644
--- a/arch/arm/mach-mx3/clock.c
+++ b/arch/arm/mach-mx3/clock.c
@@ -516,7 +516,7 @@ DEFINE_CLOCK(ipg_clk,     0, NULL,          0, ipg_get_rate, NULL, &ahb_clk);
 		.clk = &c, \
 	},
 
-static struct clk_lookup lookups[] __initdata = {
+static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "emi", emi_clk)
 	_REGISTER_CLOCK(NULL, "cspi", cspi1_clk)
 	_REGISTER_CLOCK(NULL, "cspi", cspi2_clk)
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index d245e59c51b..29970f703f3 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -72,7 +72,10 @@ void __init pxa_set_mci_info(struct pxamci_platform_data *info)
 }
 
 
-static struct pxa2xx_udc_mach_info pxa_udc_info;
+static struct pxa2xx_udc_mach_info pxa_udc_info = {
+	.gpio_pullup = -1,
+	.gpio_vbus   = -1,
+};
 
 void __init pxa_set_udc_info(struct pxa2xx_udc_mach_info *info)
 {
diff --git a/arch/arm/mach-pxa/imote2.c b/arch/arm/mach-pxa/imote2.c
index 2121309b247..2b27336c29f 100644
--- a/arch/arm/mach-pxa/imote2.c
+++ b/arch/arm/mach-pxa/imote2.c
@@ -412,7 +412,7 @@ static struct platform_device imote2_flash_device = {
  */
 static struct i2c_board_info __initdata imote2_i2c_board_info[] = {
 	{ /* UCAM sensor board */
-		.type = "max1238",
+		.type = "max1239",
 		.addr = 0x35,
 	}, { /* ITS400 Sensor board only */
 		.type = "max1363",
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3397f1e64d7..a08d9d2380d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -184,23 +184,37 @@ __v7_setup:
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
 	bl	v7_flush_dcache_all
 	ldmia	r12, {r0-r5, r7, r9, r11, lr}
+
+	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
+	and	r10, r0, #0xff000000		@ ARM?
+	teq	r10, #0x41000000
+	bne	2f
+	and	r5, r0, #0x00f00000		@ variant
+	and	r6, r0, #0x0000000f		@ revision
+	orr	r0, r6, r5, lsr #20-4		@ combine variant and revision
+
 #ifdef CONFIG_ARM_ERRATA_430973
-	mrc	p15, 0, r10, c1, c0, 1		@ read aux control register
-	orr	r10, r10, #(1 << 6)		@ set IBE to 1
-	mcr	p15, 0, r10, c1, c0, 1		@ write aux control register
+	teq	r5, #0x00100000			@ only present in r1p*
+	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
+	orreq	r10, r10, #(1 << 6)		@ set IBE to 1
+	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-	mrc	p15, 0, r10, c1, c0, 1		@ read aux control register
-	orr	r10, r10, #(1 << 5)		@ set L1NEON to 1
-	orr	r10, r10, #(1 << 9)		@ set PLDNOP to 1
-	mcr	p15, 0, r10, c1, c0, 1		@ write aux control register
+	teq	r0, #0x20			@ only present in r2p0
+	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
+	orreq	r10, r10, #(1 << 5)		@ set L1NEON to 1
+	orreq	r10, r10, #(1 << 9)		@ set PLDNOP to 1
+	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-	mrc	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
-	orr	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
-	mcr	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
+	teq	r0, #0x20			@ only present in r2p0
+	mrceq	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
+	tsteq	r10, #1 << 22
+	orreq	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
+	mcreq	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
 #endif
-	mov	r10, #0
+
+2:	mov	r10, #0
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 #endif
diff --git a/arch/cris/arch-v32/kernel/irq.c b/arch/cris/arch-v32/kernel/irq.c
index df3925cb1c7..d70b445f4a8 100644
--- a/arch/cris/arch-v32/kernel/irq.c
+++ b/arch/cris/arch-v32/kernel/irq.c
@@ -325,12 +325,14 @@ static void end_crisv32_irq(unsigned int irq)
 {
 }
 
-void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
+int set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&irq_lock, flags);
 	irq_allocations[irq - FIRST_IRQ].mask = *dest;
 	spin_unlock_irqrestore(&irq_lock, flags);
+
+	return 0;
 }
 
 static struct irq_chip crisv32_irq_type = {
diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c
index cc0a3182db3..acb5047ab57 100644
--- a/arch/ia64/hp/sim/hpsim_irq.c
+++ b/arch/ia64/hp/sim/hpsim_irq.c
@@ -21,9 +21,10 @@ hpsim_irq_noop (unsigned int irq)
 {
 }
 
-static void
+static int
 hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
 {
+	return 0;
 }
 
 static struct hw_interrupt_type irq_type_hp_sim = {
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 5510317db37..baec6f00f7f 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -636,7 +636,7 @@ void __init acpi_numa_arch_fixup(void)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity)
 {
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM)
 		return gsi;
@@ -678,7 +678,8 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 
 	fadt = (struct acpi_table_fadt *)fadt_header;
 
-	acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW);
+	acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE,
+				 ACPI_ACTIVE_LOW);
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 166e0d839fa..f92cef47bf8 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -329,7 +329,7 @@ unmask_irq (unsigned int irq)
 }
 
 
-static void
+static int
 iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 #ifdef CONFIG_SMP
@@ -343,15 +343,15 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	cpu = cpumask_first_and(cpu_online_mask, mask);
 	if (cpu >= nr_cpu_ids)
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	dest = cpu_physical_id(cpu);
 
 	if (!iosapic_intr_info[irq].count)
-		return;			/* not an IOSAPIC interrupt */
+		return -1;			/* not an IOSAPIC interrupt */
 
 	set_irq_affinity_info(irq, dest, redir);
 
@@ -376,7 +376,9 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 		iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
 		iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
 	}
+
 #endif
+	return 0;
 }
 
 /*
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 2b15e233f7f..0f8ade9331b 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -12,7 +12,7 @@
 static struct irq_chip	ia64_msi_chip;
 
 #ifdef CONFIG_SMP
-static void ia64_set_msi_irq_affinity(unsigned int irq,
+static int ia64_set_msi_irq_affinity(unsigned int irq,
 				      const cpumask_t *cpu_mask)
 {
 	struct msi_msg msg;
@@ -20,10 +20,10 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 	int cpu = first_cpu(*cpu_mask);
 
 	if (!cpu_online(cpu))
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	read_msi_msg(irq, &msg);
 
@@ -39,6 +39,8 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 
 	write_msi_msg(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
@@ -130,17 +132,17 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #ifdef CONFIG_DMAR
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
 	struct msi_msg msg;
 	int cpu = cpumask_first(mask);
 
 	if (!cpu_online(cpu))
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	dmar_msi_read(irq, &msg);
 
@@ -151,6 +153,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dmar_msi_write(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, mask);
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index 66fd705e82c..764f26abac0 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -227,7 +227,7 @@ finish_up:
 	return new_irq_info;
 }
 
-static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
+static int sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
 {
 	struct sn_irq_info *sn_irq_info, *sn_irq_info_safe;
 	nasid_t nasid;
@@ -239,6 +239,8 @@ static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
 	list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe,
 				 sn_irq_lh[irq], list)
 		(void)sn_retarget_vector(sn_irq_info, nasid, slice);
+
+	return 0;
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 81e428943d7..fbbfb970120 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -151,7 +151,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry)
 }
 
 #ifdef CONFIG_SMP
-static void sn_set_msi_irq_affinity(unsigned int irq,
+static int sn_set_msi_irq_affinity(unsigned int irq,
 				    const struct cpumask *cpu_mask)
 {
 	struct msi_msg msg;
@@ -168,7 +168,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 	cpu = cpumask_first(cpu_mask);
 	sn_irq_info = sn_msi_info[irq].sn_irq_info;
 	if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0)
-		return;
+		return -1;
 
 	/*
 	 * Release XIO resources for the old MSI PCI address
@@ -189,7 +189,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 	new_irq_info = sn_retarget_vector(sn_irq_info, nasid, slice);
 	sn_msi_info[irq].sn_irq_info = new_irq_info;
 	if (new_irq_info == NULL)
-		return;
+		return -1;
 
 	/*
 	 * Map the xio address into bus space
@@ -206,6 +206,8 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 
 	write_msi_msg(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, cpu_mask);
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 09b1287a92c..25f3b0a11ca 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -72,6 +72,7 @@ config MIPS_COBALT
 	select IRQ_CPU
 	select IRQ_GT641XX
 	select PCI_GT64XXX_PCI0
+	select PCI
 	select SYS_HAS_CPU_NEVADA
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -593,7 +594,7 @@ config WR_PPMC
 	  board, which is based on GT64120 bridge chip.
 
 config CAVIUM_OCTEON_SIMULATOR
-	bool "Support for the Cavium Networks Octeon Simulator"
+	bool "Cavium Networks Octeon Simulator"
 	select CEVT_R4K
 	select 64BIT_PHYS_ADDR
 	select DMA_COHERENT
@@ -607,7 +608,7 @@ config CAVIUM_OCTEON_SIMULATOR
 	  hardware.
 
 config CAVIUM_OCTEON_REFERENCE_BOARD
-	bool "Support for the Cavium Networks Octeon reference board"
+	bool "Cavium Networks Octeon reference board"
 	select CEVT_R4K
 	select 64BIT_PHYS_ADDR
 	select DMA_COHERENT
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 1c19af8daa6..d3a0c8154be 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -177,7 +177,7 @@ static void octeon_irq_ciu0_disable(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
+static int octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu;
 	int bit = irq - OCTEON_IRQ_WORKQ0;	/* Bit 0-63 of EN0 */
@@ -199,6 +199,8 @@ static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask
 	 */
 	cvmx_read_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2));
 	write_unlock(&octeon_irq_ciu0_rwlock);
+
+	return 0;
 }
 #endif
 
@@ -292,7 +294,7 @@ static void octeon_irq_ciu1_disable(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
+static int octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu;
 	int bit = irq - OCTEON_IRQ_WDOG0;	/* Bit 0-63 of EN1 */
@@ -315,6 +317,8 @@ static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask
 	 */
 	cvmx_read_csr(CVMX_CIU_INTX_EN1(cvmx_get_core_num() * 2 + 1));
 	write_unlock(&octeon_irq_ciu1_rwlock);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index 744cd8fb107..126044308de 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -39,8 +39,8 @@ struct cache_desc {
 #define MIPS_CACHE_PINDEX	0x00000020	/* Physically indexed cache */
 
 struct cpuinfo_mips {
-	unsigned long		udelay_val;
-	unsigned long		asid_cache;
+	unsigned int		udelay_val;
+	unsigned int		asid_cache;
 
 	/*
 	 * Capability and feature descriptor structure for MIPS CPU
diff --git a/arch/mips/include/asm/delay.h b/arch/mips/include/asm/delay.h
index b0bccd2c4ed..a07e51b2be1 100644
--- a/arch/mips/include/asm/delay.h
+++ b/arch/mips/include/asm/delay.h
@@ -11,94 +11,12 @@
 #ifndef _ASM_DELAY_H
 #define _ASM_DELAY_H
 
-#include <linux/param.h>
-#include <linux/smp.h>
+extern void __delay(unsigned int loops);
+extern void __ndelay(unsigned int ns);
+extern void __udelay(unsigned int us);
 
-#include <asm/compiler.h>
-#include <asm/war.h>
-
-static inline void __delay(unsigned long loops)
-{
-	if (sizeof(long) == 4)
-		__asm__ __volatile__ (
-		"	.set	noreorder				\n"
-		"	.align	3					\n"
-		"1:	bnez	%0, 1b					\n"
-		"	subu	%0, 1					\n"
-		"	.set	reorder					\n"
-		: "=r" (loops)
-		: "0" (loops));
-	else if (sizeof(long) == 8 && !DADDI_WAR)
-		__asm__ __volatile__ (
-		"	.set	noreorder				\n"
-		"	.align	3					\n"
-		"1:	bnez	%0, 1b					\n"
-		"	dsubu	%0, 1					\n"
-		"	.set	reorder					\n"
-		: "=r" (loops)
-		: "0" (loops));
-	else if (sizeof(long) == 8 && DADDI_WAR)
-		__asm__ __volatile__ (
-		"	.set	noreorder				\n"
-		"	.align	3					\n"
-		"1:	bnez	%0, 1b					\n"
-		"	dsubu	%0, %2					\n"
-		"	.set	reorder					\n"
-		: "=r" (loops)
-		: "0" (loops), "r" (1));
-}
-
-
-/*
- * Division by multiplication: you don't have to worry about
- * loss of precision.
- *
- * Use only for very small delays ( < 1 msec).  Should probably use a
- * lookup table, really, as the multiplications take much too long with
- * short delays.  This is a "reasonable" implementation, though (and the
- * first constant multiplications gets optimized away if the delay is
- * a constant)
- */
-
-static inline void __udelay(unsigned long usecs, unsigned long lpj)
-{
-	unsigned long hi, lo;
-
-	/*
-	 * The rates of 128 is rounded wrongly by the catchall case
-	 * for 64-bit.  Excessive precission?  Probably ...
-	 */
-#if defined(CONFIG_64BIT) && (HZ == 128)
-	usecs *= 0x0008637bd05af6c7UL;		/* 2**64 / (1000000 / HZ) */
-#elif defined(CONFIG_64BIT)
-	usecs *= (0x8000000000000000UL / (500000 / HZ));
-#else /* 32-bit junk follows here */
-	usecs *= (unsigned long) (((0x8000000000000000ULL / (500000 / HZ)) +
-	                           0x80000000ULL) >> 32);
-#endif
-
-	if (sizeof(long) == 4)
-		__asm__("multu\t%2, %3"
-		: "=h" (usecs), "=l" (lo)
-		: "r" (usecs), "r" (lpj)
-		: GCC_REG_ACCUM);
-	else if (sizeof(long) == 8 && !R4000_WAR)
-		__asm__("dmultu\t%2, %3"
-		: "=h" (usecs), "=l" (lo)
-		: "r" (usecs), "r" (lpj)
-		: GCC_REG_ACCUM);
-	else if (sizeof(long) == 8 && R4000_WAR)
-		__asm__("dmultu\t%3, %4\n\tmfhi\t%0"
-		: "=r" (usecs), "=h" (hi), "=l" (lo)
-		: "r" (usecs), "r" (lpj)
-		: GCC_REG_ACCUM);
-
-	__delay(usecs);
-}
-
-#define __udelay_val cpu_data[raw_smp_processor_id()].udelay_val
-
-#define udelay(usecs) __udelay((usecs), __udelay_val)
+#define ndelay(ns) __udelay(ns)
+#define udelay(us) __udelay(us)
 
 /* make sure "usecs *= ..." in udelay do not overflow. */
 #if HZ >= 1000
diff --git a/arch/mips/include/asm/ioctl.h b/arch/mips/include/asm/ioctl.h
index 85067e248a8..916163401b2 100644
--- a/arch/mips/include/asm/ioctl.h
+++ b/arch/mips/include/asm/ioctl.h
@@ -60,12 +60,16 @@
 	 ((nr)   << _IOC_NRSHIFT) | \
 	 ((size) << _IOC_SIZESHIFT))
 
+#ifdef __KERNEL__
 /* provoke compile error for invalid uses of size argument */
 extern unsigned int __invalid_size_argument_for_IOC;
 #define _IOC_TYPECHECK(t) \
 	((sizeof(t) == sizeof(t[1]) && \
 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
 	  sizeof(t) : __invalid_size_argument_for_IOC)
+#else
+#define _IOC_TYPECHECK(t)	(sizeof(t))
+#endif
 
 /* used to create numbers */
 #define _IO(type, nr)		_IOC(_IOC_NONE, (type), (nr), 0)
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 3214ade02d1..4f1eed107b0 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -49,7 +49,7 @@ static inline void smtc_im_ack_irq(unsigned int irq)
 #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
 #include <linux/cpumask.h>
 
-extern void plat_set_irq_affinity(unsigned int irq,
+extern int plat_set_irq_affinity(unsigned int irq,
 				  const struct cpumask *affinity);
 extern void smtc_forward_irq(unsigned int irq);
 
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 87deb8f6c45..3f43c2e3aa5 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq)
 
 static DEFINE_SPINLOCK(gic_lock);
 
-static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	cpumask_t	tmp = CPU_MASK_NONE;
 	unsigned long	flags;
@@ -166,7 +166,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 	cpumask_and(&tmp, cpumask, cpu_online_mask);
 	if (cpus_empty(tmp))
-		return;
+		return -1;
 
 	/* Assumption : cpumask refers to a single CPU */
 	spin_lock_irqsave(&gic_lock, flags);
@@ -190,6 +190,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	cpumask_copy(irq_desc[irq].affinity, cpumask);
 	spin_unlock_irqrestore(&gic_lock, flags);
 
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 26760cad8b6..e0a4ac18fa0 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -42,7 +42,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, fmt, __cpu_name[n],
 	                           (version >> 4) & 0x0f, version & 0x0f,
 	                           (fp_vers >> 4) & 0x0f, fp_vers & 0x0f);
-	seq_printf(m, "BogoMIPS\t\t: %lu.%02lu\n",
+	seq_printf(m, "BogoMIPS\t\t: %u.%02u\n",
 	              cpu_data[n].udelay_val / (500000/HZ),
 	              (cpu_data[n].udelay_val / (5000/HZ)) % 100);
 	seq_printf(m, "wait instruction\t: %s\n", cpu_wait ? "yes" : "no");
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index c13c7ad2cda..2adead5a8a3 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,8 +2,8 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o memcpy.o memcpy-inatomic.o memset.o strlen_user.o \
-	   strncpy_user.o strnlen_user.o uncached.o
+lib-y	+= csum_partial.o delay.o memcpy.o memcpy-inatomic.o memset.o \
+	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y			+= iomap.o
 obj-$(CONFIG_PCI)	+= iomap-pci.o
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
new file mode 100644
index 00000000000..f69c6b569eb
--- /dev/null
+++ b/arch/mips/lib/delay.c
@@ -0,0 +1,56 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994 by Waldorf Electronics
+ * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007  Maciej W. Rozycki
+ */
+#include <linux/module.h>
+#include <linux/param.h>
+#include <linux/smp.h>
+
+#include <asm/compiler.h>
+#include <asm/war.h>
+
+inline void __delay(unsigned int loops)
+{
+	__asm__ __volatile__ (
+	"	.set	noreorder				\n"
+	"	.align	3					\n"
+	"1:	bnez	%0, 1b					\n"
+	"	subu	%0, 1					\n"
+	"	.set	reorder					\n"
+	: "=r" (loops)
+	: "0" (loops));
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).  Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	unsigned int lpj = current_cpu_data.udelay_val;
+
+	__delay((us * 0x000010c7 * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	unsigned int lpj = current_cpu_data.udelay_val;
+
+	__delay((us * 0x00000005 * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index 5ba31888fef..499ffe5475d 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -114,7 +114,7 @@ struct plat_smp_ops msmtc_smp_ops = {
  */
 
 
-void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
+int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 {
 	cpumask_t tmask;
 	int cpu = 0;
@@ -156,5 +156,7 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 
 	/* Do any generic SMTC IRQ affinity setup */
 	smtc_set_irq_affinity(irq, tmask);
+
+	return 0;
 }
 #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index c147c4b35d3..690de06bde9 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -50,7 +50,7 @@ static void enable_bcm1480_irq(unsigned int irq);
 static void disable_bcm1480_irq(unsigned int irq);
 static void ack_bcm1480_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
+static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 
 #ifdef CONFIG_PCI
@@ -109,7 +109,7 @@ void bcm1480_unmask_irq(int cpu, int irq)
 }
 
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	int i = 0, old_cpu, cpu, int_on, k;
 	u64 cur_ints;
@@ -118,7 +118,7 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	if (cpumask_weight(mask) != 1) {
 		printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
-		return;
+		return -1;
 	}
 	i = cpumask_first(mask);
 
@@ -152,6 +152,8 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 		}
 	}
 	spin_unlock_irqrestore(&bcm1480_imr_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/sibyte/cfe/setup.c b/arch/mips/sibyte/cfe/setup.c
index 3de30f79db3..eb5396cf81b 100644
--- a/arch/mips/sibyte/cfe/setup.c
+++ b/arch/mips/sibyte/cfe/setup.c
@@ -288,13 +288,7 @@ void __init prom_init(void)
 	 */
 	cfe_cons_handle = cfe_getstdhandle(CFE_STDHANDLE_CONSOLE);
 	if (cfe_getenv("LINUX_CMDLINE", arcs_cmdline, CL_SIZE) < 0) {
-		if (argc < 0) {
-			/*
-			 * It's OK for direct boot to not provide a
-			 *  command line
-			 */
-			strcpy(arcs_cmdline, "root=/dev/ram0 ");
-		} else {
+		if (argc >= 0) {
 			/* The loader should have set the command line */
 			/* too early for panic to do any good */
 			printk("LINUX_CMDLINE not defined in cfe.");
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index 38cb998ade2..409dec79886 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -50,7 +50,7 @@ static void enable_sb1250_irq(unsigned int irq);
 static void disable_sb1250_irq(unsigned int irq);
 static void ack_sb1250_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
+static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 
 #ifdef CONFIG_SIBYTE_HAS_LDT
@@ -103,7 +103,7 @@ void sb1250_unmask_irq(int cpu, int irq)
 }
 
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	int i = 0, old_cpu, cpu, int_on;
 	u64 cur_ints;
@@ -113,7 +113,7 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	if (cpumask_weight(mask) > 1) {
 		printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
-		return;
+		return -1;
 	}
 
 	/* Convert logical CPU to physical CPU */
@@ -143,6 +143,8 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 					R_IMR_INTERRUPT_MASK));
 	}
 	spin_unlock_irqrestore(&sb1250_imr_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 4ea4229d765..8007f1e6572 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -130,15 +130,17 @@ int cpu_check_affinity(unsigned int irq, const struct cpumask *dest)
 	return cpu_dest;
 }
 
-static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
+static int cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu_dest;
 
 	cpu_dest = cpu_check_affinity(irq, dest);
 	if (cpu_dest < 0)
-		return;
+		return -1;
 
 	cpumask_copy(&irq_desc[irq].affinity, dest);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 80b513449f4..be3581a8c29 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -333,7 +333,7 @@ static void xics_eoi_lpar(unsigned int virq)
 	lpar_xirr_info_set((0xff << 24) | irq);
 }
 
-static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
+static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 {
 	unsigned int irq;
 	int status;
@@ -342,14 +342,14 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 
 	irq = (unsigned int)irq_map[virq].hwirq;
 	if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
-		return;
+		return -1;
 
 	status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq);
 
 	if (status) {
 		printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n",
 			__func__, irq, status);
-		return;
+		return -1;
 	}
 
 	/*
@@ -363,7 +363,7 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 		printk(KERN_WARNING
 			"%s: No online cpus in the mask %s for irq %d\n",
 			__func__, cpulist, virq);
-		return;
+		return -1;
 	}
 
 	status = rtas_call(ibm_set_xive, 3, 1, NULL,
@@ -372,8 +372,10 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 	if (status) {
 		printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n",
 			__func__, irq, status);
-		return;
+		return -1;
 	}
+
+	return 0;
 }
 
 static struct irq_chip xics_pic_direct = {
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0efc12d1a3d..352d8c3ef52 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq)
 
 #endif /* CONFIG_SMP */
 
-void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct mpic *mpic = mpic_from_irq(irq);
 	unsigned int src = mpic_irq_to_hw(irq);
@@ -824,6 +824,8 @@ void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION),
 			       mpic_physmask(cpus_addr(tmp)[0]));
 	}
+
+	return 0;
 }
 
 static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 3cef2af10f4..eff433c322a 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic)
 
 extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type);
 extern void mpic_set_vector(unsigned int virq, unsigned int vector);
-extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 
 #endif /* _POWERPC_SYSDEV_MPIC_H */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 639ac805448..65865726b28 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,8 +102,8 @@ struct thread_info {
 #define TI_KERN_CNTD1	0x00000488
 #define TI_PCR		0x00000490
 #define TI_RESTART_BLOCK 0x00000498
-#define TI_KUNA_REGS	0x000004c0
-#define TI_KUNA_INSN	0x000004c8
+#define TI_KUNA_REGS	0x000004c8
+#define TI_KUNA_INSN	0x000004d0
 #define TI_FPREGS	0x00000500
 
 /* We embed this in the uppermost byte of thread_info->flags */
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 5deabe921a4..e5e78f9cfc9 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -318,10 +318,12 @@ static void sun4u_irq_enable(unsigned int virt_irq)
 	}
 }
 
-static void sun4u_set_affinity(unsigned int virt_irq,
+static int sun4u_set_affinity(unsigned int virt_irq,
 			       const struct cpumask *mask)
 {
 	sun4u_irq_enable(virt_irq);
+
+	return 0;
 }
 
 /* Don't do anything.  The desc->status check for IRQ_DISABLED in
@@ -377,7 +379,7 @@ static void sun4v_irq_enable(unsigned int virt_irq)
 		       ino, err);
 }
 
-static void sun4v_set_affinity(unsigned int virt_irq,
+static int sun4v_set_affinity(unsigned int virt_irq,
 			       const struct cpumask *mask)
 {
 	unsigned int ino = virt_irq_table[virt_irq].dev_ino;
@@ -388,6 +390,8 @@ static void sun4v_set_affinity(unsigned int virt_irq,
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_intr_settarget(%x,%lu): "
 		       "err(%d)\n", ino, cpuid, err);
+
+	return 0;
 }
 
 static void sun4v_irq_disable(unsigned int virt_irq)
@@ -445,7 +449,7 @@ static void sun4v_virq_enable(unsigned int virt_irq)
 		       dev_handle, dev_ino, err);
 }
 
-static void sun4v_virt_set_affinity(unsigned int virt_irq,
+static int sun4v_virt_set_affinity(unsigned int virt_irq,
 				    const struct cpumask *mask)
 {
 	unsigned long cpuid, dev_handle, dev_ino;
@@ -461,6 +465,8 @@ static void sun4v_virt_set_affinity(unsigned int virt_irq,
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
 		       "err(%d)\n",
 		       dev_handle, dev_ino, cpuid, err);
+
+	return 0;
 }
 
 static void sun4v_virq_disable(unsigned int virt_irq)
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
new file mode 100644
index 00000000000..ad8ec356fb3
--- /dev/null
+++ b/arch/x86/Kbuild
@@ -0,0 +1,16 @@
+
+obj-$(CONFIG_KVM) += kvm/
+
+# Xen paravirtualization support
+obj-$(CONFIG_XEN) += xen/
+
+# lguest paravirtualization support
+obj-$(CONFIG_LGUEST_GUEST) += lguest/
+
+obj-y += kernel/
+obj-y += mm/
+
+obj-y += crypto/
+obj-y += vdso/
+obj-$(CONFIG_IA32_EMULATION) += ia32/
+
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cfd78c87a57..68f5578fe38 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -47,6 +47,11 @@ config X86
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 
+config OUTPUT_FORMAT
+	string
+	default "elf32-i386" if X86_32
+	default "elf64-x86-64" if X86_64
+
 config ARCH_DEFCONFIG
 	string
 	default "arch/x86/configs/i386_defconfig" if X86_32
@@ -274,15 +279,9 @@ config SPARSE_IRQ
 
 	  If you don't know what to do here, say N.
 
-config NUMA_MIGRATE_IRQ_DESC
-	bool "Move irq desc when changing irq smp_affinity"
+config NUMA_IRQ_DESC
+	def_bool y
 	depends on SPARSE_IRQ && NUMA
-	depends on BROKEN
-	default n
-	---help---
-	  This enables moving irq_desc to cpu/node that irq will use handled.
-
-	  If you don't know what to do here, say N.
 
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
@@ -355,7 +354,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
-	select X86_X2APIC
+	depends on X86_X2APIC
 	---help---
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
@@ -1467,9 +1466,7 @@ config KEXEC_JUMP
 
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
-	default "0x1000000" if X86_NUMAQ
-	default "0x200000" if X86_64
-	default "0x100000"
+	default "0x1000000"
 	---help---
 	  This gives the physical address where the kernel is loaded.
 
@@ -1488,15 +1485,15 @@ config PHYSICAL_START
 	  to be specifically compiled to run from a specific memory area
 	  (normally a reserved region) and this option comes handy.
 
-	  So if you are using bzImage for capturing the crash dump, leave
-	  the value here unchanged to 0x100000 and set CONFIG_RELOCATABLE=y.
-	  Otherwise if you plan to use vmlinux for capturing the crash dump
-	  change this value to start of the reserved region (Typically 16MB
-	  0x1000000). In other words, it can be set based on the "X" value as
-	  specified in the "crashkernel=YM@XM" command line boot parameter
-	  passed to the panic-ed kernel. Typically this parameter is set as
-	  crashkernel=64M@16M. Please take a look at
-	  Documentation/kdump/kdump.txt for more details about crash dumps.
+	  So if you are using bzImage for capturing the crash dump,
+	  leave the value here unchanged to 0x1000000 and set
+	  CONFIG_RELOCATABLE=y.  Otherwise if you plan to use vmlinux
+	  for capturing the crash dump change this value to start of
+	  the reserved region.  In other words, it can be set based on
+	  the "X" value as specified in the "crashkernel=YM@XM"
+	  command line boot parameter passed to the panic-ed
+	  kernel. Please take a look at Documentation/kdump/kdump.txt
+	  for more details about crash dumps.
 
 	  Usage of bzImage for capturing the crash dump is recommended as
 	  one does not have to build two kernels. Same kernel can be used
@@ -1509,8 +1506,8 @@ config PHYSICAL_START
 	  Don't change this unless you know what you are doing.
 
 config RELOCATABLE
-	bool "Build a relocatable kernel (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "Build a relocatable kernel"
+	default y
 	---help---
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded someplace besides the default 1MB.
@@ -1525,12 +1522,16 @@ config RELOCATABLE
 	  it has been loaded at and the compile time physical address
 	  (CONFIG_PHYSICAL_START) is ignored.
 
+# Relocation on x86-32 needs some additional build support
+config X86_NEED_RELOCS
+	def_bool y
+	depends on X86_32 && RELOCATABLE
+
 config PHYSICAL_ALIGN
 	hex
 	prompt "Alignment value to which kernel should be aligned" if X86_32
-	default "0x100000" if X86_32
-	default "0x200000" if X86_64
-	range 0x2000 0x400000
+	default "0x1000000"
+	range 0x2000 0x1000000
 	---help---
 	  This value puts the alignment restrictions on physical address
 	  where kernel is loaded and run from. Kernel is compiled for an
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index d8359e73317..d105f29bb6b 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -159,14 +159,30 @@ config IOMMU_DEBUG
 	  options. See Documentation/x86_64/boot-options.txt for more
 	  details.
 
+config IOMMU_STRESS
+	bool "Enable IOMMU stress-test mode"
+	---help---
+	  This option disables various optimizations in IOMMU related
+	  code to do real stress testing of the IOMMU code. This option
+	  will cause a performance drop and should only be enabled for
+	  testing.
+
 config IOMMU_LEAK
 	bool "IOMMU leak tracing"
-	depends on DEBUG_KERNEL
-	depends on IOMMU_DEBUG
+	depends on IOMMU_DEBUG && DMA_API_DEBUG
 	---help---
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
+config X86_DS_SELFTEST
+    bool "DS selftest"
+    default y
+    depends on DEBUG_KERNEL
+    depends on X86_DS
+	---help---
+	  Perform Debug Store selftests at boot time.
+	  If in doubt, say "N".
+
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8c86b72afdc..edbd0ca6206 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -7,8 +7,6 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
-core-$(CONFIG_KVM) += arch/x86/kvm/
-
 # BITS is used as extension for files which are available in a 32 bit
 # and a 64 bit version to simplify shared Makefiles.
 # e.g.: obj-y += foo_$(BITS).o
@@ -118,21 +116,8 @@ head-y += arch/x86/kernel/init_task.o
 
 libs-y  += arch/x86/lib/
 
-# Sub architecture files that needs linking first
-core-y += $(fcore-y)
-
-# Xen paravirtualization support
-core-$(CONFIG_XEN) += arch/x86/xen/
-
-# lguest paravirtualization support
-core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
-
-core-y += arch/x86/kernel/
-core-y += arch/x86/mm/
-
-core-y += arch/x86/crypto/
-core-y += arch/x86/vdso/
-core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/
+# See arch/x86/Kbuild for content of core part of the kernel
+core-y += arch/x86/
 
 # drivers-y are linked after core-y
 drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index 172cf8a98bd..851fe936d24 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -3,6 +3,8 @@ bzImage
 cpustr.h
 mkcpustr
 offsets.h
+voffset.h
+zoffset.h
 setup
 setup.bin
 setup.elf
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 6633b6e7505..8d16ada2504 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -26,9 +26,10 @@ targets		:= vmlinux.bin setup.bin setup.elf bzImage
 targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
 subdir-		:= compressed
 
-setup-y		+= a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o
 setup-y		+= header.o main.o mca.o memory.o pm.o pmjump.o
-setup-y		+= printf.o string.o tty.o video.o video-mode.o version.o
+setup-y		+= printf.o regs.o string.o tty.o video.o video-mode.o
+setup-y		+= version.o
 setup-$(CONFIG_X86_APM_BOOT) += apm.o
 
 # The link order of the video-*.o modules can matter.  In particular,
@@ -86,19 +87,27 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-offsets := -e 's/^00*/0/' \
-        -e 's/^\([0-9a-fA-F]*\) . \(input_data\|input_data_end\)$$/\#define \2 0x\1/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
 
-quiet_cmd_offsets = OFFSETS $@
-      cmd_offsets = $(NM) $< | sed -n $(sed-offsets) > $@
+quiet_cmd_voffset = VOFFSET $@
+      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
 
-$(obj)/offsets.h: $(obj)/compressed/vmlinux FORCE
-	$(call if_changed,offsets)
+targets += voffset.h
+$(obj)/voffset.h: vmlinux FORCE
+	$(call if_changed,voffset)
+
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+
+quiet_cmd_zoffset = ZOFFSET $@
+      cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
+
+targets += zoffset.h
+$(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,zoffset)
 
-targets += offsets.h
 
 AFLAGS_header.o += -I$(obj)
-$(obj)/header.o: $(obj)/offsets.h
+$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
 
 LDFLAGS_setup.elf	:= -T
 $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c
index 7c19ce8c244..64a31a6d751 100644
--- a/arch/x86/boot/a20.c
+++ b/arch/x86/boot/a20.c
@@ -2,7 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
- *   Copyright 2009 Intel Corporation
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -90,8 +90,11 @@ static int a20_test_long(void)
 
 static void enable_a20_bios(void)
 {
-	asm volatile("pushfl; int $0x15; popfl"
-		     : : "a" ((u16)0x2401));
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.ax = 0x2401;
+	intcall(0x15, &ireg, NULL);
 }
 
 static void enable_a20_kbc(void)
diff --git a/arch/x86/boot/apm.c b/arch/x86/boot/apm.c
index 7aa6033001f..ee274834ea8 100644
--- a/arch/x86/boot/apm.c
+++ b/arch/x86/boot/apm.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   Original APM BIOS checking by Stephen Rothwell, May 1994
  *   (sfr@canb.auug.org.au)
@@ -19,75 +20,56 @@
 
 int query_apm_bios(void)
 {
-	u16 ax, bx, cx, dx, di;
-	u32 ebx, esi;
-	u8 err;
+	struct biosregs ireg, oreg;
 
 	/* APM BIOS installation check */
-	ax = 0x5300;
-	bx = cx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
-		     : "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
-		     : : "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x53;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err)
+	if (oreg.flags & X86_EFLAGS_CF)
 		return -1;		/* No APM BIOS */
 
-	if (bx != 0x504d)	/* "PM" signature */
+	if (oreg.bx != 0x504d)		/* "PM" signature */
 		return -1;
 
-	if (!(cx & 0x02))		/* 32 bits supported? */
+	if (!(oreg.cx & 0x02))		/* 32 bits supported? */
 		return -1;
 
 	/* Disconnect first, just in case */
-	ax = 0x5304;
-	bx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
-		     : "+a" (ax), "+b" (bx)
-		     : : "ecx", "edx", "esi", "edi");
-
-	/* Paranoia */
-	ebx = esi = 0;
-	cx = dx = di = 0;
+	ireg.al = 0x04;
+	intcall(0x15, &ireg, NULL);
 
 	/* 32-bit connect */
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %6"
-		     : "=a" (ax), "+b" (ebx), "+c" (cx), "+d" (dx),
-		       "+S" (esi), "+D" (di), "=m" (err)
-		     : "a" (0x5303));
-
-	boot_params.apm_bios_info.cseg = ax;
-	boot_params.apm_bios_info.offset = ebx;
-	boot_params.apm_bios_info.cseg_16 = cx;
-	boot_params.apm_bios_info.dseg = dx;
-	boot_params.apm_bios_info.cseg_len = (u16)esi;
-	boot_params.apm_bios_info.cseg_16_len = esi >> 16;
-	boot_params.apm_bios_info.dseg_len = di;
-
-	if (err)
+	ireg.al = 0x03;
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.apm_bios_info.cseg        = oreg.ax;
+	boot_params.apm_bios_info.offset      = oreg.ebx;
+	boot_params.apm_bios_info.cseg_16     = oreg.cx;
+	boot_params.apm_bios_info.dseg        = oreg.dx;
+	boot_params.apm_bios_info.cseg_len    = oreg.si;
+	boot_params.apm_bios_info.cseg_16_len = oreg.hsi;
+	boot_params.apm_bios_info.dseg_len    = oreg.di;
+
+	if (oreg.flags & X86_EFLAGS_CF)
 		return -1;
 
 	/* Redo the installation check as the 32-bit connect;
 	   some BIOSes return different flags this way... */
 
-	ax = 0x5300;
-	bx = cx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
-		     : "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
-		     : : "esi", "edi");
+	ireg.al = 0x00;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err || bx != 0x504d) {
+	if ((oreg.eflags & X86_EFLAGS_CF) || oreg.bx != 0x504d) {
 		/* Failure with 32-bit connect, try to disconect and ignore */
-		ax = 0x5304;
-		bx = 0;
-		asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
-			     : "+a" (ax), "+b" (bx)
-			     : : "ecx", "edx", "esi", "edi");
+		ireg.al = 0x04;
+		intcall(0x15, &ireg, NULL);
 		return -1;
 	}
 
-	boot_params.apm_bios_info.version = ax;
-	boot_params.apm_bios_info.flags = cx;
+	boot_params.apm_bios_info.version = oreg.ax;
+	boot_params.apm_bios_info.flags   = oreg.cx;
 	return 0;
 }
 
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
new file mode 100644
index 00000000000..507793739ea
--- /dev/null
+++ b/arch/x86/boot/bioscall.S
@@ -0,0 +1,82 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * "Glove box" for BIOS calls.  Avoids the constant problems with BIOSes
+ * touching registers they shouldn't be.
+ */
+
+	.code16
+	.text
+	.globl	intcall
+	.type	intcall, @function
+intcall:
+	/* Self-modify the INT instruction.  Ugly, but works. */
+	cmpb	%al, 3f
+	je	1f
+	movb	%al, 3f
+	jmp	1f		/* Synchronize pipeline */
+1:
+	/* Save state */
+	pushfl
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Copy input state to stack frame */
+	subw	$44, %sp
+	movw	%dx, %si
+	movw	%sp, %di
+	movw	$11, %cx
+	rep; movsd
+
+	/* Pop full state from the stack */
+	popal
+	popw	%gs
+	popw	%fs
+	popw	%es
+	popw	%ds
+	popfl
+
+	/* Actual INT */
+	.byte	0xcd		/* INT opcode */
+3:	.byte	0
+
+	/* Push full state to the stack */
+	pushfl
+	pushw	%ds
+	pushw	%es
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Re-establish C environment invariants */
+	cld
+	movzwl	%sp, %esp
+	movw	%cs, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
+	/* Copy output state from stack frame */
+	movw	68(%esp), %di	/* Original %cx == 3rd argument */
+	andw	%di, %di
+	jz	4f
+	movw	%sp, %si
+	movw	$11, %cx
+	rep; movsd
+4:	addw	$44, %sp
+
+	/* Restore state and return */
+	popal
+	popw	%gs
+	popw	%fs
+	popfl
+	retl
+	.size	intcall, .-intcall
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 7b2692e897e..98239d2658f 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -26,6 +27,7 @@
 #include <asm/setup.h>
 #include "bitops.h"
 #include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -241,6 +243,49 @@ int enable_a20(void);
 /* apm.c */
 int query_apm_bios(void);
 
+/* bioscall.c */
+struct biosregs {
+	union {
+		struct {
+			u32 edi;
+			u32 esi;
+			u32 ebp;
+			u32 _esp;
+			u32 ebx;
+			u32 edx;
+			u32 ecx;
+			u32 eax;
+			u32 _fsgs;
+			u32 _dses;
+			u32 eflags;
+		};
+		struct {
+			u16 di, hdi;
+			u16 si, hsi;
+			u16 bp, hbp;
+			u16 _sp, _hsp;
+			u16 bx, hbx;
+			u16 dx, hdx;
+			u16 cx, hcx;
+			u16 ax, hax;
+			u16 gs, fs;
+			u16 es, ds;
+			u16 flags, hflags;
+		};
+		struct {
+			u8 dil, dih, edi2, edi3;
+			u8 sil, sih, esi2, esi3;
+			u8 bpl, bph, ebp2, ebp3;
+			u8 _spl, _sph, _esp2, _esp3;
+			u8 bl, bh, ebx2, ebx3;
+			u8 dl, dh, edx2, edx3;
+			u8 cl, ch, ecx2, ecx3;
+			u8 al, ah, eax2, eax3;
+		};
+	};
+};
+void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg);
+
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
@@ -279,6 +324,9 @@ int sprintf(char *buf, const char *fmt, ...);
 int vsprintf(char *buf, const char *fmt, va_list args);
 int printf(const char *fmt, ...);
 
+/* regs.c */
+void initregs(struct biosregs *regs);
+
 /* string.c */
 int strcmp(const char *str1, const char *str2);
 size_t strnlen(const char *s, size_t maxlen);
diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore
index 63eff3b04d0..4a46fab7162 100644
--- a/arch/x86/boot/compressed/.gitignore
+++ b/arch/x86/boot/compressed/.gitignore
@@ -1,3 +1,6 @@
 relocs
 vmlinux.bin.all
 vmlinux.relocs
+vmlinux.lds
+mkpiggy
+piggy.S
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 65551c9f857..49c8a4c37d7 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -19,7 +19,9 @@ KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 LDFLAGS := -m elf_$(UTS_MACHINE)
 LDFLAGS_vmlinux := -T
 
-$(obj)/vmlinux: $(src)/vmlinux_$(BITS).lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
+hostprogs-y	:= mkpiggy
+
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
 	$(call if_changed,ld)
 	@:
 
@@ -29,7 +31,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 
 
 targets += vmlinux.bin.all vmlinux.relocs relocs
-hostprogs-$(CONFIG_X86_32) += relocs
+hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs
 
 quiet_cmd_relocs = RELOCS  $@
       cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
@@ -37,46 +39,22 @@ $(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
 	$(call if_changed,relocs)
 
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
-vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
-quiet_cmd_relocbin = BUILD   $@
-      cmd_relocbin = cat $(filter-out FORCE,$^) > $@
-$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
-	$(call if_changed,relocbin)
-
-ifeq ($(CONFIG_X86_32),y)
+vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
 
-ifdef CONFIG_RELOCATABLE
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
-	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE
-	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE
-	$(call if_changed,lzma)
-else
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
-endif
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
 
-else
+suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,lzma)
-
-LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
-endif
+quiet_cmd_mkpiggy = MKPIGGY $@
+      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
 
-suffix_$(CONFIG_KERNEL_GZIP)  = gz
-suffix_$(CONFIG_KERNEL_BZIP2) = bz2
-suffix_$(CONFIG_KERNEL_LZMA)  = lzma
-
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
-	$(call if_changed,ld)
+targets += piggy.S
+$(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
+	$(call if_changed,mkpiggy)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 3a8a866fb2e..75e4f001e70 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -12,16 +12,16 @@
  * the page directory. [According to comments etc elsewhere on a compressed
  * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
  *
- * Page 0 is deliberately kept safe, since System Management Mode code in 
+ * Page 0 is deliberately kept safe, since System Management Mode code in
  * laptops may need to access the BIOS data stored there.  This is also
- * useful for future device drivers that either access the BIOS via VM86 
+ * useful for future device drivers that either access the BIOS via VM86
  * mode.
  */
 
 /*
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
-.text
+	.text
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
@@ -29,161 +29,151 @@
 #include <asm/boot.h>
 #include <asm/asm-offsets.h>
 
-.section ".text.head","ax",@progbits
+	.section ".text.head","ax",@progbits
 ENTRY(startup_32)
 	cld
-	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
-	 * us to not reload segments */
-	testb $(1<<6), BP_loadflags(%esi)
-	jnz 1f
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
+	testb	$(1<<6), BP_loadflags(%esi)
+	jnz	1f
 
 	cli
-	movl $(__BOOT_DS),%eax
-	movl %eax,%ds
-	movl %eax,%es
-	movl %eax,%fs
-	movl %eax,%gs
-	movl %eax,%ss
+	movl	$__BOOT_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %fs
+	movl	%eax, %gs
+	movl	%eax, %ss
 1:
 
-/* Calculate the delta between where we were compiled to run
+/*
+ * Calculate the delta between where we were compiled to run
  * at and where we were actually loaded at.  This can only be done
  * with a short local call on x86.  Nothing  else will tell us what
  * address we are running at.  The reserved chunk of the real-mode
  * data at 0x1e4 (defined as a scratch field) are used as the stack
  * for this calculation. Only 4 bytes are needed.
  */
-	leal (0x1e4+4)(%esi), %esp
-	call 1f
-1:	popl %ebp
-	subl $1b, %ebp
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	popl	%ebp
+	subl	$1b, %ebp
 
-/* %ebp contains the address we are loaded at by the boot loader and %ebx
+/*
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
  * contains the address where we should move the kernel image temporarily
  * for safe in-place decompression.
  */
 
 #ifdef CONFIG_RELOCATABLE
-	movl 	%ebp, %ebx
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
+	movl	%ebp, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl    %eax, %ebx
+	notl	%eax
+	andl    %eax, %ebx
 #else
-	movl $LOAD_PHYSICAL_ADDR, %ebx
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	subl input_len(%ebp), %ebx
-	movl output_len(%ebp), %eax
-	addl %eax, %ebx
-	/* Add 8 bytes for every 32K input block */
-	shrl $12, %eax
-	addl %eax, %ebx
-	/* Add 32K + 18 bytes of extra slack */
-	addl $(32768 + 18), %ebx
-	/* Align on a 4K boundary */
-	addl $4095, %ebx
-	andl $~4095, %ebx
-
-/* Copy the compressed kernel to the end of our buffer
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
+
+	/* Set up the stack */
+	leal	boot_stack_end(%ebx), %esp
+
+	/* Zero EFLAGS */
+	pushl	$0
+	popfl
+
+/*
+ * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	pushl %esi
-	leal _end(%ebp), %esi
-	leal _end(%ebx), %edi
-	movl $(_end - startup_32), %ecx
+	pushl	%esi
+	leal	(_bss-4)(%ebp), %esi
+	leal	(_bss-4)(%ebx), %edi
+	movl	$(_bss - startup_32), %ecx
+	shrl	$2, %ecx
 	std
-	rep
-	movsb
+	rep	movsl
 	cld
-	popl %esi
-
-/* Compute the kernel start address.
- */
-#ifdef CONFIG_RELOCATABLE
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebp
-#endif
+	popl	%esi
 
 /*
  * Jump to the relocated address.
  */
-	leal relocated(%ebx), %eax
-	jmp *%eax
+	leal	relocated(%ebx), %eax
+	jmp	*%eax
 ENDPROC(startup_32)
 
-.section ".text"
+	.text
 relocated:
 
 /*
- * Clear BSS
- */
-	xorl %eax,%eax
-	leal _edata(%ebx),%edi
-	leal _end(%ebx), %ecx
-	subl %edi,%ecx
-	cld
-	rep
-	stosb
-
-/*
- * Setup the stack for the decompressor
+ * Clear BSS (stack is currently empty)
  */
-	leal boot_stack_end(%ebx), %esp
+	xorl	%eax, %eax
+	leal	_bss(%ebx), %edi
+	leal	_ebss(%ebx), %ecx
+	subl	%edi, %ecx
+	shrl	$2, %ecx
+	rep	stosl
 
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	movl output_len(%ebx), %eax
-	pushl %eax
-			# push arguments for decompress_kernel:
-	pushl %ebp	# output address
-	movl input_len(%ebx), %eax
-	pushl %eax	# input_len
-	leal input_data(%ebx), %eax
-	pushl %eax	# input_data
-	leal boot_heap(%ebx), %eax
-	pushl %eax	# heap area
-	pushl %esi	# real mode pointer
-	call decompress_kernel
-	addl $20, %esp
-	popl %ecx
+	leal	z_extract_offset_negative(%ebx), %ebp
+				/* push arguments for decompress_kernel: */
+	pushl	%ebp		/* output address */
+	pushl	$z_input_len	/* input_len */
+	leal	input_data(%ebx), %eax
+	pushl	%eax		/* input_data */
+	leal	boot_heap(%ebx), %eax
+	pushl	%eax		/* heap area */
+	pushl	%esi		/* real mode pointer */
+	call	decompress_kernel
+	addl	$20, %esp
 
 #if CONFIG_RELOCATABLE
-/* Find the address of the relocations.
+/*
+ * Find the address of the relocations.
  */
-	movl %ebp, %edi
-	addl %ecx, %edi
+	leal	z_output_len(%ebp), %edi
 
-/* Calculate the delta between where vmlinux was compiled to run
+/*
+ * Calculate the delta between where vmlinux was compiled to run
  * and where it was actually loaded.
  */
-	movl %ebp, %ebx
-	subl $LOAD_PHYSICAL_ADDR, %ebx
-	jz   2f		/* Nothing to be done if loaded at compiled addr. */
+	movl	%ebp, %ebx
+	subl	$LOAD_PHYSICAL_ADDR, %ebx
+	jz	2f	/* Nothing to be done if loaded at compiled addr. */
 /*
  * Process relocations.
  */
 
-1:	subl $4, %edi
-	movl 0(%edi), %ecx
-	testl %ecx, %ecx
-	jz 2f
-	addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
-	jmp 1b
+1:	subl	$4, %edi
+	movl	(%edi), %ecx
+	testl	%ecx, %ecx
+	jz	2f
+	addl	%ebx, -__PAGE_OFFSET(%ebx, %ecx)
+	jmp	1b
 2:
 #endif
 
 /*
  * Jump to the decompressed kernel.
  */
-	xorl %ebx,%ebx
-	jmp *%ebp
+	xorl	%ebx, %ebx
+	jmp	*%ebp
 
-.bss
-/* Stack and heap for uncompression */
-.balign 4
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
 boot_heap:
 	.fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index ed4a8294800..f62c284db9e 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -21,8 +21,8 @@
 /*
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
-.code32
-.text
+	.code32
+	.text
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
@@ -33,12 +33,14 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
-.section ".text.head"
+	.section ".text.head"
 	.code32
 ENTRY(startup_32)
 	cld
-	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
-	 * us to not reload segments */
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
 	testb $(1<<6), BP_loadflags(%esi)
 	jnz 1f
 
@@ -49,14 +51,15 @@ ENTRY(startup_32)
 	movl	%eax, %ss
 1:
 
-/* Calculate the delta between where we were compiled to run
+/*
+ * Calculate the delta between where we were compiled to run
  * at and where we were actually loaded at.  This can only be done
  * with a short local call on x86.  Nothing  else will tell us what
  * address we are running at.  The reserved chunk of the real-mode
  * data at 0x1e4 (defined as a scratch field) are used as the stack
  * for this calculation. Only 4 bytes are needed.
  */
-	leal	(0x1e4+4)(%esi), %esp
+	leal	(BP_scratch+4)(%esi), %esp
 	call	1f
 1:	popl	%ebp
 	subl	$1b, %ebp
@@ -70,32 +73,28 @@ ENTRY(startup_32)
 	testl	%eax, %eax
 	jnz	no_longmode
 
-/* Compute the delta between where we were compiled to run at
+/*
+ * Compute the delta between where we were compiled to run at
  * and where the code will actually run at.
- */
-/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ *
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
  * contains the address where we should move the kernel image temporarily
  * for safe in-place decompression.
  */
 
 #ifdef CONFIG_RELOCATABLE
 	movl	%ebp, %ebx
-	addl	$(PMD_PAGE_SIZE -1), %ebx
-	andl	$PMD_PAGE_MASK, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl	%eax, %ebx
+	notl	%eax
+	andl	%eax, %ebx
 #else
-	movl	$CONFIG_PHYSICAL_START, %ebx
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	subl	input_len(%ebp), %ebx
-	movl	output_len(%ebp), %eax
-	addl	%eax, %ebx
-	/* Add 8 bytes for every 32K input block */
-	shrl	$12, %eax
-	addl	%eax, %ebx
-	/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-	addl	$(32768 + 18 + 4095), %ebx
-	andl	$~4095, %ebx
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -114,7 +113,7 @@ ENTRY(startup_32)
  /*
   * Build early 4G boot pagetable
   */
-	/* Initialize Page tables to 0*/
+	/* Initialize Page tables to 0 */
 	leal	pgtable(%ebx), %edi
 	xorl	%eax, %eax
 	movl	$((4096*6)/4), %ecx
@@ -155,7 +154,8 @@ ENTRY(startup_32)
 	btsl	$_EFER_LME, %eax
 	wrmsr
 
-	/* Setup for the jump to 64bit mode
+	/*
+	 * Setup for the jump to 64bit mode
 	 *
 	 * When the jump is performend we will be in long mode but
 	 * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
@@ -184,7 +184,8 @@ no_longmode:
 
 #include "../../kernel/verify_cpu_64.S"
 
-	/* Be careful here startup_64 needs to be at a predictable
+	/*
+	 * Be careful here startup_64 needs to be at a predictable
 	 * address so I can export it in an ELF header.  Bootloaders
 	 * should look at the ELF header to find this address, as
 	 * it may change in the future.
@@ -192,7 +193,8 @@ no_longmode:
 	.code64
 	.org 0x200
 ENTRY(startup_64)
-	/* We come here either from startup_32 or directly from a
+	/*
+	 * We come here either from startup_32 or directly from a
 	 * 64bit bootloader.  If we come here from a bootloader we depend on
 	 * an identity mapped page table being provied that maps our
 	 * entire text+data+bss and hopefully all of memory.
@@ -209,50 +211,54 @@ ENTRY(startup_64)
 	movl    $0x20, %eax
 	ltr	%ax
 
-	/* Compute the decompressed kernel start address.  It is where
+	/*
+	 * Compute the decompressed kernel start address.  It is where
 	 * we were loaded at aligned to a 2M boundary. %rbp contains the
 	 * decompressed kernel start address.
 	 *
 	 * If it is a relocatable kernel then decompress and run the kernel
 	 * from load address aligned to 2MB addr, otherwise decompress and
-	 * run the kernel from CONFIG_PHYSICAL_START
+	 * run the kernel from LOAD_PHYSICAL_ADDR
+	 *
+	 * We cannot rely on the calculation done in 32-bit mode, since we
+	 * may have been invoked via the 64-bit entry point.
 	 */
 
 	/* Start with the delta to where the kernel will run at. */
 #ifdef CONFIG_RELOCATABLE
 	leaq	startup_32(%rip) /* - $startup_32 */, %rbp
-	addq	$(PMD_PAGE_SIZE - 1), %rbp
-	andq	$PMD_PAGE_MASK, %rbp
-	movq	%rbp, %rbx
+	movl	BP_kernel_alignment(%rsi), %eax
+	decl	%eax
+	addq	%rax, %rbp
+	notq	%rax
+	andq	%rax, %rbp
 #else
-	movq	$CONFIG_PHYSICAL_START, %rbp
-	movq	%rbp, %rbx
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	movl	input_len(%rip), %eax
-	subq	%rax, %rbx
-	movl	output_len(%rip), %eax
-	addq	%rax, %rbx
-	/* Add 8 bytes for every 32K input block */
-	shrq	$12, %rax
-	addq	%rax, %rbx
-	/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-	addq	$(32768 + 18 + 4095), %rbx
-	andq	$~4095, %rbx
-
-/* Copy the compressed kernel to the end of our buffer
+	/* Target address to relocate to for decompression */
+	leaq	z_extract_offset(%rbp), %rbx
+
+	/* Set up the stack */
+	leaq	boot_stack_end(%rbx), %rsp
+
+	/* Zero EFLAGS */
+	pushq	$0
+	popfq
+
+/*
+ * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	leaq	_end_before_pgt(%rip), %r8
-	leaq	_end_before_pgt(%rbx), %r9
-	movq	$_end_before_pgt /* - $startup_32 */, %rcx
-1:	subq	$8, %r8
-	subq	$8, %r9
-	movq	0(%r8), %rax
-	movq	%rax, 0(%r9)
-	subq	$8, %rcx
-	jnz	1b
+	pushq	%rsi
+	leaq	(_bss-8)(%rip), %rsi
+	leaq	(_bss-8)(%rbx), %rdi
+	movq	$_bss /* - $startup_32 */, %rcx
+	shrq	$3, %rcx
+	std
+	rep	movsq
+	cld
+	popq	%rsi
 
 /*
  * Jump to the relocated address.
@@ -260,37 +266,28 @@ ENTRY(startup_64)
 	leaq	relocated(%rbx), %rax
 	jmp	*%rax
 
-.section ".text"
+	.text
 relocated:
 
 /*
- * Clear BSS
+ * Clear BSS (stack is currently empty)
  */
-	xorq	%rax, %rax
-	leaq    _edata(%rbx), %rdi
-	leaq    _end_before_pgt(%rbx), %rcx
+	xorl	%eax, %eax
+	leaq    _bss(%rip), %rdi
+	leaq    _ebss(%rip), %rcx
 	subq	%rdi, %rcx
-	cld
-	rep
-	stosb
-
-	/* Setup the stack */
-	leaq	boot_stack_end(%rip), %rsp
-
-	/* zero EFLAGS after setting rsp */
-	pushq	$0
-	popfq
+	shrq	$3, %rcx
+	rep	stosq
 
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	pushq	%rsi			# Save the real mode argument
-	movq	%rsi, %rdi		# real mode address
-	leaq	boot_heap(%rip), %rsi	# malloc area for uncompression
-	leaq	input_data(%rip), %rdx  # input_data
-	movl	input_len(%rip), %eax
-	movq	%rax, %rcx		# input_len
-	movq	%rbp, %r8		# output
+	pushq	%rsi			/* Save the real mode argument */
+	movq	%rsi, %rdi		/* real mode address */
+	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
+	leaq	input_data(%rip), %rdx  /* input_data */
+	movl	$z_input_len, %ecx	/* input_len */
+	movq	%rbp, %r8		/* output target address */
 	call	decompress_kernel
 	popq	%rsi
 
@@ -311,11 +308,21 @@ gdt:
 	.quad   0x0000000000000000	/* TS continued */
 gdt_end:
 
-.bss
-/* Stack and heap for uncompression */
-.balign 4
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
 boot_heap:
 	.fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
 	.fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
+
+/*
+ * Space for page tables (not in .bss so not zeroed)
+ */
+	.section ".pgtable","a",@nobits
+	.balign 4096
+pgtable:
+	.fill 6*4096, 1, 0
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index e45be73684f..842b2a36174 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -325,21 +325,19 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
+		error("Destination address inappropriately aligned");
 #ifdef CONFIG_X86_64
-	if ((unsigned long)output & (__KERNEL_ALIGN - 1))
-		error("Destination address not 2M aligned");
-	if ((unsigned long)output >= 0xffffffffffUL)
+	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
 #else
-	if ((u32)output & (CONFIG_PHYSICAL_ALIGN - 1))
-		error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
 	if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
 		error("Destination address too large");
+#endif
 #ifndef CONFIG_RELOCATABLE
-	if ((u32)output != LOAD_PHYSICAL_ADDR)
+	if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
 		error("Wrong destination address");
 #endif
-#endif
 
 	if (!quiet)
 		putstr("\nDecompressing Linux... ");
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
new file mode 100644
index 00000000000..bcbd36c4143
--- /dev/null
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -0,0 +1,97 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *  Copyright (C) 2009 Intel Corporation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License version
+ *  2 as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ *  02110-1301, USA.
+ *
+ *  H. Peter Anvin <hpa@linux.intel.com>
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Compute the desired load offset from a compressed program; outputs
+ * a small assembly wrapper with the appropriate symbols defined.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+
+static uint32_t getle32(const void *p)
+{
+	const uint8_t *cp = p;
+
+	return (uint32_t)cp[0] + ((uint32_t)cp[1] << 8) +
+		((uint32_t)cp[2] << 16) + ((uint32_t)cp[3] << 24);
+}
+
+int main(int argc, char *argv[])
+{
+	uint32_t olen;
+	long ilen;
+	unsigned long offs;
+	FILE *f;
+
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+		return 1;
+	}
+
+	/* Get the information for the compressed kernel image first */
+
+	f = fopen(argv[1], "r");
+	if (!f) {
+		perror(argv[1]);
+		return 1;
+	}
+
+
+	if (fseek(f, -4L, SEEK_END)) {
+		perror(argv[1]);
+	}
+	fread(&olen, sizeof olen, 1, f);
+	ilen = ftell(f);
+	olen = getle32(&olen);
+	fclose(f);
+
+	/*
+	 * Now we have the input (compressed) and output (uncompressed)
+	 * sizes, compute the necessary decompression offset...
+	 */
+
+	offs = (olen > ilen) ? olen - ilen : 0;
+	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
+	offs += 32*1024 + 18;	/* Add 32K + 18 bytes slack */
+	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+
+	printf(".section \".rodata.compressed\",\"a\",@progbits\n");
+	printf(".globl z_input_len\n");
+	printf("z_input_len = %lu\n", ilen);
+	printf(".globl z_output_len\n");
+	printf("z_output_len = %lu\n", (unsigned long)olen);
+	printf(".globl z_extract_offset\n");
+	printf("z_extract_offset = 0x%lx\n", offs);
+	/* z_extract_offset_negative allows simplification of head_32.S */
+	printf(".globl z_extract_offset_negative\n");
+	printf("z_extract_offset_negative = -0x%lx\n", offs);
+
+	printf(".globl input_data, input_data_end\n");
+	printf("input_data:\n");
+	printf(".incbin \"%s\"\n", argv[1]);
+	printf("input_data_end:\n");
+
+	return 0;
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux.lds.S
index bef1ac891bc..cc353e1b3ff 100644
--- a/arch/x86/boot/compressed/vmlinux_64.lds
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -1,6 +1,17 @@
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#undef i386
+
+#include <asm/page_types.h>
+
+#ifdef CONFIG_X86_64
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(startup_64)
+#else
+OUTPUT_ARCH(i386)
+ENTRY(startup_32)
+#endif
+
 SECTIONS
 {
 	/* Be careful parts of head_64.S assume startup_32 is at
@@ -33,16 +44,22 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
 	.bss : {
 		_bss = . ;
 		*(.bss)
 		*(.bss.*)
 		*(COMMON)
-		. = ALIGN(8);
-		_end_before_pgt = . ;
-		. = ALIGN(4096);
-		pgtable = . ;
-		. = . + 4096 * 6;
+		. = ALIGN(8);	/* For convenience during zeroing */
 		_ebss = .;
 	}
+#ifdef CONFIG_X86_64
+       . = ALIGN(PAGE_SIZE);
+       .pgtable : {
+		_pgtable = . ;
+		*(.pgtable)
+		_epgtable = . ;
+	}
+#endif
+	_end = .;
 }
diff --git a/arch/x86/boot/compressed/vmlinux.scr b/arch/x86/boot/compressed/vmlinux.scr
deleted file mode 100644
index f02382ae5c4..00000000000
--- a/arch/x86/boot/compressed/vmlinux.scr
+++ /dev/null
@@ -1,10 +0,0 @@
-SECTIONS
-{
-  .rodata.compressed : {
-	input_len = .;
-	LONG(input_data_end - input_data) input_data = .;
-	*(.data)
-	output_len = . - 4;
-	input_data_end = .;
-	}
-}
diff --git a/arch/x86/boot/compressed/vmlinux_32.lds b/arch/x86/boot/compressed/vmlinux_32.lds
deleted file mode 100644
index bb3c48379c4..00000000000
--- a/arch/x86/boot/compressed/vmlinux_32.lds
+++ /dev/null
@@ -1,43 +0,0 @@
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(startup_32)
-SECTIONS
-{
-	/* Be careful parts of head_32.S assume startup_32 is at
-	 * address 0.
-	 */
-	. = 0;
-	.text.head : {
-		_head = . ;
-		*(.text.head)
-		_ehead = . ;
-	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
-	.text :	{
-		_text = .; 	/* Text */
-		*(.text)
-		*(.text.*)
-		_etext = . ;
-	}
-	.rodata : {
-		_rodata = . ;
-		*(.rodata)	 /* read-only data */
-		*(.rodata.*)
-		_erodata = . ;
-	}
-	.data :	{
-		_data = . ;
-		*(.data)
-		*(.data.*)
-		_edata = . ;
-	}
-	.bss : {
-		_bss = . ;
-		*(.bss)
-		*(.bss.*)
-		*(COMMON)
-		_end = . ;
-	}
-}
diff --git a/arch/x86/boot/edd.c b/arch/x86/boot/edd.c
index 1aae8f3e5ca..c501a5b466f 100644
--- a/arch/x86/boot/edd.c
+++ b/arch/x86/boot/edd.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -22,17 +23,17 @@
  */
 static int read_mbr(u8 devno, void *buf)
 {
-	u16 ax, bx, cx, dx;
+	struct biosregs ireg, oreg;
 
-	ax = 0x0201;		/* Legacy Read, one sector */
-	cx = 0x0001;		/* Sector 0-0-1 */
-	dx = devno;
-	bx = (size_t)buf;
-	asm volatile("pushfl; stc; int $0x13; setc %%al; popfl"
-		     : "+a" (ax), "+c" (cx), "+d" (dx), "+b" (bx)
-		     : : "esi", "edi", "memory");
+	initregs(&ireg);
+	ireg.ax = 0x0201;		/* Legacy Read, one sector */
+	ireg.cx = 0x0001;		/* Sector 0-0-1 */
+	ireg.dl = devno;
+	ireg.bx = (size_t)buf;
 
-	return -(u8)ax;		/* 0 or -1 */
+	intcall(0x13, &ireg, &oreg);
+
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
 }
 
 static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
@@ -72,56 +73,46 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
 
 static int get_edd_info(u8 devno, struct edd_info *ei)
 {
-	u16 ax, bx, cx, dx, di;
+	struct biosregs ireg, oreg;
 
 	memset(ei, 0, sizeof *ei);
 
 	/* Check Extensions Present */
 
-	ax = 0x4100;
-	bx = EDDMAGIC1;
-	dx = devno;
-	asm("pushfl; stc; int $0x13; setc %%al; popfl"
-	    : "+a" (ax), "+b" (bx), "=c" (cx), "+d" (dx)
-	    : : "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x41;
+	ireg.bx = EDDMAGIC1;
+	ireg.dl = devno;
+	intcall(0x13, &ireg, &oreg);
 
-	if ((u8)ax)
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;	/* No extended information */
 
-	if (bx != EDDMAGIC2)
+	if (oreg.bx != EDDMAGIC2)
 		return -1;
 
 	ei->device  = devno;
-	ei->version = ax >> 8;	/* EDD version number */
-	ei->interface_support = cx; /* EDD functionality subsets */
+	ei->version = oreg.ah;		 /* EDD version number */
+	ei->interface_support = oreg.cx; /* EDD functionality subsets */
 
 	/* Extended Get Device Parameters */
 
 	ei->params.length = sizeof(ei->params);
-	ax = 0x4800;
-	dx = devno;
-	asm("pushfl; int $0x13; popfl"
-	    : "+a" (ax), "+d" (dx), "=m" (ei->params)
-	    : "S" (&ei->params)
-	    : "ebx", "ecx", "edi");
+	ireg.ah = 0x48;
+	ireg.si = (size_t)&ei->params;
+	intcall(0x13, &ireg, &oreg);
 
 	/* Get legacy CHS parameters */
 
 	/* Ralf Brown recommends setting ES:DI to 0:0 */
-	ax = 0x0800;
-	dx = devno;
-	di = 0;
-	asm("pushw %%es; "
-	    "movw %%di,%%es; "
-	    "pushfl; stc; int $0x13; setc %%al; popfl; "
-	    "popw %%es"
-	    : "+a" (ax), "=b" (bx), "=c" (cx), "+d" (dx), "+D" (di)
-	    : : "esi");
-
-	if ((u8)ax == 0) {
-		ei->legacy_max_cylinder = (cx >> 8) + ((cx & 0xc0) << 2);
-		ei->legacy_max_head = dx >> 8;
-		ei->legacy_sectors_per_track = cx & 0x3f;
+	ireg.ah = 0x08;
+	ireg.es = 0;
+	intcall(0x13, &ireg, &oreg);
+
+	if (!(oreg.eflags & X86_EFLAGS_CF)) {
+		ei->legacy_max_cylinder = oreg.ch + ((oreg.cl & 0xc0) << 2);
+		ei->legacy_max_head = oreg.dh;
+		ei->legacy_sectors_per_track = oreg.cl & 0x3f;
 	}
 
 	return 0;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 5d84d1c74e4..b31cc54b464 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -22,7 +22,8 @@
 #include <asm/page_types.h>
 #include <asm/setup.h>
 #include "boot.h"
-#include "offsets.h"
+#include "voffset.h"
+#include "zoffset.h"
 
 BOOTSEG		= 0x07C0		/* original address of boot-sector */
 SYSSEG		= 0x1000		/* historical load address >> 4 */
@@ -115,7 +116,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x0209		# header version number (>= 0x0105)
+		.word	0x020a		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -168,7 +169,11 @@ heap_end_ptr:	.word	_end+STACK_SIZE-512
 					# end of setup code can be used by setup
 					# for local heap purposes.
 
-pad1:		.word	0
+ext_loader_ver:
+		.byte	0		# Extended boot loader version
+ext_loader_type:
+		.byte	0		# Extended boot loader type
+
 cmd_line_ptr:	.long	0		# (Header version 0x0202 or later)
 					# If nonzero, a 32-bit pointer
 					# to the kernel command line.
@@ -200,7 +205,7 @@ relocatable_kernel:    .byte 1
 #else
 relocatable_kernel:    .byte 0
 #endif
-pad2:			.byte 0
+min_alignment:		.byte MIN_KERNEL_ALIGN_LG2	# minimum alignment
 pad3:			.word 0
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
@@ -212,16 +217,27 @@ hardware_subarch:	.long 0			# subarchitecture, added with 2.07
 
 hardware_subarch_data:	.quad 0
 
-payload_offset:		.long input_data
-payload_length:		.long input_data_end-input_data
+payload_offset:		.long ZO_input_data
+payload_length:		.long ZO_z_input_len
 
 setup_data:		.quad 0			# 64-bit physical pointer to
 						# single linked list of
 						# struct setup_data
 
+pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
+
+#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_extract_offset)
+#define VO_INIT_SIZE	(VO__end - VO__text)
+#if ZO_INIT_SIZE > VO_INIT_SIZE
+#define INIT_SIZE ZO_INIT_SIZE
+#else
+#define INIT_SIZE VO_INIT_SIZE
+#endif
+init_size:		.long INIT_SIZE		# kernel initialization size
+
 # End of setup header #####################################################
 
-	.section ".inittext", "ax"
+	.section ".entrytext", "ax"
 start_of_setup:
 #ifdef SAFE_RESET_DISK_CONTROLLER
 # Reset the disk controller.
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 58f0415d3ae..140172b895b 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -61,11 +62,10 @@ static void copy_boot_params(void)
  */
 static void keyboard_set_repeat(void)
 {
-	u16 ax = 0x0305;
-	u16 bx = 0;
-	asm volatile("int $0x16"
-		     : "+a" (ax), "+b" (bx)
-		     : : "ecx", "edx", "esi", "edi");
+	struct biosregs ireg;
+	initregs(&ireg);
+	ireg.ax = 0x0305;
+	intcall(0x16, &ireg, NULL);
 }
 
 /*
@@ -73,18 +73,22 @@ static void keyboard_set_repeat(void)
  */
 static void query_ist(void)
 {
+	struct biosregs ireg, oreg;
+
 	/* Some older BIOSes apparently crash on this call, so filter
 	   it from machines too old to have SpeedStep at all. */
 	if (cpu.level < 6)
 		return;
 
-	asm("int $0x15"
-	    : "=a" (boot_params.ist_info.signature),
-	      "=b" (boot_params.ist_info.command),
-	      "=c" (boot_params.ist_info.event),
-	      "=d" (boot_params.ist_info.perf_level)
-	    : "a" (0x0000e980),	 /* IST Support */
-	      "d" (0x47534943)); /* Request value */
+	initregs(&ireg);
+	ireg.ax  = 0xe980;	 /* IST Support */
+	ireg.edx = 0x47534943;	 /* Request value */
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.ist_info.signature  = oreg.eax;
+	boot_params.ist_info.command    = oreg.ebx;
+	boot_params.ist_info.event      = oreg.ecx;
+	boot_params.ist_info.perf_level = oreg.edx;
 }
 
 /*
@@ -93,13 +97,12 @@ static void query_ist(void)
 static void set_bios_mode(void)
 {
 #ifdef CONFIG_X86_64
-	u32 eax, ebx;
+	struct biosregs ireg;
 
-	eax = 0xec00;
-	ebx = 2;
-	asm volatile("int $0x15"
-		     : "+a" (eax), "+b" (ebx)
-		     : : "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ax = 0xec00;
+	ireg.bx = 2;
+	intcall(0x15, &ireg, NULL);
 #endif
 }
 
diff --git a/arch/x86/boot/mca.c b/arch/x86/boot/mca.c
index 911eaae5d69..a95a531148e 100644
--- a/arch/x86/boot/mca.c
+++ b/arch/x86/boot/mca.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -16,26 +17,22 @@
 
 int query_mca(void)
 {
-	u8 err;
-	u16 es, bx, len;
-
-	asm("pushw %%es ; "
-	    "int $0x15 ; "
-	    "setc %0 ; "
-	    "movw %%es, %1 ; "
-	    "popw %%es"
-	    : "=acd" (err), "=acdSD" (es), "=b" (bx)
-	    : "a" (0xc000));
-
-	if (err)
+	struct biosregs ireg, oreg;
+	u16 len;
+
+	initregs(&ireg);
+	ireg.ah = 0xc0;
+	intcall(0x15, &ireg, &oreg);
+
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;	/* No MCA present */
 
-	set_fs(es);
-	len = rdfs16(bx);
+	set_fs(oreg.es);
+	len = rdfs16(oreg.bx);
 
 	if (len > sizeof(boot_params.sys_desc_table))
 		len = sizeof(boot_params.sys_desc_table);
 
-	copy_from_fs(&boot_params.sys_desc_table, bx, len);
+	copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len);
 	return 0;
 }
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 74b3d2ba84e..cae3feb1035 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -20,12 +20,16 @@
 static int detect_memory_e820(void)
 {
 	int count = 0;
-	u32 next = 0;
-	u32 size, id, edi;
-	u8 err;
+	struct biosregs ireg, oreg;
 	struct e820entry *desc = boot_params.e820_map;
 	static struct e820entry buf; /* static so it is zeroed */
 
+	initregs(&ireg);
+	ireg.ax  = 0xe820;
+	ireg.cx  = sizeof buf;
+	ireg.edx = SMAP;
+	ireg.di  = (size_t)&buf;
+
 	/*
 	 * Note: at least one BIOS is known which assumes that the
 	 * buffer pointed to by one e820 call is the same one as
@@ -41,22 +45,13 @@ static int detect_memory_e820(void)
 	 */
 
 	do {
-		size = sizeof buf;
-
-		/* Important: %edx and %esi are clobbered by some BIOSes,
-		   so they must be either used for the error output
-		   or explicitly marked clobbered.  Given that, assume there
-		   is something out there clobbering %ebp and %edi, too. */
-		asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0"
-		    : "=d" (err), "+b" (next), "=a" (id), "+c" (size),
-		      "=D" (edi), "+m" (buf)
-		    : "D" (&buf), "d" (SMAP), "a" (0xe820)
-		    : "esi");
+		intcall(0x15, &ireg, &oreg);
+		ireg.ebx = oreg.ebx; /* for next iteration... */
 
 		/* BIOSes which terminate the chain with CF = 1 as opposed
 		   to %ebx = 0 don't always report the SMAP signature on
 		   the final, failing, probe. */
-		if (err)
+		if (oreg.eflags & X86_EFLAGS_CF)
 			break;
 
 		/* Some BIOSes stop returning SMAP in the middle of
@@ -64,60 +59,64 @@ static int detect_memory_e820(void)
 		   screwed up the map at that point, we might have a
 		   partial map, the full map, or complete garbage, so
 		   just return failure. */
-		if (id != SMAP) {
+		if (oreg.eax != SMAP) {
 			count = 0;
 			break;
 		}
 
 		*desc++ = buf;
 		count++;
-	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
+	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
 
 	return boot_params.e820_entries = count;
 }
 
 static int detect_memory_e801(void)
 {
-	u16 ax, bx, cx, dx;
-	u8 err;
+	struct biosregs ireg, oreg;
 
-	bx = cx = dx = 0;
-	ax = 0xe801;
-	asm("stc; int $0x15; setc %0"
-	    : "=m" (err), "+a" (ax), "+b" (bx), "+c" (cx), "+d" (dx));
+	initregs(&ireg);
+	ireg.ax = 0xe801;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err)
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;
 
 	/* Do we really need to do this? */
-	if (cx || dx) {
-		ax = cx;
-		bx = dx;
+	if (oreg.cx || oreg.dx) {
+		oreg.ax = oreg.cx;
+		oreg.bx = oreg.dx;
 	}
 
-	if (ax > 15*1024)
+	if (oreg.ax > 15*1024) {
 		return -1;	/* Bogus! */
-
-	/* This ignores memory above 16MB if we have a memory hole
-	   there.  If someone actually finds a machine with a memory
-	   hole at 16MB and no support for 0E820h they should probably
-	   generate a fake e820 map. */
-	boot_params.alt_mem_k = (ax == 15*1024) ? (dx << 6)+ax : ax;
+	} else if (oreg.ax == 15*1024) {
+		boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
+	} else {
+		/*
+		 * This ignores memory above 16MB if we have a memory
+		 * hole there.  If someone actually finds a machine
+		 * with a memory hole at 16MB and no support for
+		 * 0E820h they should probably generate a fake e820
+		 * map.
+		 */
+		boot_params.alt_mem_k = oreg.ax;
+	}
 
 	return 0;
 }
 
 static int detect_memory_88(void)
 {
-	u16 ax;
-	u8 err;
+	struct biosregs ireg, oreg;
 
-	ax = 0x8800;
-	asm("stc; int $0x15; setc %0" : "=bcdm" (err), "+a" (ax));
+	initregs(&ireg);
+	ireg.ah = 0x88;
+	intcall(0x15, &ireg, &oreg);
 
-	boot_params.screen_info.ext_mem_k = ax;
+	boot_params.screen_info.ext_mem_k = oreg.ax;
 
-	return -err;
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
 }
 
 int detect_memory(void)
diff --git a/arch/x86/boot/regs.c b/arch/x86/boot/regs.c
new file mode 100644
index 00000000000..958019b1cfa
--- /dev/null
+++ b/arch/x86/boot/regs.c
@@ -0,0 +1,29 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Simple helper function for initializing a register set.
+ *
+ * Note that this sets EFLAGS_CF in the input register set; this
+ * makes it easier to catch functions which do nothing but don't
+ * explicitly set CF.
+ */
+
+#include "boot.h"
+
+void initregs(struct biosregs *reg)
+{
+	memset(reg, 0, sizeof *reg);
+	reg->eflags |= X86_EFLAGS_CF;
+	reg->ds = ds();
+	reg->es = ds();
+	reg->fs = fs();
+	reg->gs = gs();
+}
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index bb8dc2de796..0f6ec455a2b 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -15,8 +15,11 @@ SECTIONS
 
 	. = 497;
 	.header		: { *(.header) }
+	.entrytext	: { *(.entrytext) }
 	.inittext	: { *(.inittext) }
 	.initdata	: { *(.initdata) }
+	__end_init = .;
+
 	.text		: { *(.text) }
 	.text32		: { *(.text32) }
 
@@ -52,4 +55,7 @@ SECTIONS
 
 	. = ASSERT(_end <= 0x8000, "Setup too big!");
 	. = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
+	/* Necessary for the very-old-loader check to work... */
+	. = ASSERT(__end_init <= 5*512, "init sections too big!");
+
 }
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 7e8e8b25f5f..01ec69c901c 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -22,24 +23,23 @@
 
 void __attribute__((section(".inittext"))) putchar(int ch)
 {
-	unsigned char c = ch;
+	struct biosregs ireg;
 
-	if (c == '\n')
+	if (ch == '\n')
 		putchar('\r');	/* \n -> \r\n */
 
-	/* int $0x10 is known to have bugs involving touching registers
-	   it shouldn't.  Be extra conservative... */
-	asm volatile("pushal; pushw %%ds; int $0x10; popw %%ds; popal"
-		     : : "b" (0x0007), "c" (0x0001), "a" (0x0e00|ch));
+	initregs(&ireg);
+	ireg.bx = 0x0007;
+	ireg.cx = 0x0001;
+	ireg.ah = 0x0e;
+	ireg.al = ch;
+	intcall(0x10, &ireg, NULL);
 }
 
 void __attribute__((section(".inittext"))) puts(const char *str)
 {
-	int n = 0;
-	while (*str) {
+	while (*str)
 		putchar(*str++);
-		n++;
-	}
 }
 
 /*
@@ -49,14 +49,13 @@ void __attribute__((section(".inittext"))) puts(const char *str)
 
 static u8 gettime(void)
 {
-	u16 ax = 0x0200;
-	u16 cx, dx;
+	struct biosregs ireg, oreg;
 
-	asm volatile("int $0x1a"
-		     : "+a" (ax), "=c" (cx), "=d" (dx)
-		     : : "ebx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x02;
+	intcall(0x1a, &ireg, &oreg);
 
-	return dx >> 8;
+	return oreg.dh;
 }
 
 /*
@@ -64,19 +63,24 @@ static u8 gettime(void)
  */
 int getchar(void)
 {
-	u16 ax = 0;
-	asm volatile("int $0x16" : "+a" (ax));
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	/* ireg.ah = 0x00; */
+	intcall(0x16, &ireg, &oreg);
 
-	return ax & 0xff;
+	return oreg.al;
 }
 
 static int kbd_pending(void)
 {
-	u8 pending;
-	asm volatile("int $0x16; setnz %0"
-		     : "=qm" (pending)
-		     : "a" (0x0100));
-	return pending;
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x01;
+	intcall(0x16, &ireg, &oreg);
+
+	return !(oreg.eflags & X86_EFLAGS_ZF);
 }
 
 void kbd_flush(void)
diff --git a/arch/x86/boot/video-bios.c b/arch/x86/boot/video-bios.c
index 3fa979c9c36..d660be49236 100644
--- a/arch/x86/boot/video-bios.c
+++ b/arch/x86/boot/video-bios.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -29,21 +30,21 @@ static int bios_set_mode(struct mode_info *mi)
 
 static int set_bios_mode(u8 mode)
 {
-	u16 ax;
+	struct biosregs ireg, oreg;
 	u8 new_mode;
 
-	ax = mode;		/* AH=0x00 Set Video Mode */
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.al = mode;		/* AH=0x00 Set Video Mode */
+	intcall(0x10, &ireg, NULL);
 
-	ax = 0x0f00;		/* Get Current Video Mode */
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+
+	ireg.ah = 0x0f;		/* Get Current Video Mode */
+	intcall(0x10, &ireg, &oreg);
 
 	do_restore = 1;		/* Assume video contents were lost */
-	new_mode = ax & 0x7f;	/* Not all BIOSes are clean with the top bit */
+
+	/* Not all BIOSes are clean with the top bit */
+	new_mode = ireg.al & 0x7f;
 
 	if (new_mode == mode)
 		return 0;	/* Mode change OK */
@@ -53,10 +54,8 @@ static int set_bios_mode(u8 mode)
 		/* Mode setting failed, but we didn't end up where we
 		   started.  That's bad.  Try to revert to the original
 		   video mode. */
-		ax = boot_params.screen_info.orig_video_mode;
-		asm volatile(INT10
-			     : "+a" (ax)
-			     : : "ebx", "ecx", "edx", "esi", "edi");
+		ireg.ax = boot_params.screen_info.orig_video_mode;
+		intcall(0x10, &ireg, NULL);
 	}
 #endif
 	return -1;
diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index 4a58c8ce3f6..c700147d6ff 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -31,7 +32,7 @@ static inline void vesa_store_mode_params_graphics(void) {}
 static int vesa_probe(void)
 {
 #if defined(CONFIG_VIDEO_VESA) || defined(CONFIG_FIRMWARE_EDID)
-	u16 ax, cx, di;
+	struct biosregs ireg, oreg;
 	u16 mode;
 	addr_t mode_ptr;
 	struct mode_info *mi;
@@ -39,13 +40,12 @@ static int vesa_probe(void)
 
 	video_vesa.modes = GET_HEAP(struct mode_info, 0);
 
-	ax = 0x4f00;
-	di = (size_t)&vginfo;
-	asm(INT10
-	    : "+a" (ax), "+D" (di), "=m" (vginfo)
-	    : : "ebx", "ecx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f00;
+	ireg.di = (size_t)&vginfo;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f ||
+	if (ireg.ax != 0x004f ||
 	    vginfo.signature != VESA_MAGIC ||
 	    vginfo.version < 0x0102)
 		return 0;	/* Not present */
@@ -65,14 +65,12 @@ static int vesa_probe(void)
 
 		memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
 
-		ax = 0x4f01;
-		cx = mode;
-		di = (size_t)&vminfo;
-		asm(INT10
-		    : "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
-		    : : "ebx", "edx", "esi");
+		ireg.ax = 0x4f01;
+		ireg.cx = mode;
+		ireg.di = (size_t)&vminfo;
+		intcall(0x10, &ireg, &oreg);
 
-		if (ax != 0x004f)
+		if (ireg.ax != 0x004f)
 			continue;
 
 		if ((vminfo.mode_attr & 0x15) == 0x05) {
@@ -111,20 +109,19 @@ static int vesa_probe(void)
 
 static int vesa_set_mode(struct mode_info *mode)
 {
-	u16 ax, bx, cx, di;
+	struct biosregs ireg, oreg;
 	int is_graphic;
 	u16 vesa_mode = mode->mode - VIDEO_FIRST_VESA;
 
 	memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
 
-	ax = 0x4f01;
-	cx = vesa_mode;
-	di = (size_t)&vminfo;
-	asm(INT10
-	    : "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
-	    : : "ebx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f01;
+	ireg.cx = vesa_mode;
+	ireg.di = (size_t)&vminfo;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return -1;
 
 	if ((vminfo.mode_attr & 0x15) == 0x05) {
@@ -141,14 +138,12 @@ static int vesa_set_mode(struct mode_info *mode)
 	}
 
 
-	ax = 0x4f02;
-	bx = vesa_mode;
-	di = 0;
-	asm volatile(INT10
-		     : "+a" (ax), "+b" (bx), "+D" (di)
-		     : : "ecx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f02;
+	ireg.bx = vesa_mode;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return -1;
 
 	graphic_mode = is_graphic;
@@ -171,50 +166,45 @@ static int vesa_set_mode(struct mode_info *mode)
 /* Switch DAC to 8-bit mode */
 static void vesa_dac_set_8bits(void)
 {
+	struct biosregs ireg, oreg;
 	u8 dac_size = 6;
 
 	/* If possible, switch the DAC to 8-bit mode */
 	if (vginfo.capabilities & 1) {
-		u16 ax, bx;
-
-		ax = 0x4f08;
-		bx = 0x0800;
-		asm volatile(INT10
-			     : "+a" (ax), "+b" (bx)
-			     : : "ecx", "edx", "esi", "edi");
-
-		if (ax == 0x004f)
-			dac_size = bx >> 8;
+		initregs(&ireg);
+		ireg.ax = 0x4f08;
+		ireg.bh = 0x08;
+		intcall(0x10, &ireg, &oreg);
+		if (oreg.ax == 0x004f)
+			dac_size = oreg.bh;
 	}
 
 	/* Set the color sizes to the DAC size, and offsets to 0 */
-	boot_params.screen_info.red_size = dac_size;
+	boot_params.screen_info.red_size   = dac_size;
 	boot_params.screen_info.green_size = dac_size;
-	boot_params.screen_info.blue_size = dac_size;
-	boot_params.screen_info.rsvd_size = dac_size;
+	boot_params.screen_info.blue_size  = dac_size;
+	boot_params.screen_info.rsvd_size  = dac_size;
 
-	boot_params.screen_info.red_pos = 0;
-	boot_params.screen_info.green_pos = 0;
-	boot_params.screen_info.blue_pos = 0;
-	boot_params.screen_info.rsvd_pos = 0;
+	boot_params.screen_info.red_pos    = 0;
+	boot_params.screen_info.green_pos  = 0;
+	boot_params.screen_info.blue_pos   = 0;
+	boot_params.screen_info.rsvd_pos   = 0;
 }
 
 /* Save the VESA protected mode info */
 static void vesa_store_pm_info(void)
 {
-	u16 ax, bx, di, es;
+	struct biosregs ireg, oreg;
 
-	ax = 0x4f0a;
-	bx = di = 0;
-	asm("pushw %%es; "INT10"; movw %%es,%0; popw %%es"
-	    : "=d" (es), "+a" (ax), "+b" (bx), "+D" (di)
-	    : : "ecx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f0a;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return;
 
-	boot_params.screen_info.vesapm_seg = es;
-	boot_params.screen_info.vesapm_off = di;
+	boot_params.screen_info.vesapm_seg = oreg.es;
+	boot_params.screen_info.vesapm_off = oreg.di;
 }
 
 /*
@@ -252,7 +242,7 @@ static void vesa_store_mode_params_graphics(void)
 void vesa_store_edid(void)
 {
 #ifdef CONFIG_FIRMWARE_EDID
-	u16 ax, bx, cx, dx, di;
+	struct biosregs ireg, oreg;
 
 	/* Apparently used as a nonsense token... */
 	memset(&boot_params.edid_info, 0x13, sizeof boot_params.edid_info);
@@ -260,33 +250,26 @@ void vesa_store_edid(void)
 	if (vginfo.version < 0x0200)
 		return;		/* EDID requires VBE 2.0+ */
 
-	ax = 0x4f15;		/* VBE DDC */
-	bx = 0x0000;		/* Report DDC capabilities */
-	cx = 0;			/* Controller 0 */
-	di = 0;			/* ES:DI must be 0 by spec */
-
-	/* Note: The VBE DDC spec is different from the main VESA spec;
-	   we genuinely have to assume all registers are destroyed here. */
-
-	asm("pushw %%es; movw %2,%%es; "INT10"; popw %%es"
-	    : "+a" (ax), "+b" (bx), "+c" (cx), "+D" (di)
-	    : : "esi", "edx");
+	initregs(&ireg);
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	/* ireg.bx = 0x0000; */		/* Report DDC capabilities */
+	/* ireg.cx = 0;	*/		/* Controller 0 */
+	ireg.es = 0;			/* ES:DI must be 0 by spec */
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return;		/* No EDID */
 
 	/* BH = time in seconds to transfer EDD information */
 	/* BL = DDC level supported */
 
-	ax = 0x4f15;		/* VBE DDC */
-	bx = 0x0001;		/* Read EDID */
-	cx = 0;			/* Controller 0 */
-	dx = 0;			/* EDID block number */
-	di =(size_t) &boot_params.edid_info; /* (ES:)Pointer to block */
-	asm(INT10
-	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info),
-	      "+c" (cx), "+D" (di)
-	    : : "esi");
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	ireg.bx = 0x0001;		/* Read EDID */
+	/* ireg.cx = 0; */		/* Controller 0 */
+	/* ireg.dx = 0;	*/		/* EDID block number */
+	ireg.es = ds();
+	ireg.di =(size_t)&boot_params.edid_info; /* (ES:)Pointer to block */
+	intcall(0x10, &ireg, &oreg);
 #endif /* CONFIG_FIRMWARE_EDID */
 }
 
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index 9e0587a3776..8f8d827e254 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -39,30 +40,30 @@ static __videocard video_vga;
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
 {
+	struct biosregs ireg, oreg;
 	u16 ax;
 	u8 rows;
 	u8 mode;
 
+	initregs(&ireg);
+
 #ifdef CONFIG_VIDEO_400_HACK
 	if (adapter >= ADAPTER_VGA) {
-		asm volatile(INT10
-			     : : "a" (0x1202), "b" (0x0030)
-			     : "ecx", "edx", "esi", "edi");
+		ireg.ax = 0x1202;
+		ireg.bx = 0x0030;
+		intcall(0x10, &ireg, NULL);
 	}
 #endif
 
 	ax = 0x0f00;
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
-
-	mode = (u8)ax;
+	intcall(0x10, &ireg, &oreg);
+	mode = oreg.al;
 
 	set_fs(0);
 	rows = rdfs8(0x484);	/* rows minus one */
 
 #ifndef CONFIG_VIDEO_400_HACK
-	if ((ax == 0x5003 || ax == 0x5007) &&
+	if ((oreg.ax == 0x5003 || oreg.ax == 0x5007) &&
 	    (rows == 0 || rows == 24))
 		return mode;
 #endif
@@ -71,10 +72,8 @@ static u8 vga_set_basic_mode(void)
 		mode = 3;
 
 	/* Set the mode */
-	ax = mode;
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+	ireg.ax = mode;		/* AH=0: set mode */
+	intcall(0x10, &ireg, NULL);
 	do_restore = 1;
 	return mode;
 }
@@ -82,43 +81,69 @@ static u8 vga_set_basic_mode(void)
 static void vga_set_8font(void)
 {
 	/* Set 8x8 font - 80x43 on EGA, 80x50 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 8x8 font */
-	asm volatile(INT10 : : "a" (0x1112), "b" (0));
+	ireg.ax = 0x1112;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
 
 	/* Use alternate print screen */
-	asm volatile(INT10 : : "a" (0x1200), "b" (0x20));
+	ireg.ax = 0x1200;
+	ireg.bl = 0x20;
+	intcall(0x10, &ireg, NULL);
 
 	/* Turn off cursor emulation */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
 
 	/* Cursor is scan lines 6-7 */
-	asm volatile(INT10 : : "a" (0x0100), "c" (0x0607));
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0607;
+	intcall(0x10, &ireg, NULL);
 }
 
 static void vga_set_14font(void)
 {
 	/* Set 9x14 font - 80x28 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 9x14 font */
-	asm volatile(INT10 : : "a" (0x1111), "b" (0));
+	ireg.ax = 0x1111;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
 
 	/* Turn off cursor emulation */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
 
 	/* Cursor is scan lines 11-12 */
-	asm volatile(INT10 : : "a" (0x0100), "c" (0x0b0c));
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0b0c;
+	intcall(0x10, &ireg, NULL);
 }
 
 static void vga_set_80x43(void)
 {
 	/* Set 80x43 mode on VGA (not EGA) */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 350 scans */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x30));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x30;
+	intcall(0x10, &ireg, NULL);
 
 	/* Reset video mode */
-	asm volatile(INT10 : : "a" (0x0003));
+	ireg.ax = 0x0003;
+	intcall(0x10, &ireg, NULL);
 
 	vga_set_8font();
 }
@@ -225,8 +250,6 @@ static int vga_set_mode(struct mode_info *mode)
  */
 static int vga_probe(void)
 {
-	u16 ega_bx;
-
 	static const char *card_name[] = {
 		"CGA/MDA/HGC", "EGA", "VGA"
 	};
@@ -240,26 +263,26 @@ static int vga_probe(void)
 		sizeof(ega_modes)/sizeof(struct mode_info),
 		sizeof(vga_modes)/sizeof(struct mode_info),
 	};
-	u8 vga_flag;
 
-	asm(INT10
-	    : "=b" (ega_bx)
-	    : "a" (0x1200), "b" (0x10) /* Check EGA/VGA */
-	    : "ecx", "edx", "esi", "edi");
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+
+	ireg.ax = 0x1200;
+	ireg.bl = 0x10;		/* Check EGA/VGA */
+	intcall(0x10, &ireg, &oreg);
 
 #ifndef _WAKEUP
-	boot_params.screen_info.orig_video_ega_bx = ega_bx;
+	boot_params.screen_info.orig_video_ega_bx = oreg.bx;
 #endif
 
 	/* If we have MDA/CGA/HGC then BL will be unchanged at 0x10 */
-	if ((u8)ega_bx != 0x10) {
+	if (oreg.bl != 0x10) {
 		/* EGA/VGA */
-		asm(INT10
-		    : "=a" (vga_flag)
-		    : "a" (0x1a00)
-		    : "ebx", "ecx", "edx", "esi", "edi");
+		ireg.ax = 0x1a00;
+		intcall(0x10, &ireg, &oreg);
 
-		if (vga_flag == 0x1a) {
+		if (oreg.al == 0x1a) {
 			adapter = ADAPTER_VGA;
 #ifndef _WAKEUP
 			boot_params.screen_info.orig_video_isVGA = 1;
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 3bef2c1febe..bad728b76fc 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -18,33 +19,29 @@
 
 static void store_cursor_position(void)
 {
-	u16 curpos;
-	u16 ax, bx;
+	struct biosregs ireg, oreg;
 
-	ax = 0x0300;
-	bx = 0;
-	asm(INT10
-	    : "=d" (curpos), "+a" (ax), "+b" (bx)
-	    : : "ecx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x03;
+	intcall(0x10, &ireg, &oreg);
 
-	boot_params.screen_info.orig_x = curpos;
-	boot_params.screen_info.orig_y = curpos >> 8;
+	boot_params.screen_info.orig_x = oreg.dl;
+	boot_params.screen_info.orig_y = oreg.dh;
 }
 
 static void store_video_mode(void)
 {
-	u16 ax, page;
+	struct biosregs ireg, oreg;
 
 	/* N.B.: the saving of the video page here is a bit silly,
 	   since we pretty much assume page 0 everywhere. */
-	ax = 0x0f00;
-	asm(INT10
-	    : "+a" (ax), "=b" (page)
-	    : : "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x0f;
+	intcall(0x10, &ireg, &oreg);
 
 	/* Not all BIOSes are clean with respect to the top bit */
-	boot_params.screen_info.orig_video_mode = ax & 0x7f;
-	boot_params.screen_info.orig_video_page = page >> 8;
+	boot_params.screen_info.orig_video_mode = oreg.al & 0x7f;
+	boot_params.screen_info.orig_video_page = oreg.bh;
 }
 
 /*
@@ -257,7 +254,7 @@ static void restore_screen(void)
 	int y;
 	addr_t dst = 0;
 	u16 *src = saved.data;
-	u16 ax, bx, dx;
+	struct biosregs ireg;
 
 	if (graphic_mode)
 		return;		/* Can't restore onto a graphic mode */
@@ -296,12 +293,11 @@ static void restore_screen(void)
 	}
 
 	/* Restore cursor position */
-	ax = 0x0200;		/* Set cursor position */
-	bx = 0;			/* Page number (<< 8) */
-	dx = (saved.cury << 8)+saved.curx;
-	asm volatile(INT10
-		     : "+a" (ax), "+b" (bx), "+d" (dx)
-		     : : "ecx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x02;		/* Set cursor position */
+	ireg.dh = saved.cury;
+	ireg.dl = saved.curx;
+	intcall(0x10, &ireg, NULL);
 }
 #else
 #define save_screen()		((void)0)
diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h
index ee63f5d1446..5bb174a997f 100644
--- a/arch/x86/boot/video.h
+++ b/arch/x86/boot/video.h
@@ -112,20 +112,6 @@ extern int force_x, force_y;	/* Don't query the BIOS for cols/rows */
 extern int do_restore;		/* Restore screen contents */
 extern int graphic_mode;	/* Graphics mode with linear frame buffer */
 
-/*
- * int $0x10 is notorious for touching registers it shouldn't.
- * gcc doesn't like %ebp being clobbered, so define it as a push/pop
- * sequence here.
- *
- * A number of systems, including the original PC can clobber %bp in
- * certain circumstances, like when scrolling.  There exists at least
- * one Trident video card which could clobber DS under a set of
- * circumstances that we are unlikely to encounter (scrolling when
- * using an extended graphics mode of more than 800x600 pixels), but
- * it's cheap insurance to deal with that here.
- */
-#define INT10 "pushl %%ebp; pushw %%ds; int $0x10; popw %%ds; popl %%ebp"
-
 /* Accessing VGA indexed registers */
 static inline u8 in_idx(u16 port, u8 index)
 {
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 235b81d0f6f..edb992ebef9 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,12 +1,13 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29-rc4
-# Tue Feb 24 15:50:58 2009
+# Linux kernel version: 2.6.30-rc2
+# Mon May 11 16:21:55 2009
 #
 # CONFIG_64BIT is not set
 CONFIG_X86_32=y
 # CONFIG_X86_64 is not set
 CONFIG_X86=y
+CONFIG_OUTPUT_FORMAT="elf32-i386"
 CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_CMOS_UPDATE=y
@@ -33,6 +34,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
 CONFIG_ARCH_HAS_DEFAULT_IDLE=y
 CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
 # CONFIG_HAVE_CPUMASK_OF_CPU_MAP is not set
 CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
@@ -40,15 +42,16 @@ CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 # CONFIG_AUDIT_ARCH is not set
 CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
-CONFIG_X86_SMP=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
 CONFIG_X86_32_SMP=y
 CONFIG_X86_HT=y
-CONFIG_X86_BIOS_REBOOT=y
 CONFIG_X86_TRAMPOLINE=y
+CONFIG_X86_32_LAZY_GS=y
 CONFIG_KTIME_SCALAR=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
@@ -60,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
 CONFIG_LOCALVERSION=""
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 CONFIG_TASKSTATS=y
@@ -113,23 +123,26 @@ CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_PCSPKR_PLATFORM=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
@@ -139,6 +152,7 @@ CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
@@ -154,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -167,7 +183,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_BSG=y
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -194,12 +209,12 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
 CONFIG_SPARSE_IRQ=y
-CONFIG_X86_FIND_SMP_CONFIG=y
 CONFIG_X86_MPPARSE=y
+# CONFIG_X86_BIGSMP is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
 # CONFIG_X86_ELAN is not set
-# CONFIG_X86_GENERICARCH is not set
-# CONFIG_X86_VSMP is not set
 # CONFIG_X86_RDC321X is not set
+# CONFIG_X86_32_NON_STANDARD is not set
 CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_PARAVIRT_GUEST is not set
 # CONFIG_MEMTEST is not set
@@ -230,8 +245,10 @@ CONFIG_M686=y
 # CONFIG_GENERIC_CPU is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CPU=y
+CONFIG_X86_L1_CACHE_BYTES=64
+CONFIG_X86_INTERNODE_CACHE_BYTES=64
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=5
 CONFIG_X86_XADD=y
 # CONFIG_X86_PPRO_FENCE is not set
 CONFIG_X86_WP_WORKS_OK=y
@@ -247,7 +264,7 @@ CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_CPU_SUP_INTEL=y
 CONFIG_CPU_SUP_CYRIX_32=y
 CONFIG_CPU_SUP_AMD=y
-CONFIG_CPU_SUP_CENTAUR_32=y
+CONFIG_CPU_SUP_CENTAUR=y
 CONFIG_CPU_SUP_TRANSMETA_32=y
 CONFIG_CPU_SUP_UMC_32=y
 CONFIG_X86_DS=y
@@ -279,6 +296,7 @@ CONFIG_MICROCODE_AMD=y
 CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
+# CONFIG_X86_CPU_DEBUG is not set
 # CONFIG_NOHIGHMEM is not set
 CONFIG_HIGHMEM4G=y
 # CONFIG_HIGHMEM64G is not set
@@ -302,6 +320,8 @@ CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
 CONFIG_HIGHPTE=y
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
@@ -312,6 +332,7 @@ CONFIG_MTRR=y
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
@@ -322,8 +343,9 @@ CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_RELOCATABLE=y
+CONFIG_X86_NEED_RELOCS=y
+CONFIG_PHYSICAL_ALIGN=0x1000000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
 # CONFIG_CMDLINE_BOOL is not set
@@ -363,7 +385,6 @@ CONFIG_ACPI_THERMAL=y
 CONFIG_ACPI_BLACKLIST_YEAR=0
 # CONFIG_ACPI_DEBUG is not set
 # CONFIG_ACPI_PCI_SLOT is not set
-CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
 CONFIG_ACPI_CONTAINER=y
 # CONFIG_ACPI_SBS is not set
@@ -425,6 +446,7 @@ CONFIG_PCI_BIOS=y
 CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
 CONFIG_PCI_DOMAINS=y
+# CONFIG_DMAR is not set
 CONFIG_PCIEPORTBUS=y
 # CONFIG_HOTPLUG_PCI_PCIE is not set
 CONFIG_PCIEAER=y
@@ -435,6 +457,7 @@ CONFIG_PCI_MSI=y
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCI_STUB is not set
 CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
 CONFIG_ISA_DMA_API=y
 # CONFIG_ISA is not set
 # CONFIG_MCA is not set
@@ -481,7 +504,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-CONFIG_COMPAT_NET_DEV_OPS=y
 CONFIG_PACKET=y
 CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
@@ -639,6 +661,7 @@ CONFIG_LLC=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
 CONFIG_NET_SCHED=y
 
 #
@@ -696,6 +719,7 @@ CONFIG_NET_SCH_FIFO=y
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_HAMRADIO=y
 
 #
@@ -706,12 +730,10 @@ CONFIG_HAMRADIO=y
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_PHONET is not set
 CONFIG_FIB_RULES=y
 CONFIG_WIRELESS=y
 CONFIG_CFG80211=y
 # CONFIG_CFG80211_REG_DEBUG is not set
-CONFIG_NL80211=y
 CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
 CONFIG_WIRELESS_EXT_SYSFS=y
@@ -789,6 +811,7 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_ICS932S401 is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
 # CONFIG_HP_ILO is not set
+# CONFIG_ISL29003 is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -842,6 +865,7 @@ CONFIG_SCSI_SPI_ATTRS=y
 # CONFIG_SCSI_LOWLEVEL is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 # CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
@@ -940,6 +964,7 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
+CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
@@ -977,6 +1002,8 @@ CONFIG_MII=y
 CONFIG_NET_VENDOR_3COM=y
 # CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
+# CONFIG_ETHOC is not set
+# CONFIG_DNET is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 # CONFIG_TULIP is not set
@@ -1026,6 +1053,7 @@ CONFIG_E1000=y
 CONFIG_E1000E=y
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -1040,6 +1068,7 @@ CONFIG_BNX2=y
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 # CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
 # CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
@@ -1049,6 +1078,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -1058,6 +1088,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_BNX2X is not set
 # CONFIG_QLGE is not set
 # CONFIG_SFC is not set
+# CONFIG_BE2NET is not set
 CONFIG_TR=y
 # CONFIG_IBMOL is not set
 # CONFIG_IBMLS is not set
@@ -1073,8 +1104,8 @@ CONFIG_WLAN_80211=y
 # CONFIG_LIBERTAS is not set
 # CONFIG_LIBERTAS_THINFIRM is not set
 # CONFIG_AIRO is not set
-# CONFIG_HERMES is not set
 # CONFIG_ATMEL is not set
+# CONFIG_AT76C50X_USB is not set
 # CONFIG_AIRO_CS is not set
 # CONFIG_PCMCIA_WL3501 is not set
 # CONFIG_PRISM54 is not set
@@ -1084,21 +1115,21 @@ CONFIG_WLAN_80211=y
 # CONFIG_RTL8187 is not set
 # CONFIG_ADM8211 is not set
 # CONFIG_MAC80211_HWSIM is not set
+# CONFIG_MWL8K is not set
 # CONFIG_P54_COMMON is not set
 CONFIG_ATH5K=y
 # CONFIG_ATH5K_DEBUG is not set
 # CONFIG_ATH9K is not set
+# CONFIG_AR9170_USB is not set
 # CONFIG_IPW2100 is not set
 # CONFIG_IPW2200 is not set
-# CONFIG_IWLCORE is not set
-# CONFIG_IWLWIFI_LEDS is not set
-# CONFIG_IWLAGN is not set
-# CONFIG_IWL3945 is not set
+# CONFIG_IWLWIFI is not set
 # CONFIG_HOSTAP is not set
 # CONFIG_B43 is not set
 # CONFIG_B43LEGACY is not set
 # CONFIG_ZD1211RW is not set
 # CONFIG_RT2X00 is not set
+# CONFIG_HERMES is not set
 
 #
 # Enable WiMAX (Networking options) to see the WiMAX drivers
@@ -1209,6 +1240,8 @@ CONFIG_INPUT_TABLET=y
 # CONFIG_TABLET_USB_KBTAB is not set
 # CONFIG_TABLET_USB_WACOM is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
+# CONFIG_TOUCHSCREEN_AD7879 is not set
 # CONFIG_TOUCHSCREEN_FUJITSU is not set
 # CONFIG_TOUCHSCREEN_GUNZE is not set
 # CONFIG_TOUCHSCREEN_ELO is not set
@@ -1303,6 +1336,7 @@ CONFIG_UNIX98_PTYS=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
 CONFIG_HW_RANDOM_INTEL=y
 CONFIG_HW_RANDOM_AMD=y
 CONFIG_HW_RANDOM_GEODE=y
@@ -1390,7 +1424,6 @@ CONFIG_I2C_I801=y
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
-# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_MAX6875 is not set
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
@@ -1424,6 +1457,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_ADT7475 is not set
 # CONFIG_SENSORS_K8TEMP is not set
 # CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATK0110 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
@@ -1433,6 +1467,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_FSCHER is not set
 # CONFIG_SENSORS_FSCPOS is not set
 # CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
@@ -1448,11 +1483,14 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_LM90 is not set
 # CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4215 is not set
 # CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LM95241 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1643,7 +1681,6 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_3DFX is not set
 # CONFIG_FB_VOODOO1 is not set
 # CONFIG_FB_VT8623 is not set
-# CONFIG_FB_CYBLA is not set
 # CONFIG_FB_TRIDENT is not set
 # CONFIG_FB_ARK is not set
 # CONFIG_FB_PM3 is not set
@@ -1652,6 +1689,7 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
 # CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -1738,6 +1776,8 @@ CONFIG_SND_PCI=y
 # CONFIG_SND_INDIGO is not set
 # CONFIG_SND_INDIGOIO is not set
 # CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_INDIGOIOX is not set
+# CONFIG_SND_INDIGODJX is not set
 # CONFIG_SND_EMU10K1 is not set
 # CONFIG_SND_EMU10K1X is not set
 # CONFIG_SND_ENS1370 is not set
@@ -1811,15 +1851,17 @@ CONFIG_USB_HIDDEV=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+CONFIG_HID_KYE=y
 CONFIG_HID_GYRATION=y
+CONFIG_HID_KENSINGTON=y
 CONFIG_HID_LOGITECH=y
 CONFIG_LOGITECH_FF=y
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1885,11 +1927,11 @@ CONFIG_USB_PRINTER=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
 #
 
 #
-# see USB_STORAGE Help for more information
+# also be needed; see USB_STORAGE Help for more info
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1931,7 +1973,6 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
 # CONFIG_USB_FTDI_ELAN is not set
 # CONFIG_USB_APPLEDISPLAY is not set
@@ -1947,6 +1988,7 @@ CONFIG_USB_LIBUSUAL=y
 #
 # OTG and related infrastructure
 #
+# CONFIG_NOP_USB_XCEIV is not set
 # CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
@@ -1958,8 +2000,10 @@ CONFIG_LEDS_CLASS=y
 #
 # CONFIG_LEDS_ALIX2 is not set
 # CONFIG_LEDS_PCA9532 is not set
+# CONFIG_LEDS_LP5521 is not set
 # CONFIG_LEDS_CLEVO_MAIL is not set
 # CONFIG_LEDS_PCA955X is not set
+# CONFIG_LEDS_BD2802 is not set
 
 #
 # LED Triggers
@@ -1969,6 +2013,10 @@ CONFIG_LEDS_TRIGGERS=y
 # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
 # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
 # CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
+
+#
+# iptables trigger is under Netfilter config (LED target)
+#
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 CONFIG_EDAC=y
@@ -2037,6 +2085,7 @@ CONFIG_DMADEVICES=y
 # DMA Devices
 #
 # CONFIG_INTEL_IOATDMA is not set
+# CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 # CONFIG_STAGING is not set
 CONFIG_X86_PLATFORM_DEVICES=y
@@ -2071,6 +2120,7 @@ CONFIG_DMIID=y
 #
 # CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
@@ -2101,6 +2151,11 @@ CONFIG_AUTOFS4_FS=y
 CONFIG_GENERIC_ACL=y
 
 #
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
 # CD-ROM/DVD Filesystems
 #
 CONFIG_ISO9660_FS=y
@@ -2151,6 +2206,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -2164,7 +2220,6 @@ CONFIG_NFS_ACL_SUPPORT=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
 CONFIG_SUNRPC_GSS=y
-# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -2251,6 +2306,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
@@ -2266,6 +2322,7 @@ CONFIG_TIMER_STATS=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 # CONFIG_DEBUG_HIGHMEM is not set
 CONFIG_DEBUG_BUGVERBOSE=y
@@ -2289,13 +2346,19 @@ CONFIG_FRAME_POINTER=y
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
+# CONFIG_DEBUG_PAGEALLOC is not set
 CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
+CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -2305,13 +2368,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
 # CONFIG_SYSPROF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_FTRACE_SYSCALLS is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_POWER_TRACER is not set
 # CONFIG_STACK_TRACER is not set
 # CONFIG_HW_BRANCH_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+CONFIG_BLK_DEV_IO_TRACE=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
-# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -2321,7 +2392,6 @@ CONFIG_EARLY_PRINTK=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 # CONFIG_X86_PTDUMP is not set
 CONFIG_DEBUG_RODATA=y
@@ -2329,7 +2399,7 @@ CONFIG_DEBUG_RODATA=y
 CONFIG_DEBUG_NX_TEST=m
 # CONFIG_4KSTACKS is not set
 CONFIG_DOUBLEFAULT=y
-# CONFIG_MMIOTRACE is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
 CONFIG_IO_DELAY_TYPE_0X80=0
 CONFIG_IO_DELAY_TYPE_0XED=1
 CONFIG_IO_DELAY_TYPE_UDELAY=2
@@ -2365,6 +2435,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
 CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
 # CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
 # CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_IMA is not set
 CONFIG_CRYPTO=y
 
 #
@@ -2380,10 +2452,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
 CONFIG_CRYPTO_HASH=y
 CONFIG_CRYPTO_HASH2=y
 CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_MANAGER2=y
 # CONFIG_CRYPTO_GF128MUL is not set
 # CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=y
 # CONFIG_CRYPTO_TEST is not set
@@ -2456,6 +2530,7 @@ CONFIG_CRYPTO_DES=y
 # Compression
 #
 # CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
 
 #
@@ -2467,11 +2542,13 @@ CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_GEODE is not set
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
 CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
 CONFIG_VIRTUALIZATION=y
 # CONFIG_KVM is not set
 # CONFIG_LGUEST is not set
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
@@ -2489,7 +2566,10 @@ CONFIG_CRC32=y
 # CONFIG_LIBCRC32C is not set
 CONFIG_AUDIT_GENERIC=y
 CONFIG_ZLIB_INFLATE=y
-CONFIG_PLIST=y
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
+CONFIG_NLATTR=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 9fe5d212ab4..cee1dd2e69b 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,12 +1,13 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29-rc4
-# Tue Feb 24 15:44:16 2009
+# Linux kernel version: 2.6.30-rc2
+# Mon May 11 16:22:00 2009
 #
 CONFIG_64BIT=y
 # CONFIG_X86_32 is not set
 CONFIG_X86_64=y
 CONFIG_X86=y
+CONFIG_OUTPUT_FORMAT="elf64-x86-64"
 CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_CMOS_UPDATE=y
@@ -34,6 +35,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
 CONFIG_ARCH_HAS_DEFAULT_IDLE=y
 CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
 CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y
 CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
@@ -41,14 +43,14 @@ CONFIG_ZONE_DMA32=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_AUDIT_ARCH=y
 CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
-CONFIG_X86_SMP=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
 CONFIG_X86_64_SMP=y
 CONFIG_X86_HT=y
-CONFIG_X86_BIOS_REBOOT=y
 CONFIG_X86_TRAMPOLINE=y
 # CONFIG_KTIME_SCALAR is not set
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
@@ -61,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
 CONFIG_LOCALVERSION=""
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 CONFIG_TASKSTATS=y
@@ -114,23 +123,26 @@ CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_PCSPKR_PLATFORM=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
@@ -140,6 +152,7 @@ CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
@@ -155,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -167,7 +182,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
-CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_BSG=y
 # CONFIG_BLK_DEV_INTEGRITY is not set
 CONFIG_BLOCK_COMPAT=y
@@ -195,12 +209,10 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
 CONFIG_SPARSE_IRQ=y
-# CONFIG_NUMA_MIGRATE_IRQ_DESC is not set
-CONFIG_X86_FIND_SMP_CONFIG=y
 CONFIG_X86_MPPARSE=y
-# CONFIG_X86_ELAN is not set
-# CONFIG_X86_GENERICARCH is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
 # CONFIG_X86_VSMP is not set
+# CONFIG_X86_UV is not set
 CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_PARAVIRT_GUEST is not set
 # CONFIG_MEMTEST is not set
@@ -230,10 +242,10 @@ CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_MCORE2 is not set
 CONFIG_GENERIC_CPU=y
 CONFIG_X86_CPU=y
-CONFIG_X86_L1_CACHE_BYTES=128
-CONFIG_X86_INTERNODE_CACHE_BYTES=128
+CONFIG_X86_L1_CACHE_BYTES=64
+CONFIG_X86_INTERNODE_CACHE_BYTES=64
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=6
 CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_TSC=y
 CONFIG_X86_CMPXCHG64=y
@@ -242,7 +254,7 @@ CONFIG_X86_MINIMUM_CPU_FAMILY=64
 CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_CPU_SUP_INTEL=y
 CONFIG_CPU_SUP_AMD=y
-CONFIG_CPU_SUP_CENTAUR_64=y
+CONFIG_CPU_SUP_CENTAUR=y
 CONFIG_X86_DS=y
 CONFIG_X86_PTRACE_BTS=y
 CONFIG_HPET_TIMER=y
@@ -269,6 +281,7 @@ CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
 CONFIG_X86_MCE=y
 CONFIG_X86_MCE_INTEL=y
 CONFIG_X86_MCE_AMD=y
+CONFIG_X86_MCE_THRESHOLD=y
 # CONFIG_I8K is not set
 CONFIG_MICROCODE=y
 CONFIG_MICROCODE_INTEL=y
@@ -276,6 +289,7 @@ CONFIG_MICROCODE_AMD=y
 CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
+# CONFIG_X86_CPU_DEBUG is not set
 CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
 CONFIG_DIRECT_GBPAGES=y
 CONFIG_NUMA=y
@@ -309,6 +323,8 @@ CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
 CONFIG_X86_RESERVE_LOW_64K=y
@@ -317,6 +333,7 @@ CONFIG_MTRR=y
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
@@ -325,9 +342,10 @@ CONFIG_HZ=1000
 CONFIG_SCHED_HRTICK=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+# CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_RELOCATABLE=y
+CONFIG_PHYSICAL_ALIGN=0x1000000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
 # CONFIG_CMDLINE_BOOL is not set
@@ -370,7 +388,6 @@ CONFIG_ACPI_NUMA=y
 CONFIG_ACPI_BLACKLIST_YEAR=0
 # CONFIG_ACPI_DEBUG is not set
 # CONFIG_ACPI_PCI_SLOT is not set
-CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
 CONFIG_ACPI_CONTAINER=y
 # CONFIG_ACPI_SBS is not set
@@ -436,6 +453,7 @@ CONFIG_PCI_MSI=y
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCI_STUB is not set
 CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
 CONFIG_ISA_DMA_API=y
 CONFIG_K8_NB=y
 CONFIG_PCCARD=y
@@ -481,7 +499,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-CONFIG_COMPAT_NET_DEV_OPS=y
 CONFIG_PACKET=y
 CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
@@ -639,6 +656,7 @@ CONFIG_LLC=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
 CONFIG_NET_SCHED=y
 
 #
@@ -696,6 +714,7 @@ CONFIG_NET_SCH_FIFO=y
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_HAMRADIO=y
 
 #
@@ -706,12 +725,10 @@ CONFIG_HAMRADIO=y
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_PHONET is not set
 CONFIG_FIB_RULES=y
 CONFIG_WIRELESS=y
 CONFIG_CFG80211=y
 # CONFIG_CFG80211_REG_DEBUG is not set
-CONFIG_NL80211=y
 CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
 CONFIG_WIRELESS_EXT_SYSFS=y
@@ -788,9 +805,8 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_TIFM_CORE is not set
 # CONFIG_ICS932S401 is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
-# CONFIG_SGI_XP is not set
 # CONFIG_HP_ILO is not set
-# CONFIG_SGI_GRU is not set
+# CONFIG_ISL29003 is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -844,6 +860,7 @@ CONFIG_SCSI_SPI_ATTRS=y
 # CONFIG_SCSI_LOWLEVEL is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 # CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
@@ -940,6 +957,7 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
+CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
@@ -977,6 +995,8 @@ CONFIG_MII=y
 CONFIG_NET_VENDOR_3COM=y
 # CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
+# CONFIG_ETHOC is not set
+# CONFIG_DNET is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 # CONFIG_TULIP is not set
@@ -1026,6 +1046,7 @@ CONFIG_E1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -1040,6 +1061,7 @@ CONFIG_TIGON3=y
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 # CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
 # CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
@@ -1049,6 +1071,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -1058,6 +1081,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_BNX2X is not set
 # CONFIG_QLGE is not set
 # CONFIG_SFC is not set
+# CONFIG_BE2NET is not set
 CONFIG_TR=y
 # CONFIG_IBMOL is not set
 # CONFIG_3C359 is not set
@@ -1072,8 +1096,8 @@ CONFIG_WLAN_80211=y
 # CONFIG_LIBERTAS is not set
 # CONFIG_LIBERTAS_THINFIRM is not set
 # CONFIG_AIRO is not set
-# CONFIG_HERMES is not set
 # CONFIG_ATMEL is not set
+# CONFIG_AT76C50X_USB is not set
 # CONFIG_AIRO_CS is not set
 # CONFIG_PCMCIA_WL3501 is not set
 # CONFIG_PRISM54 is not set
@@ -1083,21 +1107,21 @@ CONFIG_WLAN_80211=y
 # CONFIG_RTL8187 is not set
 # CONFIG_ADM8211 is not set
 # CONFIG_MAC80211_HWSIM is not set
+# CONFIG_MWL8K is not set
 # CONFIG_P54_COMMON is not set
 CONFIG_ATH5K=y
 # CONFIG_ATH5K_DEBUG is not set
 # CONFIG_ATH9K is not set
+# CONFIG_AR9170_USB is not set
 # CONFIG_IPW2100 is not set
 # CONFIG_IPW2200 is not set
-# CONFIG_IWLCORE is not set
-# CONFIG_IWLWIFI_LEDS is not set
-# CONFIG_IWLAGN is not set
-# CONFIG_IWL3945 is not set
+# CONFIG_IWLWIFI is not set
 # CONFIG_HOSTAP is not set
 # CONFIG_B43 is not set
 # CONFIG_B43LEGACY is not set
 # CONFIG_ZD1211RW is not set
 # CONFIG_RT2X00 is not set
+# CONFIG_HERMES is not set
 
 #
 # Enable WiMAX (Networking options) to see the WiMAX drivers
@@ -1208,6 +1232,8 @@ CONFIG_INPUT_TABLET=y
 # CONFIG_TABLET_USB_KBTAB is not set
 # CONFIG_TABLET_USB_WACOM is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
+# CONFIG_TOUCHSCREEN_AD7879 is not set
 # CONFIG_TOUCHSCREEN_FUJITSU is not set
 # CONFIG_TOUCHSCREEN_GUNZE is not set
 # CONFIG_TOUCHSCREEN_ELO is not set
@@ -1301,6 +1327,7 @@ CONFIG_UNIX98_PTYS=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
 # CONFIG_HW_RANDOM_INTEL is not set
 # CONFIG_HW_RANDOM_AMD is not set
 CONFIG_NVRAM=y
@@ -1382,7 +1409,6 @@ CONFIG_I2C_I801=y
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
-# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_MAX6875 is not set
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
@@ -1416,6 +1442,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_ADT7475 is not set
 # CONFIG_SENSORS_K8TEMP is not set
 # CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATK0110 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
@@ -1425,6 +1452,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_FSCHER is not set
 # CONFIG_SENSORS_FSCPOS is not set
 # CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
@@ -1440,11 +1468,14 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_LM90 is not set
 # CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4215 is not set
 # CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LM95241 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1635,6 +1666,7 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
 # CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -1720,6 +1752,8 @@ CONFIG_SND_PCI=y
 # CONFIG_SND_INDIGO is not set
 # CONFIG_SND_INDIGOIO is not set
 # CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_INDIGOIOX is not set
+# CONFIG_SND_INDIGODJX is not set
 # CONFIG_SND_EMU10K1 is not set
 # CONFIG_SND_EMU10K1X is not set
 # CONFIG_SND_ENS1370 is not set
@@ -1792,15 +1826,17 @@ CONFIG_USB_HIDDEV=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+CONFIG_HID_KYE=y
 CONFIG_HID_GYRATION=y
+CONFIG_HID_KENSINGTON=y
 CONFIG_HID_LOGITECH=y
 CONFIG_LOGITECH_FF=y
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1866,11 +1902,11 @@ CONFIG_USB_PRINTER=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
 #
 
 #
-# see USB_STORAGE Help for more information
+# also be needed; see USB_STORAGE Help for more info
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1912,7 +1948,6 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
 # CONFIG_USB_FTDI_ELAN is not set
 # CONFIG_USB_APPLEDISPLAY is not set
@@ -1928,6 +1963,7 @@ CONFIG_USB_LIBUSUAL=y
 #
 # OTG and related infrastructure
 #
+# CONFIG_NOP_USB_XCEIV is not set
 # CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
@@ -1939,8 +1975,10 @@ CONFIG_LEDS_CLASS=y
 #
 # CONFIG_LEDS_ALIX2 is not set
 # CONFIG_LEDS_PCA9532 is not set
+# CONFIG_LEDS_LP5521 is not set
 # CONFIG_LEDS_CLEVO_MAIL is not set
 # CONFIG_LEDS_PCA955X is not set
+# CONFIG_LEDS_BD2802 is not set
 
 #
 # LED Triggers
@@ -1950,6 +1988,10 @@ CONFIG_LEDS_TRIGGERS=y
 # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
 # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
 # CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
+
+#
+# iptables trigger is under Netfilter config (LED target)
+#
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 CONFIG_EDAC=y
@@ -2018,6 +2060,7 @@ CONFIG_DMADEVICES=y
 # DMA Devices
 #
 # CONFIG_INTEL_IOATDMA is not set
+# CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 # CONFIG_STAGING is not set
 CONFIG_X86_PLATFORM_DEVICES=y
@@ -2051,6 +2094,7 @@ CONFIG_DMIID=y
 #
 # CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
@@ -2082,6 +2126,11 @@ CONFIG_AUTOFS4_FS=y
 CONFIG_GENERIC_ACL=y
 
 #
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
 # CD-ROM/DVD Filesystems
 #
 CONFIG_ISO9660_FS=y
@@ -2132,6 +2181,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -2145,7 +2195,6 @@ CONFIG_NFS_ACL_SUPPORT=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
 CONFIG_SUNRPC_GSS=y
-# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -2232,6 +2281,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
@@ -2247,6 +2297,7 @@ CONFIG_TIMER_STATS=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
@@ -2269,13 +2320,19 @@ CONFIG_FRAME_POINTER=y
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
+# CONFIG_DEBUG_PAGEALLOC is not set
 CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
+CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -2285,13 +2342,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
 # CONFIG_SYSPROF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_FTRACE_SYSCALLS is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_POWER_TRACER is not set
 # CONFIG_STACK_TRACER is not set
 # CONFIG_HW_BRANCH_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+CONFIG_BLK_DEV_IO_TRACE=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
-# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -2301,14 +2366,13 @@ CONFIG_EARLY_PRINTK=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 # CONFIG_X86_PTDUMP is not set
 CONFIG_DEBUG_RODATA=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 # CONFIG_IOMMU_DEBUG is not set
-# CONFIG_MMIOTRACE is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
 CONFIG_IO_DELAY_TYPE_0X80=0
 CONFIG_IO_DELAY_TYPE_0XED=1
 CONFIG_IO_DELAY_TYPE_UDELAY=2
@@ -2344,6 +2408,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
 CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
 # CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
 # CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_IMA is not set
 CONFIG_CRYPTO=y
 
 #
@@ -2359,10 +2425,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
 CONFIG_CRYPTO_HASH=y
 CONFIG_CRYPTO_HASH2=y
 CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_MANAGER2=y
 # CONFIG_CRYPTO_GF128MUL is not set
 # CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=y
 # CONFIG_CRYPTO_TEST is not set
@@ -2414,6 +2482,7 @@ CONFIG_CRYPTO_SHA1=y
 #
 CONFIG_CRYPTO_AES=y
 # CONFIG_CRYPTO_AES_X86_64 is not set
+# CONFIG_CRYPTO_AES_NI_INTEL is not set
 # CONFIG_CRYPTO_ANUBIS is not set
 CONFIG_CRYPTO_ARC4=y
 # CONFIG_CRYPTO_BLOWFISH is not set
@@ -2435,6 +2504,7 @@ CONFIG_CRYPTO_DES=y
 # Compression
 #
 # CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
 
 #
@@ -2444,10 +2514,12 @@ CONFIG_CRYPTO_DES=y
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
 CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
 CONFIG_VIRTUALIZATION=y
 # CONFIG_KVM is not set
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
@@ -2464,7 +2536,10 @@ CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
-CONFIG_PLIST=y
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
+CONFIG_NLATTR=y
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index f6aa18eadf7..1a37bcdc860 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/stddef.h>
+#include <linux/stringify.h>
 #include <asm/asm.h>
 
 /*
@@ -74,6 +75,22 @@ static inline void alternatives_smp_switch(int smp) {}
 
 const unsigned char *const *find_nop_table(void);
 
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+									\
+      "661:\n\t" oldinstr "\n662:\n"					\
+      ".section .altinstructions,\"a\"\n"				\
+      _ASM_ALIGN "\n"							\
+      _ASM_PTR "661b\n"				/* label           */	\
+      _ASM_PTR "663f\n"				/* new instruction */	\
+      "	 .byte " __stringify(feature) "\n"	/* feature bit     */	\
+      "	 .byte 662b-661b\n"			/* sourcelen       */	\
+      "	 .byte 664f-663f\n"			/* replacementlen  */	\
+      ".previous\n"							\
+      ".section .altinstr_replacement, \"ax\"\n"			\
+      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
+      ".previous"
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *
@@ -87,18 +104,7 @@ const unsigned char *const *find_nop_table(void);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, newinstr, feature)			\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature) : "memory")
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
 
 /*
  * Alternative inline assembly with input.
@@ -109,35 +115,16 @@ const unsigned char *const *find_nop_table(void);
  * Best is to use constraints that are fixed size (like (%1) ... "r")
  * If you use variable sized constraints like "m" or "g" in the
  * replacement make sure to pad to the worst case length.
+ * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: : "i" (0), ## input)
 
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, feature, output, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c[feat]\n"	/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */ \
-		      ".previous" : output : [feat] "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: output : "i" (0), ## input)
 
 /*
  * use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index f712344329b..262e0282004 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -27,6 +27,8 @@ extern int amd_iommu_init(void);
 extern int amd_iommu_init_dma_ops(void);
 extern void amd_iommu_detect(void);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_flush_all_domains(void);
+extern void amd_iommu_flush_all_devices(void);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 95c8cd9d22b..0c878caaa0a 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -194,6 +194,27 @@
 #define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
 #define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
 					      domain for an IOMMU */
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)					\
+	do {								\
+		if (amd_iommu_dump)						\
+			printk(KERN_INFO "AMD IOMMU: " format, ## arg);	\
+	} while(0);
+
+/*
+ * Make iterating over all IOMMUs easier
+ */
+#define for_each_iommu(iommu) \
+	list_for_each_entry((iommu), &amd_iommu_list, list)
+#define for_each_iommu_safe(iommu, next) \
+	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+
+#define APERTURE_RANGE_SHIFT	27	/* 128 MB */
+#define APERTURE_RANGE_SIZE	(1ULL << APERTURE_RANGE_SHIFT)
+#define APERTURE_RANGE_PAGES	(APERTURE_RANGE_SIZE >> PAGE_SHIFT)
+#define APERTURE_MAX_RANGES	32	/* allows 4GB of DMA address space */
+#define APERTURE_RANGE_INDEX(a)	((a) >> APERTURE_RANGE_SHIFT)
+#define APERTURE_PAGE_INDEX(a)	(((a) >> 21) & 0x3fULL)
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -210,6 +231,26 @@ struct protection_domain {
 };
 
 /*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 *pte_pages[64];
+
+	unsigned long offset;
+};
+
+/*
  * Data container for a dma_ops specific protection domain
  */
 struct dma_ops_domain {
@@ -222,18 +263,10 @@ struct dma_ops_domain {
 	unsigned long aperture_size;
 
 	/* address we start to search for free addresses */
-	unsigned long next_bit;
-
-	/* address allocation bitmap */
-	unsigned long *bitmap;
+	unsigned long next_address;
 
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 **pte_pages;
+	/* address space relevant data */
+	struct aperture_range *aperture[APERTURE_MAX_RANGES];
 
 	/* This will be set to true when TLB needs to be flushed */
 	bool need_flush;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 42f2f837742..bb7d4792584 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -107,8 +107,7 @@ extern u32 native_safe_apic_wait_icr_idle(void);
 extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
-#define EIM_8BIT_APIC_ID	0
-#define EIM_32BIT_APIC_ID	1
+extern int x2apic_mode;
 
 #ifdef CONFIG_X86_X2APIC
 /*
@@ -166,10 +165,9 @@ static inline u64 native_x2apic_icr_read(void)
 	return val;
 }
 
-extern int x2apic, x2apic_phys;
+extern int x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void enable_IR_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
@@ -183,6 +181,8 @@ static inline int x2apic_enabled(void)
 		return 1;
 	return 0;
 }
+
+#define x2apic_supported()	(cpu_has_x2apic)
 #else
 static inline void check_x2apic(void)
 {
@@ -190,28 +190,20 @@ static inline void check_x2apic(void)
 static inline void enable_x2apic(void)
 {
 }
-static inline void enable_IR_x2apic(void)
-{
-}
 static inline int x2apic_enabled(void)
 {
 	return 0;
 }
 
-#define	x2apic	0
-
+#define	x2apic_preenabled 0
+#define	x2apic_supported()	0
 #endif
 
-extern int get_physical_broadcast(void);
+extern void enable_IR_x2apic(void);
 
-#ifdef CONFIG_X86_X2APIC
-static inline void ack_x2APIC_irq(void)
-{
-	/* Docs say use 0 for future compatibility */
-	native_apic_msr_write(APIC_EOI, 0);
-}
-#endif
+extern int get_physical_broadcast(void);
 
+extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -252,7 +244,7 @@ static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-
+static inline void apic_disable(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_64
@@ -410,7 +402,7 @@ static inline unsigned default_get_apic_id(unsigned long x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
 
-	if (APIC_XAPIC(ver))
+	if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
 		return (x >> 24) & 0xFF;
 	else
 		return (x >> 24) & 0x0F;
@@ -478,6 +470,9 @@ static inline unsigned int read_apic_id(void)
 extern void default_setup_apic_routing(void);
 
 #ifdef CONFIG_X86_32
+
+extern struct apic apic_default;
+
 /*
  * Set up the logical destination ID.
  *
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index bc9514fb3b1..7ddb36ab933 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -22,6 +22,7 @@
 #  define	APIC_INTEGRATED(x)	(1)
 #endif
 #define		APIC_XAPIC(x)		((x) >= 0x14)
+#define		APIC_EXT_SPACE(x)	((x) & 0x80000000)
 #define	APIC_TASKPRI	0x80
 #define		APIC_TPRI_MASK		0xFFu
 #define	APIC_ARBPRI	0x90
@@ -116,7 +117,9 @@
 #define		APIC_TDR_DIV_32		0x8
 #define		APIC_TDR_DIV_64		0x9
 #define		APIC_TDR_DIV_128	0xA
-#define	APIC_EILVT0     0x500
+#define	APIC_EFEAT	0x400
+#define	APIC_ECTRL	0x410
+#define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
@@ -125,9 +128,6 @@
 #define		APIC_EILVT_MSG_NMI	0x4
 #define		APIC_EILVT_MSG_EXT	0x7
 #define		APIC_EILVT_MASKED	(1 << 16)
-#define	APIC_EILVT1     0x510
-#define	APIC_EILVT2     0x520
-#define	APIC_EILVT3     0x530
 
 #define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
 #define APIC_BASE_MSR	0x800
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 6ba23dd9fc9..418e632d4a8 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,11 +8,26 @@
 
 #ifdef __KERNEL__
 
+#include <asm/page_types.h>
+
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
 				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
+/* Minimum kernel alignment, as a power of two */
+#ifdef CONFIG_x86_64
+#define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
+#else
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT+1)
+#endif
+#define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
+
+#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
+	(CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2))
+#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
+#endif
+
 #ifdef CONFIG_KERNEL_BZIP2
 #define BOOT_HEAP_SIZE             0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 433adaebf9b..1724e8de317 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -50,7 +50,8 @@ struct setup_header {
 	__u32	ramdisk_size;
 	__u32	bootsect_kludge;
 	__u16	heap_end_ptr;
-	__u16	_pad1;
+	__u8	ext_loader_ver;
+	__u8	ext_loader_type;
 	__u32	cmd_line_ptr;
 	__u32	initrd_addr_max;
 	__u32	kernel_alignment;
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
index 222802029fa..d96c1ee3a95 100644
--- a/arch/x86/include/asm/cpu_debug.h
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -86,105 +86,7 @@ enum cpu_file_bit {
 	CPU_VALUE_BIT,				/* value		*/
 };
 
-#define	CPU_FILE_VALUE			(1 << CPU_VALUE_BIT)
-
-/*
- * DisplayFamily_DisplayModel	Processor Families/Processor Number Series
- * --------------------------	------------------------------------------
- * 05_01, 05_02, 05_04		Pentium, Pentium with MMX
- *
- * 06_01			Pentium Pro
- * 06_03, 06_05			Pentium II Xeon, Pentium II
- * 06_07, 06_08, 06_0A, 06_0B	Pentium III Xeon, Pentum III
- *
- * 06_09, 060D			Pentium M
- *
- * 06_0E			Core Duo, Core Solo
- *
- * 06_0F			Xeon 3000, 3200, 5100, 5300, 7300 series,
- *				Core 2 Quad, Core 2 Extreme, Core 2 Duo,
- *				Pentium dual-core
- * 06_17			Xeon 5200, 5400 series, Core 2 Quad Q9650
- *
- * 06_1C			Atom
- *
- * 0F_00, 0F_01, 0F_02		Xeon, Xeon MP, Pentium 4
- * 0F_03, 0F_04			Xeon, Xeon MP, Pentium 4, Pentium D
- *
- * 0F_06			Xeon 7100, 5000 Series, Xeon MP,
- *				Pentium 4, Pentium D
- */
-
-/* Register processors bits */
-enum cpu_processor_bit {
-	CPU_NONE,
-/* Intel */
-	CPU_INTEL_PENTIUM_BIT,
-	CPU_INTEL_P6_BIT,
-	CPU_INTEL_PENTIUM_M_BIT,
-	CPU_INTEL_CORE_BIT,
-	CPU_INTEL_CORE2_BIT,
-	CPU_INTEL_ATOM_BIT,
-	CPU_INTEL_XEON_P4_BIT,
-	CPU_INTEL_XEON_MP_BIT,
-/* AMD */
-	CPU_AMD_K6_BIT,
-	CPU_AMD_K7_BIT,
-	CPU_AMD_K8_BIT,
-	CPU_AMD_0F_BIT,
-	CPU_AMD_10_BIT,
-	CPU_AMD_11_BIT,
-};
-
-#define	CPU_INTEL_PENTIUM	(1 << CPU_INTEL_PENTIUM_BIT)
-#define	CPU_INTEL_P6		(1 << CPU_INTEL_P6_BIT)
-#define	CPU_INTEL_PENTIUM_M	(1 << CPU_INTEL_PENTIUM_M_BIT)
-#define	CPU_INTEL_CORE		(1 << CPU_INTEL_CORE_BIT)
-#define	CPU_INTEL_CORE2		(1 << CPU_INTEL_CORE2_BIT)
-#define	CPU_INTEL_ATOM		(1 << CPU_INTEL_ATOM_BIT)
-#define	CPU_INTEL_XEON_P4	(1 << CPU_INTEL_XEON_P4_BIT)
-#define	CPU_INTEL_XEON_MP	(1 << CPU_INTEL_XEON_MP_BIT)
-
-#define	CPU_INTEL_PX		(CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
-#define	CPU_INTEL_COREX		(CPU_INTEL_CORE | CPU_INTEL_CORE2)
-#define	CPU_INTEL_XEON		(CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
-#define	CPU_CO_AT		(CPU_INTEL_CORE | CPU_INTEL_ATOM)
-#define	CPU_C2_AT		(CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
-#define	CPU_CX_AT		(CPU_INTEL_COREX | CPU_INTEL_ATOM)
-#define	CPU_CX_XE		(CPU_INTEL_COREX | CPU_INTEL_XEON)
-#define	CPU_P6_XE		(CPU_INTEL_P6 | CPU_INTEL_XEON)
-#define	CPU_PM_CO_AT		(CPU_INTEL_PENTIUM_M | CPU_CO_AT)
-#define	CPU_C2_AT_XE		(CPU_C2_AT | CPU_INTEL_XEON)
-#define	CPU_CX_AT_XE		(CPU_CX_AT | CPU_INTEL_XEON)
-#define	CPU_P6_CX_AT		(CPU_INTEL_P6 | CPU_CX_AT)
-#define	CPU_P6_CX_XE		(CPU_P6_XE | CPU_INTEL_COREX)
-#define	CPU_P6_CX_AT_XE		(CPU_INTEL_P6 | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT		(CPU_INTEL_PENTIUM_M | CPU_CX_AT)
-#define	CPU_PM_CX_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_XE)
-#define	CPU_PX_CX_AT		(CPU_INTEL_PX | CPU_CX_AT)
-#define	CPU_PX_CX_AT_XE		(CPU_INTEL_PX | CPU_CX_AT_XE)
-
-/* Select all supported Intel CPUs */
-#define	CPU_INTEL_ALL		(CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
-
-#define	CPU_AMD_K6		(1 << CPU_AMD_K6_BIT)
-#define	CPU_AMD_K7		(1 << CPU_AMD_K7_BIT)
-#define	CPU_AMD_K8		(1 << CPU_AMD_K8_BIT)
-#define	CPU_AMD_0F		(1 << CPU_AMD_0F_BIT)
-#define	CPU_AMD_10		(1 << CPU_AMD_10_BIT)
-#define	CPU_AMD_11		(1 << CPU_AMD_11_BIT)
-
-#define	CPU_K10_PLUS		(CPU_AMD_10 | CPU_AMD_11)
-#define	CPU_K0F_PLUS		(CPU_AMD_0F | CPU_K10_PLUS)
-#define	CPU_K8_PLUS		(CPU_AMD_K8 | CPU_K0F_PLUS)
-#define	CPU_K7_PLUS		(CPU_AMD_K7 | CPU_K8_PLUS)
-
-/* Select all supported AMD CPUs */
-#define	CPU_AMD_ALL		(CPU_AMD_K6 | CPU_K7_PLUS)
-
-/* Select all supported CPUs */
-#define	CPU_ALL			(CPU_INTEL_ALL | CPU_AMD_ALL)
+#define	CPU_FILE_VALUE		(1 << CPU_VALUE_BIT)
 
 #define MAX_CPU_FILES		512
 
@@ -220,7 +122,6 @@ struct cpu_debug_range {
 	unsigned		min;		/* Register range min	*/
 	unsigned		max;		/* Register range max	*/
 	unsigned		flag;		/* Supported flags	*/
-	unsigned		model;		/* Supported models	*/
 };
 
 #endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bb83b1c397a..19af42138f7 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,7 +22,7 @@
 #define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
 #define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
 #define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Exception */
 #define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
 #define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
 #define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
@@ -94,6 +94,7 @@
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -192,11 +193,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
 	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
+	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index a8f672ba100..70dac199b09 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 #ifndef _ASM_X86_DS_H
@@ -83,8 +83,10 @@ enum ds_feature {
  * The interrupt threshold is independent from the overflow callback
  * to allow users to use their own overflow interrupt handling mechanism.
  *
- * task: the task to request recording for;
- *       NULL for per-cpu recording on the current cpu
+ * The function might sleep.
+ *
+ * task: the task to request recording for
+ * cpu:  the cpu to request recording for
  * base: the base pointer for the (non-pageable) buffer;
  * size: the size of the provided buffer in bytes
  * ovfl: pointer to a function to be called on buffer overflow;
@@ -93,19 +95,28 @@ enum ds_feature {
  *     -1 if no interrupt threshold is requested.
  * flags: a bit-mask of the above flags
  */
-extern struct bts_tracer *ds_request_bts(struct task_struct *task,
-					 void *base, size_t size,
-					 bts_ovfl_callback_t ovfl,
-					 size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs(struct task_struct *task,
-					   void *base, size_t size,
-					   pebs_ovfl_callback_t ovfl,
-					   size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+					      void *base, size_t size,
+					      bts_ovfl_callback_t ovfl,
+					      size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+					     bts_ovfl_callback_t ovfl,
+					     size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+						void *base, size_t size,
+						pebs_ovfl_callback_t ovfl,
+						size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
+					       void *base, size_t size,
+					       pebs_ovfl_callback_t ovfl,
+					       size_t th, unsigned int flags);
 
 /*
  * Release BTS or PEBS resources
  * Suspend and resume BTS or PEBS tracing
  *
+ * Must be called with irq's enabled.
+ *
  * tracer: the tracer handle returned from ds_request_~()
  */
 extern void ds_release_bts(struct bts_tracer *tracer);
@@ -115,6 +126,28 @@ extern void ds_release_pebs(struct pebs_tracer *tracer);
 extern void ds_suspend_pebs(struct pebs_tracer *tracer);
 extern void ds_resume_pebs(struct pebs_tracer *tracer);
 
+/*
+ * Release BTS or PEBS resources
+ * Suspend and resume BTS or PEBS tracing
+ *
+ * Cpu tracers must call this on the traced cpu.
+ * Task tracers must call ds_release_~_noirq() for themselves.
+ *
+ * May be called with irq's disabled.
+ *
+ * Returns 0 if successful;
+ * -EPERM if the cpu tracer does not trace the current cpu.
+ * -EPERM if the task tracer does not trace itself.
+ *
+ * tracer: the tracer handle returned from ds_request_~()
+ */
+extern int ds_release_bts_noirq(struct bts_tracer *tracer);
+extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
+extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
+extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
+
 
 /*
  * The raw DS buffer state as it is used for BTS and PEBS recording.
@@ -170,9 +203,9 @@ struct bts_struct {
 		} lbr;
 		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
 		struct {
-			__u64 jiffies;
+			__u64 clock;
 			pid_t pid;
-		} timestamp;
+		} event;
 	} variant;
 };
 
@@ -201,8 +234,12 @@ struct bts_trace {
 struct pebs_trace {
 	struct ds_trace ds;
 
-	/* the PEBS reset value */
-	unsigned long long reset_value;
+	/* the number of valid counters in the below array */
+	unsigned int counters;
+
+#define MAX_PEBS_COUNTERS 4
+	/* the counter reset value */
+	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
 };
 
 
@@ -237,9 +274,11 @@ extern int ds_reset_pebs(struct pebs_tracer *tracer);
  * Returns 0 on success; -Eerrno on error
  *
  * tracer: the tracer handle returned from ds_request_pebs()
+ * counter: the index of the counter
  * value: the new counter reset value
  */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value);
+extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
+			     unsigned int counter, u64 value);
 
 /*
  * Initialization
@@ -252,21 +291,12 @@ extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
  */
 extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
 
-/*
- * Task clone/init and cleanup work
- */
-extern void ds_copy_thread(struct task_struct *tsk, struct task_struct *father);
-extern void ds_exit_thread(struct task_struct *tsk);
-
 #else /* CONFIG_X86_DS */
 
 struct cpuinfo_x86;
 static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
 static inline void ds_switch_to(struct task_struct *prev,
 				struct task_struct *next) {}
-static inline void ds_copy_thread(struct task_struct *tsk,
-				  struct task_struct *father) {}
-static inline void ds_exit_thread(struct task_struct *tsk) {}
 
 #endif /* CONFIG_X86_DS */
 #endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 4b4921d7a28..6df45f63966 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -65,7 +65,26 @@ extern unsigned long io_apic_irqs;
 extern void init_VISWS_APIC_irqs(void);
 extern void setup_IO_APIC(void);
 extern void disable_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+
+struct io_apic_irq_attr {
+	int ioapic;
+	int ioapic_pin;
+	int trigger;
+	int polarity;
+};
+
+static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
+					int ioapic, int ioapic_pin,
+					int trigger, int polarity)
+{
+	irq_attr->ioapic     = ioapic;
+	irq_attr->ioapic_pin = ioapic_pin;
+	irq_attr->trigger    = trigger;
+	irq_attr->polarity   = polarity;
+}
+
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin,
+					struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
 extern void enable_IO_APIC(void);
@@ -80,7 +99,11 @@ extern void eisa_set_level_irq(unsigned int irq);
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_generic_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_IO_APIC
+extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
+#endif
 #ifdef CONFIG_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 71c9e518398..175adf58dd4 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -67,7 +67,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
-#if 0 /* See comment in __save_init_fpu() below. */
+#if 0 /* See comment in fxsave() below. */
 		     : [fx] "r" (fx), "m" (*fx), "0" (0));
 #else
 		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
@@ -75,14 +75,6 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 	return err;
 }
 
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE)
-		return xrstor_checking(&tsk->thread.xstate->xsave);
-	else
-		return fxrstor_checking(&tsk->thread.xstate->fxsave);
-}
-
 /* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
    is pending. Clear the x87 state here by setting it to fixed
    values. The kernel data segment can be sometimes 0 and sometimes
@@ -120,7 +112,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in __fxsave_clear() below. */
+#if 0 /* See comment in fxsave() below. */
 		     : [fx] "r" (fx), "0" (0));
 #else
 		     : [fx] "cdaSDb" (fx), "0" (0));
@@ -185,12 +177,9 @@ static inline void tolerant_fwait(void)
 	asm volatile("fnclex ; fwait");
 }
 
-static inline void restore_fpu(struct task_struct *tsk)
+/* perform fxrstor iff the processor has extended states, otherwise frstor */
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
-	if (task_thread_info(tsk)->status & TS_XSAVE) {
-		xrstor_checking(&tsk->thread.xstate->xsave);
-		return;
-	}
 	/*
 	 * The "nop" is needed to make the instructions the same
 	 * length.
@@ -199,7 +188,9 @@ static inline void restore_fpu(struct task_struct *tsk)
 		"nop ; frstor %1",
 		"fxrstor %1",
 		X86_FEATURE_FXSR,
-		"m" (tsk->thread.xstate->fxsave));
+		"m" (*fx));
+
+	return 0;
 }
 
 /* We need a safe address that is cheap to find and that is already
@@ -262,6 +253,14 @@ end:
 
 #endif	/* CONFIG_X86_64 */
 
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		return xrstor_checking(&tsk->thread.xstate->xsave);
+	else
+		return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
+
 /*
  * Signal frame handlers...
  */
@@ -305,18 +304,18 @@ static inline void kernel_fpu_end(void)
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context aswell. To prevent these kernel instructions
- * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
  * should use them only in the context of irq_ts_save/restore()
  */
 static inline int irq_ts_save(void)
 {
 	/*
-	 * If we are in process context, we are ok to take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context require pre-emption to
-	 * be disabled or some heavy lifting like kernel_fpu_begin()
+	 * If in process context and not atomic, we can take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context requires disabling preemption
+	 * or some heavy lifting like kernel_fpu_begin()
 	 */
-	if (!in_interrupt())
+	if (!in_atomic())
 		return 0;
 
 	if (read_cr0() & X86_CR0_TS) {
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1a99e6c092a..58d7091eeb1 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -60,8 +60,4 @@ extern struct irq_chip i8259A_chip;
 extern void mask_8259A(void);
 extern void unmask_8259A(void);
 
-#ifdef CONFIG_X86_32
-extern void init_ISA_irqs(void);
-#endif
-
 #endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9d826e43601..daf866ed061 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -154,22 +154,19 @@ extern int timer_through_8259;
 extern int io_apic_get_unique_id(int ioapic, int apic_id);
 extern int io_apic_get_version(int ioapic);
 extern int io_apic_get_redir_entries(int ioapic);
-extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
-				   int edge_level, int active_high_low);
 #endif /* CONFIG_ACPI */
 
+struct io_apic_irq_attr;
+extern int io_apic_set_pci_routing(struct device *dev, int irq,
+		 struct io_apic_irq_attr *irq_attr);
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
-#ifdef CONFIG_X86_64
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
 extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
-extern void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries);
-#endif
 
 extern void probe_nr_irqs_gsi(void);
 
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 86af26091d6..0e9fe1d9d97 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -1,3 +1,6 @@
+#ifndef _ASM_X86_IOMAP_H
+#define _ASM_X86_IOMAP_H
+
 /*
  * Copyright © 2008 Ingo Molnar
  *
@@ -31,3 +34,5 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
 
 void
 iounmap_atomic(void *kvaddr, enum km_type type);
+
+#endif /* _ASM_X86_IOMAP_H */
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 0396760fccb..f275e224450 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -1,6 +1,6 @@
 #ifndef _ASM_X86_IRQ_REMAPPING_H
 #define _ASM_X86_IRQ_REMAPPING_H
 
-#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 4492e19f839..e997be98c9b 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -34,6 +34,7 @@
 
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
+# define IA32_SYSCALL_VECTOR		0x80
 #else
 # define IA32_SYSCALL_VECTOR		0x80
 #endif
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
index 54c8cc53b24..c2d1f3b58e5 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/k8.h
@@ -12,4 +12,17 @@ extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_scan_nodes(unsigned long start, unsigned long end);
 
+#ifdef CONFIG_K8_NB
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+	return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+}
+#else
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+	return NULL;
+}
+#endif
+
+
 #endif /* _ASM_X86_K8_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index c882664716c..ef51b501e22 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -9,20 +9,31 @@ struct cpu_signature {
 
 struct device;
 
+enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+
 struct microcode_ops {
-	int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
-	int  (*request_microcode_fw) (int cpu, struct device *device);
+	enum ucode_state (*request_microcode_user) (int cpu,
+				const void __user *buf, size_t size);
 
-	void (*apply_microcode) (int cpu);
+	enum ucode_state (*request_microcode_fw) (int cpu,
+				struct device *device);
 
-	int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 	void (*microcode_fini_cpu) (int cpu);
+
+	/*
+	 * The generic 'microcode_core' part guarantees that
+	 * the callbacks below run on a target cpu when they
+	 * are being called.
+	 * See also the "Synchronization" section in microcode_core.c.
+	 */
+	int (*apply_microcode) (int cpu);
+	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
 struct ucode_cpu_info {
-	struct cpu_signature cpu_sig;
-	int valid;
-	void *mc;
+	struct cpu_signature	cpu_sig;
+	int			valid;
+	void			*mc;
 };
 extern struct ucode_cpu_info ucode_cpu_info[];
 
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 642fc7fc8cd..e2a1bb6d71e 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -61,9 +61,11 @@ extern void get_smp_config(void);
 #ifdef CONFIG_X86_MPPARSE
 extern void find_smp_config(void);
 extern void early_reserve_e820_mpc_new(void);
+extern int enable_update_mptable;
 #else
 static inline void find_smp_config(void) { }
 static inline void early_reserve_e820_mpc_new(void) { }
+#define enable_update_mptable 0
 #endif
 
 void __cpuinit generic_processor_info(int apicid, int version);
@@ -72,20 +74,13 @@ extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
 extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
-extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+struct device;
+extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
+				 int active_high_low);
 extern int acpi_probe_gsi(void);
 #ifdef CONFIG_X86_IO_APIC
-extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-				u32 gsi, int triggering, int polarity);
 extern int mp_find_ioapic(int gsi);
 extern int mp_find_ioapic_pin(int ioapic, int gsi);
-#else
-static inline int
-mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-		   u32 gsi, int triggering, int polarity)
-{
-	return 0;
-}
 #endif
 #else /* !CONFIG_ACPI: */
 static inline int acpi_probe_gsi(void)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ec41fc16c16..4d58d04fca8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -121,7 +121,6 @@
 #define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K8_TOP_MEM2			0xc001001d
 #define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_HWCR			0xc0010015
 #define MSR_K8_INT_PENDING_MSG		0xc0010055
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c45a0a568df..c9726440993 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -64,7 +64,7 @@ static inline int nmi_watchdog_active(void)
 	 * but since they are power of two we could use a
 	 * cheaper way --cvg
 	 */
-	return nmi_watchdog & 0x3;
+	return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
 }
 #endif
 
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 064ed6df4cb..c4ae822e415 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -17,9 +17,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern void srat_reserve_add_area(int nodeid);
-extern int hotadd_percent;
-
 extern s16 apicid_to_node[MAX_LOCAL_APIC];
 
 extern unsigned long numa_free_all_bootmem(void);
@@ -27,6 +24,13 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
 
 #ifdef CONFIG_NUMA
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 0f915ae649a..6f1b7331313 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -54,10 +54,6 @@ extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
 extern void find_low_pfn_range(void);
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-extern void initmem_init(unsigned long, unsigned long);
-extern void free_initmem(void);
 extern void setup_bootmem_allocator(void);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index d38c91b7024..8d382d3abf3 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -32,22 +32,14 @@
  */
 #define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
-#define __PHYSICAL_START	CONFIG_PHYSICAL_START
-#define __KERNEL_ALIGN		0x200000
-
-/*
- * Make sure kernel is aligned to 2MB address. Catching it at compile
- * time is better. Change your config file and compile the kernel
- * for a 2MB aligned address (CONFIG_PHYSICAL_START)
- */
-#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
-#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
-#endif
+#define __PHYSICAL_START	((CONFIG_PHYSICAL_START +	 	\
+				  (CONFIG_PHYSICAL_ALIGN - 1)) &	\
+				 ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 #define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
-/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define __PHYSICAL_MASK_SHIFT	46
 #define __VIRTUAL_MASK_SHIFT	48
 
@@ -71,12 +63,6 @@ extern unsigned long __phys_addr(unsigned long);
 
 #define vmemmap ((struct page *)VMEMMAP_START)
 
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
-extern void free_initmem(void);
-
 extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 826ad37006a..6473f5ccff8 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -46,6 +46,12 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
+extern unsigned long init_memory_mapping(unsigned long start,
+					 unsigned long end);
+
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif	/* _ASM_X86_PAGE_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a53da004e08..4fb37c8a083 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -56,6 +56,7 @@ struct desc_ptr;
 struct tss_struct;
 struct mm_struct;
 struct desc_struct;
+struct task_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -203,7 +204,8 @@ struct pv_cpu_ops {
 
 	void (*swapgs)(void);
 
-	struct pv_lazy_ops lazy_mode;
+	void (*start_context_switch)(struct task_struct *prev);
+	void (*end_context_switch)(struct task_struct *next);
 };
 
 struct pv_irq_ops {
@@ -1399,25 +1401,23 @@ enum paravirt_lazy_mode {
 };
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
 
-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define  __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+	PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
 }
 
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+	PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
 }
 
-void arch_flush_lazy_cpu_mode(void);
-
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 29d96d168bc..18ef7ebf263 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -81,6 +81,8 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 #define pte_val(x)	native_pte_val(x)
 #define __pte(x)	native_make_pte(x)
 
+#define arch_end_context_switch(prev)	do {} while(0)
+
 #endif	/* CONFIG_PARAVIRT */
 
 /*
@@ -503,6 +505,8 @@ static inline int pgd_none(pgd_t pgd)
 
 #ifndef __ASSEMBLY__
 
+extern int direct_gbpages;
+
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 6b87bc6d501..abde308fdb0 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -25,10 +25,6 @@ extern pgd_t init_level4_pgt[];
 
 extern void paging_init(void);
 
-#endif /* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
-
 #define pte_ERROR(e)					\
 	printk("%s:%d: bad pte %p(%016lx).\n",		\
 	       __FILE__, __LINE__, &(e), pte_val(e))
@@ -135,8 +131,6 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 #define update_mmu_cache(vma, address, pte) do { } while (0)
 
-extern int direct_gbpages;
-
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index fbf42b8e038..766ea16fbbb 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -51,11 +51,11 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define MAXMEM		 _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
-#define VMALLOC_START    _AC(0xffffc20000000000, UL)
-#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
-#define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
+#define VMALLOC_START    _AC(0xffffc90000000000, UL)
+#define VMALLOC_END      _AC(0xffffe8ffffffffff, UL)
+#define VMEMMAP_START	 _AC(0xffffea0000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b8238dc8786..4d258ad76a0 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,7 +273,6 @@ typedef struct page *pgtable_t;
 
 extern pteval_t __supported_pte_mask;
 extern int nx_enabled;
-extern void set_nx(void);
 
 #define pgprot_writecombine	pgprot_writecombine
 extern pgprot_t pgprot_writecombine(pgprot_t prot);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c2cceae709c..c7768269b1c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -135,7 +135,8 @@ extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
 extern struct tss_struct	doublefault_tss;
-extern __u32			cleared_cpu_caps[NCAPINTS];
+extern __u32			cpu_caps_cleared[NCAPINTS];
+extern __u32			cpu_caps_set[NCAPINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
@@ -409,9 +410,6 @@ DECLARE_PER_CPU(unsigned long, stack_canary);
 extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
 
 struct thread_struct {
 	/* Cached TLS descriptors: */
@@ -427,8 +425,12 @@ struct thread_struct {
 	unsigned short		fsindex;
 	unsigned short		gsindex;
 #endif
+#ifdef CONFIG_X86_32
 	unsigned long		ip;
+#endif
+#ifdef CONFIG_X86_64
 	unsigned long		fs;
+#endif
 	unsigned long		gs;
 	/* Hardware debugging registers: */
 	unsigned long		debugreg0;
@@ -460,14 +462,8 @@ struct thread_struct {
 	unsigned		io_bitmap_max;
 /* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
 	unsigned long	debugctlmsr;
-#ifdef CONFIG_X86_DS
-/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+	/* Debug Store context; see asm/ds.h */
 	struct ds_context	*ds_ctx;
-#endif /* CONFIG_X86_DS */
-#ifdef CONFIG_X86_PTRACE_BTS
-/* the signal to send on a bts buffer overflow */
-	unsigned int	bts_ovfl_signal;
-#endif /* CONFIG_X86_PTRACE_BTS */
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -795,6 +791,21 @@ static inline unsigned long get_debugctlmsr(void)
     return debugctlmsr;
 }
 
+static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
+{
+	u64 debugctlmsr = 0;
+	u32 val1, val2;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return 0;
+#endif
+	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
+	debugctlmsr = val1 | ((u64)val2 << 32);
+
+	return debugctlmsr;
+}
+
 static inline void update_debugctlmsr(unsigned long debugctlmsr)
 {
 #ifndef CONFIG_X86_DEBUGCTLMSR
@@ -804,6 +815,18 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
+static inline void update_debugctlmsr_on_cpu(int cpu,
+					     unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return;
+#endif
+	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
+		     (u32)((u64)debugctlmsr),
+		     (u32)((u64)debugctlmsr >> 32));
+}
+
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:
@@ -814,6 +837,7 @@ extern unsigned int		BIOS_revision;
 
 /* Boot loader type from the setup header: */
 extern int			bootloader_type;
+extern int			bootloader_version;
 
 extern char			ignore_fpu_irq;
 
@@ -874,7 +898,6 @@ static inline void spin_lock_prefetch(const void *x)
 	.vm86_info		= NULL,					  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
-	.fs			= __KERNEL_PERCPU,			  \
 }
 
 /*
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 624f133943e..0f0d908349a 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -236,12 +236,11 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-extern void x86_ptrace_untrace(struct task_struct *);
-extern void x86_ptrace_fork(struct task_struct *child,
-			    unsigned long clone_flags);
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void ptrace_bts_untrace(struct task_struct *tsk);
 
-#define arch_ptrace_untrace(tsk) x86_ptrace_untrace(tsk)
-#define arch_ptrace_fork(child, flags) x86_ptrace_fork(child, flags)
+#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index a4737dddfd5..64cf2d24fad 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -48,9 +48,15 @@
 #endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE	0
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE	0
+#else
+#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
 #define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
 #define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index bdc2ada05ae..4093d1ed6db 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -33,7 +33,6 @@ struct x86_quirks {
 	int (*setup_ioapic_ids)(void);
 };
 
-extern void x86_quirk_pre_intr_init(void);
 extern void x86_quirk_intr_init(void);
 
 extern void x86_quirk_trap_init(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19e0d88b966..6a84ed166ae 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -180,7 +180,7 @@ extern int safe_smp_processor_id(void);
 static inline int logical_smp_processor_id(void)
 {
 	/* we don't want to mark this access volatile - bad code generation */
-	return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
+	return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
 }
 
 #endif
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index e3cc3c063ec..4517d6b9318 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,7 +27,7 @@
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	44 /* Can be max 45 bits */
+# define MAX_PHYSMEM_BITS	46
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 7043408f690..372b76edd63 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -1,7 +1,7 @@
 /*
  * syscalls.h - Linux syscall interfaces (arch-specific)
  *
- * Copyright (c) 2008 Jaswinder Singh
+ * Copyright (c) 2008 Jaswinder Singh Rajput
  *
  * This file is released under the GPLv2.
  * See the file COPYING for more details.
@@ -12,50 +12,55 @@
 
 #include <linux/compiler.h>
 #include <linux/linkage.h>
-#include <linux/types.h>
 #include <linux/signal.h>
+#include <linux/types.h>
 
 /* Common in X86_32 and X86_64 */
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 
+/* kernel/process.c */
+int sys_fork(struct pt_regs *);
+int sys_vfork(struct pt_regs *);
+
 /* kernel/ldt.c */
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
+/* kernel/signal.c */
+long sys_rt_sigreturn(struct pt_regs *);
+
 /* kernel/tls.c */
 asmlinkage int sys_set_thread_area(struct user_desc __user *);
 asmlinkage int sys_get_thread_area(struct user_desc __user *);
 
 /* X86_32 only */
 #ifdef CONFIG_X86_32
+/* kernel/ioport.c */
+long sys_iopl(struct pt_regs *);
+
 /* kernel/process_32.c */
-int sys_fork(struct pt_regs *);
 int sys_clone(struct pt_regs *);
-int sys_vfork(struct pt_regs *);
 int sys_execve(struct pt_regs *);
 
-/* kernel/signal_32.c */
+/* kernel/signal.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
 			     struct old_sigaction __user *);
 int sys_sigaltstack(struct pt_regs *);
 unsigned long sys_sigreturn(struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
-
-/* kernel/ioport.c */
-long sys_iopl(struct pt_regs *);
 
 /* kernel/sys_i386_32.c */
+struct mmap_arg_struct;
+struct sel_arg_struct;
+struct oldold_utsname;
+struct old_utsname;
+
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
 			  unsigned long, unsigned long, unsigned long);
-struct mmap_arg_struct;
 asmlinkage int old_mmap(struct mmap_arg_struct __user *);
-struct sel_arg_struct;
 asmlinkage int old_select(struct sel_arg_struct __user *);
 asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
-struct old_utsname;
 asmlinkage int sys_uname(struct old_utsname __user *);
-struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
 /* kernel/vm86_32.c */
@@ -65,29 +70,27 @@ int sys_vm86(struct pt_regs *);
 #else /* CONFIG_X86_32 */
 
 /* X86_64 only */
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
 /* kernel/process_64.c */
-asmlinkage long sys_fork(struct pt_regs *);
 asmlinkage long sys_clone(unsigned long, unsigned long,
 			  void __user *, void __user *,
 			  struct pt_regs *);
-asmlinkage long sys_vfork(struct pt_regs *);
 asmlinkage long sys_execve(char __user *, char __user * __user *,
 			   char __user * __user *,
 			   struct pt_regs *);
 long sys_arch_prctl(int, unsigned long);
 
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
-/* kernel/signal_64.c */
+/* kernel/signal.c */
 asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
 				struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
 
 /* kernel/sys_x86_64.c */
+struct new_utsname;
+
 asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
 			 unsigned long, unsigned long, unsigned long);
-struct new_utsname;
 asmlinkage long sys_uname(struct new_utsname __user *);
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8820a73ae09..602c769fc98 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -94,7 +94,8 @@ struct thread_info {
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
-#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
+#define TIF_SYSCALL_FTRACE	28	/* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +117,7 @@ struct thread_info {
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 16a5c84b032..a5ecc9c33e9 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -17,7 +17,7 @@
 
 static inline void __native_flush_tlb(void)
 {
-	write_cr3(read_cr3());
+	native_write_cr3(native_read_cr3());
 }
 
 static inline void __native_flush_tlb_global(void)
@@ -32,11 +32,11 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	cr4 = read_cr4();
+	cr4 = native_read_cr4();
 	/* clear PGE */
-	write_cr4(cr4 & ~X86_CR4_PGE);
+	native_write_cr4(cr4 & ~X86_CR4_PGE);
 	/* write old PGE again and flush TLBs */
-	write_cr4(cr4);
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f44b49abca4..066ef590d7e 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0d5342515b8..bfd74c032fc 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_TRAPS_H
 
 #include <asm/debugreg.h>
+#include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
 #ifdef CONFIG_X86_32
 #define dotraplinkage
@@ -13,6 +14,9 @@ asmlinkage void divide_error(void);
 asmlinkage void debug(void);
 asmlinkage void nmi(void);
 asmlinkage void int3(void);
+asmlinkage void xen_debug(void);
+asmlinkage void xen_int3(void);
+asmlinkage void xen_stack_segment(void);
 asmlinkage void overflow(void);
 asmlinkage void bounds(void);
 asmlinkage void invalid_op(void);
@@ -74,7 +78,6 @@ static inline int get_si_code(unsigned long condition)
 }
 
 extern int panic_on_unrecovered_nmi;
-extern int kstack_depth_to_print;
 
 void math_error(void __user *);
 void math_emulate(struct math_emu_info *);
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 9b0e61bf7a8..bddd44f2f0a 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -37,7 +37,7 @@
 #define UV_CPUS_PER_ACT_STATUS		32
 #define UV_ACT_STATUS_MASK		0x3
 #define UV_ACT_STATUS_SIZE		2
-#define UV_ACTIVATION_DESCRIPTOR_SIZE	32
+#define UV_ADP_SIZE			32
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
 #define UV_NET_ENDPOINT_INTD		0x38
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index d3a98ea1062..341070f7ad5 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -133,6 +133,7 @@ struct uv_scir_s {
 struct uv_hub_info_s {
 	unsigned long		global_mmr_base;
 	unsigned long		gpa_mask;
+	unsigned int		gnode_extra;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
@@ -159,7 +160,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
  * 		p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
-#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
+#define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
+#define UV_PNODE_TO_NASID(p)		(UV_PNODE_TO_GNODE(p) << 1)
 
 #define UV_LOCAL_MMR_BASE		0xf4000000UL
 #define UV_GLOBAL_MMR32_BASE		0xf8000000UL
@@ -173,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
-	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+	((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
 #define UV_APIC_PNODE_SHIFT	6
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88d1bfc847d..4f78bd68212 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit_$(BITS).o
+obj-y			+= setup.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -44,6 +44,7 @@ obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_DS)		+= ds.o
+obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 723989d7f80..631086159c5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -33,6 +33,7 @@
 #include <linux/irq.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
+#include <linux/pci.h>
 
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
@@ -522,7 +523,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 {
 	unsigned int irq;
 	unsigned int plat_gsi = gsi;
@@ -532,14 +533,14 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		if (triggering == ACPI_LEVEL_SENSITIVE)
+		if (trigger == ACPI_LEVEL_SENSITIVE)
 			eisa_set_level_irq(gsi);
 	}
 #endif
 
 #ifdef CONFIG_X86_IO_APIC
 	if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
-		plat_gsi = mp_register_gsi(gsi, triggering, polarity);
+		plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
 	}
 #endif
 	acpi_gsi_to_irq(plat_gsi, &irq);
@@ -903,10 +904,8 @@ extern int es7000_plat;
 #endif
 
 static struct {
-	int apic_id;
 	int gsi_base;
 	int gsi_end;
-	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
 } mp_ioapic_routing[MAX_IO_APICS];
 
 int mp_find_ioapic(int gsi)
@@ -986,16 +985,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
 	mp_ioapics[idx].apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
 	mp_ioapics[idx].apicver = io_apic_get_version(idx);
-#else
-	mp_ioapics[idx].apicver = 0;
-#endif
+
 	/*
 	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
 	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
 	 */
-	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
 	mp_ioapic_routing[idx].gsi_base = gsi_base;
 	mp_ioapic_routing[idx].gsi_end = gsi_base +
 	    io_apic_get_redir_entries(idx);
@@ -1158,26 +1153,52 @@ void __init mp_config_acpi_legacy_irqs(void)
 	}
 }
 
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+			int polarity)
 {
+#ifdef CONFIG_X86_MPPARSE
+	struct mpc_intsrc mp_irq;
+	struct pci_dev *pdev;
+	unsigned char number;
+	unsigned int devfn;
 	int ioapic;
-	int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM	4096
-#define IRQ_COMPRESSION_START	64
+	u8 pin;
 
-	static int pci_irq = IRQ_COMPRESSION_START;
-	/*
-	 * Mapping between Global System Interrupts, which
-	 * represent all possible interrupts, and IRQs
-	 * assigned to actual devices.
-	 */
-	static int gsi_to_irq[MAX_GSI_NUM];
-#else
+	if (!acpi_ioapic)
+		return 0;
+	if (!dev)
+		return 0;
+	if (dev->bus != &pci_bus_type)
+		return 0;
+
+	pdev = to_pci_dev(dev);
+	number = pdev->bus->number;
+	devfn = pdev->devfn;
+	pin = pdev->pin;
+	/* print the entry should happen on mptable identically */
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+	mp_irq.srcbus = number;
+	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	ioapic = mp_find_ioapic(gsi);
+	mp_irq.dstapic = mp_ioapics[ioapic].apicid;
+	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+	save_mp_irq(&mp_irq);
+#endif
+	return 0;
+}
+
+int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
+{
+	int ioapic;
+	int ioapic_pin;
+	struct io_apic_irq_attr irq_attr;
 
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
-#endif
 
 	/* Don't set up the ACPI SCI because it's already set up */
 	if (acpi_gbl_FADT.sci_interrupt == gsi)
@@ -1196,93 +1217,22 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
 		gsi = ioapic_renumber_irq(ioapic, gsi);
 #endif
 
-	/*
-	 * Avoid pin reprogramming.  PRTs typically include entries
-	 * with redundant pin->gsi mappings (but unique PCI devices);
-	 * we only program the IOAPIC on the first.
-	 */
 	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
 		printk(KERN_ERR "Invalid reference to IOAPIC pin "
-		       "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+		       "%d-%d\n", mp_ioapics[ioapic].apicid,
 		       ioapic_pin);
 		return gsi;
 	}
-	if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
-		return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
-		return gsi;
-#endif
-	}
-
-	set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
-	/*
-	 * For GSI >= 64, use IRQ compression
-	 */
-	if ((gsi >= IRQ_COMPRESSION_START)
-	    && (triggering == ACPI_LEVEL_SENSITIVE)) {
-		/*
-		 * For PCI devices assign IRQs in order, avoiding gaps
-		 * due to unused I/O APIC pins.
-		 */
-		int irq = gsi;
-		if (gsi < MAX_GSI_NUM) {
-			/*
-			 * Retain the VIA chipset work-around (gsi > 15), but
-			 * avoid a problem where the 8254 timer (IRQ0) is setup
-			 * via an override (so it's not on pin 0 of the ioapic),
-			 * and at the same time, the pin 0 interrupt is a PCI
-			 * type.  The gsi > 15 test could cause these two pins
-			 * to be shared as IRQ0, and they are not shareable.
-			 * So test for this condition, and if necessary, avoid
-			 * the pin collision.
-			 */
-			gsi = pci_irq++;
-			/*
-			 * Don't assign IRQ used by ACPI SCI
-			 */
-			if (gsi == acpi_gbl_FADT.sci_interrupt)
-				gsi = pci_irq++;
-			gsi_to_irq[irq] = gsi;
-		} else {
-			printk(KERN_ERR "GSI %u is too high\n", gsi);
-			return gsi;
-		}
-	}
-#endif
-	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
-				triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
-				polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-	return gsi;
-}
 
-int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-			u32 gsi, int triggering, int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
-	struct mpc_intsrc mp_irq;
-	int ioapic;
+	if (enable_update_mptable)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 
-	if (!acpi_ioapic)
-		return 0;
+	set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
+			     trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
+			     polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+	io_apic_set_pci_routing(dev, gsi, &irq_attr);
 
-	/* print the entry should happen on mptable identically */
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
-				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
-	mp_irq.srcbus = number;
-	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
-	ioapic = mp_find_ioapic(gsi);
-	mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
-	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
-	save_mp_irq(&mp_irq);
-#endif
-	return 0;
+	return gsi;
 }
 
 /*
diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile
index 1c31cc0e9de..167bc16ce0e 100644
--- a/arch/x86/kernel/acpi/realmode/Makefile
+++ b/arch/x86/kernel/acpi/realmode/Makefile
@@ -9,7 +9,7 @@
 always		:= wakeup.bin
 targets		:= wakeup.elf wakeup.lds
 
-wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o
+wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o bioscall.o regs.o
 
 # The link order of the video-*.o modules can matter.  In particular,
 # video-vga.o *must* be listed first, followed by video-vesa.o.
diff --git a/arch/x86/kernel/acpi/realmode/bioscall.S b/arch/x86/kernel/acpi/realmode/bioscall.S
new file mode 100644
index 00000000000..f51eb0bb56c
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/bioscall.S
@@ -0,0 +1 @@
+#include "../../../boot/bioscall.S"
diff --git a/arch/x86/kernel/acpi/realmode/regs.c b/arch/x86/kernel/acpi/realmode/regs.c
new file mode 100644
index 00000000000..6206033ba20
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/regs.c
@@ -0,0 +1 @@
+#include "../../../boot/regs.c"
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a97db99dad5..1c60554537c 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -55,7 +55,16 @@ struct iommu_cmd {
 static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 			     struct unity_map_entry *e);
 static struct dma_ops_domain *find_protection_domain(u16 devid);
+static u64* alloc_pte(struct protection_domain *dom,
+		      unsigned long address, u64
+		      **pte_page, gfp_t gfp);
+static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
+				      unsigned long start_page,
+				      unsigned int pages);
 
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
 
 #ifdef CONFIG_AMD_IOMMU_STATS
 
@@ -213,7 +222,7 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
 {
 	struct amd_iommu *iommu;
 
-	list_for_each_entry(iommu, &amd_iommu_list, list)
+	for_each_iommu(iommu)
 		iommu_poll_events(iommu);
 
 	return IRQ_HANDLED;
@@ -440,7 +449,7 @@ static void iommu_flush_domain(u16 domid)
 	__iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 				      domid, 1, 1);
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
 		spin_lock_irqsave(&iommu->lock, flags);
 		__iommu_queue_command(iommu, &cmd);
 		__iommu_completion_wait(iommu);
@@ -449,6 +458,35 @@ static void iommu_flush_domain(u16 domid)
 	}
 }
 
+void amd_iommu_flush_all_domains(void)
+{
+	int i;
+
+	for (i = 1; i < MAX_DOMAIN_ID; ++i) {
+		if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+			continue;
+		iommu_flush_domain(i);
+	}
+}
+
+void amd_iommu_flush_all_devices(void)
+{
+	struct amd_iommu *iommu;
+	int i;
+
+	for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+		if (amd_iommu_pd_table[i] == NULL)
+			continue;
+
+		iommu = amd_iommu_rlookup_table[i];
+		if (!iommu)
+			continue;
+
+		iommu_queue_inv_dev_entry(iommu, i);
+		iommu_completion_wait(iommu);
+	}
+}
+
 /****************************************************************************
  *
  * The functions below are used the create the page table mappings for
@@ -468,7 +506,7 @@ static int iommu_map_page(struct protection_domain *dom,
 			  unsigned long phys_addr,
 			  int prot)
 {
-	u64 __pte, *pte, *page;
+	u64 __pte, *pte;
 
 	bus_addr  = PAGE_ALIGN(bus_addr);
 	phys_addr = PAGE_ALIGN(phys_addr);
@@ -477,27 +515,7 @@ static int iommu_map_page(struct protection_domain *dom,
 	if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
 		return -EINVAL;
 
-	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L2_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L1_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)];
+	pte = alloc_pte(dom, bus_addr, NULL, GFP_KERNEL);
 
 	if (IOMMU_PTE_PRESENT(*pte))
 		return -EBUSY;
@@ -595,7 +613,8 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 		 * as allocated in the aperture
 		 */
 		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap);
+			__set_bit(addr >> PAGE_SHIFT,
+				  dma_dom->aperture[0]->bitmap);
 	}
 
 	return 0;
@@ -632,42 +651,191 @@ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
  ****************************************************************************/
 
 /*
- * The address allocator core function.
+ * The address allocator core functions.
  *
  * called with domain->lock held
  */
+
+/*
+ * This function checks if there is a PTE for a given dma address. If
+ * there is one, it returns the pointer to it.
+ */
+static u64* fetch_pte(struct protection_domain *domain,
+		      unsigned long address)
+{
+	u64 *pte;
+
+	pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+	return pte;
+}
+
+/*
+ * This function is used to add a new aperture range to an existing
+ * aperture in case of dma_ops domain allocation or address allocation
+ * failure.
+ */
+static int alloc_new_range(struct amd_iommu *iommu,
+			   struct dma_ops_domain *dma_dom,
+			   bool populate, gfp_t gfp)
+{
+	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i;
+
+#ifdef CONFIG_IOMMU_STRESS
+	populate = false;
+#endif
+
+	if (index >= APERTURE_MAX_RANGES)
+		return -ENOMEM;
+
+	dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp);
+	if (!dma_dom->aperture[index])
+		return -ENOMEM;
+
+	dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp);
+	if (!dma_dom->aperture[index]->bitmap)
+		goto out_free;
+
+	dma_dom->aperture[index]->offset = dma_dom->aperture_size;
+
+	if (populate) {
+		unsigned long address = dma_dom->aperture_size;
+		int i, num_ptes = APERTURE_RANGE_PAGES / 512;
+		u64 *pte, *pte_page;
+
+		for (i = 0; i < num_ptes; ++i) {
+			pte = alloc_pte(&dma_dom->domain, address,
+					&pte_page, gfp);
+			if (!pte)
+				goto out_free;
+
+			dma_dom->aperture[index]->pte_pages[i] = pte_page;
+
+			address += APERTURE_RANGE_SIZE / 64;
+		}
+	}
+
+	dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+
+	/* Intialize the exclusion range if necessary */
+	if (iommu->exclusion_start &&
+	    iommu->exclusion_start >= dma_dom->aperture[index]->offset &&
+	    iommu->exclusion_start < dma_dom->aperture_size) {
+		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
+		int pages = iommu_num_pages(iommu->exclusion_start,
+					    iommu->exclusion_length,
+					    PAGE_SIZE);
+		dma_ops_reserve_addresses(dma_dom, startpage, pages);
+	}
+
+	/*
+	 * Check for areas already mapped as present in the new aperture
+	 * range and mark those pages as reserved in the allocator. Such
+	 * mappings may already exist as a result of requested unity
+	 * mappings for devices.
+	 */
+	for (i = dma_dom->aperture[index]->offset;
+	     i < dma_dom->aperture_size;
+	     i += PAGE_SIZE) {
+		u64 *pte = fetch_pte(&dma_dom->domain, i);
+		if (!pte || !IOMMU_PTE_PRESENT(*pte))
+			continue;
+
+		dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1);
+	}
+
+	return 0;
+
+out_free:
+	free_page((unsigned long)dma_dom->aperture[index]->bitmap);
+
+	kfree(dma_dom->aperture[index]);
+	dma_dom->aperture[index] = NULL;
+
+	return -ENOMEM;
+}
+
+static unsigned long dma_ops_area_alloc(struct device *dev,
+					struct dma_ops_domain *dom,
+					unsigned int pages,
+					unsigned long align_mask,
+					u64 dma_mask,
+					unsigned long start)
+{
+	unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
+	int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i = start >> APERTURE_RANGE_SHIFT;
+	unsigned long boundary_size;
+	unsigned long address = -1;
+	unsigned long limit;
+
+	next_bit >>= PAGE_SHIFT;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			PAGE_SIZE) >> PAGE_SHIFT;
+
+	for (;i < max_index; ++i) {
+		unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
+
+		if (dom->aperture[i]->offset >= dma_mask)
+			break;
+
+		limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
+					       dma_mask >> PAGE_SHIFT);
+
+		address = iommu_area_alloc(dom->aperture[i]->bitmap,
+					   limit, next_bit, pages, 0,
+					    boundary_size, align_mask);
+		if (address != -1) {
+			address = dom->aperture[i]->offset +
+				  (address << PAGE_SHIFT);
+			dom->next_address = address + (pages << PAGE_SHIFT);
+			break;
+		}
+
+		next_bit = 0;
+	}
+
+	return address;
+}
+
 static unsigned long dma_ops_alloc_addresses(struct device *dev,
 					     struct dma_ops_domain *dom,
 					     unsigned int pages,
 					     unsigned long align_mask,
 					     u64 dma_mask)
 {
-	unsigned long limit;
 	unsigned long address;
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			PAGE_SIZE) >> PAGE_SHIFT;
-	limit = iommu_device_max_index(dom->aperture_size >> PAGE_SHIFT, 0,
-				       dma_mask >> PAGE_SHIFT);
+#ifdef CONFIG_IOMMU_STRESS
+	dom->next_address = 0;
+	dom->need_flush = true;
+#endif
 
-	if (dom->next_bit >= limit) {
-		dom->next_bit = 0;
-		dom->need_flush = true;
-	}
+	address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+				     dma_mask, dom->next_address);
 
-	address = iommu_area_alloc(dom->bitmap, limit, dom->next_bit, pages,
-				   0 , boundary_size, align_mask);
 	if (address == -1) {
-		address = iommu_area_alloc(dom->bitmap, limit, 0, pages,
-				0, boundary_size, align_mask);
+		dom->next_address = 0;
+		address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+					     dma_mask, 0);
 		dom->need_flush = true;
 	}
 
-	if (likely(address != -1)) {
-		dom->next_bit = address + pages;
-		address <<= PAGE_SHIFT;
-	} else
+	if (unlikely(address == -1))
 		address = bad_dma_address;
 
 	WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
@@ -684,11 +852,23 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
 				   unsigned long address,
 				   unsigned int pages)
 {
-	address >>= PAGE_SHIFT;
-	iommu_area_free(dom->bitmap, address, pages);
+	unsigned i = address >> APERTURE_RANGE_SHIFT;
+	struct aperture_range *range = dom->aperture[i];
 
-	if (address >= dom->next_bit)
+	BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
+
+#ifdef CONFIG_IOMMU_STRESS
+	if (i < 4)
+		return;
+#endif
+
+	if (address >= dom->next_address)
 		dom->need_flush = true;
+
+	address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
+
+	iommu_area_free(range->bitmap, address, pages);
+
 }
 
 /****************************************************************************
@@ -736,12 +916,16 @@ static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
 				      unsigned long start_page,
 				      unsigned int pages)
 {
-	unsigned int last_page = dom->aperture_size >> PAGE_SHIFT;
+	unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT;
 
 	if (start_page + pages > last_page)
 		pages = last_page - start_page;
 
-	iommu_area_reserve(dom->bitmap, start_page, pages);
+	for (i = start_page; i < start_page + pages; ++i) {
+		int index = i / APERTURE_RANGE_PAGES;
+		int page  = i % APERTURE_RANGE_PAGES;
+		__set_bit(page, dom->aperture[index]->bitmap);
+	}
 }
 
 static void free_pagetable(struct protection_domain *domain)
@@ -780,14 +964,19 @@ static void free_pagetable(struct protection_domain *domain)
  */
 static void dma_ops_domain_free(struct dma_ops_domain *dom)
 {
+	int i;
+
 	if (!dom)
 		return;
 
 	free_pagetable(&dom->domain);
 
-	kfree(dom->pte_pages);
-
-	kfree(dom->bitmap);
+	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+		if (!dom->aperture[i])
+			continue;
+		free_page((unsigned long)dom->aperture[i]->bitmap);
+		kfree(dom->aperture[i]);
+	}
 
 	kfree(dom);
 }
@@ -797,19 +986,9 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
  * It also intializes the page table and the address allocator data
  * structures required for the dma_ops interface
  */
-static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
-						   unsigned order)
+static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu)
 {
 	struct dma_ops_domain *dma_dom;
-	unsigned i, num_pte_pages;
-	u64 *l2_pde;
-	u64 address;
-
-	/*
-	 * Currently the DMA aperture must be between 32 MB and 1GB in size
-	 */
-	if ((order < 25) || (order > 30))
-		return NULL;
 
 	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
 	if (!dma_dom)
@@ -826,55 +1005,20 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
 	dma_dom->domain.priv = dma_dom;
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
-	dma_dom->aperture_size = (1ULL << order);
-	dma_dom->bitmap = kzalloc(dma_dom->aperture_size / (PAGE_SIZE * 8),
-				  GFP_KERNEL);
-	if (!dma_dom->bitmap)
-		goto free_dma_dom;
-	/*
-	 * mark the first page as allocated so we never return 0 as
-	 * a valid dma-address. So we can use 0 as error value
-	 */
-	dma_dom->bitmap[0] = 1;
-	dma_dom->next_bit = 0;
 
 	dma_dom->need_flush = false;
 	dma_dom->target_dev = 0xffff;
 
-	/* Intialize the exclusion range if necessary */
-	if (iommu->exclusion_start &&
-	    iommu->exclusion_start < dma_dom->aperture_size) {
-		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
-		int pages = iommu_num_pages(iommu->exclusion_start,
-					    iommu->exclusion_length,
-					    PAGE_SIZE);
-		dma_ops_reserve_addresses(dma_dom, startpage, pages);
-	}
+	if (alloc_new_range(iommu, dma_dom, true, GFP_KERNEL))
+		goto free_dma_dom;
 
 	/*
-	 * At the last step, build the page tables so we don't need to
-	 * allocate page table pages in the dma_ops mapping/unmapping
-	 * path.
+	 * mark the first page as allocated so we never return 0 as
+	 * a valid dma-address. So we can use 0 as error value
 	 */
-	num_pte_pages = dma_dom->aperture_size / (PAGE_SIZE * 512);
-	dma_dom->pte_pages = kzalloc(num_pte_pages * sizeof(void *),
-			GFP_KERNEL);
-	if (!dma_dom->pte_pages)
-		goto free_dma_dom;
-
-	l2_pde = (u64 *)get_zeroed_page(GFP_KERNEL);
-	if (l2_pde == NULL)
-		goto free_dma_dom;
+	dma_dom->aperture[0]->bitmap[0] = 1;
+	dma_dom->next_address = 0;
 
-	dma_dom->domain.pt_root[0] = IOMMU_L2_PDE(virt_to_phys(l2_pde));
-
-	for (i = 0; i < num_pte_pages; ++i) {
-		dma_dom->pte_pages[i] = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!dma_dom->pte_pages[i])
-			goto free_dma_dom;
-		address = virt_to_phys(dma_dom->pte_pages[i]);
-		l2_pde[i] = IOMMU_L1_PDE(address);
-	}
 
 	return dma_dom;
 
@@ -983,7 +1127,6 @@ static int device_change_notifier(struct notifier_block *nb,
 	struct protection_domain *domain;
 	struct dma_ops_domain *dma_domain;
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	unsigned long flags;
 
 	if (devid > amd_iommu_last_bdf)
@@ -1002,17 +1145,7 @@ static int device_change_notifier(struct notifier_block *nb,
 			  "to a non-dma-ops domain\n", dev_name(dev));
 
 	switch (action) {
-	case BUS_NOTIFY_BOUND_DRIVER:
-		if (domain)
-			goto out;
-		dma_domain = find_protection_domain(devid);
-		if (!dma_domain)
-			dma_domain = iommu->default_dom;
-		attach_device(iommu, &dma_domain->domain, devid);
-		printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
-		       "device %s\n", dma_domain->domain.id, dev_name(dev));
-		break;
-	case BUS_NOTIFY_UNBIND_DRIVER:
+	case BUS_NOTIFY_UNBOUND_DRIVER:
 		if (!domain)
 			goto out;
 		detach_device(domain, devid);
@@ -1022,7 +1155,7 @@ static int device_change_notifier(struct notifier_block *nb,
 		dma_domain = find_protection_domain(devid);
 		if (dma_domain)
 			goto out;
-		dma_domain = dma_ops_domain_alloc(iommu, order);
+		dma_domain = dma_ops_domain_alloc(iommu);
 		if (!dma_domain)
 			goto out;
 		dma_domain->target_dev = devid;
@@ -1133,8 +1266,8 @@ static int get_device_resources(struct device *dev,
 			dma_dom = (*iommu)->default_dom;
 		*domain = &dma_dom->domain;
 		attach_device(*iommu, *domain, *bdf);
-		printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
-				"device %s\n", (*domain)->id, dev_name(dev));
+		DUMP_printk("Using protection domain %d for device %s\n",
+			    (*domain)->id, dev_name(dev));
 	}
 
 	if (domain_for_device(_bdf) == NULL)
@@ -1144,6 +1277,66 @@ static int get_device_resources(struct device *dev,
 }
 
 /*
+ * If the pte_page is not yet allocated this function is called
+ */
+static u64* alloc_pte(struct protection_domain *dom,
+		      unsigned long address, u64 **pte_page, gfp_t gfp)
+{
+	u64 *pte, *page;
+
+	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(gfp);
+		if (!page)
+			return NULL;
+		*pte = IOMMU_L2_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(gfp);
+		if (!page)
+			return NULL;
+		*pte = IOMMU_L1_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+
+	if (pte_page)
+		*pte_page = pte;
+
+	pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+	return pte;
+}
+
+/*
+ * This function fetches the PTE for a given address in the aperture
+ */
+static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
+			    unsigned long address)
+{
+	struct aperture_range *aperture;
+	u64 *pte, *pte_page;
+
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return NULL;
+
+	pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte) {
+		pte = alloc_pte(&dom->domain, address, &pte_page, GFP_ATOMIC);
+		aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
+	} else
+		pte += IOMMU_PTE_L0_INDEX(address);
+
+	return pte;
+}
+
+/*
  * This is the generic map function. It maps one 4kb page at paddr to
  * the given address in the DMA address space for the domain.
  */
@@ -1159,8 +1352,9 @@ static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu,
 
 	paddr &= PAGE_MASK;
 
-	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
-	pte += IOMMU_PTE_L0_INDEX(address);
+	pte  = dma_ops_get_pte(dom, address);
+	if (!pte)
+		return bad_dma_address;
 
 	__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
 
@@ -1185,14 +1379,20 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
 				 struct dma_ops_domain *dom,
 				 unsigned long address)
 {
+	struct aperture_range *aperture;
 	u64 *pte;
 
 	if (address >= dom->aperture_size)
 		return;
 
-	WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return;
+
+	pte  = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte)
+		return;
 
-	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
 	pte += IOMMU_PTE_L0_INDEX(address);
 
 	WARN_ON(!*pte);
@@ -1216,7 +1416,7 @@ static dma_addr_t __map_single(struct device *dev,
 			       u64 dma_mask)
 {
 	dma_addr_t offset = paddr & ~PAGE_MASK;
-	dma_addr_t address, start;
+	dma_addr_t address, start, ret;
 	unsigned int pages;
 	unsigned long align_mask = 0;
 	int i;
@@ -1232,14 +1432,33 @@ static dma_addr_t __map_single(struct device *dev,
 	if (align)
 		align_mask = (1UL << get_order(size)) - 1;
 
+retry:
 	address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
 					  dma_mask);
-	if (unlikely(address == bad_dma_address))
-		goto out;
+	if (unlikely(address == bad_dma_address)) {
+		/*
+		 * setting next_address here will let the address
+		 * allocator only scan the new allocated range in the
+		 * first run. This is a small optimization.
+		 */
+		dma_dom->next_address = dma_dom->aperture_size;
+
+		if (alloc_new_range(iommu, dma_dom, false, GFP_ATOMIC))
+			goto out;
+
+		/*
+		 * aperture was sucessfully enlarged by 128 MB, try
+		 * allocation again
+		 */
+		goto retry;
+	}
 
 	start = address;
 	for (i = 0; i < pages; ++i) {
-		dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+		ret = dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+		if (ret == bad_dma_address)
+			goto out_unmap;
+
 		paddr += PAGE_SIZE;
 		start += PAGE_SIZE;
 	}
@@ -1255,6 +1474,17 @@ static dma_addr_t __map_single(struct device *dev,
 
 out:
 	return address;
+
+out_unmap:
+
+	for (--i; i >= 0; --i) {
+		start -= PAGE_SIZE;
+		dma_ops_domain_unmap(iommu, dma_dom, start);
+	}
+
+	dma_ops_free_addresses(dma_dom, address, pages);
+
+	return bad_dma_address;
 }
 
 /*
@@ -1537,8 +1767,10 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	*dma_addr = __map_single(dev, iommu, domain->priv, paddr,
 				 size, DMA_BIDIRECTIONAL, true, dma_mask);
 
-	if (*dma_addr == bad_dma_address)
+	if (*dma_addr == bad_dma_address) {
+		spin_unlock_irqrestore(&domain->lock, flags);
 		goto out_free;
+	}
 
 	iommu_completion_wait(iommu);
 
@@ -1625,7 +1857,6 @@ static void prealloc_protection_domains(void)
 	struct pci_dev *dev = NULL;
 	struct dma_ops_domain *dma_dom;
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	u16 devid;
 
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
@@ -1638,7 +1869,7 @@ static void prealloc_protection_domains(void)
 		iommu = amd_iommu_rlookup_table[devid];
 		if (!iommu)
 			continue;
-		dma_dom = dma_ops_domain_alloc(iommu, order);
+		dma_dom = dma_ops_domain_alloc(iommu);
 		if (!dma_dom)
 			continue;
 		init_unity_mappings_for_device(dma_dom, devid);
@@ -1664,7 +1895,6 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	int ret;
 
 	/*
@@ -1672,8 +1902,8 @@ int __init amd_iommu_init_dma_ops(void)
 	 * found in the system. Devices not assigned to any other
 	 * protection domain will be assigned to the default one.
 	 */
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
-		iommu->default_dom = dma_ops_domain_alloc(iommu, order);
+	for_each_iommu(iommu) {
+		iommu->default_dom = dma_ops_domain_alloc(iommu);
 		if (iommu->default_dom == NULL)
 			return -ENOMEM;
 		iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
@@ -1710,7 +1940,7 @@ int __init amd_iommu_init_dma_ops(void)
 
 free_domains:
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
 		if (iommu->default_dom)
 			dma_ops_domain_free(iommu->default_dom);
 	}
@@ -1842,7 +2072,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 
 	old_domain = domain_for_device(devid);
 	if (old_domain)
-		return -EBUSY;
+		detach_device(old_domain, devid);
 
 	attach_device(iommu, domain, devid);
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 8c0be0902da..238989ec077 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -115,15 +115,21 @@ struct ivmd_header {
 	u64 range_length;
 } __attribute__((packed));
 
+bool amd_iommu_dump;
+
 static int __initdata amd_iommu_detected;
 
 u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 					   to handle */
 LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
 					   we find in ACPI */
-unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
+#ifdef CONFIG_IOMMU_STRESS
+bool amd_iommu_isolate = false;
+#else
 bool amd_iommu_isolate = true;		/* if true, device isolation is
 					   enabled */
+#endif
+
 bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
 
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
@@ -175,7 +181,7 @@ static inline void update_last_devid(u16 devid)
 static inline unsigned long tbl_size(int entry_size)
 {
 	unsigned shift = PAGE_SHIFT +
-			 get_order(amd_iommu_last_bdf * entry_size);
+			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
 
 	return 1UL << shift;
 }
@@ -193,7 +199,7 @@ static inline unsigned long tbl_size(int entry_size)
  * This function set the exclusion range in the IOMMU. DMA accesses to the
  * exclusion range are passed through untranslated
  */
-static void __init iommu_set_exclusion_range(struct amd_iommu *iommu)
+static void iommu_set_exclusion_range(struct amd_iommu *iommu)
 {
 	u64 start = iommu->exclusion_start & PAGE_MASK;
 	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
@@ -225,7 +231,7 @@ static void __init iommu_set_device_table(struct amd_iommu *iommu)
 }
 
 /* Generic functions to enable/disable certain features of the IOMMU. */
-static void __init iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
 {
 	u32 ctrl;
 
@@ -244,7 +250,7 @@ static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 }
 
 /* Function to enable the hardware */
-static void __init iommu_enable(struct amd_iommu *iommu)
+static void iommu_enable(struct amd_iommu *iommu)
 {
 	printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at %s cap 0x%hx\n",
 	       dev_name(&iommu->dev->dev), iommu->cap_ptr);
@@ -252,11 +258,9 @@ static void __init iommu_enable(struct amd_iommu *iommu)
 	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
 }
 
-/* Function to enable IOMMU event logging and event interrupts */
-static void __init iommu_enable_event_logging(struct amd_iommu *iommu)
+static void iommu_disable(struct amd_iommu *iommu)
 {
-	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
-	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
 }
 
 /*
@@ -413,25 +417,36 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
 {
 	u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 			get_order(CMD_BUFFER_SIZE));
-	u64 entry;
 
 	if (cmd_buf == NULL)
 		return NULL;
 
 	iommu->cmd_buf_size = CMD_BUFFER_SIZE;
 
-	entry = (u64)virt_to_phys(cmd_buf);
+	return cmd_buf;
+}
+
+/*
+ * This function writes the command buffer address to the hardware and
+ * enables it.
+ */
+static void iommu_enable_command_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->cmd_buf == NULL);
+
+	entry = (u64)virt_to_phys(iommu->cmd_buf);
 	entry |= MMIO_CMD_SIZE_512;
+
 	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
-			&entry, sizeof(entry));
+		    &entry, sizeof(entry));
 
 	/* set head and tail to zero manually */
 	writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
 	writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 
 	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
-
-	return cmd_buf;
 }
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
@@ -443,20 +458,27 @@ static void __init free_command_buffer(struct amd_iommu *iommu)
 /* allocates the memory where the IOMMU will log its events to */
 static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
 {
-	u64 entry;
 	iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 						get_order(EVT_BUFFER_SIZE));
 
 	if (iommu->evt_buf == NULL)
 		return NULL;
 
+	return iommu->evt_buf;
+}
+
+static void iommu_enable_event_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->evt_buf == NULL);
+
 	entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+
 	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
 		    &entry, sizeof(entry));
 
-	iommu->evt_buf_size = EVT_BUFFER_SIZE;
-
-	return iommu->evt_buf;
+	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
 }
 
 static void __init free_event_buffer(struct amd_iommu *iommu)
@@ -596,32 +618,83 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	p += sizeof(struct ivhd_header);
 	end += h->length;
 
+
 	while (p < end) {
 		e = (struct ivhd_entry *)p;
 		switch (e->type) {
 		case IVHD_DEV_ALL:
+
+			DUMP_printk("  DEV_ALL\t\t\t first devid: %02x:%02x.%x"
+				    " last device %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS(iommu->first_device),
+				    PCI_SLOT(iommu->first_device),
+				    PCI_FUNC(iommu->first_device),
+				    PCI_BUS(iommu->last_device),
+				    PCI_SLOT(iommu->last_device),
+				    PCI_FUNC(iommu->last_device),
+				    e->flags);
+
 			for (dev_i = iommu->first_device;
 					dev_i <= iommu->last_device; ++dev_i)
 				set_dev_entry_from_acpi(iommu, dev_i,
 							e->flags, 0);
 			break;
 		case IVHD_DEV_SELECT:
+
+			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
 			devid = e->devid;
 			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
 			break;
 		case IVHD_DEV_SELECT_RANGE_START:
+
+			DUMP_printk("  DEV_SELECT_RANGE_START\t "
+				    "devid: %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
 			devid_start = e->devid;
 			flags = e->flags;
 			ext_flags = 0;
 			alias = false;
 			break;
 		case IVHD_DEV_ALIAS:
+
+			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x devid_to: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
 			devid = e->devid;
 			devid_to = e->ext >> 8;
-			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
 			amd_iommu_alias_table[devid] = devid_to;
 			break;
 		case IVHD_DEV_ALIAS_RANGE:
+
+			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
+				    "devid: %02x:%02x.%x flags: %02x "
+				    "devid_to: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
 			devid_start = e->devid;
 			flags = e->flags;
 			devid_to = e->ext >> 8;
@@ -629,17 +702,39 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 			alias = true;
 			break;
 		case IVHD_DEV_EXT_SELECT:
+
+			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
+				    "flags: %02x ext: %08x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
 			devid = e->devid;
 			set_dev_entry_from_acpi(iommu, devid, e->flags,
 						e->ext);
 			break;
 		case IVHD_DEV_EXT_SELECT_RANGE:
+
+			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
+				    "%02x:%02x.%x flags: %02x ext: %08x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
 			devid_start = e->devid;
 			flags = e->flags;
 			ext_flags = e->ext;
 			alias = false;
 			break;
 		case IVHD_DEV_RANGE_END:
+
+			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid));
+
 			devid = e->devid;
 			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
 				if (alias)
@@ -679,7 +774,7 @@ static void __init free_iommu_all(void)
 {
 	struct amd_iommu *iommu, *next;
 
-	list_for_each_entry_safe(iommu, next, &amd_iommu_list, list) {
+	for_each_iommu_safe(iommu, next) {
 		list_del(&iommu->list);
 		free_iommu_one(iommu);
 		kfree(iommu);
@@ -710,7 +805,6 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (!iommu->mmio_base)
 		return -ENOMEM;
 
-	iommu_set_device_table(iommu);
 	iommu->cmd_buf = alloc_command_buffer(iommu);
 	if (!iommu->cmd_buf)
 		return -ENOMEM;
@@ -746,6 +840,15 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 		h = (struct ivhd_header *)p;
 		switch (*p) {
 		case ACPI_IVHD_TYPE:
+
+			DUMP_printk("IOMMU: device: %02x:%02x.%01x cap: %04x "
+				    "seg: %d flags: %01x info %04x\n",
+				    PCI_BUS(h->devid), PCI_SLOT(h->devid),
+				    PCI_FUNC(h->devid), h->cap_ptr,
+				    h->pci_seg, h->flags, h->info);
+			DUMP_printk("       mmio-addr: %016llx\n",
+				    h->mmio_phys);
+
 			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
 			if (iommu == NULL)
 				return -ENOMEM;
@@ -773,56 +876,9 @@ static int __init init_iommu_all(struct acpi_table_header *table)
  *
  ****************************************************************************/
 
-static int __init iommu_setup_msix(struct amd_iommu *iommu)
-{
-	struct amd_iommu *curr;
-	struct msix_entry entries[32]; /* only 32 supported by AMD IOMMU */
-	int nvec = 0, i;
-
-	list_for_each_entry(curr, &amd_iommu_list, list) {
-		if (curr->dev == iommu->dev) {
-			entries[nvec].entry = curr->evt_msi_num;
-			entries[nvec].vector = 0;
-			curr->int_enabled = true;
-			nvec++;
-		}
-	}
-
-	if (pci_enable_msix(iommu->dev, entries, nvec)) {
-		pci_disable_msix(iommu->dev);
-		return 1;
-	}
-
-	for (i = 0; i < nvec; ++i) {
-		int r = request_irq(entries->vector, amd_iommu_int_handler,
-				    IRQF_SAMPLE_RANDOM,
-				    "AMD IOMMU",
-				    NULL);
-		if (r)
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	for (i -= 1; i >= 0; --i)
-		free_irq(entries->vector, NULL);
-
-	pci_disable_msix(iommu->dev);
-
-	return 1;
-}
-
 static int __init iommu_setup_msi(struct amd_iommu *iommu)
 {
 	int r;
-	struct amd_iommu *curr;
-
-	list_for_each_entry(curr, &amd_iommu_list, list) {
-		if (curr->dev == iommu->dev)
-			curr->int_enabled = true;
-	}
-
 
 	if (pci_enable_msi(iommu->dev))
 		return 1;
@@ -837,17 +893,18 @@ static int __init iommu_setup_msi(struct amd_iommu *iommu)
 		return 1;
 	}
 
+	iommu->int_enabled = true;
+	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+
 	return 0;
 }
 
-static int __init iommu_init_msi(struct amd_iommu *iommu)
+static int iommu_init_msi(struct amd_iommu *iommu)
 {
 	if (iommu->int_enabled)
 		return 0;
 
-	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSIX))
-		return iommu_setup_msix(iommu);
-	else if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
+	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
 		return iommu_setup_msi(iommu);
 
 	return 1;
@@ -899,6 +956,7 @@ static int __init init_exclusion_range(struct ivmd_header *m)
 static int __init init_unity_map_range(struct ivmd_header *m)
 {
 	struct unity_map_entry *e = 0;
+	char *s;
 
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (e == NULL)
@@ -906,14 +964,19 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 
 	switch (m->type) {
 	default:
+		kfree(e);
+		return 0;
 	case ACPI_IVMD_TYPE:
+		s = "IVMD_TYPEi\t\t\t";
 		e->devid_start = e->devid_end = m->devid;
 		break;
 	case ACPI_IVMD_TYPE_ALL:
+		s = "IVMD_TYPE_ALL\t\t";
 		e->devid_start = 0;
 		e->devid_end = amd_iommu_last_bdf;
 		break;
 	case ACPI_IVMD_TYPE_RANGE:
+		s = "IVMD_TYPE_RANGE\t\t";
 		e->devid_start = m->devid;
 		e->devid_end = m->aux;
 		break;
@@ -922,6 +985,13 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
 	e->prot = m->flags >> 1;
 
+	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
+		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
+		    PCI_BUS(e->devid_start), PCI_SLOT(e->devid_start),
+		    PCI_FUNC(e->devid_start), PCI_BUS(e->devid_end),
+		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
+		    e->address_start, e->address_end, m->flags);
+
 	list_add_tail(&e->list, &amd_iommu_unity_map);
 
 	return 0;
@@ -967,18 +1037,28 @@ static void init_device_table(void)
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
  */
-static void __init enable_iommus(void)
+static void enable_iommus(void)
 {
 	struct amd_iommu *iommu;
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
+		iommu_set_device_table(iommu);
+		iommu_enable_command_buffer(iommu);
+		iommu_enable_event_buffer(iommu);
 		iommu_set_exclusion_range(iommu);
 		iommu_init_msi(iommu);
-		iommu_enable_event_logging(iommu);
 		iommu_enable(iommu);
 	}
 }
 
+static void disable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_disable(iommu);
+}
+
 /*
  * Suspend/Resume support
  * disable suspend until real resume implemented
@@ -986,12 +1066,31 @@ static void __init enable_iommus(void)
 
 static int amd_iommu_resume(struct sys_device *dev)
 {
+	/*
+	 * Disable IOMMUs before reprogramming the hardware registers.
+	 * IOMMU is still enabled from the resume kernel.
+	 */
+	disable_iommus();
+
+	/* re-load the hardware */
+	enable_iommus();
+
+	/*
+	 * we have to flush after the IOMMUs are enabled because a
+	 * disabled IOMMU will never execute the commands we send
+	 */
+	amd_iommu_flush_all_domains();
+	amd_iommu_flush_all_devices();
+
 	return 0;
 }
 
 static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
 {
-	return -EINVAL;
+	/* disable IOMMUs to go out of the way for BIOS */
+	disable_iommus();
+
+	return 0;
 }
 
 static struct sysdev_class amd_iommu_sysdev_class = {
@@ -1137,9 +1236,6 @@ int __init amd_iommu_init(void)
 
 	enable_iommus();
 
-	printk(KERN_INFO "AMD IOMMU: aperture size is %d MB\n",
-			(1 << (amd_iommu_aperture_order-20)));
-
 	printk(KERN_INFO "AMD IOMMU: device isolation ");
 	if (amd_iommu_isolate)
 		printk("enabled\n");
@@ -1211,6 +1307,13 @@ void __init amd_iommu_detect(void)
  *
  ****************************************************************************/
 
+static int __init parse_amd_iommu_dump(char *str)
+{
+	amd_iommu_dump = true;
+
+	return 1;
+}
+
 static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
@@ -1225,15 +1328,5 @@ static int __init parse_amd_iommu_options(char *str)
 	return 1;
 }
 
-static int __init parse_amd_iommu_size_options(char *str)
-{
-	unsigned order = PAGE_SHIFT + get_order(memparse(str, &str));
-
-	if ((order > 24) && (order < 31))
-		amd_iommu_aperture_order = order;
-
-	return 1;
-}
-
+__setup("amd_iommu_dump", parse_amd_iommu_dump);
 __setup("amd_iommu=", parse_amd_iommu_options);
-__setup("amd_iommu_size=", parse_amd_iommu_size_options);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 60df2efd7c8..076d3881f3d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -100,6 +100,29 @@ early_param("lapic", parse_lapic);
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
 
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go through APIC */
+	outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go directly to BSP */
+	outb(0x00, 0x23);
+}
 #endif
 
 #ifdef CONFIG_X86_64
@@ -113,13 +136,19 @@ static __init int setup_apicpmtimer(char *s)
 __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
+int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
-int x2apic;
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
 static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
+	if (x2apic_enabled()) {
+		pr_warning("Bios already enabled x2apic, "
+			   "can't enforce nox2apic");
+		return 0;
+	}
+
 	disable_x2apic = 1;
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	return 0;
@@ -211,6 +240,31 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+static void native_apic_write_dummy(u32 reg, u32 v)
+{
+	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+static u32 native_apic_read_dummy(u32 reg)
+{
+	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+	return 0;
+}
+
+/*
+ * right after this call apic->write/read doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+	apic->read = native_apic_read_dummy;
+	apic->write = native_apic_write_dummy;
+}
+
 void native_apic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -350,7 +404,7 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 
 static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
 	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
 
 	apic_write(reg, v);
@@ -817,7 +871,7 @@ void clear_local_APIC(void)
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
-	if (!x2apic && !apic_phys)
+	if (!x2apic_mode && !apic_phys)
 		return;
 
 	maxlvt = lapic_get_maxlvt();
@@ -1290,7 +1344,7 @@ void check_x2apic(void)
 {
 	if (x2apic_enabled()) {
 		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
-		x2apic_preenabled = x2apic = 1;
+		x2apic_preenabled = x2apic_mode = 1;
 	}
 }
 
@@ -1298,7 +1352,7 @@ void enable_x2apic(void)
 {
 	int msr, msr2;
 
-	if (!x2apic)
+	if (!x2apic_mode)
 		return;
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
@@ -1307,6 +1361,7 @@ void enable_x2apic(void)
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
+#endif /* CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
 {
@@ -1315,32 +1370,21 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
-	if (!cpu_has_x2apic)
-		return;
-
-	if (!x2apic_preenabled && disable_x2apic) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of nox2apic\n");
-		return;
+	ret = dmar_table_init();
+	if (ret) {
+		pr_debug("dmar_table_init() failed with %d:\n", ret);
+		goto ir_failed;
 	}
 
-	if (x2apic_preenabled && disable_x2apic)
-		panic("Bios already enabled x2apic, can't enforce nox2apic");
-
-	if (!x2apic_preenabled && skip_ioapic_setup) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of skipping io-apic setup\n");
-		return;
+	if (!intr_remapping_supported()) {
+		pr_debug("intr-remapping not supported\n");
+		goto ir_failed;
 	}
 
-	ret = dmar_table_init();
-	if (ret) {
-		pr_info("dmar_table_init() failed with %d:\n", ret);
 
-		if (x2apic_preenabled)
-			panic("x2apic enabled by bios. But IR enabling failed");
-		else
-			pr_info("Not enabling x2apic,Intr-remapping\n");
+	if (!x2apic_preenabled && skip_ioapic_setup) {
+		pr_info("Skipped enabling intr-remap because of skipping "
+			"io-apic setup\n");
 		return;
 	}
 
@@ -1360,19 +1404,16 @@ void __init enable_IR_x2apic(void)
 	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
 
-	ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (ret && x2apic_preenabled) {
-		local_irq_restore(flags);
-		panic("x2apic enabled by bios. But IR enabling failed");
-	}
-
+	ret = enable_intr_remapping(x2apic_supported());
 	if (ret)
 		goto end_restore;
 
-	if (!x2apic) {
-		x2apic = 1;
+	pr_info("Enabled Interrupt-remapping\n");
+
+	if (x2apic_supported() && !x2apic_mode) {
+		x2apic_mode = 1;
 		enable_x2apic();
+		pr_info("Enabled x2apic\n");
 	}
 
 end_restore:
@@ -1381,37 +1422,34 @@ end_restore:
 		 * IR enabling failed
 		 */
 		restore_IO_APIC_setup(ioapic_entries);
-	else
-		reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
 
 	unmask_8259A();
 	local_irq_restore(flags);
 
 end:
-	if (!ret) {
-		if (!x2apic_preenabled)
-			pr_info("Enabled x2apic and interrupt-remapping\n");
-		else
-			pr_info("Enabled Interrupt-remapping\n");
-	} else
-		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 	if (ioapic_entries)
 		free_ioapic_entries(ioapic_entries);
+
+	if (!ret)
+		return;
+
+ir_failed:
+	if (x2apic_preenabled)
+		panic("x2apic enabled by bios. But IR enabling failed");
+	else if (cpu_has_x2apic)
+		pr_info("Not enabling x2apic,Intr-remapping\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
 
 	if (x2apic_preenabled)
 		panic("x2apic enabled prior OS handover,"
-		      " enable CONFIG_INTR_REMAP");
-
-	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-		" and x2apic\n");
+		      " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
 #endif
 
 	return;
 }
-#endif /* CONFIG_X86_X2APIC */
+
 
 #ifdef CONFIG_X86_64
 /*
@@ -1428,7 +1466,6 @@ static int __init detect_init_APIC(void)
 	}
 
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-	boot_cpu_physical_apicid = 0;
 	return 0;
 }
 #else
@@ -1542,32 +1579,49 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
-	if (x2apic) {
+	unsigned int new_apicid;
+
+	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
 		return;
 	}
 
-	/*
-	 * If no local APIC can be found then set up a fake all
-	 * zeroes page to simulate the local APIC and another
-	 * one for the IO-APIC.
-	 */
+	/* If no local APIC can be found return early */
 	if (!smp_found_config && detect_init_APIC()) {
-		apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
-		apic_phys = __pa(apic_phys);
-	} else
+		/* lets NOP'ify apic operations */
+		pr_info("APIC: disable apic facility\n");
+		apic_disable();
+	} else {
 		apic_phys = mp_lapic_addr;
 
-	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-	apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
-				APIC_BASE, apic_phys);
+		/*
+		 * acpi lapic path already maps that address in
+		 * acpi_register_lapic_address()
+		 */
+		if (!acpi_lapic)
+			set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+
+		apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
+					APIC_BASE, apic_phys);
+	}
 
 	/*
 	 * Fetch the APIC ID of the BSP in case we have a
 	 * default configuration (or the MP table is broken).
 	 */
-	if (boot_cpu_physical_apicid == -1U)
-		boot_cpu_physical_apicid = read_apic_id();
+	new_apicid = read_apic_id();
+	if (boot_cpu_physical_apicid != new_apicid) {
+		boot_cpu_physical_apicid = new_apicid;
+		/*
+		 * yeah -- we lie about apic_version
+		 * in case if apic was disabled via boot option
+		 * but it's not a problem for SMP compiled kernel
+		 * since smp_sanity_check is prepared for such a case
+		 * and disable smp mode
+		 */
+		apic_version[new_apicid] =
+			 GET_APIC_VERSION(apic_read(APIC_LVR));
+	}
 }
 
 /*
@@ -1736,8 +1790,7 @@ void __init connect_bsp_APIC(void)
 		 */
 		apic_printk(APIC_VERBOSE, "leaving PIC mode, "
 				"enabling APIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x01, 0x23);
+		imcr_pic_to_apic();
 	}
 #endif
 	if (apic->enable_apic_mode)
@@ -1765,8 +1818,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 		 */
 		apic_printk(APIC_VERBOSE, "disabling APIC mode, "
 				"entering PIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x00, 0x23);
+		imcr_apic_to_pic();
 		return;
 	}
 #endif
@@ -1972,10 +2024,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	local_irq_save(flags);
 	disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
 	if (intr_remapping_enabled)
 		disable_intr_remapping();
-#endif
+
 	local_irq_restore(flags);
 	return 0;
 }
@@ -1985,42 +2037,34 @@ static int lapic_resume(struct sys_device *dev)
 	unsigned int l, h;
 	unsigned long flags;
 	int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
-	int ret;
+	int ret = 0;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	if (!apic_pm_state.active)
 		return 0;
 
 	local_irq_save(flags);
-	if (x2apic) {
+	if (intr_remapping_enabled) {
 		ioapic_entries = alloc_ioapic_entries();
 		if (!ioapic_entries) {
 			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto restore;
 		}
 
 		ret = save_IO_APIC_setup(ioapic_entries);
 		if (ret) {
 			WARN(1, "Saving IO-APIC state failed: %d\n", ret);
 			free_ioapic_entries(ioapic_entries);
-			return ret;
+			goto restore;
 		}
 
 		mask_IO_APIC_setup(ioapic_entries);
 		mask_8259A();
-		enable_x2apic();
 	}
-#else
-	if (!apic_pm_state.active)
-		return 0;
 
-	local_irq_save(flags);
-	if (x2apic)
+	if (x2apic_mode)
 		enable_x2apic();
-#endif
-
 	else {
 		/*
 		 * Make sure the APICBASE points to the right address
@@ -2058,21 +2102,16 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-#ifdef CONFIG_INTR_REMAP
-	if (intr_remapping_enabled)
-		reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (x2apic) {
+	if (intr_remapping_enabled) {
+		reenable_intr_remapping(x2apic_mode);
 		unmask_8259A();
 		restore_IO_APIC_setup(ioapic_entries);
 		free_ioapic_entries(ioapic_entries);
 	}
-#endif
-
+restore:
 	local_irq_restore(flags);
 
-
-	return 0;
+	return ret;
 }
 
 /*
@@ -2120,31 +2159,14 @@ static void apic_pm_activate(void) { }
 #endif	/* CONFIG_PM */
 
 #ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
 	u16 *bios_cpu_apicid;
 	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
 
-	/*
-	 * there is not this kind of box with AMD CPU yet.
-	 * Some AMD box with quadcore cpu and 8 sockets apicid
-	 * will be [4, 0x23] or [8, 0x27] could be thought to
-	 * vsmp box still need checking...
-	 */
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
-		return 0;
-
 	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
@@ -2180,18 +2202,67 @@ __cpuinit int apic_is_clustered_box(void)
 			++zeros;
 	}
 
-	/* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
-	 * not guaranteed to be synced between boards
-	 */
-	if (is_vsmp_box() && clusters > 1)
+	return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+	if (multi)
+		return 0;
+	pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
+	multi = 1;
+	return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+	{
+		.callback = set_multi,
+		.ident = "IBM System Summit2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+		},
+	},
+	{}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+	if (multi_checked)
+		return;
+
+	dmi_check_system(multi_dmi_table);
+	multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+	dmi_check_multi();
+	if (multi)
 		return 1;
 
+	if (!is_vsmp_box())
+		return 0;
+
 	/*
-	 * If clusters > 2, then should be multi-chassis.
-	 * May have to revisit this when multi-core + hyperthreaded CPUs come
-	 * out, but AFAIK this will work even for them.
+	 * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+	 * not guaranteed to be synced between boards
 	 */
-	return (clusters > 2);
+	if (apic_cluster_num() > 1)
+		return 1;
+
+	return 0;
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 306e5e88fb6..d0c99abc26c 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -161,7 +161,7 @@ static int flat_apic_id_registered(void)
 
 static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
 {
-	return hard_smp_processor_id() >> index_msb;
+	return initial_apic_id >> index_msb;
 }
 
 struct apic apic_flat =  {
@@ -235,7 +235,7 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	 * regardless of how many processors are present (x86_64 ES7000
 	 * is an example).
 	 */
-	if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
 		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "system APIC only can use physical flat");
 		return 1;
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 30294777557..69328ac8de9 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -145,7 +145,7 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
 {
 	unsigned long vect = 0, psaival = 0;
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 30da617d18e..1946fac42ab 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -59,6 +59,7 @@
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
+#include <asm/hw_irq.h>
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_irq.h>
 
@@ -129,12 +130,9 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+static struct irq_pin_list *get_one_free_irq_2_pin(int node)
 {
 	struct irq_pin_list *pin;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
 
@@ -148,9 +146,6 @@ struct irq_cfg {
 	unsigned move_cleanup_count;
 	u8 vector;
 	u8 move_in_progress : 1;
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-	u8 move_desc_pending : 1;
-#endif
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -212,12 +207,9 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 	return cfg;
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+static struct irq_cfg *get_one_free_irq_cfg(int node)
 {
 	struct irq_cfg *cfg;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
 	if (cfg) {
@@ -238,13 +230,13 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu)
 	return cfg;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int cpu)
+int arch_init_chip_data(struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 
 	cfg = desc->chip_data;
 	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(cpu);
+		desc->chip_data = get_one_free_irq_cfg(node);
 		if (!desc->chip_data) {
 			printk(KERN_ERR "can not alloc irq_cfg\n");
 			BUG_ON(1);
@@ -254,10 +246,9 @@ int arch_init_chip_data(struct irq_desc *desc, int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-
+/* for move_irq_desc */
 static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
 {
 	struct irq_pin_list *old_entry, *head, *tail, *entry;
 
@@ -266,7 +257,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	if (!old_entry)
 		return;
 
-	entry = get_one_free_irq_2_pin(cpu);
+	entry = get_one_free_irq_2_pin(node);
 	if (!entry)
 		return;
 
@@ -276,7 +267,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	tail		= entry;
 	old_entry	= old_entry->next;
 	while (old_entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			entry = head;
 			while (entry) {
@@ -316,12 +307,12 @@ static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
 }
 
 void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int cpu)
+				 struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 	struct irq_cfg *old_cfg;
 
-	cfg = get_one_free_irq_cfg(cpu);
+	cfg = get_one_free_irq_cfg(node);
 
 	if (!cfg)
 		return;
@@ -332,7 +323,7 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc,
 
 	memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
 
-	init_copy_irq_2_pin(old_cfg, cfg, cpu);
+	init_copy_irq_2_pin(old_cfg, cfg, node);
 }
 
 static void free_irq_cfg(struct irq_cfg *old_cfg)
@@ -356,19 +347,7 @@ void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
 		old_desc->chip_data = NULL;
 	}
 }
-
-static void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg = desc->chip_data;
-
-	if (!cfg->move_in_progress) {
-		/* it means that domain is not changed */
-		if (!cpumask_intersects(desc->affinity, mask))
-			cfg->move_desc_pending = 1;
-	}
-}
-#endif
+/* end for move_irq_desc */
 
 #else
 static struct irq_cfg *irq_cfg(unsigned int irq)
@@ -378,13 +357,6 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 
 #endif
 
-#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
-static inline void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-}
-#endif
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -518,132 +490,18 @@ static void ioapic_mask_entry(int apic, int pin)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-		cfg->move_cleanup_count = 0;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			cfg->move_cleanup_count++;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
-		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
-	cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-		unsigned int reg;
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		/*
-		 * With interrupt-remapping, destination information comes
-		 * from interrupt-remapping table entry.
-		 */
-		if (!irq_remapped(irq))
-			io_apic_write(apic, 0x11 + pin*2, dest);
-		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
-		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-		if (!entry->next)
-			break;
-		entry = entry->next;
-	}
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned int irq;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return BAD_APICID;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
-		return BAD_APICID;
-
-	/* check that before desc->addinity get updated */
-	set_extra_move_desc(desc, mask);
-
-	cpumask_copy(desc->affinity, mask);
-
-	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static void
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	dest = set_desc_affinity(desc, mask);
-	if (dest != BAD_APICID) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
-	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list *entry;
 
 	entry = cfg->irq_2_pin;
 	if (!entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
 					apic, pin);
@@ -663,7 +521,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 		entry = entry->next;
 	}
 
-	entry->next = get_one_free_irq_2_pin(cpu);
+	entry->next = get_one_free_irq_2_pin(node);
 	entry = entry->next;
 	entry->apic = apic;
 	entry->pin = pin;
@@ -672,7 +530,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 /*
  * Reroute an IRQ to a different pin.
  */
-static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
 				      int oldapic, int oldpin,
 				      int newapic, int newpin)
 {
@@ -692,7 +550,7 @@ static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
 
 	/* why? call replace before add? */
 	if (!replaced)
-		add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+		add_pin_to_irq_node(cfg, node, newapic, newpin);
 }
 
 static inline void io_apic_modify_irq(struct irq_cfg *cfg,
@@ -850,7 +708,6 @@ static int __init ioapic_pirq_setup(char *str)
 __setup("pirq=", ioapic_pirq_setup);
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_INTR_REMAP
 struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 {
 	int apic;
@@ -948,20 +805,6 @@ int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 	return 0;
 }
 
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries)
-
-{
-	/*
-	 * for now plain restore of previous settings.
-	 * TBD: In the case of OS enabling interrupt-remapping,
-	 * IO-APIC RTE's need to be setup to point to interrupt-remapping
-	 * table entries. for now, do a plain restore, and wait for
-	 * the setup_IO_APIC_irqs() to do proper initialization.
-	 */
-	restore_IO_APIC_setup(ioapic_entries);
-}
-
 void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic;
@@ -971,7 +814,6 @@ void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 
 	kfree(ioapic_entries);
 }
-#endif
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -1032,54 +874,6 @@ static int __init find_isa_irq_apic(int irq, int type)
 	return -1;
 }
 
-/*
- * Find a specific PCI IRQ entry.
- * Not an __init, possibly needed by modules
- */
-static int pin_2_irq(int idx, int apic, int pin);
-
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
-{
-	int apic, i, best_guess = -1;
-
-	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
-		bus, slot, pin);
-	if (test_bit(bus, mp_bus_not_pci)) {
-		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
-		return -1;
-	}
-	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].srcbus;
-
-		for (apic = 0; apic < nr_ioapics; apic++)
-			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
-			    mp_irqs[i].dstapic == MP_APIC_ALL)
-				break;
-
-		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].irqtype &&
-		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
-
-			if (!(apic || IO_APIC_IRQ(irq)))
-				continue;
-
-			if (pin == (mp_irqs[i].srcbusirq & 3))
-				return irq;
-			/*
-			 * Use the first all-but-pin matching entry as a
-			 * best-guess fuzzy result for broken mptables.
-			 */
-			if (best_guess < 0)
-				best_guess = irq;
-		}
-	}
-	return best_guess;
-}
-
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 /*
  * EISA Edge/Level control register, ELCR
@@ -1298,6 +1092,64 @@ static int pin_2_irq(int idx, int apic, int pin)
 	return irq;
 }
 
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int apic, i, best_guess = -1;
+
+	apic_printk(APIC_DEBUG,
+		    "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+		    bus, slot, pin);
+	if (test_bit(bus, mp_bus_not_pci)) {
+		apic_printk(APIC_VERBOSE,
+			    "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+		return -1;
+	}
+	for (i = 0; i < mp_irq_entries; i++) {
+		int lbus = mp_irqs[i].srcbus;
+
+		for (apic = 0; apic < nr_ioapics; apic++)
+			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+			    mp_irqs[i].dstapic == MP_APIC_ALL)
+				break;
+
+		if (!test_bit(lbus, mp_bus_not_pci) &&
+		    !mp_irqs[i].irqtype &&
+		    (bus == lbus) &&
+		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+			if (!(apic || IO_APIC_IRQ(irq)))
+				continue;
+
+			if (pin == (mp_irqs[i].srcbusirq & 3)) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				return irq;
+			}
+			/*
+			 * Use the first all-but-pin matching entry as a
+			 * best-guess fuzzy result for broken mptables.
+			 */
+			if (best_guess < 0) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				best_guess = irq;
+			}
+		}
+	}
+	return best_guess;
+}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
 void lock_vector_lock(void)
 {
 	/* Used to the online set of cpus does not change
@@ -1628,58 +1480,70 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 	ioapic_write_entry(apic_id, pin, entry);
 }
 
+static struct {
+	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
+	int apic_id = 0, pin, idx, irq;
 	int notcon = 0;
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
-	for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
-		for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
-
-			idx = find_irq_entry(apic_id, pin, mp_INT);
-			if (idx == -1) {
-				if (!notcon) {
-					notcon = 1;
-					apic_printk(APIC_VERBOSE,
-						KERN_DEBUG " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				} else
-					apic_printk(APIC_VERBOSE, " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				continue;
-			}
-			if (notcon) {
-				apic_printk(APIC_VERBOSE,
-					" (apicid-pin) not connected\n");
-				notcon = 0;
-			}
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		apic_id = mp_find_ioapic(0);
+		if (apic_id < 0)
+			apic_id = 0;
+	}
+#endif
 
-			irq = pin_2_irq(idx, apic_id, pin);
+	for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+		idx = find_irq_entry(apic_id, pin, mp_INT);
+		if (idx == -1) {
+			if (!notcon) {
+				notcon = 1;
+				apic_printk(APIC_VERBOSE,
+					KERN_DEBUG " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			} else
+				apic_printk(APIC_VERBOSE, " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			continue;
+		}
+		if (notcon) {
+			apic_printk(APIC_VERBOSE,
+				" (apicid-pin) not connected\n");
+			notcon = 0;
+		}
 
-			/*
-			 * Skip the timer IRQ if there's a quirk handler
-			 * installed and if it returns 1:
-			 */
-			if (apic->multi_timer_check &&
-					apic->multi_timer_check(apic_id, irq))
-				continue;
+		irq = pin_2_irq(idx, apic_id, pin);
 
-			desc = irq_to_desc_alloc_cpu(irq, cpu);
-			if (!desc) {
-				printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-				continue;
-			}
-			cfg = desc->chip_data;
-			add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
+		/*
+		 * Skip the timer IRQ if there's a quirk handler
+		 * installed and if it returns 1:
+		 */
+		if (apic->multi_timer_check &&
+				apic->multi_timer_check(apic_id, irq))
+			continue;
 
-			setup_IO_APIC_irq(apic_id, pin, irq, desc,
-					irq_trigger(idx), irq_polarity(idx));
+		desc = irq_to_desc_alloc_node(irq, node);
+		if (!desc) {
+			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+			continue;
 		}
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, apic_id, pin);
+		/*
+		 * don't mark it in pin_programmed, so later acpi could
+		 * set it correctly when irq < 16
+		 */
+		setup_IO_APIC_irq(apic_id, pin, irq, desc,
+				irq_trigger(idx), irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1869,7 +1733,7 @@ __apicdebuginit(void) print_APIC_bitfield(int base)
 
 __apicdebuginit(void) print_local_APIC(void *dummy)
 {
-	unsigned int v, ver, maxlvt;
+	unsigned int i, v, ver, maxlvt;
 	u64 icr;
 
 	if (apic_verbosity == APIC_QUIET)
@@ -1957,6 +1821,18 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
 	v = apic_read(APIC_TDCR);
 	printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		v = apic_read(APIC_EFEAT);
+		maxlvt = (v >> 16) & 0xff;
+		printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
+		v = apic_read(APIC_ECTRL);
+		printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
+		for (i = 0; i < maxlvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
+		}
+	}
 	printk("\n");
 }
 
@@ -2005,6 +1881,11 @@ __apicdebuginit(void) print_PIC(void)
 __apicdebuginit(int) print_all_ICs(void)
 {
 	print_PIC();
+
+	/* don't print out if apic is not there */
+	if (!cpu_has_apic || disable_apic)
+		return 0;
+
 	print_all_local_APICs();
 	print_IO_APIC();
 
@@ -2360,6 +2241,118 @@ static int ioapic_retrigger_irq(unsigned int irq)
  */
 
 #ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	cpumask_var_t cleanup_mask;
+
+	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+		unsigned int i;
+		cfg->move_cleanup_count = 0;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			cfg->move_cleanup_count++;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+	} else {
+		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		free_cpumask_var(cleanup_mask);
+	}
+	cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+	u8 vector = cfg->vector;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+		unsigned int reg;
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		/*
+		 * With interrupt-remapping, destination information comes
+		 * from interrupt-remapping table entry.
+		 */
+		if (!irq_remapped(irq))
+			io_apic_write(apic, 0x11 + pin*2, dest);
+		reg = io_apic_read(apic, 0x10 + pin*2);
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+		reg |= vector;
+		io_apic_modify(apic, 0x10 + pin*2, reg);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned int irq;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return BAD_APICID;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+	if (assign_irq_vector(irq, cfg, mask))
+		return BAD_APICID;
+
+	cpumask_copy(desc->affinity, mask);
+
+	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int dest;
+	unsigned int irq;
+	int ret = -1;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	dest = set_desc_affinity(desc, mask);
+	if (dest != BAD_APICID) {
+		/* Only the high 8 bits are valid. */
+		dest = SET_APIC_LOGICAL_ID(dest);
+		__target_IO_APIC_irq(irq, dest, cfg);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+
+	return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	return set_ioapic_affinity_irq_desc(desc, mask);
+}
 
 #ifdef CONFIG_INTR_REMAP
 
@@ -2374,26 +2367,25 @@ static int ioapic_retrigger_irq(unsigned int irq)
  * Real vector that is used for interrupting cpu will be coming from
  * the interrupt-remapping table entry.
  */
-static void
+static int
 migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 {
 	struct irq_cfg *cfg;
 	struct irte irte;
 	unsigned int dest;
 	unsigned int irq;
+	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return;
+		return ret;
 
 	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return;
+		return ret;
 
 	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return;
-
-	set_extra_move_desc(desc, mask);
+		return ret;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2409,27 +2401,30 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 		send_cleanup_vector(cfg);
 
 	cpumask_copy(desc->affinity, mask);
+
+	return 0;
 }
 
 /*
  * Migrates the IRQ destination in the process context.
  */
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 					    const struct cpumask *mask)
 {
-	migrate_ioapic_irq_desc(desc, mask);
+	return migrate_ioapic_irq_desc(desc, mask);
 }
-static void set_ir_ioapic_affinity_irq(unsigned int irq,
+static int set_ir_ioapic_affinity_irq(unsigned int irq,
 				       const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	set_ir_ioapic_affinity_irq_desc(desc, mask);
+	return set_ir_ioapic_affinity_irq_desc(desc, mask);
 }
 #else
-static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 						   const struct cpumask *mask)
 {
+	return 0;
 }
 #endif
 
@@ -2491,86 +2486,19 @@ static void irq_complete_move(struct irq_desc **descp)
 	struct irq_cfg *cfg = desc->chip_data;
 	unsigned vector, me;
 
-	if (likely(!cfg->move_in_progress)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		if (likely(!cfg->move_desc_pending))
-			return;
-
-		/* domain has not changed, but affinity did */
-		me = smp_processor_id();
-		if (cpumask_test_cpu(me, desc->affinity)) {
-			*descp = desc = move_irq_desc(desc, me);
-			/* get the new one */
-			cfg = desc->chip_data;
-			cfg->move_desc_pending = 0;
-		}
-#endif
+	if (likely(!cfg->move_in_progress))
 		return;
-	}
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
 
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		*descp = desc = move_irq_desc(desc, me);
-		/* get the new one */
-		cfg = desc->chip_data;
-#endif
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
-	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		io_apic_eoi(apic, pin);
-		entry = entry->next;
-	}
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#ifdef CONFIG_X86_X2APIC
-static void ack_x2apic_level(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	ack_x2APIC_irq();
-	eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
-	ack_x2APIC_irq();
-}
-#endif
-
 static void ack_apic_edge(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -2634,9 +2562,6 @@ static void ack_apic_level(unsigned int irq)
 	 */
 	ack_APIC_irq();
 
-	if (irq_remapped(irq))
-		eoi_ioapic_irq(desc);
-
 	/* Now we can move and renable the irq */
 	if (unlikely(do_unmask_irq)) {
 		/* Only migrate the irq if the ack has been received.
@@ -2683,22 +2608,50 @@ static void ack_apic_level(unsigned int irq)
 }
 
 #ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		io_apic_eoi(apic, pin);
+		entry = entry->next;
+	}
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int irq;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__eoi_ioapic_irq(irq, cfg);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
 static void ir_ack_apic_edge(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_edge(irq);
-#endif
-       return ack_apic_edge(irq);
+	ack_APIC_irq();
 }
 
 static void ir_ack_apic_level(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_level(irq);
-#endif
-       return ack_apic_level(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	ack_APIC_irq();
+	eoi_ioapic_irq(desc);
 }
 #endif /* CONFIG_INTR_REMAP */
 
@@ -2903,7 +2856,7 @@ static inline void __init check_timer(void)
 {
 	struct irq_desc *desc = irq_to_desc(0);
 	struct irq_cfg *cfg = desc->chip_data;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2969,7 +2922,7 @@ static inline void __init check_timer(void)
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
 		if (no_pin1) {
-			add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
 			/* for edge trigger, setup_IO_APIC_irq already
@@ -3006,7 +2959,7 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
@@ -3218,14 +3171,13 @@ static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
 {
 	/* Allocate an unused irq */
 	unsigned int irq;
 	unsigned int new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new = NULL;
-	int cpu = boot_cpu_id;
 	struct irq_desc *desc_new = NULL;
 
 	irq = 0;
@@ -3234,7 +3186,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 	spin_lock_irqsave(&vector_lock, flags);
 	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_cpu(new, cpu);
+		desc_new = irq_to_desc_alloc_node(new, node);
 		if (!desc_new) {
 			printk(KERN_INFO "can not get irq_desc for %d\n", new);
 			continue;
@@ -3243,6 +3195,9 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 		if (cfg_new->vector != 0)
 			continue;
+
+		desc_new = move_irq_desc(desc_new, node);
+
 		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
 			irq = new;
 		break;
@@ -3260,11 +3215,12 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 int create_irq(void)
 {
+	int node = cpu_to_node(boot_cpu_id);
 	unsigned int irq_want;
 	int irq;
 
 	irq_want = nr_irqs_gsi;
-	irq = create_irq_nr(irq_want);
+	irq = create_irq_nr(irq_want, node);
 
 	if (irq == 0)
 		irq = -1;
@@ -3366,7 +3322,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 }
 
 #ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3375,7 +3331,7 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3387,13 +3343,15 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg_desc(desc, &msg);
+
+	return 0;
 }
 #ifdef CONFIG_INTR_REMAP
 /*
  * Migrate the MSI irq to another cpumask. This migration is
  * done in the process context using interrupt-remapping hardware.
  */
-static void
+static int
 ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -3402,11 +3360,11 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
-		return;
+		return -1;
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	irte.vector = cfg->vector;
 	irte.dest_id = IRTE_DEST(dest);
@@ -3423,6 +3381,8 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	 */
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
+
+	return 0;
 }
 
 #endif
@@ -3518,15 +3478,17 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
 	int index = 0;
+	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
+	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = create_irq_nr(irq_want);
+		irq = create_irq_nr(irq_want, node);
 		if (irq == 0)
 			return -1;
 		irq_want = irq + 1;
@@ -3576,7 +3538,7 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3585,7 +3547,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3597,6 +3559,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3630,7 +3594,7 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3639,7 +3603,7 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3651,6 +3615,8 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	hpet_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3707,7 +3673,7 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3715,11 +3681,13 @@ static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
 	target_ht_irq(irq, dest, cfg->vector);
+
+	return 0;
 }
 
 #endif
@@ -3794,6 +3762,8 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	unsigned long flags;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	cfg = irq_cfg(irq);
 
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
@@ -3807,15 +3777,13 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
-	entry->vector = cfg->vector;
-	entry->delivery_mode = apic->irq_delivery_mode;
-	entry->dest_mode = apic->irq_dest_mode;
-	entry->polarity = 0;
-	entry->trigger = 0;
-	entry->mask = 0;
-	entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+	entry->vector		= cfg->vector;
+	entry->delivery_mode	= apic->irq_delivery_mode;
+	entry->dest_mode	= apic->irq_dest_mode;
+	entry->polarity		= 0;
+	entry->trigger		= 0;
+	entry->mask		= 0;
+	entry->dest		= apic->cpu_mask_to_apicid(eligible_cpu);
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
@@ -3833,10 +3801,10 @@ void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
 	entry->mask = 1;
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
@@ -3900,6 +3868,71 @@ int __init arch_probe_nr_irqs(void)
 }
 #endif
 
+static int __io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	struct irq_desc *desc;
+	struct irq_cfg *cfg;
+	int node;
+	int ioapic, pin;
+	int trigger, polarity;
+
+	ioapic = irq_attr->ioapic;
+	if (!IO_APIC_IRQ(irq)) {
+		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+			ioapic);
+		return -EINVAL;
+	}
+
+	if (dev)
+		node = dev_to_node(dev);
+	else
+		node = cpu_to_node(boot_cpu_id);
+
+	desc = irq_to_desc_alloc_node(irq, node);
+	if (!desc) {
+		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+		return 0;
+	}
+
+	pin = irq_attr->ioapic_pin;
+	trigger = irq_attr->trigger;
+	polarity = irq_attr->polarity;
+
+	/*
+	 * IRQs < 16 are already in the irq_2_pin[] map
+	 */
+	if (irq >= NR_IRQS_LEGACY) {
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, ioapic, pin);
+	}
+
+	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+
+	return 0;
+}
+
+int io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int ioapic, pin;
+	/*
+	 * Avoid pin reprogramming.  PRTs typically include entries
+	 * with redundant pin->gsi mappings (but unique PCI devices);
+	 * we only program the IOAPIC on the first.
+	 */
+	ioapic = irq_attr->ioapic;
+	pin = irq_attr->ioapic_pin;
+	if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+		pr_debug("Pin %d-%d already programmed\n",
+			 mp_ioapics[ioapic].apicid, pin);
+		return 0;
+	}
+	set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
+
+	return __io_apic_set_pci_routing(dev, irq, irq_attr);
+}
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
@@ -3980,6 +4013,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 
 	return apic_id;
 }
+#endif
 
 int __init io_apic_get_version(int ioapic)
 {
@@ -3992,39 +4026,6 @@ int __init io_apic_get_version(int ioapic)
 
 	return reg_01.bits.version;
 }
-#endif
-
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
-{
-	struct irq_desc *desc;
-	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
-
-	if (!IO_APIC_IRQ(irq)) {
-		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
-			ioapic);
-		return -EINVAL;
-	}
-
-	desc = irq_to_desc_alloc_cpu(irq, cpu);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
-		return 0;
-	}
-
-	/*
-	 * IRQs < 16 are already in the irq_2_pin[] map
-	 */
-	if (irq >= NR_IRQS_LEGACY) {
-		cfg = desc->chip_data;
-		add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
-	}
-
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
-
-	return 0;
-}
-
 
 int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 {
@@ -4055,51 +4056,44 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 #ifdef CONFIG_SMP
 void __init setup_ioapic_dest(void)
 {
-	int pin, ioapic, irq, irq_entry;
+	int pin, ioapic = 0, irq, irq_entry;
 	struct irq_desc *desc;
-	struct irq_cfg *cfg;
 	const struct cpumask *mask;
 
 	if (skip_ioapic_setup == 1)
 		return;
 
-	for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
-		for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
-			irq_entry = find_irq_entry(ioapic, pin, mp_INT);
-			if (irq_entry == -1)
-				continue;
-			irq = pin_2_irq(irq_entry, ioapic, pin);
-
-			/* setup_IO_APIC_irqs could fail to get vector for some device
-			 * when you have too many devices, because at that time only boot
-			 * cpu is online.
-			 */
-			desc = irq_to_desc(irq);
-			cfg = desc->chip_data;
-			if (!cfg->vector) {
-				setup_IO_APIC_irq(ioapic, pin, irq, desc,
-						  irq_trigger(irq_entry),
-						  irq_polarity(irq_entry));
-				continue;
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		ioapic = mp_find_ioapic(0);
+		if (ioapic < 0)
+			ioapic = 0;
+	}
+#endif
 
-			}
+	for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+		irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+		if (irq_entry == -1)
+			continue;
+		irq = pin_2_irq(irq_entry, ioapic, pin);
 
-			/*
-			 * Honour affinities which have been set in early boot
-			 */
-			if (desc->status &
-			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = desc->affinity;
-			else
-				mask = apic->target_cpus();
+		desc = irq_to_desc(irq);
 
-			if (intr_remapping_enabled)
-				set_ir_ioapic_affinity_irq_desc(desc, mask);
-			else
-				set_ioapic_affinity_irq_desc(desc, mask);
-		}
+		/*
+		 * Honour affinities which have been set in early boot
+		 */
+		if (desc->status &
+		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+			mask = desc->affinity;
+		else
+			mask = apic->target_cpus();
 
+		if (intr_remapping_enabled)
+			set_ir_ioapic_affinity_irq_desc(desc, mask);
+		else
+			set_ioapic_affinity_irq_desc(desc, mask);
 	}
+
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index ce4fbfa315a..a691302dc3f 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -104,7 +104,7 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
-static void report_broken_nmi(int cpu, int *prev_nmi_count)
+static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
 {
 	printk(KERN_CONT "\n");
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 01eda2ac65e..440a8bccd91 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -160,7 +160,6 @@ extern struct apic apic_summit;
 extern struct apic apic_bigsmp;
 extern struct apic apic_es7000;
 extern struct apic apic_es7000_cluster;
-extern struct apic apic_default;
 
 struct apic *apic = &apic_default;
 EXPORT_SYMBOL_GPL(apic);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 1783652bb0e..bc3e880f9b8 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,7 +50,7 @@ static struct apic *apic_probe[] __initdata = {
 void __init default_setup_apic_routing(void)
 {
 #ifdef CONFIG_X86_X2APIC
-	if (x2apic && (apic != &apic_x2apic_phys &&
+	if (x2apic_mode && (apic != &apic_x2apic_phys &&
 #ifdef CONFIG_X86_UV
 		       apic != &apic_x2apic_uv_x &&
 #endif
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9cfe1f415d8..344eee4ac0a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -173,13 +173,6 @@ static inline int is_WPEG(struct rio_detail *rio){
 		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
 static const struct cpumask *summit_target_cpus(void)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 4a903e2f0d1..8e4cbb255c3 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -10,7 +10,7 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 
-DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
 
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 2bda6935297..ef0ae207a7c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -105,7 +105,7 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 #ifdef CONFIG_SMP
 	unsigned long val;
@@ -562,7 +562,7 @@ void __init uv_system_init(void)
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
-	int max_pnode = 0;
+	int gnode_extra, max_pnode = 0;
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask;
 
@@ -574,6 +574,13 @@ void __init uv_system_init(void)
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
+	pnode_mask = (1 << n_val) - 1;
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
+	gnode_upper = ((unsigned long)gnode_extra  << m_val);
+	printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
+			n_val, m_val, gnode_upper, gnode_extra);
+
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
 	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
@@ -583,15 +590,18 @@ void __init uv_system_init(void)
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_blade_info);
 
 	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
 
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
 	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_node_to_blade);
 	memset(uv_node_to_blade, 255, bytes);
 
 	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
 	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_cpu_to_blade);
 	memset(uv_cpu_to_blade, 255, bytes);
 
 	blade = 0;
@@ -607,11 +617,6 @@ void __init uv_system_init(void)
 		}
 	}
 
-	pnode_mask = (1 << n_val) - 1;
-	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	gnode_upper = (((unsigned long)node_id.s.node_id) &
-		       ~((1 << n_val) - 1)) << m_val;
-
 	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
 			    &sn_coherency_id, &sn_region_size);
@@ -634,6 +639,7 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
+		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
 		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 5a6aa1c1162..1a830cbd701 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -146,4 +146,5 @@ void foo(void)
 	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
+	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 }
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index e72f062fb4b..898ecc47e12 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -125,6 +125,7 @@ int main(void)
 	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
+	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 
 	BLANK();
 	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7e4a459daa6..e5b27d8f1b4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
+#include <asm/pci-direct.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/numa_64.h>
@@ -272,7 +273,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	int cpu = smp_processor_id();
 	int node;
-	unsigned apicid = hard_smp_processor_id();
+	unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	node = c->phys_proc_id;
 	if (apicid_to_node[apicid] != NUMA_NO_NODE)
@@ -351,6 +352,15 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 		    (c->x86_model == 8 && c->x86_mask >= 8))
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+	/* check CPU config space for extended APIC ID */
+	if (c->x86 >= 0xf) {
+		unsigned int val;
+		val = read_pci_config(0, 24, 0, 0x68);
+		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
+			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+	}
+#endif
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f60409081cb..3ffdcfa9abd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -300,7 +300,8 @@ static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_set[NCAPINTS] __cpuinitdata;
 
 void load_percpu_segment(int cpu)
 {
@@ -769,6 +770,12 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	if (this_cpu->c_identify)
 		this_cpu->c_identify(c);
 
+	/* Clear/Set all flags overriden by options, after probe */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 #ifdef CONFIG_X86_64
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 #endif
@@ -814,6 +821,16 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 #endif
 
 	init_hypervisor(c);
+
+	/*
+	 * Clear/Set all flags overriden by options, need do it
+	 * before following smp all cpus cap AND.
+	 */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
@@ -826,10 +843,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
 	}
 
-	/* Clear all flags overriden by options */
-	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] &= ~cleared_cpu_caps[i];
-
 #ifdef CONFIG_X86_MCE
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 46e29ab96c6..6b2a52dd040 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -32,9 +32,7 @@
 
 static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
 static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
-static DEFINE_PER_CPU(unsigned, cpu_modelflag);
 static DEFINE_PER_CPU(int, cpu_priv_count);
-static DEFINE_PER_CPU(unsigned, cpu_model);
 
 static DEFINE_MUTEX(cpu_debug_lock);
 
@@ -80,302 +78,102 @@ static struct cpu_file_base cpu_file[] = {
 	{ "value",	CPU_REG_ALL,	1	},
 };
 
-/* Intel Registers Range */
-static struct cpu_debug_range cpu_intel_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	CPU_INTEL_ALL		},
-	{ 0x00000006, 0x00000007, CPU_MONITOR,	CPU_CX_AT_XE		},
-	{ 0x00000010, 0x00000010, CPU_TIME,	CPU_INTEL_ALL		},
-	{ 0x00000011, 0x00000013, CPU_PMC,	CPU_INTEL_PENTIUM	},
-	{ 0x00000017, 0x00000017, CPU_PLATFORM,	CPU_PX_CX_AT_XE		},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	CPU_P6_CX_AT_XE		},
-
-	{ 0x0000002A, 0x0000002A, CPU_POWERON,	CPU_PX_CX_AT_XE		},
-	{ 0x0000002B, 0x0000002B, CPU_POWERON,	CPU_INTEL_XEON		},
-	{ 0x0000002C, 0x0000002C, CPU_FREQ,	CPU_INTEL_XEON		},
-	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	CPU_CX_AT_XE		},
-
-	{ 0x00000040, 0x00000043, CPU_LBRANCH,	CPU_PM_CX_AT_XE		},
-	{ 0x00000044, 0x00000047, CPU_LBRANCH,	CPU_PM_CO_AT		},
-	{ 0x00000060, 0x00000063, CPU_LBRANCH,	CPU_C2_AT		},
-	{ 0x00000064, 0x00000067, CPU_LBRANCH,	CPU_INTEL_ATOM		},
-
-	{ 0x00000079, 0x00000079, CPU_BIOS,	CPU_P6_CX_AT_XE		},
-	{ 0x00000088, 0x0000008A, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x0000008B, 0x0000008B, CPU_BIOS,	CPU_P6_CX_AT_XE		},
-	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	CPU_INTEL_XEON		},
-
-	{ 0x000000C1, 0x000000C2, CPU_PMC,	CPU_P6_CX_AT		},
-	{ 0x000000CD, 0x000000CD, CPU_FREQ,	CPU_CX_AT		},
-	{ 0x000000E7, 0x000000E8, CPU_PERF,	CPU_CX_AT		},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	CPU_P6_CX_XE		},
-
-	{ 0x00000116, 0x00000116, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x00000118, 0x00000118, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x00000119, 0x00000119, CPU_CACHE,	CPU_INTEL_PX		},
-	{ 0x0000011A, 0x0000011B, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x0000011E, 0x0000011E, CPU_CACHE,	CPU_PX_CX_AT		},
-
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	CPU_P6_CX_AT_XE		},
-	{ 0x00000179, 0x0000017A, CPU_MC,	CPU_PX_CX_AT_XE		},
-	{ 0x0000017B, 0x0000017B, CPU_MC,	CPU_P6_XE		},
-	{ 0x00000186, 0x00000187, CPU_PMC,	CPU_P6_CX_AT		},
-	{ 0x00000198, 0x00000199, CPU_PERF,	CPU_PM_CX_AT_XE		},
-	{ 0x0000019A, 0x0000019A, CPU_TIME,	CPU_PM_CX_AT_XE		},
-	{ 0x0000019B, 0x0000019D, CPU_THERM,	CPU_PM_CX_AT_XE		},
-	{ 0x000001A0, 0x000001A0, CPU_MISC,	CPU_PM_CX_AT_XE		},
-
-	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	CPU_PM_CX_AT		},
-	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	CPU_CX_AT_XE		},
-	{ 0x000001DA, 0x000001DA, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000001DB, 0x000001DB, CPU_LBRANCH,	CPU_P6_XE		},
-	{ 0x000001DC, 0x000001DC, CPU_LBRANCH,	CPU_INTEL_P6		},
-	{ 0x000001DD, 0x000001DE, CPU_LBRANCH,	CPU_PX_CX_AT_XE		},
-	{ 0x000001E0, 0x000001E0, CPU_LBRANCH,	CPU_INTEL_P6		},
-
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000277, 0x00000277, CPU_PAT,	CPU_C2_AT_XE		},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	CPU_P6_CX_XE		},
-
-	{ 0x00000300, 0x00000308, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x00000309, 0x0000030B, CPU_PMC,	CPU_C2_AT_XE		},
-	{ 0x0000030C, 0x00000311, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x00000345, 0x00000345, CPU_PMC,	CPU_C2_AT		},
-	{ 0x00000360, 0x00000371, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x0000038D, 0x00000390, CPU_PMC,	CPU_C2_AT		},
-	{ 0x000003A0, 0x000003BE, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003C0, 0x000003CD, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003E0, 0x000003E1, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003F0, 0x000003F0, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003F1, 0x000003F1, CPU_PMC,	CPU_C2_AT_XE		},
-	{ 0x000003F2, 0x000003F2, CPU_PMC,	CPU_INTEL_XEON		},
-
-	{ 0x00000400, 0x00000402, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000403, 0x00000403, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000404, 0x00000406, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000407, 0x00000407, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000408, 0x0000040A, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x0000040B, 0x0000040B, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x0000040C, 0x0000040E, CPU_MC,	CPU_PM_CX_XE		},
-	{ 0x0000040F, 0x0000040F, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000410, 0x00000412, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000413, 0x00000417, CPU_MC,	CPU_CX_AT_XE		},
-	{ 0x00000480, 0x0000048B, CPU_VMX,	CPU_CX_AT_XE		},
-
-	{ 0x00000600, 0x00000600, CPU_DEBUG,	CPU_PM_CX_AT_XE		},
-	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	CPU_INTEL_XEON		},
-
-	{ 0x000107CC, 0x000107D3, CPU_PMC,	CPU_INTEL_XEON_MP	},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	CPU_INTEL_XEON		},
-	{ 0xC0000081, 0xC0000082, CPU_CALL,	CPU_INTEL_XEON		},
-	{ 0xC0000084, 0xC0000084, CPU_CALL,	CPU_INTEL_XEON		},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	CPU_INTEL_XEON		},
+/* CPU Registers Range */
+static struct cpu_debug_range cpu_reg_range[] = {
+	{ 0x00000000, 0x00000001, CPU_MC,	},
+	{ 0x00000006, 0x00000007, CPU_MONITOR,	},
+	{ 0x00000010, 0x00000010, CPU_TIME,	},
+	{ 0x00000011, 0x00000013, CPU_PMC,	},
+	{ 0x00000017, 0x00000017, CPU_PLATFORM,	},
+	{ 0x0000001B, 0x0000001B, CPU_APIC,	},
+	{ 0x0000002A, 0x0000002B, CPU_POWERON,	},
+	{ 0x0000002C, 0x0000002C, CPU_FREQ,	},
+	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	},
+	{ 0x00000040, 0x00000047, CPU_LBRANCH,	},
+	{ 0x00000060, 0x00000067, CPU_LBRANCH,	},
+	{ 0x00000079, 0x00000079, CPU_BIOS,	},
+	{ 0x00000088, 0x0000008A, CPU_CACHE,	},
+	{ 0x0000008B, 0x0000008B, CPU_BIOS,	},
+	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	},
+	{ 0x000000C1, 0x000000C4, CPU_PMC,	},
+	{ 0x000000CD, 0x000000CD, CPU_FREQ,	},
+	{ 0x000000E7, 0x000000E8, CPU_PERF,	},
+	{ 0x000000FE, 0x000000FE, CPU_MTRR,	},
+
+	{ 0x00000116, 0x0000011E, CPU_CACHE,	},
+	{ 0x00000174, 0x00000176, CPU_SYSENTER,	},
+	{ 0x00000179, 0x0000017B, CPU_MC,	},
+	{ 0x00000186, 0x00000189, CPU_PMC,	},
+	{ 0x00000198, 0x00000199, CPU_PERF,	},
+	{ 0x0000019A, 0x0000019A, CPU_TIME,	},
+	{ 0x0000019B, 0x0000019D, CPU_THERM,	},
+	{ 0x000001A0, 0x000001A0, CPU_MISC,	},
+	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	},
+	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	},
+	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	},
+	{ 0x000001DA, 0x000001E0, CPU_LBRANCH,	},
+
+	{ 0x00000200, 0x0000020F, CPU_MTRR,	},
+	{ 0x00000250, 0x00000250, CPU_MTRR,	},
+	{ 0x00000258, 0x00000259, CPU_MTRR,	},
+	{ 0x00000268, 0x0000026F, CPU_MTRR,	},
+	{ 0x00000277, 0x00000277, CPU_PAT,	},
+	{ 0x000002FF, 0x000002FF, CPU_MTRR,	},
+
+	{ 0x00000300, 0x00000311, CPU_PMC,	},
+	{ 0x00000345, 0x00000345, CPU_PMC,	},
+	{ 0x00000360, 0x00000371, CPU_PMC,	},
+	{ 0x0000038D, 0x00000390, CPU_PMC,	},
+	{ 0x000003A0, 0x000003BE, CPU_PMC,	},
+	{ 0x000003C0, 0x000003CD, CPU_PMC,	},
+	{ 0x000003E0, 0x000003E1, CPU_PMC,	},
+	{ 0x000003F0, 0x000003F2, CPU_PMC,	},
+
+	{ 0x00000400, 0x00000417, CPU_MC,	},
+	{ 0x00000480, 0x0000048B, CPU_VMX,	},
+
+	{ 0x00000600, 0x00000600, CPU_DEBUG,	},
+	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	},
+	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	},
+
+	{ 0x000107CC, 0x000107D3, CPU_PMC,	},
+
+	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	},
+	{ 0xC0000081, 0xC0000084, CPU_CALL,	},
+	{ 0xC0000100, 0xC0000102, CPU_BASE,	},
+	{ 0xC0000103, 0xC0000103, CPU_TIME,	},
+
+	{ 0xC0010000, 0xC0010007, CPU_PMC,	},
+	{ 0xC0010010, 0xC0010010, CPU_CONF,	},
+	{ 0xC0010015, 0xC0010015, CPU_CONF,	},
+	{ 0xC0010016, 0xC001001A, CPU_MTRR,	},
+	{ 0xC001001D, 0xC001001D, CPU_MTRR,	},
+	{ 0xC001001F, 0xC001001F, CPU_CONF,	},
+	{ 0xC0010030, 0xC0010035, CPU_BIOS,	},
+	{ 0xC0010044, 0xC0010048, CPU_MC,	},
+	{ 0xC0010050, 0xC0010056, CPU_SMM,	},
+	{ 0xC0010058, 0xC0010058, CPU_CONF,	},
+	{ 0xC0010060, 0xC0010060, CPU_CACHE,	},
+	{ 0xC0010061, 0xC0010068, CPU_SMM,	},
+	{ 0xC0010069, 0xC001006B, CPU_SMM,	},
+	{ 0xC0010070, 0xC0010071, CPU_SMM,	},
+	{ 0xC0010111, 0xC0010113, CPU_SMM,	},
+	{ 0xC0010114, 0xC0010118, CPU_SVM,	},
+	{ 0xC0010140, 0xC0010141, CPU_OSVM,	},
+	{ 0xC0011022, 0xC0011023, CPU_CONF,	},
 };
 
-/* AMD Registers Range */
-static struct cpu_debug_range cpu_amd_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	CPU_K10_PLUS,		},
-	{ 0x00000010, 0x00000010, CPU_TIME,	CPU_K8_PLUS,		},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	CPU_K8_PLUS,		},
-	{ 0x0000002A, 0x0000002A, CPU_POWERON,	CPU_K7_PLUS		},
-	{ 0x0000008B, 0x0000008B, CPU_VER,	CPU_K8_PLUS		},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	CPU_K8_PLUS,		},
-
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	CPU_K8_PLUS,		},
-	{ 0x00000179, 0x0000017B, CPU_MC,	CPU_K8_PLUS,		},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	CPU_K8_PLUS,		},
-	{ 0x000001DB, 0x000001DE, CPU_LBRANCH,	CPU_K8_PLUS,		},
-
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000277, 0x00000277, CPU_PAT,	CPU_K8_PLUS,		},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	CPU_K8_PLUS,		},
-
-	{ 0x00000400, 0x00000413, CPU_MC,	CPU_K8_PLUS,		},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	CPU_AMD_ALL,		},
-	{ 0xC0000081, 0xC0000084, CPU_CALL,	CPU_K8_PLUS,		},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	CPU_K8_PLUS,		},
-	{ 0xC0000103, 0xC0000103, CPU_TIME,	CPU_K10_PLUS,		},
-
-	{ 0xC0010000, 0xC0010007, CPU_PMC,	CPU_K8_PLUS,		},
-	{ 0xC0010010, 0xC0010010, CPU_CONF,	CPU_K7_PLUS,		},
-	{ 0xC0010015, 0xC0010015, CPU_CONF,	CPU_K7_PLUS,		},
-	{ 0xC0010016, 0xC001001A, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0xC001001D, 0xC001001D, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0xC001001F, 0xC001001F, CPU_CONF,	CPU_K8_PLUS,		},
-	{ 0xC0010030, 0xC0010035, CPU_BIOS,	CPU_K8_PLUS,		},
-	{ 0xC0010044, 0xC0010048, CPU_MC,	CPU_K8_PLUS,		},
-	{ 0xC0010050, 0xC0010056, CPU_SMM,	CPU_K0F_PLUS,		},
-	{ 0xC0010058, 0xC0010058, CPU_CONF,	CPU_K10_PLUS,		},
-	{ 0xC0010060, 0xC0010060, CPU_CACHE,	CPU_AMD_11,		},
-	{ 0xC0010061, 0xC0010068, CPU_SMM,	CPU_K10_PLUS,		},
-	{ 0xC0010069, 0xC001006B, CPU_SMM,	CPU_AMD_11,		},
-	{ 0xC0010070, 0xC0010071, CPU_SMM,	CPU_K10_PLUS,		},
-	{ 0xC0010111, 0xC0010113, CPU_SMM,	CPU_K8_PLUS,		},
-	{ 0xC0010114, 0xC0010118, CPU_SVM,	CPU_K10_PLUS,		},
-	{ 0xC0010140, 0xC0010141, CPU_OSVM,	CPU_K10_PLUS,		},
-	{ 0xC0011022, 0xC0011023, CPU_CONF,	CPU_K10_PLUS,		},
-};
-
-
-/* Intel */
-static int get_intel_modelflag(unsigned model)
-{
-	int flag;
-
-	switch (model) {
-	case 0x0501:
-	case 0x0502:
-	case 0x0504:
-		flag = CPU_INTEL_PENTIUM;
-		break;
-	case 0x0601:
-	case 0x0603:
-	case 0x0605:
-	case 0x0607:
-	case 0x0608:
-	case 0x060A:
-	case 0x060B:
-		flag = CPU_INTEL_P6;
-		break;
-	case 0x0609:
-	case 0x060D:
-		flag = CPU_INTEL_PENTIUM_M;
-		break;
-	case 0x060E:
-		flag = CPU_INTEL_CORE;
-		break;
-	case 0x060F:
-	case 0x0617:
-		flag = CPU_INTEL_CORE2;
-		break;
-	case 0x061C:
-		flag = CPU_INTEL_ATOM;
-		break;
-	case 0x0F00:
-	case 0x0F01:
-	case 0x0F02:
-	case 0x0F03:
-	case 0x0F04:
-		flag = CPU_INTEL_XEON_P4;
-		break;
-	case 0x0F06:
-		flag = CPU_INTEL_XEON_MP;
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-/* AMD */
-static int get_amd_modelflag(unsigned model)
-{
-	int flag;
-
-	switch (model >> 8) {
-	case 0x6:
-		flag = CPU_AMD_K6;
-		break;
-	case 0x7:
-		flag = CPU_AMD_K7;
-		break;
-	case 0x8:
-		flag = CPU_AMD_K8;
-		break;
-	case 0xf:
-		flag = CPU_AMD_0F;
-		break;
-	case 0x10:
-		flag = CPU_AMD_10;
-		break;
-	case 0x11:
-		flag = CPU_AMD_11;
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-static int get_cpu_modelflag(unsigned cpu)
-{
-	int flag;
-
-	flag = per_cpu(cpu_model, cpu);
-
-	switch (flag >> 16) {
-	case X86_VENDOR_INTEL:
-		flag = get_intel_modelflag(flag);
-		break;
-	case X86_VENDOR_AMD:
-		flag = get_amd_modelflag(flag & 0xffff);
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-static int get_cpu_range_count(unsigned cpu)
-{
-	int index;
-
-	switch (per_cpu(cpu_model, cpu) >> 16) {
-	case X86_VENDOR_INTEL:
-		index = ARRAY_SIZE(cpu_intel_range);
-		break;
-	case X86_VENDOR_AMD:
-		index = ARRAY_SIZE(cpu_amd_range);
-		break;
-	default:
-		index = 0;
-		break;
-	}
-
-	return index;
-}
-
 static int is_typeflag_valid(unsigned cpu, unsigned flag)
 {
-	unsigned vendor, modelflag;
-	int i, index;
+	int i;
 
 	/* Standard Registers should be always valid */
 	if (flag >= CPU_TSS)
 		return 1;
 
-	modelflag = per_cpu(cpu_modelflag, cpu);
-	vendor = per_cpu(cpu_model, cpu) >> 16;
-	index = get_cpu_range_count(cpu);
-
-	for (i = 0; i < index; i++) {
-		switch (vendor) {
-		case X86_VENDOR_INTEL:
-			if ((cpu_intel_range[i].model & modelflag) &&
-			    (cpu_intel_range[i].flag & flag))
-				return 1;
-			break;
-		case X86_VENDOR_AMD:
-			if ((cpu_amd_range[i].model & modelflag) &&
-			    (cpu_amd_range[i].flag & flag))
-				return 1;
-			break;
-		}
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
+		if (cpu_reg_range[i].flag == flag)
+			return 1;
 	}
 
 	/* Invalid */
@@ -385,26 +183,11 @@ static int is_typeflag_valid(unsigned cpu, unsigned flag)
 static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
 			      int index, unsigned flag)
 {
-	unsigned modelflag;
-
-	modelflag = per_cpu(cpu_modelflag, cpu);
-	*max = 0;
-	switch (per_cpu(cpu_model, cpu) >> 16) {
-	case X86_VENDOR_INTEL:
-		if ((cpu_intel_range[index].model & modelflag) &&
-		    (cpu_intel_range[index].flag & flag)) {
-			*min = cpu_intel_range[index].min;
-			*max = cpu_intel_range[index].max;
-		}
-		break;
-	case X86_VENDOR_AMD:
-		if ((cpu_amd_range[index].model & modelflag) &&
-		    (cpu_amd_range[index].flag & flag)) {
-			*min = cpu_amd_range[index].min;
-			*max = cpu_amd_range[index].max;
-		}
-		break;
-	}
+	if (cpu_reg_range[index].flag == flag) {
+		*min = cpu_reg_range[index].min;
+		*max = cpu_reg_range[index].max;
+	} else
+		*max = 0;
 
 	return *max;
 }
@@ -434,7 +217,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
 	unsigned msr, msr_min, msr_max;
 	struct cpu_private *priv;
 	u32 low, high;
-	int i, range;
+	int i;
 
 	if (seq) {
 		priv = seq->private;
@@ -446,9 +229,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
 		}
 	}
 
-	range = get_cpu_range_count(cpu);
-
-	for (i = 0; i < range; i++) {
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
 		if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
 			continue;
 
@@ -588,8 +369,20 @@ static void print_apic(void *arg)
 	seq_printf(seq, " TMICT\t\t: %08x\n",  apic_read(APIC_TMICT));
 	seq_printf(seq, " TMCCT\t\t: %08x\n",  apic_read(APIC_TMCCT));
 	seq_printf(seq, " TDCR\t\t: %08x\n",  apic_read(APIC_TDCR));
-#endif /* CONFIG_X86_LOCAL_APIC */
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		unsigned int i, v, maxeilvt;
+
+		v = apic_read(APIC_EFEAT);
+		maxeilvt = (v >> 16) & 0xff;
+		seq_printf(seq, " EFEAT\t\t: %08x\n", v);
+		seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
 
+		for (i = 0; i < maxeilvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
+		}
+	}
+#endif /* CONFIG_X86_LOCAL_APIC */
 	seq_printf(seq, "\n MSR\t:\n");
 }
 
@@ -788,13 +581,11 @@ static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
 {
 	struct dentry *cpu_dentry = NULL;
 	unsigned reg, reg_min, reg_max;
-	int i, range, err = 0;
+	int i, err = 0;
 	char reg_dir[12];
 	u32 low, high;
 
-	range = get_cpu_range_count(cpu);
-
-	for (i = 0; i < range; i++) {
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
 		if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
 				   cpu_base[type].flag))
 			continue;
@@ -850,10 +641,6 @@ static int cpu_init_cpu(void)
 		cpui = &cpu_data(cpu);
 		if (!cpu_has(cpui, X86_FEATURE_MSR))
 			continue;
-		per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) |
-					   (cpui->x86 << 8) |
-					   (cpui->x86_model));
-		per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu);
 
 		sprintf(cpu_dir, "cpu%d", cpu);
 		cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index 52c83987547..f138c6c389b 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -220,11 +220,14 @@ config X86_LONGHAUL
 	  If in doubt, say N.
 
 config X86_E_POWERSAVER
-	tristate "VIA C7 Enhanced PowerSaver"
+	tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
 	select CPU_FREQ_TABLE
-	depends on X86_32
+	depends on X86_32 && EXPERIMENTAL
 	help
-	  This adds the CPUFreq driver for VIA C7 processors.
+	  This adds the CPUFreq driver for VIA C7 processors.  However, this driver
+	  does not have any safeguards to prevent operating the CPU out of spec
+	  and is thus considered dangerous.  Please use the regular ACPI cpufreq
+	  driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
 
 	  If in doubt, say N.
 
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 54b6de2cd94..ae9b503220c 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -90,11 +90,7 @@ static int check_est_cpu(unsigned int cpuid)
 {
 	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
 
-	if (cpu->x86_vendor != X86_VENDOR_INTEL ||
-	    !cpu_has(cpu, X86_FEATURE_EST))
-		return 0;
-
-	return 1;
+	return cpu_has(cpu, X86_FEATURE_EST);
 }
 
 static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
@@ -550,7 +546,7 @@ static int __init acpi_cpufreq_early_init(void)
 		return -ENOMEM;
 	}
 	for_each_possible_cpu(i) {
-		if (!alloc_cpumask_var_node(
+		if (!zalloc_cpumask_var_node(
 			&per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
 			GFP_KERNEL, cpu_to_node(i))) {
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index a8363e5be4e..d47c775eb0a 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -322,7 +322,7 @@ static int powernow_acpi_init(void)
 		goto err0;
 	}
 
-	if (!alloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
+	if (!zalloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
 								GFP_KERNEL)) {
 		retval = -ENOMEM;
 		goto err05;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index f6b32d11235..cf52215d9eb 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -835,7 +835,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
 	struct cpufreq_frequency_table *powernow_table;
 	int ret_val = -ENODEV;
-	acpi_integer space_id;
+	acpi_integer control, status;
 
 	if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
 		dprintk("register performance failed: bad ACPI data\n");
@@ -848,12 +848,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		goto err_out;
 	}
 
-	space_id = data->acpi_data.control_register.space_id;
-	if ((space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
-		(space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
+	control = data->acpi_data.control_register.space_id;
+	status = data->acpi_data.status_register.space_id;
+
+	if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
+	    (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
 		dprintk("Invalid control/status registers (%x - %x)\n",
-			data->acpi_data.control_register.space_id,
-			space_id);
+			control, status);
 		goto err_out;
 	}
 
@@ -886,7 +887,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
 
-	if (!alloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
 		printk(KERN_ERR PFX
 				"unable to alloc powernow_k8_data cpumask\n");
 		ret_val = -ENOMEM;
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index c9f1fdc0283..55c831ed71c 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -471,7 +471,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 
 	if (unlikely(!alloc_cpumask_var(&saved_mask, GFP_KERNEL)))
 		return -ENOMEM;
-	if (unlikely(!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
+	if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
 		free_cpumask_var(saved_mask);
 		return -ENOMEM;
 	}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7437fa133c0..daed39ba261 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -229,12 +229,12 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 }
 #endif
 
-static void __cpuinit srat_detect_node(void)
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	unsigned node;
 	int cpu = smp_processor_id();
-	int apicid = hard_smp_processor_id();
+	int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
@@ -400,7 +400,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	}
 
 	/* Work around errata */
-	srat_detect_node();
+	srat_detect_node(c);
 
 	if (cpu_has(c, X86_FEATURE_VMX))
 		detect_vmx_virtcap(c);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 483eda96e10..789efe217e1 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,6 +17,7 @@
 
 #include <asm/processor.h>
 #include <asm/smp.h>
+#include <asm/k8.h>
 
 #define LVL_1_INST	1
 #define LVL_1_DATA	2
@@ -159,14 +160,6 @@ struct _cpuid4_info_regs {
 	unsigned long can_disable;
 };
 
-#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
-static struct pci_device_id k8_nb_id[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
-	{}
-};
-#endif
-
 unsigned short			num_cache_leaves;
 
 /* AMD doesn't have CPUID4. Emulate it here to report the same
@@ -207,10 +200,17 @@ union l3_cache {
 };
 
 static const unsigned short __cpuinitconst assocs[] = {
-	[1] = 1, [2] = 2, [4] = 4, [6] = 8,
-	[8] = 16, [0xa] = 32, [0xb] = 48,
+	[1] = 1,
+	[2] = 2,
+	[4] = 4,
+	[6] = 8,
+	[8] = 16,
+	[0xa] = 32,
+	[0xb] = 48,
 	[0xc] = 64,
-	[0xf] = 0xffff // ??
+	[0xd] = 96,
+	[0xe] = 128,
+	[0xf] = 0xffff /* fully associative - no way to show this currently */
 };
 
 static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
@@ -271,7 +271,8 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
 	if (leaf == 3)
-		eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+		eax->split.num_threads_sharing =
+			current_cpu_data.x86_max_cores - 1;
 	else
 		eax->split.num_threads_sharing = 0;
 	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
@@ -291,6 +292,14 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 {
 	if (index < 3)
 		return;
+
+	if (boot_cpu_data.x86 == 0x11)
+		return;
+
+	/* see erratum #382 */
+	if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+		return;
+
 	this_leaf->can_disable = 1;
 }
 
@@ -696,97 +705,75 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
 #define to_object(k)	container_of(k, struct _index_kobject, kobj)
 #define to_attr(a)	container_of(a, struct _cache_attr, attr)
 
-#ifdef CONFIG_PCI
-static struct pci_dev *get_k8_northbridge(int node)
-{
-	struct pci_dev *dev = NULL;
-	int i;
-
-	for (i = 0; i <= node; i++) {
-		do {
-			dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-			if (!dev)
-				break;
-		} while (!pci_match_id(&k8_nb_id[0], dev));
-		if (!dev)
-			break;
-	}
-	return dev;
-}
-#else
-static struct pci_dev *get_k8_northbridge(int node)
-{
-	return NULL;
-}
-#endif
-
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+				  unsigned int index)
 {
-	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
-	int node = cpu_to_node(cpumask_first(mask));
-	struct pci_dev *dev = NULL;
-	ssize_t ret = 0;
-	int i;
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = cpu_to_node(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned int reg = 0;
 
 	if (!this_leaf->can_disable)
-		return sprintf(buf, "Feature not enabled\n");
-
-	dev = get_k8_northbridge(node);
-	if (!dev) {
-		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
 		return -EINVAL;
-	}
 
-	for (i = 0; i < 2; i++) {
-		unsigned int reg;
+	if (!dev)
+		return -EINVAL;
 
-		pci_read_config_dword(dev, 0x1BC + i * 4, &reg);
+	pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+	return sprintf(buf, "%x\n", reg);
+}
 
-		ret += sprintf(buf, "%sEntry: %d\n", buf, i);
-		ret += sprintf(buf, "%sReads:  %s\tNew Entries: %s\n",  
-			buf,
-			reg & 0x80000000 ? "Disabled" : "Allowed",
-			reg & 0x40000000 ? "Disabled" : "Allowed");
-		ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
-			buf, (reg & 0x30000) >> 16, reg & 0xfff);
-	}
-	return ret;
+#define SHOW_CACHE_DISABLE(index)					\
+static ssize_t								\
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)  	\
+{									\
+	return show_cache_disable(this_leaf, buf, index);		\
 }
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
 
-static ssize_t
-store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
-		    size_t count)
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+	const char *buf, size_t count, unsigned int index)
 {
-	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
-	int node = cpu_to_node(cpumask_first(mask));
-	struct pci_dev *dev = NULL;
-	unsigned int ret, index, val;
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = cpu_to_node(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned long val = 0;
+	unsigned int scrubber = 0;
 
 	if (!this_leaf->can_disable)
-		return 0;
-
-	if (strlen(buf) > 15)
 		return -EINVAL;
 
-	ret = sscanf(buf, "%x %x", &index, &val);
-	if (ret != 2)
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!dev)
 		return -EINVAL;
-	if (index > 1)
+
+	if (strict_strtoul(buf, 10, &val) < 0)
 		return -EINVAL;
 
 	val |= 0xc0000000;
-	dev = get_k8_northbridge(node);
-	if (!dev) {
-		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
-		return -EINVAL;
-	}
+
+	pci_read_config_dword(dev, 0x58, &scrubber);
+	scrubber &= ~0x1f000000;
+	pci_write_config_dword(dev, 0x58, scrubber);
 
 	pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
 	wbinvd();
 	pci_write_config_dword(dev, 0x1BC + index * 4, val);
+	return count;
+}
 
-	return 1;
+#define STORE_CACHE_DISABLE(index)					\
+static ssize_t								\
+store_cache_disable_##index(struct _cpuid4_info *this_leaf,	     	\
+			    const char *buf, size_t count)		\
+{									\
+	return store_cache_disable(this_leaf, buf, count, index);	\
 }
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
 
 struct _cache_attr {
 	struct attribute attr;
@@ -808,7 +795,10 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+		show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+		show_cache_disable_1, store_cache_disable_1);
 
 static struct attribute * default_attrs[] = {
 	&type.attr,
@@ -820,7 +810,8 @@ static struct attribute * default_attrs[] = {
 	&size.attr,
 	&shared_cpu_map.attr,
 	&shared_cpu_list.attr,
-	&cache_disable.attr,
+	&cache_disable_0.attr,
+	&cache_disable_1.attr,
 	NULL
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 6fb0b359d2a..09dd1d414fc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -1163,7 +1163,7 @@ static __init int mce_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
-	alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
+	zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
 
 	err = mce_init_banks();
 	if (err)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index cef3ee30744..65a0fceedcd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -15,7 +15,6 @@
 #include <asm/hw_irq.h>
 #include <asm/idle.h>
 #include <asm/therm_throt.h>
-#include <asm/apic.h>
 
 asmlinkage void smp_thermal_interrupt(void)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index ce0fe4b5c04..1d584a18a50 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -808,7 +808,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 
 	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
 		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
+	rdmsr(MSR_MTRRdefType, def, dummy);
 	def &= 0xff;
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
@@ -1003,7 +1003,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	 */
 	if (!is_cpu(INTEL) || disable_mtrr_trim)
 		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
+	rdmsr(MSR_MTRRdefType, def, dummy);
 	def &= 0xff;
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d21d4fb161f..0543f69f0b2 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -20,9 +20,9 @@ struct fixed_range_block {
 };
 
 static struct fixed_range_block fixed_range_blocks[] = {
-	{ MTRRfix64K_00000_MSR, 1 }, /* one  64k MTRR  */
-	{ MTRRfix16K_80000_MSR, 2 }, /* two  16k MTRRs */
-	{ MTRRfix4K_C0000_MSR,  8 }, /* eight 4k MTRRs */
+	{ MSR_MTRRfix64K_00000, 1 }, /* one  64k MTRR  */
+	{ MSR_MTRRfix16K_80000, 2 }, /* two  16k MTRRs */
+	{ MSR_MTRRfix4K_C0000,  8 }, /* eight 4k MTRRs */
 	{}
 };
 
@@ -194,12 +194,12 @@ get_fixed_ranges(mtrr_type * frs)
 
 	k8_check_syscfg_dram_mod_en();
 
-	rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
+	rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]);
 
 	for (i = 0; i < 2; i++)
-		rdmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], p[3 + i * 2]);
+		rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]);
 	for (i = 0; i < 8; i++)
-		rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
+		rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]);
 }
 
 void mtrr_save_fixed_ranges(void *info)
@@ -310,7 +310,7 @@ void __init get_mtrr_state(void)
 
 	vrs = mtrr_state.var_ranges;
 
-	rdmsr(MTRRcap_MSR, lo, dummy);
+	rdmsr(MSR_MTRRcap, lo, dummy);
 	mtrr_state.have_fixed = (lo >> 8) & 1;
 
 	for (i = 0; i < num_var_ranges; i++)
@@ -318,7 +318,7 @@ void __init get_mtrr_state(void)
 	if (mtrr_state.have_fixed)
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 
-	rdmsr(MTRRdefType_MSR, lo, dummy);
+	rdmsr(MSR_MTRRdefType, lo, dummy);
 	mtrr_state.def_type = (lo & 0xff);
 	mtrr_state.enabled = (lo & 0xc00) >> 10;
 
@@ -583,10 +583,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	__flush_tlb();
 
 	/*  Save MTRR state */
-	rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+	rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
 
 	/*  Disable MTRRs, and set the default type to uncached  */
-	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi);
+	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
@@ -595,7 +595,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
-	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
 		
 	/*  Enable caches  */
 	write_cr0(read_cr0() & 0xbfffffff);
@@ -707,7 +707,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i
 static int generic_have_wrcomb(void)
 {
 	unsigned long config, dummy;
-	rdmsr(MTRRcap_MSR, config, dummy);
+	rdmsr(MSR_MTRRcap, config, dummy);
 	return (config & (1 << 10));
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 03cda01f57c..8fc248b5aea 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -104,7 +104,7 @@ static void __init set_num_var_ranges(void)
 	unsigned long config = 0, dummy;
 
 	if (use_intel()) {
-		rdmsr(MTRRcap_MSR, config, dummy);
+		rdmsr(MSR_MTRRcap, config, dummy);
 	} else if (is_cpu(AMD))
 		config = 2;
 	else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 77f67f7b347..7538b767f20 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -5,21 +5,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 
-#define MTRRcap_MSR     0x0fe
-#define MTRRdefType_MSR 0x2ff
-
-#define MTRRfix64K_00000_MSR 0x250
-#define MTRRfix16K_80000_MSR 0x258
-#define MTRRfix16K_A0000_MSR 0x259
-#define MTRRfix4K_C0000_MSR 0x268
-#define MTRRfix4K_C8000_MSR 0x269
-#define MTRRfix4K_D0000_MSR 0x26a
-#define MTRRfix4K_D8000_MSR 0x26b
-#define MTRRfix4K_E0000_MSR 0x26c
-#define MTRRfix4K_E8000_MSR 0x26d
-#define MTRRfix4K_F0000_MSR 0x26e
-#define MTRRfix4K_F8000_MSR 0x26f
-
 #define MTRR_CHANGE_MASK_FIXED     0x01
 #define MTRR_CHANGE_MASK_VARIABLE  0x02
 #define MTRR_CHANGE_MASK_DEFTYPE   0x04
diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c
index 7f7e2753685..1f5fb1588d1 100644
--- a/arch/x86/kernel/cpu/mtrr/state.c
+++ b/arch/x86/kernel/cpu/mtrr/state.c
@@ -35,7 +35,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt)
 
 		if (use_intel())
 			/*  Save MTRR state */
-			rdmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+			rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
 		else
 			/* Cyrix ARRs - everything else were excluded at the top */
 			ctxt->ccr3 = getCx86(CX86_CCR3);
@@ -46,7 +46,7 @@ void set_mtrr_cache_disable(struct set_mtrr_context *ctxt)
 {
 	if (use_intel())
 		/*  Disable MTRRs, and set the default type to uncached  */
-		mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo & 0xf300UL,
+		mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL,
 		      ctxt->deftype_hi);
 	else if (is_cpu(CYRIX))
 		/* Cyrix ARRs - everything else were excluded at the top */
@@ -64,7 +64,7 @@ void set_mtrr_done(struct set_mtrr_context *ctxt)
 		/*  Restore MTRRdefType  */
 		if (use_intel())
 			/* Intel (P6) standard MTRRs */
-			mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+			mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
 		else
 			/* Cyrix ARRs - everything else was excluded at the top */
 			setCx86(CX86_CCR3, ctxt->ccr3);
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 87b67e3a765..48bfe138603 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -19,45 +19,61 @@
  * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
-
-#include <asm/ds.h>
-
-#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/slab.h>
+#include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/kernel.h>
+#include <linux/trace_clock.h>
+
+#include <asm/ds.h>
 
+#include "ds_selftest.h"
 
 /*
- * The configuration for a particular DS hardware implementation.
+ * The configuration for a particular DS hardware implementation:
  */
 struct ds_configuration {
-	/* the name of the configuration */
-	const char *name;
-	/* the size of one pointer-typed field in the DS structure and
-	   in the BTS and PEBS buffers in bytes;
-	   this covers the first 8 DS fields related to buffer management. */
-	unsigned char  sizeof_field;
-	/* the size of a BTS/PEBS record in bytes */
-	unsigned char  sizeof_rec[2];
-	/* a series of bit-masks to control various features indexed
-	 * by enum ds_feature */
-	unsigned long ctl[dsf_ctl_max];
+	/* The name of the configuration: */
+	const char		*name;
+
+	/* The size of pointer-typed fields in DS, BTS, and PEBS: */
+	unsigned char		sizeof_ptr_field;
+
+	/* The size of a BTS/PEBS record in bytes: */
+	unsigned char		sizeof_rec[2];
+
+	/* The number of pebs counter reset values in the DS structure. */
+	unsigned char		nr_counter_reset;
+
+	/* Control bit-masks indexed by enum ds_feature: */
+	unsigned long		ctl[dsf_ctl_max];
 };
-static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
+static struct ds_configuration ds_cfg __read_mostly;
+
+
+/* Maximal size of a DS configuration: */
+#define MAX_SIZEOF_DS		0x80
 
-#define ds_cfg per_cpu(ds_cfg_array, smp_processor_id())
+/* Maximal size of a BTS record: */
+#define MAX_SIZEOF_BTS		(3 * 8)
 
-#define MAX_SIZEOF_DS (12 * 8)	/* maximal size of a DS configuration */
-#define MAX_SIZEOF_BTS (3 * 8)	/* maximal size of a BTS record */
-#define DS_ALIGNMENT (1 << 3)	/* BTS and PEBS buffer alignment */
+/* BTS and PEBS buffer alignment: */
+#define DS_ALIGNMENT		(1 << 3)
 
-#define BTS_CONTROL \
- (ds_cfg.ctl[dsf_bts] | ds_cfg.ctl[dsf_bts_kernel] | ds_cfg.ctl[dsf_bts_user] |\
-  ds_cfg.ctl[dsf_bts_overflow])
+/* Number of buffer pointers in DS: */
+#define NUM_DS_PTR_FIELDS	8
 
+/* Size of a pebs reset value in DS: */
+#define PEBS_RESET_FIELD_SIZE	8
+
+/* Mask of control bits in the DS MSR register: */
+#define BTS_CONTROL				  \
+	( ds_cfg.ctl[dsf_bts]			| \
+	  ds_cfg.ctl[dsf_bts_kernel]		| \
+	  ds_cfg.ctl[dsf_bts_user]		| \
+	  ds_cfg.ctl[dsf_bts_overflow] )
 
 /*
  * A BTS or PEBS tracer.
@@ -66,29 +82,36 @@ static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
  * to identify tracers.
  */
 struct ds_tracer {
-	/* the DS context (partially) owned by this tracer */
-	struct ds_context *context;
-	/* the buffer provided on ds_request() and its size in bytes */
-	void *buffer;
-	size_t size;
+	/* The DS context (partially) owned by this tracer. */
+	struct ds_context	*context;
+	/* The buffer provided on ds_request() and its size in bytes. */
+	void			*buffer;
+	size_t			size;
 };
 
 struct bts_tracer {
-	/* the common DS part */
-	struct ds_tracer ds;
-	/* the trace including the DS configuration */
-	struct bts_trace trace;
-	/* buffer overflow notification function */
-	bts_ovfl_callback_t ovfl;
+	/* The common DS part: */
+	struct ds_tracer	ds;
+
+	/* The trace including the DS configuration: */
+	struct bts_trace	trace;
+
+	/* Buffer overflow notification function: */
+	bts_ovfl_callback_t	ovfl;
+
+	/* Active flags affecting trace collection. */
+	unsigned int		flags;
 };
 
 struct pebs_tracer {
-	/* the common DS part */
-	struct ds_tracer ds;
-	/* the trace including the DS configuration */
-	struct pebs_trace trace;
-	/* buffer overflow notification function */
-	pebs_ovfl_callback_t ovfl;
+	/* The common DS part: */
+	struct ds_tracer	ds;
+
+	/* The trace including the DS configuration: */
+	struct pebs_trace	trace;
+
+	/* Buffer overflow notification function: */
+	pebs_ovfl_callback_t	ovfl;
 };
 
 /*
@@ -97,6 +120,7 @@ struct pebs_tracer {
  *
  * The DS configuration consists of the following fields; different
  * architetures vary in the size of those fields.
+ *
  * - double-word aligned base linear address of the BTS buffer
  * - write pointer into the BTS buffer
  * - end linear address of the BTS buffer (one byte beyond the end of
@@ -135,21 +159,22 @@ enum ds_field {
 };
 
 enum ds_qualifier {
-	ds_bts  = 0,
+	ds_bts = 0,
 	ds_pebs
 };
 
-static inline unsigned long ds_get(const unsigned char *base,
-				   enum ds_qualifier qual, enum ds_field field)
+static inline unsigned long
+ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field)
 {
-	base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
 	return *(unsigned long *)base;
 }
 
-static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
-			  enum ds_field field, unsigned long value)
+static inline void
+ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field,
+       unsigned long value)
 {
-	base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
 	(*(unsigned long *)base) = value;
 }
 
@@ -159,7 +184,6 @@ static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
  */
 static DEFINE_SPINLOCK(ds_lock);
 
-
 /*
  * We either support (system-wide) per-cpu or per-thread allocation.
  * We distinguish the two based on the task_struct pointer, where a
@@ -178,12 +202,28 @@ static DEFINE_SPINLOCK(ds_lock);
  */
 static atomic_t tracers = ATOMIC_INIT(0);
 
-static inline void get_tracer(struct task_struct *task)
+static inline int get_tracer(struct task_struct *task)
 {
-	if (task)
+	int error;
+
+	spin_lock_irq(&ds_lock);
+
+	if (task) {
+		error = -EPERM;
+		if (atomic_read(&tracers) < 0)
+			goto out;
 		atomic_inc(&tracers);
-	else
+	} else {
+		error = -EPERM;
+		if (atomic_read(&tracers) > 0)
+			goto out;
 		atomic_dec(&tracers);
+	}
+
+	error = 0;
+out:
+	spin_unlock_irq(&ds_lock);
+	return error;
 }
 
 static inline void put_tracer(struct task_struct *task)
@@ -194,14 +234,6 @@ static inline void put_tracer(struct task_struct *task)
 		atomic_inc(&tracers);
 }
 
-static inline int check_tracer(struct task_struct *task)
-{
-	return task ?
-		(atomic_read(&tracers) >= 0) :
-		(atomic_read(&tracers) <= 0);
-}
-
-
 /*
  * The DS context is either attached to a thread or to a cpu:
  * - in the former case, the thread_struct contains a pointer to the
@@ -213,61 +245,58 @@ static inline int check_tracer(struct task_struct *task)
  * deallocated when the last user puts the context.
  */
 struct ds_context {
-	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
-	unsigned char ds[MAX_SIZEOF_DS];
-	/* the owner of the BTS and PEBS configuration, respectively */
-	struct bts_tracer *bts_master;
-	struct pebs_tracer *pebs_master;
-	/* use count */
-	unsigned long count;
-	/* a pointer to the context location inside the thread_struct
-	 * or the per_cpu context array */
-	struct ds_context **this;
-	/* a pointer to the task owning this context, or NULL, if the
-	 * context is owned by a cpu */
-	struct task_struct *task;
-};
+	/* The DS configuration; goes into MSR_IA32_DS_AREA: */
+	unsigned char		ds[MAX_SIZEOF_DS];
+
+	/* The owner of the BTS and PEBS configuration, respectively: */
+	struct bts_tracer	*bts_master;
+	struct pebs_tracer	*pebs_master;
 
-static DEFINE_PER_CPU(struct ds_context *, system_context_array);
+	/* Use count: */
+	unsigned long		count;
 
-#define system_context per_cpu(system_context_array, smp_processor_id())
+	/* Pointer to the context pointer field: */
+	struct ds_context	**this;
+
+	/* The traced task; NULL for cpu tracing: */
+	struct task_struct	*task;
+
+	/* The traced cpu; only valid if task is NULL: */
+	int			cpu;
+};
 
+static DEFINE_PER_CPU(struct ds_context *, cpu_context);
 
-static inline struct ds_context *ds_get_context(struct task_struct *task)
+
+static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
 {
 	struct ds_context **p_context =
-		(task ? &task->thread.ds_ctx : &system_context);
+		(task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu));
 	struct ds_context *context = NULL;
 	struct ds_context *new_context = NULL;
-	unsigned long irq;
 
 	/* Chances are small that we already have a context. */
 	new_context = kzalloc(sizeof(*new_context), GFP_KERNEL);
 	if (!new_context)
 		return NULL;
 
-	spin_lock_irqsave(&ds_lock, irq);
+	spin_lock_irq(&ds_lock);
 
 	context = *p_context;
-	if (!context) {
+	if (likely(!context)) {
 		context = new_context;
 
 		context->this = p_context;
 		context->task = task;
+		context->cpu = cpu;
 		context->count = 0;
 
-		if (task)
-			set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-
-		if (!task || (task == current))
-			wrmsrl(MSR_IA32_DS_AREA, (unsigned long)context->ds);
-
 		*p_context = context;
 	}
 
 	context->count++;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
 	if (context != new_context)
 		kfree(new_context);
@@ -275,8 +304,9 @@ static inline struct ds_context *ds_get_context(struct task_struct *task)
 	return context;
 }
 
-static inline void ds_put_context(struct ds_context *context)
+static void ds_put_context(struct ds_context *context)
 {
+	struct task_struct *task;
 	unsigned long irq;
 
 	if (!context)
@@ -291,17 +321,55 @@ static inline void ds_put_context(struct ds_context *context)
 
 	*(context->this) = NULL;
 
-	if (context->task)
-		clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+	task = context->task;
+
+	if (task)
+		clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
 
-	if (!context->task || (context->task == current))
-		wrmsrl(MSR_IA32_DS_AREA, 0);
+	/*
+	 * We leave the (now dangling) pointer to the DS configuration in
+	 * the DS_AREA msr. This is as good or as bad as replacing it with
+	 * NULL - the hardware would crash if we enabled tracing.
+	 *
+	 * This saves us some problems with having to write an msr on a
+	 * different cpu while preventing others from doing the same for the
+	 * next context for that same cpu.
+	 */
 
 	spin_unlock_irqrestore(&ds_lock, irq);
 
+	/* The context might still be in use for context switching. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
 	kfree(context);
 }
 
+static void ds_install_ds_area(struct ds_context *context)
+{
+	unsigned long ds;
+
+	ds = (unsigned long)context->ds;
+
+	/*
+	 * There is a race between the bts master and the pebs master.
+	 *
+	 * The thread/cpu access is synchronized via get/put_cpu() for
+	 * task tracing and via wrmsr_on_cpu for cpu tracing.
+	 *
+	 * If bts and pebs are collected for the same task or same cpu,
+	 * the same confiuration is written twice.
+	 */
+	if (context->task) {
+		get_cpu();
+		if (context->task == current)
+			wrmsrl(MSR_IA32_DS_AREA, ds);
+		set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+		put_cpu();
+	} else
+		wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA,
+			     (u32)((u64)ds), (u32)((u64)ds >> 32));
+}
 
 /*
  * Call the tracer's callback on a buffer overflow.
@@ -332,9 +400,9 @@ static void ds_overflow(struct ds_context *context, enum ds_qualifier qual)
  * The remainder of any partially written record is zeroed out.
  *
  * context: the DS context
- * qual: the buffer type
- * record: the data to write
- * size: the size of the data
+ * qual:    the buffer type
+ * record:  the data to write
+ * size:    the size of the data
  */
 static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		    const void *record, size_t size)
@@ -349,14 +417,14 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		unsigned long write_size, adj_write_size;
 
 		/*
-		 * write as much as possible without producing an
+		 * Write as much as possible without producing an
 		 * overflow interrupt.
 		 *
-		 * interrupt_threshold must either be
+		 * Interrupt_threshold must either be
 		 * - bigger than absolute_maximum or
 		 * - point to a record between buffer_base and absolute_maximum
 		 *
-		 * index points to a valid record.
+		 * Index points to a valid record.
 		 */
 		base   = ds_get(context->ds, qual, ds_buffer_base);
 		index  = ds_get(context->ds, qual, ds_index);
@@ -365,8 +433,10 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 
 		write_end = min(end, int_th);
 
-		/* if we are already beyond the interrupt threshold,
-		 * we fill the entire buffer */
+		/*
+		 * If we are already beyond the interrupt threshold,
+		 * we fill the entire buffer.
+		 */
 		if (write_end <= index)
 			write_end = end;
 
@@ -383,7 +453,7 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
 		adj_write_size *= ds_cfg.sizeof_rec[qual];
 
-		/* zero out trailing bytes */
+		/* Zero out trailing bytes. */
 		memset((char *)index + write_size, 0,
 		       adj_write_size - write_size);
 		index += adj_write_size;
@@ -410,7 +480,7 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
  * Later architectures use 64bit pointers throughout, whereas earlier
  * architectures use 32bit pointers in 32bit mode.
  *
- * We compute the base address for the first 8 fields based on:
+ * We compute the base address for the fields based on:
  * - the field size stored in the DS configuration
  * - the relative field position
  *
@@ -431,23 +501,23 @@ enum bts_field {
 	bts_to,
 	bts_flags,
 
-	bts_qual = bts_from,
-	bts_jiffies = bts_to,
-	bts_pid = bts_flags,
+	bts_qual		= bts_from,
+	bts_clock		= bts_to,
+	bts_pid			= bts_flags,
 
-	bts_qual_mask = (bts_qual_max - 1),
-	bts_escape = ((unsigned long)-1 & ~bts_qual_mask)
+	bts_qual_mask		= (bts_qual_max - 1),
+	bts_escape		= ((unsigned long)-1 & ~bts_qual_mask)
 };
 
 static inline unsigned long bts_get(const char *base, enum bts_field field)
 {
-	base += (ds_cfg.sizeof_field * field);
+	base += (ds_cfg.sizeof_ptr_field * field);
 	return *(unsigned long *)base;
 }
 
 static inline void bts_set(char *base, enum bts_field field, unsigned long val)
 {
-	base += (ds_cfg.sizeof_field * field);;
+	base += (ds_cfg.sizeof_ptr_field * field);;
 	(*(unsigned long *)base) = val;
 }
 
@@ -463,8 +533,8 @@ static inline void bts_set(char *base, enum bts_field field, unsigned long val)
  *
  * return: bytes read/written on success; -Eerrno, otherwise
  */
-static int bts_read(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out)
+static int
+bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out)
 {
 	if (!tracer)
 		return -EINVAL;
@@ -478,8 +548,8 @@ static int bts_read(struct bts_tracer *tracer, const void *at,
 	memset(out, 0, sizeof(*out));
 	if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) {
 		out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask);
-		out->variant.timestamp.jiffies = bts_get(at, bts_jiffies);
-		out->variant.timestamp.pid = bts_get(at, bts_pid);
+		out->variant.event.clock = bts_get(at, bts_clock);
+		out->variant.event.pid = bts_get(at, bts_pid);
 	} else {
 		out->qualifier = bts_branch;
 		out->variant.lbr.from = bts_get(at, bts_from);
@@ -516,8 +586,8 @@ static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in)
 	case bts_task_arrives:
 	case bts_task_departs:
 		bts_set(raw, bts_qual, (bts_escape | in->qualifier));
-		bts_set(raw, bts_jiffies, in->variant.timestamp.jiffies);
-		bts_set(raw, bts_pid, in->variant.timestamp.pid);
+		bts_set(raw, bts_clock, in->variant.event.clock);
+		bts_set(raw, bts_pid, in->variant.event.pid);
 		break;
 	default:
 		return -EINVAL;
@@ -555,7 +625,8 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 			     unsigned int flags) {
 	unsigned long buffer, adj;
 
-	/* adjust the buffer address and size to meet alignment
+	/*
+	 * Adjust the buffer address and size to meet alignment
 	 * constraints:
 	 * - buffer is double-word aligned
 	 * - size is multiple of record size
@@ -577,9 +648,11 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 	trace->begin = (void *)buffer;
 	trace->top = trace->begin;
 	trace->end = (void *)(buffer + size);
-	/* The value for 'no threshold' is -1, which will set the
+	/*
+	 * The value for 'no threshold' is -1, which will set the
 	 * threshold outside of the buffer, just like we want it.
 	 */
+	ith *= ds_cfg.sizeof_rec[qual];
 	trace->ith = (void *)(buffer + size - ith);
 
 	trace->flags = flags;
@@ -588,18 +661,27 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 
 static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
 		      enum ds_qualifier qual, struct task_struct *task,
-		      void *base, size_t size, size_t th, unsigned int flags)
+		      int cpu, void *base, size_t size, size_t th)
 {
 	struct ds_context *context;
 	int error;
+	size_t req_size;
+
+	error = -EOPNOTSUPP;
+	if (!ds_cfg.sizeof_rec[qual])
+		goto out;
 
 	error = -EINVAL;
 	if (!base)
 		goto out;
 
-	/* we require some space to do alignment adjustments below */
+	req_size = ds_cfg.sizeof_rec[qual];
+	/* We might need space for alignment adjustments. */
+	if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT))
+		req_size += DS_ALIGNMENT;
+
 	error = -EINVAL;
-	if (size < (DS_ALIGNMENT + ds_cfg.sizeof_rec[qual]))
+	if (size < req_size)
 		goto out;
 
 	if (th != (size_t)-1) {
@@ -614,182 +696,318 @@ static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
 	tracer->size = size;
 
 	error = -ENOMEM;
-	context = ds_get_context(task);
+	context = ds_get_context(task, cpu);
 	if (!context)
 		goto out;
 	tracer->context = context;
 
-	ds_init_ds_trace(trace, qual, base, size, th, flags);
+	/*
+	 * Defer any tracer-specific initialization work for the context until
+	 * context ownership has been clarified.
+	 */
 
 	error = 0;
  out:
 	return error;
 }
 
-struct bts_tracer *ds_request_bts(struct task_struct *task,
-				  void *base, size_t size,
-				  bts_ovfl_callback_t ovfl, size_t th,
-				  unsigned int flags)
+static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu,
+					 void *base, size_t size,
+					 bts_ovfl_callback_t ovfl, size_t th,
+					 unsigned int flags)
 {
 	struct bts_tracer *tracer;
-	unsigned long irq;
 	int error;
 
+	/* Buffer overflow notification is not yet implemented. */
 	error = -EOPNOTSUPP;
-	if (!ds_cfg.ctl[dsf_bts])
+	if (ovfl)
 		goto out;
 
-	/* buffer overflow notification is not yet implemented */
-	error = -EOPNOTSUPP;
-	if (ovfl)
+	error = get_tracer(task);
+	if (error < 0)
 		goto out;
 
 	error = -ENOMEM;
 	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
-		goto out;
+		goto out_put_tracer;
 	tracer->ovfl = ovfl;
 
+	/* Do some more error checking and acquire a tracing context. */
 	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_bts, task, base, size, th, flags);
+			   ds_bts, task, cpu, base, size, th);
 	if (error < 0)
 		goto out_tracer;
 
-
-	spin_lock_irqsave(&ds_lock, irq);
-
-	error = -EPERM;
-	if (!check_tracer(task))
-		goto out_unlock;
-	get_tracer(task);
+	/* Claim the bts part of the tracing context we acquired above. */
+	spin_lock_irq(&ds_lock);
 
 	error = -EPERM;
 	if (tracer->ds.context->bts_master)
-		goto out_put_tracer;
+		goto out_unlock;
 	tracer->ds.context->bts_master = tracer;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
+	/*
+	 * Now that we own the bts part of the context, let's complete the
+	 * initialization for that part.
+	 */
+	ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags);
+	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	ds_install_ds_area(tracer->ds.context);
 
 	tracer->trace.read  = bts_read;
 	tracer->trace.write = bts_write;
 
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	/* Start tracing. */
 	ds_resume_bts(tracer);
 
 	return tracer;
 
- out_put_tracer:
-	put_tracer(task);
  out_unlock:
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 	ds_put_context(tracer->ds.context);
  out_tracer:
 	kfree(tracer);
+ out_put_tracer:
+	put_tracer(task);
  out:
 	return ERR_PTR(error);
 }
 
-struct pebs_tracer *ds_request_pebs(struct task_struct *task,
-				    void *base, size_t size,
-				    pebs_ovfl_callback_t ovfl, size_t th,
-				    unsigned int flags)
+struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+				       void *base, size_t size,
+				       bts_ovfl_callback_t ovfl,
+				       size_t th, unsigned int flags)
+{
+	return ds_request_bts(task, 0, base, size, ovfl, th, flags);
+}
+
+struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+				      bts_ovfl_callback_t ovfl,
+				      size_t th, unsigned int flags)
+{
+	return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu,
+					   void *base, size_t size,
+					   pebs_ovfl_callback_t ovfl, size_t th,
+					   unsigned int flags)
 {
 	struct pebs_tracer *tracer;
-	unsigned long irq;
 	int error;
 
-	/* buffer overflow notification is not yet implemented */
+	/* Buffer overflow notification is not yet implemented. */
 	error = -EOPNOTSUPP;
 	if (ovfl)
 		goto out;
 
+	error = get_tracer(task);
+	if (error < 0)
+		goto out;
+
 	error = -ENOMEM;
 	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
-		goto out;
+		goto out_put_tracer;
 	tracer->ovfl = ovfl;
 
+	/* Do some more error checking and acquire a tracing context. */
 	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_pebs, task, base, size, th, flags);
+			   ds_pebs, task, cpu, base, size, th);
 	if (error < 0)
 		goto out_tracer;
 
-	spin_lock_irqsave(&ds_lock, irq);
-
-	error = -EPERM;
-	if (!check_tracer(task))
-		goto out_unlock;
-	get_tracer(task);
+	/* Claim the pebs part of the tracing context we acquired above. */
+	spin_lock_irq(&ds_lock);
 
 	error = -EPERM;
 	if (tracer->ds.context->pebs_master)
-		goto out_put_tracer;
+		goto out_unlock;
 	tracer->ds.context->pebs_master = tracer;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
+	/*
+	 * Now that we own the pebs part of the context, let's complete the
+	 * initialization for that part.
+	 */
+	ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags);
 	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
+	ds_install_ds_area(tracer->ds.context);
+
+	/* Start tracing. */
 	ds_resume_pebs(tracer);
 
 	return tracer;
 
- out_put_tracer:
-	put_tracer(task);
  out_unlock:
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 	ds_put_context(tracer->ds.context);
  out_tracer:
 	kfree(tracer);
+ out_put_tracer:
+	put_tracer(task);
  out:
 	return ERR_PTR(error);
 }
 
-void ds_release_bts(struct bts_tracer *tracer)
+struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+					 void *base, size_t size,
+					 pebs_ovfl_callback_t ovfl,
+					 size_t th, unsigned int flags)
 {
-	if (!tracer)
-		return;
+	return ds_request_pebs(task, 0, base, size, ovfl, th, flags);
+}
 
-	ds_suspend_bts(tracer);
+struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size,
+					pebs_ovfl_callback_t ovfl,
+					size_t th, unsigned int flags)
+{
+	return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static void ds_free_bts(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+
+	task = tracer->ds.context->task;
 
 	WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
 	tracer->ds.context->bts_master = NULL;
 
-	put_tracer(tracer->ds.context->task);
+	/* Make sure tracing stopped and the tracer is not in use. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
 	ds_put_context(tracer->ds.context);
+	put_tracer(task);
 
 	kfree(tracer);
 }
 
+void ds_release_bts(struct bts_tracer *tracer)
+{
+	might_sleep();
+
+	if (!tracer)
+		return;
+
+	ds_suspend_bts(tracer);
+	ds_free_bts(tracer);
+}
+
+int ds_release_bts_noirq(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long irq;
+	int error;
+
+	if (!tracer)
+		return 0;
+
+	task = tracer->ds.context->task;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task &&
+	    (tracer->ds.context->cpu != smp_processor_id()))
+		goto out;
+
+	error = -EPERM;
+	if (task && (task != current))
+		goto out;
+
+	ds_suspend_bts_noirq(tracer);
+	ds_free_bts(tracer);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static void update_task_debugctlmsr(struct task_struct *task,
+				    unsigned long debugctlmsr)
+{
+	task->thread.debugctlmsr = debugctlmsr;
+
+	get_cpu();
+	if (task == current)
+		update_debugctlmsr(debugctlmsr);
+	put_cpu();
+}
+
 void ds_suspend_bts(struct bts_tracer *tracer)
 {
 	struct task_struct *task;
+	unsigned long debugctlmsr;
+	int cpu;
 
 	if (!tracer)
 		return;
 
+	tracer->flags = 0;
+
 	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
 
-	if (!task || (task == current))
-		update_debugctlmsr(get_debugctlmsr() & ~BTS_CONTROL);
+	WARN_ON(!task && irqs_disabled());
 
-	if (task) {
-		task->thread.debugctlmsr &= ~BTS_CONTROL;
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr_on_cpu(cpu));
+	debugctlmsr &= ~BTS_CONTROL;
 
-		if (!task->thread.debugctlmsr)
-			clear_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
-	}
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
 }
 
-void ds_resume_bts(struct bts_tracer *tracer)
+int ds_suspend_bts_noirq(struct bts_tracer *tracer)
 {
 	struct task_struct *task;
-	unsigned long control;
+	unsigned long debugctlmsr, irq;
+	int cpu, error = 0;
 
 	if (!tracer)
-		return;
+		return 0;
+
+	tracer->flags = 0;
 
 	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task && (cpu != smp_processor_id()))
+		goto out;
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr());
+	debugctlmsr &= ~BTS_CONTROL;
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr(debugctlmsr);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static unsigned long ds_bts_control(struct bts_tracer *tracer)
+{
+	unsigned long control;
 
 	control = ds_cfg.ctl[dsf_bts];
 	if (!(tracer->trace.ds.flags & BTS_KERNEL))
@@ -797,41 +1015,149 @@ void ds_resume_bts(struct bts_tracer *tracer)
 	if (!(tracer->trace.ds.flags & BTS_USER))
 		control |= ds_cfg.ctl[dsf_bts_user];
 
-	if (task) {
-		task->thread.debugctlmsr |= control;
-		set_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
-	}
-
-	if (!task || (task == current))
-		update_debugctlmsr(get_debugctlmsr() | control);
+	return control;
 }
 
-void ds_release_pebs(struct pebs_tracer *tracer)
+void ds_resume_bts(struct bts_tracer *tracer)
 {
+	struct task_struct *task;
+	unsigned long debugctlmsr;
+	int cpu;
+
 	if (!tracer)
 		return;
 
-	ds_suspend_pebs(tracer);
+	tracer->flags = tracer->trace.ds.flags;
+
+	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	WARN_ON(!task && irqs_disabled());
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr_on_cpu(cpu));
+	debugctlmsr |= ds_bts_control(tracer);
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
+}
+
+int ds_resume_bts_noirq(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long debugctlmsr, irq;
+	int cpu, error = 0;
+
+	if (!tracer)
+		return 0;
+
+	tracer->flags = tracer->trace.ds.flags;
+
+	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task && (cpu != smp_processor_id()))
+		goto out;
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr());
+	debugctlmsr |= ds_bts_control(tracer);
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr(debugctlmsr);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static void ds_free_pebs(struct pebs_tracer *tracer)
+{
+	struct task_struct *task;
+
+	task = tracer->ds.context->task;
 
 	WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer);
 	tracer->ds.context->pebs_master = NULL;
 
-	put_tracer(tracer->ds.context->task);
 	ds_put_context(tracer->ds.context);
+	put_tracer(task);
 
 	kfree(tracer);
 }
 
+void ds_release_pebs(struct pebs_tracer *tracer)
+{
+	might_sleep();
+
+	if (!tracer)
+		return;
+
+	ds_suspend_pebs(tracer);
+	ds_free_pebs(tracer);
+}
+
+int ds_release_pebs_noirq(struct pebs_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long irq;
+	int error;
+
+	if (!tracer)
+		return 0;
+
+	task = tracer->ds.context->task;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task &&
+	    (tracer->ds.context->cpu != smp_processor_id()))
+		goto out;
+
+	error = -EPERM;
+	if (task && (task != current))
+		goto out;
+
+	ds_suspend_pebs_noirq(tracer);
+	ds_free_pebs(tracer);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
 void ds_suspend_pebs(struct pebs_tracer *tracer)
 {
 
 }
 
+int ds_suspend_pebs_noirq(struct pebs_tracer *tracer)
+{
+	return 0;
+}
+
 void ds_resume_pebs(struct pebs_tracer *tracer)
 {
 
 }
 
+int ds_resume_pebs_noirq(struct pebs_tracer *tracer)
+{
+	return 0;
+}
+
 const struct bts_trace *ds_read_bts(struct bts_tracer *tracer)
 {
 	if (!tracer)
@@ -847,8 +1173,12 @@ const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer)
 		return NULL;
 
 	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-	tracer->trace.reset_value =
-		*(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8));
+
+	tracer->trace.counters = ds_cfg.nr_counter_reset;
+	memcpy(tracer->trace.counter_reset,
+	       tracer->ds.context->ds +
+	       (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field),
+	       ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE);
 
 	return &tracer->trace;
 }
@@ -873,18 +1203,24 @@ int ds_reset_pebs(struct pebs_tracer *tracer)
 
 	tracer->trace.ds.top = tracer->trace.ds.begin;
 
-	ds_set(tracer->ds.context->ds, ds_bts, ds_index,
+	ds_set(tracer->ds.context->ds, ds_pebs, ds_index,
 	       (unsigned long)tracer->trace.ds.top);
 
 	return 0;
 }
 
-int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
+int ds_set_pebs_reset(struct pebs_tracer *tracer,
+		      unsigned int counter, u64 value)
 {
 	if (!tracer)
 		return -EINVAL;
 
-	*(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8)) = value;
+	if (ds_cfg.nr_counter_reset < counter)
+		return -EINVAL;
+
+	*(u64 *)(tracer->ds.context->ds +
+		 (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) +
+		 (counter * PEBS_RESET_FIELD_SIZE)) = value;
 
 	return 0;
 }
@@ -894,73 +1230,117 @@ static const struct ds_configuration ds_cfg_netburst = {
 	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
 	.ctl[dsf_bts_kernel]	= (1 << 5),
 	.ctl[dsf_bts_user]	= (1 << 6),
-
-	.sizeof_field		= sizeof(long),
-	.sizeof_rec[ds_bts]	= sizeof(long) * 3,
-#ifdef __i386__
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 10,
-#else
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
-#endif
+	.nr_counter_reset	= 1,
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
 	.name = "Pentium M",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-
-	.sizeof_field		= sizeof(long),
-	.sizeof_rec[ds_bts]	= sizeof(long) * 3,
-#ifdef __i386__
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 10,
-#else
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
-#endif
+	.nr_counter_reset	= 1,
 };
 static const struct ds_configuration ds_cfg_core2_atom = {
 	.name = "Core 2/Atom",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 	.ctl[dsf_bts_kernel]	= (1 << 9),
 	.ctl[dsf_bts_user]	= (1 << 10),
-
-	.sizeof_field		= 8,
-	.sizeof_rec[ds_bts]	= 8 * 3,
-	.sizeof_rec[ds_pebs]	= 8 * 18,
+	.nr_counter_reset	= 1,
+};
+static const struct ds_configuration ds_cfg_core_i7 = {
+	.name = "Core i7",
+	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
+	.ctl[dsf_bts_kernel]	= (1 << 9),
+	.ctl[dsf_bts_user]	= (1 << 10),
+	.nr_counter_reset	= 4,
 };
 
 static void
-ds_configure(const struct ds_configuration *cfg)
+ds_configure(const struct ds_configuration *cfg,
+	     struct cpuinfo_x86 *cpu)
 {
+	unsigned long nr_pebs_fields = 0;
+
+	printk(KERN_INFO "[ds] using %s configuration\n", cfg->name);
+
+#ifdef __i386__
+	nr_pebs_fields = 10;
+#else
+	nr_pebs_fields = 18;
+#endif
+
+	/*
+	 * Starting with version 2, architectural performance
+	 * monitoring supports a format specifier.
+	 */
+	if ((cpuid_eax(0xa) & 0xff) > 1) {
+		unsigned long perf_capabilities, format;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+
+		format = (perf_capabilities >> 8) & 0xf;
+
+		switch (format) {
+		case 0:
+			nr_pebs_fields = 18;
+			break;
+		case 1:
+			nr_pebs_fields = 22;
+			break;
+		default:
+			printk(KERN_INFO
+			       "[ds] unknown PEBS format: %lu\n", format);
+			nr_pebs_fields = 0;
+			break;
+		}
+	}
+
 	memset(&ds_cfg, 0, sizeof(ds_cfg));
 	ds_cfg = *cfg;
 
-	printk(KERN_INFO "[ds] using %s configuration\n", ds_cfg.name);
+	ds_cfg.sizeof_ptr_field =
+		(cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4);
+
+	ds_cfg.sizeof_rec[ds_bts]  = ds_cfg.sizeof_ptr_field * 3;
+	ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields;
 
-	if (!cpu_has_bts) {
-		ds_cfg.ctl[dsf_bts] = 0;
+	if (!cpu_has(cpu, X86_FEATURE_BTS)) {
+		ds_cfg.sizeof_rec[ds_bts] = 0;
 		printk(KERN_INFO "[ds] bts not available\n");
 	}
-	if (!cpu_has_pebs)
+	if (!cpu_has(cpu, X86_FEATURE_PEBS)) {
+		ds_cfg.sizeof_rec[ds_pebs] = 0;
 		printk(KERN_INFO "[ds] pebs not available\n");
+	}
+
+	printk(KERN_INFO "[ds] sizes: address: %u bit, ",
+	       8 * ds_cfg.sizeof_ptr_field);
+	printk("bts/pebs record: %u/%u bytes\n",
+	       ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]);
 
-	WARN_ON_ONCE(MAX_SIZEOF_DS < (12 * ds_cfg.sizeof_field));
+	WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset);
 }
 
 void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 {
+	/* Only configure the first cpu. Others are identical. */
+	if (ds_cfg.name)
+		return;
+
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
 		case 0x9:
 		case 0xd: /* Pentium M */
-			ds_configure(&ds_cfg_pentium_m);
+			ds_configure(&ds_cfg_pentium_m, c);
 			break;
 		case 0xf:
 		case 0x17: /* Core2 */
 		case 0x1c: /* Atom */
-			ds_configure(&ds_cfg_core2_atom);
+			ds_configure(&ds_cfg_core2_atom, c);
+			break;
+		case 0x1a: /* Core i7 */
+			ds_configure(&ds_cfg_core_i7, c);
 			break;
-		case 0x1a: /* i7 */
 		default:
-			/* sorry, don't know about them */
+			/* Sorry, don't know about them. */
 			break;
 		}
 		break;
@@ -969,64 +1349,89 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 		case 0x0:
 		case 0x1:
 		case 0x2: /* Netburst */
-			ds_configure(&ds_cfg_netburst);
+			ds_configure(&ds_cfg_netburst, c);
 			break;
 		default:
-			/* sorry, don't know about them */
+			/* Sorry, don't know about them. */
 			break;
 		}
 		break;
 	default:
-		/* sorry, don't know about them */
+		/* Sorry, don't know about them. */
 		break;
 	}
 }
 
+static inline void ds_take_timestamp(struct ds_context *context,
+				     enum bts_qualifier qualifier,
+				     struct task_struct *task)
+{
+	struct bts_tracer *tracer = context->bts_master;
+	struct bts_struct ts;
+
+	/* Prevent compilers from reading the tracer pointer twice. */
+	barrier();
+
+	if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
+		return;
+
+	memset(&ts, 0, sizeof(ts));
+	ts.qualifier		= qualifier;
+	ts.variant.event.clock	= trace_clock_global();
+	ts.variant.event.pid	= task->pid;
+
+	bts_write(tracer, &ts);
+}
+
 /*
  * Change the DS configuration from tracing prev to tracing next.
  */
 void ds_switch_to(struct task_struct *prev, struct task_struct *next)
 {
-	struct ds_context *prev_ctx = prev->thread.ds_ctx;
-	struct ds_context *next_ctx = next->thread.ds_ctx;
+	struct ds_context *prev_ctx	= prev->thread.ds_ctx;
+	struct ds_context *next_ctx	= next->thread.ds_ctx;
+	unsigned long debugctlmsr	= next->thread.debugctlmsr;
+
+	/* Make sure all data is read before we start. */
+	barrier();
 
 	if (prev_ctx) {
 		update_debugctlmsr(0);
 
-		if (prev_ctx->bts_master &&
-		    (prev_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
-			struct bts_struct ts = {
-				.qualifier = bts_task_departs,
-				.variant.timestamp.jiffies = jiffies_64,
-				.variant.timestamp.pid = prev->pid
-			};
-			bts_write(prev_ctx->bts_master, &ts);
-		}
+		ds_take_timestamp(prev_ctx, bts_task_departs, prev);
 	}
 
 	if (next_ctx) {
-		if (next_ctx->bts_master &&
-		    (next_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
-			struct bts_struct ts = {
-				.qualifier = bts_task_arrives,
-				.variant.timestamp.jiffies = jiffies_64,
-				.variant.timestamp.pid = next->pid
-			};
-			bts_write(next_ctx->bts_master, &ts);
-		}
+		ds_take_timestamp(next_ctx, bts_task_arrives, next);
 
 		wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
 	}
 
-	update_debugctlmsr(next->thread.debugctlmsr);
+	update_debugctlmsr(debugctlmsr);
 }
 
-void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
+static __init int ds_selftest(void)
 {
-	clear_tsk_thread_flag(tsk, TIF_DS_AREA_MSR);
-	tsk->thread.ds_ctx = NULL;
-}
+	if (ds_cfg.sizeof_rec[ds_bts]) {
+		int error;
 
-void ds_exit_thread(struct task_struct *tsk)
-{
+		error = ds_selftest_bts();
+		if (error) {
+			WARN(1, "[ds] selftest failed. disabling bts.\n");
+			ds_cfg.sizeof_rec[ds_bts] = 0;
+		}
+	}
+
+	if (ds_cfg.sizeof_rec[ds_pebs]) {
+		int error;
+
+		error = ds_selftest_pebs();
+		if (error) {
+			WARN(1, "[ds] selftest failed. disabling pebs.\n");
+			ds_cfg.sizeof_rec[ds_pebs] = 0;
+		}
+	}
+
+	return 0;
 }
+device_initcall(ds_selftest);
diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c
new file mode 100644
index 00000000000..6bc7c199ab9
--- /dev/null
+++ b/arch/x86/kernel/ds_selftest.c
@@ -0,0 +1,408 @@
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#include "ds_selftest.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+
+#include <asm/ds.h>
+
+
+#define BUFFER_SIZE		521	/* Intentionally chose an odd size. */
+#define SMALL_BUFFER_SIZE	24	/* A single bts entry. */
+
+struct ds_selftest_bts_conf {
+	struct bts_tracer *tracer;
+	int error;
+	int (*suspend)(struct bts_tracer *);
+	int (*resume)(struct bts_tracer *);
+};
+
+static int ds_selftest_bts_consistency(const struct bts_trace *trace)
+{
+	int error = 0;
+
+	if (!trace) {
+		printk(KERN_CONT "failed to access trace...");
+		/* Bail out. Other tests are pointless. */
+		return -1;
+	}
+
+	if (!trace->read) {
+		printk(KERN_CONT "bts read not available...");
+		error = -1;
+	}
+
+	/* Do some sanity checks on the trace configuration. */
+	if (!trace->ds.n) {
+		printk(KERN_CONT "empty bts buffer...");
+		error = -1;
+	}
+	if (!trace->ds.size) {
+		printk(KERN_CONT "bad bts trace setup...");
+		error = -1;
+	}
+	if (trace->ds.end !=
+	    (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) {
+		printk(KERN_CONT "bad bts buffer setup...");
+		error = -1;
+	}
+	/*
+	 * We allow top in [begin; end], since its not clear when the
+	 * overflow adjustment happens: after the increment or before the
+	 * write.
+	 */
+	if ((trace->ds.top < trace->ds.begin) ||
+	    (trace->ds.end < trace->ds.top)) {
+		printk(KERN_CONT "bts top out of bounds...");
+		error = -1;
+	}
+
+	return error;
+}
+
+static int ds_selftest_bts_read(struct bts_tracer *tracer,
+				const struct bts_trace *trace,
+				const void *from, const void *to)
+{
+	const unsigned char *at;
+
+	/*
+	 * Check a few things which do not belong to this test.
+	 * They should be covered by other tests.
+	 */
+	if (!trace)
+		return -1;
+
+	if (!trace->read)
+		return -1;
+
+	if (to < from)
+		return -1;
+
+	if (from < trace->ds.begin)
+		return -1;
+
+	if (trace->ds.end < to)
+		return -1;
+
+	if (!trace->ds.size)
+		return -1;
+
+	/* Now to the test itself. */
+	for (at = from; (void *)at < to; at += trace->ds.size) {
+		struct bts_struct bts;
+		unsigned long index;
+		int error;
+
+		if (((void *)at - trace->ds.begin) % trace->ds.size) {
+			printk(KERN_CONT
+			       "read from non-integer index...");
+			return -1;
+		}
+		index = ((void *)at - trace->ds.begin) / trace->ds.size;
+
+		memset(&bts, 0, sizeof(bts));
+		error = trace->read(tracer, at, &bts);
+		if (error < 0) {
+			printk(KERN_CONT
+			       "error reading bts trace at [%lu] (0x%p)...",
+			       index, at);
+			return error;
+		}
+
+		switch (bts.qualifier) {
+		case BTS_BRANCH:
+			break;
+		default:
+			printk(KERN_CONT
+			       "unexpected bts entry %llu at [%lu] (0x%p)...",
+			       bts.qualifier, index, at);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static void ds_selftest_bts_cpu(void *arg)
+{
+	struct ds_selftest_bts_conf *conf = arg;
+	const struct bts_trace *trace;
+	void *top;
+
+	if (IS_ERR(conf->tracer)) {
+		conf->error = PTR_ERR(conf->tracer);
+		conf->tracer = NULL;
+
+		printk(KERN_CONT
+		       "initialization failed (err: %d)...", conf->error);
+		return;
+	}
+
+	/* We should meanwhile have enough trace. */
+	conf->error = conf->suspend(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	/* Let's see if we can access the trace. */
+	trace = ds_read_bts(conf->tracer);
+
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	/* If everything went well, we should have a few trace entries. */
+	if (trace->ds.top == trace->ds.begin) {
+		/*
+		 * It is possible but highly unlikely that we got a
+		 * buffer overflow and end up at exactly the same
+		 * position we started from.
+		 * Let's issue a warning, but continue.
+		 */
+		printk(KERN_CONT "no trace/overflow...");
+	}
+
+	/* Let's try to read the trace we collected. */
+	conf->error =
+		ds_selftest_bts_read(conf->tracer, trace,
+				     trace->ds.begin, trace->ds.top);
+	if (conf->error < 0)
+		return;
+
+	/*
+	 * Let's read the trace again.
+	 * Since we suspended tracing, we should get the same result.
+	 */
+	top = trace->ds.top;
+
+	trace = ds_read_bts(conf->tracer);
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	if (top != trace->ds.top) {
+		printk(KERN_CONT "suspend not working...");
+		conf->error = -1;
+		return;
+	}
+
+	/* Let's collect some more trace - see if resume is working. */
+	conf->error = conf->resume(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	conf->error = conf->suspend(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	trace = ds_read_bts(conf->tracer);
+
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	if (trace->ds.top == top) {
+		/*
+		 * It is possible but highly unlikely that we got a
+		 * buffer overflow and end up at exactly the same
+		 * position we started from.
+		 * Let's issue a warning and check the full trace.
+		 */
+		printk(KERN_CONT
+		       "no resume progress/overflow...");
+
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace,
+					     trace->ds.begin, trace->ds.end);
+	} else if (trace->ds.top < top) {
+		/*
+		 * We had a buffer overflow - the entire buffer should
+		 * contain trace records.
+		 */
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace,
+					     trace->ds.begin, trace->ds.end);
+	} else {
+		/*
+		 * It is quite likely that the buffer did not overflow.
+		 * Let's just check the delta trace.
+		 */
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace, top,
+					     trace->ds.top);
+	}
+	if (conf->error < 0)
+		return;
+
+	conf->error = 0;
+}
+
+static int ds_suspend_bts_wrap(struct bts_tracer *tracer)
+{
+	ds_suspend_bts(tracer);
+	return 0;
+}
+
+static int ds_resume_bts_wrap(struct bts_tracer *tracer)
+{
+	ds_resume_bts(tracer);
+	return 0;
+}
+
+static void ds_release_bts_noirq_wrap(void *tracer)
+{
+	(void)ds_release_bts_noirq(tracer);
+}
+
+static int ds_selftest_bts_bad_release_noirq(int cpu,
+					     struct bts_tracer *tracer)
+{
+	int error = -EPERM;
+
+	/* Try to release the tracer on the wrong cpu. */
+	get_cpu();
+	if (cpu != smp_processor_id()) {
+		error = ds_release_bts_noirq(tracer);
+		if (error != -EPERM)
+			printk(KERN_CONT "release on wrong cpu...");
+	}
+	put_cpu();
+
+	return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer)
+{
+	struct bts_tracer *tracer;
+	int error;
+
+	/* Try to request cpu tracing while task tracing is active. */
+	tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL,
+				    (size_t)-1, BTS_KERNEL);
+	error = PTR_ERR(tracer);
+	if (!IS_ERR(tracer)) {
+		ds_release_bts(tracer);
+		error = 0;
+	}
+
+	if (error != -EPERM)
+		printk(KERN_CONT "cpu/task tracing overlap...");
+
+	return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_task(void *buffer)
+{
+	struct bts_tracer *tracer;
+	int error;
+
+	/* Try to request cpu tracing while task tracing is active. */
+	tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL,
+				    (size_t)-1, BTS_KERNEL);
+	error = PTR_ERR(tracer);
+	if (!IS_ERR(tracer)) {
+		error = 0;
+		ds_release_bts(tracer);
+	}
+
+	if (error != -EPERM)
+		printk(KERN_CONT "task/cpu tracing overlap...");
+
+	return error ? 0 : -1;
+}
+
+int ds_selftest_bts(void)
+{
+	struct ds_selftest_bts_conf conf;
+	unsigned char buffer[BUFFER_SIZE], *small_buffer;
+	unsigned long irq;
+	int cpu;
+
+	printk(KERN_INFO "[ds] bts selftest...");
+	conf.error = 0;
+
+	small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		conf.suspend = ds_suspend_bts_wrap;
+		conf.resume = ds_resume_bts_wrap;
+		conf.tracer =
+			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+					   NULL, (size_t)-1, BTS_KERNEL);
+		ds_selftest_bts_cpu(&conf);
+		if (conf.error >= 0)
+			conf.error = ds_selftest_bts_bad_request_task(buffer);
+		ds_release_bts(conf.tracer);
+		if (conf.error < 0)
+			goto out;
+
+		conf.suspend = ds_suspend_bts_noirq;
+		conf.resume = ds_resume_bts_noirq;
+		conf.tracer =
+			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+					   NULL, (size_t)-1, BTS_KERNEL);
+		smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1);
+		if (conf.error >= 0) {
+			conf.error =
+				ds_selftest_bts_bad_release_noirq(cpu,
+								  conf.tracer);
+			/* We must not release the tracer twice. */
+			if (conf.error < 0)
+				conf.tracer = NULL;
+		}
+		if (conf.error >= 0)
+			conf.error = ds_selftest_bts_bad_request_task(buffer);
+		smp_call_function_single(cpu, ds_release_bts_noirq_wrap,
+					 conf.tracer, 1);
+		if (conf.error < 0)
+			goto out;
+	}
+
+	conf.suspend = ds_suspend_bts_wrap;
+	conf.resume = ds_resume_bts_wrap;
+	conf.tracer =
+		ds_request_bts_task(current, buffer, BUFFER_SIZE,
+				    NULL, (size_t)-1, BTS_KERNEL);
+	ds_selftest_bts_cpu(&conf);
+	if (conf.error >= 0)
+		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+	ds_release_bts(conf.tracer);
+	if (conf.error < 0)
+		goto out;
+
+	conf.suspend = ds_suspend_bts_noirq;
+	conf.resume = ds_resume_bts_noirq;
+	conf.tracer =
+		ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE,
+				   NULL, (size_t)-1, BTS_KERNEL);
+	local_irq_save(irq);
+	ds_selftest_bts_cpu(&conf);
+	if (conf.error >= 0)
+		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+	ds_release_bts_noirq(conf.tracer);
+	local_irq_restore(irq);
+	if (conf.error < 0)
+		goto out;
+
+	conf.error = 0;
+ out:
+	put_online_cpus();
+	printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed"));
+
+	return conf.error;
+}
+
+int ds_selftest_pebs(void)
+{
+	return 0;
+}
diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h
new file mode 100644
index 00000000000..2ba8745c666
--- /dev/null
+++ b/arch/x86/kernel/ds_selftest.h
@@ -0,0 +1,15 @@
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#ifdef CONFIG_X86_DS_SELFTEST
+extern int ds_selftest_bts(void);
+extern int ds_selftest_pebs(void);
+#else
+static inline int ds_selftest_bts(void) { return 0; }
+static inline int ds_selftest_pebs(void) { return 0; }
+#endif
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index da87590b869..81086c227ab 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,7 +29,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl);
 
 extern unsigned int code_bytes;
-extern int kstack_depth_to_print;
 
 /* The form of the top of the frame on the stack */
 struct stack_frame {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 00628130292..7271fa33d79 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -617,7 +617,7 @@ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
  */
 __init void e820_setup_gap(void)
 {
-	unsigned long gapstart, gapsize, round;
+	unsigned long gapstart, gapsize;
 	int found;
 
 	gapstart = 0x10000000;
@@ -635,14 +635,9 @@ __init void e820_setup_gap(void)
 #endif
 
 	/*
-	 * See how much we want to round up: start off with
-	 * rounding to the next 1MB area.
+	 * e820_reserve_resources_late protect stolen RAM already
 	 */
-	round = 0x100000;
-	while ((gapsize >> 4) > round)
-		round += round;
-	/* Fun with two's complement */
-	pci_mem_start = (gapstart + round) & -round;
+	pci_mem_start = gapstart;
 
 	printk(KERN_INFO
 	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
@@ -1371,6 +1366,23 @@ void __init e820_reserve_resources(void)
 	}
 }
 
+/* How much should we pad RAM ending depending on where it is? */
+static unsigned long ram_alignment(resource_size_t pos)
+{
+	unsigned long mb = pos >> 20;
+
+	/* To 64kB in the first megabyte */
+	if (!mb)
+		return 64*1024;
+
+	/* To 1MB in the first 16MB */
+	if (mb < 16)
+		return 1024*1024;
+
+	/* To 32MB for anything above that */
+	return 32*1024*1024;
+}
+
 void __init e820_reserve_resources_late(void)
 {
 	int i;
@@ -1382,6 +1394,24 @@ void __init e820_reserve_resources_late(void)
 			insert_resource_expand_to_fit(&iomem_resource, res);
 		res++;
 	}
+
+	/*
+	 * Try to bump up RAM regions to reasonable boundaries to
+	 * avoid stolen RAM:
+	 */
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *entry = &e820_saved.map[i];
+		resource_size_t start, end;
+
+		if (entry->type != E820_RAM)
+			continue;
+		start = entry->addr + entry->size;
+		end = round_up(start, ram_alignment(start));
+		if (start == end)
+			continue;
+		reserve_region_with_split(&iomem_resource, start,
+						  end - 1, "RAM buffer");
+	}
 }
 
 char *__init default_machine_specific_memory_setup(void)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 76b8cd953de..ebdb85cf268 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,6 +97,7 @@ static void __init nvidia_bugs(int num, int slot, int func)
 }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
+#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
 	u32 d;
@@ -114,6 +115,7 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 	d &= 0xff;
 	return d;
 }
+#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7985c010f8a..a4742a340d8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -147,27 +147,14 @@ END(ftrace_graph_caller)
 GLOBAL(return_to_handler)
 	subq  $80, %rsp
 
+	/* Save the return values */
 	movq %rax, (%rsp)
-	movq %rcx, 8(%rsp)
-	movq %rdx, 16(%rsp)
-	movq %rsi, 24(%rsp)
-	movq %rdi, 32(%rsp)
-	movq %r8, 40(%rsp)
-	movq %r9, 48(%rsp)
-	movq %r10, 56(%rsp)
-	movq %r11, 64(%rsp)
+	movq %rdx, 8(%rsp)
 
 	call ftrace_return_to_handler
 
 	movq %rax, 72(%rsp)
-	movq 64(%rsp), %r11
-	movq 56(%rsp), %r10
-	movq 48(%rsp), %r9
-	movq 40(%rsp), %r8
-	movq 32(%rsp), %rdi
-	movq 24(%rsp), %rsi
-	movq 16(%rsp), %rdx
-	movq 8(%rsp), %rcx
+	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $72, %rsp
 	retq
@@ -1384,6 +1371,11 @@ END(xen_failsafe_callback)
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
 paranoiderrorentry stack_segment do_stack_segment
+#ifdef CONFIG_XEN
+zeroentry xen_debug do_debug
+zeroentry xen_int3 do_int3
+errorentry xen_stack_segment do_stack_segment
+#endif
 errorentry general_protection do_general_protection
 errorentry page_fault do_page_fault
 #ifdef CONFIG_X86_MCE
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 30683883e0c..dc5ed4bdd88 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -608,13 +608,6 @@ ignore_int:
 ENTRY(initial_code)
 	.long i386_start_kernel
 
-.section .text
-/*
- * Real beginning of normal "text" segment
- */
-ENTRY(stext)
-ENTRY(_stext)
-
 /*
  * BSS section
  */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 8279fb8df17..38287b5f116 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -12,6 +12,7 @@
 #include <asm/io_apic.h>
 #include <asm/irq.h>
 #include <asm/idle.h>
+#include <asm/hw_irq.h>
 
 atomic_t irq_err_count;
 
@@ -24,9 +25,9 @@ void (*generic_interrupt_extension)(void) = NULL;
  */
 void ack_bad_irq(unsigned int irq)
 {
-	printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+	if (printk_ratelimit())
+		pr_err("unexpected IRQ trap at vector %02x\n", irq);
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * Currently unexpected vectors happen only on SMP and APIC.
 	 * We _must_ ack these because every local APIC has only N
@@ -36,9 +37,7 @@ void ack_bad_irq(unsigned int irq)
 	 * completely.
 	 * But only ack when the APIC is enabled -AK
 	 */
-	if (cpu_has_apic)
-		ack_APIC_irq();
-#endif
+	ack_APIC_irq();
 }
 
 #define irq_stats(x)		(&per_cpu(irq_stat, x))
@@ -188,7 +187,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->irq_thermal_count;
 # ifdef CONFIG_X86_64
 	sum += irq_stats(cpu)->irq_threshold_count;
-#endif
+# endif
 #endif
 	return sum;
 }
@@ -223,14 +222,11 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	irq = __get_cpu_var(vector_irq)[vector];
 
 	if (!handle_irq(irq, regs)) {
-#ifdef CONFIG_X86_64
-		if (!disable_apic)
-			ack_APIC_irq();
-#endif
+		ack_APIC_irq();
 
 		if (printk_ratelimit())
-			printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n",
-			       __func__, smp_processor_id(), vector, irq);
+			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
+				__func__, smp_processor_id(), vector, irq);
 	}
 
 	irq_exit();
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit.c
index 205bdd880d3..267c6624c77 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit.c
@@ -1,20 +1,25 @@
+#include <linux/linkage.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/timex.h>
 #include <linux/slab.h>
 #include <linux/random.h>
+#include <linux/kprobes.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
+#include <linux/acpi.h>
 #include <linux/io.h>
 #include <linux/delay.h>
 
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/timer.h>
+#include <asm/hw_irq.h>
 #include <asm/pgtable.h>
 #include <asm/desc.h>
 #include <asm/apic.h>
@@ -22,8 +27,24 @@
 #include <asm/i8259.h>
 #include <asm/traps.h>
 
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
 
 /*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+
+#ifdef CONFIG_X86_32
+/*
  * Note that on a 486, we don't want to do a SIGFPE on an irq13
  * as the irq is unreliable, and exception 16 works correctly
  * (ie as explained in the intel literature). On a 386, you
@@ -52,30 +73,7 @@ static struct irqaction fpu_irq = {
 	.handler = math_error_irq,
 	.name = "fpu",
 };
-
-void __init init_ISA_irqs(void)
-{
-	int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	init_bsp_APIC();
 #endif
-	init_8259A(0);
-
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
-}
 
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
@@ -118,9 +116,37 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	return 0;
 }
 
+static void __init init_ISA_irqs(void)
+{
+	int i;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+	init_bsp_APIC();
+#endif
+	init_8259A(0);
+
+	/*
+	 * 16 old-style INTA-cycle interrupts:
+	 */
+	for (i = 0; i < NR_IRQS_LEGACY; i++) {
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = NULL;
+		desc->depth = 1;
+
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
+					      handle_level_irq, "XT");
+	}
+}
+
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
 static void __init smp_intr_init(void)
 {
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/*
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
@@ -140,21 +166,32 @@ static void __init smp_intr_init(void)
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
-	/* IPI for single call function */
+	/* IPI for generic single function call */
 	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-				 call_function_single_interrupt);
+			call_function_single_interrupt);
 
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
 #endif
+#endif /* CONFIG_SMP */
 }
 
 static void __init apic_intr_init(void)
 {
 	smp_intr_init();
 
-#ifdef CONFIG_X86_LOCAL_APIC
+#ifdef CONFIG_X86_THERMAL_VECTOR
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+#endif
+#ifdef CONFIG_X86_THRESHOLD
+	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+#endif
+#if defined(CONFIG_X86_NEW_MCE) && defined(CONFIG_X86_LOCAL_APIC)
+	alloc_intr_gate(MCE_SELF_VECTOR, mce_self_interrupt);
+#endif
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
@@ -164,19 +201,34 @@ static void __init apic_intr_init(void)
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+	/* Performance monitoring interrupts: */
 # ifdef CONFIG_PERF_COUNTERS
 	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
 # endif
 
-# ifdef CONFIG_X86_MCE_P4THERMAL
-	/* thermal monitor LVT interrupt */
-	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-# endif
 #endif
 }
 
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+/**
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
+ *
+ * Description:
+ *	Perform any necessary interrupt initialisation prior to setting up
+ *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
+ *	interrupts should be initialised here if the machine emulates a PC
+ *	in any way.
+ **/
+static void __init x86_quirk_pre_intr_init(void)
+{
+#ifdef CONFIG_X86_32
+	if (x86_quirks->arch_pre_intr_init) {
+		if (x86_quirks->arch_pre_intr_init())
+			return;
+	}
+#endif
+	init_ISA_irqs();
+}
 
 void __init native_init_IRQ(void)
 {
@@ -192,16 +244,16 @@ void __init native_init_IRQ(void)
 	 * us. (some of these will be overridden and become
 	 * 'special' SMP interrupts)
 	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (!test_bit(vector, used_vectors))
-			set_intr_gate(vector, interrupt[i]);
+	for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
+		if (!test_bit(i, used_vectors))
+			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
 	}
 
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Call quirks after call gates are initialised (usually add in
 	 * the architecture specific gates):
@@ -216,4 +268,5 @@ void __init native_init_IRQ(void)
 		setup_irq(FPU_IRQ, &fpu_irq);
 
 	irq_ctx_init(smp_processor_id());
+#endif
 }
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
deleted file mode 100644
index fa6ef692000..00000000000
--- a/arch/x86/kernel/irqinit_64.c
+++ /dev/null
@@ -1,183 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] != -1)
-			return 1;
-	}
-
-	return 0;
-}
-
-static void __init init_ISA_irqs(void)
-{
-	int i;
-
-	init_bsp_APIC();
-	init_8259A(0);
-
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		/*
-		 * 16 old-style INTA-cycle interrupts:
-		 */
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-						      handle_level_irq, "XT");
-	}
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-static void __init smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-	 * IPI, driven by wakeup.
-	 */
-	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
-	/* IPIs for invalidation */
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
-	/* IPI for generic function call */
-	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
-	/* IPI for generic single function call */
-	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-			call_function_single_interrupt);
-
-	/* Low priority IPI to cleanup after moving an irq */
-	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-}
-
-static void __init apic_intr_init(void)
-{
-	smp_intr_init();
-
-	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
-	/* self generated IPI for local APIC timer */
-	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
-	/* generic IPI for platform specific use */
-	alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
-	/* IPI vectors for APIC spurious and error interrupts */
-	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-
-	/* Performance monitoring interrupt: */
-#ifdef CONFIG_PERF_COUNTERS
-	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
-#endif
-}
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	init_ISA_irqs();
-
-	apic_intr_init();
-
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (!test_bit(vector, used_vectors))
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index b1f4dffb919..8d82a77a3f3 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -142,7 +142,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 	gdb_regs32[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
 	gdb_regs32[GDB_CS]	= __KERNEL_CS;
 	gdb_regs32[GDB_SS]	= __KERNEL_DS;
-	gdb_regs[GDB_PC]	= p->thread.ip;
+	gdb_regs[GDB_PC]	= 0;
 	gdb_regs[GDB_R8]	= 0;
 	gdb_regs[GDB_R9]	= 0;
 	gdb_regs[GDB_R10]	= 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33019ddb56b..6551dedee20 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -195,7 +195,7 @@ static void kvm_leave_lazy_mmu(void)
 	struct kvm_para_state *state = kvm_para_state();
 
 	mmu_queue_flush(state);
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
+	paravirt_leave_lazy_mmu();
 	state->mode = paravirt_get_lazy_mode();
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 453b5795a5c..366baa17991 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -13,25 +13,13 @@
  *  Licensed under the terms of the GNU General Public
  *  License version 2. See file COPYING for details.
  */
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
 #include <linux/firmware.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
 #include <linux/pci_ids.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
 #include <linux/pci.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -79,9 +67,6 @@ struct microcode_amd {
 #define UCODE_CONTAINER_SECTION_HDR	8
 #define UCODE_CONTAINER_HEADER_SIZE	12
 
-/* serialize access to the physical write */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
 static struct equiv_cpu_entry *equiv_cpu_table;
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
@@ -144,9 +129,8 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 	return 1;
 }
 
-static void apply_microcode_amd(int cpu)
+static int apply_microcode_amd(int cpu)
 {
-	unsigned long flags;
 	u32 rev, dummy;
 	int cpu_num = raw_smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
@@ -156,25 +140,25 @@ static void apply_microcode_amd(int cpu)
 	BUG_ON(cpu_num != cpu);
 
 	if (mc_amd == NULL)
-		return;
+		return 0;
 
-	spin_lock_irqsave(&microcode_update_lock, flags);
 	wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
 	/* get patch id after patching */
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 
 	/* check current patch id and patch's id for match */
 	if (rev != mc_amd->hdr.patch_id) {
 		printk(KERN_ERR "microcode: CPU%d: update failed "
 		       "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
-		return;
+		return -1;
 	}
 
 	printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n",
 	       cpu, rev);
 
 	uci->cpu_sig.rev = rev;
+
+	return 0;
 }
 
 static int get_ucode_data(void *to, const u8 *from, size_t n)
@@ -257,13 +241,12 @@ static int install_equiv_cpu_table(const u8 *buf)
 
 static void free_equiv_cpu_table(void)
 {
-	if (equiv_cpu_table) {
-		vfree(equiv_cpu_table);
-		equiv_cpu_table = NULL;
-	}
+	vfree(equiv_cpu_table);
+	equiv_cpu_table = NULL;
 }
 
-static int generic_load_microcode(int cpu, const u8 *data, size_t size)
+static enum ucode_state
+generic_load_microcode(int cpu, const u8 *data, size_t size)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	const u8 *ucode_ptr = data;
@@ -272,12 +255,13 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover;
 	unsigned long offset;
+	enum ucode_state state = UCODE_OK;
 
 	offset = install_equiv_cpu_table(ucode_ptr);
 	if (!offset) {
 		printk(KERN_ERR "microcode: failed to create "
 		       "equivalent cpu table\n");
-		return -EINVAL;
+		return UCODE_ERROR;
 	}
 
 	ucode_ptr += offset;
@@ -293,8 +277,7 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 		mc_header = (struct microcode_header_amd *)mc;
 		if (get_matching_microcode(cpu, mc, new_rev)) {
-			if (new_mc)
-				vfree(new_mc);
+			vfree(new_mc);
 			new_rev = mc_header->patch_id;
 			new_mc  = mc;
 		} else
@@ -306,34 +289,32 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 	if (new_mc) {
 		if (!leftover) {
-			if (uci->mc)
-				vfree(uci->mc);
+			vfree(uci->mc);
 			uci->mc = new_mc;
 			pr_debug("microcode: CPU%d found a matching microcode "
 				 "update with version 0x%x (current=0x%x)\n",
 				 cpu, new_rev, uci->cpu_sig.rev);
-		} else
+		} else {
 			vfree(new_mc);
-	}
+			state = UCODE_ERROR;
+		}
+	} else
+		state = UCODE_NFOUND;
 
 	free_equiv_cpu_table();
 
-	return (int)leftover;
+	return state;
 }
 
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
 	const char *fw_name = "amd-ucode/microcode_amd.bin";
 	const struct firmware *firmware;
-	int ret;
-
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
+	enum ucode_state ret;
 
-	ret = request_firmware(&firmware, fw_name, device);
-	if (ret) {
+	if (request_firmware(&firmware, fw_name, device)) {
 		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
-		return ret;
+		return UCODE_NFOUND;
 	}
 
 	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
@@ -343,11 +324,12 @@ static int request_microcode_fw(int cpu, struct device *device)
 	return ret;
 }
 
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
 	printk(KERN_INFO "microcode: AMD microcode update via "
 	       "/dev/cpu/microcode not supported\n");
-	return -1;
+	return UCODE_ERROR;
 }
 
 static void microcode_fini_cpu_amd(int cpu)
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 98c470c069d..9c4461501fc 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -71,27 +71,18 @@
  *		Thanks to Stuart Swales for pointing out this bug.
  */
 #include <linux/platform_device.h>
-#include <linux/capability.h>
 #include <linux/miscdevice.h>
-#include <linux/firmware.h>
+#include <linux/capability.h>
 #include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
-#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
@@ -101,36 +92,110 @@ MODULE_LICENSE("GPL");
 
 static struct microcode_ops	*microcode_ops;
 
-/* no concurrent ->write()s are allowed on /dev/cpu/microcode */
+/*
+ * Synchronization.
+ *
+ * All non cpu-hotplug-callback call sites use:
+ *
+ * - microcode_mutex to synchronize with each other;
+ * - get/put_online_cpus() to synchronize with
+ *   the cpu-hotplug-callback call sites.
+ *
+ * We guarantee that only a single cpu is being
+ * updated at any particular moment of time.
+ */
 static DEFINE_MUTEX(microcode_mutex);
 
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
+/*
+ * Operations that are run on a target cpu:
+ */
+
+struct cpu_info_ctx {
+	struct cpu_signature	*cpu_sig;
+	int			err;
+};
+
+static void collect_cpu_info_local(void *arg)
+{
+	struct cpu_info_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(),
+						   ctx->cpu_sig);
+}
+
+static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig)
+{
+	struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
+static int collect_cpu_info(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	int ret;
+
+	memset(uci, 0, sizeof(*uci));
+
+	ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig);
+	if (!ret)
+		uci->valid = 1;
+
+	return ret;
+}
+
+struct apply_microcode_ctx {
+	int err;
+};
+
+static void apply_microcode_local(void *arg)
+{
+	struct apply_microcode_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+}
+
+static int apply_microcode_on_target(int cpu)
+{
+	struct apply_microcode_ctx ctx = { .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
 #ifdef CONFIG_MICROCODE_OLD_INTERFACE
 static int do_microcode_update(const void __user *buf, size_t size)
 {
-	cpumask_t old;
 	int error = 0;
 	int cpu;
 
-	old = current->cpus_allowed;
-
 	for_each_online_cpu(cpu) {
 		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+		enum ucode_state ustate;
 
 		if (!uci->valid)
 			continue;
 
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-		error = microcode_ops->request_microcode_user(cpu, buf, size);
-		if (error < 0)
-			goto out;
-		if (!error)
-			microcode_ops->apply_microcode(cpu);
+		ustate = microcode_ops->request_microcode_user(cpu, buf, size);
+		if (ustate == UCODE_ERROR) {
+			error = -1;
+			break;
+		} else if (ustate == UCODE_OK)
+			apply_microcode_on_target(cpu);
 	}
-out:
-	set_cpus_allowed_ptr(current, &old);
+
 	return error;
 }
 
@@ -143,19 +208,17 @@ static int microcode_open(struct inode *unused1, struct file *unused2)
 static ssize_t microcode_write(struct file *file, const char __user *buf,
 			       size_t len, loff_t *ppos)
 {
-	ssize_t ret;
+	ssize_t ret = -EINVAL;
 
 	if ((len >> PAGE_SHIFT) > num_physpages) {
-		printk(KERN_ERR "microcode: too much data (max %ld pages)\n",
-		       num_physpages);
-		return -EINVAL;
+		pr_err("microcode: too much data (max %ld pages)\n", num_physpages);
+		return ret;
 	}
 
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
 
-	ret = do_microcode_update(buf, len);
-	if (!ret)
+	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
 	mutex_unlock(&microcode_mutex);
@@ -165,15 +228,15 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 }
 
 static const struct file_operations microcode_fops = {
-	.owner		= THIS_MODULE,
-	.write		= microcode_write,
-	.open		= microcode_open,
+	.owner			= THIS_MODULE,
+	.write			= microcode_write,
+	.open			= microcode_open,
 };
 
 static struct miscdevice microcode_dev = {
-	.minor		= MICROCODE_MINOR,
-	.name		= "microcode",
-	.fops		= &microcode_fops,
+	.minor			= MICROCODE_MINOR,
+	.name			= "microcode",
+	.fops			= &microcode_fops,
 };
 
 static int __init microcode_dev_init(void)
@@ -182,9 +245,7 @@ static int __init microcode_dev_init(void)
 
 	error = misc_register(&microcode_dev);
 	if (error) {
-		printk(KERN_ERR
-			"microcode: can't misc_register on minor=%d\n",
-			MICROCODE_MINOR);
+		pr_err("microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR);
 		return error;
 	}
 
@@ -205,42 +266,51 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static long reload_for_cpu(void *unused)
+static int reload_for_cpu(int cpu)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	int err = 0;
 
 	mutex_lock(&microcode_mutex);
 	if (uci->valid) {
-		err = microcode_ops->request_microcode_fw(smp_processor_id(),
-							  &microcode_pdev->dev);
-		if (!err)
-			microcode_ops->apply_microcode(smp_processor_id());
+		enum ucode_state ustate;
+
+		ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
+		if (ustate == UCODE_OK)
+			apply_microcode_on_target(cpu);
+		else
+			if (ustate == UCODE_ERROR)
+				err = -EINVAL;
 	}
 	mutex_unlock(&microcode_mutex);
+
 	return err;
 }
 
 static ssize_t reload_store(struct sys_device *dev,
 			    struct sysdev_attribute *attr,
-			    const char *buf, size_t sz)
+			    const char *buf, size_t size)
 {
-	char *end;
-	unsigned long val = simple_strtoul(buf, &end, 0);
-	int err = 0;
+	unsigned long val;
 	int cpu = dev->id;
+	int ret = 0;
+	char *end;
 
+	val = simple_strtoul(buf, &end, 0);
 	if (end == buf)
 		return -EINVAL;
+
 	if (val == 1) {
 		get_online_cpus();
 		if (cpu_online(cpu))
-			err = work_on_cpu(cpu, reload_for_cpu, NULL);
+			ret = reload_for_cpu(cpu);
 		put_online_cpus();
 	}
-	if (err)
-		return err;
-	return sz;
+
+	if (!ret)
+		ret = size;
+
+	return ret;
 }
 
 static ssize_t version_show(struct sys_device *dev,
@@ -271,11 +341,11 @@ static struct attribute *mc_default_attrs[] = {
 };
 
 static struct attribute_group mc_attr_group = {
-	.attrs		= mc_default_attrs,
-	.name		= "microcode",
+	.attrs			= mc_default_attrs,
+	.name			= "microcode",
 };
 
-static void __microcode_fini_cpu(int cpu)
+static void microcode_fini_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
@@ -283,103 +353,68 @@ static void __microcode_fini_cpu(int cpu)
 	uci->valid = 0;
 }
 
-static void microcode_fini_cpu(int cpu)
-{
-	mutex_lock(&microcode_mutex);
-	__microcode_fini_cpu(cpu);
-	mutex_unlock(&microcode_mutex);
-}
-
-static void collect_cpu_info(int cpu)
+static enum ucode_state microcode_resume_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-	memset(uci, 0, sizeof(*uci));
-	if (!microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig))
-		uci->valid = 1;
+	if (!uci->mc)
+		return UCODE_NFOUND;
+
+	pr_debug("microcode: CPU%d updated upon resume\n", cpu);
+	apply_microcode_on_target(cpu);
+
+	return UCODE_OK;
 }
 
-static int microcode_resume_cpu(int cpu)
+static enum ucode_state microcode_init_cpu(int cpu)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct cpu_signature nsig;
+	enum ucode_state ustate;
 
-	pr_debug("microcode: CPU%d resumed\n", cpu);
+	if (collect_cpu_info(cpu))
+		return UCODE_ERROR;
 
-	if (!uci->mc)
-		return 1;
+	/* --dimm. Trigger a delayed update? */
+	if (system_state != SYSTEM_RUNNING)
+		return UCODE_NFOUND;
 
-	/*
-	 * Let's verify that the 'cached' ucode does belong
-	 * to this cpu (a bit of paranoia):
-	 */
-	if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
-		__microcode_fini_cpu(cpu);
-		printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
-				cpu);
-		return -1;
-	}
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
 
-	if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
-		__microcode_fini_cpu(cpu);
-		printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
-				cpu);
-		/* Should we look for a new ucode here? */
-		return 1;
+	if (ustate == UCODE_OK) {
+		pr_debug("microcode: CPU%d updated upon init\n", cpu);
+		apply_microcode_on_target(cpu);
 	}
 
-	return 0;
+	return ustate;
 }
 
-static long microcode_update_cpu(void *unused)
+static enum ucode_state microcode_update_cpu(int cpu)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
-	int err = 0;
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	enum ucode_state ustate;
 
-	/*
-	 * Check if the system resume is in progress (uci->valid != NULL),
-	 * otherwise just request a firmware:
-	 */
-	if (uci->valid) {
-		err = microcode_resume_cpu(smp_processor_id());
-	} else {
-		collect_cpu_info(smp_processor_id());
-		if (uci->valid && system_state == SYSTEM_RUNNING)
-			err = microcode_ops->request_microcode_fw(
-					smp_processor_id(),
-					&microcode_pdev->dev);
-	}
-	if (!err)
-		microcode_ops->apply_microcode(smp_processor_id());
-	return err;
-}
+	if (uci->valid)
+		ustate = microcode_resume_cpu(cpu);
+	else
+		ustate = microcode_init_cpu(cpu);
 
-static int microcode_init_cpu(int cpu)
-{
-	int err;
-	mutex_lock(&microcode_mutex);
-	err = work_on_cpu(cpu, microcode_update_cpu, NULL);
-	mutex_unlock(&microcode_mutex);
-
-	return err;
+	return ustate;
 }
 
 static int mc_sysdev_add(struct sys_device *sys_dev)
 {
 	int err, cpu = sys_dev->id;
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 	if (!cpu_online(cpu))
 		return 0;
 
 	pr_debug("microcode: CPU%d added\n", cpu);
-	memset(uci, 0, sizeof(*uci));
 
 	err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
 	if (err)
 		return err;
 
-	err = microcode_init_cpu(cpu);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
+		err = -EINVAL;
 
 	return err;
 }
@@ -400,19 +435,30 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
 static int mc_sysdev_resume(struct sys_device *dev)
 {
 	int cpu = dev->id;
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 	if (!cpu_online(cpu))
 		return 0;
 
-	/* only CPU 0 will apply ucode here */
-	microcode_update_cpu(NULL);
+	/*
+	 * All non-bootup cpus are still disabled,
+	 * so only CPU 0 will apply ucode here.
+	 *
+	 * Moreover, there can be no concurrent
+	 * updates from any other places at this point.
+	 */
+	WARN_ON(cpu != 0);
+
+	if (uci->valid && uci->mc)
+		microcode_ops->apply_microcode(cpu);
+
 	return 0;
 }
 
 static struct sysdev_driver mc_sysdev_driver = {
-	.add		= mc_sysdev_add,
-	.remove		= mc_sysdev_remove,
-	.resume		= mc_sysdev_resume,
+	.add			= mc_sysdev_add,
+	.remove			= mc_sysdev_remove,
+	.resume			= mc_sysdev_resume,
 };
 
 static __cpuinit int
@@ -425,15 +471,12 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		if (microcode_init_cpu(cpu))
-			printk(KERN_ERR "microcode: failed to init CPU%d\n",
-			       cpu);
+		microcode_update_cpu(cpu);
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		pr_debug("microcode: CPU%d added\n", cpu);
 		if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group))
-			printk(KERN_ERR "microcode: Failed to create the sysfs "
-				"group for CPU%d\n", cpu);
+			pr_err("microcode: Failed to create group for CPU%d\n", cpu);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -465,13 +508,10 @@ static int __init microcode_init(void)
 		microcode_ops = init_amd_microcode();
 
 	if (!microcode_ops) {
-		printk(KERN_ERR "microcode: no support for this CPU vendor\n");
+		pr_err("microcode: no support for this CPU vendor\n");
 		return -ENODEV;
 	}
 
-	error = microcode_dev_init();
-	if (error)
-		return error;
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
 	if (IS_ERR(microcode_pdev)) {
@@ -480,23 +520,31 @@ static int __init microcode_init(void)
 	}
 
 	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
 	error = sysdev_driver_register(&cpu_sysdev_class, &mc_sysdev_driver);
+
+	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
+
 	if (error) {
-		microcode_dev_exit();
 		platform_device_unregister(microcode_pdev);
 		return error;
 	}
 
+	error = microcode_dev_init();
+	if (error)
+		return error;
+
 	register_hotcpu_notifier(&mc_cpu_notifier);
 
-	printk(KERN_INFO
-	       "Microcode Update Driver: v" MICROCODE_VERSION
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
 	       " <tigran@aivazian.fsnet.co.uk>,"
 	       " Peter Oruba\n");
 
 	return 0;
 }
+module_init(microcode_init);
 
 static void __exit microcode_exit(void)
 {
@@ -505,16 +553,17 @@ static void __exit microcode_exit(void)
 	unregister_hotcpu_notifier(&mc_cpu_notifier);
 
 	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
 	sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+
+	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
 	platform_device_unregister(microcode_pdev);
 
 	microcode_ops = NULL;
 
-	printk(KERN_INFO
-	       "Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
 }
-
-module_init(microcode_init);
 module_exit(microcode_exit);
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 149b9ec7c1a..0d334ddd0a9 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -70,24 +70,11 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
 #include <linux/firmware.h>
-#include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -150,13 +137,9 @@ struct extended_sigtable {
 
 #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
 
-/* serialize access to the physical write to MSR 0x79 */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-	unsigned long flags;
 	unsigned int val[2];
 
 	memset(csig, 0, sizeof(*csig));
@@ -176,18 +159,14 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 		csig->pf = 1 << ((val[1] >> 18) & 7);
 	}
 
-	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);
-
 	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
 	/* see notes above for revision 1.07.  Apparent chip bug */
 	sync_core();
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 
-	pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
-			csig->sig, csig->pf, csig->rev);
+	printk(KERN_INFO "microcode: CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
+			cpu_num, csig->sig, csig->pf, csig->rev);
 
 	return 0;
 }
@@ -318,11 +297,10 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev)
 	return 0;
 }
 
-static void apply_microcode(int cpu)
+static int apply_microcode(int cpu)
 {
 	struct microcode_intel *mc_intel;
 	struct ucode_cpu_info *uci;
-	unsigned long flags;
 	unsigned int val[2];
 	int cpu_num;
 
@@ -334,10 +312,7 @@ static void apply_microcode(int cpu)
 	BUG_ON(cpu_num != cpu);
 
 	if (mc_intel == NULL)
-		return;
-
-	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);
+		return 0;
 
 	/* write microcode via MSR 0x79 */
 	wrmsr(MSR_IA32_UCODE_WRITE,
@@ -351,30 +326,32 @@ static void apply_microcode(int cpu)
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
 
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 	if (val[1] != mc_intel->hdr.rev) {
-		printk(KERN_ERR "microcode: CPU%d update from revision "
-				"0x%x to 0x%x failed\n",
-			cpu_num, uci->cpu_sig.rev, val[1]);
-		return;
+		printk(KERN_ERR "microcode: CPU%d update "
+				"to revision 0x%x failed\n",
+			cpu_num, mc_intel->hdr.rev);
+		return -1;
 	}
-	printk(KERN_INFO "microcode: CPU%d updated from revision "
-			 "0x%x to 0x%x, date = %04x-%02x-%02x \n",
-		cpu_num, uci->cpu_sig.rev, val[1],
+	printk(KERN_INFO "microcode: CPU%d updated to revision "
+			 "0x%x, date = %04x-%02x-%02x \n",
+		cpu_num, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
 		(mc_intel->hdr.date >> 16) & 0xff);
 
 	uci->cpu_sig.rev = val[1];
+
+	return 0;
 }
 
-static int generic_load_microcode(int cpu, void *data, size_t size,
-		int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
+				int (*get_ucode_data)(void *, const void *, size_t))
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	u8 *ucode_ptr = data, *new_mc = NULL, *mc;
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover = size;
+	enum ucode_state state = UCODE_OK;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -412,11 +389,15 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (!new_mc)
+	if (leftover) {
+		if (new_mc)
+			vfree(new_mc);
+		state = UCODE_ERROR;
 		goto out;
+	}
 
-	if (leftover) {
-		vfree(new_mc);
+	if (!new_mc) {
+		state = UCODE_NFOUND;
 		goto out;
 	}
 
@@ -427,9 +408,8 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 	pr_debug("microcode: CPU%d found a matching microcode update with"
 		 " version 0x%x (current=0x%x)\n",
 			cpu, new_rev, uci->cpu_sig.rev);
-
- out:
-	return (int)leftover;
+out:
+	return state;
 }
 
 static int get_ucode_fw(void *to, const void *from, size_t n)
@@ -438,21 +418,19 @@ static int get_ucode_fw(void *to, const void *from, size_t n)
 	return 0;
 }
 
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
 	char name[30];
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	const struct firmware *firmware;
-	int ret;
+	enum ucode_state ret;
 
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
-	ret = request_firmware(&firmware, name, device);
-	if (ret) {
+
+	if (request_firmware(&firmware, name, device)) {
 		pr_debug("microcode: data file %s load failed\n", name);
-		return ret;
+		return UCODE_NFOUND;
 	}
 
 	ret = generic_load_microcode(cpu, (void *)firmware->data,
@@ -468,11 +446,9 @@ static int get_ucode_user(void *to, const void *from, size_t n)
 	return copy_from_user(to, from, n);
 }
 
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
-
 	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 70fd7e414c1..651c93b2886 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -17,6 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/smp.h>
+#include <linux/pci.h>
 
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
@@ -870,24 +871,17 @@ static
 inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
 #endif /* CONFIG_X86_IO_APIC */
 
-static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length,
-		      int count)
+static int
+check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
 {
-	if (!mpc_new_phys) {
-		pr_info("No spare slots, try to append...take your risk, "
-			"new mpc_length %x\n", count);
-	} else {
-		if (count <= mpc_new_length)
-			pr_info("No spare slots, try to append..., "
-				"new mpc_length %x\n", count);
-		else {
-			pr_err("mpc_new_length %lx is too small\n",
-				mpc_new_length);
-			return -1;
-		}
+	int ret = 0;
+
+	if (!mpc_new_phys || count <= mpc_new_length) {
+		WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
+		return -1;
 	}
 
-	return 0;
+	return ret;
 }
 
 static int  __init replace_intsrc_all(struct mpc_table *mpc,
@@ -946,7 +940,7 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
 		} else {
 			struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
 			count += sizeof(struct mpc_intsrc);
-			if (!check_slot(mpc_new_phys, mpc_new_length, count))
+			if (check_slot(mpc_new_phys, mpc_new_length, count) < 0)
 				goto out;
 			assign_to_mpc_intsrc(&mp_irqs[i], m);
 			mpc->length = count;
@@ -963,11 +957,14 @@ out:
 	return 0;
 }
 
-static int __initdata enable_update_mptable;
+int enable_update_mptable;
 
 static int __init update_mptable_setup(char *str)
 {
 	enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+	pci_routeirq = 1;
+#endif
 	return 0;
 }
 early_param("update_mptable", update_mptable_setup);
@@ -980,6 +977,9 @@ static int __initdata alloc_mptable;
 static int __init parse_alloc_mptable_opt(char *p)
 {
 	enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+	pci_routeirq = 1;
+#endif
 	alloc_mptable = 1;
 	if (!p)
 		return 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9faf43bea33..70ec9b951d7 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -248,18 +248,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LA
 
 static inline void enter_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
 
-	__get_cpu_var(paravirt_lazy_mode) = mode;
+	percpu_write(paravirt_lazy_mode, mode);
 }
 
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != mode);
 
-	__get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+	percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 void paravirt_enter_lazy_mmu(void)
@@ -269,22 +267,36 @@ void paravirt_enter_lazy_mmu(void)
 
 void paravirt_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
-void paravirt_enter_lazy_cpu(void)
+void paravirt_start_context_switch(struct task_struct *prev)
 {
+	BUG_ON(preemptible());
+
+	if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
 	enter_lazy(PARAVIRT_LAZY_CPU);
 }
 
-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+	BUG_ON(preemptible());
+
+	leave_lazy(PARAVIRT_LAZY_CPU);
+
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 {
-	return __get_cpu_var(paravirt_lazy_mode);
+	if (in_interrupt())
+		return PARAVIRT_LAZY_NONE;
+
+	return percpu_read(paravirt_lazy_mode);
 }
 
 void arch_flush_lazy_mmu_mode(void)
@@ -292,7 +304,6 @@ void arch_flush_lazy_mmu_mode(void)
 	preempt_disable();
 
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		WARN_ON(preempt_count() == 1);
 		arch_leave_lazy_mmu_mode();
 		arch_enter_lazy_mmu_mode();
 	}
@@ -300,19 +311,6 @@ void arch_flush_lazy_mmu_mode(void)
 	preempt_enable();
 }
 
-void arch_flush_lazy_cpu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-		WARN_ON(preempt_count() == 1);
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -404,10 +402,8 @@ struct pv_cpu_ops pv_cpu_ops = {
 	.set_iopl_mask = native_set_iopl_mask,
 	.io_delay = native_io_delay,
 
-	.lazy_mode = {
-		.enter = paravirt_nop,
-		.leave = paravirt_nop,
-	},
+	.start_context_switch = paravirt_nop,
+	.end_context_switch = paravirt_nop,
 };
 
 struct pv_apic_ops pv_apic_ops = {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 755c21e906f..971a3bec47a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -186,37 +186,6 @@ static struct cal_chipset_ops calioc2_chip_ops = {
 
 static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
 
-/* enable this to stress test the chip's TCE cache */
-#ifdef CONFIG_IOMMU_DEBUG
-static int debugging = 1;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
-	int expected, unsigned long start, unsigned long end)
-{
-	unsigned long idx = start;
-
-	BUG_ON(start >= end);
-
-	while (idx < end) {
-		if (!!test_bit(idx, bitmap) != expected)
-			return idx;
-		++idx;
-	}
-
-	/* all bits have the expected value */
-	return ~0UL;
-}
-#else /* debugging is disabled */
-static int debugging;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
-	int expected, unsigned long start, unsigned long end)
-{
-	return ~0UL;
-}
-
-#endif /* CONFIG_IOMMU_DEBUG */
-
 static inline int translation_enabled(struct iommu_table *tbl)
 {
 	/* only PHBs with translation enabled have an IOMMU table */
@@ -228,7 +197,6 @@ static void iommu_range_reserve(struct iommu_table *tbl,
 {
 	unsigned long index;
 	unsigned long end;
-	unsigned long badbit;
 	unsigned long flags;
 
 	index = start_addr >> PAGE_SHIFT;
@@ -243,14 +211,6 @@ static void iommu_range_reserve(struct iommu_table *tbl,
 
 	spin_lock_irqsave(&tbl->it_lock, flags);
 
-	badbit = verify_bit_range(tbl->it_map, 0, index, end);
-	if (badbit != ~0UL) {
-		if (printk_ratelimit())
-			printk(KERN_ERR "Calgary: entry already allocated at "
-			       "0x%lx tbl %p dma 0x%lx npages %u\n",
-			       badbit, tbl, start_addr, npages);
-	}
-
 	iommu_area_reserve(tbl->it_map, index, npages);
 
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
@@ -326,7 +286,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned int npages)
 {
 	unsigned long entry;
-	unsigned long badbit;
 	unsigned long badend;
 	unsigned long flags;
 
@@ -346,14 +305,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 	spin_lock_irqsave(&tbl->it_lock, flags);
 
-	badbit = verify_bit_range(tbl->it_map, 1, entry, entry + npages);
-	if (badbit != ~0UL) {
-		if (printk_ratelimit())
-			printk(KERN_ERR "Calgary: bit is off at 0x%lx "
-			       "tbl %p dma 0x%Lx entry 0x%lx npages %u\n",
-			       badbit, tbl, dma_addr, entry, npages);
-	}
-
 	iommu_area_free(tbl->it_map, entry, npages);
 
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
@@ -1488,9 +1439,8 @@ void __init detect_calgary(void)
 		iommu_detected = 1;
 		calgary_detected = 1;
 		printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n");
-		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
-		       "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
-		       debugging ? "enabled" : "disabled");
+		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n",
+		       specified_table_size);
 
 		/* swiotlb for devices that aren't behind the Calgary. */
 		if (max_pfn > MAX_DMA32_PFN)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index b284b58c035..cfd9f906389 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -144,48 +144,21 @@ static void flush_gart(void)
 }
 
 #ifdef CONFIG_IOMMU_LEAK
-
-#define SET_LEAK(x)							\
-	do {								\
-		if (iommu_leak_tab)					\
-			iommu_leak_tab[x] = __builtin_return_address(0);\
-	} while (0)
-
-#define CLEAR_LEAK(x)							\
-	do {								\
-		if (iommu_leak_tab)					\
-			iommu_leak_tab[x] = NULL;			\
-	} while (0)
-
 /* Debugging aid for drivers that don't free their IOMMU tables */
-static void **iommu_leak_tab;
 static int leak_trace;
 static int iommu_leak_pages = 20;
 
 static void dump_leak(void)
 {
-	int i;
 	static int dump;
 
-	if (dump || !iommu_leak_tab)
+	if (dump)
 		return;
 	dump = 1;
-	show_stack(NULL, NULL);
 
-	/* Very crude. dump some from the end of the table too */
-	printk(KERN_DEBUG "Dumping %d pages from end of IOMMU:\n",
-	       iommu_leak_pages);
-	for (i = 0; i < iommu_leak_pages; i += 2) {
-		printk(KERN_DEBUG "%lu: ", iommu_pages-i);
-		printk_address((unsigned long) iommu_leak_tab[iommu_pages-i],
-				0);
-		printk(KERN_CONT "%c", (i+1)%2 == 0 ? '\n' : ' ');
-	}
-	printk(KERN_DEBUG "\n");
+	show_stack(NULL, NULL);
+	debug_dma_dump_mappings(NULL);
 }
-#else
-# define SET_LEAK(x)
-# define CLEAR_LEAK(x)
 #endif
 
 static void iommu_full(struct device *dev, size_t size, int dir)
@@ -248,7 +221,6 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = GPTE_ENCODE(phys_mem);
-		SET_LEAK(iommu_page + i);
 		phys_mem += PAGE_SIZE;
 	}
 	return iommu_bus_base + iommu_page*PAGE_SIZE + (phys_mem & ~PAGE_MASK);
@@ -294,7 +266,6 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
-		CLEAR_LEAK(iommu_page + i);
 	}
 	free_iommu(iommu_page, npages);
 }
@@ -377,7 +348,6 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
 		pages = iommu_num_pages(s->offset, s->length, PAGE_SIZE);
 		while (pages--) {
 			iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
-			SET_LEAK(iommu_page);
 			addr += PAGE_SIZE;
 			iommu_page++;
 		}
@@ -688,8 +658,6 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	agp_gatt_table = gatt;
 
-	enable_gart_translations();
-
 	error = sysdev_class_register(&gart_sysdev_class);
 	if (!error)
 		error = sysdev_register(&device_gart);
@@ -801,11 +769,12 @@ void __init gart_iommu_init(void)
 
 #ifdef CONFIG_IOMMU_LEAK
 	if (leak_trace) {
-		iommu_leak_tab = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
-				  get_order(iommu_pages*sizeof(void *)));
-		if (!iommu_leak_tab)
+		int ret;
+
+		ret = dma_debug_resize_entries(iommu_pages);
+		if (ret)
 			printk(KERN_DEBUG
-			       "PCI-DMA: Cannot allocate leak trace area\n");
+			       "PCI-DMA: Cannot trace all the entries\n");
 	}
 #endif
 
@@ -845,6 +814,14 @@ void __init gart_iommu_init(void)
 	 * the pages as Not-Present:
 	 */
 	wbinvd();
+	
+	/*
+	 * Now all caches are flushed and we can safely enable
+	 * GART hardware.  Doing it early leaves the possibility
+	 * of stale cache entries that can lead to GART PTE
+	 * errors.
+	 */
+	enable_gart_translations();
 
 	/*
 	 * Try to workaround a bug (thanks to BenH):
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 221a3853e26..a1712f2b50f 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -28,7 +28,7 @@ dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
 {
 	return baddr;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ca989158e84..3bb2be1649b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,12 +8,15 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <linux/random.h>
 #include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/syscalls.h>
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
+#include <asm/ds.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -45,6 +48,8 @@ void free_thread_xstate(struct task_struct *tsk)
 		kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
 		tsk->thread.xstate = NULL;
 	}
+
+	WARN(tsk->thread.ds_ctx, "leaking DS context\n");
 }
 
 void free_thread_info(struct thread_info *ti)
@@ -83,8 +88,6 @@ void exit_thread(void)
 		put_cpu();
 		kfree(bp);
 	}
-
-	ds_exit_thread(current);
 }
 
 void flush_thread(void)
@@ -613,3 +616,16 @@ static int __init idle_setup(char *str)
 }
 early_param("idle", idle_setup);
 
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_int() % 8192;
+	return sp & ~0xf;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long range_end = mm->brk + 0x02000000;
+	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+}
+
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 76f8f84043a..59f4524984a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,8 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -33,7 +31,6 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/personality.h>
 #include <linux/tick.h>
 #include <linux/percpu.h>
@@ -290,7 +287,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		p->thread.io_bitmap_max = 0;
 	}
 
-	ds_copy_thread(p, current);
+	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+	p->thread.ds_ctx = NULL;
 
 	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
 	p->thread.debugctlmsr = 0;
@@ -407,7 +405,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
@@ -497,15 +495,3 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b751a41392b..ebefb5407b9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,8 +14,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -32,7 +30,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -335,7 +332,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 			goto out;
 	}
 
-	ds_copy_thread(p, me);
+	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+	p->thread.ds_ctx = NULL;
 
 	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
 	p->thread.debugctlmsr = 0;
@@ -428,7 +426,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/*
 	 * Switch FS and GS.
@@ -660,15 +658,3 @@ long sys_arch_prctl(int code, unsigned long addr)
 	return do_arch_prctl(current, code, addr);
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 23b7c8f017e..09ecbde91c1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
+#include <linux/workqueue.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -578,17 +579,130 @@ static int ioperm_get(struct task_struct *target,
 }
 
 #ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * A branch trace store context.
+ *
+ * Contexts may only be installed by ptrace_bts_config() and only for
+ * ptraced tasks.
+ *
+ * Contexts are destroyed when the tracee is detached from the tracer.
+ * The actual destruction work requires interrupts enabled, so the
+ * work is deferred and will be scheduled during __ptrace_unlink().
+ *
+ * Contexts hold an additional task_struct reference on the traced
+ * task, as well as a reference on the tracer's mm.
+ *
+ * Ptrace already holds a task_struct for the duration of ptrace operations,
+ * but since destruction is deferred, it may be executed after both
+ * tracer and tracee exited.
+ */
+struct bts_context {
+	/* The branch trace handle. */
+	struct bts_tracer	*tracer;
+
+	/* The buffer used to store the branch trace and its size. */
+	void			*buffer;
+	unsigned int		size;
+
+	/* The mm that paid for the above buffer. */
+	struct mm_struct	*mm;
+
+	/* The task this context belongs to. */
+	struct task_struct	*task;
+
+	/* The signal to send on a bts buffer overflow. */
+	unsigned int		bts_ovfl_signal;
+
+	/* The work struct to destroy a context. */
+	struct work_struct	work;
+};
+
+static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
+{
+	void *buffer = NULL;
+	int err = -ENOMEM;
+
+	err = account_locked_memory(current->mm, current->signal->rlim, size);
+	if (err < 0)
+		return err;
+
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
+		goto out_refund;
+
+	context->buffer = buffer;
+	context->size = size;
+	context->mm = get_task_mm(current);
+
+	return 0;
+
+ out_refund:
+	refund_locked_memory(current->mm, size);
+	return err;
+}
+
+static inline void free_bts_buffer(struct bts_context *context)
+{
+	if (!context->buffer)
+		return;
+
+	kfree(context->buffer);
+	context->buffer = NULL;
+
+	refund_locked_memory(context->mm, context->size);
+	context->size = 0;
+
+	mmput(context->mm);
+	context->mm = NULL;
+}
+
+static void free_bts_context_work(struct work_struct *w)
+{
+	struct bts_context *context;
+
+	context = container_of(w, struct bts_context, work);
+
+	ds_release_bts(context->tracer);
+	put_task_struct(context->task);
+	free_bts_buffer(context);
+	kfree(context);
+}
+
+static inline void free_bts_context(struct bts_context *context)
+{
+	INIT_WORK(&context->work, free_bts_context_work);
+	schedule_work(&context->work);
+}
+
+static inline struct bts_context *alloc_bts_context(struct task_struct *task)
+{
+	struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (context) {
+		context->task = task;
+		task->bts = context;
+
+		get_task_struct(task);
+	}
+
+	return context;
+}
+
 static int ptrace_bts_read_record(struct task_struct *child, size_t index,
 				  struct bts_struct __user *out)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	struct bts_struct bts;
 	const unsigned char *at;
 	int error;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	at = trace->ds.top - ((index + 1) * trace->ds.size);
 	if ((void *)at < trace->ds.begin)
@@ -597,7 +711,7 @@ static int ptrace_bts_read_record(struct task_struct *child, size_t index,
 	if (!trace->read)
 		return -EOPNOTSUPP;
 
-	error = trace->read(child->bts, at, &bts);
+	error = trace->read(context->tracer, at, &bts);
 	if (error < 0)
 		return error;
 
@@ -611,13 +725,18 @@ static int ptrace_bts_drain(struct task_struct *child,
 			    long size,
 			    struct bts_struct __user *out)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	const unsigned char *at;
 	int error, drained = 0;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	if (!trace->read)
 		return -EOPNOTSUPP;
@@ -628,9 +747,8 @@ static int ptrace_bts_drain(struct task_struct *child,
 	for (at = trace->ds.begin; (void *)at < trace->ds.top;
 	     out++, drained++, at += trace->ds.size) {
 		struct bts_struct bts;
-		int error;
 
-		error = trace->read(child->bts, at, &bts);
+		error = trace->read(context->tracer, at, &bts);
 		if (error < 0)
 			return error;
 
@@ -640,35 +758,18 @@ static int ptrace_bts_drain(struct task_struct *child,
 
 	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
 
-	error = ds_reset_bts(child->bts);
+	error = ds_reset_bts(context->tracer);
 	if (error < 0)
 		return error;
 
 	return drained;
 }
 
-static int ptrace_bts_allocate_buffer(struct task_struct *child, size_t size)
-{
-	child->bts_buffer = alloc_locked_buffer(size);
-	if (!child->bts_buffer)
-		return -ENOMEM;
-
-	child->bts_size = size;
-
-	return 0;
-}
-
-static void ptrace_bts_free_buffer(struct task_struct *child)
-{
-	free_locked_buffer(child->bts_buffer, child->bts_size);
-	child->bts_buffer = NULL;
-	child->bts_size = 0;
-}
-
 static int ptrace_bts_config(struct task_struct *child,
 			     long cfg_size,
 			     const struct ptrace_bts_config __user *ucfg)
 {
+	struct bts_context *context;
 	struct ptrace_bts_config cfg;
 	unsigned int flags = 0;
 
@@ -678,28 +779,33 @@ static int ptrace_bts_config(struct task_struct *child,
 	if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
 		return -EFAULT;
 
-	if (child->bts) {
-		ds_release_bts(child->bts);
-		child->bts = NULL;
-	}
+	context = child->bts;
+	if (!context)
+		context = alloc_bts_context(child);
+	if (!context)
+		return -ENOMEM;
 
 	if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
 		if (!cfg.signal)
 			return -EINVAL;
 
-		child->thread.bts_ovfl_signal = cfg.signal;
 		return -EOPNOTSUPP;
+		context->bts_ovfl_signal = cfg.signal;
 	}
 
-	if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
-	    (cfg.size != child->bts_size)) {
-		int error;
+	ds_release_bts(context->tracer);
+	context->tracer = NULL;
 
-		ptrace_bts_free_buffer(child);
+	if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
+		int err;
 
-		error = ptrace_bts_allocate_buffer(child, cfg.size);
-		if (error < 0)
-			return error;
+		free_bts_buffer(context);
+		if (!cfg.size)
+			return 0;
+
+		err = alloc_bts_buffer(context, cfg.size);
+		if (err < 0)
+			return err;
 	}
 
 	if (cfg.flags & PTRACE_BTS_O_TRACE)
@@ -708,15 +814,14 @@ static int ptrace_bts_config(struct task_struct *child,
 	if (cfg.flags & PTRACE_BTS_O_SCHED)
 		flags |= BTS_TIMESTAMPS;
 
-	child->bts = ds_request_bts(child, child->bts_buffer, child->bts_size,
-				    /* ovfl = */ NULL, /* th = */ (size_t)-1,
-				    flags);
-	if (IS_ERR(child->bts)) {
-		int error = PTR_ERR(child->bts);
-
-		ptrace_bts_free_buffer(child);
-		child->bts = NULL;
+	context->tracer =
+		ds_request_bts_task(child, context->buffer, context->size,
+				    NULL, (size_t)-1, flags);
+	if (unlikely(IS_ERR(context->tracer))) {
+		int error = PTR_ERR(context->tracer);
 
+		free_bts_buffer(context);
+		context->tracer = NULL;
 		return error;
 	}
 
@@ -727,20 +832,25 @@ static int ptrace_bts_status(struct task_struct *child,
 			     long cfg_size,
 			     struct ptrace_bts_config __user *ucfg)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	struct ptrace_bts_config cfg;
 
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
 	if (cfg_size < sizeof(cfg))
 		return -EIO;
 
-	trace = ds_read_bts(child->bts);
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	memset(&cfg, 0, sizeof(cfg));
-	cfg.size = trace->ds.end - trace->ds.begin;
-	cfg.signal = child->thread.bts_ovfl_signal;
-	cfg.bts_size = sizeof(struct bts_struct);
+	cfg.size	= trace->ds.end - trace->ds.begin;
+	cfg.signal	= context->bts_ovfl_signal;
+	cfg.bts_size	= sizeof(struct bts_struct);
 
 	if (cfg.signal)
 		cfg.flags |= PTRACE_BTS_O_SIGNAL;
@@ -759,80 +869,51 @@ static int ptrace_bts_status(struct task_struct *child,
 
 static int ptrace_bts_clear(struct task_struct *child)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
 
-	return ds_reset_bts(child->bts);
+	return ds_reset_bts(context->tracer);
 }
 
 static int ptrace_bts_size(struct task_struct *child)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	return (trace->ds.top - trace->ds.begin) / trace->ds.size;
 }
 
-static void ptrace_bts_fork(struct task_struct *tsk)
-{
-	tsk->bts = NULL;
-	tsk->bts_buffer = NULL;
-	tsk->bts_size = 0;
-	tsk->thread.bts_ovfl_signal = 0;
-}
-
-static void ptrace_bts_untrace(struct task_struct *child)
+/*
+ * Called from __ptrace_unlink() after the child has been moved back
+ * to its original parent.
+ */
+void ptrace_bts_untrace(struct task_struct *child)
 {
 	if (unlikely(child->bts)) {
-		ds_release_bts(child->bts);
+		free_bts_context(child->bts);
 		child->bts = NULL;
-
-		/* We cannot update total_vm and locked_vm since
-		   child's mm is already gone. But we can reclaim the
-		   memory. */
-		kfree(child->bts_buffer);
-		child->bts_buffer = NULL;
-		child->bts_size = 0;
 	}
 }
-
-static void ptrace_bts_detach(struct task_struct *child)
-{
-	/*
-	 * Ptrace_detach() races with ptrace_untrace() in case
-	 * the child dies and is reaped by another thread.
-	 *
-	 * We only do the memory accounting at this point and
-	 * leave the buffer deallocation and the bts tracer
-	 * release to ptrace_bts_untrace() which will be called
-	 * later on with tasklist_lock held.
-	 */
-	release_locked_buffer(child->bts_buffer, child->bts_size);
-}
-#else
-static inline void ptrace_bts_fork(struct task_struct *tsk) {}
-static inline void ptrace_bts_detach(struct task_struct *child) {}
-static inline void ptrace_bts_untrace(struct task_struct *child) {}
 #endif /* CONFIG_X86_PTRACE_BTS */
 
-void x86_ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
-	ptrace_bts_fork(child);
-}
-
-void x86_ptrace_untrace(struct task_struct *child)
-{
-	ptrace_bts_untrace(child);
-}
-
 /*
  * Called by kernel/ptrace.c when detaching..
  *
@@ -844,7 +925,6 @@ void ptrace_disable(struct task_struct *child)
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
-	ptrace_bts_detach(child);
 }
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7563b31b4f0..af71d06624b 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -491,5 +491,42 @@ void force_hpet_resume(void)
 		break;
 	}
 }
+#endif
+
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
+/* Set correct numa_node information for AMD NB functions */
+static void __init quirk_amd_nb_node(struct pci_dev *dev)
+{
+	struct pci_dev *nb_ht;
+	unsigned int devfn;
+	u32 val;
+
+	devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+	nb_ht = pci_get_slot(dev->bus, devfn);
+	if (!nb_ht)
+		return;
+
+	pci_read_config_dword(nb_ht, 0x60, &val);
+	set_dev_node(&dev->dev, val & 7);
+	pci_dev_put(dev);
+}
 
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_HT,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MAP,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
+			quirk_amd_nb_node);
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 667188e0b5a..d2d1ce8170f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -192,6 +192,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
 		},
 	},
+	{   /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 360",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
+			DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4158439bf6..d1c636bf31a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,14 @@
 #define ARCH_SETUP
 #endif
 
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
 RESERVE_BRK(dmi_alloc, 65536);
 
 unsigned int boot_cpu_id __read_mostly;
@@ -214,8 +222,8 @@ unsigned long mmu_cr4_features;
 unsigned long mmu_cr4_features = X86_CR4_PAE;
 #endif
 
-/* Boot loader ID as an integer, for the benefit of proc_dointvec */
-int bootloader_type;
+/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
+int bootloader_type, bootloader_version;
 
 /*
  * Setup options
@@ -706,6 +714,12 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	saved_video_mode = boot_params.hdr.vid_mode;
 	bootloader_type = boot_params.hdr.type_of_loader;
+	if ((bootloader_type >> 4) == 0xe) {
+		bootloader_type &= 0xf;
+		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+	}
+	bootloader_version  = bootloader_type & 0xf;
+	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
 
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
@@ -854,12 +868,16 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = max_pfn;
 
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 	setup_bios_corruption_check();
 #endif
 
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_brk();
 
 	/* max_pfn_mapped is updated here */
@@ -997,24 +1015,6 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_X86_32
 
 /**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- *	Perform any necessary interrupt initialisation prior to setting up
- *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
- *	interrupts should be initialised here if the machine emulates a PC
- *	in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
-	if (x86_quirks->arch_pre_intr_init) {
-		if (x86_quirks->arch_pre_intr_init())
-			return;
-	}
-	init_ISA_irqs();
-}
-
-/**
  * x86_quirk_intr_init - post gate setup interrupt initialisation
  *
  * Description:
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 8f0e13be36b..9c3f0823e6a 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -425,6 +425,14 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+	/*
+	 * make sure boot cpu node_number is right, when boot cpu is on the
+	 * node that doesn't have mem installed
+	 */
+	per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+#endif
+
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
 
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 13f33ea8cca..f6db48c405b 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -193,19 +193,19 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 }
 
 struct smp_ops smp_ops = {
-	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
-	.smp_prepare_cpus = native_smp_prepare_cpus,
-	.smp_cpus_done = native_smp_cpus_done,
+	.smp_prepare_boot_cpu	= native_smp_prepare_boot_cpu,
+	.smp_prepare_cpus	= native_smp_prepare_cpus,
+	.smp_cpus_done		= native_smp_cpus_done,
 
-	.smp_send_stop = native_smp_send_stop,
-	.smp_send_reschedule = native_smp_send_reschedule,
+	.smp_send_stop		= native_smp_send_stop,
+	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up = native_cpu_up,
-	.cpu_die = native_cpu_die,
-	.cpu_disable = native_cpu_disable,
-	.play_dead = native_play_dead,
+	.cpu_up			= native_cpu_up,
+	.cpu_die		= native_cpu_die,
+	.cpu_disable		= native_cpu_disable,
+	.play_dead		= native_play_dead,
 
-	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_ipi	= native_send_call_func_ipi,
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 58d24ef917d..7c80007ea5f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -504,7 +504,7 @@ void __inquire_remote_apic(int apicid)
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
  */
-int __devinit
+int __cpuinit
 wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -538,7 +538,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 	return (send_status | accept_status);
 }
 
-int __devinit
+static int __cpuinit
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -822,10 +822,12 @@ do_rest:
 	/* mark "stuck" area as not stuck */
 	*((volatile unsigned long *)trampoline_base) = 0;
 
-	/*
-	 * Cleanup possible dangling ends...
-	 */
-	smpboot_restore_warm_reset_vector();
+	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+		/*
+		 * Cleanup possible dangling ends...
+		 */
+		smpboot_restore_warm_reset_vector();
+	}
 
 	return boot_error;
 }
@@ -990,10 +992,12 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	 */
 	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
 	    !cpu_has_apic) {
-		printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
-			boot_cpu_physical_apicid);
-		printk(KERN_ERR "... forcing use of dummy APIC emulation."
+		if (!disable_apic) {
+			pr_err("BIOS bug, local APIC #%d not detected!...\n",
+				boot_cpu_physical_apicid);
+			pr_err("... forcing use of dummy APIC emulation."
 				"(tell your hw vendor)\n");
+		}
 		smpboot_clear_io_apic();
 		arch_disable_smp_support();
 		return -1;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index f7bddc2e37d..4aaf7e48394 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -20,7 +20,7 @@ save_stack_warning_symbol(void *data, char *msg, unsigned long symbol)
 
 static int save_stack_stack(void *data, char *name)
 {
-	return -1;
+	return 0;
 }
 
 static void save_stack_address(void *data, unsigned long addr, int reliable)
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index ed0c33761e6..124d40c575d 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -715,7 +715,12 @@ uv_activation_descriptor_init(int node, int pnode)
 	struct bau_desc *adp;
 	struct bau_desc *ad2;
 
-	adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node);
+	/*
+	 * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
+	 * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per blade
+	 */
+	adp = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)*
+		UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
 	BUG_ON(!adp);
 
 	pa = uv_gpa(adp); /* need the real nasid*/
@@ -729,7 +734,13 @@ uv_activation_descriptor_init(int node, int pnode)
 				      (n << UV_DESC_BASE_PNODE_SHIFT | m));
 	}
 
-	for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) {
+	/*
+	 * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+	 * cpu even though we only use the first one; one descriptor can
+	 * describe a broadcast to 256 nodes.
+	 */
+	for (i = 0, ad2 = adp; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR);
+		i++, ad2++) {
 		memset(ad2, 0, sizeof(struct bau_desc));
 		ad2->header.sw_ack_flag = 1;
 		/*
@@ -832,7 +843,7 @@ static int __init uv_bau_init(void)
 		return 0;
 
 	for_each_possible_cpu(cur_cpu)
-		alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
+		zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
 				       GFP_KERNEL, cpu_to_node(cur_cpu));
 
 	uv_bau_retry_limit = 1;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2cc162e09c4..07d60c870ce 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -839,9 +839,6 @@ asmlinkage void math_state_restore(void)
 	}
 
 	clts();				/* Allow maths ops (or we recurse) */
-#ifdef CONFIG_X86_32
-	restore_fpu(tsk);
-#else
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
@@ -850,7 +847,7 @@ asmlinkage void math_state_restore(void)
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
-#endif
+
 	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
 	tsk->fpu_counter++;
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index d57de05dc43..3e1c057e98f 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -384,13 +384,13 @@ unsigned long native_calibrate_tsc(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
+	unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	tsc_khz = get_hypervisor_tsc_freq();
-	if (tsc_khz) {
+	hv_tsc_khz = get_hypervisor_tsc_freq();
+	if (hv_tsc_khz) {
 		printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
-		return tsc_khz;
+		return hv_tsc_khz;
 	}
 
 	local_irq_save(flags);
@@ -710,7 +710,16 @@ static cycle_t read_tsc(struct clocksource *cs)
 #ifdef CONFIG_X86_64
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
-	cycle_t ret = (cycle_t)vget_cycles();
+	cycle_t ret;
+
+	/*
+	 * Surround the RDTSC by barriers, to make sure it's not
+	 * speculated to outside the seqlock critical section and
+	 * does not cause time warps:
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
+	rdtsc_barrier();
 
 	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
 		ret : __vsyscall_gtod_data.clock.cycle_last;
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index bf36328f6ef..027b5b49899 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -34,6 +34,7 @@ static __cpuinitdata atomic_t stop_count;
  * of a critical section, to be able to prove TSC time-warps:
  */
 static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED;
+
 static __cpuinitdata cycles_t last_tsc;
 static __cpuinitdata cycles_t max_warp;
 static __cpuinitdata int nr_warps;
@@ -113,13 +114,12 @@ void __cpuinit check_tsc_sync_source(int cpu)
 		return;
 
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
-		printk(KERN_INFO
-		       "Skipping synchronization checks as TSC is reliable.\n");
+		pr_info("Skipping synchronization checks as TSC is reliable.\n");
 		return;
 	}
 
-	printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
-			  smp_processor_id(), cpu);
+	pr_info("checking TSC synchronization [CPU#%d -> CPU#%d]:",
+		smp_processor_id(), cpu);
 
 	/*
 	 * Reset it - in case this is a second bootup:
@@ -143,8 +143,8 @@ void __cpuinit check_tsc_sync_source(int cpu)
 
 	if (nr_warps) {
 		printk("\n");
-		printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
-				    " turning off TSC clock.\n", max_warp);
+		pr_warning("Measured %Ld cycles TSC warp between CPUs, "
+			   "turning off TSC clock.\n", max_warp);
 		mark_tsc_unstable("check_tsc_sync_source failed");
 	} else {
 		printk(" passed.\n");
@@ -195,5 +195,3 @@ void __cpuinit check_tsc_sync_target(void)
 	while (atomic_read(&stop_count) != cpus)
 		cpu_relax();
 }
-#undef NR_LOOPS
-
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index d7ac84e7fc1..9c4e6253905 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -287,10 +287,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	info->regs.pt.ds = 0;
 	info->regs.pt.es = 0;
 	info->regs.pt.fs = 0;
-
-/* we are clearing gs later just before "jmp resume_userspace",
- * because it is not saved/restored.
- */
+#ifndef CONFIG_X86_32_LAZY_GS
+	info->regs.pt.gs = 0;
+#endif
 
 /*
  * The flags register is also special: we cannot trust that the user
@@ -318,9 +317,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	}
 
 /*
- * Save old state, set default return value (%ax) to 0
+ * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL)
  */
-	info->regs32->ax = 0;
+	info->regs32->ax = VM86_SIGNAL;
 	tsk->thread.saved_sp0 = tsk->thread.sp0;
 	tsk->thread.saved_fs = info->regs32->fs;
 	tsk->thread.saved_gs = get_user_gs(info->regs32);
@@ -343,7 +342,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	__asm__ __volatile__(
 		"movl %0,%%esp\n\t"
 		"movl %1,%%ebp\n\t"
+#ifdef CONFIG_X86_32_LAZY_GS
 		"mov  %2, %%gs\n\t"
+#endif
 		"jmp resume_userspace"
 		: /* no outputs */
 		:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95deb9f2211..b263423fbe2 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -462,22 +462,28 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
 {
-	paravirt_enter_lazy_cpu();
+	paravirt_start_context_switch(prev);
 	vmi_ops.set_lazy_mode(2);
 }
 
+static void vmi_end_context_switch(struct task_struct *next)
+{
+	vmi_ops.set_lazy_mode(0);
+	paravirt_end_context_switch(next);
+}
+
 static void vmi_enter_lazy_mmu(void)
 {
 	paravirt_enter_lazy_mmu();
 	vmi_ops.set_lazy_mode(1);
 }
 
-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	vmi_ops.set_lazy_mode(0);
+	paravirt_leave_lazy_mmu();
 }
 
 static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -711,14 +717,14 @@ static inline int __init activate_vmi(void)
 	para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
 	para_fill(pv_cpu_ops.io_delay, IODelay);
 
-	para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+	para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
 		  set_lazy_mode, SetLazyMode);
 
 	para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
 
 	/* user and kernel flush are just handled with different flags to FlushTLB */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 849ee611f01..4c85b2e2bb6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -1,5 +1,431 @@
+/*
+ * ld script for the x86 kernel
+ *
+ * Historic 32-bit version written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * Modernisation, unification and other changes and fixes:
+ *   Copyright (C) 2007-2009  Sam Ravnborg <sam@ravnborg.org>
+ *
+ *
+ * Don't define absolute symbols until and unless you know that symbol
+ * value is should remain constant even if kernel image is relocated
+ * at run time. Absolute symbols are not relocated. If symbol value should
+ * change if kernel is relocated, make the symbol section relative and
+ * put it inside the section definition.
+ */
+
 #ifdef CONFIG_X86_32
-# include "vmlinux_32.lds.S"
+#define LOAD_OFFSET __PAGE_OFFSET
 #else
-# include "vmlinux_64.lds.S"
+#define LOAD_OFFSET __START_KERNEL_map
 #endif
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page_types.h>
+#include <asm/cache.h>
+#include <asm/boot.h>
+
+#undef i386     /* in case the preprocessor is a 32bit one */
+
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#ifdef CONFIG_X86_32
+OUTPUT_ARCH(i386)
+ENTRY(phys_startup_32)
+jiffies = jiffies_64;
+#else
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(phys_startup_64)
+jiffies_64 = jiffies;
+#endif
+
+PHDRS {
+	text PT_LOAD FLAGS(5);          /* R_E */
+	data PT_LOAD FLAGS(7);          /* RWE */
+#ifdef CONFIG_X86_64
+	user PT_LOAD FLAGS(7);          /* RWE */
+	data.init PT_LOAD FLAGS(7);     /* RWE */
+#ifdef CONFIG_SMP
+	percpu PT_LOAD FLAGS(7);        /* RWE */
+#endif
+	data.init2 PT_LOAD FLAGS(7);    /* RWE */
+#endif
+	note PT_NOTE FLAGS(0);          /* ___ */
+}
+
+SECTIONS
+{
+#ifdef CONFIG_X86_32
+        . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
+        phys_startup_32 = startup_32 - LOAD_OFFSET;
+#else
+        . = __START_KERNEL;
+        phys_startup_64 = startup_64 - LOAD_OFFSET;
+#endif
+
+	/* Text and read-only data */
+
+	/* bootstrapping code */
+	.text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
+		_text = .;
+		*(.text.head)
+	} :text = 0x9090
+
+	/* The rest of the text */
+	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
+#ifdef CONFIG_X86_32
+		/* not really needed, already page aligned */
+		. = ALIGN(PAGE_SIZE);
+		*(.text.page_aligned)
+#endif
+		. = ALIGN(8);
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+		/* End of text section */
+		_etext = .;
+	} :text = 0x9090
+
+	NOTES :text :note
+
+	/* Exception table */
+	. = ALIGN(16);
+	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+		__start___ex_table = .;
+		*(__ex_table)
+		__stop___ex_table = .;
+	} :text = 0x9090
+
+	RODATA
+
+	/* Data */
+	. = ALIGN(PAGE_SIZE);
+	.data : AT(ADDR(.data) - LOAD_OFFSET) {
+		DATA_DATA
+		CONSTRUCTORS
+
+#ifdef CONFIG_X86_64
+		/* End of data section */
+		_edata = .;
+#endif
+	} :data
+
+#ifdef CONFIG_X86_32
+	/* 32 bit has nosave before _edata */
+	. = ALIGN(PAGE_SIZE);
+	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+		__nosave_begin = .;
+		*(.data.nosave)
+		. = ALIGN(PAGE_SIZE);
+		__nosave_end = .;
+	}
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+	.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+		*(.data.page_aligned)
+		*(.data.idt)
+	}
+
+#ifdef CONFIG_X86_32
+	. = ALIGN(32);
+#else
+	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+#endif
+	.data.cacheline_aligned :
+		AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
+		*(.data.cacheline_aligned)
+	}
+
+	/* rarely changed data like cpu maps */
+#ifdef CONFIG_X86_32
+	. = ALIGN(32);
+#else
+	. = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
+#endif
+	.data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
+		*(.data.read_mostly)
+
+#ifdef CONFIG_X86_32
+		/* End of data section */
+		_edata = .;
+#endif
+	}
+
+#ifdef CONFIG_X86_64
+
+#define VSYSCALL_ADDR (-10*1024*1024)
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
+                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
+                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+
+#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
+#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
+
+#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
+#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+
+	. = VSYSCALL_ADDR;
+	.vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
+		*(.vsyscall_0)
+	} :user
+
+	__vsyscall_0 = VSYSCALL_VIRT_ADDR;
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
+		*(.vsyscall_fn)
+	}
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
+		*(.vsyscall_gtod_data)
+	}
+
+	vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+	.vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
+		*(.vsyscall_clock)
+	}
+	vsyscall_clock = VVIRT(.vsyscall_clock);
+
+
+	.vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
+		*(.vsyscall_1)
+	}
+	.vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
+		*(.vsyscall_2)
+	}
+
+	.vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
+		*(.vgetcpu_mode)
+	}
+	vgetcpu_mode = VVIRT(.vgetcpu_mode);
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.jiffies : AT(VLOAD(.jiffies)) {
+		*(.jiffies)
+	}
+	jiffies = VVIRT(.jiffies);
+
+	.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
+		*(.vsyscall_3)
+	}
+
+	. = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
+
+#undef VSYSCALL_ADDR
+#undef VSYSCALL_PHYS_ADDR
+#undef VSYSCALL_VIRT_ADDR
+#undef VLOAD_OFFSET
+#undef VLOAD
+#undef VVIRT_OFFSET
+#undef VVIRT
+
+#endif /* CONFIG_X86_64 */
+
+	/* init_task */
+	. = ALIGN(THREAD_SIZE);
+	.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
+		*(.data.init_task)
+	}
+#ifdef CONFIG_X86_64
+	 :data.init
+#endif
+
+	/*
+	 * smp_locks might be freed after init
+	 * start/end must be page aligned
+	 */
+	. = ALIGN(PAGE_SIZE);
+	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+		__smp_locks = .;
+		*(.smp_locks)
+		__smp_locks_end = .;
+		. = ALIGN(PAGE_SIZE);
+	}
+
+	/* Init code and data - will be freed after init */
+	. = ALIGN(PAGE_SIZE);
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+		__init_begin = .; /* paired with __init_end */
+		_sinittext = .;
+		INIT_TEXT
+		_einittext = .;
+	}
+
+	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
+		INIT_DATA
+	}
+
+	. = ALIGN(16);
+	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
+		__setup_start = .;
+		*(.init.setup)
+		__setup_end = .;
+	}
+	.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
+		__initcall_start = .;
+		INITCALLS
+		__initcall_end = .;
+	}
+
+	.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
+		__con_initcall_start = .;
+		*(.con_initcall.init)
+		__con_initcall_end = .;
+	}
+
+	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
+		__x86_cpu_dev_start = .;
+		*(.x86_cpu_dev.init)
+		__x86_cpu_dev_end = .;
+	}
+
+	SECURITY_INIT
+
+	. = ALIGN(8);
+	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
+		__parainstructions = .;
+		*(.parainstructions)
+		__parainstructions_end = .;
+	}
+
+	. = ALIGN(8);
+	.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
+
+	.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
+		*(.altinstr_replacement)
+	}
+
+	/*
+	 * .exit.text is discard at runtime, not link time, to deal with
+	 *  references from .altinstructions and .eh_frame
+	 */
+	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		EXIT_TEXT
+	}
+
+	.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
+		EXIT_DATA
+	}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	. = ALIGN(PAGE_SIZE);
+	.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
+		__initramfs_start = .;
+		*(.init.ramfs)
+		__initramfs_end = .;
+	}
+#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
+	/*
+	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
+	 * output PHDR, so the next output section - __data_nosave - should
+	 * start another section data.init2.  Also, pda should be at the head of
+	 * percpu area.  Preallocate it and define the percpu offset symbol
+	 * so that it can be accessed as a percpu variable.
+	 */
+	. = ALIGN(PAGE_SIZE);
+	PERCPU_VADDR(0, :percpu)
+#else
+	PERCPU(PAGE_SIZE)
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+
+	/* freed after init ends here */
+	.init.end : AT(ADDR(.init.end) - LOAD_OFFSET) {
+		__init_end = .;
+	}
+
+#ifdef CONFIG_X86_64
+	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+		. = ALIGN(PAGE_SIZE);
+		__nosave_begin = .;
+		*(.data.nosave)
+		. = ALIGN(PAGE_SIZE);
+		__nosave_end = .;
+	} :data.init2
+	/* use another section data.init2, see PERCPU_VADDR() above */
+#endif
+
+	/* BSS */
+	. = ALIGN(PAGE_SIZE);
+	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+		__bss_start = .;
+		*(.bss.page_aligned)
+		*(.bss)
+		. = ALIGN(4);
+		__bss_stop = .;
+	}
+
+	. = ALIGN(PAGE_SIZE);
+	.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
+		__brk_base = .;
+		. += 64 * 1024;		/* 64k alignment slop space */
+		*(.brk_reservation)	/* areas brk users have reserved */
+		__brk_limit = .;
+	}
+
+	.end : AT(ADDR(.end) - LOAD_OFFSET) {
+		_end = .;
+	}
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.exitcall.exit)
+		*(.eh_frame)
+		*(.discard)
+	}
+
+        STABS_DEBUG
+        DWARF_DEBUG
+}
+
+
+#ifdef CONFIG_X86_32
+ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+        "kernel image bigger than KERNEL_IMAGE_SIZE")
+#else
+/*
+ * Per-cpu symbols which need to be offset from __per_cpu_load
+ * for the boot processor.
+ */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
+/*
+ * Build-time check on the image size:
+ */
+ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+	"kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+        "irq_stack_union is not at start of per-cpu area");
+#endif
+
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_KEXEC
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+       "kexec control code size is too big")
+#endif
+
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
deleted file mode 100644
index 62ad500d55f..00000000000
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ /dev/null
@@ -1,229 +0,0 @@
-/* ld script to make i386 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- *
- * Don't define absolute symbols until and unless you know that symbol
- * value is should remain constant even if kernel image is relocated
- * at run time. Absolute symbols are not relocated. If symbol value should
- * change if kernel is relocated, make the symbol section relative and
- * put it inside the section definition.
- */
-
-#define LOAD_OFFSET __PAGE_OFFSET
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/thread_info.h>
-#include <asm/page_types.h>
-#include <asm/cache.h>
-#include <asm/boot.h>
-
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(phys_startup_32)
-jiffies = jiffies_64;
-
-PHDRS {
-	text PT_LOAD FLAGS(5);	/* R_E */
-	data PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(0);	/* ___ */
-}
-SECTIONS
-{
-  . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
-  phys_startup_32 = startup_32 - LOAD_OFFSET;
-
-  .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
-  	_text = .;			/* Text and read-only data */
-	*(.text.head)
-  } :text = 0x9090
-
-  /* read-only */
-  .text : AT(ADDR(.text) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE); /* not really needed, already page aligned */
-	*(.text.page_aligned)
-	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	KPROBES_TEXT
-	IRQENTRY_TEXT
-	*(.fixup)
-	*(.gnu.warning)
-  	_etext = .;			/* End of text section */
-  } :text = 0x9090
-
-  NOTES :text :note
-
-  . = ALIGN(16);		/* Exception table */
-  __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-  	__start___ex_table = .;
-	 *(__ex_table)
-  	__stop___ex_table = .;
-  } :text = 0x9090
-
-  RODATA
-
-  /* writeable */
-  . = ALIGN(PAGE_SIZE);
-  .data : AT(ADDR(.data) - LOAD_OFFSET) {	/* Data */
-	DATA_DATA
-	CONSTRUCTORS
-	} :data
-
-  . = ALIGN(PAGE_SIZE);
-  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-  	__nosave_begin = .;
-	*(.data.nosave)
-  	. = ALIGN(PAGE_SIZE);
-  	__nosave_end = .;
-  }
-
-  . = ALIGN(PAGE_SIZE);
-  .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-	*(.data.page_aligned)
-	*(.data.idt)
-  }
-
-  . = ALIGN(32);
-  .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-	*(.data.cacheline_aligned)
-  }
-
-  /* rarely changed data like cpu maps */
-  . = ALIGN(32);
-  .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-	*(.data.read_mostly)
-	_edata = .;		/* End of data section */
-  }
-
-  . = ALIGN(THREAD_SIZE);	/* init_task */
-  .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-	*(.data.init_task)
-  }
-
-  /* might get freed after init */
-  . = ALIGN(PAGE_SIZE);
-  .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
-  	__smp_locks = .;
-	*(.smp_locks)
-	__smp_locks_end = .;
-  }
-  /* will be freed after init
-   * Following ALIGN() is required to make sure no other data falls on the
-   * same page where __smp_alt_end is pointing as that page might be freed
-   * after boot. Always make sure that ALIGN() directive is present after
-   * the section which contains __smp_alt_end.
-   */
-  . = ALIGN(PAGE_SIZE);
-
-  /* will be freed after init */
-  . = ALIGN(PAGE_SIZE);		/* Init code and data */
-  .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-  	__init_begin = .;
-	_sinittext = .;
-	INIT_TEXT
-	_einittext = .;
-  }
-  .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
-	INIT_DATA
-  }
-  . = ALIGN(16);
-  .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-  	__setup_start = .;
-	*(.init.setup)
-  	__setup_end = .;
-   }
-  .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-  	__initcall_start = .;
-	INITCALLS
-  	__initcall_end = .;
-  }
-  .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-  	__con_initcall_start = .;
-	*(.con_initcall.init)
-  	__con_initcall_end = .;
-  }
-  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-	__x86_cpu_dev_start = .;
-	*(.x86_cpu_dev.init)
-	__x86_cpu_dev_end = .;
-  }
-  SECURITY_INIT
-  . = ALIGN(4);
-  .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
-  	__alt_instructions = .;
-	*(.altinstructions)
-	__alt_instructions_end = .;
-  }
-  .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
-	*(.altinstr_replacement)
-  }
-  . = ALIGN(4);
-  .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-  	__parainstructions = .;
-	*(.parainstructions)
-  	__parainstructions_end = .;
-  }
-  /* .exit.text is discard at runtime, not link time, to deal with references
-     from .altinstructions and .eh_frame */
-  .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
-	EXIT_TEXT
-  }
-  .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
-	EXIT_DATA
-  }
-#if defined(CONFIG_BLK_DEV_INITRD)
-  . = ALIGN(PAGE_SIZE);
-  .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-	__initramfs_start = .;
-	*(.init.ramfs)
-	__initramfs_end = .;
-  }
-#endif
-  PERCPU(PAGE_SIZE)
-  . = ALIGN(PAGE_SIZE);
-  /* freed after init ends here */
-
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-	__init_end = .;
-	__bss_start = .;		/* BSS */
-	*(.bss.page_aligned)
-	*(.bss)
-	. = ALIGN(4);
-	__bss_stop = .;
-  }
-
-  .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__brk_base = . ;
- 	. += 64 * 1024 ;	/* 64k alignment slop space */
-	*(.brk_reservation)	/* areas brk users have reserved */
-	__brk_limit = . ;
-  }
-
-  .end : AT(ADDR(.end) - LOAD_OFFSET) {
-	_end = . ;
-  }
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	*(.exitcall.exit)
-	*(.discard)
-	}
-
-  STABS_DEBUG
-
-  DWARF_DEBUG
-}
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
-	"kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_KEXEC
-/* Link time checks */
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-       "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
deleted file mode 100644
index c8742507b03..00000000000
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ /dev/null
@@ -1,298 +0,0 @@
-/* ld script to make x86-64 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- */
-
-#define LOAD_OFFSET __START_KERNEL_map
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/asm-offsets.h>
-#include <asm/page_types.h>
-
-#undef i386	/* in case the preprocessor is a 32bit one */
-
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
-OUTPUT_ARCH(i386:x86-64)
-ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
-PHDRS {
-	text PT_LOAD FLAGS(5);	/* R_E */
-	data PT_LOAD FLAGS(7);	/* RWE */
-	user PT_LOAD FLAGS(7);	/* RWE */
-	data.init PT_LOAD FLAGS(7);	/* RWE */
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(7);	/* RWE */
-#endif
-	data.init2 PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(0);	/* ___ */
-}
-SECTIONS
-{
-  . = __START_KERNEL;
-  phys_startup_64 = startup_64 - LOAD_OFFSET;
-  .text :  AT(ADDR(.text) - LOAD_OFFSET) {
-	_text = .;			/* Text and read-only data */
-	/* First the code that has to be first for bootstrapping */
-	*(.text.head)
-	_stext = .;
-	/* Then the rest */
-	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	KPROBES_TEXT
-	IRQENTRY_TEXT
-	*(.fixup)
-	*(.gnu.warning)
-	_etext = .;		/* End of text section */
-  } :text = 0x9090
-
-  NOTES :text :note
-
-  . = ALIGN(16);		/* Exception table */
-  __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-  	__start___ex_table = .;
-	 *(__ex_table)
-  	__stop___ex_table = .;
-  } :text = 0x9090
-
-  RODATA
-
-  . = ALIGN(PAGE_SIZE);		/* Align data segment to page size boundary */
-				/* Data */
-  .data : AT(ADDR(.data) - LOAD_OFFSET) {
-	DATA_DATA
-	CONSTRUCTORS
-	_edata = .;			/* End of data section */
-	} :data
-
-
-  .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-	*(.data.cacheline_aligned)
-  }
-  . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
-  .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-  	*(.data.read_mostly)
-  }
-
-#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
-  . = VSYSCALL_ADDR;
-  .vsyscall_0 :	 AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user
-  __vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
-		{ *(.vsyscall_gtod_data) }
-  vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
-  .vsyscall_clock : AT(VLOAD(.vsyscall_clock))
-		{ *(.vsyscall_clock) }
-  vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
-  .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
-		{ *(.vsyscall_1) }
-  .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
-		{ *(.vsyscall_2) }
-
-  .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
-  vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
-  jiffies = VVIRT(.jiffies);
-
-  .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
-		{ *(.vsyscall_3) }
-
-  . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
-
-#undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
-  .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-	. = ALIGN(THREAD_SIZE);	/* init_task */
-	*(.data.init_task)
-  }:data.init
-
-  .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	*(.data.page_aligned)
-  }
-
-  .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
-	/* might get freed after init */
-	. = ALIGN(PAGE_SIZE);
-	__smp_alt_begin = .;
-	__smp_locks = .;
-	*(.smp_locks)
-	__smp_locks_end = .;
-	. = ALIGN(PAGE_SIZE);
-	__smp_alt_end = .;
-  }
-
-  . = ALIGN(PAGE_SIZE);		/* Init code and data */
-  __init_begin = .;	/* paired with __init_end */
-  .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-	_sinittext = .;
-	INIT_TEXT
-	_einittext = .;
-  }
-  .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
-	__initdata_begin = .;
-	INIT_DATA
-	__initdata_end = .;
-   }
-
-  .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-	. = ALIGN(16);
-	__setup_start = .;
-	*(.init.setup)
-	__setup_end = .;
-  }
-  .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-	__initcall_start = .;
-	INITCALLS
-	__initcall_end = .;
-  }
-  .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-	__con_initcall_start = .;
-	*(.con_initcall.init)
-	__con_initcall_end = .;
-  }
-  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-	__x86_cpu_dev_start = .;
-	*(.x86_cpu_dev.init)
-	__x86_cpu_dev_end = .;
-  }
-  SECURITY_INIT
-
-  . = ALIGN(8);
-  .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-	__parainstructions = .;
-       *(.parainstructions)
-	__parainstructions_end = .;
-  }
-
-  .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
-	. = ALIGN(8);
-	__alt_instructions = .;
-	*(.altinstructions)
-	__alt_instructions_end = .;
-  }
-  .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
-	*(.altinstr_replacement)
-  }
-  /* .exit.text is discard at runtime, not link time, to deal with references
-     from .altinstructions and .eh_frame */
-  .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
-	EXIT_TEXT
-  }
-  .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
-	EXIT_DATA
-  }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-  . = ALIGN(PAGE_SIZE);
-  .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-	__initramfs_start = .;
-	*(.init.ramfs)
-	__initramfs_end = .;
-  }
-#endif
-
-#ifdef CONFIG_SMP
-  /*
-   * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-   * output PHDR, so the next output section - __data_nosave - should
-   * start another section data.init2.  Also, pda should be at the head of
-   * percpu area.  Preallocate it and define the percpu offset symbol
-   * so that it can be accessed as a percpu variable.
-   */
-  . = ALIGN(PAGE_SIZE);
-  PERCPU_VADDR(0, :percpu)
-#else
-  PERCPU(PAGE_SIZE)
-#endif
-
-  . = ALIGN(PAGE_SIZE);
-  __init_end = .;
-
-  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__nosave_begin = .;
-	*(.data.nosave)
-	. = ALIGN(PAGE_SIZE);
-	__nosave_end = .;
-  } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
-
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__bss_start = .;		/* BSS */
-	*(.bss.page_aligned)
-	*(.bss)
-	__bss_stop = .;
-  }
-
-  .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__brk_base = . ;
- 	. += 64 * 1024 ;	/* 64k alignment slop space */
-	*(.brk_reservation)	/* areas brk users have reserved */
-	__brk_limit = . ;
-  }
-
-  _end = . ;
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	*(.exitcall.exit)
-	*(.eh_frame)
-	*(.discard)
-	}
-
-  STABS_DEBUG
-
-  DWARF_DEBUG
-}
-
- /*
-  * Per-cpu symbols which need to be offset from __per_cpu_load
-  * for the boot processor.
-  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
-	"kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
-        "irq_stack_union is not at start of per-cpu area");
-#endif
-
-#ifdef CONFIG_KEXEC
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-       "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 44153afc906..25ee06a80aa 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -132,15 +132,7 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 			return;
 		}
 
-		/*
-		 * Surround the RDTSC by barriers, to make sure it's not
-		 * speculated to outside the seqlock critical section and
-		 * does not cause time warps:
-		 */
-		rdtsc_barrier();
 		now = vread();
-		rdtsc_barrier();
-
 		base = __vsyscall_gtod_data.clock.cycle_last;
 		mask = __vsyscall_gtod_data.clock.mask;
 		mult = __vsyscall_gtod_data.clock.mult;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 33a93b41739..4e0c2655939 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -167,10 +167,16 @@ static void lazy_hcall3(unsigned long call,
 
 /* When lazy mode is turned off reset the per-cpu lazy mode variable and then
  * issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_end_context_switch(next);
 }
 
 /*G:033
@@ -637,7 +643,7 @@ static void __init lguest_init_IRQ(void)
 
 void lguest_setup_irq(unsigned int irq)
 {
-	irq_to_desc_alloc_cpu(irq, 0);
+	irq_to_desc_alloc_node(irq, 0);
 	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }
@@ -1054,8 +1060,8 @@ __init void lguest_init(void)
 	pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
 	pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
 	pv_cpu_ops.wbinvd = lguest_wbinvd;
-	pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
-	pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+	pv_cpu_ops.end_context_switch = lguest_end_context_switch;
 
 	/* pagetable management */
 	pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1068,7 +1074,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr2 = lguest_read_cr2;
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
-	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index e7277cbcfb4..a725b7f760a 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -161,13 +161,14 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		   st->current_address >= st->marker[1].start_address) {
 		const char *unit = units;
 		unsigned long delta;
+		int width = sizeof(unsigned long) * 2;
 
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%p-0x%p   ",
-			   (void *)st->start_address,
-			   (void *)st->current_address);
+		seq_printf(m, "0x%0*lx-0x%0*lx   ",
+			   width, st->start_address,
+			   width, st->current_address);
 
 		delta = (st->current_address - st->start_address) >> 10;
 		while (!(delta & 1023) && unit[1]) {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 5c6d816f30b..c6acc632637 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,41 +3,17 @@
  *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-#include <linux/perf_counter.h>
-
-#include <asm-generic/sections.h>
-
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <linux/magic.h>		/* STACK_END_MAGIC		*/
+#include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/kdebug.h>		/* oops_begin/end, ...		*/
+#include <linux/module.h>		/* search_exception_table	*/
+#include <linux/bootmem.h>		/* max_low_pfn			*/
+#include <linux/kprobes.h>		/* __kprobes, ...		*/
+#include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
+#include <linux/perf_counter.h>		/* perf_swcounter_event		*/
+
+#include <asm/traps.h>			/* dotraplinkage, ...		*/
+#include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 
 /*
  * Page fault error code bits:
@@ -226,12 +202,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pmd_present(*pmd_k))
 		return NULL;
 
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else {
+	else
 		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-	}
 
 	return pmd_k;
 }
@@ -539,8 +513,6 @@ bad:
 static int is_errata93(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_64
-	static int once;
-
 	if (address != regs->ip)
 		return 0;
 
@@ -550,10 +522,7 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 	address |= 0xffffffffUL << 32;
 	if ((address >= (u64)_stext && address <= (u64)_etext) ||
 	    (address >= MODULES_VADDR && address <= MODULES_END)) {
-		if (!once) {
-			printk(errata93_warning);
-			once = 1;
-		}
+		printk_once(errata93_warning);
 		regs->ip = address;
 		return 1;
 	}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 8126e8d1a2a..58f621e8191 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -44,7 +44,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -74,7 +73,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
 	}
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ae4f7b5d710..34c1bfb64f1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
 
@@ -10,6 +11,9 @@
 #include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 unsigned long __initdata e820_table_start;
 unsigned long __meminitdata e820_table_end;
@@ -23,6 +27,69 @@ int direct_gbpages
 #endif
 ;
 
+int nx_enabled;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static int disable_nx __cpuinitdata;
+
+/*
+ * noexec = on|off
+ *
+ * Control non-executable mappings for processes.
+ *
+ * on      Enable
+ * off     Disable
+ */
+static int __init noexec_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		disable_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		disable_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
+	}
+	return 0;
+}
+early_param("noexec", noexec_setup);
+#endif
+
+#ifdef CONFIG_X86_PAE
+static void __init set_nx(void)
+{
+	unsigned int v[4], l, h;
+
+	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+
+		if ((v[3] & (1 << 20)) && !disable_nx) {
+			rdmsr(MSR_EFER, l, h);
+			l |= EFER_NX;
+			wrmsr(MSR_EFER, l, h);
+			nx_enabled = 1;
+			__supported_pte_mask |= _PAGE_NX;
+		}
+	}
+}
+#else
+static inline void set_nx(void)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || disable_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+#endif
+
 static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
@@ -66,12 +133,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 	 */
 #ifdef CONFIG_X86_32
 	start = 0x7000;
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
-					tables, PAGE_SIZE);
-#else /* CONFIG_X86_64 */
+#else
 	start = 0x8000;
-	e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
 #endif
+	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+					tables, PAGE_SIZE);
 	if (e820_table_start == -1UL)
 		panic("Cannot find space for the kernel page tables");
 
@@ -159,12 +225,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	use_gbpages = direct_gbpages;
 #endif
 
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_PAE
 	set_nx();
 	if (nx_enabled)
 		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
 
 	/* Enable PSE if available */
 	if (cpu_has_pse)
@@ -175,7 +238,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		set_in_cr4(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
-#endif
 
 	if (use_gbpages)
 		page_size_mask |= 1 << PG_LEVEL_1G;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 749559ed80f..949708d7a48 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,12 +49,9 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/page_types.h>
 #include <asm/init.h>
 
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
@@ -587,61 +584,9 @@ void zap_low_mappings(void)
 	flush_tlb_all();
 }
 
-int nx_enabled;
-
 pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-#ifdef CONFIG_X86_PAE
-
-static int disable_nx __initdata;
-
-/*
- * noexec = on|off
- *
- * Control non executable mappings.
- *
- * on      Enable
- * off     Disable
- */
-static int __init noexec_setup(char *str)
-{
-	if (!str || !strcmp(str, "on")) {
-		if (cpu_has_nx) {
-			__supported_pte_mask |= _PAGE_NX;
-			disable_nx = 0;
-		}
-	} else {
-		if (!strcmp(str, "off")) {
-			disable_nx = 1;
-			__supported_pte_mask &= ~_PAGE_NX;
-		} else {
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-early_param("noexec", noexec_setup);
-
-void __init set_nx(void)
-{
-	unsigned int v[4], l, h;
-
-	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
-		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
-
-		if ((v[3] & (1 << 20)) && !disable_nx) {
-			rdmsr(MSR_EFER, l, h);
-			l |= EFER_NX;
-			wrmsr(MSR_EFER, l, h);
-			nx_enabled = 1;
-			__supported_pte_mask |= _PAGE_NX;
-		}
-	}
-}
-#endif
-
 /* user-defined highmem size */
 static unsigned int highmem_pages = -1;
 
@@ -761,15 +706,15 @@ void __init initmem_init(unsigned long start_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	memory_present(0, 0, highend_pfn);
 	e820_register_active_regions(0, 0, highend_pfn);
+	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	memory_present(0, 0, max_low_pfn);
 	e820_register_active_regions(0, 0, max_low_pfn);
+	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1753e8020df..52bb9519bb8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -50,18 +50,8 @@
 #include <asm/cacheflush.h>
 #include <asm/init.h>
 
-/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
- */
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
 static unsigned long dma_reserve __initdata;
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -85,39 +75,6 @@ early_param("gbpages", parse_direct_gbpages_on);
 pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-static int disable_nx __cpuinitdata;
-
-/*
- * noexec=on|off
- * Control non-executable mappings for 64-bit processes.
- *
- * on	Enable (default)
- * off	Disable
- */
-static int __init nonx_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-	if (!strncmp(str, "on", 2)) {
-		__supported_pte_mask |= _PAGE_NX;
-		disable_nx = 0;
-	} else if (!strncmp(str, "off", 3)) {
-		disable_nx = 1;
-		__supported_pte_mask &= ~_PAGE_NX;
-	}
-	return 0;
-}
-early_param("noexec", nonx_setup);
-
-void __cpuinit check_efer(void)
-{
-	unsigned long efer;
-
-	rdmsrl(MSR_EFER, efer);
-	if (!(efer & EFER_NX) || disable_nx)
-		__supported_pte_mask &= ~_PAGE_NX;
-}
-
 int force_personality32;
 
 /*
@@ -628,6 +585,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
+#endif
 
 void __init paging_init(void)
 {
@@ -638,11 +596,10 @@ void __init paging_init(void)
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
-	memory_present(0, 0, max_pfn);
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	free_area_init_nodes(max_zone_pfns);
 }
-#endif
 
 /*
  * Memory hotplug specific functions
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 8056545e2d3..fe6f84ca121 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -82,7 +82,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
 	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 50dc802a1c4..16ccbd77917 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -32,7 +32,7 @@ struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
 	unsigned long page; /* location of the fault page */
-	bool old_presence; /* page presence prior to arming */
+	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
 	/*
@@ -97,60 +97,62 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
 {
 	struct list_head *head;
-	struct kmmio_fault_page *p;
+	struct kmmio_fault_page *f;
 
 	page &= PAGE_MASK;
 	head = kmmio_page_list(page);
-	list_for_each_entry_rcu(p, head, list) {
-		if (p->page == page)
-			return p;
+	list_for_each_entry_rcu(f, head, list) {
+		if (f->page == page)
+			return f;
 	}
 	return NULL;
 }
 
-static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
 	pmdval_t v = pmd_val(*pmd);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pmd(pmd, __pmd(v));
 }
 
-static void set_pte_presence(pte_t *pte, bool present, bool *old)
+static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pte_atomic(pte, __pte(v));
 }
 
-static int set_page_presence(unsigned long addr, bool present, bool *old)
+static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(addr, &level);
+	pte_t *pte = lookup_address(f->page, &level);
 
 	if (!pte) {
-		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
+		pr_err("kmmio: no pte for page 0x%08lx\n", f->page);
 		return -1;
 	}
 
 	switch (level) {
 	case PG_LEVEL_2M:
-		set_pmd_presence((pmd_t *)pte, present, old);
+		clear_pmd_presence((pmd_t *)pte, clear, &f->old_presence);
 		break;
 	case PG_LEVEL_4K:
-		set_pte_presence(pte, present, old);
+		clear_pte_presence(pte, clear, &f->old_presence);
 		break;
 	default:
 		pr_err("kmmio: unexpected page level 0x%x.\n", level);
 		return -1;
 	}
 
-	__flush_tlb_one(addr);
+	__flush_tlb_one(f->page);
 	return 0;
 }
 
@@ -171,9 +173,9 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
 	if (f->armed) {
 		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
-					f->page, f->count, f->old_presence);
+					f->page, f->count, !!f->old_presence);
 	}
-	ret = set_page_presence(f->page, false, &f->old_presence);
+	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
 	f->armed = true;
 	return ret;
@@ -182,8 +184,7 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 /** Restore the given page to saved presence state. */
 static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	bool tmp;
-	int ret = set_page_presence(f->page, f->old_presence, &tmp);
+	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
 			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
 	f->armed = false;
@@ -310,7 +311,12 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
 
 	if (!ctx->active) {
-		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+		/*
+		 * debug traps without an active context are due to either
+		 * something external causing them (f.e. using a debugger while
+		 * mmio tracing enabled), or erroneous behaviour
+		 */
+		pr_warning("kmmio: unexpected debug trap on CPU %d.\n",
 							smp_processor_id());
 		goto out;
 	}
@@ -439,12 +445,12 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
 						head,
 						struct kmmio_delayed_release,
 						rcu);
-	struct kmmio_fault_page *p = dr->release_list;
-	while (p) {
-		struct kmmio_fault_page *next = p->release_next;
-		BUG_ON(p->count);
-		kfree(p);
-		p = next;
+	struct kmmio_fault_page *f = dr->release_list;
+	while (f) {
+		struct kmmio_fault_page *next = f->release_next;
+		BUG_ON(f->count);
+		kfree(f);
+		f = next;
 	}
 	kfree(dr);
 }
@@ -453,19 +459,19 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
 {
 	struct kmmio_delayed_release *dr =
 		container_of(head, struct kmmio_delayed_release, rcu);
-	struct kmmio_fault_page *p = dr->release_list;
+	struct kmmio_fault_page *f = dr->release_list;
 	struct kmmio_fault_page **prevp = &dr->release_list;
 	unsigned long flags;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	while (p) {
-		if (!p->count) {
-			list_del_rcu(&p->list);
-			prevp = &p->release_next;
+	while (f) {
+		if (!f->count) {
+			list_del_rcu(&f->list);
+			prevp = &f->release_next;
 		} else {
-			*prevp = p->release_next;
+			*prevp = f->release_next;
 		}
-		p = p->release_next;
+		f = f->release_next;
 	}
 	spin_unlock_irqrestore(&kmmio_lock, flags);
 
@@ -528,8 +534,8 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 }
 EXPORT_SYMBOL(unregister_kmmio_probe);
 
-static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val,
-								void *args)
+static int
+kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
 {
 	struct die_args *arg = args;
 
@@ -544,11 +550,23 @@ static struct notifier_block nb_die = {
 	.notifier_call = kmmio_die_notifier
 };
 
-static int __init init_kmmio(void)
+int kmmio_init(void)
 {
 	int i;
+
 	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
 		INIT_LIST_HEAD(&kmmio_page_table[i]);
+
 	return register_die_notifier(&nb_die);
 }
-fs_initcall(init_kmmio); /* should be before device_initcall() */
+
+void kmmio_cleanup(void)
+{
+	int i;
+
+	unregister_die_notifier(&nb_die);
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) {
+		WARN_ONCE(!list_empty(&kmmio_page_table[i]),
+			KERN_ERR "kmmio_page_table not empty at cleanup, any further tracing will leak memory.\n");
+	}
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 605c8be0621..c0bedcd10f9 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -40,23 +40,23 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
 {
-	u64 i, count;
-	u64 *start;
+	u64 *p;
+	void *start, *end;
 	u64 start_bad, last_bad;
 	u64 start_phys_aligned;
 	size_t incr;
 
 	incr = sizeof(pattern);
 	start_phys_aligned = ALIGN(start_phys, incr);
-	count = (size - (start_phys_aligned - start_phys))/incr;
 	start = __va(start_phys_aligned);
+	end = start + size - (start_phys_aligned - start_phys);
 	start_bad = 0;
 	last_bad = 0;
 
-	for (i = 0; i < count; i++)
-		start[i] = pattern;
-	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
-		if (*start == pattern)
+	for (p = start; p < end; p++)
+		*p = pattern;
+	for (p = start; p < end; p++, start_phys_aligned += incr) {
+		if (*p == pattern)
 			continue;
 		if (start_phys_aligned == last_bad + incr) {
 			last_bad += incr;
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index c9342ed8b40..132772a8ec5 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -451,6 +451,7 @@ void enable_mmiotrace(void)
 
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
+	kmmio_init();
 	enter_uniprocessor();
 	spin_lock_irq(&trace_lock);
 	atomic_inc(&mmiotrace_enabled);
@@ -473,6 +474,7 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
+	kmmio_cleanup();
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 2d05a12029d..459913beac7 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -179,18 +179,25 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 }
 
 /* Initialize bootmem allocator for a node */
-void __init setup_node_bootmem(int nodeid, unsigned long start,
-			       unsigned long end)
+void __init
+setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
 	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
-	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
 	if (!end)
 		return;
 
+	/*
+	 * Don't confuse VM with a node that doesn't have the
+	 * minimum amount of memory:
+	 */
+	if (end && (end - start) < NODE_MIN_SIZE)
+		return;
+
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
@@ -272,9 +279,6 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 		reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
 				 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
 
-#ifdef CONFIG_ACPI_NUMA
-	srat_reserve_add_area(nodeid);
-#endif
 	node_set_online(nodeid);
 }
 
@@ -578,21 +582,6 @@ unsigned long __init numa_free_all_bootmem(void)
 	return pages;
 }
 
-void __init paging_init(void)
-{
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
-
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
-	max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
-	sparse_init();
-
-	free_area_init_nodes(max_zone_pfns);
-}
-
 static __init int numa_setup(char *opt)
 {
 	if (!opt)
@@ -606,8 +595,6 @@ static __init int numa_setup(char *opt)
 #ifdef CONFIG_ACPI_NUMA
 	if (!strncmp(opt, "noacpi", 6))
 		acpi_numa = -1;
-	if (!strncmp(opt, "hotadd=", 7))
-		hotadd_percent = simple_strtoul(opt+7, NULL, 10);
 #endif
 	return 0;
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e17efed088c..6ce9518fe2a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -839,13 +839,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	vm_unmap_aliases();
 
-	/*
-	 * If we're called with lazy mmu updates enabled, the
-	 * in-memory pte state may be stale.  Flush pending updates to
-	 * bring them up to date.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 	cpa.vaddr = addr;
 	cpa.pages = pages;
 	cpa.numpages = numpages;
@@ -890,13 +883,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	} else
 		cpa_flush_all(cache);
 
-	/*
-	 * If we've been called with lazy mmu updates enabled, then
-	 * make sure that everything gets flushed out before we
-	 * return.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 out:
 	return ret;
 }
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 01765955baa..2dfcbf9df2a 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -31,17 +31,11 @@ static nodemask_t nodes_parsed __initdata;
 static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
-static int found_add_area __initdata;
-int hotadd_percent __initdata = 0;
 
 static int num_node_memblks __initdata;
 static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
 static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
 
-/* Too small nodes confuse the VM badly. Usually they result
-   from BIOS bugs. */
-#define NODE_MIN_SIZE (4*1024*1024)
-
 static __init int setup_node(int pxm)
 {
 	return acpi_map_pxm_to_node(pxm);
@@ -66,9 +60,6 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end)
 {
 	struct bootnode *nd = &nodes[i];
 
-	if (found_add_area)
-		return;
-
 	if (nd->start < start) {
 		nd->start = start;
 		if (nd->end < nd->start)
@@ -86,7 +77,6 @@ static __init void bad_srat(void)
 	int i;
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
-	found_add_area = 0;
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
 		apicid_to_node[i] = NUMA_NO_NODE;
 	for (i = 0; i < MAX_NUMNODES; i++)
@@ -182,24 +172,21 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	       pxm, apic_id, node);
 }
 
-static int update_end_of_memory(unsigned long end) {return -1;}
-static int hotadd_enough_memory(struct bootnode *nd) {return 1;}
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static inline int save_add_info(void) {return 1;}
 #else
 static inline int save_add_info(void) {return 0;}
 #endif
 /*
- * Update nodes_add and decide if to include add are in the zone.
- * Both SPARSE and RESERVE need nodes_add information.
- * This code supports one contiguous hot add area per node.
+ * Update nodes_add[]
+ * This code supports one contiguous hot add area per node
  */
-static int __init
-reserve_hotadd(int node, unsigned long start, unsigned long end)
+static void __init
+update_nodes_add(int node, unsigned long start, unsigned long end)
 {
 	unsigned long s_pfn = start >> PAGE_SHIFT;
 	unsigned long e_pfn = end >> PAGE_SHIFT;
-	int ret = 0, changed = 0;
+	int changed = 0;
 	struct bootnode *nd = &nodes_add[node];
 
 	/* I had some trouble with strange memory hotadd regions breaking
@@ -210,7 +197,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 	   mistakes */
 	if ((signed long)(end - start) < NODE_MIN_SIZE) {
 		printk(KERN_ERR "SRAT: Hotplug area too small\n");
-		return -1;
+		return;
 	}
 
 	/* This check might be a bit too strict, but I'm keeping it for now. */
@@ -218,12 +205,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 		printk(KERN_ERR
 			"SRAT: Hotplug area %lu -> %lu has existing memory\n",
 			s_pfn, e_pfn);
-		return -1;
-	}
-
-	if (!hotadd_enough_memory(&nodes_add[node]))  {
-		printk(KERN_ERR "SRAT: Hotplug area too large\n");
-		return -1;
+		return;
 	}
 
 	/* Looks good */
@@ -245,11 +227,9 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
 	}
 
-	ret = update_end_of_memory(nd->end);
-
 	if (changed)
-	 	printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end);
-	return ret;
+		printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
+				 nd->start, nd->end);
 }
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
@@ -310,13 +290,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	       start, end);
 	e820_register_active_regions(node, start >> PAGE_SHIFT,
 				     end >> PAGE_SHIFT);
-	push_node_boundaries(node, nd->start >> PAGE_SHIFT,
-						nd->end >> PAGE_SHIFT);
 
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) &&
-	    (reserve_hotadd(node, start, end) < 0)) {
-		/* Ignore hotadd region. Undo damage */
-		printk(KERN_NOTICE "SRAT: Hotplug region ignored\n");
+	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+		update_nodes_add(node, start, end);
+		/* restore nodes[node] */
 		*nd = oldnode;
 		if ((nd->start | nd->end) == 0)
 			node_clear(node, nodes_parsed);
@@ -345,9 +322,9 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-	/* We seem to lose 3 pages somewhere. Allow a bit of slack. */
-	if ((long)(e820ram - pxmram) >= 1*1024*1024) {
+	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
 	"SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
 			(pxmram << PAGE_SHIFT) >> 20,
@@ -357,17 +334,6 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 	return 1;
 }
 
-static void __init unparse_node(int node)
-{
-	int i;
-	node_clear(node, nodes_parsed);
-	node_clear(node, cpu_nodes_parsed);
-	for (i = 0; i < MAX_LOCAL_APIC; i++) {
-		if (apicid_to_node[i] == node)
-			apicid_to_node[i] = NUMA_NO_NODE;
-	}
-}
-
 void __init acpi_numa_arch_fixup(void) {}
 
 /* Use the information discovered above to actually set up the nodes. */
@@ -379,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 
 	/* First clean up the node list */
-	for (i = 0; i < MAX_NUMNODES; i++) {
+	for (i = 0; i < MAX_NUMNODES; i++)
 		cutoff_node(i, start, end);
-		/*
-		 * don't confuse VM with a node that doesn't have the
-		 * minimum memory.
-		 */
-		if (nodes[i].end &&
-			(nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
-			unparse_node(i);
-			node_set_offline(i);
-		}
-	}
 
 	if (!nodes_cover_memory(nodes)) {
 		bad_srat();
@@ -423,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 
 		if (node == NUMA_NO_NODE)
 			continue;
-		if (!node_isset(node, node_possible_map))
+		if (!node_online(node))
 			numa_clear_node(i);
 	}
 	numa_init_array();
@@ -510,26 +466,6 @@ static int null_slit_node_compare(int a, int b)
 }
 #endif /* CONFIG_NUMA_EMU */
 
-void __init srat_reserve_add_area(int nodeid)
-{
-	if (found_add_area && nodes_add[nodeid].end) {
-		u64 total_mb;
-
-		printk(KERN_INFO "SRAT: Reserving hot-add memory space "
-				"for node %d at %Lx-%Lx\n",
-			nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end);
-		total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start)
-					>> PAGE_SHIFT;
-		total_mb *= sizeof(struct page);
-		total_mb >>= 20;
-		printk(KERN_INFO "SRAT: This will cost you %Lu MB of "
-				"pre-allocated memory.\n", (unsigned long long)total_mb);
-		reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start,
-			       nodes_add[nodeid].end - nodes_add[nodeid].start,
-			       BOOTMEM_DEFAULT);
-	}
-}
-
 int __node_distance(int a, int b)
 {
 	int index;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index c638685136e..b07dd8d0b32 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -357,14 +357,11 @@ static void exit_sysfs(void)
 #define exit_sysfs() do { } while (0)
 #endif /* CONFIG_PM */
 
-static int p4force;
-module_param(p4force, int, 0);
-
 static int __init p4_init(char **cpu_type)
 {
 	__u8 cpu_model = boot_cpu_data.x86_model;
 
-	if (!p4force && (cpu_model > 6 || cpu_model == 5))
+	if (cpu_model > 6 || cpu_model == 5)
 		return 0;
 
 #ifndef CONFIG_SMP
@@ -390,10 +387,25 @@ static int __init p4_init(char **cpu_type)
 	return 0;
 }
 
+static int force_arch_perfmon;
+static int force_cpu_type(const char *str, struct kernel_param *kp)
+{
+	if (!strcmp(str, "archperfmon")) {
+		force_arch_perfmon = 1;
+		printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
+	}
+
+	return 0;
+}
+module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
+
 static int __init ppro_init(char **cpu_type)
 {
 	__u8 cpu_model = boot_cpu_data.x86_model;
 
+	if (force_arch_perfmon && cpu_has_arch_perfmon)
+		return 0;
+
 	switch (cpu_model) {
 	case 0 ... 2:
 		*cpu_type = "i386/ppro";
@@ -415,6 +427,13 @@ static int __init ppro_init(char **cpu_type)
 	case 15: case 23:
 		*cpu_type = "i386/core_2";
 		break;
+	case 26:
+		arch_perfmon_setup_counters();
+		*cpu_type = "i386/core_i7";
+		break;
+	case 28:
+		*cpu_type = "i386/atom";
+		break;
 	default:
 		/* Unknown */
 		return 0;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index fecbce6e7d7..0696d506c4a 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -889,6 +889,9 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		return 0;
 	}
 
+	if (io_apic_assign_pci_irqs)
+		return 0;
+
 	/* Find IRQ routing entry */
 
 	if (!pirq_table)
@@ -1039,56 +1042,15 @@ static void __init pcibios_fixup_irqs(void)
 		pirq_penalty[dev->irq]++;
 	}
 
+	if (io_apic_assign_pci_irqs)
+		return;
+
 	dev = NULL;
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
 		pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 		if (!pin)
 			continue;
 
-#ifdef CONFIG_X86_IO_APIC
-		/*
-		 * Recalculate IRQ numbers if we use the I/O APIC.
-		 */
-		if (io_apic_assign_pci_irqs) {
-			int irq;
-
-			/*
-			 * interrupt pins are numbered starting from 1
-			 */
-			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-				PCI_SLOT(dev->devfn), pin - 1);
-			/*
-			 * Busses behind bridges are typically not listed in the
-			 * MP-table.  In this case we have to look up the IRQ
-			 * based on the parent bus, parent slot, and pin number.
-			 * The SMP code detects such bridged busses itself so we
-			 * should get into this branch reliably.
-			 */
-			if (irq < 0 && dev->bus->parent) {
-				/* go back to the bridge */
-				struct pci_dev *bridge = dev->bus->self;
-				int bus;
-
-				pin = pci_swizzle_interrupt_pin(dev, pin);
-				bus = bridge->bus->number;
-				irq = IO_APIC_get_PCI_irq_vector(bus,
-						PCI_SLOT(bridge->devfn), pin - 1);
-				if (irq >= 0)
-					dev_warn(&dev->dev,
-						"using bridge %s INT %c to "
-							"get IRQ %d\n",
-						 pci_name(bridge),
-						 'A' + pin - 1, irq);
-			}
-			if (irq >= 0) {
-				dev_info(&dev->dev,
-					"PCI->APIC IRQ transform: INT %c "
-						"-> IRQ %d\n",
-					'A' + pin - 1, irq);
-				dev->irq = irq;
-			}
-		}
-#endif
 		/*
 		 * Still no IRQ? Try to lookup one...
 		 */
@@ -1183,6 +1145,19 @@ int __init pcibios_irq_init(void)
 	pcibios_enable_irq = pirq_enable_irq;
 
 	pcibios_fixup_irqs();
+
+	if (io_apic_assign_pci_irqs && pci_routeirq) {
+		struct pci_dev *dev = NULL;
+		/*
+		 * PCI IRQ routing is set up by pci_enable_device(), but we
+		 * also do it here in case there are still broken drivers that
+		 * don't use pci_enable_device().
+		 */
+		printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+		for_each_pci_dev(dev)
+			pirq_enable_irq(dev);
+	}
+
 	return 0;
 }
 
@@ -1213,16 +1188,23 @@ void pcibios_penalize_isa_irq(int irq, int active)
 static int pirq_enable_irq(struct pci_dev *dev)
 {
 	u8 pin;
-	struct pci_dev *temp_dev;
 
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
-	if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) {
+	if (pin && !pcibios_lookup_irq(dev, 1)) {
 		char *msg = "";
 
+		if (!io_apic_assign_pci_irqs && dev->irq)
+			return 0;
+
 		if (io_apic_assign_pci_irqs) {
+#ifdef CONFIG_X86_IO_APIC
+			struct pci_dev *temp_dev;
 			int irq;
+			struct io_apic_irq_attr irq_attr;
 
-			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin - 1);
+			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+						PCI_SLOT(dev->devfn),
+						pin - 1, &irq_attr);
 			/*
 			 * Busses behind bridges are typically not listed in the MP-table.
 			 * In this case we have to look up the IRQ based on the parent bus,
@@ -1235,7 +1217,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 
 				pin = pci_swizzle_interrupt_pin(dev, pin);
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
-						PCI_SLOT(bridge->devfn), pin - 1);
+						PCI_SLOT(bridge->devfn),
+						pin - 1, &irq_attr);
 				if (irq >= 0)
 					dev_warn(&dev->dev, "using bridge %s "
 						 "INT %c to get IRQ %d\n",
@@ -1245,12 +1228,15 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
+				io_apic_set_pci_routing(&dev->dev, irq,
+							 &irq_attr);
+				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
-				dev->irq = irq;
 				return 0;
 			} else
 				msg = "; probably buggy MP table";
+#endif
 		} else if (pci_probe & PCI_BIOS_IRQ_SCAN)
 			msg = "";
 		else
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 5fa10bb9604..8766b0e216c 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -375,7 +375,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
 		if (!fixmem32)
 			return AE_OK;
 		if ((mcfg_res->start >= fixmem32->address) &&
-		    (mcfg_res->end <= (fixmem32->address +
+		    (mcfg_res->end < (fixmem32->address +
 				      fixmem32->address_length))) {
 			mcfg_res->flags = 1;
 			return AE_CTRL_TERMINATE;
@@ -392,7 +392,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
 		return AE_OK;
 
 	if ((mcfg_res->start >= address.minimum) &&
-	    (mcfg_res->end <= (address.minimum + address.address_length))) {
+	    (mcfg_res->end < (address.minimum + address.address_length))) {
 		mcfg_res->flags = 1;
 		return AE_CTRL_TERMINATE;
 	}
@@ -418,7 +418,7 @@ static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used)
 	struct resource mcfg_res;
 
 	mcfg_res.start = start;
-	mcfg_res.end = end;
+	mcfg_res.end = end - 1;
 	mcfg_res.flags = 0;
 
 	acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL);
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 93b7a2938b2..21e1aeb9f3e 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/random.h>
+#include <linux/elf.h>
 #include <asm/vsyscall.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f09e8c36ee8..0a1700a2be9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
+#include <linux/kprobes.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -44,6 +45,7 @@
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/msr-index.h>
+#include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
@@ -240,10 +242,10 @@ static unsigned long xen_get_debugreg(int reg)
 	return HYPERVISOR_get_debugreg(reg);
 }
 
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	xen_mc_flush();
+	paravirt_end_context_switch(next);
 }
 
 static unsigned long xen_store_tr(void)
@@ -428,11 +430,44 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
 			    struct trap_info *info)
 {
+	unsigned long addr;
+
 	if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
 		return 0;
 
 	info->vector = vector;
-	info->address = gate_offset(*val);
+
+	addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+	/*
+	 * Look for known traps using IST, and substitute them
+	 * appropriately.  The debugger ones are the only ones we care
+	 * about.  Xen will handle faults like double_fault and
+	 * machine_check, so we should never see them.  Warn if
+	 * there's an unexpected IST-using fault handler.
+	 */
+	if (addr == (unsigned long)debug)
+		addr = (unsigned long)xen_debug;
+	else if (addr == (unsigned long)int3)
+		addr = (unsigned long)xen_int3;
+	else if (addr == (unsigned long)stack_segment)
+		addr = (unsigned long)xen_stack_segment;
+	else if (addr == (unsigned long)double_fault ||
+		 addr == (unsigned long)nmi) {
+		/* Don't need to handle these */
+		return 0;
+#ifdef CONFIG_X86_MCE
+	} else if (addr == (unsigned long)machine_check) {
+		return 0;
+#endif
+	} else {
+		/* Some other trap using IST? */
+		if (WARN_ON(val->ist != 0))
+			return 0;
+	}
+#endif	/* CONFIG_X86_64 */
+	info->address = addr;
+
 	info->cs = gate_segment(*val);
 	info->flags = val->dpl;
 	/* interrupt gates clear IF */
@@ -623,10 +658,26 @@ static void xen_clts(void)
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+	unsigned long cr0 = percpu_read(xen_cr0_value);
+
+	if (unlikely(cr0 == 0)) {
+		cr0 = native_read_cr0();
+		percpu_write(xen_cr0_value, cr0);
+	}
+
+	return cr0;
+}
+
 static void xen_write_cr0(unsigned long cr0)
 {
 	struct multicall_space mcs;
 
+	percpu_write(xen_cr0_value, cr0);
+
 	/* Only pay attention to cr0.TS; everything else is
 	   ignored. */
 	mcs = xen_mc_entry(0);
@@ -812,7 +863,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 
 	.clts = xen_clts,
 
-	.read_cr0 = native_read_cr0,
+	.read_cr0 = xen_read_cr0,
 	.write_cr0 = xen_write_cr0,
 
 	.read_cr4 = native_read_cr4,
@@ -860,10 +911,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	/* Xen takes care of %gs when switching to usermode for us */
 	.swapgs = paravirt_nop,
 
-	.lazy_mode = {
-		.enter = paravirt_enter_lazy_cpu,
-		.leave = xen_leave_lazy,
-	},
+	.start_context_switch = paravirt_start_context_switch,
+	.end_context_switch = xen_end_context_switch,
 };
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fba55b1a402..4ceb2858165 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -452,10 +452,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval)
 {
-	/* updates to init_mm may be done without lock */
-	if (mm == &init_mm)
-		preempt_disable();
-
 	ADD_STATS(set_pte_at, 1);
 //	ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
 	ADD_STATS(set_pte_at_current, mm == current->mm);
@@ -476,9 +472,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	}
 	xen_set_pte(ptep, pteval);
 
-out:
-	if (mm == &init_mm)
-		preempt_enable();
+out:	return;
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
@@ -1152,10 +1146,8 @@ static void drop_other_mm_ref(void *info)
 
 	/* If this cpu still has a stale cr3 reference, then make sure
 	   it has been flushed. */
-	if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+	if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
 		load_cr3(swapper_pg_dir);
-		arch_flush_lazy_cpu_mode();
-	}
 }
 
 static void xen_drop_mm_ref(struct mm_struct *mm)
@@ -1168,7 +1160,6 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
 			load_cr3(swapper_pg_dir);
 		else
 			leave_mm(smp_processor_id());
-		arch_flush_lazy_cpu_mode();
 	}
 
 	/* Get the "official" set of cpus referring to our pagetable. */
@@ -1876,6 +1867,14 @@ __init void xen_post_allocator_init(void)
 	xen_mark_init_mm_pinned();
 }
 
+static void xen_leave_lazy_mmu(void)
+{
+	preempt_disable();
+	xen_mc_flush();
+	paravirt_leave_lazy_mmu();
+	preempt_enable();
+}
+
 const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.pagetable_setup_start = xen_pagetable_setup_start,
 	.pagetable_setup_done = xen_pagetable_setup_done,
@@ -1949,7 +1948,7 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
-		.leave = xen_leave_lazy,
+		.leave = xen_leave_lazy_mmu,
 	},
 
 	.set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 15c6c68db6a..ad0047f47cd 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -61,9 +61,9 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	e820_add_region(__pa(xen_start_info->mfn_list),
-			xen_start_info->pt_base - xen_start_info->mfn_list,
-			E820_RESERVED);
+	reserve_early(__pa(xen_start_info->mfn_list),
+		      __pa(xen_start_info->pt_base),
+			"XEN START INFO");
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ca6596b05d5..22494fd4c9b 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,7 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 
-void xen_leave_lazy(void);
 void xen_post_allocator_init(void);
 
 char * __init xen_memory_setup(void);
diff --git a/block/blk-core.c b/block/blk-core.c
index c89883be873..9475bf99b89 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -28,22 +28,14 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/blktrace_api.h>
 #include <linux/fault-inject.h>
-#include <trace/block.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
 
 #include "blk.h"
 
-DEFINE_TRACE(block_plug);
-DEFINE_TRACE(block_unplug_io);
-DEFINE_TRACE(block_unplug_timer);
-DEFINE_TRACE(block_getrq);
-DEFINE_TRACE(block_sleeprq);
-DEFINE_TRACE(block_rq_requeue);
-DEFINE_TRACE(block_bio_backmerge);
-DEFINE_TRACE(block_bio_frontmerge);
-DEFINE_TRACE(block_bio_queue);
-DEFINE_TRACE(block_rq_complete);
-DEFINE_TRACE(block_remap);	/* Also used in drivers/md/dm.c */
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 
 static int __make_request(struct request_queue *q, struct bio *bio);
 
@@ -1277,7 +1269,7 @@ static inline void blk_partition_remap(struct bio *bio)
 		bio->bi_bdev = bdev->bd_contains;
 
 		trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
-				    bdev->bd_dev, bio->bi_sector,
+				    bdev->bd_dev,
 				    bio->bi_sector - p->start_sect);
 	}
 }
@@ -1446,8 +1438,7 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 
 		if (old_sector != -1)
-			trace_block_remap(q, bio, old_dev, bio->bi_sector,
-					    old_sector);
+			trace_block_remap(q, bio, old_dev, old_sector);
 
 		trace_block_bio_queue(q, bio);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3ff9bba3379..26f9ec28f56 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -383,16 +383,21 @@ struct kobj_type blk_queue_ktype = {
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
+	struct device *dev = disk_to_dev(disk);
 
 	struct request_queue *q = disk->queue;
 
 	if (WARN_ON(!q))
 		return -ENXIO;
 
+	ret = blk_trace_init_sysfs(dev);
+	if (ret)
+		return ret;
+
 	if (!q->request_fn)
 		return 0;
 
-	ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
+	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj),
 			  "%s", "queue");
 	if (ret < 0)
 		return ret;
diff --git a/block/bsg.c b/block/bsg.c
index 206060e795d..dd81be455e0 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -315,6 +315,7 @@ out:
 	blk_put_request(rq);
 	if (next_rq) {
 		blk_rq_unmap_user(next_rq->bio);
+		next_rq->bio = NULL;
 		blk_put_request(next_rq);
 	}
 	return ERR_PTR(ret);
@@ -448,6 +449,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		hdr->dout_resid = rq->data_len;
 		hdr->din_resid = rq->next_rq->data_len;
 		blk_rq_unmap_user(bidi_bio);
+		rq->next_rq->bio = NULL;
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
 		hdr->din_resid = rq->data_len;
@@ -466,6 +468,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	blk_rq_unmap_user(bio);
 	if (rq->cmd != rq->__cmd)
 		kfree(rq->cmd);
+	rq->bio = NULL;
 	blk_put_request(rq);
 
 	return ret;
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index f87615dea46..f8c218cd08e 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -568,7 +568,7 @@ static int compat_blk_trace_setup(struct block_device *bdev, char __user *arg)
 	memcpy(&buts.name, &cbuts.name, 32);
 
 	mutex_lock(&bdev->bd_mutex);
-	ret = do_blk_trace_setup(q, b, bdev->bd_dev, &buts);
+	ret = do_blk_trace_setup(q, b, bdev->bd_dev, bdev, &buts);
 	mutex_unlock(&bdev->bd_mutex);
 	if (ret)
 		return ret;
diff --git a/block/elevator.c b/block/elevator.c
index 7073a907257..e220f0c543e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -33,17 +33,16 @@
 #include <linux/compiler.h>
 #include <linux/delay.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <linux/hash.h>
 #include <linux/uaccess.h>
 
+#include <trace/events/block.h>
+
 #include "blk.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
 
-DEFINE_TRACE(block_rq_abort);
-
 /*
  * Merge hash stuff.
  */
@@ -55,9 +54,6 @@ static const int elv_hash_shift = 6;
 #define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-DEFINE_TRACE(block_rq_insert);
-DEFINE_TRACE(block_rq_issue);
-
 /*
  * Query io scheduler to see if the current process issuing bio may be
  * merged with rq.
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 51b9f8280f8..2faa9e2ac89 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -401,7 +401,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		/* Interrupt Line values above 0xF are forbidden */
 		if (dev->irq > 0 && (dev->irq <= 0xF)) {
 			printk(" - using IRQ %d\n", dev->irq);
-			acpi_register_gsi(dev->irq, ACPI_LEVEL_SENSITIVE,
+			acpi_register_gsi(&dev->dev, dev->irq,
+					  ACPI_LEVEL_SENSITIVE,
 					  ACPI_ACTIVE_LOW);
 			return 0;
 		} else {
@@ -410,7 +411,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		}
 	}
 
-	rc = acpi_register_gsi(gsi, triggering, polarity);
+	rc = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
 	if (rc < 0) {
 		dev_warn(&dev->dev, "PCI INT %c: failed to register GSI\n",
 			 pin_name(pin));
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 45ad3288c5f..23f0fb84f1c 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -844,7 +844,7 @@ static int acpi_processor_add(struct acpi_device *device)
 	if (!pr)
 		return -ENOMEM;
 
-	if (!alloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
 		kfree(pr);
 		return -ENOMEM;
 	}
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 08186ecbaf8..6b91c26a463 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -220,6 +220,7 @@ enum {
 	AHCI_HFLAG_NO_HOTPLUG		= (1 << 7), /* ignore PxSERR.DIAG.N */
 	AHCI_HFLAG_SECT255		= (1 << 8), /* max 255 sectors */
 	AHCI_HFLAG_YES_NCQ		= (1 << 9), /* force NCQ cap on */
+	AHCI_HFLAG_NO_SUSPEND		= (1 << 10), /* don't suspend */
 
 	/* ap->flags bits */
 
@@ -2316,9 +2317,17 @@ static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
 	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
 	void __iomem *mmio = host->iomap[AHCI_PCI_BAR];
 	u32 ctl;
 
+	if (mesg.event & PM_EVENT_SUSPEND &&
+	    hpriv->flags & AHCI_HFLAG_NO_SUSPEND) {
+		dev_printk(KERN_ERR, &pdev->dev,
+			   "BIOS update required for suspend/resume\n");
+		return -EIO;
+	}
+
 	if (mesg.event & PM_EVENT_SLEEP) {
 		/* AHCI spec rev1.1 section 8.3.3:
 		 * Software must disable interrupts prior to requesting a
@@ -2610,6 +2619,63 @@ static bool ahci_broken_system_poweroff(struct pci_dev *pdev)
 	return false;
 }
 
+static bool ahci_broken_suspend(struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		/*
+		 * On HP dv[4-6] and HDX18 with earlier BIOSen, link
+		 * to the harddisk doesn't become online after
+		 * resuming from STR.  Warn and fail suspend.
+		 */
+		{
+			.ident = "dv4",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+				DMI_MATCH(DMI_PRODUCT_NAME,
+					  "HP Pavilion dv4 Notebook PC"),
+			},
+			.driver_data = "F.30", /* cutoff BIOS version */
+		},
+		{
+			.ident = "dv5",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+				DMI_MATCH(DMI_PRODUCT_NAME,
+					  "HP Pavilion dv5 Notebook PC"),
+			},
+			.driver_data = "F.16", /* cutoff BIOS version */
+		},
+		{
+			.ident = "dv6",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+				DMI_MATCH(DMI_PRODUCT_NAME,
+					  "HP Pavilion dv6 Notebook PC"),
+			},
+			.driver_data = "F.21",	/* cutoff BIOS version */
+		},
+		{
+			.ident = "HDX18",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+				DMI_MATCH(DMI_PRODUCT_NAME,
+					  "HP HDX18 Notebook PC"),
+			},
+			.driver_data = "F.23",	/* cutoff BIOS version */
+		},
+		{ }	/* terminate list */
+	};
+	const struct dmi_system_id *dmi = dmi_first_match(sysids);
+	const char *ver;
+
+	if (!dmi || pdev->bus->number || pdev->devfn != PCI_DEVFN(0x1f, 2))
+		return false;
+
+	ver = dmi_get_system_info(DMI_BIOS_VERSION);
+
+	return !ver || strcmp(ver, dmi->driver_data) < 0;
+}
+
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	static int printed_version;
@@ -2715,6 +2781,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			"quirky BIOS, skipping spindown on poweroff\n");
 	}
 
+	if (ahci_broken_suspend(pdev)) {
+		hpriv->flags |= AHCI_HFLAG_NO_SUSPEND;
+		dev_printk(KERN_WARNING, &pdev->dev,
+			   "BIOS update required for suspend/resume\n");
+	}
+
 	/* CAP.NP sometimes indicate the index of the last enabled
 	 * port, at other times, that of the last possible port, so
 	 * determining the maximum port number requires looking at
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index d51a17c0f59..1aeb7082b0c 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -1455,6 +1455,15 @@ static bool piix_broken_system_poweroff(struct pci_dev *pdev)
 			/* PCI slot number of the controller */
 			.driver_data = (void *)0x1FUL,
 		},
+		{
+			.ident = "HP Compaq nc6000",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nc6000"),
+			},
+			/* PCI slot number of the controller */
+			.driver_data = (void *)0x1FUL,
+		},
 
 		{ }	/* terminate list */
 	};
diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c
index 751b7ea4816..fc9c5d6d7d8 100644
--- a/drivers/ata/pata_ali.c
+++ b/drivers/ata/pata_ali.c
@@ -497,14 +497,16 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	/* Revision 0x20 added DMA */
 	static const struct ata_port_info info_20 = {
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48 |
+							ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.port_ops = &ali_20_port_ops
 	};
 	/* Revision 0x20 with support logic added UDMA */
 	static const struct ata_port_info info_20_udma = {
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48 |
+							ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.udma_mask = ATA_UDMA2,
@@ -512,7 +514,8 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	/* Revision 0xC2 adds UDMA66 */
 	static const struct ata_port_info info_c2 = {
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48 |
+							ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.udma_mask = ATA_UDMA4,
@@ -520,7 +523,8 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	/* Revision 0xC3 is UDMA66 for now */
 	static const struct ata_port_info info_c3 = {
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48 |
+							ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.udma_mask = ATA_UDMA4,
@@ -528,7 +532,8 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	/* Revision 0xC4 is UDMA100 */
 	static const struct ata_port_info info_c4 = {
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_LBA48 |
+							ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.udma_mask = ATA_UDMA5,
@@ -536,7 +541,7 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	};
 	/* Revision 0xC5 is UDMA133 with LBA48 DMA */
 	static const struct ata_port_info info_c5 = {
-		.flags = ATA_FLAG_SLAVE_POSS,
+		.flags = ATA_FLAG_SLAVE_POSS | 	ATA_FLAG_IGN_SIMPLEX,
 		.pio_mask = ATA_PIO4,
 		.mwdma_mask = ATA_MWDMA2,
 		.udma_mask = ATA_UDMA6,
diff --git a/drivers/ata/pata_efar.c b/drivers/ata/pata_efar.c
index 2085e0a3a05..2a6412f5d11 100644
--- a/drivers/ata/pata_efar.c
+++ b/drivers/ata/pata_efar.c
@@ -22,7 +22,7 @@
 #include <linux/ata.h>
 
 #define DRV_NAME	"pata_efar"
-#define DRV_VERSION	"0.4.4"
+#define DRV_VERSION	"0.4.5"
 
 /**
  *	efar_pre_reset	-	Enable bits
@@ -98,18 +98,17 @@ static void efar_set_piomode (struct ata_port *ap, struct ata_device *adev)
 			    { 2, 1 },
 			    { 2, 3 }, };
 
-	if (pio > 2)
-		control |= 1;	/* TIME1 enable */
+	if (pio > 1)
+		control |= 1;	/* TIME */
 	if (ata_pio_need_iordy(adev))	/* PIO 3/4 require IORDY */
-		control |= 2;	/* IE enable */
-	/* Intel specifies that the PPE functionality is for disk only */
+		control |= 2;	/* IE */
+	/* Intel specifies that the prefetch/posting is for disk only */
 	if (adev->class == ATA_DEV_ATA)
-		control |= 4;	/* PPE enable */
+		control |= 4;	/* PPE */
 
 	pci_read_config_word(dev, idetm_port, &idetm_data);
 
-	/* Enable PPE, IE and TIME as appropriate */
-
+	/* Set PPE, IE, and TIME as appropriate */
 	if (adev->devno == 0) {
 		idetm_data &= 0xCCF0;
 		idetm_data |= control;
@@ -129,7 +128,7 @@ static void efar_set_piomode (struct ata_port *ap, struct ata_device *adev)
 		pci_write_config_byte(dev, 0x44, slave_data);
 	}
 
-	idetm_data |= 0x4000;	/* Ensure SITRE is enabled */
+	idetm_data |= 0x4000;	/* Ensure SITRE is set */
 	pci_write_config_word(dev, idetm_port, idetm_data);
 }
 
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index f72c6c5b820..6932e56d179 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -48,6 +48,7 @@
  *
  */
 
+#include <linux/async.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
@@ -1028,6 +1029,7 @@ static __init int legacy_init_one(struct legacy_probe *probe)
 				&legacy_sht);
 	if (ret)
 		goto fail;
+	async_synchronize_full();
 	ld->platform_dev = pdev;
 
 	/* Nothing found means we drop the port as its probably not there */
diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
index 9a698097134..f0d52f72f5b 100644
--- a/drivers/ata/pata_netcell.c
+++ b/drivers/ata/pata_netcell.c
@@ -26,7 +26,7 @@ static unsigned int netcell_read_id(struct ata_device *adev,
 	unsigned int err_mask = ata_do_dev_read_id(adev, tf, id);
 	/* Firmware forgets to mark words 85-87 valid */
 	if (err_mask == 0)
-		id[ATA_ID_CSF_DEFAULT] |= 0x0400;
+		id[ATA_ID_CSF_DEFAULT] |= 0x4000;
 	return err_mask;
 }
 
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 340ba4f9dc5..4a9f3492b92 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -224,7 +224,7 @@ static void hpet_timer_set_irq(struct hpet_dev *devp)
 			break;
 		}
 
-		gsi = acpi_register_gsi(irq, ACPI_LEVEL_SENSITIVE,
+		gsi = acpi_register_gsi(NULL, irq, ACPI_LEVEL_SENSITIVE,
 					ACPI_ACTIVE_LOW);
 		if (gsi > 0)
 			break;
@@ -939,7 +939,7 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 		irqp = &res->data.extended_irq;
 
 		for (i = 0; i < irqp->interrupt_count; i++) {
-			irq = acpi_register_gsi(irqp->interrupts[i],
+			irq = acpi_register_gsi(NULL, irqp->interrupts[i],
 				      irqp->triggering, irqp->polarity);
 			if (irq < 0)
 				return AE_ERROR;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 65e12bca657..f96d0bef855 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -694,9 +694,8 @@ static ssize_t read_zero(struct file * file, char __user * buf,
 		written += chunk - unwritten;
 		if (unwritten)
 			break;
-		/* Consider changing this to just 'signal_pending()' with lots of testing */
-		if (fatal_signal_pending(current))
-			return written ? written : -EINTR;
+		if (signal_pending(current))
+			return written ? written : -ERESTARTSYS;
 		buf += chunk;
 		count -= chunk;
 		cond_resched();
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index a420e8d437d..13f8871e5b2 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -2711,7 +2711,7 @@ static int __init mxser_module_init(void)
 			continue;
 
 		brd = &mxser_boards[m];
-		retval = mxser_get_ISA_conf(!ioaddr[b], brd);
+		retval = mxser_get_ISA_conf(ioaddr[b], brd);
 		if (retval <= 0) {
 			brd->info = NULL;
 			continue;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 47d2ad0ae07..6e2ec0b1894 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -808,7 +808,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 		ret = -ENOMEM;
 		goto nomem_out;
 	}
-	if (!alloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) {
 		free_cpumask_var(policy->cpus);
 		kfree(policy);
 		ret = -ENOMEM;
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 80a257554b3..0411d912d82 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -371,8 +371,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 	list->user_token = list->hash.key << PAGE_SHIFT;
 	mutex_unlock(&dev->struct_mutex);
 
-	if (!(map->flags & _DRM_DRIVER))
-		list->master = dev->primary->master;
+	list->master = dev->primary->master;
 	*maplist = list;
 	return 0;
 	}
diff --git a/drivers/ide/pdc202xx_old.c b/drivers/ide/pdc202xx_old.c
index 248a54bd238..b3bc96f930a 100644
--- a/drivers/ide/pdc202xx_old.c
+++ b/drivers/ide/pdc202xx_old.c
@@ -1,6 +1,6 @@
 /*
  *  Copyright (C) 1998-2002		Andre Hedrick <andre@linux-ide.org>
- *  Copyright (C) 2006-2007		MontaVista Software, Inc.
+ *  Copyright (C) 2006-2007, 2009	MontaVista Software, Inc.
  *  Copyright (C) 2007			Bartlomiej Zolnierkiewicz
  *
  *  Portions Copyright (C) 1999 Promise Technology, Inc.
@@ -227,28 +227,19 @@ somebody_else:
 	return (dma_stat & 4) == 4;	/* return 1 if INTR asserted */
 }
 
-static void pdc202xx_reset_host (ide_hwif_t *hwif)
+static void pdc202xx_reset(ide_drive_t *drive)
 {
+	ide_hwif_t *hwif	= drive->hwif;
 	unsigned long high_16	= hwif->extra_base - 16;
 	u8 udma_speed_flag	= inb(high_16 | 0x001f);
 
+	printk(KERN_WARNING "PDC202xx: software reset...\n");
+
 	outb(udma_speed_flag | 0x10, high_16 | 0x001f);
 	mdelay(100);
 	outb(udma_speed_flag & ~0x10, high_16 | 0x001f);
 	mdelay(2000);	/* 2 seconds ?! */
 
-	printk(KERN_WARNING "PDC202XX: %s channel reset.\n",
-		hwif->channel ? "Secondary" : "Primary");
-}
-
-static void pdc202xx_reset (ide_drive_t *drive)
-{
-	ide_hwif_t *hwif	= drive->hwif;
-	ide_hwif_t *mate	= hwif->mate;
-
-	pdc202xx_reset_host(hwif);
-	pdc202xx_reset_host(mate);
-
 	ide_set_max_pio(drive);
 }
 
@@ -328,9 +319,8 @@ static const struct ide_dma_ops pdc20246_dma_ops = {
 	.dma_start		= ide_dma_start,
 	.dma_end		= ide_dma_end,
 	.dma_test_irq		= pdc202xx_dma_test_irq,
-	.dma_lost_irq		= pdc202xx_dma_lost_irq,
+	.dma_lost_irq		= ide_dma_lost_irq,
 	.dma_timer_expiry	= ide_dma_sff_timer_expiry,
-	.dma_clear		= pdc202xx_reset,
 	.dma_sff_read_status	= ide_dma_sff_read_status,
 };
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 424f7b048c3..3fd8b1e6548 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -20,7 +20,8 @@
 #include <linux/idr.h>
 #include <linux/hdreg.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
+
+#include <trace/events/block.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -53,8 +54,6 @@ struct dm_target_io {
 	union map_info info;
 };
 
-DEFINE_TRACE(block_bio_complete);
-
 /*
  * For request-based dm.
  * One of these is allocated per request.
@@ -656,8 +655,7 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/* the bio has been remapped so dispatch it */
 
 		trace_block_remap(bdev_get_queue(clone->bi_bdev), clone,
-				    tio->io->bio->bi_bdev->bd_dev,
-				    clone->bi_sector, sector);
+				    tio->io->bio->bi_bdev->bd_dev, sector);
 
 		generic_make_request(clone);
 	} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5d400aef8d9..bb37fb1b2d8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -362,7 +362,7 @@ static void raid5_unplug_device(struct request_queue *q);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,
-		  int previous, int noblock)
+		  int previous, int noblock, int noquiesce)
 {
 	struct stripe_head *sh;
 
@@ -372,7 +372,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
 
 	do {
 		wait_event_lock_irq(conf->wait_for_stripe,
-				    conf->quiesce == 0,
+				    conf->quiesce == 0 || noquiesce,
 				    conf->device_lock, /* nothing */);
 		sh = __find_stripe(conf, sector, conf->generation - previous);
 		if (!sh) {
@@ -2671,7 +2671,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 			sector_t bn = compute_blocknr(sh, i, 1);
 			sector_t s = raid5_compute_sector(conf, bn, 0,
 							  &dd_idx, NULL);
-			sh2 = get_active_stripe(conf, s, 0, 1);
+			sh2 = get_active_stripe(conf, s, 0, 1, 1);
 			if (sh2 == NULL)
 				/* so far only the early blocks of this stripe
 				 * have been requested.  When later blocks
@@ -2944,7 +2944,7 @@ static bool handle_stripe5(struct stripe_head *sh)
 	/* Finish reconstruct operations initiated by the expansion process */
 	if (sh->reconstruct_state == reconstruct_state_result) {
 		struct stripe_head *sh2
-			= get_active_stripe(conf, sh->sector, 1, 1);
+			= get_active_stripe(conf, sh->sector, 1, 1, 1);
 		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
 			/* sh cannot be written until sh2 has been read.
 			 * so arrange for sh to be delayed a little
@@ -3189,7 +3189,7 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 
 	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
 		struct stripe_head *sh2
-			= get_active_stripe(conf, sh->sector, 1, 1);
+			= get_active_stripe(conf, sh->sector, 1, 1, 1);
 		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
 			/* sh cannot be written until sh2 has been read.
 			 * so arrange for sh to be delayed a little
@@ -3288,7 +3288,7 @@ static void unplug_slaves(mddev_t *mddev)
 	int i;
 
 	rcu_read_lock();
-	for (i=0; i<mddev->raid_disks; i++) {
+	for (i = 0; i < conf->raid_disks; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
 			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
@@ -3675,7 +3675,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 			(unsigned long long)logical_sector);
 
 		sh = get_active_stripe(conf, new_sector, previous,
-				       (bi->bi_rw&RWA_MASK));
+				       (bi->bi_rw&RWA_MASK), 0);
 		if (sh) {
 			if (unlikely(previous)) {
 				/* expansion might have moved on while waiting for a
@@ -3873,7 +3873,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
 		int j;
 		int skipped = 0;
-		sh = get_active_stripe(conf, stripe_addr+i, 0, 0);
+		sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
 		set_bit(STRIPE_EXPANDING, &sh->state);
 		atomic_inc(&conf->reshape_stripes);
 		/* If any of this stripe is beyond the end of the old
@@ -3916,13 +3916,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 		raid5_compute_sector(conf, stripe_addr*(new_data_disks),
 				     1, &dd_idx, NULL);
 	last_sector =
-		raid5_compute_sector(conf, ((stripe_addr+conf->chunk_size/512)
+		raid5_compute_sector(conf, ((stripe_addr+reshape_sectors)
 					    *(new_data_disks) - 1),
 				     1, &dd_idx, NULL);
 	if (last_sector >= mddev->dev_sectors)
 		last_sector = mddev->dev_sectors - 1;
 	while (first_sector <= last_sector) {
-		sh = get_active_stripe(conf, first_sector, 1, 0);
+		sh = get_active_stripe(conf, first_sector, 1, 0, 1);
 		set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 		set_bit(STRIPE_HANDLE, &sh->state);
 		release_stripe(sh);
@@ -4022,9 +4022,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 
-	sh = get_active_stripe(conf, sector_nr, 0, 1);
+	sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
 	if (sh == NULL) {
-		sh = get_active_stripe(conf, sector_nr, 0, 0);
+		sh = get_active_stripe(conf, sector_nr, 0, 0, 0);
 		/* make sure we don't swamp the stripe cache if someone else
 		 * is trying to get access
 		 */
@@ -4034,7 +4034,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	 * We don't need to check the 'failed' flag as when that gets set,
 	 * recovery aborts.
 	 */
-	for (i=0; i<mddev->raid_disks; i++)
+	for (i = 0; i < conf->raid_disks; i++)
 		if (conf->disks[i].rdev == NULL)
 			still_degraded = 1;
 
@@ -4086,7 +4086,7 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 			/* already done this stripe */
 			continue;
 
-		sh = get_active_stripe(conf, sector, 0, 1);
+		sh = get_active_stripe(conf, sector, 0, 1, 0);
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
diff --git a/drivers/media/video/ivtv/ivtv-queue.c b/drivers/media/video/ivtv/ivtv-queue.c
index ff7b7deded4..7fde36e6d22 100644
--- a/drivers/media/video/ivtv/ivtv-queue.c
+++ b/drivers/media/video/ivtv/ivtv-queue.c
@@ -230,7 +230,8 @@ int ivtv_stream_alloc(struct ivtv_stream *s)
 		return -ENOMEM;
 	}
 	if (ivtv_might_use_dma(s)) {
-		s->sg_handle = pci_map_single(itv->pdev, s->sg_dma, sizeof(struct ivtv_sg_element), s->dma);
+		s->sg_handle = pci_map_single(itv->pdev, s->sg_dma,
+				sizeof(struct ivtv_sg_element), PCI_DMA_TODEVICE);
 		ivtv_stream_sync_for_cpu(s);
 	}
 
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index c643d0fe118..b56d72ff06e 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -64,6 +64,31 @@ static int mvsd_setup_data(struct mvsd_host *host, struct mmc_data *data)
 	unsigned int tmout;
 	int tmout_index;
 
+	/*
+	 * Hardware weirdness.  The FIFO_EMPTY bit of the HW_STATE
+	 * register is sometimes not set before a while when some
+	 * "unusual" data block sizes are used (such as with the SWITCH
+	 * command), even despite the fact that the XFER_DONE interrupt
+	 * was raised.  And if another data transfer starts before
+	 * this bit comes to good sense (which eventually happens by
+	 * itself) then the new transfer simply fails with a timeout.
+	 */
+	if (!(mvsd_read(MVSD_HW_STATE) & (1 << 13))) {
+		unsigned long t = jiffies + HZ;
+		unsigned int hw_state,  count = 0;
+		do {
+			if (time_after(jiffies, t)) {
+				dev_warn(host->dev, "FIFO_EMPTY bit missing\n");
+				break;
+			}
+			hw_state = mvsd_read(MVSD_HW_STATE);
+			count++;
+		} while (!(hw_state & (1 << 13)));
+		dev_dbg(host->dev, "*** wait for FIFO_EMPTY bit "
+				   "(hw=0x%04x, count=%d, jiffies=%ld)\n",
+				   hw_state, count, jiffies - (t - HZ));
+	}
+
 	/* If timeout=0 then maximum timeout index is used. */
 	tmout = DIV_ROUND_UP(data->timeout_ns, host->ns_per_clk);
 	tmout += data->timeout_clks;
@@ -620,9 +645,18 @@ static void mvsd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->bus_width == MMC_BUS_WIDTH_4)
 		ctrl_reg |= MVSD_HOST_CTRL_DATA_WIDTH_4_BITS;
 
+	/*
+	 * The HI_SPEED_EN bit is causing trouble with many (but not all)
+	 * high speed SD, SDHC and SDIO cards.  Not enabling that bit
+	 * makes all cards work.  So let's just ignore that bit for now
+	 * and revisit this issue if problems for not enabling this bit
+	 * are ever reported.
+	 */
+#if 0
 	if (ios->timing == MMC_TIMING_MMC_HS ||
 	    ios->timing == MMC_TIMING_SD_HS)
 		ctrl_reg |= MVSD_HOST_CTRL_HI_SPEED_EN;
+#endif
 
 	host->ctrl = ctrl_reg;
 	mvsd_write(MVSD_HOST_CTRL, ctrl_reg);
@@ -882,3 +916,4 @@ module_param(nodma, int, 0);
 MODULE_AUTHOR("Maen Suleiman, Nicolas Pitre");
 MODULE_DESCRIPTION("Marvell MMC,SD,SDIO Host Controller driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mvsdio");
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index b4a615c55f2..f4cbe473670 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -140,6 +140,8 @@ struct mxcmci_host {
 	struct work_struct	datawork;
 };
 
+static void mxcmci_set_clk_rate(struct mxcmci_host *host, unsigned int clk_ios);
+
 static inline int mxcmci_use_dma(struct mxcmci_host *host)
 {
 	return host->do_dma;
@@ -160,7 +162,7 @@ static void mxcmci_softreset(struct mxcmci_host *host)
 	writew(0xff, host->base + MMC_REG_RES_TO);
 }
 
-static void mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
+static int mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 {
 	unsigned int nob = data->blocks;
 	unsigned int blksz = data->blksz;
@@ -168,6 +170,7 @@ static void mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 #ifdef HAS_DMA
 	struct scatterlist *sg;
 	int i;
+	int ret;
 #endif
 	if (data->flags & MMC_DATA_STREAM)
 		nob = 0xffff;
@@ -183,7 +186,7 @@ static void mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 	for_each_sg(data->sg, sg, data->sg_len, i) {
 		if (sg->offset & 3 || sg->length & 3) {
 			host->do_dma = 0;
-			return;
+			return 0;
 		}
 	}
 
@@ -192,23 +195,30 @@ static void mxcmci_setup_data(struct mxcmci_host *host, struct mmc_data *data)
 		host->dma_nents = dma_map_sg(mmc_dev(host->mmc), data->sg,
 					     data->sg_len,  host->dma_dir);
 
-		imx_dma_setup_sg(host->dma, data->sg, host->dma_nents, datasize,
-				 host->res->start + MMC_REG_BUFFER_ACCESS,
-				 DMA_MODE_READ);
+		ret = imx_dma_setup_sg(host->dma, data->sg, host->dma_nents,
+				datasize,
+				host->res->start + MMC_REG_BUFFER_ACCESS,
+				DMA_MODE_READ);
 	} else {
 		host->dma_dir = DMA_TO_DEVICE;
 		host->dma_nents = dma_map_sg(mmc_dev(host->mmc), data->sg,
 					     data->sg_len,  host->dma_dir);
 
-		imx_dma_setup_sg(host->dma, data->sg, host->dma_nents, datasize,
-				 host->res->start + MMC_REG_BUFFER_ACCESS,
-				 DMA_MODE_WRITE);
+		ret = imx_dma_setup_sg(host->dma, data->sg, host->dma_nents,
+				datasize,
+				host->res->start + MMC_REG_BUFFER_ACCESS,
+				DMA_MODE_WRITE);
 	}
 
+	if (ret) {
+		dev_err(mmc_dev(host->mmc), "failed to setup DMA : %d\n", ret);
+		return ret;
+	}
 	wmb();
 
 	imx_dma_enable(host->dma);
 #endif /* HAS_DMA */
+	return 0;
 }
 
 static int mxcmci_start_cmd(struct mxcmci_host *host, struct mmc_command *cmd,
@@ -345,8 +355,11 @@ static int mxcmci_poll_status(struct mxcmci_host *host, u32 mask)
 		stat = readl(host->base + MMC_REG_STATUS);
 		if (stat & STATUS_ERR_MASK)
 			return stat;
-		if (time_after(jiffies, timeout))
+		if (time_after(jiffies, timeout)) {
+			mxcmci_softreset(host);
+			mxcmci_set_clk_rate(host, host->clock);
 			return STATUS_TIME_OUT_READ;
+		}
 		if (stat & mask)
 			return 0;
 		cpu_relax();
@@ -531,6 +544,7 @@ static void mxcmci_request(struct mmc_host *mmc, struct mmc_request *req)
 {
 	struct mxcmci_host *host = mmc_priv(mmc);
 	unsigned int cmdat = host->cmdat;
+	int error;
 
 	WARN_ON(host->req != NULL);
 
@@ -540,7 +554,12 @@ static void mxcmci_request(struct mmc_host *mmc, struct mmc_request *req)
 	host->do_dma = 1;
 #endif
 	if (req->data) {
-		mxcmci_setup_data(host, req->data);
+		error = mxcmci_setup_data(host, req->data);
+		if (error) {
+			req->cmd->error = error;
+			goto out;
+		}
+
 
 		cmdat |= CMD_DAT_CONT_DATA_ENABLE;
 
@@ -548,7 +567,9 @@ static void mxcmci_request(struct mmc_host *mmc, struct mmc_request *req)
 			cmdat |= CMD_DAT_CONT_WRITE;
 	}
 
-	if (mxcmci_start_cmd(host, req->cmd, cmdat))
+	error = mxcmci_start_cmd(host, req->cmd, cmdat);
+out:
+	if (error)
 		mxcmci_finish_request(host, req);
 }
 
@@ -724,7 +745,9 @@ static int mxcmci_probe(struct platform_device *pdev)
 		goto out_clk_put;
 	}
 
-	mmc->f_min = clk_get_rate(host->clk) >> 7;
+	mmc->f_min = clk_get_rate(host->clk) >> 16;
+	if (mmc->f_min < 400000)
+		mmc->f_min = 400000;
 	mmc->f_max = clk_get_rate(host->clk) >> 1;
 
 	/* recommended in data sheet */
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index bfa25c01c87..dceb5ee3bda 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -822,7 +822,7 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id)
 		del_timer(&host->cmd_abort_timer);
 		host->abort = 1;
 		OMAP_MMC_WRITE(host, IE, 0);
-		disable_irq(host->irq);
+		disable_irq_nosync(host->irq);
 		schedule_work(&host->cmd_abort_work);
 		return IRQ_HANDLED;
 	}
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index e62a22a7f00..c40cb96255a 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -680,7 +680,7 @@ static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data)
 	host->dma_ch = -1;
 	/*
 	 * DMA Callback: run in interrupt context.
-	 * mutex_unlock will through a kernel warning if used.
+	 * mutex_unlock will throw a kernel warning if used.
 	 */
 	up(&host->sem);
 }
diff --git a/drivers/mmc/host/sdhci-of.c b/drivers/mmc/host/sdhci-of.c
index 3ff4ac3abe8..128c614d11a 100644
--- a/drivers/mmc/host/sdhci-of.c
+++ b/drivers/mmc/host/sdhci-of.c
@@ -55,7 +55,13 @@ static u32 esdhc_readl(struct sdhci_host *host, int reg)
 
 static u16 esdhc_readw(struct sdhci_host *host, int reg)
 {
-	return in_be16(host->ioaddr + (reg ^ 0x2));
+	u16 ret;
+
+	if (unlikely(reg == SDHCI_HOST_VERSION))
+		ret = in_be16(host->ioaddr + reg);
+	else
+		ret = in_be16(host->ioaddr + (reg ^ 0x2));
+	return ret;
 }
 
 static u8 esdhc_readb(struct sdhci_host *host, int reg)
@@ -277,6 +283,7 @@ static int __devexit sdhci_of_remove(struct of_device *ofdev)
 static const struct of_device_id sdhci_of_match[] = {
 	{ .compatible = "fsl,mpc8379-esdhc", .data = &sdhci_esdhc, },
 	{ .compatible = "fsl,mpc8536-esdhc", .data = &sdhci_esdhc, },
+	{ .compatible = "fsl,esdhc", .data = &sdhci_esdhc, },
 	{ .compatible = "generic-sdhci", },
 	{},
 };
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 0119220de7d..02700f769b8 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -407,16 +407,17 @@ static int __init nand_davinci_probe(struct platform_device *pdev)
 	}
 	info->chip.ecc.mode = ecc_mode;
 
-	info->clk = clk_get(&pdev->dev, "AEMIFCLK");
+	info->clk = clk_get(&pdev->dev, "aemif");
 	if (IS_ERR(info->clk)) {
 		ret = PTR_ERR(info->clk);
-		dev_dbg(&pdev->dev, "unable to get AEMIFCLK, err %d\n", ret);
+		dev_dbg(&pdev->dev, "unable to get AEMIF clock, err %d\n", ret);
 		goto err_clk;
 	}
 
 	ret = clk_enable(info->clk);
 	if (ret < 0) {
-		dev_dbg(&pdev->dev, "unable to enable AEMIFCLK, err %d\n", ret);
+		dev_dbg(&pdev->dev, "unable to enable AEMIF clock, err %d\n",
+			ret);
 		goto err_clk_enable;
 	}
 
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 8247a945a1d..3b19e0ce290 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -66,7 +66,6 @@ static const int multicast_filter_limit = 32;
 #define RX_DMA_BURST	6	/* Maximum PCI burst, '6' is 1024 */
 #define TX_DMA_BURST	6	/* Maximum PCI burst, '6' is 1024 */
 #define EarlyTxThld	0x3F	/* 0x3F means NO early transmit */
-#define RxPacketMaxSize	0x3FE8	/* 16K - 1 - ETH_HLEN - VLAN - CRC... */
 #define SafeMtu		0x1c20	/* ... actually life sucks beyond ~7k */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
 
@@ -2357,10 +2356,10 @@ static u16 rtl_rw_cpluscmd(void __iomem *ioaddr)
 	return cmd;
 }
 
-static void rtl_set_rx_max_size(void __iomem *ioaddr)
+static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz)
 {
 	/* Low hurts. Let's disable the filtering. */
-	RTL_W16(RxMaxSize, 16383);
+	RTL_W16(RxMaxSize, rx_buf_sz);
 }
 
 static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version)
@@ -2407,7 +2406,7 @@ static void rtl_hw_start_8169(struct net_device *dev)
 
 	RTL_W8(EarlyTxThres, EarlyTxThld);
 
-	rtl_set_rx_max_size(ioaddr);
+	rtl_set_rx_max_size(ioaddr, tp->rx_buf_sz);
 
 	if ((tp->mac_version == RTL_GIGA_MAC_VER_01) ||
 	    (tp->mac_version == RTL_GIGA_MAC_VER_02) ||
@@ -2668,7 +2667,7 @@ static void rtl_hw_start_8168(struct net_device *dev)
 
 	RTL_W8(EarlyTxThres, EarlyTxThld);
 
-	rtl_set_rx_max_size(ioaddr);
+	rtl_set_rx_max_size(ioaddr, tp->rx_buf_sz);
 
 	tp->cp_cmd |= RTL_R16(CPlusCmd) | PktCntrDisable | INTT_1;
 
@@ -2846,7 +2845,7 @@ static void rtl_hw_start_8101(struct net_device *dev)
 
 	RTL_W8(EarlyTxThres, EarlyTxThld);
 
-	rtl_set_rx_max_size(ioaddr);
+	rtl_set_rx_max_size(ioaddr, tp->rx_buf_sz);
 
 	tp->cp_cmd |= rtl_rw_cpluscmd(ioaddr) | PCIMulRW;
 
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 73348c4047e..4a9cc92d4d1 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -702,7 +702,7 @@ static unsigned int iosapic_startup_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void iosapic_set_affinity_irq(unsigned int irq,
+static int iosapic_set_affinity_irq(unsigned int irq,
 				     const struct cpumask *dest)
 {
 	struct vector_info *vi = iosapic_get_vector(irq);
@@ -712,7 +712,7 @@ static void iosapic_set_affinity_irq(unsigned int irq,
 
 	dest_cpu = cpu_check_affinity(irq, dest);
 	if (dest_cpu < 0)
-		return;
+		return -1;
 
 	cpumask_copy(irq_desc[irq].affinity, cpumask_of(dest_cpu));
 	vi->txn_addr = txn_affinity_addr(irq, dest_cpu);
@@ -724,6 +724,8 @@ static void iosapic_set_affinity_irq(unsigned int irq,
 	iosapic_set_irt_data(vi, &dummy_d0, &d1);
 	iosapic_wr_irt_entry(vi, d0, d1);
 	spin_unlock_irqrestore(&iosapic_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index dd18f857dfb..42e4260c3b1 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -153,45 +153,47 @@ int ibmphp_init_devno(struct slot **cur_slot)
 		return -1;
 	}
 	for (loop = 0; loop < len; loop++) {
-		if ((*cur_slot)->number == rtable->slots[loop].slot) {
-		if ((*cur_slot)->bus == rtable->slots[loop].bus) {
+		if ((*cur_slot)->number == rtable->slots[loop].slot &&
+		    (*cur_slot)->bus == rtable->slots[loop].bus) {
+			struct io_apic_irq_attr irq_attr;
+
 			(*cur_slot)->device = PCI_SLOT(rtable->slots[loop].devfn);
 			for (i = 0; i < 4; i++)
 				(*cur_slot)->irq[i] = IO_APIC_get_PCI_irq_vector((int) (*cur_slot)->bus,
-						(int) (*cur_slot)->device, i);
-
-				debug("(*cur_slot)->irq[0] = %x\n",
-						(*cur_slot)->irq[0]);
-				debug("(*cur_slot)->irq[1] = %x\n",
-						(*cur_slot)->irq[1]);
-				debug("(*cur_slot)->irq[2] = %x\n",
-						(*cur_slot)->irq[2]);
-				debug("(*cur_slot)->irq[3] = %x\n",
-						(*cur_slot)->irq[3]);
-
-				debug("rtable->exlusive_irqs = %x\n",
+						(int) (*cur_slot)->device, i,
+						&irq_attr);
+
+			debug("(*cur_slot)->irq[0] = %x\n",
+					(*cur_slot)->irq[0]);
+			debug("(*cur_slot)->irq[1] = %x\n",
+					(*cur_slot)->irq[1]);
+			debug("(*cur_slot)->irq[2] = %x\n",
+					(*cur_slot)->irq[2]);
+			debug("(*cur_slot)->irq[3] = %x\n",
+					(*cur_slot)->irq[3]);
+
+			debug("rtable->exlusive_irqs = %x\n",
 					rtable->exclusive_irqs);
-				debug("rtable->slots[loop].irq[0].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[0].bitmap = %x\n",
 					rtable->slots[loop].irq[0].bitmap);
-				debug("rtable->slots[loop].irq[1].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[1].bitmap = %x\n",
 					rtable->slots[loop].irq[1].bitmap);
-				debug("rtable->slots[loop].irq[2].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[2].bitmap = %x\n",
 					rtable->slots[loop].irq[2].bitmap);
-				debug("rtable->slots[loop].irq[3].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[3].bitmap = %x\n",
 					rtable->slots[loop].irq[3].bitmap);
 
-				debug("rtable->slots[loop].irq[0].link = %x\n",
+			debug("rtable->slots[loop].irq[0].link = %x\n",
 					rtable->slots[loop].irq[0].link);
-				debug("rtable->slots[loop].irq[1].link = %x\n",
+			debug("rtable->slots[loop].irq[1].link = %x\n",
 					rtable->slots[loop].irq[1].link);
-				debug("rtable->slots[loop].irq[2].link = %x\n",
+			debug("rtable->slots[loop].irq[2].link = %x\n",
 					rtable->slots[loop].irq[2].link);
-				debug("rtable->slots[loop].irq[3].link = %x\n",
+			debug("rtable->slots[loop].irq[3].link = %x\n",
 					rtable->slots[loop].irq[3].link);
-				debug("end of init_devno\n");
-				kfree(rtable);
-				return 0;
-			}
+			debug("end of init_devno\n");
+			kfree(rtable);
+			return 0;
 		}
 	}
 
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 6808d8333ec..737a1c44b07 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -98,6 +98,7 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	int max_irq;
 	int pos;
 	int irq;
+	int node;
 
 	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
 	if (!pos)
@@ -125,7 +126,8 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	cfg->msg.address_lo = 0xffffffff;
 	cfg->msg.address_hi = 0xffffffff;
 
-	irq = create_irq();
+	node = dev_to_node(&dev->dev);
+	irq = create_irq_nr(0, node);
 
 	if (irq <= 0) {
 		kfree(cfg);
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index a563fbe559d..cd389162735 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1972,15 +1972,6 @@ static int __init init_dmars(void)
 		}
 	}
 
-#ifdef CONFIG_INTR_REMAP
-	if (!intr_remapping_enabled) {
-		ret = enable_intr_remapping(0);
-		if (ret)
-			printk(KERN_ERR
-			       "IOMMU: enable interrupt remapping failed\n");
-	}
-#endif
-
 	/*
 	 * For each rmrr
 	 *   for each dev attached to rmrr
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index f5e0ea724a6..3a0cb0bb059 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -15,6 +15,14 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static int ir_ioapic_num;
 int intr_remapping_enabled;
 
+static int disable_intremap;
+static __init int setup_nointremap(char *str)
+{
+	disable_intremap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
 struct irq_2_iommu {
 	struct intel_iommu *iommu;
 	u16 irte_index;
@@ -23,15 +31,12 @@ struct irq_2_iommu {
 };
 
 #ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
+static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
 {
 	struct irq_2_iommu *iommu;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "alloc irq_2_iommu on cpu %d node %d\n", cpu, node);
+	printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
 
 	return iommu;
 }
@@ -48,7 +53,7 @@ static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 	return desc->irq_2_iommu;
 }
 
-static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
+static struct irq_2_iommu *irq_2_iommu_alloc_node(unsigned int irq, int node)
 {
 	struct irq_desc *desc;
 	struct irq_2_iommu *irq_iommu;
@@ -56,7 +61,7 @@ static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
 	/*
 	 * alloc irq desc if not allocated already.
 	 */
-	desc = irq_to_desc_alloc_cpu(irq, cpu);
+	desc = irq_to_desc_alloc_node(irq, node);
 	if (!desc) {
 		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
 		return NULL;
@@ -65,14 +70,14 @@ static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
 	irq_iommu = desc->irq_2_iommu;
 
 	if (!irq_iommu)
-		desc->irq_2_iommu = get_one_free_irq_2_iommu(cpu);
+		desc->irq_2_iommu = get_one_free_irq_2_iommu(node);
 
 	return desc->irq_2_iommu;
 }
 
 static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
 {
-	return irq_2_iommu_alloc_cpu(irq, boot_cpu_id);
+	return irq_2_iommu_alloc_node(irq, cpu_to_node(boot_cpu_id));
 }
 
 #else /* !CONFIG_SPARSE_IRQ */
@@ -423,20 +428,6 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
 		      readl, (sts & DMA_GSTS_IRTPS), sts);
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-	if (mode == 0) {
-		spin_lock_irqsave(&iommu->register_lock, flags);
-
-		/* enable comaptiblity format interrupt pass through */
-		cmd = iommu->gcmd | DMA_GCMD_CFI;
-		iommu->gcmd |= DMA_GCMD_CFI;
-		writel(cmd, iommu->reg + DMAR_GCMD_REG);
-
-		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
-			      readl, (sts & DMA_GSTS_CFIS), sts);
-
-		spin_unlock_irqrestore(&iommu->register_lock, flags);
-	}
-
 	/*
 	 * global invalidation of interrupt entry cache before enabling
 	 * interrupt-remapping.
@@ -516,6 +507,23 @@ end:
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 }
 
+int __init intr_remapping_supported(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	if (disable_intremap)
+		return 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			return 0;
+	}
+
+	return 1;
+}
+
 int __init enable_intr_remapping(int eim)
 {
 	struct dmar_drhd_unit *drhd;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e3c3e081b83..f1ae2475fff 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -745,6 +745,8 @@ int pci_setup_device(struct pci_dev *dev)
 
 	/* Early fixups, before probing the BARs */
 	pci_fixup_device(pci_fixup_early, dev);
+	/* device class may be changed after fixup */
+	class = dev->class >> 8;
 
 	switch (dev->hdr_type) {		    /* header type */
 	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index adf17856bac..7f207f335be 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -123,7 +123,7 @@ static void pnpacpi_parse_allocated_irqresource(struct pnp_dev *dev,
 	}
 
 	flags = irq_flags(triggering, polarity, shareable);
-	irq = acpi_register_gsi(gsi, triggering, polarity);
+	irq = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
 	if (irq >= 0)
 		pcibios_penalize_isa_irq(irq, 1);
 	else
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index e1716f14cd4..91e316fe652 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1065,6 +1065,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 		return blk_trace_setup(sdp->device->request_queue,
 				       sdp->disk->disk_name,
 				       MKDEV(SCSI_GENERIC_MAJOR, sdp->index),
+				       NULL,
 				       (char *)arg);
 	case BLKTRACESTART:
 		return blk_trace_startstop(sdp->device->request_queue, 1);
diff --git a/drivers/serial/imx.c b/drivers/serial/imx.c
index 9f460b175c5..5f0be40dfda 100644
--- a/drivers/serial/imx.c
+++ b/drivers/serial/imx.c
@@ -1031,6 +1031,8 @@ imx_console_setup(struct console *co, char *options)
 	if (co->index == -1 || co->index >= ARRAY_SIZE(imx_ports))
 		co->index = 0;
 	sport = imx_ports[co->index];
+	if(sport == NULL)
+		return -ENODEV;
 
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c
index 7dc3a6b4139..a0e0d246b59 100644
--- a/drivers/ssb/embedded.c
+++ b/drivers/ssb/embedded.c
@@ -29,6 +29,7 @@ int ssb_watchdog_timer_set(struct ssb_bus *bus, u32 ticks)
 	}
 	return -ENODEV;
 }
+EXPORT_SYMBOL(ssb_watchdog_timer_set);
 
 u32 ssb_gpio_in(struct ssb_bus *bus, u32 mask)
 {
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 8ac9cddac57..cab100acf98 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -18,6 +18,16 @@ config XEN_SCRUB_PAGES
 	  secure, but slightly less efficient.
 	  If in doubt, say yes.
 
+config XEN_DEV_EVTCHN
+	tristate "Xen /dev/xen/evtchn device"
+	depends on XEN
+	default y
+	help
+	  The evtchn driver allows a userspace process to triger event
+	  channels and to receive notification of an event channel
+	  firing.
+	  If in doubt, say yes.
+
 config XENFS
 	tristate "Xen filesystem"
 	depends on XEN
@@ -41,3 +51,13 @@ config XEN_COMPAT_XENFS
          a xen platform.
          If in doubt, say yes.
 
+config XEN_SYS_HYPERVISOR
+       bool "Create xen entries under /sys/hypervisor"
+       depends on XEN && SYSFS
+       select SYS_HYPERVISOR
+       default y
+       help
+         Create entries under /sys/hypervisor describing the Xen
+	 hypervisor environment.  When running native or in another
+	 virtual environment, /sys/hypervisor will still be present,
+	 but will have no xen contents.
+\ No newline at end of file
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index ff8accc9e10..ec2a39b1e26 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -4,4 +4,6 @@ obj-y	+= xenbus/
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu_hotplug.o
 obj-$(CONFIG_XEN_XENCOMM)	+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)	+= balloon.o
-obj-$(CONFIG_XENFS)		+= xenfs/
-\ No newline at end of file
+obj-$(CONFIG_XEN_DEV_EVTCHN)	+= evtchn.o
+obj-$(CONFIG_XENFS)		+= xenfs/
+obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
+\ No newline at end of file
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 30963af5dba..891d2e90753 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -151,6 +151,12 @@ static unsigned int evtchn_from_irq(unsigned irq)
 	return info_for_irq(irq)->evtchn;
 }
 
+unsigned irq_from_evtchn(unsigned int evtchn)
+{
+	return evtchn_to_irq[evtchn];
+}
+EXPORT_SYMBOL_GPL(irq_from_evtchn);
+
 static enum ipi_vector ipi_from_irq(unsigned irq)
 {
 	struct irq_info *info = info_for_irq(irq);
@@ -335,7 +341,7 @@ static int find_unbound_irq(void)
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	desc = irq_to_desc_alloc_cpu(irq, 0);
+	desc = irq_to_desc_alloc_node(irq, 0);
 	if (WARN_ON(desc == NULL))
 		return -1;
 
@@ -688,13 +694,13 @@ void rebind_evtchn_irq(int evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
+static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
 	int evtchn = evtchn_from_irq(irq);
 
 	if (!VALID_EVTCHN(evtchn))
-		return;
+		return -1;
 
 	/* Send future instances of this interrupt to other vcpu. */
 	bind_vcpu.port = evtchn;
@@ -707,13 +713,15 @@ static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu);
-}
 
+	return 0;
+}
 
-static void set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
 {
 	unsigned tcpu = cpumask_first(dest);
-	rebind_irq_to_cpu(irq, tcpu);
+
+	return rebind_irq_to_cpu(irq, tcpu);
 }
 
 int resend_irq_on_evtchn(unsigned int irq)
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
new file mode 100644
index 00000000000..af031950f9b
--- /dev/null
+++ b/drivers/xen/evtchn.c
@@ -0,0 +1,507 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+	struct mutex bind_mutex; /* serialize bind/unbind operations */
+
+	/* Notification ring, accessed via /dev/xen/evtchn. */
+#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
+#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+	evtchn_port_t *ring;
+	unsigned int ring_cons, ring_prod, ring_overflow;
+	struct mutex ring_cons_mutex; /* protect against concurrent readers */
+
+	/* Processes wait on this queue when ring is empty. */
+	wait_queue_head_t evtchn_wait;
+	struct fasync_struct *evtchn_async_queue;
+	const char *name;
+};
+
+/* Who's bound to each port? */
+static struct per_user_data *port_user[NR_EVENT_CHANNELS];
+static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+
+irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+	unsigned int port = (unsigned long)data;
+	struct per_user_data *u;
+
+	spin_lock(&port_user_lock);
+
+	u = port_user[port];
+
+	disable_irq_nosync(irq);
+
+	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
+		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+		wmb(); /* Ensure ring contents visible */
+		if (u->ring_cons == u->ring_prod++) {
+			wake_up_interruptible(&u->evtchn_wait);
+			kill_fasync(&u->evtchn_async_queue,
+				    SIGIO, POLL_IN);
+		}
+	} else {
+		u->ring_overflow = 1;
+	}
+
+	spin_unlock(&port_user_lock);
+
+	return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	int rc;
+	unsigned int c, p, bytes1 = 0, bytes2 = 0;
+	struct per_user_data *u = file->private_data;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	if (count == 0)
+		return 0;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	for (;;) {
+		mutex_lock(&u->ring_cons_mutex);
+
+		rc = -EFBIG;
+		if (u->ring_overflow)
+			goto unlock_out;
+
+		c = u->ring_cons;
+		p = u->ring_prod;
+		if (c != p)
+			break;
+
+		mutex_unlock(&u->ring_cons_mutex);
+
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		rc = wait_event_interruptible(u->evtchn_wait,
+					      u->ring_cons != u->ring_prod);
+		if (rc)
+			return rc;
+	}
+
+	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+	if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
+		bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+			sizeof(evtchn_port_t);
+		bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+	} else {
+		bytes1 = (p - c) * sizeof(evtchn_port_t);
+		bytes2 = 0;
+	}
+
+	/* Truncate chunks according to caller's maximum byte count. */
+	if (bytes1 > count) {
+		bytes1 = count;
+		bytes2 = 0;
+	} else if ((bytes1 + bytes2) > count) {
+		bytes2 = count - bytes1;
+	}
+
+	rc = -EFAULT;
+	rmb(); /* Ensure that we see the port before we copy it. */
+	if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+	    ((bytes2 != 0) &&
+	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+		goto unlock_out;
+
+	u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
+	rc = bytes1 + bytes2;
+
+ unlock_out:
+	mutex_unlock(&u->ring_cons_mutex);
+	return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	int rc, i;
+	evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	struct per_user_data *u = file->private_data;
+
+	if (kbuf == NULL)
+		return -ENOMEM;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	rc = 0;
+	if (count == 0)
+		goto out;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	rc = -EFAULT;
+	if (copy_from_user(kbuf, buf, count) != 0)
+		goto out;
+
+	spin_lock_irq(&port_user_lock);
+	for (i = 0; i < (count/sizeof(evtchn_port_t)); i++)
+		if ((kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u))
+			enable_irq(irq_from_evtchn(kbuf[i]));
+	spin_unlock_irq(&port_user_lock);
+
+	rc = count;
+
+ out:
+	free_page((unsigned long)kbuf);
+	return rc;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, int port)
+{
+	int rc = 0;
+
+	/*
+	 * Ports are never reused, so every caller should pass in a
+	 * unique port.
+	 *
+	 * (Locking not necessary because we haven't registered the
+	 * interrupt handler yet, and our caller has already
+	 * serialized bind operations.)
+	 */
+	BUG_ON(port_user[port] != NULL);
+	port_user[port] = u;
+
+	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+				       u->name, (void *)(unsigned long)port);
+	if (rc >= 0)
+		rc = 0;
+
+	return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+{
+	int irq = irq_from_evtchn(port);
+
+	unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+
+	/* make sure we unbind the irq handler before clearing the port */
+	barrier();
+
+	port_user[port] = NULL;
+}
+
+static long evtchn_ioctl(struct file *file,
+			 unsigned int cmd, unsigned long arg)
+{
+	int rc;
+	struct per_user_data *u = file->private_data;
+	void __user *uarg = (void __user *) arg;
+
+	/* Prevent bind from racing with unbind */
+	mutex_lock(&u->bind_mutex);
+
+	switch (cmd) {
+	case IOCTL_EVTCHN_BIND_VIRQ: {
+		struct ioctl_evtchn_bind_virq bind;
+		struct evtchn_bind_virq bind_virq;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_virq.virq = bind.virq;
+		bind_virq.vcpu = 0;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						 &bind_virq);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_virq.port);
+		if (rc == 0)
+			rc = bind_virq.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+		struct ioctl_evtchn_bind_interdomain bind;
+		struct evtchn_bind_interdomain bind_interdomain;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_interdomain.remote_dom  = bind.remote_domain;
+		bind_interdomain.remote_port = bind.remote_port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+						 &bind_interdomain);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+		if (rc == 0)
+			rc = bind_interdomain.local_port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+		struct ioctl_evtchn_bind_unbound_port bind;
+		struct evtchn_alloc_unbound alloc_unbound;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		alloc_unbound.dom        = DOMID_SELF;
+		alloc_unbound.remote_dom = bind.remote_domain;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+						 &alloc_unbound);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, alloc_unbound.port);
+		if (rc == 0)
+			rc = alloc_unbound.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_UNBIND: {
+		struct ioctl_evtchn_unbind unbind;
+
+		rc = -EFAULT;
+		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+			break;
+
+		rc = -EINVAL;
+		if (unbind.port >= NR_EVENT_CHANNELS)
+			break;
+
+		spin_lock_irq(&port_user_lock);
+
+		rc = -ENOTCONN;
+		if (port_user[unbind.port] != u) {
+			spin_unlock_irq(&port_user_lock);
+			break;
+		}
+
+		evtchn_unbind_from_user(u, unbind.port);
+
+		spin_unlock_irq(&port_user_lock);
+
+		rc = 0;
+		break;
+	}
+
+	case IOCTL_EVTCHN_NOTIFY: {
+		struct ioctl_evtchn_notify notify;
+
+		rc = -EFAULT;
+		if (copy_from_user(&notify, uarg, sizeof(notify)))
+			break;
+
+		if (notify.port >= NR_EVENT_CHANNELS) {
+			rc = -EINVAL;
+		} else if (port_user[notify.port] != u) {
+			rc = -ENOTCONN;
+		} else {
+			notify_remote_via_evtchn(notify.port);
+			rc = 0;
+		}
+		break;
+	}
+
+	case IOCTL_EVTCHN_RESET: {
+		/* Initialise the ring to empty. Clear errors. */
+		mutex_lock(&u->ring_cons_mutex);
+		spin_lock_irq(&port_user_lock);
+		u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+		spin_unlock_irq(&port_user_lock);
+		mutex_unlock(&u->ring_cons_mutex);
+		rc = 0;
+		break;
+	}
+
+	default:
+		rc = -ENOSYS;
+		break;
+	}
+	mutex_unlock(&u->bind_mutex);
+
+	return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+	unsigned int mask = POLLOUT | POLLWRNORM;
+	struct per_user_data *u = file->private_data;
+
+	poll_wait(file, &u->evtchn_wait, wait);
+	if (u->ring_cons != u->ring_prod)
+		mask |= POLLIN | POLLRDNORM;
+	if (u->ring_overflow)
+		mask = POLLERR;
+	return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+	struct per_user_data *u = filp->private_data;
+	return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+	struct per_user_data *u;
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+	if (u->name == NULL) {
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	init_waitqueue_head(&u->evtchn_wait);
+
+	u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	if (u->ring == NULL) {
+		kfree(u->name);
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	mutex_init(&u->bind_mutex);
+	mutex_init(&u->ring_cons_mutex);
+
+	filp->private_data = u;
+
+	return 0;
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+	int i;
+	struct per_user_data *u = filp->private_data;
+
+	spin_lock_irq(&port_user_lock);
+
+	free_page((unsigned long)u->ring);
+
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+		if (port_user[i] != u)
+			continue;
+
+		evtchn_unbind_from_user(port_user[i], i);
+	}
+
+	spin_unlock_irq(&port_user_lock);
+
+	kfree(u->name);
+	kfree(u);
+
+	return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+	.owner   = THIS_MODULE,
+	.read    = evtchn_read,
+	.write   = evtchn_write,
+	.unlocked_ioctl = evtchn_ioctl,
+	.poll    = evtchn_poll,
+	.fasync  = evtchn_fasync,
+	.open    = evtchn_open,
+	.release = evtchn_release,
+};
+
+static struct miscdevice evtchn_miscdev = {
+	.minor        = MISC_DYNAMIC_MINOR,
+	.name         = "evtchn",
+	.fops         = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	spin_lock_init(&port_user_lock);
+	memset(port_user, 0, sizeof(port_user));
+
+	/* Create '/dev/misc/evtchn'. */
+	err = misc_register(&evtchn_miscdev);
+	if (err != 0) {
+		printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+		return err;
+	}
+
+	printk(KERN_INFO "Event-channel device installed.\n");
+
+	return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+	misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 4b5b84837ee..fddc2025dec 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -98,9 +98,8 @@ static void do_suspend(void)
 		goto out;
 	}
 
-	printk("suspending xenbus...\n");
-	/* XXX use normal device tree? */
-	xenbus_suspend();
+	printk(KERN_DEBUG "suspending xenstore...\n");
+	xs_suspend();
 
 	err = device_power_down(PMSG_SUSPEND);
 	if (err) {
@@ -116,9 +115,9 @@ static void do_suspend(void)
 
 	if (!cancelled) {
 		xen_arch_resume();
-		xenbus_resume();
+		xs_resume();
 	} else
-		xenbus_suspend_cancel();
+		xs_suspend_cancel();
 
 	device_power_up(PMSG_RESUME);
 
diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
new file mode 100644
index 00000000000..88a60e03ccf
--- /dev/null
+++ b/drivers/xen/sys-hypervisor.c
@@ -0,0 +1,445 @@
+/*
+ *  copyright (c) 2006 IBM Corporation
+ *  Authored by: Mike D. Day <ncmike@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr  _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = \
+	__ATTR(_name, 0644, _name##_show, _name##_store)
+
+struct hyp_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+	ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+	void *hyp_attr_data;
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static void xen_sysfs_type_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version >> 16);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version & 0xff);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *extra;
+
+	extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+	if (extra) {
+		ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", extra);
+		kfree(extra);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+	&major_attr.attr,
+	&minor_attr.attr,
+	&extra_attr.attr,
+	NULL
+};
+
+static struct attribute_group version_group = {
+	.name = "version",
+	.attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+static void xen_sysfs_version_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	char *vm, *val;
+	int ret;
+	extern int xenstored_ready;
+
+	if (!xenstored_ready)
+		return -EBUSY;
+
+	vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+	if (IS_ERR(vm))
+		return PTR_ERR(vm);
+	val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+	kfree(vm);
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+	ret = sprintf(buffer, "%s\n", val);
+	kfree(val);
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+static void xen_sysfs_uuid_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compiler);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_by);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_date);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+	&compiler_attr.attr,
+	&compiled_by_attr.attr,
+	&compile_date_attr.attr,
+	NULL
+};
+
+static struct attribute_group xen_compilation_group = {
+	.name = "compilation",
+	.attrs = xen_compile_attrs,
+};
+
+int __init static xen_compilation_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+static void xen_compilation_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *caps;
+
+	caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+	if (caps) {
+		ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", caps);
+		kfree(caps);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *cset;
+
+	cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+	if (cset) {
+		ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", cset);
+		kfree(cset);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_platform_parameters *parms;
+
+	parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+	if (parms) {
+		ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+					     parms);
+		if (!ret)
+			ret = sprintf(buffer, "%lx\n", parms->virt_start);
+		kfree(parms);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+
+	ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+	if (ret > 0)
+		ret = sprintf(buffer, "%x\n", ret);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+	ssize_t ret;
+	struct xen_feature_info info;
+
+	info.submap_idx = index;
+	ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+	if (!ret)
+		ret = sprintf(buffer, "%08x", info.submap);
+
+	return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t len;
+	int i;
+
+	len = 0;
+	for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+		int ret = xen_feature_show(i, buffer + len);
+		if (ret < 0) {
+			if (len == 0)
+				len = ret;
+			break;
+		}
+		len += ret;
+	}
+	if (len > 0)
+		buffer[len++] = '\n';
+
+	return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static struct attribute *xen_properties_attrs[] = {
+	&capabilities_attr.attr,
+	&changeset_attr.attr,
+	&virtual_start_attr.attr,
+	&pagesize_attr.attr,
+	&features_attr.attr,
+	NULL
+};
+
+static struct attribute_group xen_properties_group = {
+	.name = "properties",
+	.attrs = xen_properties_attrs,
+};
+
+static int __init xen_properties_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static void xen_properties_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static int __init hyper_sysfs_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	ret = xen_sysfs_type_init();
+	if (ret)
+		goto out;
+	ret = xen_sysfs_version_init();
+	if (ret)
+		goto version_out;
+	ret = xen_compilation_init();
+	if (ret)
+		goto comp_out;
+	ret = xen_sysfs_uuid_init();
+	if (ret)
+		goto uuid_out;
+	ret = xen_properties_init();
+	if (ret)
+		goto prop_out;
+
+	goto out;
+
+prop_out:
+	xen_sysfs_uuid_destroy();
+uuid_out:
+	xen_compilation_destroy();
+comp_out:
+	xen_sysfs_version_destroy();
+version_out:
+	xen_sysfs_type_destroy();
+out:
+	return ret;
+}
+
+static void __exit hyper_sysfs_exit(void)
+{
+	xen_properties_destroy();
+	xen_compilation_destroy();
+	xen_sysfs_uuid_destroy();
+	xen_sysfs_version_destroy();
+	xen_sysfs_type_destroy();
+
+}
+module_init(hyper_sysfs_init);
+module_exit(hyper_sysfs_exit);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+			      struct attribute *attr,
+			      char *buffer)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->show)
+		return hyp_attr->show(hyp_attr, buffer);
+	return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buffer,
+			       size_t len)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->store)
+		return hyp_attr->store(hyp_attr, buffer, len);
+	return 0;
+}
+
+static struct sysfs_ops hyp_sysfs_ops = {
+	.show = hyp_sysfs_show,
+	.store = hyp_sysfs_store,
+};
+
+static struct kobj_type hyp_sysfs_kobj_type = {
+	.sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+	return 0;
+}
+device_initcall(hypervisor_subsys_init);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 773d1cf2328..d42e25d5968 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -71,6 +71,9 @@ static int xenbus_probe_frontend(const char *type, const char *name);
 
 static void xenbus_dev_shutdown(struct device *_dev);
 
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state);
+static int xenbus_dev_resume(struct device *dev);
+
 /* If something in array of ids matches this device, return it. */
 static const struct xenbus_device_id *
 match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
@@ -188,6 +191,9 @@ static struct xen_bus_type xenbus_frontend = {
 		.remove    = xenbus_dev_remove,
 		.shutdown  = xenbus_dev_shutdown,
 		.dev_attrs = xenbus_dev_attrs,
+
+		.suspend   = xenbus_dev_suspend,
+		.resume    = xenbus_dev_resume,
 	},
 };
 
@@ -654,6 +660,7 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 
 	kfree(root);
 }
+EXPORT_SYMBOL_GPL(xenbus_dev_changed);
 
 static void frontend_changed(struct xenbus_watch *watch,
 			     const char **vec, unsigned int len)
@@ -669,7 +676,7 @@ static struct xenbus_watch fe_watch = {
 	.callback = frontend_changed,
 };
 
-static int suspend_dev(struct device *dev, void *data)
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state)
 {
 	int err = 0;
 	struct xenbus_driver *drv;
@@ -682,35 +689,14 @@ static int suspend_dev(struct device *dev, void *data)
 	drv = to_xenbus_driver(dev->driver);
 	xdev = container_of(dev, struct xenbus_device, dev);
 	if (drv->suspend)
-		err = drv->suspend(xdev);
+		err = drv->suspend(xdev, state);
 	if (err)
 		printk(KERN_WARNING
 		       "xenbus: suspend %s failed: %i\n", dev_name(dev), err);
 	return 0;
 }
 
-static int suspend_cancel_dev(struct device *dev, void *data)
-{
-	int err = 0;
-	struct xenbus_driver *drv;
-	struct xenbus_device *xdev;
-
-	DPRINTK("");
-
-	if (dev->driver == NULL)
-		return 0;
-	drv = to_xenbus_driver(dev->driver);
-	xdev = container_of(dev, struct xenbus_device, dev);
-	if (drv->suspend_cancel)
-		err = drv->suspend_cancel(xdev);
-	if (err)
-		printk(KERN_WARNING
-		       "xenbus: suspend_cancel %s failed: %i\n",
-		       dev_name(dev), err);
-	return 0;
-}
-
-static int resume_dev(struct device *dev, void *data)
+static int xenbus_dev_resume(struct device *dev)
 {
 	int err;
 	struct xenbus_driver *drv;
@@ -755,33 +741,6 @@ static int resume_dev(struct device *dev, void *data)
 	return 0;
 }
 
-void xenbus_suspend(void)
-{
-	DPRINTK("");
-
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_dev);
-	xenbus_backend_suspend(suspend_dev);
-	xs_suspend();
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend);
-
-void xenbus_resume(void)
-{
-	xb_init_comms();
-	xs_resume();
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, resume_dev);
-	xenbus_backend_resume(resume_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_resume);
-
-void xenbus_suspend_cancel(void)
-{
-	xs_suspend_cancel();
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_cancel_dev);
-	xenbus_backend_resume(suspend_cancel_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend_cancel);
-
 /* A flag to determine if xenstored is 'ready' (i.e. has started) */
 int xenstored_ready = 0;
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index e325eab4724..eab33f1dbdf 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -673,6 +673,8 @@ void xs_resume(void)
 	struct xenbus_watch *watch;
 	char token[sizeof(watch) * 2 + 1];
 
+	xb_init_comms();
+
 	mutex_unlock(&xs_state.response_mutex);
 	mutex_unlock(&xs_state.request_mutex);
 	up_write(&xs_state.transaction_mutex);
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 515741a8e6b..6559e0c752c 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -20,10 +20,27 @@
 MODULE_DESCRIPTION("Xen filesystem");
 MODULE_LICENSE("GPL");
 
+static ssize_t capabilities_read(struct file *file, char __user *buf,
+				 size_t size, loff_t *off)
+{
+	char *tmp = "";
+
+	if (xen_initial_domain())
+		tmp = "control_d\n";
+
+	return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
+}
+
+static const struct file_operations capabilities_file_ops = {
+	.read = capabilities_read,
+};
+
 static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	static struct tree_descr xenfs_files[] = {
-		[2] = {"xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR},
+		[1] = {},
+		{ "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
+		{ "capabilities", &capabilities_file_ops, S_IRUGO },
 		{""},
 	};
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index eeb24684590..2341375386f 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -297,20 +297,14 @@ static int validate_request(struct autofs_wait_queue **wait,
 	 */
 	if (notify == NFY_MOUNT) {
 		/*
-		 * If the dentry isn't hashed just go ahead and try the
-		 * mount again with a new wait (not much else we can do).
-		*/
-		if (!d_unhashed(dentry)) {
-			/*
-			 * But if the dentry is hashed, that means that we
-			 * got here through the revalidate path.  Thus, we
-			 * need to check if the dentry has been mounted
-			 * while we waited on the wq_mutex. If it has,
-			 * simply return success.
-			 */
-			if (d_mountpoint(dentry))
-				return 0;
-		}
+		 * If the dentry was successfully mounted while we slept
+		 * on the wait queue mutex we can return success. If it
+		 * isn't mounted (doesn't have submounts for the case of
+		 * a multi-mount with no mount at it's base) we can
+		 * continue on and create a new request.
+		 */
+		if (have_submounts(dentry))
+			return 0;
 	}
 
 	return 1;
diff --git a/fs/bio.c b/fs/bio.c
index 98711647ece..740699c4f90 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -26,10 +26,9 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
-DEFINE_TRACE(block_split);
+#include <trace/events/block.h>
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3e2c7c738f2..35af9335506 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2622,7 +2622,18 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 						       search_start);
 		if (block_group && block_group_bits(block_group, data)) {
 			down_read(&space_info->groups_sem);
-			goto have_block_group;
+			if (list_empty(&block_group->list) ||
+			    block_group->ro) {
+				/*
+				 * someone is removing this block group,
+				 * we can't jump into the have_block_group
+				 * target because our list pointers are not
+				 * valid
+				 */
+				btrfs_put_block_group(block_group);
+				up_read(&space_info->groups_sem);
+			} else
+				goto have_block_group;
 		} else if (block_group) {
 			btrfs_put_block_group(block_group);
 		}
@@ -2656,6 +2667,13 @@ have_block_group:
 			 * people trying to start a new cluster
 			 */
 			spin_lock(&last_ptr->refill_lock);
+			if (last_ptr->block_group &&
+			    (last_ptr->block_group->ro ||
+			    !block_group_bits(last_ptr->block_group, data))) {
+				offset = 0;
+				goto refill_cluster;
+			}
+
 			offset = btrfs_alloc_from_cluster(block_group, last_ptr,
 						 num_bytes, search_start);
 			if (offset) {
@@ -2681,10 +2699,17 @@ have_block_group:
 
 				last_ptr_loop = 1;
 				search_start = block_group->key.objectid;
+				/*
+				 * we know this block group is properly
+				 * in the list because
+				 * btrfs_remove_block_group, drops the
+				 * cluster before it removes the block
+				 * group from the list
+				 */
 				goto have_block_group;
 			}
 			spin_unlock(&last_ptr->lock);
-
+refill_cluster:
 			/*
 			 * this cluster didn't work out, free it and
 			 * start over
@@ -5968,6 +5993,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_path *path;
 	struct btrfs_block_group_cache *block_group;
+	struct btrfs_free_cluster *cluster;
 	struct btrfs_key key;
 	int ret;
 
@@ -5979,6 +6005,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	memcpy(&key, &block_group->key, sizeof(key));
 
+	/* make sure this block group isn't part of an allocation cluster */
+	cluster = &root->fs_info->data_alloc_cluster;
+	spin_lock(&cluster->refill_lock);
+	btrfs_return_cluster_to_free_space(block_group, cluster);
+	spin_unlock(&cluster->refill_lock);
+
+	/*
+	 * make sure this block group isn't part of a metadata
+	 * allocation cluster
+	 */
+	cluster = &root->fs_info->meta_alloc_cluster;
+	spin_lock(&cluster->refill_lock);
+	btrfs_return_cluster_to_free_space(block_group, cluster);
+	spin_unlock(&cluster->refill_lock);
+
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
@@ -5988,7 +6029,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&root->fs_info->block_group_cache_lock);
 	btrfs_remove_free_space_cache(block_group);
 	down_write(&block_group->space_info->groups_sem);
-	list_del(&block_group->list);
+	/*
+	 * we must use list_del_init so people can check to see if they
+	 * are still on the list after taking the semaphore
+	 */
+	list_del_init(&block_group->list);
 	up_write(&block_group->space_info->groups_sem);
 
 	spin_lock(&block_group->space_info->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5f01dad4b69..a6d35b0054c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1440,6 +1440,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	device->io_align = root->sectorsize;
 	device->sector_size = root->sectorsize;
 	device->total_bytes = i_size_read(bdev->bd_inode);
+	device->disk_total_bytes = device->total_bytes;
 	device->dev_root = root->fs_info->dev_root;
 	device->bdev = bdev;
 	device->in_fs_metadata = 1;
diff --git a/fs/buffer.c b/fs/buffer.c
index aed297739eb..49106127a4a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2736,6 +2736,8 @@ has_buffers:
 		pos += blocksize;
 	}
 
+	map_bh.b_size = blocksize;
+	map_bh.b_state = 0;
 	err = get_block(inode, iblock, &map_bh, 0);
 	if (err)
 		goto unlock;
diff --git a/fs/inode.c b/fs/inode.c
index 0571983755d..bca0c618fdb 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -219,6 +219,7 @@ static struct inode *alloc_inode(struct super_block *sb)
 void destroy_inode(struct inode *inode)
 {
 	BUG_ON(inode_has_buffers(inode));
+	ima_inode_free(inode);
 	security_inode_free(inode);
 	if (inode->i_sb->s_op->destroy_inode)
 		inode->i_sb->s_op->destroy_inode(inode);
@@ -1053,13 +1054,22 @@ int insert_inode_locked(struct inode *inode)
 	struct super_block *sb = inode->i_sb;
 	ino_t ino = inode->i_ino;
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
-	struct inode *old;
 
 	inode->i_state |= I_LOCK|I_NEW;
 	while (1) {
+		struct hlist_node *node;
+		struct inode *old = NULL;
 		spin_lock(&inode_lock);
-		old = find_inode_fast(sb, head, ino);
-		if (likely(!old)) {
+		hlist_for_each_entry(old, node, head, i_hash) {
+			if (old->i_ino != ino)
+				continue;
+			if (old->i_sb != sb)
+				continue;
+			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+				continue;
+			break;
+		}
+		if (likely(!node)) {
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode_lock);
 			return 0;
@@ -1081,14 +1091,24 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 {
 	struct super_block *sb = inode->i_sb;
 	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
-	struct inode *old;
 
 	inode->i_state |= I_LOCK|I_NEW;
 
 	while (1) {
+		struct hlist_node *node;
+		struct inode *old = NULL;
+
 		spin_lock(&inode_lock);
-		old = find_inode(sb, head, test, data);
-		if (likely(!old)) {
+		hlist_for_each_entry(old, node, head, i_hash) {
+			if (old->i_sb != sb)
+				continue;
+			if (!test(old, data))
+				continue;
+			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+				continue;
+			break;
+		}
+		if (likely(!node)) {
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode_lock);
 			return 0;
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 06560c520f4..618e21c0b7a 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -241,7 +241,7 @@ write_out_data:
 			spin_lock(&journal->j_list_lock);
 		}
 		/* Someone already cleaned up the buffer? */
-		if (!buffer_jbd(bh)
+		if (!buffer_jbd(bh) || bh2jh(bh) != jh
 			|| jh->b_transaction != commit_transaction
 			|| jh->b_jlist != BJ_SyncData) {
 			jbd_unlock_bh_state(bh);
@@ -478,7 +478,9 @@ void journal_commit_transaction(journal_t *journal)
 			spin_lock(&journal->j_list_lock);
 			continue;
 		}
-		if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
+		if (buffer_jbd(bh) && bh2jh(bh) == jh &&
+		    jh->b_transaction == commit_transaction &&
+		    jh->b_jlist == BJ_Locked) {
 			__journal_unfile_buffer(jh);
 			jbd_unlock_bh_state(bh);
 			journal_remove_journal_head(bh);
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index 9bca39cf99e..1afa4dd4cae 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -12,20 +12,14 @@
 
 static int loadavg_proc_show(struct seq_file *m, void *v)
 {
-	int a, b, c;
-	unsigned long seq;
+	unsigned long avnrun[3];
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		a = avenrun[0] + (FIXED_1/200);
-		b = avenrun[1] + (FIXED_1/200);
-		c = avenrun[2] + (FIXED_1/200);
-	} while (read_seqretry(&xtime_lock, seq));
+	get_avenrun(avnrun, FIXED_1/200, 0);
 
-	seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
-		LOAD_INT(a), LOAD_FRAC(a),
-		LOAD_INT(b), LOAD_FRAC(b),
-		LOAD_INT(c), LOAD_FRAC(c),
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
 		task_active_pid_ns(current)->last_pid);
 	return 0;
diff --git a/include/Kbuild b/include/Kbuild
index d8c3e3cbf41..fe36accd432 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -8,3 +8,4 @@ header-y += mtd/
 header-y += rdma/
 header-y += video/
 header-y += drm/
+header-y += xen/
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e6d0ca70ab..e410f602cab 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -280,17 +280,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif
 
 /*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests.  By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
  */
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode()	do {} while (0)
-#define arch_leave_lazy_cpu_mode()	do {} while (0)
-#define arch_flush_lazy_cpu_mode()	do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 89853bcd27a..f1736ca7922 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,7 +63,7 @@
 #define BRANCH_PROFILE()
 #endif
 
-#ifdef CONFIG_EVENT_TRACER
+#ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
 			*(_ftrace_events)				\
 			VMLINUX_SYMBOL(__stop_ftrace_events) = .;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 88be890ee3c..51b4b0a5ce8 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -119,7 +119,7 @@ extern int pci_mmcfg_config_num;
 extern int sbf_port;
 extern unsigned long acpi_realmode_flags;
 
-int acpi_register_gsi (u32 gsi, int triggering, int polarity);
+int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index 48ee32a18ac..64a982ea5d5 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -159,6 +159,7 @@
 #define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
+struct amba_device; /* in uncompress this is included but amba/bus.h is not */
 struct amba_pl010_data {
 	void (*set_mctrl)(struct amba_device *dev, void __iomem *base, unsigned int mctrl);
 };
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d960889e92e..7e4350ece0f 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -116,9 +116,9 @@ struct blk_io_trace {
  * The remap event
  */
 struct blk_io_trace_remap {
-	__be32 device;
 	__be32 device_from;
-	__be64 sector;
+	__be32 device_to;
+	__be64 sector_from;
 };
 
 enum {
@@ -165,8 +165,9 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q,
-	char *name, dev_t dev, struct blk_user_trace_setup *buts);
+extern int do_blk_trace_setup(struct request_queue *q, char *name,
+			      dev_t dev, struct block_device *bdev,
+			      struct blk_user_trace_setup *buts);
 extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
 /**
@@ -193,22 +194,42 @@ extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
 				void *data, size_t len);
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			   struct block_device *bdev,
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
+extern int blk_trace_init_sysfs(struct device *dev);
 
 extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
-#define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
-#define blk_trace_shutdown(q)			do { } while (0)
-#define do_blk_trace_setup(q, name, dev, buts)	(-ENOTTY)
-#define blk_add_driver_data(q, rq, data, len)	do {} while (0)
-#define blk_trace_setup(q, name, dev, arg)	(-ENOTTY)
-#define blk_trace_startstop(q, start)		(-ENOTTY)
-#define blk_trace_remove(q)			(-ENOTTY)
-#define blk_add_trace_msg(q, fmt, ...)		do { } while (0)
+# define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
+# define blk_trace_shutdown(q)				do { } while (0)
+# define do_blk_trace_setup(q, name, dev, bdev, buts)	(-ENOTTY)
+# define blk_add_driver_data(q, rq, data, len)		do {} while (0)
+# define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
+# define blk_trace_startstop(q, start)			(-ENOTTY)
+# define blk_trace_remove(q)				(-ENOTTY)
+# define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
+static inline int blk_trace_init_sysfs(struct device *dev)
+{
+	return 0;
+}
 
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+
+static inline int blk_cmd_buf_len(struct request *rq)
+{
+	return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+}
+
+extern void blk_dump_cmd(char *buf, struct request *rq);
+extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
+
+#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 9f315382610..c5ac87ca7bc 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1022,6 +1022,8 @@ typedef struct cpumask *cpumask_var_t;
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
@@ -1040,6 +1042,19 @@ static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 	return true;
 }
 
+static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	cpumask_clear(*mask);
+	return true;
+}
+
+static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+					  int node)
+{
+	cpumask_clear(*mask);
+	return true;
+}
+
 static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 28d53cb7b5a..171ad8aedc8 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -32,6 +32,8 @@ extern void dma_debug_add_bus(struct bus_type *bus);
 
 extern void dma_debug_init(u32 num_entries);
 
+extern int dma_debug_resize_entries(u32 num_entries);
+
 extern void debug_dma_map_page(struct device *dev, struct page *page,
 			       size_t offset, size_t size,
 			       int direction, dma_addr_t dma_addr,
@@ -91,6 +93,11 @@ static inline void dma_debug_init(u32 num_entries)
 {
 }
 
+static inline int dma_debug_resize_entries(u32 num_entries)
+{
+	return 0;
+}
+
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,
 				      int direction, dma_addr_t dma_addr,
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e397dc342cd..10ff5c49882 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -108,6 +108,7 @@ struct irte {
 };
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
+extern int intr_remapping_supported(void);
 extern int enable_intr_remapping(int);
 extern void disable_intr_remapping(void);
 extern int reenable_intr_remapping(int);
@@ -157,6 +158,8 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic)
 }
 #define irq_remapped(irq)		(0)
 #define enable_intr_remapping(mode)	(-1)
+#define disable_intr_remapping()	(0)
+#define reenable_intr_remapping(mode)	(0)
 #define intr_remapping_enabled		(0)
 #endif
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a0c2f221e6..39b95c56587 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -233,8 +233,6 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
-extern void ftrace_release(void *start, unsigned long size);
-
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
@@ -325,13 +323,8 @@ static inline void __ftrace_enabled_restore(int enabled)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(struct module *mod,
-			       unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
-static inline void
-ftrace_init_module(struct module *mod,
-		   unsigned long *start, unsigned long *end) { }
 #endif
 
 /*
@@ -368,6 +361,7 @@ struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
 	unsigned long long calltime;
+	unsigned long long subtime;
 };
 
 /*
@@ -379,8 +373,6 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
-extern void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -496,8 +488,15 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 
 extern int ftrace_dump_on_oops;
 
+#ifdef CONFIG_PREEMPT
+#define INIT_TRACE_RECURSION		.trace_recursion = 0,
+#endif
+
 #endif /* CONFIG_TRACING */
 
+#ifndef INIT_TRACE_RECURSION
+#define INIT_TRACE_RECURSION
+#endif
 
 #ifdef CONFIG_HW_BRANCH_TRACER
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
new file mode 100644
index 00000000000..5c093ffc655
--- /dev/null
+++ b/include/linux/ftrace_event.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_FTRACE_EVENT_H
+#define _LINUX_FTRACE_EVENT_H
+
+#include <linux/trace_seq.h>
+#include <linux/ring_buffer.h>
+#include <linux/percpu.h>
+
+struct trace_array;
+struct tracer;
+struct dentry;
+
+DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
+
+struct trace_print_flags {
+	unsigned long		mask;
+	const char		*name;
+};
+
+const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+				   unsigned long flags,
+				   const struct trace_print_flags *flag_array);
+
+const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+				     const struct trace_print_flags *symbol_array);
+
+/*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+	unsigned short		type;
+	unsigned char		flags;
+	unsigned char		preempt_count;
+	int			pid;
+	int			tgid;
+};
+
+#define FTRACE_MAX_EVENT						\
+	((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)
+
+/*
+ * Trace iterator - used by printout routines who present trace
+ * results to users and which routines might sleep, etc:
+ */
+struct trace_iterator {
+	struct trace_array	*tr;
+	struct tracer		*trace;
+	void			*private;
+	int			cpu_file;
+	struct mutex		mutex;
+	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
+	unsigned long		iter_flags;
+
+	/* The below is zeroed out in pipe_read */
+	struct trace_seq	seq;
+	struct trace_entry	*ent;
+	int			cpu;
+	u64			ts;
+
+	loff_t			pos;
+	long			idx;
+
+	cpumask_var_t		started;
+};
+
+
+typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
+					      int flags);
+struct trace_event {
+	struct hlist_node	node;
+	struct list_head	list;
+	int			type;
+	trace_print_func	trace;
+	trace_print_func	raw;
+	trace_print_func	hex;
+	trace_print_func	binary;
+};
+
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+/* Return values for print_line callback */
+enum print_line_t {
+	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
+	TRACE_TYPE_HANDLED	= 1,
+	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
+	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
+};
+
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(int type, unsigned long len,
+				  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+
+void tracing_record_cmdline(struct task_struct *tsk);
+
+struct ftrace_event_call {
+	struct list_head	list;
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	struct trace_event	*event;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	int			filter_active;
+	void			*filter;
+	void			*mod;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
+};
+
+#define MAX_FILTER_PRED		32
+#define MAX_FILTER_STR_VAL	128
+
+extern int init_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_current_check_discard(struct ftrace_event_call *call,
+					void *rec,
+					struct ring_buffer_event *event);
+
+extern int trace_define_field(struct ftrace_event_call *call, char *type,
+			      char *name, int offset, int size, int is_signed);
+
+#define is_signed_type(type)	(((type)(-1)) < 0)
+
+int trace_set_clr_event(const char *system, const char *event, int set);
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...)				\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	tracing_record_cmdline(current);				\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
+	} else								\
+		__trace_printk(ip, fmt, ##args);			\
+} while (0)
+
+#define __common_field(type, item, is_signed)				\
+	ret = trace_define_field(event_call, #type, "common_" #item,	\
+				 offsetof(typeof(field.ent), item),	\
+				 sizeof(field.ent.item), is_signed);	\
+	if (ret)							\
+		return ret;
+
+#endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3bf5bb5a34f..34956c8fdeb 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,6 +23,8 @@ union ktime;
 #define FUTEX_TRYLOCK_PI	8
 #define FUTEX_WAIT_BITSET	9
 #define FUTEX_WAKE_BITSET	10
+#define FUTEX_WAIT_REQUEUE_PI	11
+#define FUTEX_CMP_REQUEUE_PI	12
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -38,6 +40,10 @@ union ktime;
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE	(FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_BITSET_PRIVATE	(FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE	(FUTEX_WAIT_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 353c0ac7723..b6b7cf23c2a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -184,6 +184,7 @@ extern struct cred init_cred;
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 	INIT_FTRACE_GRAPH						\
+	INIT_TRACE_RECURSION						\
 }
 
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 91bb76f44f1..ff374ceface 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -566,6 +566,6 @@ struct irq_desc;
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b7cbeed972e..eedbb8e5e0c 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -117,7 +117,7 @@ struct irq_chip {
 	void		(*eoi)(unsigned int irq);
 
 	void		(*end)(unsigned int irq);
-	void		(*set_affinity)(unsigned int irq,
+	int		(*set_affinity)(unsigned int irq,
 					const struct cpumask *dest);
 	int		(*retrigger)(unsigned int irq);
 	int		(*set_type)(unsigned int irq, unsigned int flow_type);
@@ -187,7 +187,7 @@ struct irq_desc {
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
 	cpumask_var_t		affinity;
-	unsigned int		cpu;
+	unsigned int		node;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_var_t		pending_mask;
 #endif
@@ -201,26 +201,23 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-					struct irq_desc *desc, int cpu);
+					struct irq_desc *desc, int node);
 extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
 
 #ifndef CONFIG_SPARSE_IRQ
 extern struct irq_desc irq_desc[NR_IRQS];
-#else /* CONFIG_SPARSE_IRQ */
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu);
-#endif /* CONFIG_SPARSE_IRQ */
-
-extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
+#endif
 
-static inline struct irq_desc *
-irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-	return irq_to_desc(irq);
+#ifdef CONFIG_NUMA_IRQ_DESC
+extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
 #else
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
 	return desc;
-#endif
 }
+#endif
+
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
 
 /*
  * Migration helpers for obsolete names, they will go away:
@@ -386,7 +383,7 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
-extern unsigned int create_irq_nr(unsigned int irq_want);
+extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
@@ -424,47 +421,48 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #ifdef CONFIG_SMP
 /**
- * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * alloc_desc_masks - allocate cpumasks for irq_desc
  * @desc:	pointer to irq_desc struct
  * @cpu:	cpu which will be handling the cpumasks
  * @boot:	true if need bootmem
  *
  * Allocates affinity and pending_mask cpumask if required.
  * Returns true if successful (or not required).
- * Side effect: affinity has all bits set, pending_mask has all bits clear.
  */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 								bool boot)
 {
-	int node;
-
+#ifdef CONFIG_CPUMASK_OFFSTACK
 	if (boot) {
 		alloc_bootmem_cpumask_var(&desc->affinity);
-		cpumask_setall(desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 		alloc_bootmem_cpumask_var(&desc->pending_mask);
-		cpumask_clear(desc->pending_mask);
 #endif
 		return true;
 	}
 
-	node = cpu_to_node(cpu);
-
 	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
 		return false;
-	cpumask_setall(desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
 		free_cpumask_var(desc->affinity);
 		return false;
 	}
-	cpumask_clear(desc->pending_mask);
+#endif
 #endif
 	return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+	cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
+}
+
 /**
  * init_copy_desc_masks - copy cpumasks for irq_desc
  * @old_desc:	pointer to old irq_desc struct
@@ -478,7 +476,7 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 					struct irq_desc *new_desc)
 {
-#ifdef CONFIG_CPUMASKS_OFFSTACK
+#ifdef CONFIG_CPUMASK_OFFSTACK
 	cpumask_copy(new_desc->affinity, old_desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -499,12 +497,16 @@ static inline void free_desc_masks(struct irq_desc *old_desc,
 
 #else /* !CONFIG_SMP */
 
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 								bool boot)
 {
 	return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+}
+
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 					struct irq_desc *new_desc)
 {
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
new file mode 100644
index 00000000000..b616d3930c3
--- /dev/null
+++ b/include/linux/kmemtrace.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ *
+ * This file is released under GPL version 2.
+ */
+
+#ifndef _LINUX_KMEMTRACE_H
+#define _LINUX_KMEMTRACE_H
+
+#ifdef __KERNEL__
+
+#include <trace/events/kmem.h>
+
+#ifdef CONFIG_KMEMTRACE
+extern void kmemtrace_init(void);
+#else
+static inline void kmemtrace_init(void)
+{
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_KMEMTRACE_H */
+
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bff1f0d475c..9772d6cbfc8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,6 +19,7 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
+struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1031,8 +1032,6 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
 extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
-extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
-					unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 						unsigned long end_pfn);
@@ -1319,8 +1318,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern void *alloc_locked_buffer(size_t size);
-extern void free_locked_buffer(void *buffer, size_t size);
-extern void release_locked_buffer(void *buffer, size_t size);
+extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+				 size_t size);
+extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 3d1b7bde128..97491f78b08 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -30,6 +30,8 @@ extern unsigned int kmmio_count;
 
 extern int register_kmmio_probe(struct kmmio_probe *p);
 extern void unregister_kmmio_probe(struct kmmio_probe *p);
+extern int kmmio_init(void);
+extern void kmmio_cleanup(void);
 
 #ifdef CONFIG_MMIOTRACE
 /* kmmio is active by some kmmio_probes? */
diff --git a/include/linux/module.h b/include/linux/module.h
index 627ac082e2a..a8f2c0aa4c3 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -337,6 +337,14 @@ struct module
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
 #endif
+#ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call *trace_events;
+	unsigned int num_trace_events;
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+	unsigned long *ftrace_callsites;
+	unsigned int num_ftrace_callsites;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 67c15653fc2..59e133d39d5 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -95,7 +95,6 @@ extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer);
-extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
 /* Returns 0 on success, -errno on denial. */
@@ -327,15 +326,6 @@ static inline void user_enable_block_step(struct task_struct *task)
 #define arch_ptrace_untrace(task)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_fork
-/*
- * Do machine-specific work to initialize a new task.
- *
- * This is called from copy_process().
- */
-#define arch_ptrace_fork(child, clone_flags)	do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e649bd3f2c9..5710f43bbc9 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -198,6 +198,32 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	at->prev = last;
 }
 
+/**
+ * list_entry_rcu - get the struct for this entry
+ * @ptr:        the &struct list_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_entry_rcu(ptr, type, member) \
+	container_of(rcu_dereference(ptr), type, member)
+
+/**
+ * list_first_entry_rcu - get the first element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_first_entry_rcu(ptr, type, member) \
+	list_entry_rcu((ptr)->next, type, member)
+
 #define __list_for_each_rcu(pos, head) \
 	for (pos = rcu_dereference((head)->next); \
 		pos != (head); \
@@ -214,9 +240,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
 		prefetch(pos->member.next), &pos->member != (head); \
-		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 
 /**
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 58b2aa5312b..5a5153806c4 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -161,8 +161,15 @@ struct rcu_data {
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long resched_ipi;	/* Sent a resched IPI. */
 
-	/* 5) For future __rcu_pending statistics. */
+	/* 5) __rcu_pending() statistics. */
 	long n_rcu_pending;		/* rcu_pending() calls since boot. */
+	long n_rp_qs_pending;
+	long n_rp_cb_ready;
+	long n_rp_cpu_needs_gp;
+	long n_rp_gp_completed;
+	long n_rp_gp_started;
+	long n_rp_need_fqs;
+	long n_rp_need_nothing;
 
 	int cpu;
 };
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e1b7b217388..8670f1575fe 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -11,7 +11,7 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
-	u32		type:2, len:3, time_delta:27;
+	u32		type_len:5, time_delta:27;
 	u32		array[];
 };
 
@@ -24,7 +24,8 @@ struct ring_buffer_event {
  *				  size is variable depending on how much
  *				  padding is needed
  *				 If time_delta is non zero:
- *				  everything else same as RINGBUF_TYPE_DATA
+ *				  array[0] holds the actual length
+ *				  size = 4 + length (bytes)
  *
  * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
  *				 array[0] = time delta (28 .. 59)
@@ -35,22 +36,23 @@ struct ring_buffer_event {
  *				 array[1..2] = tv_sec
  *				 size = 16 bytes
  *
- * @RINGBUF_TYPE_DATA:		Data record
- *				 If len is zero:
+ * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
+ *				Data record
+ *				 If type_len is zero:
  *				  array[0] holds the actual length
  *				  array[1..(length+3)/4] holds data
- *				  size = 4 + 4 + length (bytes)
+ *				  size = 4 + length (bytes)
  *				 else
- *				  length = len << 2
+ *				  length = type_len << 2
  *				  array[0..(length+3)/4-1] holds data
  *				  size = 4 + length (bytes)
  */
 enum ring_buffer_type {
+	RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
 	RINGBUF_TYPE_PADDING,
 	RINGBUF_TYPE_TIME_EXTEND,
 	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
 	RINGBUF_TYPE_TIME_STAMP,
-	RINGBUF_TYPE_DATA,
 };
 
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
@@ -68,13 +70,54 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
+/*
+ * ring_buffer_event_discard can discard any event in the ring buffer.
+ *   it is up to the caller to protect against a reader from
+ *   consuming it or a writer from wrapping and replacing it.
+ *
+ * No external protection is needed if this is called before
+ * the event is commited. But in that case it would be better to
+ * use ring_buffer_discard_commit.
+ *
+ * Note, if an event that has not been committed is discarded
+ * with ring_buffer_event_discard, it must still be committed.
+ */
 void ring_buffer_event_discard(struct ring_buffer_event *event);
 
 /*
+ * ring_buffer_discard_commit will remove an event that has not
+ *   ben committed yet. If this is used, then ring_buffer_unlock_commit
+ *   must not be called on the discarded event. This function
+ *   will try to remove the event from the ring buffer completely
+ *   if another event has not been written after it.
+ *
+ * Example use:
+ *
+ *  if (some_condition)
+ *    ring_buffer_discard_commit(buffer, event);
+ *  else
+ *    ring_buffer_unlock_commit(buffer, event);
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event);
+
+/*
  * size is in bytes for each per CPU buffer.
  */
 struct ring_buffer *
-ring_buffer_alloc(unsigned long size, unsigned flags);
+__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key);
+
+/*
+ * Because the ring buffer is generic, if other users of the ring buffer get
+ * traced by ftrace, it can produce lockdep warnings. We need to keep each
+ * ring buffer's lock class separate.
+ */
+#define ring_buffer_alloc(size, flags)			\
+({							\
+	static struct lock_class_key __key;		\
+	__ring_buffer_alloc((size), (flags), &__key);	\
+})
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
@@ -122,6 +165,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
@@ -137,6 +182,11 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
 			  size_t len, int cpu, int full);
 
+struct trace_seq;
+
+int ring_buffer_print_entry_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_seq *s);
+
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bc9326dcdde..28c774ff3cc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -77,6 +77,7 @@ struct sched_param {
 #include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/rtmutex.h>
 
 #include <linux/time.h>
@@ -96,8 +97,8 @@ struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
 struct bio;
-struct bts_tracer;
 struct fs_struct;
+struct bts_context;
 struct perf_counter_context;
 
 /*
@@ -117,6 +118,7 @@ struct perf_counter_context;
  *    11 bit fractions.
  */
 extern unsigned long avenrun[];		/* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
@@ -136,8 +138,8 @@ DECLARE_PER_CPU(unsigned long, process_counts);
 extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
-extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
 extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
@@ -844,7 +846,17 @@ struct sched_group {
 	 */
 	u32 reciprocal_cpu_power;
 
-	unsigned long cpumask[];
+	/*
+	 * The CPUs this group covers.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_group' in kernel/sched.c)
+	 */
+	unsigned long cpumask[0];
 };
 
 static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
@@ -930,8 +942,17 @@ struct sched_domain {
 	char *name;
 #endif
 
-	/* span of all CPUs in this domain */
-	unsigned long span[];
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
+	 */
+	unsigned long span[0];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
@@ -1216,18 +1237,11 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-#ifdef CONFIG_X86_PTRACE_BTS
 	/*
 	 * This is the tracer handle for the ptrace BTS extension.
 	 * This field actually belongs to the ptracer task.
 	 */
-	struct bts_tracer *bts;
-	/*
-	 * The buffer to hold the BTS data.
-	 */
-	void *bts_buffer;
-	size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+	struct bts_context *bts;
 
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
@@ -1440,7 +1454,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
-#endif
+	/* bitmask of trace recursion */
+	unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2013,8 +2029,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
@@ -2022,7 +2040,8 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
 #define for_each_process(p) \
 	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
@@ -2061,8 +2080,8 @@ int same_thread_group(struct task_struct *p1, struct task_struct *p2)
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
 {
-	return list_entry(rcu_dereference(p->thread_group.next),
-			  struct task_struct, thread_group);
+	return list_entry_rcu(p->thread_group.next,
+			      struct task_struct, thread_group);
 }
 
 static inline int thread_group_empty(struct task_struct *p)
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 5ac9b0bcaf9..713f841ecaa 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,7 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 /* Size description struct for general caches. */
 struct cache_sizes {
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 5046f90c117..be5d40c43bd 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,7 +10,7 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 938234c4a99..d4841ed8215 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -60,6 +60,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 #define __raw_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched.c and kernel_lock.c: */
 # define __raw_spin_lock(lock)		do { (void)(lock); } while (0)
+# define __raw_spin_lock_flags(lock, flags)	do { (void)(lock); } while (0)
 # define __raw_spin_unlock(lock)	do { (void)(lock); } while (0)
 # define __raw_spin_trylock(lock)	({ (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ac9ff54f7cb..cb1a6631b8f 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -29,7 +29,8 @@ extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
 
 extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
 				      phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address);
+extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
+				       dma_addr_t address);
 
 extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
 
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e6b820f8b56..a8cc4e13434 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -21,13 +21,14 @@ struct restart_block {
 		struct {
 			unsigned long arg0, arg1, arg2, arg3;
 		};
-		/* For futex_wait */
+		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
+			u32 *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
new file mode 100644
index 00000000000..c68bccba207
--- /dev/null
+++ b/include/linux/trace_seq.h
@@ -0,0 +1,92 @@
+#ifndef _LINUX_TRACE_SEQ_H
+#define _LINUX_TRACE_SEQ_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE.
+ */
+
+struct trace_seq {
+	unsigned char		buffer[PAGE_SIZE];
+	unsigned int		len;
+	unsigned int		readpos;
+};
+
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+}
+
+/*
+ * Currently only defined when tracing is enabled.
+ */
+#ifdef CONFIG_TRACING
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+extern int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+
+#else /* CONFIG_TRACING */
+static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	return 0;
+}
+static inline int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+	return 0;
+}
+
+static inline void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+}
+static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt)
+{
+	return 0;
+}
+static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	return 0;
+}
+static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	return 0;
+}
+static inline int
+trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+	return 0;
+}
+static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				       size_t len)
+{
+	return 0;
+}
+static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+	return NULL;
+}
+static inline int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+	return 0;
+}
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_SEQ_H */
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index c7aa154f4bf..eb96603d92d 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -259,14 +259,12 @@ static inline void tracehook_finish_clone(struct task_struct *child,
 
 /**
  * tracehook_report_clone - in parent, new child is about to start running
- * @trace:		return value from tracehook_prepare_clone()
  * @regs:		parent's user register state
  * @clone_flags:	flags from parent's system call
  * @pid:		new child's PID in the parent's namespace
  * @child:		new child task
  *
- * Called after a child is set up, but before it has been started
- * running.  @trace is the value returned by tracehook_prepare_clone().
+ * Called after a child is set up, but before it has been started running.
  * This is not a good place to block, because the child has not started
  * yet.  Suspend the child here if desired, and then block in
  * tracehook_report_clone_complete().  This must prevent the child from
@@ -276,13 +274,14 @@ static inline void tracehook_finish_clone(struct task_struct *child,
  *
  * Called with no locks held, but the child cannot run until this returns.
  */
-static inline void tracehook_report_clone(int trace, struct pt_regs *regs,
+static inline void tracehook_report_clone(struct pt_regs *regs,
 					  unsigned long clone_flags,
 					  pid_t pid, struct task_struct *child)
 {
-	if (unlikely(trace) || unlikely(clone_flags & CLONE_PTRACE)) {
+	if (unlikely(task_ptrace(child))) {
 		/*
-		 * The child starts up with an immediate SIGSTOP.
+		 * It doesn't matter who attached/attaching to this
+		 * task, the pending SIGSTOP is right in any case.
 		 */
 		sigaddset(&child->pending.signal, SIGSTOP);
 		set_tsk_thread_flag(child, TIF_SIGPENDING);
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index d35a7ee7611..14df7e635d4 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -31,6 +31,8 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
+#ifndef DECLARE_TRACE
+
 #define TP_PROTO(args...)	args
 #define TP_ARGS(args...)		args
 
@@ -114,6 +116,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)
 { }
 #endif /* CONFIG_TRACEPOINTS */
+#endif /* DECLARE_TRACE */
 
 /*
  * Connect a probe to a tracepoint.
@@ -154,10 +157,8 @@ static inline void tracepoint_synchronize_unregister(void)
 }
 
 #define PARAMS(args...) args
-#define TRACE_FORMAT(name, proto, args, fmt)		\
-	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-
 
+#ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
  *
@@ -262,5 +263,6 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
 
 #endif
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bc024632f36..6788e1a4d4c 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,8 +132,6 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
 	list_del(&old->task_list);
 }
 
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
diff --git a/include/trace/block.h b/include/trace/block.h
deleted file mode 100644
index 25b7068b819..00000000000
--- a/include/trace/block.h
+++ /dev/null
@@ -1,76 +0,0 @@
-#ifndef _TRACE_BLOCK_H
-#define _TRACE_BLOCK_H
-
-#include <linux/blkdev.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(block_rq_abort,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_insert,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_issue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_requeue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_complete,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_bio_bounce,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_complete,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_backmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_frontmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_queue,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_getrq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_sleeprq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_plug,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_timer,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_io,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_split,
-	TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu),
-	      TP_ARGS(q, bio, pdu));
-
-DECLARE_TRACE(block_remap,
-	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
-		 sector_t from, sector_t to),
-	      TP_ARGS(q, bio, dev, from, to));
-
-#endif
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
new file mode 100644
index 00000000000..f7a7ae1e8f9
--- /dev/null
+++ b/include/trace/define_trace.h
@@ -0,0 +1,75 @@
+/*
+ * Trace files that want to automate creationg of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ *     This macro may be defined to tell define_trace.h what file to include.
+ *     Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ *     then this macro can define the path to use. Note, the path is relative to
+ *     define_trace.h, not the file including it. Full path names for out of tree
+ *     modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	DEFINE_TRACE(name)
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)	\
+	DEFINE_TRACE(name)
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#ifdef CONFIG_EVENT_TRACING
+#include <trace/ftrace.h>
+#endif
+
+#undef TRACE_HEADER_MULTI_READ
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
new file mode 100644
index 00000000000..53effd496a5
--- /dev/null
+++ b/include/trace/events/block.h
@@ -0,0 +1,498 @@
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+TRACE_EVENT(block_rq_abort,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_insert,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,         comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->bytes     = blk_pc_request(rq) ? rq->data_len : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_issue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,		comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->bytes     = blk_pc_request(rq) ? rq->data_len : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_requeue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors	   = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_complete,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+TRACE_EVENT(block_bio_bounce,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_complete,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned,	nr_sector	)
+		__field( int,		error		)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->error)
+);
+
+TRACE_EVENT(block_bio_backmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_frontmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_queue,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_getrq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+        ),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			      bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_sleeprq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			    bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_plug,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s]", __entry->comm)
+);
+
+TRACE_EVENT(block_unplug_timer,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_unplug_io,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_split,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio,
+		 unsigned int new_sector),
+
+	TP_ARGS(q, bio, new_sector),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev				)
+		__field( sector_t,	sector				)
+		__field( sector_t,	new_sector			)
+		__array( char,		rwbs,		6		)
+		__array( char,		comm,		TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->new_sector	= new_sector;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu / %llu [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  (unsigned long long)__entry->new_sector,
+		  __entry->comm)
+);
+
+TRACE_EVENT(block_remap,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
+		 sector_t from),
+
+	TP_ARGS(q, bio, dev, from),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sector	)
+		__field( dev_t,		old_dev		)
+		__field( sector_t,	old_sector	)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector,
+		  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+		  (unsigned long long)__entry->old_sector)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
new file mode 100644
index 00000000000..b0c7ede55eb
--- /dev/null
+++ b/include/trace/events/irq.h
@@ -0,0 +1,145 @@
+#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/interrupt.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+#define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
+#define show_softirq_name(val)			\
+	__print_symbolic(val,			\
+			 softirq_name(HI),	\
+			 softirq_name(TIMER),	\
+			 softirq_name(NET_TX),	\
+			 softirq_name(NET_RX),	\
+			 softirq_name(BLOCK),	\
+			 softirq_name(TASKLET),	\
+			 softirq_name(SCHED),	\
+			 softirq_name(HRTIMER),	\
+			 softirq_name(RCU))
+
+/**
+ * irq_handler_entry - called immediately before the irq action handler
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ *
+ * The struct irqaction pointed to by @action contains various
+ * information about the handler, including the device name,
+ * @action->name, and the device id, @action->dev_id. When used in
+ * conjunction with the irq_handler_exit tracepoint, we can figure
+ * out irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_entry,
+
+	TP_PROTO(int irq, struct irqaction *action),
+
+	TP_ARGS(irq, action),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq		)
+		__string(	name,	action->name	)
+	),
+
+	TP_fast_assign(
+		__entry->irq = irq;
+		__assign_str(name, action->name);
+	),
+
+	TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+);
+
+/**
+ * irq_handler_exit - called immediately after the irq action handler returns
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ * @ret: return value
+ *
+ * If the @ret value is set to IRQ_HANDLED, then we know that the corresponding
+ * @action->handler scuccessully handled this irq. Otherwise, the irq might be
+ * a shared irq line, or the irq was not handled successfully. Can be used in
+ * conjunction with the irq_handler_entry to understand irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_exit,
+
+	TP_PROTO(int irq, struct irqaction *action, int ret),
+
+	TP_ARGS(irq, action, ret),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq	)
+		__field(	int,	ret	)
+	),
+
+	TP_fast_assign(
+		__entry->irq	= irq;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("irq=%d return=%s",
+		  __entry->irq, __entry->ret ? "handled" : "unhandled")
+);
+
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+TRACE_EVENT(softirq_entry,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+/**
+ * softirq_exit - called immediately after the softirq handler returns
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the struct softirq_action
+ * that has handled the softirq. By subtracting the @vec pointer from
+ * the @h pointer, we can determine the softirq number. Also, when used in
+ * combination with the softirq_entry tracepoint we can determine the softirq
+ * latency.
+ */
+TRACE_EVENT(softirq_exit,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
new file mode 100644
index 00000000000..9baba50d651
--- /dev/null
+++ b/include/trace/events/kmem.h
@@ -0,0 +1,231 @@
+#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KMEM_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ *  GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+#define show_gfp_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"}, \
+	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
+	{(unsigned long)GFP_USER,		"GFP_USER"},		\
+	{(unsigned long)GFP_TEMPORARY,		"GFP_TEMPORARY"},	\
+	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
+	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
+	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
+	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
+	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
+	{(unsigned long)__GFP_WAIT,		"GFP_WAIT"},		\
+	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
+	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
+	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
+	{(unsigned long)__GFP_REPEAT,		"GFP_REPEAT"},		\
+	{(unsigned long)__GFP_NOFAIL,		"GFP_NOFAIL"},		\
+	{(unsigned long)__GFP_NORETRY,		"GFP_NORETRY"},		\
+	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
+	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
+	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
+	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
+	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"}		\
+	) : "GFP_NOWAIT"
+
+TRACE_EVENT(kmalloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmem_cache_alloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmalloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kmem_cache_alloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kfree,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+
+TRACE_EVENT(kmem_cache_free,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+#endif /* _TRACE_KMEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h
new file mode 100644
index 00000000000..0e956c9dfd7
--- /dev/null
+++ b/include/trace/events/lockdep.h
@@ -0,0 +1,96 @@
+#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_EVENT(lock_acquire,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+
+	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, flags)
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+TRACE_EVENT(lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+
+	TP_ARGS(lock, nested, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_EVENT(lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(lock_acquired,
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+	TP_ARGS(lock, ip, waittime),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+		__field(unsigned long, wait_usec)
+		__field(unsigned long, wait_nsec_rem)
+	),
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+		__entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+		__entry->wait_usec = (unsigned long) waittime;
+	),
+	TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
+				       __entry->wait_nsec_rem)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCKDEP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/sched_event_types.h b/include/trace/events/sched.h
index 63547dc1125..24ab5bcff7b 100644
--- a/include/trace/sched_event_types.h
+++ b/include/trace/events/sched.h
@@ -1,9 +1,8 @@
+#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_H
 
-/* use <trace/sched.h> instead */
-#ifndef TRACE_EVENT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM sched
@@ -157,6 +156,7 @@ TRACE_EVENT(sched_switch,
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	prev_pid			)
 		__field(	int,	prev_prio			)
+		__field(	long,	prev_state			)
 		__array(	char,	next_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	next_pid			)
 		__field(	int,	next_prio			)
@@ -166,13 +166,19 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
+		__entry->prev_state	= prev->state;
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+		__entry->prev_state ?
+		  __print_flags(__entry->prev_state, "|",
+				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
+				{ 128, "W" }) : "R",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
@@ -181,9 +187,9 @@ TRACE_EVENT(sched_switch,
  */
 TRACE_EVENT(sched_migrate_task,
 
-	TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
+	TP_PROTO(struct task_struct *p, int dest_cpu),
 
-	TP_ARGS(p, orig_cpu, dest_cpu),
+	TP_ARGS(p, dest_cpu),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -197,7 +203,7 @@ TRACE_EVENT(sched_migrate_task,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->orig_cpu	= orig_cpu;
+		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
 
@@ -334,4 +340,7 @@ TRACE_EVENT(sched_signal_send,
 		  __entry->sig, __entry->comm, __entry->pid)
 );
 
-#undef TRACE_SYSTEM
+#endif /* _TRACE_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
new file mode 100644
index 00000000000..1e8fabb57c0
--- /dev/null
+++ b/include/trace/events/skb.h
@@ -0,0 +1,40 @@
+#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SKB_H
+
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
+/*
+ * Tracepoint for free an sk_buff:
+ */
+TRACE_EVENT(kfree_skb,
+
+	TP_PROTO(struct sk_buff *skb, void *location),
+
+	TP_ARGS(skb, location),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned short,	protocol	)
+		__field(	void *,		location	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		if (skb) {
+			__entry->protocol = ntohs(skb->protocol);
+		}
+		__entry->location = location;
+	),
+
+	TP_printk("skbaddr=%p protocol=%u location=%p",
+		__entry->skbaddr, __entry->protocol, __entry->location)
+);
+
+#endif /* _TRACE_SKB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
new file mode 100644
index 00000000000..035f1bff288
--- /dev/null
+++ b/include/trace/events/workqueue.h
@@ -0,0 +1,100 @@
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+TRACE_EVENT(workqueue_insertion,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+TRACE_EVENT(workqueue_execution,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+/* Trace the creation of one workqueue thread on a cpu */
+TRACE_EVENT(workqueue_creation,
+
+	TP_PROTO(struct task_struct *wq_thread, int cpu),
+
+	TP_ARGS(wq_thread, cpu),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+		__field(int,	cpu)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->cpu		= cpu;
+	),
+
+	TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
+		__entry->thread_pid, __entry->cpu)
+);
+
+TRACE_EVENT(workqueue_destruction,
+
+	TP_PROTO(struct task_struct *wq_thread),
+
+	TP_ARGS(wq_thread),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+	),
+
+	TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+);
+
+#endif /* _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
new file mode 100644
index 00000000000..1867553c61e
--- /dev/null
+++ b/include/trace/ftrace.h
@@ -0,0 +1,591 @@
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ *	struct trace_entry		ent;
+ *	<type>				<item>;
+ *	<type2>				<item2>[<len>];
+ *	[...]
+ * };
+ *
+ * The <type> <item> is created by the __field(type, item) macro or
+ * the __array(type2, item2, len) macro.
+ * We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#include <linux/ftrace_event.h>
+
+#undef __field
+#define __field(type, item)		type	item;
+
+#undef __array
+#define __array(type, item, len)	type	item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	struct ftrace_raw_##name {				\
+		struct trace_entry	ent;			\
+		tstruct						\
+		char			__data[0];		\
+	};							\
+	static struct ftrace_event_call event_##name
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+
+/*
+ * Stage 2 of the trace events.
+ *
+ * Include the following:
+ *
+ * struct ftrace_data_offsets_<call> {
+ *	int				<item1>;
+ *	int				<item2>;
+ *	[...]
+ * };
+ *
+ * The __dynamic_array() macro will create each int <item>, this is
+ * to keep the offset of each array from the beginning of the event.
+ */
+
+#undef __field
+#define __field(type, item);
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)	int item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+	struct ftrace_data_offsets_##call {				\
+		tstruct;						\
+	};
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ *	struct ftrace_raw_##call field;
+ *	int ret;
+ *
+ *	ret = trace_seq_printf(s, #type " " #item ";"
+ *			       " offset:%u; size:%u;\n",
+ *			       offsetof(struct ftrace_raw_##call, item),
+ *			       sizeof(field.type));
+ *
+ * }
+ */
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef __field
+#define __field(type, item)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __array
+#define __array(type, item, len)						\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t"	       \
+			       "offset:%u;\tsize:%u;\n",		       \
+			       (unsigned int)offsetof(typeof(field),	       \
+					__data_loc_##item),		       \
+			       (unsigned int)sizeof(field.__data_loc_##item)); \
+	if (!ret)							       \
+		return 0;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+static int								\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct ftrace_raw_##call field __attribute__((unused));		\
+	int ret = 0;							\
+									\
+	tstruct;							\
+									\
+	trace_seq_printf(s, "\nprint fmt: " print);			\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ *	struct trace_seq *s = &iter->seq;
+ *	struct ftrace_raw_<call> *field; <-- defined in stage 1
+ *	struct trace_entry *entry;
+ *	struct trace_seq *p;
+ *	int ret;
+ *
+ *	entry = iter->ent;
+ *
+ *	if (entry->type != event_<call>.id) {
+ *		WARN_ON_ONCE(1);
+ *		return TRACE_TYPE_UNHANDLED;
+ *	}
+ *
+ *	field = (typeof(field))entry;
+ *
+ *	p = get_cpu_var(ftrace_event_seq);
+ *	trace_seq_init(p);
+ *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	put_cpu();
+ *	if (!ret)
+ *		return TRACE_TYPE_PARTIAL_LINE;
+ *
+ *	return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * This is the method used to print the raw event to the trace
+ * output format. Note, this is not needed if the data is read
+ * in binary.
+ */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + __entry->__data_loc_##field)
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags flags[] =		\
+			{ flag_array, { -1, NULL }};			\
+		ftrace_print_flags_seq(p, delim, flag, flags);		\
+	})
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags symbols[] =	\
+			{ symbol_array, { -1, NULL }};			\
+		ftrace_print_symbols_seq(p, value, symbols);		\
+	})
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+enum print_line_t							\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+{									\
+	struct trace_seq *s = &iter->seq;				\
+	struct ftrace_raw_##call *field;				\
+	struct trace_entry *entry;					\
+	struct trace_seq *p;						\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_##call.id) {				\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	p = &get_cpu_var(ftrace_event_seq);				\
+	trace_seq_init(p);						\
+	ret = trace_seq_printf(s, #call ": " print);			\
+	put_cpu();							\
+	if (!ret)							\
+		return TRACE_TYPE_PARTIAL_LINE;				\
+									\
+	return TRACE_TYPE_HANDLED;					\
+}
+	
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed_type(type));	\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0);		\
+	if (ret)							\
+		return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
+				offsetof(typeof(field), __data_loc_##item),    \
+				 sizeof(field.__data_loc_##item), 0);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_raw_##call field;					\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	int ret;							\
+									\
+	__common_field(int, type, 1);					\
+	__common_field(unsigned char, flags, 0);			\
+	__common_field(unsigned char, preempt_count, 0);		\
+	__common_field(int, pid, 1);					\
+	__common_field(int, tgid, 1);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data);	\
+	__data_size += (len) * sizeof(type);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static inline int ftrace_get_offsets_##call(				\
+	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
+{									\
+	int __data_size = 0;						\
+	struct ftrace_raw_##call __maybe_unused *entry;			\
+									\
+	tstruct;							\
+									\
+	return __data_size;						\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to  <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ *	struct ring_buffer_event *event;
+ *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *	unsigned long irq_flags;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *				  sizeof(struct ftrace_raw_<call>),
+ *				  irq_flags, pc);
+ *	if (!event)
+ *		return;
+ *	entry	= ring_buffer_event_data(event);
+ *
+ *	<assign>;  <-- Here we assign the entries by the __field and
+ *			__array macros.
+ *
+ *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_raw_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ *	.trace			= ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ *	int id;
+ *
+ *	id = register_ftrace_event(&ftrace_event_type_<call>);
+ *	if (!id)
+ *		return -ENODEV;
+ *	event_<call>.id = id;
+ *	return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ *	.name			= "<call>",
+ *	.system			= "<system>",
+ *	.raw_init		= ftrace_raw_init_event_<call>,
+ *	.regfunc		= ftrace_reg_event_<call>,
+ *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.show_format		= ftrace_format_<call>,
+ * }
+ *
+ */
+
+#undef TP_FMT
+#define TP_FMT(fmt, args...)	fmt "\n", ##args
+
+#ifdef CONFIG_EVENT_PROFILE
+#define _TRACE_PROFILE(call, proto, args)				\
+static void ftrace_profile_##call(proto)				\
+{									\
+	extern void perf_tpcounter_event(int);				\
+	perf_tpcounter_event(event_##call.id);				\
+}									\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&event_call->profile_count))		\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{									\
+	if (atomic_add_negative(-1, &event_call->profile_count))	\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#define _TRACE_PROFILE_INIT(call)					\
+	.profile_count = ATOMIC_INIT(-1),				\
+	.profile_enable = ftrace_profile_enable_##call,			\
+	.profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)       	\
+
+#undef __assign_str
+#define __assign_str(dst, src)						\
+	strcpy(__get_str(dst), src);
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
+									\
+static struct ftrace_event_call event_##call;				\
+									\
+static void ftrace_raw_event_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct ring_buffer_event *event;				\
+	struct ftrace_raw_##call *entry;				\
+	unsigned long irq_flags;					\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+									\
+	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+				 sizeof(*entry) + __data_size,		\
+				 irq_flags, pc);			\
+	if (!event)							\
+		return;							\
+	entry	= ring_buffer_event_data(event);			\
+									\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	if (!filter_current_check_discard(event_call, entry, event))	\
+		trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+}									\
+									\
+static int ftrace_raw_reg_event_##call(void)				\
+{									\
+	int ret;							\
+									\
+	ret = register_trace_##call(ftrace_raw_event_##call);		\
+	if (ret)							\
+		pr_info("event trace: Could not activate trace point "	\
+			"probe to " #call "\n");			\
+	return ret;							\
+}									\
+									\
+static void ftrace_raw_unreg_event_##call(void)				\
+{									\
+	unregister_trace_##call(ftrace_raw_event_##call);		\
+}									\
+									\
+static struct trace_event ftrace_event_type_##call = {			\
+	.trace			= ftrace_raw_output_##call,		\
+};									\
+									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	int id;								\
+									\
+	id = register_ftrace_event(&ftrace_event_type_##call);		\
+	if (!id)							\
+		return -ENODEV;						\
+	event_##call.id = id;						\
+	INIT_LIST_HEAD(&event_##call.fields);				\
+	init_preds(&event_##call);					\
+	return 0;							\
+}									\
+									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.event			= &ftrace_event_type_##call,		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.regfunc		= ftrace_raw_reg_event_##call,		\
+	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+	_TRACE_PROFILE_INIT(call)					\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
diff --git a/include/trace/irq.h b/include/trace/irq.h
deleted file mode 100644
index ff5d4495dc3..00000000000
--- a/include/trace/irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_IRQ_H
-#define _TRACE_IRQ_H
-
-#include <linux/interrupt.h>
-#include <linux/tracepoint.h>
-
-#include <trace/irq_event_types.h>
-
-#endif
diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
deleted file mode 100644
index 85964ebd47e..00000000000
--- a/include/trace/irq_event_types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-
-/* use <trace/irq.h> instead */
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
-/*
- * Tracepoint for entry of interrupt handler:
- */
-TRACE_FORMAT(irq_handler_entry,
-	TP_PROTO(int irq, struct irqaction *action),
-	TP_ARGS(irq, action),
-	TP_FMT("irq=%d handler=%s", irq, action->name)
-	);
-
-/*
- * Tracepoint for return of an interrupt handler:
- */
-TRACE_EVENT(irq_handler_exit,
-
-	TP_PROTO(int irq, struct irqaction *action, int ret),
-
-	TP_ARGS(irq, action, ret),
-
-	TP_STRUCT__entry(
-		__field(	int,	irq	)
-		__field(	int,	ret	)
-	),
-
-	TP_fast_assign(
-		__entry->irq	= irq;
-		__entry->ret	= ret;
-	),
-
-	TP_printk("irq=%d return=%s",
-		  __entry->irq, __entry->ret ? "handled" : "unhandled")
-);
-
-TRACE_FORMAT(softirq_entry,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-TRACE_FORMAT(softirq_exit,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h
deleted file mode 100644
index 28ee69f9cd4..00000000000
--- a/include/trace/kmemtrace.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <linux/tracepoint.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-DECLARE_TRACE(kmalloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmem_cache_alloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmalloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kmem_cache_alloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kfree,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-DECLARE_TRACE(kmem_cache_free,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h
deleted file mode 100644
index 5ca67df87f2..00000000000
--- a/include/trace/lockdep.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_LOCKDEP_H
-#define _TRACE_LOCKDEP_H
-
-#include <linux/lockdep.h>
-#include <linux/tracepoint.h>
-
-#include <trace/lockdep_event_types.h>
-
-#endif
diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h
deleted file mode 100644
index adccfcd2ec8..00000000000
--- a/include/trace/lockdep_event_types.h
+++ /dev/null
@@ -1,44 +0,0 @@
-
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lock
-
-#ifdef CONFIG_LOCKDEP
-
-TRACE_FORMAT(lock_acquire,
-	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
-		int trylock, int read, int check,
-		struct lockdep_map *next_lock, unsigned long ip),
-	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
-	TP_FMT("%s%s%s", trylock ? "try " : "",
-		read ? "read " : "", lock->name)
-	);
-
-TRACE_FORMAT(lock_release,
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
-	TP_ARGS(lock, nested, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_FORMAT(lock_contended,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-TRACE_FORMAT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#endif
-#endif
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/sched.h b/include/trace/sched.h
deleted file mode 100644
index 4e372a1a29b..00000000000
--- a/include/trace/sched.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_SCHED_H
-#define _TRACE_SCHED_H
-
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-#include <trace/sched_event_types.h>
-
-#endif
diff --git a/include/trace/skb.h b/include/trace/skb.h
deleted file mode 100644
index b66206d9be7..00000000000
--- a/include/trace/skb.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _TRACE_SKB_H_
-#define _TRACE_SKB_H_
-
-#include <linux/skbuff.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(kfree_skb,
-	TP_PROTO(struct sk_buff *skb, void *location),
-	TP_ARGS(skb, location));
-
-#endif
diff --git a/include/trace/trace_event_types.h b/include/trace/trace_event_types.h
deleted file mode 100644
index df56f5694be..00000000000
--- a/include/trace/trace_event_types.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>_event_types.h here */
-
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
-#include <trace/lockdep_event_types.h>
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
deleted file mode 100644
index fd13750ca4b..00000000000
--- a/include/trace/trace_events.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>.h here */
-
-#include <trace/sched.h>
-#include <trace/irq.h>
-#include <trace/lockdep.h>
diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h
deleted file mode 100644
index 7626523deeb..00000000000
--- a/include/trace/workqueue.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __TRACE_WORKQUEUE_H
-#define __TRACE_WORKQUEUE_H
-
-#include <linux/tracepoint.h>
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-
-DECLARE_TRACE(workqueue_insertion,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-DECLARE_TRACE(workqueue_execution,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-/* Trace the creation of one workqueue thread on a cpu */
-DECLARE_TRACE(workqueue_creation,
-	   TP_PROTO(struct task_struct *wq_thread, int cpu),
-	   TP_ARGS(wq_thread, cpu));
-
-DECLARE_TRACE(workqueue_destruction,
-	   TP_PROTO(struct task_struct *wq_thread),
-	   TP_ARGS(wq_thread));
-
-#endif /* __TRACE_WORKQUEUE_H */
diff --git a/include/xen/Kbuild b/include/xen/Kbuild
new file mode 100644
index 00000000000..4e65c16a445
--- /dev/null
+++ b/include/xen/Kbuild
@@ -0,0 +1 @@
+header-y += evtchn.h
diff --git a/include/xen/events.h b/include/xen/events.h
index 0d5f1adc036..e68d59a90ca 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -53,4 +53,7 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
 #endif	/* _XEN_EVENTS_H */
diff --git a/include/xen/evtchn.h b/include/xen/evtchn.h
new file mode 100644
index 00000000000..14e833ee4e0
--- /dev/null
+++ b/include/xen/evtchn.h
@@ -0,0 +1,88 @@
+/******************************************************************************
+ * evtchn.h
+ *
+ * Interface to /dev/xen/evtchn.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_EVTCHN_H__
+#define __LINUX_PUBLIC_EVTCHN_H__
+
+/*
+ * Bind a fresh port to VIRQ @virq.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_VIRQ				\
+	_IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq))
+struct ioctl_evtchn_bind_virq {
+	unsigned int virq;
+};
+
+/*
+ * Bind a fresh port to remote <@remote_domain, @remote_port>.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_INTERDOMAIN			\
+	_IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain))
+struct ioctl_evtchn_bind_interdomain {
+	unsigned int remote_domain, remote_port;
+};
+
+/*
+ * Allocate a fresh port for binding to @remote_domain.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_UNBOUND_PORT			\
+	_IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port))
+struct ioctl_evtchn_bind_unbound_port {
+	unsigned int remote_domain;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_UNBIND				\
+	_IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind))
+struct ioctl_evtchn_unbind {
+	unsigned int port;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_NOTIFY				\
+	_IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify))
+struct ioctl_evtchn_notify {
+	unsigned int port;
+};
+
+/* Clear and reinitialise the event buffer. Clear error condition. */
+#define IOCTL_EVTCHN_RESET				\
+	_IOC(_IOC_NONE, 'E', 5, 0)
+
+#endif /* __LINUX_PUBLIC_EVTCHN_H__ */
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 453235e923f..e8b6519d47e 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -57,4 +57,7 @@ struct xen_feature_info {
 /* Declares the features reported by XENVER_get_features. */
 #include "features.h"
 
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
 #endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index f87f9614844..b9763badbd7 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -91,8 +91,7 @@ struct xenbus_driver {
 	void (*otherend_changed)(struct xenbus_device *dev,
 				 enum xenbus_state backend_state);
 	int (*remove)(struct xenbus_device *dev);
-	int (*suspend)(struct xenbus_device *dev);
-	int (*suspend_cancel)(struct xenbus_device *dev);
+	int (*suspend)(struct xenbus_device *dev, pm_message_t state);
 	int (*resume)(struct xenbus_device *dev);
 	int (*uevent)(struct xenbus_device *, char **, int, char *, int);
 	struct device_driver driver;
diff --git a/init/Kconfig b/init/Kconfig
index aef16f9b3d2..9b68fee8d79 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -308,7 +308,7 @@ menu "RCU Subsystem"
 
 choice
 	prompt "RCU Implementation"
-	default CLASSIC_RCU
+	default TREE_RCU
 
 config CLASSIC_RCU
 	bool "Classic RCU"
diff --git a/init/main.c b/init/main.c
index d721dad05dd..bb7dc57eee3 100644
--- a/init/main.c
+++ b/init/main.c
@@ -64,6 +64,7 @@
 #include <linux/idr.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/kmemtrace.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -71,7 +72,6 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
-#include <trace/kmemtrace.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/smp.h>
diff --git a/ipc/sem.c b/ipc/sem.c
index 16a2189e96f..87c2b641fd7 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1290,8 +1290,8 @@ void exit_sem(struct task_struct *tsk)
 		int i;
 
 		rcu_read_lock();
-		un = list_entry(rcu_dereference(ulp->list_proc.next),
-					struct sem_undo, list_proc);
+		un = list_entry_rcu(ulp->list_proc.next,
+				    struct sem_undo, list_proc);
 		if (&un->list_proc == &ulp->list_proc)
 			semid = -1;
 		 else
diff --git a/ipc/shm.c b/ipc/shm.c
index faa46da99eb..42597160048 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -969,10 +969,13 @@ SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
 SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma, *next;
+	struct vm_area_struct *vma;
 	unsigned long addr = (unsigned long)shmaddr;
-	loff_t size = 0;
 	int retval = -EINVAL;
+#ifdef CONFIG_MMU
+	loff_t size = 0;
+	struct vm_area_struct *next;
+#endif
 
 	if (addr & ~PAGE_MASK)
 		return retval;
diff --git a/kernel/Makefile b/kernel/Makefile
index e914ca992d7..90b53f6dc22 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -93,6 +93,7 @@ obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
 obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
diff --git a/kernel/async.c b/kernel/async.c
index 50540301ed0..27235f5de19 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -92,23 +92,18 @@ extern int initcall_debug;
 static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
-	async_cookie_t ret = next_cookie; /* begin with "infinity" value */
 
 	if (!list_empty(running)) {
 		entry = list_first_entry(running,
 			struct async_entry, list);
-		ret = entry->cookie;
+		return entry->cookie;
 	}
 
-	if (!list_empty(&async_pending)) {
-		list_for_each_entry(entry, &async_pending, list)
-			if (entry->running == running) {
-				ret = entry->cookie;
-				break;
-			}
-	}
+	list_for_each_entry(entry, &async_pending, list)
+		if (entry->running == running)
+			return entry->cookie;
 
-	return ret;
+	return next_cookie;	/* "infinity" value */
 }
 
 static async_cookie_t  lowest_in_progress(struct list_head *running)
diff --git a/kernel/exit.c b/kernel/exit.c
index 99ad4063ee4..49cdf6946f3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -49,7 +49,7 @@
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <linux/perf_counter.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -57,10 +57,6 @@
 #include <asm/mmu_context.h>
 #include "cred-internals.h"
 
-DEFINE_TRACE(sched_process_free);
-DEFINE_TRACE(sched_process_exit);
-DEFINE_TRACE(sched_process_wait);
-
 static void exit_mm(struct task_struct * tsk);
 
 static void __unhash_process(struct task_struct *p)
diff --git a/kernel/fork.c b/kernel/fork.c
index f4466ca37ec..4430eb1376f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,7 +61,6 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
-#include <trace/sched.h>
 #include <linux/magic.h>
 #include <linux/perf_counter.h>
 
@@ -72,6 +71,8 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/sched.h>
+
 /*
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
@@ -84,8 +85,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
-DEFINE_TRACE(sched_process_fork);
-
 int nr_processes(void)
 {
 	int cpu;
@@ -983,6 +982,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!p)
 		goto fork_out;
 
+	ftrace_graph_init_task(p);
+
 	rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -1090,8 +1091,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-	if (unlikely(current->ptrace))
-		ptrace_fork(p, clone_flags);
+
+	p->bts = NULL;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
@@ -1136,8 +1137,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	ftrace_graph_init_task(p);
-
 	p->pid = pid_nr(pid);
 	p->tgid = p->pid;
 	if (clone_flags & CLONE_THREAD)
@@ -1146,7 +1145,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (current->nsproxy != p->nsproxy) {
 		retval = ns_cgroup_clone(p, pid);
 		if (retval)
-			goto bad_fork_free_graph;
+			goto bad_fork_free_pid;
 	}
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1238,7 +1237,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_free_graph;
+		goto bad_fork_free_pid;
 	}
 
 	if (clone_flags & CLONE_THREAD) {
@@ -1273,8 +1272,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	cgroup_post_fork(p);
 	return p;
 
-bad_fork_free_graph:
-	ftrace_graph_exit_task(p);
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
@@ -1421,7 +1418,7 @@ long do_fork(unsigned long clone_flags,
 		}
 
 		audit_finish_fork(p);
-		tracehook_report_clone(trace, regs, clone_flags, nr, p);
+		tracehook_report_clone(regs, clone_flags, nr, p);
 
 		/*
 		 * We set PF_STARTING at creation in case tracing wants to
diff --git a/kernel/futex.c b/kernel/futex.c
index d546b2d53a6..80b5ce71659 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -19,6 +19,10 @@
  *  PRIVATE futexes by Eric Dumazet
  *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
  *
+ *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
+ *  Copyright (C) IBM Corporation, 2009
+ *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
+ *
  *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
  *  enough at me, Linus for the original (flawed) idea, Matthew
  *  Kirkwood for proof-of-concept implementation.
@@ -96,8 +100,8 @@ struct futex_pi_state {
  */
 struct futex_q {
 	struct plist_node list;
-	/* There can only be a single waiter */
-	wait_queue_head_t waiter;
+	/* Waiter reference */
+	struct task_struct *task;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -107,7 +111,9 @@ struct futex_q {
 
 	/* Optional priority inheritance state: */
 	struct futex_pi_state *pi_state;
-	struct task_struct *task;
+
+	/* rt_waiter storage for requeue_pi: */
+	struct rt_mutex_waiter *rt_waiter;
 
 	/* Bitset for the optional bitmasked wakeup */
 	u32 bitset;
@@ -278,6 +284,25 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
+/**
+ * futex_top_waiter() - Return the highest priority waiter on a futex
+ * @hb:     the hash bucket the futex_q's reside in
+ * @key:    the futex key (to distinguish it from other futex futex_q's)
+ *
+ * Must be called with the hb lock held.
+ */
+static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
+					union futex_key *key)
+{
+	struct futex_q *this;
+
+	plist_for_each_entry(this, &hb->chain, list) {
+		if (match_futex(&this->key, key))
+			return this;
+	}
+	return NULL;
+}
+
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	u32 curval;
@@ -539,28 +564,160 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+/**
+ * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * @uaddr:		the pi futex user address
+ * @hb:			the pi futex hash bucket
+ * @key:		the futex key associated with uaddr and hb
+ * @ps:			the pi_state pointer where we store the result of the
+ *			lookup
+ * @task:		the task to perform the atomic lock work for.  This will
+ *			be "current" except in the case of requeue pi.
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Returns:
+ *  0 - ready to wait
+ *  1 - acquired the lock
+ * <0 - error
+ *
+ * The hb->lock and futex_key refs shall be held by the caller.
+ */
+static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+				union futex_key *key,
+				struct futex_pi_state **ps,
+				struct task_struct *task, int set_waiters)
+{
+	int lock_taken, ret, ownerdied = 0;
+	u32 uval, newval, curval;
+
+retry:
+	ret = lock_taken = 0;
+
+	/*
+	 * To avoid races, we attempt to take the lock here again
+	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
+	 * the locks. It will most likely not succeed.
+	 */
+	newval = task_pid_vnr(task);
+	if (set_waiters)
+		newval |= FUTEX_WAITERS;
+
+	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+
+	/*
+	 * Detect deadlocks.
+	 */
+	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+		return -EDEADLK;
+
+	/*
+	 * Surprise - we got the lock. Just return to userspace:
+	 */
+	if (unlikely(!curval))
+		return 1;
+
+	uval = curval;
+
+	/*
+	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
+	 * to wake at the next unlock.
+	 */
+	newval = curval | FUTEX_WAITERS;
+
+	/*
+	 * There are two cases, where a futex might have no owner (the
+	 * owner TID is 0): OWNER_DIED. We take over the futex in this
+	 * case. We also do an unconditional take over, when the owner
+	 * of the futex died.
+	 *
+	 * This is safe as we are protected by the hash bucket lock !
+	 */
+	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
+		/* Keep the OWNER_DIED bit */
+		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		ownerdied = 0;
+		lock_taken = 1;
+	}
+
+	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+	if (unlikely(curval != uval))
+		goto retry;
+
+	/*
+	 * We took the lock due to owner died take over.
+	 */
+	if (unlikely(lock_taken))
+		return 1;
+
+	/*
+	 * We dont have the lock. Look up the PI state (or create it if
+	 * we are the first waiter):
+	 */
+	ret = lookup_pi_state(uval, hb, key, ps);
+
+	if (unlikely(ret)) {
+		switch (ret) {
+		case -ESRCH:
+			/*
+			 * No owner found for this futex. Check if the
+			 * OWNER_DIED bit is set to figure out whether
+			 * this is a robust futex or not.
+			 */
+			if (get_futex_value_locked(&curval, uaddr))
+				return -EFAULT;
+
+			/*
+			 * We simply start over in case of a robust
+			 * futex. The code above will take the futex
+			 * and return happy.
+			 */
+			if (curval & FUTEX_OWNER_DIED) {
+				ownerdied = 1;
+				goto retry;
+			}
+		default:
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
  */
 static void wake_futex(struct futex_q *q)
 {
-	plist_del(&q->list, &q->list.plist);
+	struct task_struct *p = q->task;
+
 	/*
-	 * The lock in wake_up_all() is a crucial memory barrier after the
-	 * plist_del() and also before assigning to q->lock_ptr.
+	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
+	 * a non futex wake up happens on another CPU then the task
+	 * might exit and p would dereference a non existing task
+	 * struct. Prevent this by holding a reference on p across the
+	 * wake up.
 	 */
-	wake_up(&q->waiter);
+	get_task_struct(p);
+
+	plist_del(&q->list, &q->list.plist);
 	/*
-	 * The waiting task can free the futex_q as soon as this is written,
-	 * without taking any locks.  This must come last.
-	 *
-	 * A memory barrier is required here to prevent the following store to
-	 * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
-	 * end of wake_up() does not prevent this store from moving.
+	 * The waiting task can free the futex_q as soon as
+	 * q->lock_ptr = NULL is written, without taking any locks. A
+	 * memory barrier is required here to prevent the following
+	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
+
+	wake_up_state(p, TASK_NORMAL);
+	put_task_struct(p);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
@@ -689,7 +846,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key)) {
-			if (this->pi_state) {
+			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
 				break;
 			}
@@ -802,24 +959,185 @@ out:
 	return ret;
 }
 
-/*
- * Requeue all waiters hashed on one physical page to another
- * physical page.
+/**
+ * requeue_futex() - Requeue a futex_q from one hb to another
+ * @q:		the futex_q to requeue
+ * @hb1:	the source hash_bucket
+ * @hb2:	the target hash_bucket
+ * @key2:	the new key for the requeued futex_q
+ */
+static inline
+void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
+		   struct futex_hash_bucket *hb2, union futex_key *key2)
+{
+
+	/*
+	 * If key1 and key2 hash to the same bucket, no need to
+	 * requeue.
+	 */
+	if (likely(&hb1->chain != &hb2->chain)) {
+		plist_del(&q->list, &hb1->chain);
+		plist_add(&q->list, &hb2->chain);
+		q->lock_ptr = &hb2->lock;
+#ifdef CONFIG_DEBUG_PI_LIST
+		q->list.plist.lock = &hb2->lock;
+#endif
+	}
+	get_futex_key_refs(key2);
+	q->key = *key2;
+}
+
+/**
+ * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
+ * q:	the futex_q
+ * key:	the key of the requeue target futex
+ *
+ * During futex_requeue, with requeue_pi=1, it is possible to acquire the
+ * target futex if it is uncontended or via a lock steal.  Set the futex_q key
+ * to the requeue target futex so the waiter can detect the wakeup on the right
+ * futex, but remove it from the hb and NULL the rt_waiter so it can detect
+ * atomic lock acquisition.  Must be called with the q->lock_ptr held.
+ */
+static inline
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
+{
+	drop_futex_key_refs(&q->key);
+	get_futex_key_refs(key);
+	q->key = *key;
+
+	WARN_ON(plist_node_empty(&q->list));
+	plist_del(&q->list, &q->list.plist);
+
+	WARN_ON(!q->rt_waiter);
+	q->rt_waiter = NULL;
+
+	wake_up_state(q->task, TASK_NORMAL);
+}
+
+/**
+ * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
+ * @pifutex:		the user address of the to futex
+ * @hb1:		the from futex hash bucket, must be locked by the caller
+ * @hb2:		the to futex hash bucket, must be locked by the caller
+ * @key1:		the from futex key
+ * @key2:		the to futex key
+ * @ps:			address to store the pi_state pointer
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Try and get the lock on behalf of the top waiter if we can do it atomically.
+ * Wake the top waiter if we succeed.  If the caller specified set_waiters,
+ * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
+ * hb1 and hb2 must be held by the caller.
+ *
+ * Returns:
+ *  0 - failed to acquire the lock atomicly
+ *  1 - acquired the lock
+ * <0 - error
+ */
+static int futex_proxy_trylock_atomic(u32 __user *pifutex,
+				 struct futex_hash_bucket *hb1,
+				 struct futex_hash_bucket *hb2,
+				 union futex_key *key1, union futex_key *key2,
+				 struct futex_pi_state **ps, int set_waiters)
+{
+	struct futex_q *top_waiter = NULL;
+	u32 curval;
+	int ret;
+
+	if (get_futex_value_locked(&curval, pifutex))
+		return -EFAULT;
+
+	/*
+	 * Find the top_waiter and determine if there are additional waiters.
+	 * If the caller intends to requeue more than 1 waiter to pifutex,
+	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
+	 * as we have means to handle the possible fault.  If not, don't set
+	 * the bit unecessarily as it will force the subsequent unlock to enter
+	 * the kernel.
+	 */
+	top_waiter = futex_top_waiter(hb1, key1);
+
+	/* There are no waiters, nothing for us to do. */
+	if (!top_waiter)
+		return 0;
+
+	/*
+	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
+	 * the contended case or if set_waiters is 1.  The pi_state is returned
+	 * in ps in contended cases.
+	 */
+	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
+				   set_waiters);
+	if (ret == 1)
+		requeue_pi_wake_futex(top_waiter, key2);
+
+	return ret;
+}
+
+/**
+ * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
+ * uaddr1:	source futex user address
+ * uaddr2:	target futex user address
+ * nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
+ * nr_requeue:	number of waiters to requeue (0-INT_MAX)
+ * requeue_pi:	if we are attempting to requeue from a non-pi futex to a
+ * 		pi futex (pi to pi requeue is not supported)
+ *
+ * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
+ * uaddr2 atomically on behalf of the top waiter.
+ *
+ * Returns:
+ * >=0 - on success, the number of tasks requeued or woken
+ *  <0 - on error
  */
 static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
-			 int nr_wake, int nr_requeue, u32 *cmpval)
+			 int nr_wake, int nr_requeue, u32 *cmpval,
+			 int requeue_pi)
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+	int drop_count = 0, task_count = 0, ret;
+	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
-	int ret, drop_count = 0;
+	u32 curval2;
+
+	if (requeue_pi) {
+		/*
+		 * requeue_pi requires a pi_state, try to allocate it now
+		 * without any locks in case it fails.
+		 */
+		if (refill_pi_state_cache())
+			return -ENOMEM;
+		/*
+		 * requeue_pi must wake as many tasks as it can, up to nr_wake
+		 * + nr_requeue, since it acquires the rt_mutex prior to
+		 * returning to userspace, so as to not leave the rt_mutex with
+		 * waiters and no owner.  However, second and third wake-ups
+		 * cannot be predicted as they involve race conditions with the
+		 * first wake and a fault while looking up the pi_state.  Both
+		 * pthread_cond_signal() and pthread_cond_broadcast() should
+		 * use nr_wake=1.
+		 */
+		if (nr_wake != 1)
+			return -EINVAL;
+	}
 
 retry:
+	if (pi_state != NULL) {
+		/*
+		 * We will have to lookup the pi_state again, so free this one
+		 * to keep the accounting correct.
+		 */
+		free_pi_state(pi_state);
+		pi_state = NULL;
+	}
+
 	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_READ);
+	ret = get_futex_key(uaddr2, fshared, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -854,32 +1172,99 @@ retry_private:
 		}
 	}
 
+	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+		/*
+		 * Attempt to acquire uaddr2 and wake the top waiter. If we
+		 * intend to requeue waiters, force setting the FUTEX_WAITERS
+		 * bit.  We force this here where we are able to easily handle
+		 * faults rather in the requeue loop below.
+		 */
+		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+						 &key2, &pi_state, nr_requeue);
+
+		/*
+		 * At this point the top_waiter has either taken uaddr2 or is
+		 * waiting on it.  If the former, then the pi_state will not
+		 * exist yet, look it up one more time to ensure we have a
+		 * reference to it.
+		 */
+		if (ret == 1) {
+			WARN_ON(pi_state);
+			task_count++;
+			ret = get_futex_value_locked(&curval2, uaddr2);
+			if (!ret)
+				ret = lookup_pi_state(curval2, hb2, &key2,
+						      &pi_state);
+		}
+
+		switch (ret) {
+		case 0:
+			break;
+		case -EFAULT:
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			ret = get_user(curval2, uaddr2);
+			if (!ret)
+				goto retry;
+			goto out;
+		case -EAGAIN:
+			/* The owner was exiting, try again. */
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			cond_resched();
+			goto retry;
+		default:
+			goto out_unlock;
+		}
+	}
+
 	head1 = &hb1->chain;
 	plist_for_each_entry_safe(this, next, head1, list) {
-		if (!match_futex (&this->key, &key1))
+		if (task_count - nr_wake >= nr_requeue)
+			break;
+
+		if (!match_futex(&this->key, &key1))
 			continue;
-		if (++ret <= nr_wake) {
+
+		WARN_ON(!requeue_pi && this->rt_waiter);
+		WARN_ON(requeue_pi && !this->rt_waiter);
+
+		/*
+		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
+		 * lock, we already woke the top_waiter.  If not, it will be
+		 * woken by futex_unlock_pi().
+		 */
+		if (++task_count <= nr_wake && !requeue_pi) {
 			wake_futex(this);
-		} else {
-			/*
-			 * If key1 and key2 hash to the same bucket, no need to
-			 * requeue.
-			 */
-			if (likely(head1 != &hb2->chain)) {
-				plist_del(&this->list, &hb1->chain);
-				plist_add(&this->list, &hb2->chain);
-				this->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-				this->list.plist.lock = &hb2->lock;
-#endif
-			}
-			this->key = key2;
-			get_futex_key_refs(&key2);
-			drop_count++;
+			continue;
+		}
 
-			if (ret - nr_wake >= nr_requeue)
-				break;
+		/*
+		 * Requeue nr_requeue waiters and possibly one more in the case
+		 * of requeue_pi if we couldn't acquire the lock atomically.
+		 */
+		if (requeue_pi) {
+			/* Prepare the waiter to take the rt_mutex. */
+			atomic_inc(&pi_state->refcount);
+			this->pi_state = pi_state;
+			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+							this->rt_waiter,
+							this->task, 1);
+			if (ret == 1) {
+				/* We got the lock. */
+				requeue_pi_wake_futex(this, &key2);
+				continue;
+			} else if (ret) {
+				/* -EDEADLK */
+				this->pi_state = NULL;
+				free_pi_state(pi_state);
+				goto out_unlock;
+			}
 		}
+		requeue_futex(this, hb1, hb2, &key2);
+		drop_count++;
 	}
 
 out_unlock:
@@ -899,7 +1284,9 @@ out_put_keys:
 out_put_key1:
 	put_futex_key(fshared, &key1);
 out:
-	return ret;
+	if (pi_state != NULL)
+		free_pi_state(pi_state);
+	return ret ? ret : task_count;
 }
 
 /* The key must be already stored in q->key. */
@@ -907,8 +1294,6 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	init_waitqueue_head(&q->waiter);
-
 	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
@@ -1119,35 +1504,149 @@ handle_fault:
  */
 #define FLAGS_SHARED		0x01
 #define FLAGS_CLOCKRT		0x02
+#define FLAGS_HAS_TIMEOUT	0x04
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, int fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+/**
+ * fixup_owner() - Post lock pi_state and corner case management
+ * @uaddr:	user address of the futex
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		futex_q (contains pi_state and access to the rt_mutex)
+ * @locked:	if the attempt to take the rt_mutex succeeded (1) or not (0)
+ *
+ * After attempting to lock an rt_mutex, this function is called to cleanup
+ * the pi_state owner as well as handle race conditions that may allow us to
+ * acquire the lock. Must be called with the hb lock held.
+ *
+ * Returns:
+ *  1 - success, lock taken
+ *  0 - success, lock not taken
+ * <0 - on error (-EFAULT)
+ */
+static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
+		       int locked)
 {
-	struct task_struct *curr = current;
-	struct restart_block *restart;
-	DECLARE_WAITQUEUE(wait, curr);
-	struct futex_hash_bucket *hb;
-	struct futex_q q;
-	u32 uval;
-	int ret;
-	struct hrtimer_sleeper t;
-	int rem = 0;
+	struct task_struct *owner;
+	int ret = 0;
 
-	if (!bitset)
-		return -EINVAL;
+	if (locked) {
+		/*
+		 * Got the lock. We might not be the anticipated owner if we
+		 * did a lock-steal - fix up the PI-state in that case:
+		 */
+		if (q->pi_state->owner != current)
+			ret = fixup_pi_state_owner(uaddr, q, current, fshared);
+		goto out;
+	}
 
-	q.pi_state = NULL;
-	q.bitset = bitset;
-retry:
-	q.key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ);
-	if (unlikely(ret != 0))
+	/*
+	 * Catch the rare case, where the lock was released when we were on the
+	 * way back before we locked the hash bucket.
+	 */
+	if (q->pi_state->owner == current) {
+		/*
+		 * Try to get the rt_mutex now. This might fail as some other
+		 * task acquired the rt_mutex after we removed ourself from the
+		 * rt_mutex waiters list.
+		 */
+		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+			locked = 1;
+			goto out;
+		}
+
+		/*
+		 * pi_state is incorrect, some other task did a lock steal and
+		 * we returned due to timeout or signal without taking the
+		 * rt_mutex. Too late. We can access the rt_mutex_owner without
+		 * locking, as the other task is now blocked on the hash bucket
+		 * lock. Fix the state up.
+		 */
+		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+		ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
 		goto out;
+	}
 
-retry_private:
-	hb = queue_lock(&q);
+	/*
+	 * Paranoia check. If we did not take the lock, then we should not be
+	 * the owner, nor the pending owner, of the rt_mutex.
+	 */
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
+				"pi-state %p\n", ret,
+				q->pi_state->pi_mutex.owner,
+				q->pi_state->owner);
+
+out:
+	return ret ? ret : locked;
+}
+
+/**
+ * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal
+ * @hb:		the futex hash bucket, must be locked by the caller
+ * @q:		the futex_q to queue up on
+ * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
+ */
+static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
+				struct hrtimer_sleeper *timeout)
+{
+	queue_me(q, hb);
+
+	/*
+	 * There might have been scheduling since the queue_me(), as we
+	 * cannot hold a spinlock across the get_user() in case it
+	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
+	 * queueing ourselves into the futex hash. This code thus has to
+	 * rely on the futex_wake() code removing us from hash when it
+	 * wakes us up.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* Arm the timer */
+	if (timeout) {
+		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+		if (!hrtimer_active(&timeout->timer))
+			timeout->task = NULL;
+	}
+
+	/*
+	 * !plist_node_empty() is safe here without any lock.
+	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+	 */
+	if (likely(!plist_node_empty(&q->list))) {
+		/*
+		 * If the timer has already expired, current will already be
+		 * flagged for rescheduling. Only call schedule if there
+		 * is no timeout, or if it has yet to expire.
+		 */
+		if (!timeout || timeout->task)
+			schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+/**
+ * futex_wait_setup() - Prepare to wait on a futex
+ * @uaddr:	the futex userspace address
+ * @val:	the expected value
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		the associated futex_q
+ * @hb:		storage for hash_bucket pointer to be returned to caller
+ *
+ * Setup the futex_q and locate the hash_bucket.  Get the futex value and
+ * compare it with the expected value.  Handle atomic faults internally.
+ * Return with the hb lock held and a q.key reference on success, and unlocked
+ * with no q.key reference on failure.
+ *
+ * Returns:
+ *  0 - uaddr contains val and hb has been locked
+ * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
+ */
+static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+			   struct futex_q *q, struct futex_hash_bucket **hb)
+{
+	u32 uval;
+	int ret;
 
 	/*
 	 * Access the page AFTER the hash-bucket is locked.
@@ -1165,95 +1664,83 @@ retry_private:
 	 * A consequence is that futex_wait() can return zero and absorb
 	 * a wakeup when *uaddr != val on entry to the syscall.  This is
 	 * rare, but normal.
-	 *
-	 * For shared futexes, we hold the mmap semaphore, so the mapping
-	 * cannot have changed since we looked it up in get_futex_key.
 	 */
+retry:
+	q->key = FUTEX_KEY_INIT;
+	ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+retry_private:
+	*hb = queue_lock(q);
+
 	ret = get_futex_value_locked(&uval, uaddr);
 
-	if (unlikely(ret)) {
-		queue_unlock(&q, hb);
+	if (ret) {
+		queue_unlock(q, *hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
-			goto out_put_key;
+			goto out;
 
 		if (!fshared)
 			goto retry_private;
 
-		put_futex_key(fshared, &q.key);
+		put_futex_key(fshared, &q->key);
 		goto retry;
 	}
-	ret = -EWOULDBLOCK;
-	if (unlikely(uval != val)) {
-		queue_unlock(&q, hb);
-		goto out_put_key;
-	}
 
-	/* Only actually queue if *uaddr contained val.  */
-	queue_me(&q, hb);
+	if (uval != val) {
+		queue_unlock(q, *hb);
+		ret = -EWOULDBLOCK;
+	}
 
-	/*
-	 * There might have been scheduling since the queue_me(), as we
-	 * cannot hold a spinlock across the get_user() in case it
-	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
-	 * queueing ourselves into the futex hash.  This code thus has to
-	 * rely on the futex_wake() code removing us from hash when it
-	 * wakes us up.
-	 */
+out:
+	if (ret)
+		put_futex_key(fshared, &q->key);
+	return ret;
+}
 
-	/* add_wait_queue is the barrier after __set_current_state. */
-	__set_current_state(TASK_INTERRUPTIBLE);
-	add_wait_queue(&q.waiter, &wait);
-	/*
-	 * !plist_node_empty() is safe here without any lock.
-	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
-	 */
-	if (likely(!plist_node_empty(&q.list))) {
-		if (!abs_time)
-			schedule();
-		else {
-			hrtimer_init_on_stack(&t.timer,
-					      clockrt ? CLOCK_REALTIME :
-					      CLOCK_MONOTONIC,
-					      HRTIMER_MODE_ABS);
-			hrtimer_init_sleeper(&t, current);
-			hrtimer_set_expires_range_ns(&t.timer, *abs_time,
-						     current->timer_slack_ns);
-
-			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
-			if (!hrtimer_active(&t.timer))
-				t.task = NULL;
+static int futex_wait(u32 __user *uaddr, int fshared,
+		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+{
+	struct hrtimer_sleeper timeout, *to = NULL;
+	struct restart_block *restart;
+	struct futex_hash_bucket *hb;
+	struct futex_q q;
+	int ret;
 
-			/*
-			 * the timer could have already expired, in which
-			 * case current would be flagged for rescheduling.
-			 * Don't bother calling schedule.
-			 */
-			if (likely(t.task))
-				schedule();
+	if (!bitset)
+		return -EINVAL;
 
-			hrtimer_cancel(&t.timer);
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = NULL;
 
-			/* Flag if a timeout occured */
-			rem = (t.task == NULL);
+	if (abs_time) {
+		to = &timeout;
 
-			destroy_hrtimer_on_stack(&t.timer);
-		}
+		hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+				      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+		hrtimer_init_sleeper(to, current);
+		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+					     current->timer_slack_ns);
 	}
-	__set_current_state(TASK_RUNNING);
 
-	/*
-	 * NOTE: we don't remove ourselves from the waitqueue because
-	 * we are the only user of it.
-	 */
+	/* Prepare to wait on uaddr. */
+	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+	if (ret)
+		goto out;
+
+	/* queue_me and wait for wakeup, timeout, or a signal. */
+	futex_wait_queue_me(hb, &q, to);
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	ret = 0;
 	if (!unqueue_me(&q))
 		goto out_put_key;
 	ret = -ETIMEDOUT;
-	if (rem)
+	if (to && !to->task)
 		goto out_put_key;
 
 	/*
@@ -1270,7 +1757,7 @@ retry_private:
 	restart->futex.val = val;
 	restart->futex.time = abs_time->tv64;
 	restart->futex.bitset = bitset;
-	restart->futex.flags = 0;
+	restart->futex.flags = FLAGS_HAS_TIMEOUT;
 
 	if (fshared)
 		restart->futex.flags |= FLAGS_SHARED;
@@ -1282,6 +1769,10 @@ retry_private:
 out_put_key:
 	put_futex_key(fshared, &q.key);
 out:
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
 	return ret;
 }
 
@@ -1290,13 +1781,16 @@ static long futex_wait_restart(struct restart_block *restart)
 {
 	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
 	int fshared = 0;
-	ktime_t t;
+	ktime_t t, *tp = NULL;
 
-	t.tv64 = restart->futex.time;
+	if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
+		t.tv64 = restart->futex.time;
+		tp = &t;
+	}
 	restart->fn = do_no_restart_syscall;
 	if (restart->futex.flags & FLAGS_SHARED)
 		fshared = 1;
-	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
+	return (long)futex_wait(uaddr, fshared, restart->futex.val, tp,
 				restart->futex.bitset,
 				restart->futex.flags & FLAGS_CLOCKRT);
 }
@@ -1312,11 +1806,10 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 			 int detect, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
-	struct task_struct *curr = current;
 	struct futex_hash_bucket *hb;
-	u32 uval, newval, curval;
+	u32 uval;
 	struct futex_q q;
-	int ret, lock_taken, ownerdied = 0;
+	int res, ret;
 
 	if (refill_pi_state_cache())
 		return -ENOMEM;
@@ -1330,6 +1823,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 	}
 
 	q.pi_state = NULL;
+	q.rt_waiter = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
@@ -1339,81 +1833,15 @@ retry:
 retry_private:
 	hb = queue_lock(&q);
 
-retry_locked:
-	ret = lock_taken = 0;
-
-	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
-	 */
-	newval = task_pid_vnr(current);
-
-	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-	if (unlikely(curval == -EFAULT))
-		goto uaddr_faulted;
-
-	/*
-	 * Detect deadlocks. In case of REQUEUE_PI this is a valid
-	 * situation and we return success to user space.
-	 */
-	if (unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(current))) {
-		ret = -EDEADLK;
-		goto out_unlock_put_key;
-	}
-
-	/*
-	 * Surprise - we got the lock. Just return to userspace:
-	 */
-	if (unlikely(!curval))
-		goto out_unlock_put_key;
-
-	uval = curval;
-
-	/*
-	 * Set the WAITERS flag, so the owner will know it has someone
-	 * to wake at next unlock
-	 */
-	newval = curval | FUTEX_WAITERS;
-
-	/*
-	 * There are two cases, where a futex might have no owner (the
-	 * owner TID is 0): OWNER_DIED. We take over the futex in this
-	 * case. We also do an unconditional take over, when the owner
-	 * of the futex died.
-	 *
-	 * This is safe as we are protected by the hash bucket lock !
-	 */
-	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
-		/* Keep the OWNER_DIED bit */
-		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(current);
-		ownerdied = 0;
-		lock_taken = 1;
-	}
-
-	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-	if (unlikely(curval == -EFAULT))
-		goto uaddr_faulted;
-	if (unlikely(curval != uval))
-		goto retry_locked;
-
-	/*
-	 * We took the lock due to owner died take over.
-	 */
-	if (unlikely(lock_taken))
-		goto out_unlock_put_key;
-
-	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
-	 */
-	ret = lookup_pi_state(uval, hb, &q.key, &q.pi_state);
-
+	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
 	if (unlikely(ret)) {
 		switch (ret) {
-
+		case 1:
+			/* We got the lock. */
+			ret = 0;
+			goto out_unlock_put_key;
+		case -EFAULT:
+			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
 			 * Task is exiting and we just wait for the
@@ -1423,25 +1851,6 @@ retry_locked:
 			put_futex_key(fshared, &q.key);
 			cond_resched();
 			goto retry;
-
-		case -ESRCH:
-			/*
-			 * No owner found for this futex. Check if the
-			 * OWNER_DIED bit is set to figure out whether
-			 * this is a robust futex or not.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				goto uaddr_faulted;
-
-			/*
-			 * We simply start over in case of a robust
-			 * futex. The code above will take the futex
-			 * and return happy.
-			 */
-			if (curval & FUTEX_OWNER_DIED) {
-				ownerdied = 1;
-				goto retry_locked;
-			}
 		default:
 			goto out_unlock_put_key;
 		}
@@ -1465,71 +1874,21 @@ retry_locked:
 	}
 
 	spin_lock(q.lock_ptr);
-
-	if (!ret) {
-		/*
-		 * Got the lock. We might not be the anticipated owner
-		 * if we did a lock-steal - fix up the PI-state in
-		 * that case:
-		 */
-		if (q.pi_state->owner != curr)
-			ret = fixup_pi_state_owner(uaddr, &q, curr, fshared);
-	} else {
-		/*
-		 * Catch the rare case, where the lock was released
-		 * when we were on the way back before we locked the
-		 * hash bucket.
-		 */
-		if (q.pi_state->owner == curr) {
-			/*
-			 * Try to get the rt_mutex now. This might
-			 * fail as some other task acquired the
-			 * rt_mutex after we removed ourself from the
-			 * rt_mutex waiters list.
-			 */
-			if (rt_mutex_trylock(&q.pi_state->pi_mutex))
-				ret = 0;
-			else {
-				/*
-				 * pi_state is incorrect, some other
-				 * task did a lock steal and we
-				 * returned due to timeout or signal
-				 * without taking the rt_mutex. Too
-				 * late. We can access the
-				 * rt_mutex_owner without locking, as
-				 * the other task is now blocked on
-				 * the hash bucket lock. Fix the state
-				 * up.
-				 */
-				struct task_struct *owner;
-				int res;
-
-				owner = rt_mutex_owner(&q.pi_state->pi_mutex);
-				res = fixup_pi_state_owner(uaddr, &q, owner,
-							   fshared);
-
-				/* propagate -EFAULT, if the fixup failed */
-				if (res)
-					ret = res;
-			}
-		} else {
-			/*
-			 * Paranoia check. If we did not take the lock
-			 * in the trylock above, then we should not be
-			 * the owner of the rtmutex, neither the real
-			 * nor the pending one:
-			 */
-			if (rt_mutex_owner(&q.pi_state->pi_mutex) == curr)
-				printk(KERN_ERR "futex_lock_pi: ret = %d "
-				       "pi-mutex: %p pi-state %p\n", ret,
-				       q.pi_state->pi_mutex.owner,
-				       q.pi_state->owner);
-		}
-	}
+	/*
+	 * Fixup the pi_state owner and possibly acquire the lock if we
+	 * haven't already.
+	 */
+	res = fixup_owner(uaddr, fshared, &q, !ret);
+	/*
+	 * If fixup_owner() returned an error, proprogate that.  If it acquired
+	 * the lock, clear our -ETIMEDOUT or -EINTR.
+	 */
+	if (res)
+		ret = (res < 0) ? res : 0;
 
 	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock it and return the fault to userspace.
+	 * If fixup_owner() faulted and was unable to handle the fault, unlock
+	 * it and return the fault to userspace.
 	 */
 	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
 		rt_mutex_unlock(&q.pi_state->pi_mutex);
@@ -1537,9 +1896,7 @@ retry_locked:
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
-	if (to)
-		destroy_hrtimer_on_stack(&to->timer);
-	return ret != -EINTR ? ret : -ERESTARTNOINTR;
+	goto out;
 
 out_unlock_put_key:
 	queue_unlock(&q, hb);
@@ -1549,7 +1906,7 @@ out_put_key:
 out:
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
-	return ret;
+	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
 	/*
@@ -1572,7 +1929,6 @@ uaddr_faulted:
 	goto retry;
 }
 
-
 /*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),
@@ -1674,6 +2030,229 @@ pi_faulted:
 	return ret;
 }
 
+/**
+ * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex
+ * @hb:		the hash_bucket futex_q was original enqueued on
+ * @q:		the futex_q woken while waiting to be requeued
+ * @key2:	the futex_key of the requeue target futex
+ * @timeout:	the timeout associated with the wait (NULL if none)
+ *
+ * Detect if the task was woken on the initial futex as opposed to the requeue
+ * target futex.  If so, determine if it was a timeout or a signal that caused
+ * the wakeup and return the appropriate error code to the caller.  Must be
+ * called with the hb lock held.
+ *
+ * Returns
+ *  0 - no early wakeup detected
+ * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ */
+static inline
+int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
+				   struct futex_q *q, union futex_key *key2,
+				   struct hrtimer_sleeper *timeout)
+{
+	int ret = 0;
+
+	/*
+	 * With the hb lock held, we avoid races while we process the wakeup.
+	 * We only need to hold hb (and not hb2) to ensure atomicity as the
+	 * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb.
+	 * It can't be requeued from uaddr2 to something else since we don't
+	 * support a PI aware source futex for requeue.
+	 */
+	if (!match_futex(&q->key, key2)) {
+		WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr));
+		/*
+		 * We were woken prior to requeue by a timeout or a signal.
+		 * Unqueue the futex_q and determine which it was.
+		 */
+		plist_del(&q->list, &q->list.plist);
+		drop_futex_key_refs(&q->key);
+
+		if (timeout && !timeout->task)
+			ret = -ETIMEDOUT;
+		else
+			ret = -ERESTARTNOINTR;
+	}
+	return ret;
+}
+
+/**
+ * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
+ * @uaddr:	the futex we initialyl wait on (non-pi)
+ * @fshared:	whether the futexes are shared (1) or not (0).  They must be
+ * 		the same type, no requeueing from private to shared, etc.
+ * @val:	the expected value of uaddr
+ * @abs_time:	absolute timeout
+ * @bitset:	32 bit wakeup bitset set by userspace, defaults to all.
+ * @clockrt:	whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
+ * @uaddr2:	the pi futex we will take prior to returning to user-space
+ *
+ * The caller will wait on uaddr and will be requeued by futex_requeue() to
+ * uaddr2 which must be PI aware.  Normal wakeup will wake on uaddr2 and
+ * complete the acquisition of the rt_mutex prior to returning to userspace.
+ * This ensures the rt_mutex maintains an owner when it has waiters; without
+ * one, the pi logic wouldn't know which task to boost/deboost, if there was a
+ * need to.
+ *
+ * We call schedule in futex_wait_queue_me() when we enqueue and return there
+ * via the following:
+ * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
+ * 2) wakeup on uaddr2 after a requeue and subsequent unlock
+ * 3) signal (before or after requeue)
+ * 4) timeout (before or after requeue)
+ *
+ * If 3, we setup a restart_block with futex_wait_requeue_pi() as the function.
+ *
+ * If 2, we may then block on trying to take the rt_mutex and return via:
+ * 5) successful lock
+ * 6) signal
+ * 7) timeout
+ * 8) other lock acquisition failure
+ *
+ * If 6, we setup a restart_block with futex_lock_pi() as the function.
+ *
+ * If 4 or 7, we cleanup and return with -ETIMEDOUT.
+ *
+ * Returns:
+ *  0 - On success
+ * <0 - On error
+ */
+static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
+				 u32 val, ktime_t *abs_time, u32 bitset,
+				 int clockrt, u32 __user *uaddr2)
+{
+	struct hrtimer_sleeper timeout, *to = NULL;
+	struct rt_mutex_waiter rt_waiter;
+	struct rt_mutex *pi_mutex = NULL;
+	struct futex_hash_bucket *hb;
+	union futex_key key2;
+	struct futex_q q;
+	int res, ret;
+
+	if (!bitset)
+		return -EINVAL;
+
+	if (abs_time) {
+		to = &timeout;
+		hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+				      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+		hrtimer_init_sleeper(to, current);
+		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+					     current->timer_slack_ns);
+	}
+
+	/*
+	 * The waiter is allocated on our stack, manipulated by the requeue
+	 * code while we sleep on uaddr.
+	 */
+	debug_rt_mutex_init_waiter(&rt_waiter);
+	rt_waiter.task = NULL;
+
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = &rt_waiter;
+
+	key2 = FUTEX_KEY_INIT;
+	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
+	if (unlikely(ret != 0))
+		goto out;
+
+	/* Prepare to wait on uaddr. */
+	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+	if (ret)
+		goto out_key2;
+
+	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
+	futex_wait_queue_me(hb, &q, to);
+
+	spin_lock(&hb->lock);
+	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+	spin_unlock(&hb->lock);
+	if (ret)
+		goto out_put_keys;
+
+	/*
+	 * In order for us to be here, we know our q.key == key2, and since
+	 * we took the hb->lock above, we also know that futex_requeue() has
+	 * completed and we no longer have to concern ourselves with a wakeup
+	 * race with the atomic proxy lock acquition by the requeue code.
+	 */
+
+	/* Check if the requeue code acquired the second futex for us. */
+	if (!q.rt_waiter) {
+		/*
+		 * Got the lock. We might not be the anticipated owner if we
+		 * did a lock-steal - fix up the PI-state in that case.
+		 */
+		if (q.pi_state && (q.pi_state->owner != current)) {
+			spin_lock(q.lock_ptr);
+			ret = fixup_pi_state_owner(uaddr2, &q, current,
+						   fshared);
+			spin_unlock(q.lock_ptr);
+		}
+	} else {
+		/*
+		 * We have been woken up by futex_unlock_pi(), a timeout, or a
+		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
+		 * the pi_state.
+		 */
+		WARN_ON(!&q.pi_state);
+		pi_mutex = &q.pi_state->pi_mutex;
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		debug_rt_mutex_free_waiter(&rt_waiter);
+
+		spin_lock(q.lock_ptr);
+		/*
+		 * Fixup the pi_state owner and possibly acquire the lock if we
+		 * haven't already.
+		 */
+		res = fixup_owner(uaddr2, fshared, &q, !ret);
+		/*
+		 * If fixup_owner() returned an error, proprogate that.  If it
+		 * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+		 */
+		if (res)
+			ret = (res < 0) ? res : 0;
+
+		/* Unqueue and drop the lock. */
+		unqueue_me_pi(&q);
+	}
+
+	/*
+	 * If fixup_pi_state_owner() faulted and was unable to handle the
+	 * fault, unlock the rt_mutex and return the fault to userspace.
+	 */
+	if (ret == -EFAULT) {
+		if (rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+	} else if (ret == -EINTR) {
+		/*
+		 * We've already been requeued, but we have no way to
+		 * restart by calling futex_lock_pi() directly. We
+		 * could restart the syscall, but that will look at
+		 * the user space value and return right away. So we
+		 * drop back with EWOULDBLOCK to tell user space that
+		 * "val" has been changed. That's the same what the
+		 * restart of the syscall would do in
+		 * futex_wait_setup().
+		 */
+		ret = -EWOULDBLOCK;
+	}
+
+out_put_keys:
+	put_futex_key(fshared, &q.key);
+out_key2:
+	put_futex_key(fshared, &key2);
+
+out:
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
+	return ret;
+}
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
@@ -1896,7 +2475,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		fshared = 1;
 
 	clockrt = op & FUTEX_CLOCK_REALTIME;
-	if (clockrt && cmd != FUTEX_WAIT_BITSET)
+	if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
 		return -ENOSYS;
 
 	switch (cmd) {
@@ -1911,10 +2490,11 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		ret = futex_wake(uaddr, fshared, val, val3);
 		break;
 	case FUTEX_REQUEUE:
-		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL);
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0);
 		break;
 	case FUTEX_CMP_REQUEUE:
-		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3);
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+				    0);
 		break;
 	case FUTEX_WAKE_OP:
 		ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3);
@@ -1931,6 +2511,15 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		if (futex_cmpxchg_enabled)
 			ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1);
 		break;
+	case FUTEX_WAIT_REQUEUE_PI:
+		val3 = FUTEX_BITSET_MATCH_ANY;
+		ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3,
+					    clockrt, uaddr2);
+		break;
+	case FUTEX_CMP_REQUEUE_PI:
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+				    1);
+		break;
 	default:
 		ret = -ENOSYS;
 	}
@@ -1948,7 +2537,8 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	int cmd = op & FUTEX_CMD_MASK;
 
 	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
-		      cmd == FUTEX_WAIT_BITSET)) {
+		      cmd == FUTEX_WAIT_BITSET ||
+		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
 		if (copy_from_user(&ts, utime, sizeof(ts)) != 0)
 			return -EFAULT;
 		if (!timespec_valid(&ts))
@@ -1960,11 +2550,11 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 		tp = &t;
 	}
 	/*
-	 * requeue parameter in 'utime' if cmd == FUTEX_REQUEUE.
+	 * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*.
 	 * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP.
 	 */
 	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
-	    cmd == FUTEX_WAKE_OP)
+	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
 		val2 = (u32) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 3394f8f5296..7d047808419 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -3,5 +3,5 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
+obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c687ba4363f..13c68e71b72 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -359,7 +359,6 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	spin_lock(&desc->lock);
 	mask_ack_irq(desc, irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -438,7 +437,6 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	desc->status &= ~IRQ_INPROGRESS;
 out:
 	desc->chip->eoi(irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	spin_unlock(&desc->lock);
 }
@@ -475,7 +473,6 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
 		mask_ack_irq(desc, irq);
-		desc = irq_remap_to_desc(irq, desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -483,7 +480,6 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	/* Start handling the irq */
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -544,10 +540,8 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi) {
+	if (desc->chip->eoi)
 		desc->chip->eoi(irq);
-		desc = irq_remap_to_desc(irq, desc);
-	}
 }
 
 void
@@ -582,10 +576,8 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip) {
+		if (desc->chip != &no_irq_chip)
 			mask_ack_irq(desc, irq);
-			desc = irq_remap_to_desc(irq, desc);
-		}
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 26e08754744..a60018402f4 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,14 +11,15 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
-#include <trace/irq.h>
 #include <linux/bootmem.h>
+#include <trace/events/irq.h>
 
 #include "internals.h"
 
@@ -81,45 +82,48 @@ static struct irq_desc irq_desc_init = {
 	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
 };
 
-void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
+void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
 {
-	int node;
 	void *ptr;
 
-	node = cpu_to_node(cpu);
-	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node);
+	if (slab_is_available())
+		ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+				   GFP_ATOMIC, node);
+	else
+		ptr = alloc_bootmem_node(NODE_DATA(node),
+				nr * sizeof(*desc->kstat_irqs));
 
 	/*
 	 * don't overwite if can not get new one
 	 * init_copy_kstat_irqs() could still use old one
 	 */
 	if (ptr) {
-		printk(KERN_DEBUG "  alloc kstat_irqs on cpu %d node %d\n",
-			 cpu, node);
+		printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
 		desc->kstat_irqs = ptr;
 	}
 }
 
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
+static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
 {
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
 	desc->irq = irq;
 #ifdef CONFIG_SMP
-	desc->cpu = cpu;
+	desc->node = node;
 #endif
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_kstat_irqs(desc, cpu, nr_cpu_ids);
+	init_kstat_irqs(desc, node, nr_cpu_ids);
 	if (!desc->kstat_irqs) {
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, cpu, false)) {
+	if (!alloc_desc_masks(desc, node, false)) {
 		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
 		BUG_ON(1);
 	}
-	arch_init_chip_data(desc, cpu);
+	init_desc_masks(desc);
+	arch_init_chip_data(desc, node);
 }
 
 /*
@@ -169,7 +173,8 @@ int __init early_irq_init(void)
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		init_alloc_desc_masks(&desc[i], 0, true);
+		alloc_desc_masks(&desc[i], 0, true);
+		init_desc_masks(&desc[i]);
 		irq_desc_ptrs[i] = desc + i;
 	}
 
@@ -187,11 +192,10 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 {
 	struct irq_desc *desc;
 	unsigned long flags;
-	int node;
 
 	if (irq >= nr_irqs) {
 		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
@@ -210,15 +214,17 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	if (desc)
 		goto out_unlock;
 
-	node = cpu_to_node(cpu);
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "  alloc irq_desc for %d on cpu %d node %d\n",
-		 irq, cpu, node);
+	if (slab_is_available())
+		desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+	else
+		desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+
+	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
 	if (!desc) {
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
-	init_one_irq_desc(irq, desc, cpu);
+	init_one_irq_desc(irq, desc, node);
 
 	irq_desc_ptrs[irq] = desc;
 
@@ -256,7 +262,8 @@ int __init early_irq_init(void)
 
 	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
-		init_alloc_desc_masks(&desc[i], 0, true);
+		alloc_desc_masks(&desc[i], 0, true);
+		init_desc_masks(&desc[i]);
 		desc[i].kstat_irqs = kstat_irqs_all[i];
 	}
 	return arch_early_irq_init();
@@ -267,7 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
 {
 	return irq_to_desc(irq);
 }
@@ -348,9 +355,6 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
-DEFINE_TRACE(irq_handler_entry);
-DEFINE_TRACE(irq_handler_exit);
-
 /**
  * handle_IRQ_event - irq action chain handler
  * @irq:	the interrupt number
@@ -453,11 +457,8 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack) {
+		if (desc->chip->ack)
 			desc->chip->ack(irq);
-			/* get new one */
-			desc = irq_remap_to_desc(irq, desc);
-		}
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
@@ -468,10 +469,8 @@ unsigned int __do_IRQ(unsigned int irq)
 	}
 
 	spin_lock(&desc->lock);
-	if (desc->chip->ack) {
+	if (desc->chip->ack)
 		desc->chip->ack(irq);
-		desc = irq_remap_to_desc(irq, desc);
-	}
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 01ce20eab38..73468253143 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,7 @@ extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
 extern struct lock_class_key irq_desc_lock_class;
-extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
+extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 extern void clear_kstat_irqs(struct irq_desc *desc);
 extern spinlock_t sparse_irq_lock;
 
@@ -42,6 +42,9 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern int irq_select_affinity_usr(unsigned int irq);
 
+extern void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 2734eca5924..aaf5c9d0577 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -80,7 +80,7 @@ int irq_can_set_affinity(unsigned int irq)
 	return 1;
 }
 
-static void
+void
 irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
 {
 	struct irqaction *action = desc->action;
@@ -109,17 +109,22 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT)
-		desc->chip->set_affinity(irq, cpumask);
+	if (desc->status & IRQ_MOVE_PCNTXT) {
+		if (!desc->chip->set_affinity(irq, cpumask)) {
+			cpumask_copy(desc->affinity, cpumask);
+			irq_set_thread_affinity(desc, cpumask);
+		}
+	}
 	else {
 		desc->status |= IRQ_MOVE_PENDING;
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	cpumask_copy(desc->affinity, cpumask);
-	desc->chip->set_affinity(irq, cpumask);
+	if (!desc->chip->set_affinity(irq, cpumask)) {
+		cpumask_copy(desc->affinity, cpumask);
+		irq_set_thread_affinity(desc, cpumask);
+	}
 #endif
-	irq_set_thread_affinity(desc, cpumask);
 	desc->status |= IRQ_AFFINITY_SET;
 	spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index e05ad9be43b..cfe767ca154 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -1,5 +1,8 @@
 
 #include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
 
 void move_masked_irq(int irq)
 {
@@ -39,11 +42,12 @@ void move_masked_irq(int irq)
 	 * masking the irqs.
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids)) {
-		cpumask_and(desc->affinity,
-			    desc->pending_mask, cpu_online_mask);
-		desc->chip->set_affinity(irq, desc->affinity);
-	}
+		   < nr_cpu_ids))
+		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
+			cpumask_copy(desc->affinity, desc->pending_mask);
+			irq_set_thread_affinity(desc, desc->pending_mask);
+		}
+
 	cpumask_clear(desc->pending_mask);
 }
 
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 44bbdcbaf8d..2f69bee57bf 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -15,9 +15,9 @@
 
 static void init_copy_kstat_irqs(struct irq_desc *old_desc,
 				 struct irq_desc *desc,
-				 int cpu, int nr)
+				 int node, int nr)
 {
-	init_kstat_irqs(desc, cpu, nr);
+	init_kstat_irqs(desc, node, nr);
 
 	if (desc->kstat_irqs != old_desc->kstat_irqs)
 		memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
@@ -34,20 +34,20 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
 }
 
 static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
-		 struct irq_desc *desc, int cpu)
+		 struct irq_desc *desc, int node)
 {
 	memcpy(desc, old_desc, sizeof(struct irq_desc));
-	if (!init_alloc_desc_masks(desc, cpu, false)) {
+	if (!alloc_desc_masks(desc, node, false)) {
 		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
 				"for migration.\n", irq);
 		return false;
 	}
 	spin_lock_init(&desc->lock);
-	desc->cpu = cpu;
+	desc->node = node;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
 	init_copy_desc_masks(old_desc, desc);
-	arch_init_copy_chip_data(old_desc, desc, cpu);
+	arch_init_copy_chip_data(old_desc, desc, node);
 	return true;
 }
 
@@ -59,12 +59,11 @@ static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
 }
 
 static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
-						int cpu)
+						int node)
 {
 	struct irq_desc *desc;
 	unsigned int irq;
 	unsigned long flags;
-	int node;
 
 	irq = old_desc->irq;
 
@@ -76,7 +75,6 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	if (desc && old_desc != desc)
 		goto out_unlock;
 
-	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 	if (!desc) {
 		printk(KERN_ERR "irq %d: can not get new irq_desc "
@@ -85,7 +83,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 		desc = old_desc;
 		goto out_unlock;
 	}
-	if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
+	if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
 		/* still use old one */
 		kfree(desc);
 		desc = old_desc;
@@ -97,9 +95,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 
 	/* free the old one */
 	free_one_irq_desc(old_desc, desc);
-	spin_unlock(&old_desc->lock);
 	kfree(old_desc);
-	spin_lock(&desc->lock);
 
 	return desc;
 
@@ -109,24 +105,14 @@ out_unlock:
 	return desc;
 }
 
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu)
+struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 {
-	int old_cpu;
-	int node, old_node;
-
 	/* those all static, do move them */
 	if (desc->irq < NR_IRQS_LEGACY)
 		return desc;
 
-	old_cpu = desc->cpu;
-	if (old_cpu != cpu) {
-		node = cpu_to_node(cpu);
-		old_node = cpu_to_node(old_cpu);
-		if (old_node != node)
-			desc = __real_move_irq_desc(desc, cpu);
-		else
-			desc->cpu = cpu;
-	}
+	if (desc->node != node)
+		desc = __real_move_irq_desc(desc, node);
 
 	return desc;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4ebaf8519ab..41c88fe4050 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,7 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -21,9 +21,6 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
-DEFINE_TRACE(sched_kthread_stop);
-DEFINE_TRACE(sched_kthread_stop_ret);
-
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index accb40cdb12..8bbeef996c7 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -42,12 +42,14 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
-#include <trace/lockdep.h>
 
 #include <asm/sections.h>
 
 #include "lockdep_internals.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/lockdep.h>
+
 #ifdef CONFIG_PROVE_LOCKING
 int prove_locking = 1;
 module_param(prove_locking, int, 0644);
@@ -2935,8 +2937,6 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 }
 EXPORT_SYMBOL_GPL(lock_set_class);
 
-DEFINE_TRACE(lock_acquire);
-
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
@@ -2963,8 +2963,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 }
 EXPORT_SYMBOL_GPL(lock_acquire);
 
-DEFINE_TRACE(lock_release);
-
 void lock_release(struct lockdep_map *lock, int nested,
 			  unsigned long ip)
 {
@@ -3105,6 +3103,8 @@ found_it:
 		hlock->holdtime_stamp = now;
 	}
 
+	trace_lock_acquired(lock, ip, waittime);
+
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -3120,8 +3120,6 @@ found_it:
 	lock->ip = ip;
 }
 
-DEFINE_TRACE(lock_contended);
-
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
@@ -3143,14 +3141,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-DEFINE_TRACE(lock_acquired);
-
 void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_acquired(lock, ip);
-
 	if (unlikely(!lock_stat))
 		return;
 
diff --git a/kernel/module.c b/kernel/module.c
index e797812a4d9..2383e60fcf3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -18,6 +18,7 @@
 */
 #include <linux/module.h>
 #include <linux/moduleloader.h>
+#include <linux/ftrace_event.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
@@ -1489,9 +1490,6 @@ static void free_module(struct module *mod)
 	/* Free any allocated parameters. */
 	destroy_params(mod->kp, mod->num_kp);
 
-	/* release any pointers to mcount in this module */
-	ftrace_release(mod->module_core, mod->core_size);
-
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
@@ -1892,11 +1890,9 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
 	unsigned int modindex, versindex, infoindex, pcpuindex;
-	unsigned int num_mcount;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
-	unsigned long *mseg;
 	mm_segment_t old_fs;
 
 	DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2172,7 +2168,19 @@ static noinline struct module *load_module(void __user *umod,
 					sizeof(*mod->tracepoints),
 					&mod->num_tracepoints);
 #endif
-
+#ifdef CONFIG_EVENT_TRACING
+	mod->trace_events = section_objs(hdr, sechdrs, secstrings,
+					 "_ftrace_events",
+					 sizeof(*mod->trace_events),
+					 &mod->num_trace_events);
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+	/* sechdrs[0].sh_size is always zero */
+	mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings,
+					     "__mcount_loc",
+					     sizeof(*mod->ftrace_callsites),
+					     &mod->num_ftrace_callsites);
+#endif
 #ifdef CONFIG_MODVERSIONS
 	if ((mod->num_syms && !mod->crcs)
 	    || (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -2237,11 +2245,6 @@ static noinline struct module *load_module(void __user *umod,
 			dynamic_debug_setup(debug, num_debug);
 	}
 
-	/* sechdrs[0].sh_size is always zero */
-	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
-			    sizeof(*mseg), &num_mcount);
-	ftrace_init_module(mod, mseg, mseg + num_mcount);
-
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
@@ -2302,7 +2305,6 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
-	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
diff --git a/kernel/mutex.c b/kernel/mutex.c
index f788a5ace24..947b3ad551f 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -249,7 +249,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 		/* didnt get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		__schedule();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0692ab5a0d6..2442d140bd9 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -25,16 +25,6 @@
 
 
 /*
- * Initialize a new task whose father had been ptraced.
- *
- * Called from copy_process().
- */
-void ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
-	arch_ptrace_fork(child, clone_flags);
-}
-
-/*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
  *
@@ -304,6 +294,8 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 	if (child->ptrace) {
 		child->exit_code = data;
 		dead = __ptrace_detach(current, child);
+		if (!child->exit_state)
+			wake_up_process(child);
 	}
 	write_unlock_irq(&tasklist_lock);
 
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index ce97a4df64d..beb0e659adc 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1356,17 +1356,11 @@ static int rcu_sched_grace_period(void *arg)
 
 		rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
 		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		ret = 0;
+		ret = 0; /* unused */
 		__wait_event_interruptible(rcu_ctrlblk.sched_wq,
 			rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
 			ret);
 
-		/*
-		 * Signals would prevent us from sleeping, and we cannot
-		 * do much with them in any case.  So flush them.
-		 */
-		if (ret)
-			flush_signals(current);
 		couldsleepnext = 0;
 
 	} while (!kthread_should_stop());
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d2a372fb0b9..0dccfbba6d2 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1259,31 +1259,44 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	check_cpu_stall(rsp, rdp);
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->qs_pending)
+	if (rdp->qs_pending) {
+		rdp->n_rp_qs_pending++;
 		return 1;
+	}
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (cpu_has_callbacks_ready_to_invoke(rdp))
+	if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+		rdp->n_rp_cb_ready++;
 		return 1;
+	}
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (cpu_needs_another_gp(rsp, rdp))
+	if (cpu_needs_another_gp(rsp, rdp)) {
+		rdp->n_rp_cpu_needs_gp++;
 		return 1;
+	}
 
 	/* Has another RCU grace period completed?  */
-	if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+	if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+		rdp->n_rp_gp_completed++;
 		return 1;
+	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+		rdp->n_rp_gp_started++;
 		return 1;
+	}
 
 	/* Has an RCU GP gone long enough to send resched IPIs &c? */
 	if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
-	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0))
+	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
+		rdp->n_rp_need_fqs++;
 		return 1;
+	}
 
 	/* nothing to do */
+	rdp->n_rp_need_nothing++;
 	return 0;
 }
 
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 4b1875ba940..fe1dcdbf1ca 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -213,7 +213,63 @@ static struct file_operations rcugp_fops = {
 	.release = single_release,
 };
 
-static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
+{
+	seq_printf(m, "%3d%cnp=%ld "
+		   "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+		   rdp->cpu,
+		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
+		   rdp->n_rcu_pending,
+		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_cb_ready,
+		   rdp->n_rp_cpu_needs_gp,
+		   rdp->n_rp_gp_completed,
+		   rdp->n_rp_gp_started,
+		   rdp->n_rp_need_fqs,
+		   rdp->n_rp_need_nothing);
+}
+
+static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
+{
+	int cpu;
+	struct rcu_data *rdp;
+
+	for_each_possible_cpu(cpu) {
+		rdp = rsp->rda[cpu];
+		if (rdp->beenonline)
+			print_one_rcu_pending(m, rdp);
+	}
+}
+
+static int show_rcu_pending(struct seq_file *m, void *unused)
+{
+	seq_puts(m, "rcu:\n");
+	print_rcu_pendings(m, &rcu_state);
+	seq_puts(m, "rcu_bh:\n");
+	print_rcu_pendings(m, &rcu_bh_state);
+	return 0;
+}
+
+static int rcu_pending_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcu_pending, NULL);
+}
+
+static struct file_operations rcu_pending_fops = {
+	.owner = THIS_MODULE,
+	.open = rcu_pending_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static struct dentry *rcudir;
+static struct dentry *datadir;
+static struct dentry *datadir_csv;
+static struct dentry *gpdir;
+static struct dentry *hierdir;
+static struct dentry *rcu_pendingdir;
+
 static int __init rcuclassic_trace_init(void)
 {
 	rcudir = debugfs_create_dir("rcu", NULL);
@@ -238,6 +294,11 @@ static int __init rcuclassic_trace_init(void)
 						NULL, &rcuhier_fops);
 	if (!hierdir)
 		goto free_out;
+
+	rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+						NULL, &rcu_pending_fops);
+	if (!rcu_pendingdir)
+		goto free_out;
 	return 0;
 free_out:
 	if (datadir)
@@ -257,6 +318,7 @@ static void __exit rcuclassic_trace_cleanup(void)
 	debugfs_remove(datadir_csv);
 	debugfs_remove(gpdir);
 	debugfs_remove(hierdir);
+	debugfs_remove(rcu_pendingdir);
 	debugfs_remove(rcudir);
 }
 
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 013882e8349..820c5af44f3 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -300,7 +300,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
  * assigned pending owner [which might not have taken the
  * lock yet]:
  */
-static inline int try_to_steal_lock(struct rt_mutex *lock)
+static inline int try_to_steal_lock(struct rt_mutex *lock,
+				    struct task_struct *task)
 {
 	struct task_struct *pendowner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *next;
@@ -309,11 +310,11 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
 	if (!rt_mutex_owner_pending(lock))
 		return 0;
 
-	if (pendowner == current)
+	if (pendowner == task)
 		return 1;
 
 	spin_lock_irqsave(&pendowner->pi_lock, flags);
-	if (current->prio >= pendowner->prio) {
+	if (task->prio >= pendowner->prio) {
 		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
 		return 0;
 	}
@@ -338,21 +339,21 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
 	 * We are going to steal the lock and a waiter was
 	 * enqueued on the pending owners pi_waiters queue. So
 	 * we have to enqueue this waiter into
-	 * current->pi_waiters list. This covers the case,
-	 * where current is boosted because it holds another
+	 * task->pi_waiters list. This covers the case,
+	 * where task is boosted because it holds another
 	 * lock and gets unboosted because the booster is
 	 * interrupted, so we would delay a waiter with higher
-	 * priority as current->normal_prio.
+	 * priority as task->normal_prio.
 	 *
 	 * Note: in the rare case of a SCHED_OTHER task changing
 	 * its priority and thus stealing the lock, next->task
-	 * might be current:
+	 * might be task:
 	 */
-	if (likely(next->task != current)) {
-		spin_lock_irqsave(&current->pi_lock, flags);
-		plist_add(&next->pi_list_entry, &current->pi_waiters);
-		__rt_mutex_adjust_prio(current);
-		spin_unlock_irqrestore(&current->pi_lock, flags);
+	if (likely(next->task != task)) {
+		spin_lock_irqsave(&task->pi_lock, flags);
+		plist_add(&next->pi_list_entry, &task->pi_waiters);
+		__rt_mutex_adjust_prio(task);
+		spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 	return 1;
 }
@@ -389,7 +390,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 	 */
 	mark_rt_mutex_waiters(lock);
 
-	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
 		return 0;
 
 	/* We got the lock. */
@@ -411,6 +412,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
  */
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
+				   struct task_struct *task,
 				   int detect_deadlock)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
@@ -418,21 +420,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	unsigned long flags;
 	int chain_walk = 0, res;
 
-	spin_lock_irqsave(&current->pi_lock, flags);
-	__rt_mutex_adjust_prio(current);
-	waiter->task = current;
+	spin_lock_irqsave(&task->pi_lock, flags);
+	__rt_mutex_adjust_prio(task);
+	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, current->prio);
-	plist_node_init(&waiter->pi_list_entry, current->prio);
+	plist_node_init(&waiter->list_entry, task->prio);
+	plist_node_init(&waiter->pi_list_entry, task->prio);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
 	plist_add(&waiter->list_entry, &lock->wait_list);
 
-	current->pi_blocked_on = waiter;
+	task->pi_blocked_on = waiter;
 
-	spin_unlock_irqrestore(&current->pi_lock, flags);
+	spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		spin_lock_irqsave(&owner->pi_lock, flags);
@@ -460,7 +462,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	spin_unlock(&lock->wait_lock);
 
 	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 current);
+					 task);
 
 	spin_lock(&lock->wait_lock);
 
@@ -605,37 +607,25 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
 }
 
-/*
- * Slow path lock function:
+/**
+ * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * @lock:		 the rt_mutex to take
+ * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
+ * 			 or TASK_UNINTERRUPTIBLE)
+ * @timeout:		 the pre-initialized and started timer, or NULL for none
+ * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @detect_deadlock:	 passed to task_blocks_on_rt_mutex
+ *
+ * lock->wait_lock must be held by the caller.
  */
 static int __sched
-rt_mutex_slowlock(struct rt_mutex *lock, int state,
-		  struct hrtimer_sleeper *timeout,
-		  int detect_deadlock)
+__rt_mutex_slowlock(struct rt_mutex *lock, int state,
+		    struct hrtimer_sleeper *timeout,
+		    struct rt_mutex_waiter *waiter,
+		    int detect_deadlock)
 {
-	struct rt_mutex_waiter waiter;
 	int ret = 0;
 
-	debug_rt_mutex_init_waiter(&waiter);
-	waiter.task = NULL;
-
-	spin_lock(&lock->wait_lock);
-
-	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock)) {
-		spin_unlock(&lock->wait_lock);
-		return 0;
-	}
-
-	set_current_state(state);
-
-	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout)) {
-		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
-
 	for (;;) {
 		/* Try to acquire the lock: */
 		if (try_to_take_rt_mutex(lock))
@@ -656,19 +646,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		}
 
 		/*
-		 * waiter.task is NULL the first time we come here and
+		 * waiter->task is NULL the first time we come here and
 		 * when we have been woken up by the previous owner
 		 * but the lock got stolen by a higher prio task.
 		 */
-		if (!waiter.task) {
-			ret = task_blocks_on_rt_mutex(lock, &waiter,
+		if (!waiter->task) {
+			ret = task_blocks_on_rt_mutex(lock, waiter, current,
 						      detect_deadlock);
 			/*
 			 * If we got woken up by the owner then start loop
 			 * all over without going into schedule to try
 			 * to get the lock now:
 			 */
-			if (unlikely(!waiter.task)) {
+			if (unlikely(!waiter->task)) {
 				/*
 				 * Reset the return value. We might
 				 * have returned with -EDEADLK and the
@@ -684,15 +674,52 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 		spin_unlock(&lock->wait_lock);
 
-		debug_rt_mutex_print_deadlock(&waiter);
+		debug_rt_mutex_print_deadlock(waiter);
 
-		if (waiter.task)
+		if (waiter->task)
 			schedule_rt_mutex(lock);
 
 		spin_lock(&lock->wait_lock);
 		set_current_state(state);
 	}
 
+	return ret;
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+		  struct hrtimer_sleeper *timeout,
+		  int detect_deadlock)
+{
+	struct rt_mutex_waiter waiter;
+	int ret = 0;
+
+	debug_rt_mutex_init_waiter(&waiter);
+	waiter.task = NULL;
+
+	spin_lock(&lock->wait_lock);
+
+	/* Try to acquire the lock again: */
+	if (try_to_take_rt_mutex(lock)) {
+		spin_unlock(&lock->wait_lock);
+		return 0;
+	}
+
+	set_current_state(state);
+
+	/* Setup the timer, when timeout != NULL */
+	if (unlikely(timeout)) {
+		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+		if (!hrtimer_active(&timeout->timer))
+			timeout->task = NULL;
+	}
+
+	ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
+				  detect_deadlock);
+
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(waiter.task))
@@ -986,6 +1013,59 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 }
 
 /**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ * @detect_deadlock:	perform deadlock detection (1) or not (0)
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+			      struct rt_mutex_waiter *waiter,
+			      struct task_struct *task, int detect_deadlock)
+{
+	int ret;
+
+	spin_lock(&lock->wait_lock);
+
+	mark_rt_mutex_waiters(lock);
+
+	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
+		/* We got the lock for task. */
+		debug_rt_mutex_lock(lock);
+
+		rt_mutex_set_owner(lock, task, 0);
+
+		rt_mutex_deadlock_account_lock(lock, task);
+		return 1;
+	}
+
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+
+
+	if (ret && !waiter->task) {
+		/*
+		 * Reset the return value. We might have
+		 * returned with -EDEADLK and the owner
+		 * released the lock while we were walking the
+		 * pi chain.  Let the waiter sort it out.
+		 */
+		ret = 0;
+	}
+	spin_unlock(&lock->wait_lock);
+
+	debug_rt_mutex_print_deadlock(waiter);
+
+	return ret;
+}
+
+/**
  * rt_mutex_next_owner - return the next owner of the lock
  *
  * @lock: the rt lock query
@@ -1004,3 +1084,57 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
 
 	return rt_mutex_top_waiter(lock)->task;
 }
+
+/**
+ * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @to:			the timeout, null if none. hrtimer should already have
+ * 			been started.
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @detect_deadlock:	perform deadlock detection (1) or not (0)
+ *
+ * Complete the lock acquisition started our behalf by another thread.
+ *
+ * Returns:
+ *  0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ *
+ * Special API call for PI-futex requeue support
+ */
+int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter,
+			       int detect_deadlock)
+{
+	int ret;
+
+	spin_lock(&lock->wait_lock);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
+				  detect_deadlock);
+
+	set_current_state(TASK_RUNNING);
+
+	if (unlikely(waiter->task))
+		remove_waiter(lock, waiter);
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	spin_unlock(&lock->wait_lock);
+
+	/*
+	 * Readjust priority, when we did not get the lock. We might have been
+	 * the pending owner and boosted. Since we did not take the lock, the
+	 * PI boost has to go.
+	 */
+	if (unlikely(ret))
+		rt_mutex_adjust_prio(current);
+
+	return ret;
+}
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index e124bf5800e..97a2f81866a 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -120,6 +120,14 @@ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task,
+				     int detect_deadlock);
+extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+				      struct hrtimer_sleeper *to,
+				      struct rt_mutex_waiter *waiter,
+				      int detect_deadlock);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/sched.c b/kernel/sched.c
index 8d43347a0c0..5b3f6ec1b0b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -73,13 +73,15 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 
 #include "sched_cpupri.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -119,12 +121,6 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
 #ifdef CONFIG_SMP
 
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -632,6 +628,10 @@ struct rq {
 	struct list_head migration_queue;
 #endif
 
+	/* calc_load related fields */
+	unsigned long calc_load_update;
+	long calc_load_active;
+
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
 	int hrtick_csd_pending;
@@ -1730,6 +1730,8 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
+static void calc_load_account_active(struct rq *this_rq);
+
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -1960,7 +1962,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	clock_offset = old_rq->clock - new_rq->clock;
 
-	trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+	trace_sched_migrate_task(p, new_cpu);
 
 #ifdef CONFIG_SCHEDSTATS
 	if (p->se.wait_start)
@@ -2021,6 +2023,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 }
 
 /*
+ * wait_task_context_switch -	wait for a thread to complete at least one
+ *				context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+	unsigned long nvcsw, nivcsw, flags;
+	int running;
+	struct rq *rq;
+
+	nvcsw	= p->nvcsw;
+	nivcsw	= p->nivcsw;
+	for (;;) {
+		/*
+		 * The runqueue is assigned before the actual context
+		 * switch. We need to take the runqueue lock.
+		 *
+		 * We could check initially without the lock but it is
+		 * very likely that we need to take the lock in every
+		 * iteration.
+		 */
+		rq = task_rq_lock(p, &flags);
+		running = task_running(rq, p);
+		task_rq_unlock(rq, &flags);
+
+		if (likely(!running))
+			break;
+		/*
+		 * The switch count is incremented before the actual
+		 * context switch. We thus wait for two switches to be
+		 * sure at least one completed.
+		 */
+		if ((p->nvcsw - nvcsw) > 1)
+			break;
+		if ((p->nivcsw - nivcsw) > 1)
+			break;
+
+		cpu_relax();
+	}
+}
+
+/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2485,6 +2530,17 @@ out:
 	return success;
 }
 
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
 int wake_up_process(struct task_struct *p)
 {
 	return try_to_wake_up(p, TASK_ALL, 0);
@@ -2795,7 +2851,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * combine the page table reload and the switch backend into
 	 * one hypercall.
 	 */
-	arch_enter_lazy_cpu_mode();
+	arch_start_context_switch(prev);
 
 	if (unlikely(!mm)) {
 		next->active_mm = oldmm;
@@ -2885,19 +2941,72 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
-unsigned long nr_active(void)
+/* Variables and functions for calc_load */
+static atomic_long_t calc_load_tasks;
+static unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun);
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
+
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
 {
-	unsigned long i, running = 0, uninterruptible = 0;
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	return load >> FSHIFT;
+}
 
-	for_each_online_cpu(i) {
-		running += cpu_rq(i)->nr_running;
-		uninterruptible += cpu_rq(i)->nr_uninterruptible;
-	}
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ */
+void calc_global_load(void)
+{
+	unsigned long upd = calc_load_update + 10;
+	long active;
 
-	if (unlikely((long)uninterruptible < 0))
-		uninterruptible = 0;
+	if (time_before(jiffies, upd))
+		return;
 
-	return running + uninterruptible;
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
+
+	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+	calc_load_update += LOAD_FREQ;
+}
+
+/*
+ * Either called from update_cpu_load() or from a cpu going idle
+ */
+static void calc_load_account_active(struct rq *this_rq)
+{
+	long nr_active, delta;
+
+	nr_active = this_rq->nr_running;
+	nr_active += (long) this_rq->nr_uninterruptible;
+
+	if (nr_active != this_rq->calc_load_active) {
+		delta = nr_active - this_rq->calc_load_active;
+		this_rq->calc_load_active = nr_active;
+		atomic_long_add(delta, &calc_load_tasks);
+	}
 }
 
 /*
@@ -2937,6 +3046,11 @@ static void update_cpu_load(struct rq *this_rq)
 			new_load += scale-1;
 		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
 	}
+
+	if (time_after_eq(jiffies, this_rq->calc_load_update)) {
+		this_rq->calc_load_update += LOAD_FREQ;
+		calc_load_account_active(this_rq);
+	}
 }
 
 #ifdef CONFIG_SMP
@@ -4278,10 +4392,126 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 static struct {
 	atomic_t load_balancer;
 	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
 } nohz ____cacheline_aligned = {
 	.load_balancer = ATOMIC_INIT(-1),
 };
 
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group:	group to be checked for semi-idleness
+ *
+ * Returns:	1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+					sched_group_cpus(ilb_group));
+
+	/*
+	 * A sched_group is semi-idle when it has atleast one busy cpu
+	 * and atleast one idle cpu.
+	 */
+	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+		return 0;
+
+	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+		return 0;
+
+	return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu:	The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns:	Returns the id of the idle load balancer if it exists,
+ *		Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+	struct sched_domain *sd;
+	struct sched_group *ilb_group;
+
+	/*
+	 * Have idle load balancer selection from semi-idle packages only
+	 * when power-aware load balancing is enabled
+	 */
+	if (!(sched_smt_power_savings || sched_mc_power_savings))
+		goto out_done;
+
+	/*
+	 * Optimize for the case when we have no idle CPUs or only one
+	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
+	 */
+	if (cpumask_weight(nohz.cpu_mask) < 2)
+		goto out_done;
+
+	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+		ilb_group = sd->groups;
+
+		do {
+			if (is_semi_idle_group(ilb_group))
+				return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+			ilb_group = ilb_group->next;
+
+		} while (ilb_group != sd->groups);
+	}
+
+out_done:
+	return cpumask_first(nohz.cpu_mask);
+}
+#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+	return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
 /*
  * This routine will try to nominate the ilb (idle load balancing)
  * owner among the cpus whose ticks are stopped. ilb owner will do the idle
@@ -4336,8 +4566,24 @@ int select_nohz_load_balancer(int stop_tick)
 			/* make me the ilb owner */
 			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
 				return 1;
-		} else if (atomic_read(&nohz.load_balancer) == cpu)
+		} else if (atomic_read(&nohz.load_balancer) == cpu) {
+			int new_ilb;
+
+			if (!(sched_smt_power_savings ||
+						sched_mc_power_savings))
+				return 1;
+			/*
+			 * Check to see if there is a more power-efficient
+			 * ilb.
+			 */
+			new_ilb = find_new_ilb(cpu);
+			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+				atomic_set(&nohz.load_balancer, -1);
+				resched_cpu(new_ilb);
+				return 0;
+			}
 			return 1;
+		}
 	} else {
 		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
 			return 0;
@@ -4506,15 +4752,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 		}
 
 		if (atomic_read(&nohz.load_balancer) == -1) {
-			/*
-			 * simple selection for now: Nominate the
-			 * first cpu in the nohz list to be the next
-			 * ilb owner.
-			 *
-			 * TBD: Traverse the sched domains and nominate
-			 * the nearest cpu in the nohz.cpu_mask.
-			 */
-			int ilb = cpumask_first(nohz.cpu_mask);
+			int ilb = find_new_ilb(cpu);
 
 			if (ilb < nr_cpu_ids)
 				resched_cpu(ilb);
@@ -5047,13 +5285,15 @@ pick_next_task(struct rq *rq)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched __schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
+need_resched:
+	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_qsctr_inc(cpu);
@@ -5111,15 +5351,9 @@ need_resched_nonpreemptible:
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
-}
 
-asmlinkage void __sched schedule(void)
-{
-need_resched:
-	preempt_disable();
-	__schedule();
 	preempt_enable_no_resched();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+	if (need_resched())
 		goto need_resched;
 }
 EXPORT_SYMBOL(schedule);
@@ -5262,7 +5496,7 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
@@ -5282,6 +5516,9 @@ void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5320,6 +5557,9 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
  * with each other. This can prevent needless bouncing between CPUs.
  *
  * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5356,6 +5596,9 @@ EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
  * awakened in the same order in which they were queued.
  *
  * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete(struct completion *x)
 {
@@ -5373,6 +5616,9 @@ EXPORT_SYMBOL(complete);
  * @x:  holds the state of this particular completion
  *
  * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete_all(struct completion *x)
 {
@@ -6531,8 +6777,9 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
-	printk(KERN_CONT "%5lu %5d %6d\n", free,
-		task_pid_nr(p), task_pid_nr(p->real_parent));
+	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent),
+		(unsigned long)task_thread_info(p)->flags);
 
 	show_stack(p, NULL);
 }
@@ -7011,6 +7258,14 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 
 	}
 }
+
+/*
+ * remove the tasks which were accounted by rq from calc_load_tasks.
+ */
+static void calc_global_load_remove(struct rq *rq)
+{
+	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+}
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -7245,6 +7500,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
+		rq->calc_load_update = calc_load_update;
+		rq->calc_load_active = 0;
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
@@ -7284,7 +7541,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		cpuset_unlock();
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
-
+		calc_global_load_remove(rq);
 		/*
 		 * No need to migrate the tasks: it was best-effort if
 		 * they didn't take sched_hotcpu_mutex. Just wake up
@@ -7796,8 +8053,9 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
 /*
  * The cpus mask in sched_group and sched_domain hangs off the end.
- * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
- * for nr_cpu_ids < CONFIG_NR_CPUS.
+ *
+ * ( See the the comments in include/linux/sched.h:struct sched_group
+ *   and struct sched_domain. )
  */
 struct static_sched_group {
 	struct sched_group sg;
@@ -7918,7 +8176,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 			struct sched_domain *sd;
 
 			sd = &per_cpu(phys_domains, j).sd;
-			if (j != cpumask_first(sched_group_cpus(sd->groups))) {
+			if (j != group_first_cpu(sd->groups)) {
 				/*
 				 * Only add "power" once for each
 				 * physical package.
@@ -7996,7 +8254,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	WARN_ON(!sd || !sd->groups);
 
-	if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
+	if (cpu != group_first_cpu(sd->groups))
 		return;
 
 	child = sd->child;
@@ -8981,6 +9239,8 @@ void __init sched_init(void)
 		rq = cpu_rq(i);
 		spin_lock_init(&rq->lock);
 		rq->nr_running = 0;
+		rq->calc_load_active = 0;
+		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs, rq);
 		init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -9088,6 +9348,9 @@ void __init sched_init(void)
 	 * when this runqueue becomes "idle".
 	 */
 	init_idle(current, smp_processor_id());
+
+	calc_load_update = jiffies + LOAD_FREQ;
+
 	/*
 	 * During early bootup we pretend to be a normal task:
 	 */
@@ -9098,6 +9361,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
 	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+	alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
 #endif
 	alloc_bootmem_cpumask_var(&cpu_isolated_map);
 #endif /* SMP */
@@ -9845,6 +10109,13 @@ static int sched_rt_global_constraints(void)
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
+	/*
+	 * There's always some RT tasks in the root group
+	 * -- migration, kstopmachine etc..
+	 */
+	if (sysctl_sched_rt_runtime == 0)
+		return -EBUSY;
+
 	spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
 	for_each_possible_cpu(i) {
 		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index cdd3c89574c..344712a5e3e 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -165,7 +165,7 @@ int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 		vec->count = 0;
 		if (bootmem)
 			alloc_bootmem_cpumask_var(&vec->mask);
-		else if (!alloc_cpumask_var(&vec->mask, GFP_KERNEL))
+		else if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
 			goto cleanup;
 	}
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3816f217f11..5f9650e8fe7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1487,17 +1487,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 
 	find_matching_se(&se, &pse);
 
-	while (se) {
-		BUG_ON(!pse);
+	BUG_ON(!pse);
 
-		if (wakeup_preempt_entity(se, pse) == 1) {
-			resched_task(curr);
-			break;
-		}
-
-		se = parent_entity(se);
-		pse = parent_entity(pse);
-	}
+	if (wakeup_preempt_entity(se, pse) == 1)
+		resched_task(curr);
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 8a21a2e28c1..499672c10cb 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -22,7 +22,8 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sy
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-
+	/* adjust the active tasks as we might go into a long sleep */
+	calc_load_account_active(rq);
 	return rq->idle;
 }
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index f2c66f8f971..9bf0d2a7304 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1591,7 +1591,7 @@ static inline void init_sched_rt_class(void)
 	unsigned int i;
 
 	for_each_possible_cpu(i)
-		alloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
+		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
 					GFP_KERNEL, cpu_to_node(i));
 }
 #endif /* CONFIG_SMP */
diff --git a/kernel/signal.c b/kernel/signal.c
index f79b3b9f837..dba6ae99978 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -27,7 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -41,8 +41,6 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
-DEFINE_TRACE(sched_signal_send);
-
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;
diff --git a/kernel/smp.c b/kernel/smp.c
index 858baac568e..ad63d850120 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -52,7 +52,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (!alloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
+		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				cpu_to_node(cpu)))
 			return NOTIFY_BAD;
 		break;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b525dd34851..258885a543d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -24,7 +24,9 @@
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
-#include <trace/irq.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq.h>
 
 #include <asm/irq.h>
 /*
@@ -186,9 +188,6 @@ EXPORT_SYMBOL(local_bh_enable_ip);
  */
 #define MAX_SOFTIRQ_RESTART 10
 
-DEFINE_TRACE(softirq_entry);
-DEFINE_TRACE(softirq_exit);
-
 asmlinkage void __do_softirq(void)
 {
 	struct softirq_action *h;
@@ -828,7 +827,7 @@ int __init __weak arch_early_irq_init(void)
 	return 0;
 }
 
-int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
+int __weak arch_init_chip_data(struct irq_desc *desc, int node)
 {
 	return 0;
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9fd4e436b69..a7e4eb0525b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -732,6 +732,14 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "bootloader_version",
+		.data		= &bootloader_version,
+		.maxlen		= sizeof (int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "kstack_depth_to_print",
 		.data		= &kstack_depth_to_print,
 		.maxlen		= sizeof(int),
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 687dff49f6e..52a8bf8931f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -22,7 +22,7 @@
 
 /*
  * This read-write spinlock protects us from races in SMP while
- * playing with xtime and avenrun.
+ * playing with xtime.
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index fed53be44fd..c01e568935e 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1124,47 +1124,6 @@ void update_process_times(int user_tick)
 }
 
 /*
- * Nr of active tasks - counted in fixed-point numbers
- */
-static unsigned long count_active_tasks(void)
-{
-	return nr_active() * FIXED_1;
-}
-
-/*
- * Hmm.. Changed this, as the GNU make sources (load.c) seems to
- * imply that avenrun[] is the standard name for this kind of thing.
- * Nothing else seems to be standardized: the fractional size etc
- * all seem to differ on different machines.
- *
- * Requires xtime_lock to access.
- */
-unsigned long avenrun[3];
-
-EXPORT_SYMBOL(avenrun);
-
-/*
- * calc_load - given tick count, update the avenrun load estimates.
- * This is called while holding a write_lock on xtime_lock.
- */
-static inline void calc_load(unsigned long ticks)
-{
-	unsigned long active_tasks; /* fixed-point */
-	static int count = LOAD_FREQ;
-
-	count -= ticks;
-	if (unlikely(count < 0)) {
-		active_tasks = count_active_tasks();
-		do {
-			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
-			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
-			CALC_LOAD(avenrun[2], EXP_15, active_tasks);
-			count += LOAD_FREQ;
-		} while (count < 0);
-	}
-}
-
-/*
  * This function runs timers and the timer-tq in bottom half context.
  */
 static void run_timer_softirq(struct softirq_action *h)
@@ -1190,16 +1149,6 @@ void run_local_timers(void)
 }
 
 /*
- * Called by the timer interrupt. xtime_lock must already be taken
- * by the timer IRQ!
- */
-static inline void update_times(unsigned long ticks)
-{
-	update_wall_time();
-	calc_load(ticks);
-}
-
-/*
  * The 64-bit jiffies value is not atomic - you MUST NOT read it
  * without sampling the sequence number in xtime_lock.
  * jiffies is defined in the linker script...
@@ -1208,7 +1157,8 @@ static inline void update_times(unsigned long ticks)
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	update_times(ticks);
+	update_wall_time();
+	calc_global_load();
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM
@@ -1409,37 +1359,17 @@ int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	unsigned long seq;
+	struct timespec tp;
 
 	memset(info, 0, sizeof(struct sysinfo));
 
-	do {
-		struct timespec tp;
-		seq = read_seqbegin(&xtime_lock);
-
-		/*
-		 * This is annoying.  The below is the same thing
-		 * posix_get_clock_monotonic() does, but it wants to
-		 * take the lock which we want to cover the loads stuff
-		 * too.
-		 */
-
-		getnstimeofday(&tp);
-		tp.tv_sec += wall_to_monotonic.tv_sec;
-		tp.tv_nsec += wall_to_monotonic.tv_nsec;
-		monotonic_to_bootbased(&tp);
-		if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
-			tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
-			tp.tv_sec++;
-		}
-		info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
+	ktime_get_ts(&tp);
+	monotonic_to_bootbased(&tp);
+	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
-		info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
+	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
 
-		info->procs = nr_threads;
-	} while (read_seqretry(&xtime_lock, seq));
+	info->procs = nr_threads;
 
 	si_meminfo(info);
 	si_swapinfo(info);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 417d1985e29..4a13e5a01ce 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -48,6 +48,21 @@ config FTRACE_NMI_ENTER
        depends on HAVE_FTRACE_NMI_ENTER
        default y
 
+config EVENT_TRACING
+	select CONTEXT_SWITCH_TRACER
+	bool
+
+config CONTEXT_SWITCH_TRACER
+	select MARKERS
+	bool
+
+# All tracer options should select GENERIC_TRACER. For those options that are
+# enabled by all tracers (context switch and event tracer) they select TRACING.
+# This allows those options to appear when no other tracer is selected. But the
+# options do not appear when something else selects it. We need the two options
+# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
+# hidding of the automatic options options.
+
 config TRACING
 	bool
 	select DEBUG_FS
@@ -56,6 +71,11 @@ config TRACING
 	select TRACEPOINTS
 	select NOP_TRACER
 	select BINARY_PRINTF
+	select EVENT_TRACING
+
+config GENERIC_TRACER
+	bool
+	select TRACING
 
 #
 # Minimum requirements an architecture has to meet for us to
@@ -73,14 +93,20 @@ config TRACING_SUPPORT
 
 if TRACING_SUPPORT
 
-menu "Tracers"
+menuconfig FTRACE
+	bool "Tracers"
+	default y if DEBUG_KERNEL
+	help
+	 Enable the kernel tracing infrastructure.
+
+if FTRACE
 
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
 	select FRAME_POINTER
 	select KALLSYMS
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  Enable the kernel to trace every kernel function. This is done
@@ -104,13 +130,14 @@ config FUNCTION_GRAPH_TRACER
 	  the return value. This is done by setting the current return 
 	  address on the current task structure into a stack of calls.
 
+
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
 	depends on GENERIC_TIME
 	select TRACE_IRQFLAGS
-	select TRACING
+	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This option measures the time spent in irqs-off critical
@@ -131,7 +158,7 @@ config PREEMPT_TRACER
 	default n
 	depends on GENERIC_TIME
 	depends on PREEMPT
-	select TRACING
+	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This option measures the time spent in preemption off critical
@@ -150,7 +177,7 @@ config PREEMPT_TRACER
 config SYSPROF_TRACER
 	bool "Sysprof Tracer"
 	depends on X86
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer provides the trace needed by the 'Sysprof' userspace
@@ -158,40 +185,33 @@ config SYSPROF_TRACER
 
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
 
-config CONTEXT_SWITCH_TRACER
-	bool "Trace process context switches"
-	select TRACING
-	select MARKERS
-	help
-	  This tracer gets called from the context switch and records
-	  all switching of tasks.
-
-config EVENT_TRACER
-	bool "Trace various events in the kernel"
+config ENABLE_DEFAULT_TRACERS
+	bool "Trace process context switches and events"
+	depends on !GENERIC_TRACER
 	select TRACING
 	help
 	  This tracer hooks to various trace points in the kernel
 	  allowing the user to pick and choose which trace point they
-	  want to trace.
+	  want to trace. It also includes the sched_switch tracer plugin.
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
 	depends on HAVE_FTRACE_SYSCALLS
-	select TRACING
+	select GENERIC_TRACER
 	select KALLSYMS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
 config BOOT_TRACER
 	bool "Trace boot initcalls"
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer helps developers to optimize boot times: it records
@@ -207,8 +227,36 @@ config BOOT_TRACER
 	  to enable this on bootup.
 
 config TRACE_BRANCH_PROFILING
+	bool
+	select GENERIC_TRACER
+
+choice
+	prompt "Branch Profiling"
+	default BRANCH_PROFILE_NONE
+	help
+	 The branch profiling is a software profiler. It will add hooks
+	 into the C conditionals to test which path a branch takes.
+
+	 The likely/unlikely profiler only looks at the conditions that
+	 are annotated with a likely or unlikely macro.
+
+	 The "all branch" profiler will profile every if statement in the
+	 kernel. This profiler will also enable the likely/unlikely
+	 profiler as well.
+
+	 Either of the above profilers add a bit of overhead to the system.
+	 If unsure choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+	bool "No branch profiling"
+	help
+	 No branch profiling. Branch profiling adds a bit of overhead.
+	 Only enable it if you want to analyse the branching behavior.
+	 Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
 	bool "Trace likely/unlikely profiler"
-	select TRACING
+	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all the the likely and unlikely macros
 	  in the kernel. It will display the results in:
@@ -218,11 +266,9 @@ config TRACE_BRANCH_PROFILING
 	  Note: this will add a significant overhead, only turn this
 	  on if you need to profile the system's use of these macros.
 
-	  Say N if unsure.
-
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals"
-	depends on TRACE_BRANCH_PROFILING
+	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
@@ -230,11 +276,12 @@ config PROFILE_ALL_BRANCHES
 
 	  /debugfs/tracing/profile_branch
 
+	  This option also enables the likely/unlikely profiler.
+
 	  This configuration, when enabled, will impose a great overhead
 	  on the system. This should only be enabled when the system
 	  is to be analyzed
-
-	  Say N if unsure.
+endchoice
 
 config TRACING_BRANCHES
 	bool
@@ -261,7 +308,7 @@ config BRANCH_TRACER
 config POWER_TRACER
 	bool "Trace power consumption behavior"
 	depends on X86
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  This tracer helps developers to analyze and optimize the kernels
 	  power management decisions, specifically the C-state and P-state
@@ -295,14 +342,14 @@ config STACK_TRACER
 config HW_BRANCH_TRACER
 	depends on HAVE_HW_BRANCH_TRACER
 	bool "Trace hw branches"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  This tracer records all branches on the system in a circular
 	  buffer giving access to the last N branches for each cpu.
 
 config KMEMTRACE
 	bool "Trace SLAB allocations"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  kmemtrace provides tracing for slab allocator functions, such as
 	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
@@ -322,7 +369,7 @@ config KMEMTRACE
 
 config WORKQUEUE_TRACER
 	bool "Trace workqueues"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  The workqueue tracer provides some statistical informations
           about each cpu workqueue thread such as the number of the
@@ -338,7 +385,7 @@ config BLK_DEV_IO_TRACE
 	select RELAY
 	select DEBUG_FS
 	select TRACEPOINTS
-	select TRACING
+	select GENERIC_TRACER
 	select STACKTRACE
 	help
 	  Say Y here if you want to be able to trace the block layer actions
@@ -375,6 +422,20 @@ config DYNAMIC_FTRACE
 	 were made. If so, it runs stop_machine (stops all CPUS)
 	 and modifies the code to jump over the call to ftrace.
 
+config FUNCTION_PROFILER
+	bool "Kernel function profiler"
+	depends on FUNCTION_TRACER
+	default n
+	help
+	 This option enables the kernel function profiler. A file is created
+	 in debugfs called function_profile_enabled which defaults to zero.
+	 When a 1 is echoed into this file profiling begins, and when a
+	 zero is entered, profiling stops. A file in the trace_stats
+	 directory called functions, that show the list of functions that
+	 have been hit and their counters.
+
+	 If in doubt, say N
+
 config FTRACE_MCOUNT_RECORD
 	def_bool y
 	depends on DYNAMIC_FTRACE
@@ -385,7 +446,7 @@ config FTRACE_SELFTEST
 
 config FTRACE_STARTUP_TEST
 	bool "Perform a startup test on ftrace"
-	depends on TRACING
+	depends on GENERIC_TRACER
 	select FTRACE_SELFTEST
 	help
 	  This option performs a series of startup tests on ftrace. On bootup
@@ -396,7 +457,7 @@ config FTRACE_STARTUP_TEST
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on HAVE_MMIOTRACE_SUPPORT && PCI
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
 	  debugging and reverse engineering. It is called from the ioremap
@@ -416,7 +477,23 @@ config MMIOTRACE_TEST
 
 	  Say N, unless you absolutely know what you are doing.
 
-endmenu
+config RING_BUFFER_BENCHMARK
+	tristate "Ring buffer benchmark stress tester"
+	depends on RING_BUFFER
+	help
+	  This option creates a test to stress the ring buffer and bench mark it.
+	  It creates its own ring buffer such that it will not interfer with
+	  any other users of the ring buffer (such as ftrace). It then creates
+	  a producer and consumer that will run for 10 seconds and sleep for
+	  10 seconds. Each interval it will print out the number of events
+	  it recorded and give a rough estimate of how long each iteration took.
+
+	  It does not disable interrupts or raise its priority, so it may be
+	  affected by processes that are running.
+
+	  If unsure, say N
+
+endif # FTRACE
 
 endif # TRACING_SUPPORT
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 2630f5121ec..844164dca90 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -15,11 +15,17 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+#
+# Make the trace clocks available generally: it's infrastructure
+# relied on by ptrace for example:
+#
+obj-y += trace_clock.o
+
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
 
 obj-$(CONFIG_TRACING) += trace.o
-obj-$(CONFIG_TRACING) += trace_clock.o
 obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
@@ -39,12 +45,14 @@ obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events.o
-obj-$(CONFIG_EVENT_TRACER) += events.o
-obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 921ef5d1f0b..7bd6a9893c2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,10 +23,14 @@
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
 #include <linux/time.h>
-#include <trace/block.h>
 #include <linux/uaccess.h>
+
+#include <trace/events/block.h>
+
 #include "trace_output.h"
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+
 static unsigned int blktrace_seq __read_mostly = 1;
 
 static struct trace_array *blk_tr;
@@ -147,7 +151,7 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 {
 	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
 		return 1;
-	if (sector < bt->start_lba || sector > bt->end_lba)
+	if (sector && (sector < bt->start_lba || sector > bt->end_lba))
 		return 1;
 	if (bt->pid && pid != bt->pid)
 		return 1;
@@ -192,7 +196,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(rw, DISCARD);
 
 	pid = tsk->pid;
-	if (unlikely(act_log_check(bt, what, sector, pid)))
+	if (act_log_check(bt, what, sector, pid))
 		return;
 	cpu = raw_smp_processor_id();
 
@@ -262,6 +266,7 @@ static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
+	debugfs_remove(bt->dir);
 	relay_close(bt->rchan);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
@@ -403,11 +408,29 @@ static struct rchan_callbacks blk_relay_callbacks = {
 	.remove_buf_file	= blk_remove_buf_file_callback,
 };
 
+static void blk_trace_setup_lba(struct blk_trace *bt,
+				struct block_device *bdev)
+{
+	struct hd_struct *part = NULL;
+
+	if (bdev)
+		part = bdev->bd_part;
+
+	if (part) {
+		bt->start_lba = part->start_sect;
+		bt->end_lba = part->start_sect + part->nr_sects;
+	} else {
+		bt->start_lba = 0;
+		bt->end_lba = -1ULL;
+	}
+}
+
 /*
  * Setup everything required to start tracing
  */
 int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-			struct blk_user_trace_setup *buts)
+		       struct block_device *bdev,
+		       struct blk_user_trace_setup *buts)
 {
 	struct blk_trace *old_bt, *bt = NULL;
 	struct dentry *dir = NULL;
@@ -480,10 +503,13 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->act_mask)
 		bt->act_mask = (u16) -1;
 
-	bt->start_lba = buts->start_lba;
-	bt->end_lba = buts->end_lba;
-	if (!bt->end_lba)
-		bt->end_lba = -1ULL;
+	blk_trace_setup_lba(bt, bdev);
+
+	/* overwrite with user settings */
+	if (buts->start_lba)
+		bt->start_lba = buts->start_lba;
+	if (buts->end_lba)
+		bt->end_lba = buts->end_lba;
 
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
@@ -505,6 +531,7 @@ err:
 }
 
 int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+		    struct block_device *bdev,
 		    char __user *arg)
 {
 	struct blk_user_trace_setup buts;
@@ -514,7 +541,7 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (ret)
 		return -EFAULT;
 
-	ret = do_blk_trace_setup(q, name, dev, &buts);
+	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
 	if (ret)
 		return ret;
 
@@ -582,7 +609,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	switch (cmd) {
 	case BLKTRACESETUP:
 		bdevname(bdev, b);
-		ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
+		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 	case BLKTRACESTART:
 		start = 1;
@@ -809,7 +836,6 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  * @bio:	the source bio
  * @dev:	target device
  * @from:	source sector
- * @to:		target sector
  *
  * Description:
  *     Device mapper or raid target sometimes need to split a bio because
@@ -817,7 +843,7 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  *
  **/
 static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
-				       dev_t dev, sector_t from, sector_t to)
+				       dev_t dev, sector_t from)
 {
 	struct blk_trace *bt = q->blk_trace;
 	struct blk_io_trace_remap r;
@@ -825,12 +851,13 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 	if (likely(!bt))
 		return;
 
-	r.device = cpu_to_be32(dev);
-	r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
-	r.sector = cpu_to_be64(to);
+	r.device_from = cpu_to_be32(dev);
+	r.device_to   = cpu_to_be32(bio->bi_bdev->bd_dev);
+	r.sector_from = cpu_to_be64(from);
 
-	__blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
-			!bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+	__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+			BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
+			sizeof(r), &r);
 }
 
 /**
@@ -971,6 +998,16 @@ static inline const void *pdu_start(const struct trace_entry *ent)
 	return te_blk_io_trace(ent) + 1;
 }
 
+static inline u32 t_action(const struct trace_entry *ent)
+{
+	return te_blk_io_trace(ent)->action;
+}
+
+static inline u32 t_bytes(const struct trace_entry *ent)
+{
+	return te_blk_io_trace(ent)->bytes;
+}
+
 static inline u32 t_sec(const struct trace_entry *ent)
 {
 	return te_blk_io_trace(ent)->bytes >> 9;
@@ -996,11 +1033,11 @@ static void get_pdu_remap(const struct trace_entry *ent,
 			  struct blk_io_trace_remap *r)
 {
 	const struct blk_io_trace_remap *__r = pdu_start(ent);
-	__u64 sector = __r->sector;
+	__u64 sector_from = __r->sector_from;
 
-	r->device = be32_to_cpu(__r->device);
 	r->device_from = be32_to_cpu(__r->device_from);
-	r->sector = be64_to_cpu(sector);
+	r->device_to   = be32_to_cpu(__r->device_to);
+	r->sector_from = be64_to_cpu(sector_from);
 }
 
 typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
@@ -1031,36 +1068,98 @@ static int blk_log_action(struct trace_iterator *iter, const char *act)
 				MAJOR(t->device), MINOR(t->device), act, rwbs);
 }
 
+static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+{
+	const unsigned char *pdu_buf;
+	int pdu_len;
+	int i, end, ret;
+
+	pdu_buf = pdu_start(ent);
+	pdu_len = te_blk_io_trace(ent)->pdu_len;
+
+	if (!pdu_len)
+		return 1;
+
+	/* find the last zero that needs to be printed */
+	for (end = pdu_len - 1; end >= 0; end--)
+		if (pdu_buf[end])
+			break;
+	end++;
+
+	if (!trace_seq_putc(s, '('))
+		return 0;
+
+	for (i = 0; i < pdu_len; i++) {
+
+		ret = trace_seq_printf(s, "%s%02x",
+				       i == 0 ? "" : " ", pdu_buf[i]);
+		if (!ret)
+			return ret;
+
+		/*
+		 * stop when the rest is just zeroes and indicate so
+		 * with a ".." appended
+		 */
+		if (i == end && end != pdu_len - 1)
+			return trace_seq_puts(s, " ..) ");
+	}
+
+	return trace_seq_puts(s, ") ");
+}
+
 static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
 {
 	char cmd[TASK_COMM_LEN];
 
 	trace_find_cmdline(ent->pid, cmd);
 
-	if (t_sec(ent))
-		return trace_seq_printf(s, "%llu + %u [%s]\n",
-					t_sector(ent), t_sec(ent), cmd);
-	return trace_seq_printf(s, "[%s]\n", cmd);
+	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+		int ret;
+
+		ret = trace_seq_printf(s, "%u ", t_bytes(ent));
+		if (!ret)
+			return 0;
+		ret = blk_log_dump_pdu(s, ent);
+		if (!ret)
+			return 0;
+		return trace_seq_printf(s, "[%s]\n", cmd);
+	} else {
+		if (t_sec(ent))
+			return trace_seq_printf(s, "%llu + %u [%s]\n",
+						t_sector(ent), t_sec(ent), cmd);
+		return trace_seq_printf(s, "[%s]\n", cmd);
+	}
 }
 
 static int blk_log_with_error(struct trace_seq *s,
 			      const struct trace_entry *ent)
 {
-	if (t_sec(ent))
-		return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent),
-					t_sec(ent), t_error(ent));
-	return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent));
+	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+		int ret;
+
+		ret = blk_log_dump_pdu(s, ent);
+		if (ret)
+			return trace_seq_printf(s, "[%d]\n", t_error(ent));
+		return 0;
+	} else {
+		if (t_sec(ent))
+			return trace_seq_printf(s, "%llu + %u [%d]\n",
+						t_sector(ent),
+						t_sec(ent), t_error(ent));
+		return trace_seq_printf(s, "%llu [%d]\n",
+					t_sector(ent), t_error(ent));
+	}
 }
 
 static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
 {
-	struct blk_io_trace_remap r = { .device = 0, };
+	struct blk_io_trace_remap r = { .device_from = 0, };
 
 	get_pdu_remap(ent, &r);
 	return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
-			       t_sector(ent),
-			       t_sec(ent), MAJOR(r.device), MINOR(r.device),
-			       (unsigned long long)r.sector);
+				t_sector(ent), t_sec(ent),
+				MAJOR(r.device_from), MINOR(r.device_from),
+				(unsigned long long)r.sector_from);
 }
 
 static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
@@ -1117,7 +1216,6 @@ static void blk_tracer_print_header(struct seq_file *m)
 static void blk_tracer_start(struct trace_array *tr)
 {
 	blk_tracer_enabled = true;
-	trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
 }
 
 static int blk_tracer_init(struct trace_array *tr)
@@ -1130,7 +1228,6 @@ static int blk_tracer_init(struct trace_array *tr)
 static void blk_tracer_stop(struct trace_array *tr)
 {
 	blk_tracer_enabled = false;
-	trace_flags |= TRACE_ITER_CONTEXT_INFO;
 }
 
 static void blk_tracer_reset(struct trace_array *tr)
@@ -1182,7 +1279,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 	}
 
 	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
-		ret = trace_seq_printf(s, "Bad pc action %x\n", what);
+		ret = trace_seq_printf(s, "Unknown action %x\n", what);
 	else {
 		ret = log_action(iter, what2act[what].act[long_act]);
 		if (ret)
@@ -1195,9 +1292,6 @@ out:
 static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
 					       int flags)
 {
-	if (!trace_print_context(iter))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return print_one_line(iter, false);
 }
 
@@ -1232,6 +1326,18 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 	return print_one_line(iter, true);
 }
 
+static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+{
+	/* don't output context-info for blk_classic output */
+	if (bit == TRACE_BLK_OPT_CLASSIC) {
+		if (set)
+			trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+		else
+			trace_flags |= TRACE_ITER_CONTEXT_INFO;
+	}
+	return 0;
+}
+
 static struct tracer blk_tracer __read_mostly = {
 	.name		= "blk",
 	.init		= blk_tracer_init,
@@ -1241,6 +1347,7 @@ static struct tracer blk_tracer __read_mostly = {
 	.print_header	= blk_tracer_print_header,
 	.print_line	= blk_tracer_print_line,
 	.flags		= &blk_tracer_flags,
+	.set_flag	= blk_tracer_set_flag,
 };
 
 static struct trace_event trace_blk_event = {
@@ -1285,7 +1392,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
 /*
  * Setup everything required to start tracing
  */
-static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
+static int blk_trace_setup_queue(struct request_queue *q,
+				 struct block_device *bdev)
 {
 	struct blk_trace *old_bt, *bt = NULL;
 	int ret = -ENOMEM;
@@ -1298,9 +1406,10 @@ static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
 	if (!bt->msg_data)
 		goto free_bt;
 
-	bt->dev = dev;
+	bt->dev = bdev->bd_dev;
 	bt->act_mask = (u16)-1;
-	bt->end_lba = -1ULL;
+
+	blk_trace_setup_lba(bt, bdev);
 
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt != NULL) {
@@ -1517,7 +1626,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	if (attr == &dev_attr_enable) {
 		if (value)
-			ret = blk_trace_setup_queue(q, bdev->bd_dev);
+			ret = blk_trace_setup_queue(q, bdev);
 		else
 			ret = blk_trace_remove_queue(q);
 		goto out_unlock_bdev;
@@ -1525,7 +1634,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	ret = 0;
 	if (q->blk_trace == NULL)
-		ret = blk_trace_setup_queue(q, bdev->bd_dev);
+		ret = blk_trace_setup_queue(q, bdev);
 
 	if (ret == 0) {
 		if (attr == &dev_attr_act_mask)
@@ -1548,3 +1657,80 @@ out:
 	return ret ? ret : count;
 }
 
+int blk_trace_init_sysfs(struct device *dev)
+{
+	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
+}
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#ifdef CONFIG_EVENT_TRACING
+
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+	int i, end;
+	int len = rq->cmd_len;
+	unsigned char *cmd = rq->cmd;
+
+	if (!blk_pc_request(rq)) {
+		buf[0] = '\0';
+		return;
+	}
+
+	for (end = len - 1; end >= 0; end--)
+		if (cmd[end])
+			break;
+	end++;
+
+	for (i = 0; i < len; i++) {
+		buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
+		if (i == end && end != len - 1) {
+			sprintf(buf, " ..");
+			break;
+		}
+	}
+}
+
+void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+{
+	int i = 0;
+
+	if (rw & WRITE)
+		rwbs[i++] = 'W';
+	else if (rw & 1 << BIO_RW_DISCARD)
+		rwbs[i++] = 'D';
+	else if (bytes)
+		rwbs[i++] = 'R';
+	else
+		rwbs[i++] = 'N';
+
+	if (rw & 1 << BIO_RW_AHEAD)
+		rwbs[i++] = 'A';
+	if (rw & 1 << BIO_RW_BARRIER)
+		rwbs[i++] = 'B';
+	if (rw & 1 << BIO_RW_SYNCIO)
+		rwbs[i++] = 'S';
+	if (rw & 1 << BIO_RW_META)
+		rwbs[i++] = 'M';
+
+	rwbs[i] = '\0';
+}
+
+void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
+{
+	int rw = rq->cmd_flags & 0x03;
+	int bytes;
+
+	if (blk_discard_rq(rq))
+		rw |= (1 << BIO_RW_DISCARD);
+
+	if (blk_pc_request(rq))
+		bytes = rq->data_len;
+	else
+		bytes = rq->hard_nr_sectors << 9;
+
+	blk_fill_rwbs(rwbs, rw, bytes);
+}
+
+#endif /* CONFIG_EVENT_TRACING */
+
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
deleted file mode 100644
index 246f2aa6dc4..00000000000
--- a/kernel/trace/events.c
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * This is the place to register all trace points as events.
- */
-
-#include <linux/stringify.h>
-
-#include <trace/trace_events.h>
-
-#include "trace_output.h"
-
-#include "trace_events_stage_1.h"
-#include "trace_events_stage_2.h"
-#include "trace_events_stage_3.h"
-
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f1ed080406c..bb60732ade0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -29,11 +29,13 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include <asm/ftrace.h>
+#include <asm/setup.h>
 
-#include "trace.h"
+#include "trace_output.h"
+#include "trace_stat.h"
 
 #define FTRACE_WARN_ON(cond)			\
 	do {					\
@@ -68,7 +70,7 @@ static DEFINE_MUTEX(ftrace_lock);
 
 static struct ftrace_ops ftrace_list_end __read_mostly =
 {
-	.func = ftrace_stub,
+	.func		= ftrace_stub,
 };
 
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
@@ -240,6 +242,580 @@ static void ftrace_update_pid_func(void)
 #endif
 }
 
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+	struct hlist_node		node;
+	unsigned long			ip;
+	unsigned long			counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	unsigned long long		time;
+#endif
+};
+
+struct ftrace_profile_page {
+	struct ftrace_profile_page	*next;
+	unsigned long			index;
+	struct ftrace_profile		records[];
+};
+
+struct ftrace_profile_stat {
+	atomic_t			disabled;
+	struct hlist_head		*hash;
+	struct ftrace_profile_page	*pages;
+	struct ftrace_profile_page	*start;
+	struct tracer_stat		stat;
+};
+
+#define PROFILE_RECORDS_SIZE						\
+	(PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE					\
+	(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+	struct ftrace_profile *rec = v;
+	struct ftrace_profile_page *pg;
+
+	pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+	rec++;
+	if ((void *)rec >= (void *)&pg->records[pg->index]) {
+		pg = pg->next;
+		if (!pg)
+			return NULL;
+		rec = &pg->records[0];
+		if (!rec->counter)
+			goto again;
+	}
+
+	return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+	struct ftrace_profile_stat *stat =
+		container_of(trace, struct ftrace_profile_stat, stat);
+
+	if (!stat || !stat->start)
+		return NULL;
+
+	return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_profile *a = p1;
+	struct ftrace_profile *b = p2;
+
+	if (a->time < b->time)
+		return -1;
+	if (a->time > b->time)
+		return 1;
+	else
+		return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_profile *a = p1;
+	struct ftrace_profile *b = p2;
+
+	if (a->counter < b->counter)
+		return -1;
+	if (a->counter > b->counter)
+		return 1;
+	else
+		return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	seq_printf(m, "  Function                               "
+		   "Hit    Time            Avg\n"
+		      "  --------                               "
+		   "---    ----            ---\n");
+#else
+	seq_printf(m, "  Function                               Hit\n"
+		      "  --------                               ---\n");
+#endif
+	return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+	struct ftrace_profile *rec = v;
+	char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	static DEFINE_MUTEX(mutex);
+	static struct trace_seq s;
+	unsigned long long avg;
+#endif
+
+	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+	seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	seq_printf(m, "    ");
+	avg = rec->time;
+	do_div(avg, rec->counter);
+
+	mutex_lock(&mutex);
+	trace_seq_init(&s);
+	trace_print_graph_duration(rec->time, &s);
+	trace_seq_puts(&s, "    ");
+	trace_print_graph_duration(avg, &s);
+	trace_print_seq(m, &s);
+	mutex_unlock(&mutex);
+#endif
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+	struct ftrace_profile_page *pg;
+
+	pg = stat->pages = stat->start;
+
+	while (pg) {
+		memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+		pg->index = 0;
+		pg = pg->next;
+	}
+
+	memset(stat->hash, 0,
+	       FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+	struct ftrace_profile_page *pg;
+	int functions;
+	int pages;
+	int i;
+
+	/* If we already allocated, do nothing */
+	if (stat->pages)
+		return 0;
+
+	stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!stat->pages)
+		return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	functions = ftrace_update_tot_cnt;
+#else
+	/*
+	 * We do not know the number of functions that exist because
+	 * dynamic tracing is what counts them. With past experience
+	 * we have around 20K functions. That should be more than enough.
+	 * It is highly unlikely we will execute every function in
+	 * the kernel.
+	 */
+	functions = 20000;
+#endif
+
+	pg = stat->start = stat->pages;
+
+	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+	for (i = 0; i < pages; i++) {
+		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pg->next)
+			goto out_free;
+		pg = pg->next;
+	}
+
+	return 0;
+
+ out_free:
+	pg = stat->start;
+	while (pg) {
+		unsigned long tmp = (unsigned long)pg;
+
+		pg = pg->next;
+		free_page(tmp);
+	}
+
+	free_page((unsigned long)stat->pages);
+	stat->pages = NULL;
+	stat->start = NULL;
+
+	return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+	struct ftrace_profile_stat *stat;
+	int size;
+
+	stat = &per_cpu(ftrace_profile_stats, cpu);
+
+	if (stat->hash) {
+		/* If the profile is already created, simply reset it */
+		ftrace_profile_reset(stat);
+		return 0;
+	}
+
+	/*
+	 * We are profiling all functions, but usually only a few thousand
+	 * functions are hit. We'll make a hash of 1024 items.
+	 */
+	size = FTRACE_PROFILE_HASH_SIZE;
+
+	stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+	if (!stat->hash)
+		return -ENOMEM;
+
+	if (!ftrace_profile_bits) {
+		size--;
+
+		for (; size; size >>= 1)
+			ftrace_profile_bits++;
+	}
+
+	/* Preallocate the function profiling pages */
+	if (ftrace_profile_pages_init(stat) < 0) {
+		kfree(stat->hash);
+		stat->hash = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+	int cpu;
+	int ret = 0;
+
+	for_each_online_cpu(cpu) {
+		ret = ftrace_profile_init_cpu(cpu);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+	struct ftrace_profile *rec;
+	struct hlist_head *hhd;
+	struct hlist_node *n;
+	unsigned long key;
+
+	key = hash_long(ip, ftrace_profile_bits);
+	hhd = &stat->hash[key];
+
+	if (hlist_empty(hhd))
+		return NULL;
+
+	hlist_for_each_entry_rcu(rec, n, hhd, node) {
+		if (rec->ip == ip)
+			return rec;
+	}
+
+	return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+			       struct ftrace_profile *rec)
+{
+	unsigned long key;
+
+	key = hash_long(rec->ip, ftrace_profile_bits);
+	hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+	struct ftrace_profile *rec = NULL;
+
+	/* prevent recursion (from NMIs) */
+	if (atomic_inc_return(&stat->disabled) != 1)
+		goto out;
+
+	/*
+	 * Try to find the function again since an NMI
+	 * could have added it
+	 */
+	rec = ftrace_find_profiled_func(stat, ip);
+	if (rec)
+		goto out;
+
+	if (stat->pages->index == PROFILES_PER_PAGE) {
+		if (!stat->pages->next)
+			goto out;
+		stat->pages = stat->pages->next;
+	}
+
+	rec = &stat->pages->records[stat->pages->index++];
+	rec->ip = ip;
+	ftrace_add_profile(stat, rec);
+
+ out:
+	atomic_dec(&stat->disabled);
+
+	return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_profile_stat *stat;
+	struct ftrace_profile *rec;
+	unsigned long flags;
+
+	if (!ftrace_profile_enabled)
+		return;
+
+	local_irq_save(flags);
+
+	stat = &__get_cpu_var(ftrace_profile_stats);
+	if (!stat->hash || !ftrace_profile_enabled)
+		goto out;
+
+	rec = ftrace_find_profiled_func(stat, ip);
+	if (!rec) {
+		rec = ftrace_profile_alloc(stat, ip);
+		if (!rec)
+			goto out;
+	}
+
+	rec->counter++;
+ out:
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+	function_profile_call(trace->func, 0);
+	return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct ftrace_profile_stat *stat;
+	unsigned long long calltime;
+	struct ftrace_profile *rec;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	stat = &__get_cpu_var(ftrace_profile_stats);
+	if (!stat->hash || !ftrace_profile_enabled)
+		goto out;
+
+	calltime = trace->rettime - trace->calltime;
+
+	if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+		int index;
+
+		index = trace->depth;
+
+		/* Append this call time to the parent time to subtract */
+		if (index)
+			current->ret_stack[index - 1].subtime += calltime;
+
+		if (current->ret_stack[index].subtime < calltime)
+			calltime -= current->ret_stack[index].subtime;
+		else
+			calltime = 0;
+	}
+
+	rec = ftrace_find_profiled_func(stat, trace->func);
+	if (rec)
+		rec->time += calltime;
+
+ out:
+	local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+	return register_ftrace_graph(&profile_graph_return,
+				     &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+	unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+	.func		= function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+	return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+	unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	char buf[64];		/* big enough to hold a number */
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	val = !!val;
+
+	mutex_lock(&ftrace_profile_lock);
+	if (ftrace_profile_enabled ^ val) {
+		if (val) {
+			ret = ftrace_profile_init();
+			if (ret < 0) {
+				cnt = ret;
+				goto out;
+			}
+
+			ret = register_ftrace_profiler();
+			if (ret < 0) {
+				cnt = ret;
+				goto out;
+			}
+			ftrace_profile_enabled = 1;
+		} else {
+			ftrace_profile_enabled = 0;
+			/*
+			 * unregister_ftrace_profiler calls stop_machine
+			 * so this acts like an synchronize_sched.
+			 */
+			unregister_ftrace_profiler();
+		}
+	}
+ out:
+	mutex_unlock(&ftrace_profile_lock);
+
+	filp->f_pos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	char buf[64];		/* big enough to hold a number */
+	int r;
+
+	r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+	.open		= tracing_open_generic,
+	.read		= ftrace_profile_read,
+	.write		= ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+	.name		= "functions",
+	.stat_start	= function_stat_start,
+	.stat_next	= function_stat_next,
+	.stat_cmp	= function_stat_cmp,
+	.stat_headers	= function_stat_headers,
+	.stat_show	= function_stat_show
+};
+
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+	struct ftrace_profile_stat *stat;
+	struct dentry *entry;
+	char *name;
+	int ret;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		stat = &per_cpu(ftrace_profile_stats, cpu);
+
+		/* allocate enough for function name + cpu number */
+		name = kmalloc(32, GFP_KERNEL);
+		if (!name) {
+			/*
+			 * The files created are permanent, if something happens
+			 * we still do not free memory.
+			 */
+			kfree(stat);
+			WARN(1,
+			     "Could not allocate stat file for cpu %d\n",
+			     cpu);
+			return;
+		}
+		stat->stat = function_stats;
+		snprintf(name, 32, "function%d", cpu);
+		stat->stat.name = name;
+		ret = register_stat_tracer(&stat->stat);
+		if (ret) {
+			WARN(1,
+			     "Could not register function stat for cpu %d\n",
+			     cpu);
+			kfree(name);
+			return;
+		}
+	}
+
+	entry = debugfs_create_file("function_profile_enabled", 0644,
+				    d_tracer, NULL, &ftrace_profile_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
 /* set when tracing only a pid */
 struct pid *ftrace_pid_trace;
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
@@ -261,7 +837,6 @@ struct ftrace_func_probe {
 	struct rcu_head		rcu;
 };
 
-
 enum {
 	FTRACE_ENABLE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
@@ -346,30 +921,6 @@ static void ftrace_free_rec(struct dyn_ftrace *rec)
 	rec->flags |= FTRACE_FL_FREE;
 }
 
-void ftrace_release(void *start, unsigned long size)
-{
-	struct dyn_ftrace *rec;
-	struct ftrace_page *pg;
-	unsigned long s = (unsigned long)start;
-	unsigned long e = s + size;
-
-	if (ftrace_disabled || !start)
-		return;
-
-	mutex_lock(&ftrace_lock);
-	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e)) {
-			/*
-			 * rec->ip is changed in ftrace_free_rec()
-			 * It should not between s and e if record was freed.
-			 */
-			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
-			ftrace_free_rec(rec);
-		}
-	} while_for_each_ftrace_rec();
-	mutex_unlock(&ftrace_lock);
-}
-
 static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
@@ -1408,7 +1959,7 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
 {
-	.func = function_trace_probe_call,
+	.func		= function_trace_probe_call,
 };
 
 static int ftrace_probe_registered;
@@ -1823,6 +2374,45 @@ void ftrace_set_notrace(unsigned char *buf, int len, int reset)
 	ftrace_set_regex(buf, len, reset, 0);
 }
 
+/*
+ * command line interface to allow users to set filters on boot up.
+ */
+#define FTRACE_FILTER_SIZE		COMMAND_LINE_SIZE
+static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
+
+static int __init set_ftrace_notrace(char *str)
+{
+	strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_notrace=", set_ftrace_notrace);
+
+static int __init set_ftrace_filter(char *str)
+{
+	strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_filter=", set_ftrace_filter);
+
+static void __init set_ftrace_early_filter(char *buf, int enable)
+{
+	char *func;
+
+	while (buf) {
+		func = strsep(&buf, ",");
+		ftrace_set_regex(func, strlen(func), 0, enable);
+	}
+}
+
+static void __init set_ftrace_early_filters(void)
+{
+	if (ftrace_filter_buf[0])
+		set_ftrace_early_filter(ftrace_filter_buf, 1);
+	if (ftrace_notrace_buf[0])
+		set_ftrace_early_filter(ftrace_notrace_buf, 0);
+}
+
 static int
 ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 {
@@ -2128,38 +2718,23 @@ static const struct file_operations ftrace_graph_fops = {
 
 static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 {
-	struct dentry *entry;
 
-	entry = debugfs_create_file("available_filter_functions", 0444,
-				    d_tracer, NULL, &ftrace_avail_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'available_filter_functions' entry\n");
+	trace_create_file("available_filter_functions", 0444,
+			d_tracer, NULL, &ftrace_avail_fops);
 
-	entry = debugfs_create_file("failures", 0444,
-				    d_tracer, NULL, &ftrace_failures_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'failures' entry\n");
+	trace_create_file("failures", 0444,
+			d_tracer, NULL, &ftrace_failures_fops);
 
-	entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
-				    NULL, &ftrace_filter_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_filter' entry\n");
+	trace_create_file("set_ftrace_filter", 0644, d_tracer,
+			NULL, &ftrace_filter_fops);
 
-	entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer,
+	trace_create_file("set_ftrace_notrace", 0644, d_tracer,
 				    NULL, &ftrace_notrace_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_notrace' entry\n");
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	entry = debugfs_create_file("set_graph_function", 0444, d_tracer,
+	trace_create_file("set_graph_function", 0444, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_graph_function' entry\n");
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 	return 0;
@@ -2197,14 +2772,72 @@ static int ftrace_convert_nops(struct module *mod,
 	return 0;
 }
 
-void ftrace_init_module(struct module *mod,
-			unsigned long *start, unsigned long *end)
+#ifdef CONFIG_MODULES
+void ftrace_release(void *start, void *end)
+{
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+	unsigned long s = (unsigned long)start;
+	unsigned long e = (unsigned long)end;
+
+	if (ftrace_disabled || !start || start == end)
+		return;
+
+	mutex_lock(&ftrace_lock);
+	do_for_each_ftrace_rec(pg, rec) {
+		if ((rec->ip >= s) && (rec->ip < e)) {
+			/*
+			 * rec->ip is changed in ftrace_free_rec()
+			 * It should not between s and e if record was freed.
+			 */
+			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
+			ftrace_free_rec(rec);
+		}
+	} while_for_each_ftrace_rec();
+	mutex_unlock(&ftrace_lock);
+}
+
+static void ftrace_init_module(struct module *mod,
+			       unsigned long *start, unsigned long *end)
 {
 	if (ftrace_disabled || start == end)
 		return;
 	ftrace_convert_nops(mod, start, end);
 }
 
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ftrace_init_module(mod, mod->ftrace_callsites,
+				   mod->ftrace_callsites +
+				   mod->num_ftrace_callsites);
+		break;
+	case MODULE_STATE_GOING:
+		ftrace_release(mod->ftrace_callsites,
+			       mod->ftrace_callsites +
+			       mod->num_ftrace_callsites);
+		break;
+	}
+
+	return 0;
+}
+#else
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block ftrace_module_nb = {
+	.notifier_call = ftrace_module_notify,
+	.priority = 0,
+};
+
 extern unsigned long __start_mcount_loc[];
 extern unsigned long __stop_mcount_loc[];
 
@@ -2236,6 +2869,12 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
+	ret = register_module_notifier(&ftrace_module_nb);
+	if (ret)
+		pr_warning("Failed to register trace ftrace module notifier\n");
+
+	set_ftrace_early_filters();
+
 	return;
  failed:
 	ftrace_disabled = 1;
@@ -2417,7 +3056,6 @@ static const struct file_operations ftrace_pid_fops = {
 static __init int ftrace_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -2425,11 +3063,11 @@ static __init int ftrace_init_debugfs(void)
 
 	ftrace_init_dyn_debugfs(d_tracer);
 
-	entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
-				    NULL, &ftrace_pid_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_pid' entry\n");
+	trace_create_file("set_ftrace_pid", 0644, d_tracer,
+			    NULL, &ftrace_pid_fops);
+
+	ftrace_profile_debugfs(d_tracer);
+
 	return 0;
 }
 fs_initcall(ftrace_init_debugfs);
@@ -2538,7 +3176,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-static atomic_t ftrace_graph_active;
+static int ftrace_graph_active;
 static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
@@ -2580,12 +3218,12 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 
 		if (t->ret_stack == NULL) {
-			t->curr_ret_stack = -1;
-			/* Make sure IRQs see the -1 first: */
-			barrier();
-			t->ret_stack = ret_stack_list[start++];
 			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
+			t->curr_ret_stack = -1;
+			/* Make sure the tasks see the -1 first: */
+			smp_wmb();
+			t->ret_stack = ret_stack_list[start++];
 		}
 	} while_each_thread(g, t);
 
@@ -2643,8 +3281,10 @@ static int start_graph_tracing(void)
 		return -ENOMEM;
 
 	/* The cpu_boot init_task->ret_stack will never be freed */
-	for_each_online_cpu(cpu)
-		ftrace_graph_init_task(idle_task(cpu));
+	for_each_online_cpu(cpu) {
+		if (!idle_task(cpu)->ret_stack)
+			ftrace_graph_init_task(idle_task(cpu));
+	}
 
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
@@ -2690,7 +3330,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	mutex_lock(&ftrace_lock);
 
 	/* we currently allow only one tracer registered at a time */
-	if (atomic_read(&ftrace_graph_active)) {
+	if (ftrace_graph_active) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -2698,10 +3338,10 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
-	atomic_inc(&ftrace_graph_active);
+	ftrace_graph_active++;
 	ret = start_graph_tracing();
 	if (ret) {
-		atomic_dec(&ftrace_graph_active);
+		ftrace_graph_active--;
 		goto out;
 	}
 
@@ -2719,10 +3359,10 @@ void unregister_ftrace_graph(void)
 {
 	mutex_lock(&ftrace_lock);
 
-	if (!unlikely(atomic_read(&ftrace_graph_active)))
+	if (unlikely(!ftrace_graph_active))
 		goto out;
 
-	atomic_dec(&ftrace_graph_active);
+	ftrace_graph_active--;
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
@@ -2736,18 +3376,25 @@ void unregister_ftrace_graph(void)
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
-	if (atomic_read(&ftrace_graph_active)) {
-		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+	/* Make sure we do not use the parent ret_stack */
+	t->ret_stack = NULL;
+
+	if (ftrace_graph_active) {
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
 				* sizeof(struct ftrace_ret_stack),
 				GFP_KERNEL);
-		if (!t->ret_stack)
+		if (!ret_stack)
 			return;
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
 		t->ftrace_timestamp = 0;
-	} else
-		t->ret_stack = NULL;
+		/* make curr_ret_stack visable before we add the ret_stack */
+		smp_wmb();
+		t->ret_stack = ret_stack;
+	}
 }
 
 void ftrace_graph_exit_task(struct task_struct *t)
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 5011f4d91e3..86cdf671d7e 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -12,7 +12,7 @@
 #include <linux/dcache.h>
 #include <linux/fs.h>
 
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 #include "trace_output.h"
 #include "trace.h"
@@ -42,6 +42,7 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
 				   gfp_t gfp_flags,
 				   int node)
 {
+	struct ftrace_event_call *call = &event_kmem_alloc;
 	struct trace_array *tr = kmemtrace_array;
 	struct kmemtrace_alloc_entry *entry;
 	struct ring_buffer_event *event;
@@ -62,7 +63,8 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
 	entry->gfp_flags	= gfp_flags;
 	entry->node		= node;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 	trace_wake_up();
 }
@@ -71,6 +73,7 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
 				  unsigned long call_site,
 				  const void *ptr)
 {
+	struct ftrace_event_call *call = &event_kmem_free;
 	struct trace_array *tr = kmemtrace_array;
 	struct kmemtrace_free_entry *entry;
 	struct ring_buffer_event *event;
@@ -86,7 +89,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
 	entry->call_site	= call_site;
 	entry->ptr		= ptr;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 	trace_wake_up();
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 960cbf44c84..2e642b2b725 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -22,6 +22,28 @@
 #include "trace.h"
 
 /*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+	int ret;
+
+	ret = trace_seq_printf(s, "# compressed entry header\n");
+	ret = trace_seq_printf(s, "\ttype_len    :    5 bits\n");
+	ret = trace_seq_printf(s, "\ttime_delta  :   27 bits\n");
+	ret = trace_seq_printf(s, "\tarray       :   32 bits\n");
+	ret = trace_seq_printf(s, "\n");
+	ret = trace_seq_printf(s, "\tpadding     : type == %d\n",
+			       RINGBUF_TYPE_PADDING);
+	ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+			       RINGBUF_TYPE_TIME_EXTEND);
+	ret = trace_seq_printf(s, "\tdata max type_len  == %d\n",
+			       RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+	return ret;
+}
+
+/*
  * The ring buffer is made up of a list of pages. A separate list of pages is
  * allocated for each CPU. A writer may only write to a buffer that is
  * associated with the CPU it is currently executing on.  A reader may read
@@ -182,7 +204,10 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
-#define RB_MAX_SMALL_DATA	28
+#define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
 
 enum {
 	RB_LEN_TIME_EXTEND = 8,
@@ -191,48 +216,28 @@ enum {
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+	return event->type_len == RINGBUF_TYPE_PADDING
+			&& event->time_delta == 0;
 }
 
 static inline int rb_discarded_event(struct ring_buffer_event *event)
 {
-	return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+	return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
-	event->type = RINGBUF_TYPE_PADDING;
+	event->type_len = RINGBUF_TYPE_PADDING;
 	event->time_delta = 0;
 }
 
-/**
- * ring_buffer_event_discard - discard an event in the ring buffer
- * @buffer: the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
-{
-	event->type = RINGBUF_TYPE_PADDING;
-	/* time delta must be non zero */
-	if (!event->time_delta)
-		event->time_delta = 1;
-}
-
 static unsigned
 rb_event_data_length(struct ring_buffer_event *event)
 {
 	unsigned length;
 
-	if (event->len)
-		length = event->len * RB_ALIGNMENT;
+	if (event->type_len)
+		length = event->type_len * RB_ALIGNMENT;
 	else
 		length = event->array[0];
 	return length + RB_EVNT_HDR_SIZE;
@@ -242,12 +247,12 @@ rb_event_data_length(struct ring_buffer_event *event)
 static unsigned
 rb_event_length(struct ring_buffer_event *event)
 {
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event))
 			/* undefined */
 			return -1;
-		return rb_event_data_length(event);
+		return  event->array[0] + RB_EVNT_HDR_SIZE;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		return RB_LEN_TIME_EXTEND;
@@ -271,7 +276,7 @@ rb_event_length(struct ring_buffer_event *event)
 unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
 	unsigned length = rb_event_length(event);
-	if (event->type != RINGBUF_TYPE_DATA)
+	if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 		return length;
 	length -= RB_EVNT_HDR_SIZE;
 	if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
@@ -284,9 +289,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 static void *
 rb_event_data(struct ring_buffer_event *event)
 {
-	BUG_ON(event->type != RINGBUF_TYPE_DATA);
+	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 	/* If length is in len field, then array[0] has the data */
-	if (event->len)
+	if (event->type_len)
 		return (void *)&event->array[0];
 	/* Otherwise length is in array[0] and array[1] has the data */
 	return (void *)&event->array[1];
@@ -316,9 +321,10 @@ struct buffer_data_page {
 };
 
 struct buffer_page {
+	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
-	struct list_head list;		/* list of free pages */
+	local_t		 entries;	/* entries on this page */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -361,6 +367,34 @@ static inline int test_time_stamp(u64 delta)
 
 #define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
 
+/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
+#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
+
+/* Max number of timestamps that can fit on a page */
+#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+	struct buffer_data_page field;
+	int ret;
+
+	ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+			       "offset:0;\tsize:%u;\n",
+			       (unsigned int)sizeof(field.time_stamp));
+
+	ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+			       "offset:%u;\tsize:%u;\n",
+			       (unsigned int)offsetof(typeof(field), commit),
+			       (unsigned int)sizeof(field.commit));
+
+	ret = trace_seq_printf(s, "\tfield: char data;\t"
+			       "offset:%u;\tsize:%u;\n",
+			       (unsigned int)offsetof(typeof(field), data),
+			       (unsigned int)BUF_PAGE_SIZE);
+
+	return ret;
+}
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
@@ -375,8 +409,11 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
+	unsigned long			nmi_dropped;
+	unsigned long			commit_overrun;
 	unsigned long			overrun;
-	unsigned long			entries;
+	unsigned long			read;
+	local_t				entries;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -389,6 +426,8 @@ struct ring_buffer {
 	atomic_t			record_disabled;
 	cpumask_var_t			cpumask;
 
+	struct lock_class_key		*reader_lock_key;
+
 	struct mutex			mutex;
 
 	struct ring_buffer_per_cpu	**buffers;
@@ -420,13 +459,18 @@ struct ring_buffer_iter {
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
+static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+	/* shift to debug/test normalization and TIME_EXTENTS */
+	return buffer->clock() << DEBUG_SHIFT;
+}
+
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 {
 	u64 time;
 
 	preempt_disable_notrace();
-	/* shift to debug/test normalization and TIME_EXTENTS */
-	time = buffer->clock() << DEBUG_SHIFT;
+	time = rb_time_stamp(buffer, cpu);
 	preempt_enable_no_resched_notrace();
 
 	return time;
@@ -523,6 +567,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
 	spin_lock_init(&cpu_buffer->reader_lock);
+	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	INIT_LIST_HEAD(&cpu_buffer->pages);
 
@@ -593,7 +638,8 @@ static int rb_cpu_notify(struct notifier_block *self,
  * when the buffer wraps. If this flag is not set, the buffer will
  * drop data when the tail hits the head.
  */
-struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
+struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
+					struct lock_class_key *key)
 {
 	struct ring_buffer *buffer;
 	int bsize;
@@ -616,6 +662,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
+	buffer->reader_lock_key = key;
 
 	/* need at least two pages */
 	if (buffer->pages == 1)
@@ -673,7 +720,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	kfree(buffer);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_alloc);
+EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
 
 /**
  * ring_buffer_free - free a ring buffer.
@@ -947,31 +994,6 @@ static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
 	return rb_page_commit(cpu_buffer->head_page);
 }
 
-/*
- * When the tail hits the head and the buffer is in overwrite mode,
- * the head jumps to the next page and all content on the previous
- * page is discarded. But before doing so, we update the overrun
- * variable of the buffer.
- */
-static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	struct ring_buffer_event *event;
-	unsigned long head;
-
-	for (head = 0; head < rb_head_size(cpu_buffer);
-	     head += rb_event_length(event)) {
-
-		event = __rb_page_index(cpu_buffer->head_page, head);
-		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
-			return;
-		/* Only count data entries */
-		if (event->type != RINGBUF_TYPE_DATA)
-			continue;
-		cpu_buffer->overrun++;
-		cpu_buffer->entries--;
-	}
-}
-
 static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
 			       struct buffer_page **bpage)
 {
@@ -991,7 +1013,7 @@ rb_event_index(struct ring_buffer_event *event)
 	return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
 }
 
-static int
+static inline int
 rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct ring_buffer_event *event)
 {
@@ -1110,28 +1132,21 @@ static void
 rb_update_event(struct ring_buffer_event *event,
 			 unsigned type, unsigned length)
 {
-	event->type = type;
+	event->type_len = type;
 
 	switch (type) {
 
 	case RINGBUF_TYPE_PADDING:
-		break;
-
 	case RINGBUF_TYPE_TIME_EXTEND:
-		event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT);
-		break;
-
 	case RINGBUF_TYPE_TIME_STAMP:
-		event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT);
 		break;
 
-	case RINGBUF_TYPE_DATA:
+	case 0:
 		length -= RB_EVNT_HDR_SIZE;
-		if (length > RB_MAX_SMALL_DATA) {
-			event->len = 0;
+		if (length > RB_MAX_SMALL_DATA)
 			event->array[0] = length;
-		} else
-			event->len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+		else
+			event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
 		break;
 	default:
 		BUG();
@@ -1155,131 +1170,156 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
+
 static struct ring_buffer_event *
-__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
-		  unsigned type, unsigned long length, u64 *ts)
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+	     unsigned long length, unsigned long tail,
+	     struct buffer_page *commit_page,
+	     struct buffer_page *tail_page, u64 *ts)
 {
-	struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
-	unsigned long tail, write;
+	struct buffer_page *next_page, *head_page, *reader_page;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct ring_buffer_event *event;
-	unsigned long flags;
 	bool lock_taken = false;
+	unsigned long flags;
 
-	commit_page = cpu_buffer->commit_page;
-	/* we just need to protect against interrupts */
-	barrier();
-	tail_page = cpu_buffer->tail_page;
-	write = local_add_return(length, &tail_page->write);
-	tail = write - length;
+	next_page = tail_page;
 
-	/* See if we shot pass the end of this buffer page */
-	if (write > BUF_PAGE_SIZE) {
-		struct buffer_page *next_page = tail_page;
+	local_irq_save(flags);
+	/*
+	 * Since the write to the buffer is still not
+	 * fully lockless, we must be careful with NMIs.
+	 * The locks in the writers are taken when a write
+	 * crosses to a new page. The locks protect against
+	 * races with the readers (this will soon be fixed
+	 * with a lockless solution).
+	 *
+	 * Because we can not protect against NMIs, and we
+	 * want to keep traces reentrant, we need to manage
+	 * what happens when we are in an NMI.
+	 *
+	 * NMIs can happen after we take the lock.
+	 * If we are in an NMI, only take the lock
+	 * if it is not already taken. Otherwise
+	 * simply fail.
+	 */
+	if (unlikely(in_nmi())) {
+		if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+			cpu_buffer->nmi_dropped++;
+			goto out_reset;
+		}
+	} else
+		__raw_spin_lock(&cpu_buffer->lock);
 
-		local_irq_save(flags);
-		/*
-		 * Since the write to the buffer is still not
-		 * fully lockless, we must be careful with NMIs.
-		 * The locks in the writers are taken when a write
-		 * crosses to a new page. The locks protect against
-		 * races with the readers (this will soon be fixed
-		 * with a lockless solution).
-		 *
-		 * Because we can not protect against NMIs, and we
-		 * want to keep traces reentrant, we need to manage
-		 * what happens when we are in an NMI.
-		 *
-		 * NMIs can happen after we take the lock.
-		 * If we are in an NMI, only take the lock
-		 * if it is not already taken. Otherwise
-		 * simply fail.
-		 */
-		if (unlikely(in_nmi())) {
-			if (!__raw_spin_trylock(&cpu_buffer->lock))
-				goto out_reset;
-		} else
-			__raw_spin_lock(&cpu_buffer->lock);
+	lock_taken = true;
 
-		lock_taken = true;
+	rb_inc_page(cpu_buffer, &next_page);
 
-		rb_inc_page(cpu_buffer, &next_page);
+	head_page = cpu_buffer->head_page;
+	reader_page = cpu_buffer->reader_page;
 
-		head_page = cpu_buffer->head_page;
-		reader_page = cpu_buffer->reader_page;
+	/* we grabbed the lock before incrementing */
+	if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+		goto out_reset;
 
-		/* we grabbed the lock before incrementing */
-		if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-			goto out_reset;
+	/*
+	 * If for some reason, we had an interrupt storm that made
+	 * it all the way around the buffer, bail, and warn
+	 * about it.
+	 */
+	if (unlikely(next_page == commit_page)) {
+		cpu_buffer->commit_overrun++;
+		goto out_reset;
+	}
 
-		/*
-		 * If for some reason, we had an interrupt storm that made
-		 * it all the way around the buffer, bail, and warn
-		 * about it.
-		 */
-		if (unlikely(next_page == commit_page)) {
-			WARN_ON_ONCE(1);
+	if (next_page == head_page) {
+		if (!(buffer->flags & RB_FL_OVERWRITE))
 			goto out_reset;
-		}
 
-		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE))
-				goto out_reset;
-
-			/* tail_page has not moved yet? */
-			if (tail_page == cpu_buffer->tail_page) {
-				/* count overflows */
-				rb_update_overflow(cpu_buffer);
+		/* tail_page has not moved yet? */
+		if (tail_page == cpu_buffer->tail_page) {
+			/* count overflows */
+			cpu_buffer->overrun +=
+				local_read(&head_page->entries);
 
-				rb_inc_page(cpu_buffer, &head_page);
-				cpu_buffer->head_page = head_page;
-				cpu_buffer->head_page->read = 0;
-			}
+			rb_inc_page(cpu_buffer, &head_page);
+			cpu_buffer->head_page = head_page;
+			cpu_buffer->head_page->read = 0;
 		}
+	}
 
-		/*
-		 * If the tail page is still the same as what we think
-		 * it is, then it is up to us to update the tail
-		 * pointer.
-		 */
-		if (tail_page == cpu_buffer->tail_page) {
-			local_set(&next_page->write, 0);
-			local_set(&next_page->page->commit, 0);
-			cpu_buffer->tail_page = next_page;
+	/*
+	 * If the tail page is still the same as what we think
+	 * it is, then it is up to us to update the tail
+	 * pointer.
+	 */
+	if (tail_page == cpu_buffer->tail_page) {
+		local_set(&next_page->write, 0);
+		local_set(&next_page->entries, 0);
+		local_set(&next_page->page->commit, 0);
+		cpu_buffer->tail_page = next_page;
+
+		/* reread the time stamp */
+		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+		cpu_buffer->tail_page->page->time_stamp = *ts;
+	}
 
-			/* reread the time stamp */
-			*ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
-			cpu_buffer->tail_page->page->time_stamp = *ts;
-		}
+	/*
+	 * The actual tail page has moved forward.
+	 */
+	if (tail < BUF_PAGE_SIZE) {
+		/* Mark the rest of the page with padding */
+		event = __rb_page_index(tail_page, tail);
+		rb_event_set_padding(event);
+	}
 
-		/*
-		 * The actual tail page has moved forward.
-		 */
-		if (tail < BUF_PAGE_SIZE) {
-			/* Mark the rest of the page with padding */
-			event = __rb_page_index(tail_page, tail);
-			rb_event_set_padding(event);
-		}
+	/* Set the write back to the previous setting */
+	local_sub(length, &tail_page->write);
 
-		if (tail <= BUF_PAGE_SIZE)
-			/* Set the write back to the previous setting */
-			local_set(&tail_page->write, tail);
+	/*
+	 * If this was a commit entry that failed,
+	 * increment that too
+	 */
+	if (tail_page == cpu_buffer->commit_page &&
+	    tail == rb_commit_index(cpu_buffer)) {
+		rb_set_commit_to_write(cpu_buffer);
+	}
 
-		/*
-		 * If this was a commit entry that failed,
-		 * increment that too
-		 */
-		if (tail_page == cpu_buffer->commit_page &&
-		    tail == rb_commit_index(cpu_buffer)) {
-			rb_set_commit_to_write(cpu_buffer);
-		}
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
+
+	/* fail and let the caller try again */
+	return ERR_PTR(-EAGAIN);
+
+ out_reset:
+	/* reset write */
+	local_sub(length, &tail_page->write);
 
+	if (likely(lock_taken))
 		__raw_spin_unlock(&cpu_buffer->lock);
-		local_irq_restore(flags);
+	local_irq_restore(flags);
+	return NULL;
+}
 
-		/* fail and let the caller try again */
-		return ERR_PTR(-EAGAIN);
-	}
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+		  unsigned type, unsigned long length, u64 *ts)
+{
+	struct buffer_page *tail_page, *commit_page;
+	struct ring_buffer_event *event;
+	unsigned long tail, write;
+
+	commit_page = cpu_buffer->commit_page;
+	/* we just need to protect against interrupts */
+	barrier();
+	tail_page = cpu_buffer->tail_page;
+	write = local_add_return(length, &tail_page->write);
+	tail = write - length;
+
+	/* See if we shot pass the end of this buffer page */
+	if (write > BUF_PAGE_SIZE)
+		return rb_move_tail(cpu_buffer, length, tail,
+				    commit_page, tail_page, ts);
 
 	/* We reserved something on the buffer */
 
@@ -1289,6 +1329,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	event = __rb_page_index(tail_page, tail);
 	rb_update_event(event, type, length);
 
+	/* The passed in type is zero for DATA */
+	if (likely(!type))
+		local_inc(&tail_page->entries);
+
 	/*
 	 * If this is a commit and the tail is zero, then update
 	 * this page's time stamp.
@@ -1297,16 +1341,38 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		cpu_buffer->commit_page->page->time_stamp = *ts;
 
 	return event;
+}
 
- out_reset:
-	/* reset write */
-	if (tail <= BUF_PAGE_SIZE)
-		local_set(&tail_page->write, tail);
+static inline int
+rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event)
+{
+	unsigned long new_index, old_index;
+	struct buffer_page *bpage;
+	unsigned long index;
+	unsigned long addr;
 
-	if (likely(lock_taken))
-		__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
-	return NULL;
+	new_index = rb_event_index(event);
+	old_index = new_index + rb_event_length(event);
+	addr = (unsigned long)event;
+	addr &= PAGE_MASK;
+
+	bpage = cpu_buffer->tail_page;
+
+	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		/*
+		 * This is on the tail page. It is possible that
+		 * a write could come in and move the tail page
+		 * and write to the next page. That is fine
+		 * because we just shorten what is on this page.
+		 */
+		index = local_cmpxchg(&bpage->write, old_index, new_index);
+		if (index == old_index)
+			return 1;
+	}
+
+	/* could not discard */
+	return 0;
 }
 
 static int
@@ -1351,16 +1417,23 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 			event->array[0] = *delta >> TS_SHIFT;
 		} else {
 			cpu_buffer->commit_page->page->time_stamp = *ts;
-			event->time_delta = 0;
-			event->array[0] = 0;
+			/* try to discard, since we do not need this */
+			if (!rb_try_to_discard(cpu_buffer, event)) {
+				/* nope, just zero it */
+				event->time_delta = 0;
+				event->array[0] = 0;
+			}
 		}
 		cpu_buffer->write_stamp = *ts;
 		/* let the caller know this was the commit */
 		ret = 1;
 	} else {
-		/* Darn, this is just wasted space */
-		event->time_delta = 0;
-		event->array[0] = 0;
+		/* Try to discard the event */
+		if (!rb_try_to_discard(cpu_buffer, event)) {
+			/* Darn, this is just wasted space */
+			event->time_delta = 0;
+			event->array[0] = 0;
+		}
 		ret = 0;
 	}
 
@@ -1371,13 +1444,14 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 
 static struct ring_buffer_event *
 rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
-		      unsigned type, unsigned long length)
+		      unsigned long length)
 {
 	struct ring_buffer_event *event;
-	u64 ts, delta;
+	u64 ts, delta = 0;
 	int commit = 0;
 	int nr_loops = 0;
 
+	length = rb_calculate_event_length(length);
  again:
 	/*
 	 * We allow for interrupts to reenter here and do a trace.
@@ -1391,7 +1465,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		return NULL;
 
-	ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+	ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
 
 	/*
 	 * Only the first commit can update the timestamp.
@@ -1401,23 +1475,24 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * also be made. But only the entry that did the actual
 	 * commit will be something other than zero.
 	 */
-	if (cpu_buffer->tail_page == cpu_buffer->commit_page &&
-	    rb_page_write(cpu_buffer->tail_page) ==
-	    rb_commit_index(cpu_buffer)) {
+	if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
+		   rb_page_write(cpu_buffer->tail_page) ==
+		   rb_commit_index(cpu_buffer))) {
+		u64 diff;
 
-		delta = ts - cpu_buffer->write_stamp;
+		diff = ts - cpu_buffer->write_stamp;
 
-		/* make sure this delta is calculated here */
+		/* make sure this diff is calculated here */
 		barrier();
 
 		/* Did the write stamp get updated already? */
 		if (unlikely(ts < cpu_buffer->write_stamp))
-			delta = 0;
+			goto get_event;
 
-		if (test_time_stamp(delta)) {
+		delta = diff;
+		if (unlikely(test_time_stamp(delta))) {
 
 			commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
-
 			if (commit == -EBUSY)
 				return NULL;
 
@@ -1426,12 +1501,11 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 			RB_WARN_ON(cpu_buffer, commit < 0);
 		}
-	} else
-		/* Non commits have zero deltas */
-		delta = 0;
+	}
 
-	event = __rb_reserve_next(cpu_buffer, type, length, &ts);
-	if (PTR_ERR(event) == -EAGAIN)
+ get_event:
+	event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+	if (unlikely(PTR_ERR(event) == -EAGAIN))
 		goto again;
 
 	if (!event) {
@@ -1448,7 +1522,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If the timestamp was commited, make the commit our entry
 	 * now so that we will update it when needed.
 	 */
-	if (commit)
+	if (unlikely(commit))
 		rb_set_commit_event(cpu_buffer, event);
 	else if (!rb_is_commit(cpu_buffer, event))
 		delta = 0;
@@ -1458,6 +1532,36 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 }
 
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+	current->trace_recursion++;
+
+	if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+		return 0;
+
+	/* Disable all tracing before we do anything else */
+	tracing_off_permanent();
+
+	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+		    current->trace_recursion,
+		    hardirq_count() >> HARDIRQ_SHIFT,
+		    softirq_count() >> SOFTIRQ_SHIFT,
+		    in_nmi());
+
+	WARN_ON_ONCE(1);
+	return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+	WARN_ON_ONCE(!current->trace_recursion);
+
+	current->trace_recursion--;
+}
+
 static DEFINE_PER_CPU(int, rb_need_resched);
 
 /**
@@ -1491,6 +1595,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	/* If we are tracing schedule, we don't want to recurse */
 	resched = ftrace_preempt_disable();
 
+	if (trace_recursive_lock())
+		goto out_nocheck;
+
 	cpu = raw_smp_processor_id();
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -1501,11 +1608,10 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	length = rb_calculate_event_length(length);
-	if (length > BUF_PAGE_SIZE)
+	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+	event = rb_reserve_next_event(cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1520,6 +1626,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	return event;
 
  out:
+	trace_recursive_unlock();
+
+ out_nocheck:
 	ftrace_preempt_enable(resched);
 	return NULL;
 }
@@ -1528,7 +1637,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
-	cpu_buffer->entries++;
+	local_inc(&cpu_buffer->entries);
 
 	/* Only process further if we own the commit */
 	if (!rb_is_commit(cpu_buffer, event))
@@ -1558,6 +1667,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	trace_recursive_unlock();
+
 	/*
 	 * Only the last preempt count needs to restore preemption.
 	 */
@@ -1570,6 +1681,99 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+	/* array[0] holds the actual length for the discarded event */
+	event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+	event->type_len = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	if (!event->time_delta)
+		event->time_delta = 1;
+}
+
+/**
+ * ring_buffer_event_discard - discard any event in the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+	rb_event_discard(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * This is similar to ring_buffer_event_discard but must only be
+ * performed on an event that has not been committed yet. The difference
+ * is that this will also try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
+
+	/* The event is discarded regardless */
+	rb_event_discard(event);
+
+	/*
+	 * This must only be called if the event has not been
+	 * committed yet. Thus we can assume that preemption
+	 * is still disabled.
+	 */
+	RB_WARN_ON(buffer, preemptible());
+
+	cpu = smp_processor_id();
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!rb_try_to_discard(cpu_buffer, event))
+		goto out;
+
+	/*
+	 * The commit is still visible by the reader, so we
+	 * must increment entries.
+	 */
+	local_inc(&cpu_buffer->entries);
+ out:
+	/*
+	 * If a write came in and pushed the tail page
+	 * we still need to update the commit pointer
+	 * if we were the commit.
+	 */
+	if (rb_is_commit(cpu_buffer, event))
+		rb_set_commit_to_write(cpu_buffer);
+
+	trace_recursive_unlock();
+
+	/*
+	 * Only the last preempt count needs to restore preemption.
+	 */
+	if (preempt_count() == 1)
+		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+	else
+		preempt_enable_no_resched_notrace();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
+
 /**
  * ring_buffer_write - write data to the buffer without reserving
  * @buffer: The ring buffer to write to.
@@ -1589,7 +1793,6 @@ int ring_buffer_write(struct ring_buffer *buffer,
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
-	unsigned long event_length;
 	void *body;
 	int ret = -EBUSY;
 	int cpu, resched;
@@ -1612,9 +1815,10 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	event_length = rb_calculate_event_length(length);
-	event = rb_reserve_next_event(cpu_buffer,
-				      RINGBUF_TYPE_DATA, event_length);
+	if (length > BUF_MAX_DATA_SIZE)
+		goto out;
+
+	event = rb_reserve_next_event(cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1728,7 +1932,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->entries;
+	ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+		- cpu_buffer->read;
 
 	return ret;
 }
@@ -1755,6 +1960,47 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = cpu_buffer->nmi_dropped;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = cpu_buffer->commit_overrun;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
+/**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
  *
@@ -1770,7 +2016,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		entries += cpu_buffer->entries;
+		entries += (local_read(&cpu_buffer->entries) -
+			    cpu_buffer->overrun) - cpu_buffer->read;
 	}
 
 	return entries;
@@ -1862,7 +2109,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 {
 	u64 delta;
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		return;
 
@@ -1893,7 +2140,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 {
 	u64 delta;
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		return;
 
@@ -1966,6 +2213,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
 	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 
 	/* Make the reader page now replace the head */
@@ -2008,8 +2256,9 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
-		cpu_buffer->entries--;
+	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+			|| rb_discarded_event(event))
+		cpu_buffer->read++;
 
 	rb_update_read_stamp(cpu_buffer, event);
 
@@ -2031,8 +2280,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * Check if we are at the end of the buffer.
 	 */
 	if (iter->head >= rb_page_size(iter->head_page)) {
-		if (RB_WARN_ON(buffer,
-			       iter->head_page == cpu_buffer->commit_page))
+		/* discarded commits can make the page empty */
+		if (iter->head_page == cpu_buffer->commit_page)
 			return;
 		rb_inc_iter(iter);
 		return;
@@ -2075,12 +2324,10 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	/*
 	 * We repeat when a timestamp is encountered. It is possible
 	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have.  Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
+	 * as one timestamp is about to be written, or from discarded
+	 * commits. The most that we can have is the number on a single page.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	reader = rb_get_reader_page(cpu_buffer);
@@ -2089,7 +2336,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	event = rb_reader_event(cpu_buffer);
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event))
 			RB_WARN_ON(cpu_buffer, 1);
@@ -2146,14 +2393,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
  again:
 	/*
-	 * We repeat when a timestamp is encountered. It is possible
-	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have. Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
+	 * We repeat when a timestamp is encountered.
+	 * We can get multiple timestamps by nested interrupts or also
+	 * if filtering is on (discarding commits). Since discarding
+	 * commits can be frequent we can get a lot of timestamps.
+	 * But we limit them by not adding timestamps if they begin
+	 * at the start of a page.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
@@ -2161,7 +2408,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	event = rb_iter_head_event(iter);
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event)) {
 			rb_inc_iter(iter);
@@ -2220,7 +2467,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2248,7 +2495,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2293,7 +2540,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2386,7 +2633,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2411,6 +2658,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
 	local_set(&cpu_buffer->head_page->write, 0);
+	local_set(&cpu_buffer->head_page->entries, 0);
 	local_set(&cpu_buffer->head_page->page->commit, 0);
 
 	cpu_buffer->head_page->read = 0;
@@ -2420,11 +2668,15 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
+	cpu_buffer->nmi_dropped = 0;
+	cpu_buffer->commit_overrun = 0;
 	cpu_buffer->overrun = 0;
-	cpu_buffer->entries = 0;
+	cpu_buffer->read = 0;
+	local_set(&cpu_buffer->entries, 0);
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
@@ -2443,6 +2695,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
+	atomic_inc(&cpu_buffer->record_disabled);
+
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	__raw_spin_lock(&cpu_buffer->lock);
@@ -2452,6 +2706,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	__raw_spin_unlock(&cpu_buffer->lock);
 
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	atomic_dec(&cpu_buffer->record_disabled);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
@@ -2578,28 +2834,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 
-static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
-			      struct buffer_data_page *bpage,
-			      unsigned int offset)
-{
-	struct ring_buffer_event *event;
-	unsigned long head;
-
-	__raw_spin_lock(&cpu_buffer->lock);
-	for (head = offset; head < local_read(&bpage->commit);
-	     head += rb_event_length(event)) {
-
-		event = __rb_data_page_index(bpage, head);
-		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
-			return;
-		/* Only count data entries */
-		if (event->type != RINGBUF_TYPE_DATA)
-			continue;
-		cpu_buffer->entries--;
-	}
-	__raw_spin_unlock(&cpu_buffer->lock);
-}
-
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
  * @buffer: the buffer to allocate for.
@@ -2630,6 +2864,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 
 	return bpage;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
 
 /**
  * ring_buffer_free_read_page - free an allocated read page
@@ -2642,6 +2877,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
 {
 	free_page((unsigned long)data);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
 /**
  * ring_buffer_read_page - extract a page from the ring buffer
@@ -2768,16 +3004,17 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		/* we copied everything to the beginning */
 		read = 0;
 	} else {
+		/* update the entry counter */
+		cpu_buffer->read += local_read(&reader->entries);
+
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
 		reader->page = *data_page;
 		local_set(&reader->write, 0);
+		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
-
-		/* update the entry counter */
-		rb_remove_entries(cpu_buffer, bpage, read);
 	}
 	ret = read;
 
@@ -2787,6 +3024,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
  out:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
 static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
@@ -2845,14 +3083,11 @@ static const struct file_operations rb_simple_fops = {
 static __init int rb_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("tracing_on", 0644, d_tracer,
-				    &ring_buffer_flags, &rb_simple_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_on' entry\n");
+	trace_create_file("tracing_on", 0644, d_tracer,
+			    &ring_buffer_flags, &rb_simple_fops);
 
 	return 0;
 }
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
new file mode 100644
index 00000000000..8d68e149a8b
--- /dev/null
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -0,0 +1,416 @@
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/time.h>
+
+struct rb_page {
+	u64		ts;
+	local_t		commit;
+	char		data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME	10
+#define SLEEP_TIME	10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static struct completion read_start;
+static struct completion read_done;
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static int read_events;
+
+static int kill_test;
+
+#define KILL_TEST()				\
+	do {					\
+		if (!kill_test) {		\
+			kill_test = 1;		\
+			WARN_ON(1);		\
+		}				\
+	} while (0)
+
+enum event_status {
+	EVENT_FOUND,
+	EVENT_DROPPED,
+};
+
+static enum event_status read_event(int cpu)
+{
+	struct ring_buffer_event *event;
+	int *entry;
+	u64 ts;
+
+	event = ring_buffer_consume(buffer, cpu, &ts);
+	if (!event)
+		return EVENT_DROPPED;
+
+	entry = ring_buffer_event_data(event);
+	if (*entry != cpu) {
+		KILL_TEST();
+		return EVENT_DROPPED;
+	}
+
+	read++;
+	return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+	struct ring_buffer_event *event;
+	struct rb_page *rpage;
+	unsigned long commit;
+	void *bpage;
+	int *entry;
+	int ret;
+	int inc;
+	int i;
+
+	bpage = ring_buffer_alloc_read_page(buffer);
+	if (!bpage)
+		return EVENT_DROPPED;
+
+	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	if (ret >= 0) {
+		rpage = bpage;
+		commit = local_read(&rpage->commit);
+		for (i = 0; i < commit && !kill_test; i += inc) {
+
+			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+				KILL_TEST();
+				break;
+			}
+
+			inc = -1;
+			event = (void *)&rpage->data[i];
+			switch (event->type_len) {
+			case RINGBUF_TYPE_PADDING:
+				/* We don't expect any padding */
+				KILL_TEST();
+				break;
+			case RINGBUF_TYPE_TIME_EXTEND:
+				inc = 8;
+				break;
+			case 0:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					KILL_TEST();
+					break;
+				}
+				read++;
+				if (!event->array[0]) {
+					KILL_TEST();
+					break;
+				}
+				inc = event->array[0];
+				break;
+			default:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					KILL_TEST();
+					break;
+				}
+				read++;
+				inc = ((event->type_len + 1) * 4);
+			}
+			if (kill_test)
+				break;
+
+			if (inc <= 0) {
+				KILL_TEST();
+				break;
+			}
+		}
+	}
+	ring_buffer_free_read_page(buffer, bpage);
+
+	if (ret < 0)
+		return EVENT_DROPPED;
+	return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+	/* toggle between reading pages and events */
+	read_events ^= 1;
+
+	read = 0;
+	while (!reader_finish && !kill_test) {
+		int found;
+
+		do {
+			int cpu;
+
+			found = 0;
+			for_each_online_cpu(cpu) {
+				enum event_status stat;
+
+				if (read_events)
+					stat = read_event(cpu);
+				else
+					stat = read_page(cpu);
+
+				if (kill_test)
+					break;
+				if (stat == EVENT_FOUND)
+					found = 1;
+			}
+		} while (found && !kill_test);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (reader_finish)
+			break;
+
+		schedule();
+		__set_current_state(TASK_RUNNING);
+	}
+	reader_finish = 0;
+	complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+	struct timeval start_tv;
+	struct timeval end_tv;
+	unsigned long long time;
+	unsigned long long entries;
+	unsigned long long overruns;
+	unsigned long missed = 0;
+	unsigned long hit = 0;
+	unsigned long avg;
+	int cnt = 0;
+
+	/*
+	 * Hammer the buffer for 10 secs (this may
+	 * make the system stall)
+	 */
+	pr_info("Starting ring buffer hammer\n");
+	do_gettimeofday(&start_tv);
+	do {
+		struct ring_buffer_event *event;
+		int *entry;
+
+		event = ring_buffer_lock_reserve(buffer, 10);
+		if (!event) {
+			missed++;
+		} else {
+			hit++;
+			entry = ring_buffer_event_data(event);
+			*entry = smp_processor_id();
+			ring_buffer_unlock_commit(buffer, event);
+		}
+		do_gettimeofday(&end_tv);
+
+		cnt++;
+		if (consumer && !(cnt % wakeup_interval))
+			wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPT
+		/*
+		 * If we are a non preempt kernel, the 10 second run will
+		 * stop everything while it runs. Instead, we will call
+		 * cond_resched and also add any time that was lost by a
+		 * rescedule.
+		 *
+		 * Do a cond resched at the same frequency we would wake up
+		 * the reader.
+		 */
+		if (cnt % wakeup_interval)
+			cond_resched();
+#endif
+
+	} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
+	pr_info("End ring buffer hammer\n");
+
+	if (consumer) {
+		/* Init both completions here to avoid races */
+		init_completion(&read_start);
+		init_completion(&read_done);
+		/* the completions must be visible before the finish var */
+		smp_wmb();
+		reader_finish = 1;
+		/* finish var visible before waking up the consumer */
+		smp_wmb();
+		wake_up_process(consumer);
+		wait_for_completion(&read_done);
+	}
+
+	time = end_tv.tv_sec - start_tv.tv_sec;
+	time *= USEC_PER_SEC;
+	time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
+
+	entries = ring_buffer_entries(buffer);
+	overruns = ring_buffer_overruns(buffer);
+
+	if (kill_test)
+		pr_info("ERROR!\n");
+	pr_info("Time:     %lld (usecs)\n", time);
+	pr_info("Overruns: %lld\n", overruns);
+	if (disable_reader)
+		pr_info("Read:     (reader disabled)\n");
+	else
+		pr_info("Read:     %ld  (by %s)\n", read,
+			read_events ? "events" : "pages");
+	pr_info("Entries:  %lld\n", entries);
+	pr_info("Total:    %lld\n", entries + overruns + read);
+	pr_info("Missed:   %ld\n", missed);
+	pr_info("Hit:      %ld\n", hit);
+
+	/* Convert time from usecs to millisecs */
+	do_div(time, USEC_PER_MSEC);
+	if (time)
+		hit /= (long)time;
+	else
+		pr_info("TIME IS ZERO??\n");
+
+	pr_info("Entries per millisec: %ld\n", hit);
+
+	if (hit) {
+		/* Calculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / hit;
+		pr_info("%ld ns per entry\n", avg);
+	}
+
+	if (missed) {
+		if (time)
+			missed /= (long)time;
+
+		pr_info("Total iterations per millisec: %ld\n", hit + missed);
+
+		/* it is possible that hit + missed will overflow and be zero */
+		if (!(hit + missed)) {
+			pr_info("hit + missed overflowed and totalled zero!\n");
+			hit--; /* make it non zero */
+		}
+
+		/* Caculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / (hit + missed);
+		pr_info("%ld ns per entry\n", avg);
+	}
+}
+
+static void wait_to_die(void)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+	while (!kthread_should_stop() && !kill_test) {
+		complete(&read_start);
+
+		ring_buffer_consumer();
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop() || kill_test)
+			break;
+
+		schedule();
+		__set_current_state(TASK_RUNNING);
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (kill_test)
+		wait_to_die();
+
+	return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+	init_completion(&read_start);
+
+	while (!kthread_should_stop() && !kill_test) {
+		ring_buffer_reset(buffer);
+
+		if (consumer) {
+			smp_wmb();
+			wake_up_process(consumer);
+			wait_for_completion(&read_start);
+		}
+
+		ring_buffer_producer();
+
+		pr_info("Sleeping for 10 secs\n");
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(HZ * SLEEP_TIME);
+		__set_current_state(TASK_RUNNING);
+	}
+
+	if (kill_test)
+		wait_to_die();
+
+	return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+	int ret;
+
+	/* make a one meg buffer in overwite mode */
+	buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+	if (!buffer)
+		return -ENOMEM;
+
+	if (!disable_reader) {
+		consumer = kthread_create(ring_buffer_consumer_thread,
+					  NULL, "rb_consumer");
+		ret = PTR_ERR(consumer);
+		if (IS_ERR(consumer))
+			goto out_fail;
+	}
+
+	producer = kthread_run(ring_buffer_producer_thread,
+			       NULL, "rb_producer");
+	ret = PTR_ERR(producer);
+
+	if (IS_ERR(producer))
+		goto out_kill;
+
+	return 0;
+
+ out_kill:
+	if (consumer)
+		kthread_stop(consumer);
+
+ out_fail:
+	ring_buffer_free(buffer);
+	return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+	kthread_stop(producer);
+	if (consumer)
+		kthread_stop(consumer);
+	ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index cda81ec58d9..8acd9b81a5d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -171,6 +171,13 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+				 struct ring_buffer_event *event)
+{
+	return filter_check_discard(call, rec, global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(filter_current_check_discard);
+
 cycle_t ftrace_now(int cpu)
 {
 	u64 ts;
@@ -255,7 +262,8 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
+	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+	TRACE_ITER_GRAPH_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -317,6 +325,7 @@ static const char *trace_options[] = {
 	"latency-format",
 	"global-clock",
 	"sleep-time",
+	"graph-time",
 	NULL
 };
 
@@ -402,17 +411,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
-	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
-	s->buffer[len] = 0;
-	seq_puts(m, s->buffer);
-
-	trace_seq_init(s);
-}
-
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -641,6 +639,16 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 }
 
+void tracing_reset_current(int cpu)
+{
+	tracing_reset(&global_trace, cpu);
+}
+
+void tracing_reset_current_online_cpus(void)
+{
+	tracing_reset_online_cpus(&global_trace);
+}
+
 #define SAVED_CMDLINES 128
 #define NO_CMDLINE_MAP UINT_MAX
 static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -800,6 +808,7 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
+	preempt_disable();
 	__raw_spin_lock(&trace_cmdline_lock);
 	map = map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
@@ -808,6 +817,7 @@ void trace_find_cmdline(int pid, char comm[])
 		strcpy(comm, "<...>");
 
 	__raw_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 }
 
 void tracing_record_cmdline(struct task_struct *tsk)
@@ -840,7 +850,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 }
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    unsigned char type,
+						    int type,
 						    unsigned long len,
 						    unsigned long flags, int pc)
 {
@@ -883,30 +893,40 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+trace_current_buffer_lock_reserve(int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
 	return trace_buffer_lock_reserve(&global_trace,
 					 type, len, flags, pc);
 }
+EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
 }
+EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
 void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+{
+	ring_buffer_discard_commit(global_trace.buffer, event);
 }
+EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
 	       int pc)
 {
+	struct ftrace_event_call *call = &event_function;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -921,7 +941,9 @@ trace_function(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
-	ring_buffer_unlock_commit(tr->buffer, event);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -930,6 +952,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ent_entry *entry;
 
@@ -942,7 +965,8 @@ static int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(global_trace.buffer, event);
 
 	return 1;
 }
@@ -952,6 +976,7 @@ static void __trace_graph_return(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ret_entry *entry;
 
@@ -964,7 +989,8 @@ static void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(global_trace.buffer, event);
 }
 #endif
 
@@ -982,6 +1008,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 				 int skip, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
@@ -999,7 +1026,8 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
 
@@ -1024,6 +1052,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 	struct stack_trace trace;
@@ -1045,7 +1074,8 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
 
@@ -1089,6 +1119,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   struct task_struct *next,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_context_switch;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1104,7 +1135,9 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_prio		= next->prio;
 	entry->next_state		= next->state;
 	entry->next_cpu	= task_cpu(next);
-	trace_buffer_unlock_commit(tr, event, flags, pc);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, flags, pc);
 }
 
 void
@@ -1113,6 +1146,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 			   struct task_struct *curr,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1129,7 +1163,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= wakee->state;
 	entry->next_cpu			= task_cpu(wakee);
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
 }
@@ -1230,11 +1265,13 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	static u32 trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	struct bprint_entry *entry;
 	unsigned long flags;
+	int disable;
 	int resched;
 	int cpu, len = 0, size, pc;
 
@@ -1249,7 +1286,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
-	if (unlikely(atomic_read(&data->disabled)))
+	disable = atomic_inc_return(&data->disabled);
+	if (unlikely(disable != 1))
 		goto out;
 
 	/* Lockdep uses trace_printk for lock tracing */
@@ -1269,13 +1307,15 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
 	local_irq_restore(flags);
 
 out:
+	atomic_dec_return(&data->disabled);
 	ftrace_preempt_enable(resched);
 	unpause_graph_tracing();
 
@@ -1288,12 +1328,14 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
 	struct print_entry *entry;
 	unsigned long irq_flags;
+	int disable;
 
 	if (tracing_disabled || tracing_selftest_running)
 		return 0;
@@ -1303,7 +1345,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
-	if (unlikely(atomic_read(&data->disabled)))
+	disable = atomic_inc_return(&data->disabled);
+	if (unlikely(disable != 1))
 		goto out;
 
 	pause_graph_tracing();
@@ -1323,13 +1366,15 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
  out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
 	raw_local_irq_restore(irq_flags);
 	unpause_graph_tracing();
  out:
+	atomic_dec_return(&data->disabled);
 	preempt_enable_notrace();
 
 	return len;
@@ -1526,12 +1571,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		p = s_next(m, p, &l);
 	}
 
+	trace_event_read_lock();
 	return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
 	atomic_dec(&trace_record_cmdline_disabled);
+	trace_event_read_unlock();
 }
 
 static void print_lat_help_header(struct seq_file *m)
@@ -1774,6 +1821,7 @@ static int trace_empty(struct trace_iterator *iter)
 	return 1;
 }
 
+/*  Called with trace_event_read_lock() held. */
 static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
@@ -2397,6 +2445,56 @@ static const struct file_operations tracing_readme_fops = {
 };
 
 static ssize_t
+tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	char *buf_comm;
+	char *file_buf;
+	char *buf;
+	int len = 0;
+	int pid;
+	int i;
+
+	file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
+	if (!file_buf)
+		return -ENOMEM;
+
+	buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
+	if (!buf_comm) {
+		kfree(file_buf);
+		return -ENOMEM;
+	}
+
+	buf = file_buf;
+
+	for (i = 0; i < SAVED_CMDLINES; i++) {
+		int r;
+
+		pid = map_cmdline_to_pid[i];
+		if (pid == -1 || pid == NO_CMDLINE_MAP)
+			continue;
+
+		trace_find_cmdline(pid, buf_comm);
+		r = sprintf(buf, "%d %s\n", pid, buf_comm);
+		buf += r;
+		len += r;
+	}
+
+	len = simple_read_from_buffer(ubuf, cnt, ppos,
+				      file_buf, len);
+
+	kfree(file_buf);
+	kfree(buf_comm);
+
+	return len;
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+    .open       = tracing_open_generic,
+    .read       = tracing_saved_cmdlines_read,
+};
+
+static ssize_t
 tracing_ctrl_read(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
@@ -2728,6 +2826,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	/* trace pipe does not show start of buffer */
 	cpumask_setall(iter->started);
 
+	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		iter->iter_flags |= TRACE_FILE_LAT_FMT;
+
 	iter->cpu_file = cpu_file;
 	iter->tr = &global_trace;
 	mutex_init(&iter->mutex);
@@ -2915,6 +3016,7 @@ waitagain:
 	       offsetof(struct trace_iterator, seq));
 	iter->pos = -1;
 
+	trace_event_read_lock();
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
@@ -2931,6 +3033,7 @@ waitagain:
 		if (iter->seq.len >= cnt)
 			break;
 	}
+	trace_event_read_unlock();
 
 	/* Now copy what we have to the user */
 	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
@@ -3053,6 +3156,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		goto out_err;
 	}
 
+	trace_event_read_lock();
+
 	/* Fill as many pages as possible. */
 	for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
 		pages[i] = alloc_page(GFP_KERNEL);
@@ -3075,6 +3180,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		trace_seq_init(&iter->seq);
 	}
 
+	trace_event_read_unlock();
 	mutex_unlock(&iter->mutex);
 
 	spd.nr_pages = i;
@@ -3425,7 +3531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
-	int size, i;
+	int entries, size, i;
 	size_t ret;
 
 	if (*ppos & (PAGE_SIZE - 1)) {
@@ -3440,7 +3546,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
-	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
+	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+
+	for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 
@@ -3457,7 +3565,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 
 		r = ring_buffer_read_page(ref->buffer, &ref->page,
-					  len, info->cpu, 0);
+					  len, info->cpu, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer,
 						   ref->page);
@@ -3481,6 +3589,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
 		*ppos += PAGE_SIZE;
+
+		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 	}
 
 	spd.nr_pages = i;
@@ -3508,6 +3618,45 @@ static const struct file_operations tracing_buffers_fops = {
 	.llseek		= no_llseek,
 };
 
+static ssize_t
+tracing_stats_read(struct file *filp, char __user *ubuf,
+		   size_t count, loff_t *ppos)
+{
+	unsigned long cpu = (unsigned long)filp->private_data;
+	struct trace_array *tr = &global_trace;
+	struct trace_seq *s;
+	unsigned long cnt;
+
+	s = kmalloc(sizeof(*s), GFP_ATOMIC);
+	if (!s)
+		return ENOMEM;
+
+	trace_seq_init(s);
+
+	cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "entries: %ld\n", cnt);
+
+	cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "overrun: %ld\n", cnt);
+
+	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
+
+	cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
+
+	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return count;
+}
+
+static const struct file_operations tracing_stats_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_stats_read,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int __weak ftrace_arch_read_dyn_info(char *buf, int size)
@@ -3597,7 +3746,7 @@ struct dentry *tracing_dentry_percpu(void)
 static void tracing_init_debugfs_percpu(long cpu)
 {
 	struct dentry *d_percpu = tracing_dentry_percpu();
-	struct dentry *entry, *d_cpu;
+	struct dentry *d_cpu;
 	/* strlen(cpu) + MAX(log10(cpu)) + '\0' */
 	char cpu_dir[7];
 
@@ -3612,21 +3761,18 @@ static void tracing_init_debugfs_percpu(long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	entry = debugfs_create_file("trace_pipe", 0444, d_cpu,
-				(void *) cpu, &tracing_pipe_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_pipe' entry\n");
+	trace_create_file("trace_pipe", 0444, d_cpu,
+			(void *) cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	entry = debugfs_create_file("trace", 0644, d_cpu,
-				(void *) cpu, &tracing_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace' entry\n");
+	trace_create_file("trace", 0644, d_cpu,
+			(void *) cpu, &tracing_fops);
+
+	trace_create_file("trace_pipe_raw", 0444, d_cpu,
+			(void *) cpu, &tracing_buffers_fops);
 
-	entry = debugfs_create_file("trace_pipe_raw", 0444, d_cpu,
-				    (void *) cpu, &tracing_buffers_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_pipe_raw' entry\n");
+	trace_create_file("stats", 0444, d_cpu,
+			(void *) cpu, &tracing_stats_fops);
 }
 
 #ifdef CONFIG_FTRACE_SELFTEST
@@ -3782,6 +3928,22 @@ static const struct file_operations trace_options_core_fops = {
 	.write = trace_options_core_write,
 };
 
+struct dentry *trace_create_file(const char *name,
+				 mode_t mode,
+				 struct dentry *parent,
+				 void *data,
+				 const struct file_operations *fops)
+{
+	struct dentry *ret;
+
+	ret = debugfs_create_file(name, mode, parent, data, fops);
+	if (!ret)
+		pr_warning("Could not create debugfs '%s' entry\n", name);
+
+	return ret;
+}
+
+
 static struct dentry *trace_options_init_dentry(void)
 {
 	struct dentry *d_tracer;
@@ -3809,7 +3971,6 @@ create_trace_option_file(struct trace_option_dentry *topt,
 			 struct tracer_opt *opt)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
@@ -3818,11 +3979,9 @@ create_trace_option_file(struct trace_option_dentry *topt,
 	topt->flags = flags;
 	topt->opt = opt;
 
-	entry = debugfs_create_file(opt->name, 0644, t_options, topt,
+	topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
 				    &trace_options_fops);
 
-	topt->entry = entry;
-
 }
 
 static struct trace_option_dentry *
@@ -3877,123 +4036,84 @@ static struct dentry *
 create_trace_option_core_file(const char *option, long index)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
 		return NULL;
 
-	entry = debugfs_create_file(option, 0644, t_options, (void *)index,
+	return trace_create_file(option, 0644, t_options, (void *)index,
 				    &trace_options_core_fops);
-
-	return entry;
 }
 
 static __init void create_trace_options_dir(void)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 	int i;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
 		return;
 
-	for (i = 0; trace_options[i]; i++) {
-		entry = create_trace_option_core_file(trace_options[i], i);
-		if (!entry)
-			pr_warning("Could not create debugfs %s entry\n",
-				   trace_options[i]);
-	}
+	for (i = 0; trace_options[i]; i++)
+		create_trace_option_core_file(trace_options[i], i);
 }
 
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 	int cpu;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("tracing_enabled", 0644, d_tracer,
-				    &global_trace, &tracing_ctrl_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
+	trace_create_file("tracing_enabled", 0644, d_tracer,
+			&global_trace, &tracing_ctrl_fops);
 
-	entry = debugfs_create_file("trace_options", 0644, d_tracer,
-				    NULL, &tracing_iter_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_options' entry\n");
+	trace_create_file("trace_options", 0644, d_tracer,
+			NULL, &tracing_iter_fops);
 
-	create_trace_options_dir();
+	trace_create_file("tracing_cpumask", 0644, d_tracer,
+			NULL, &tracing_cpumask_fops);
+
+	trace_create_file("trace", 0644, d_tracer,
+			(void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
 
-	entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
-				    NULL, &tracing_cpumask_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
-
-	entry = debugfs_create_file("trace", 0644, d_tracer,
-				 (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace' entry\n");
-
-	entry = debugfs_create_file("available_tracers", 0444, d_tracer,
-				    &global_trace, &show_traces_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'available_tracers' entry\n");
-
-	entry = debugfs_create_file("current_tracer", 0444, d_tracer,
-				    &global_trace, &set_tracer_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'current_tracer' entry\n");
-
-	entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer,
-				    &tracing_max_latency,
-				    &tracing_max_lat_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'tracing_max_latency' entry\n");
-
-	entry = debugfs_create_file("tracing_thresh", 0644, d_tracer,
-				    &tracing_thresh, &tracing_max_lat_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'tracing_thresh' entry\n");
-	entry = debugfs_create_file("README", 0644, d_tracer,
-				    NULL, &tracing_readme_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'README' entry\n");
-
-	entry = debugfs_create_file("trace_pipe", 0444, d_tracer,
+	trace_create_file("available_tracers", 0444, d_tracer,
+			&global_trace, &show_traces_fops);
+
+	trace_create_file("current_tracer", 0644, d_tracer,
+			&global_trace, &set_tracer_fops);
+
+	trace_create_file("tracing_max_latency", 0644, d_tracer,
+			&tracing_max_latency, &tracing_max_lat_fops);
+
+	trace_create_file("tracing_thresh", 0644, d_tracer,
+			&tracing_thresh, &tracing_max_lat_fops);
+
+	trace_create_file("README", 0444, d_tracer,
+			NULL, &tracing_readme_fops);
+
+	trace_create_file("trace_pipe", 0444, d_tracer,
 			(void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'trace_pipe' entry\n");
-
-	entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
-				    &global_trace, &tracing_entries_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'buffer_size_kb' entry\n");
-
-	entry = debugfs_create_file("trace_marker", 0220, d_tracer,
-				    NULL, &tracing_mark_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'trace_marker' entry\n");
+
+	trace_create_file("buffer_size_kb", 0644, d_tracer,
+			&global_trace, &tracing_entries_fops);
+
+	trace_create_file("trace_marker", 0220, d_tracer,
+			NULL, &tracing_mark_fops);
+
+	trace_create_file("saved_cmdlines", 0444, d_tracer,
+			NULL, &tracing_saved_cmdlines_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
-				    &ftrace_update_tot_cnt,
-				    &tracing_dyn_info_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'dyn_ftrace_total_info' entry\n");
+	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
 #ifdef CONFIG_SYSPROF_TRACER
 	init_tracer_sysprof_debugfs(d_tracer);
 #endif
 
+	create_trace_options_dir();
+
 	for_each_tracing_cpu(cpu)
 		tracing_init_debugfs_percpu(cpu);
 
@@ -4064,7 +4184,8 @@ trace_printk_seq(struct trace_seq *s)
 
 static void __ftrace_dump(bool disable_tracing)
 {
-	static DEFINE_SPINLOCK(ftrace_dump_lock);
+	static raw_spinlock_t ftrace_dump_lock =
+		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
 	unsigned int old_userobj;
@@ -4073,7 +4194,8 @@ static void __ftrace_dump(bool disable_tracing)
 	int cnt = 0, cpu;
 
 	/* only one dump */
-	spin_lock_irqsave(&ftrace_dump_lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&ftrace_dump_lock);
 	if (dump_ran)
 		goto out;
 
@@ -4145,7 +4267,8 @@ static void __ftrace_dump(bool disable_tracing)
 	}
 
  out:
-	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+	__raw_spin_unlock(&ftrace_dump_lock);
+	local_irq_restore(flags);
 }
 
 /* By default: disable tracing after the dump */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e685ac2b2ba..6e735d4771f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,9 +9,12 @@
 #include <linux/mmiotrace.h>
 #include <linux/ftrace.h>
 #include <trace/boot.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <trace/power.h>
 
+#include <linux/trace_seq.h>
+#include <linux/ftrace_event.h>
+
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
 
@@ -42,20 +45,6 @@ enum trace_type {
 };
 
 /*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
- */
-struct trace_entry {
-	unsigned char		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			tgid;
-};
-
-/*
  * Function trace entry - function address and parent function addres:
  */
 struct ftrace_entry {
@@ -263,8 +252,6 @@ struct trace_array_cpu {
 	char			comm[TASK_COMM_LEN];
 };
 
-struct trace_iterator;
-
 /*
  * The trace array - an array of per-CPU trace arrays. This is the
  * highest level data structure that individual tracers deal with.
@@ -339,15 +326,6 @@ extern void __ftrace_bad_type(void);
 		__ftrace_bad_type();					\
 	} while (0)
 
-/* Return values for print_line callback */
-enum print_line_t {
-	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
-	TRACE_TYPE_HANDLED	= 1,
-	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
-	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
-};
-
-
 /*
  * An option specific to a tracer. This is a boolean value.
  * The bit is the bit index that sets its value on the
@@ -423,60 +401,30 @@ struct tracer {
 	struct tracer_stat	*stats;
 };
 
-struct trace_seq {
-	unsigned char		buffer[PAGE_SIZE];
-	unsigned int		len;
-	unsigned int		readpos;
-};
-
-static inline void
-trace_seq_init(struct trace_seq *s)
-{
-	s->len = 0;
-	s->readpos = 0;
-}
-
 
 #define TRACE_PIPE_ALL_CPU	-1
 
-/*
- * Trace iterator - used by printout routines who present trace
- * results to users and which routines might sleep, etc:
- */
-struct trace_iterator {
-	struct trace_array	*tr;
-	struct tracer		*trace;
-	void			*private;
-	int			cpu_file;
-	struct mutex		mutex;
-	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
-
-	/* The below is zeroed out in pipe_read */
-	struct trace_seq	seq;
-	struct trace_entry	*ent;
-	int			cpu;
-	u64			ts;
-
-	unsigned long		iter_flags;
-	loff_t			pos;
-	long			idx;
-
-	cpumask_var_t		started;
-};
-
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset_current(int cpu);
+void tracing_reset_current_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
+struct dentry *trace_create_file(const char *name,
+				 mode_t mode,
+				 struct dentry *parent,
+				 void *data,
+				 const struct file_operations *fops);
+
 struct dentry *tracing_init_dentry(void);
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    unsigned char type,
+						    int type,
 						    unsigned long len,
 						    unsigned long flags,
 						    int pc);
@@ -484,14 +432,6 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
-struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
-				  unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
 
@@ -514,7 +454,6 @@ void tracing_sched_switch_trace(struct trace_array *tr,
 				struct task_struct *prev,
 				struct task_struct *next,
 				unsigned long flags, int pc);
-void tracing_record_cmdline(struct task_struct *tsk);
 
 void tracing_sched_wakeup_trace(struct trace_array *tr,
 				struct task_struct *wakee,
@@ -599,6 +538,8 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
+extern int trace_selftest_startup_hw_branches(struct tracer *trace,
+					      struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -613,6 +554,8 @@ extern unsigned long trace_flags;
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
@@ -644,7 +587,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
 	return 1;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
-
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
 print_graph_function(struct trace_iterator *iter)
@@ -692,6 +634,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
 	TRACE_ITER_GLOBAL_CLK		= 0x80000,
 	TRACE_ITER_SLEEP_TIME		= 0x100000,
+	TRACE_ITER_GRAPH_TIME		= 0x200000,
 };
 
 /*
@@ -790,103 +733,113 @@ struct ftrace_event_field {
 	char			*type;
 	int			offset;
 	int			size;
+	int			is_signed;
 };
 
-struct ftrace_event_call {
-	char			*name;
-	char			*system;
-	struct dentry		*dir;
-	int			enabled;
-	int			(*regfunc)(void);
-	void			(*unregfunc)(void);
-	int			id;
-	int			(*raw_init)(void);
-	int			(*show_format)(struct trace_seq *s);
-	int			(*define_fields)(void);
-	struct list_head	fields;
+struct event_filter {
+	int			n_preds;
 	struct filter_pred	**preds;
-
-#ifdef CONFIG_EVENT_PROFILE
-	atomic_t	profile_count;
-	int		(*profile_enable)(struct ftrace_event_call *);
-	void		(*profile_disable)(struct ftrace_event_call *);
-#endif
+	char			*filter_string;
 };
 
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
 	struct dentry		*entry;
-	struct filter_pred	**preds;
+	void			*filter;
 };
 
-#define events_for_each(event)						\
-	for (event = __start_ftrace_events;				\
-	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
-	     event++)
-
-#define MAX_FILTER_PRED 8
-
 struct filter_pred;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
+				 int val1, int val2);
 
 struct filter_pred {
 	filter_pred_fn_t fn;
 	u64 val;
-	char *str_val;
+	char str_val[MAX_FILTER_STR_VAL];
 	int str_len;
 	char *field_name;
 	int offset;
 	int not;
-	int or;
-	int compound;
-	int clear;
+	int op;
+	int pop_n;
 };
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size);
-extern void filter_free_pred(struct filter_pred *pred);
-extern void filter_print_preds(struct filter_pred **preds,
+extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
-extern int filter_parse(char **pbuf, struct filter_pred *pred);
-extern int filter_add_pred(struct ftrace_event_call *call,
-			   struct filter_pred *pred);
-extern void filter_free_preds(struct ftrace_event_call *call);
-extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern void filter_free_subsystem_preds(struct event_subsystem *system);
-extern int filter_add_subsystem_pred(struct event_subsystem *system,
-				     struct filter_pred *pred);
-
-void event_trace_printk(unsigned long ip, const char *fmt, ...);
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
-
-#define for_each_event(event)						\
-	for (event = __start_ftrace_events;				\
-	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
-	     event++)
+extern int apply_event_filter(struct ftrace_event_call *call,
+			      char *filter_string);
+extern int apply_subsystem_event_filter(struct event_subsystem *system,
+					char *filter_string);
+extern void print_subsystem_event_filter(struct event_subsystem *system,
+					 struct trace_seq *s);
+
+static inline int
+filter_check_discard(struct ftrace_event_call *call, void *rec,
+		     struct ring_buffer *buffer,
+		     struct ring_buffer_event *event)
+{
+	if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+		ring_buffer_discard_commit(buffer, event);
+		return 1;
+	}
+
+	return 0;
+}
+
+#define DEFINE_COMPARISON_PRED(type)					\
+static int filter_pred_##type(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	type *addr = (type *)(event + pred->offset);			\
+	type val = (type)pred->val;					\
+	int match = 0;							\
+									\
+	switch (pred->op) {						\
+	case OP_LT:							\
+		match = (*addr < val);					\
+		break;							\
+	case OP_LE:							\
+		match = (*addr <= val);					\
+		break;							\
+	case OP_GT:							\
+		match = (*addr > val);					\
+		break;							\
+	case OP_GE:							\
+		match = (*addr >= val);					\
+		break;							\
+	default:							\
+		break;							\
+	}								\
+									\
+	return match;							\
+}
+
+#define DEFINE_EQUALITY_PRED(size)					\
+static int filter_pred_##size(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	u##size *addr = (u##size *)(event + pred->offset);		\
+	u##size val = (u##size)pred->val;				\
+	int match;							\
+									\
+	match = (val == *addr) ^ pred->not;				\
+									\
+	return match;							\
+}
+
+extern struct mutex event_mutex;
+extern struct list_head ftrace_events;
 
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
-/*
- * The double __builtin_constant_p is because gcc will give us an error
- * if we try to allocate the static variable to fmt if it is not a
- * constant. Even with the outer if statement optimizing out.
- */
-#define event_trace_printk(ip, fmt, args...)				\
-do {									\
-	__trace_printk_check_format(fmt, ##args);			\
-	tracing_record_cmdline(current);				\
-	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
-			__builtin_constant_p(fmt) ? fmt : NULL;		\
-									\
-		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
-	} else								\
-		__trace_printk(ip, fmt, ##args);			\
-} while (0)
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+	extern struct ftrace_event_call event_##call;
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
+#include "trace_event_types.h"
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7a30fc4c364..a29ef23ffb4 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
 #include <linux/kallsyms.h>
+#include <linux/time.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -67,7 +68,7 @@ initcall_call_print_line(struct trace_iterator *iter)
 	trace_assign_type(field, entry);
 	call = &field->boot_call;
 	ts = iter->ts;
-	nsec_rem = do_div(ts, 1000000000);
+	nsec_rem = do_div(ts, NSEC_PER_SEC);
 
 	ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
 			(unsigned long)ts, nsec_rem, call->func, call->caller);
@@ -92,7 +93,7 @@ initcall_ret_print_line(struct trace_iterator *iter)
 	trace_assign_type(field, entry);
 	init_ret = &field->boot_ret;
 	ts = iter->ts;
-	nsec_rem = do_div(ts, 1000000000);
+	nsec_rem = do_div(ts, NSEC_PER_SEC);
 
 	ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
 			"returned %d after %llu msecs\n",
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 8333715e406..7a7a9fd249a 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -30,6 +30,7 @@ static struct trace_array *branch_tracer;
 static void
 probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 {
+	struct ftrace_event_call *call = &event_branch;
 	struct trace_array *tr = branch_tracer;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
@@ -73,7 +74,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
@@ -271,7 +273,7 @@ static int branch_stat_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static void *annotated_branch_stat_start(void)
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
 {
 	return __start_annotated_branch_profile;
 }
@@ -346,7 +348,7 @@ static int all_branch_stat_headers(struct seq_file *m)
 	return 0;
 }
 
-static void *all_branch_stat_start(void)
+static void *all_branch_stat_start(struct tracer_stat *trace)
 {
 	return __start_branch_profile;
 }
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 22cba997077..5b5895afecf 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -10,22 +10,30 @@
 int ftrace_profile_enable(int event_id)
 {
 	struct ftrace_event_call *event;
+	int ret = -EINVAL;
 
-	for_each_event(event) {
-		if (event->id == event_id)
-			return event->profile_enable(event);
+	mutex_lock(&event_mutex);
+	list_for_each_entry(event, &ftrace_events, list) {
+		if (event->id == event_id) {
+			ret = event->profile_enable(event);
+			break;
+		}
 	}
+	mutex_unlock(&event_mutex);
 
-	return -EINVAL;
+	return ret;
 }
 
 void ftrace_profile_disable(int event_id)
 {
 	struct ftrace_event_call *event;
 
-	for_each_event(event) {
-		if (event->id == event_id)
-			return event->profile_disable(event);
+	mutex_lock(&event_mutex);
+	list_for_each_entry(event, &ftrace_events, list) {
+		if (event->id == event_id) {
+			event->profile_disable(event);
+			break;
+		}
 	}
+	mutex_unlock(&event_mutex);
 }
-
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index fd78bee71dd..5e32e375134 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -57,7 +57,7 @@ TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore,
 	TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
 );
 
-TRACE_EVENT_FORMAT(special, TRACE_SPECIAL, special_entry, ignore,
+TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, arg1, arg1)
 		TRACE_FIELD(unsigned long, arg2, arg2)
@@ -122,8 +122,10 @@ TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
 TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned int, line, line)
-		TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, func)
-		TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, file)
+		TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
+				    TRACE_FUNC_SIZE+1, func)
+		TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
+				    TRACE_FUNC_SIZE+1, file)
 		TRACE_FIELD(char, correct, correct)
 	),
 	TP_RAW_FMT("%u:%s:%s (%u)")
@@ -139,8 +141,8 @@ TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore,
 
 TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
 	TRACE_STRUCT(
-		TRACE_FIELD(ktime_t, state_data.stamp, stamp)
-		TRACE_FIELD(ktime_t, state_data.end, end)
+		TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
+		TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
 		TRACE_FIELD(int, state_data.type, type)
 		TRACE_FIELD(int, state_data.state, state)
 	),
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 576f4fa2af0..aa08be69a1b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -8,19 +8,25 @@
  *
  */
 
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/delay.h>
 
 #include "trace_output.h"
 
 #define TRACE_SYSTEM "TRACE_SYSTEM"
 
-static DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_mutex);
+
+LIST_HEAD(ftrace_events);
 
 int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size)
+		       char *name, int offset, int size, int is_signed)
 {
 	struct ftrace_event_field *field;
 
@@ -38,6 +44,7 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
 
 	field->offset = offset;
 	field->size = size;
+	field->is_signed = is_signed;
 	list_add(&field->link, &call->fields);
 
 	return 0;
@@ -51,47 +58,94 @@ err:
 
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(trace_define_field);
 
-static void ftrace_clear_events(void)
-{
-	struct ftrace_event_call *call = (void *)__start_ftrace_events;
-
+#ifdef CONFIG_MODULES
 
-	while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {
+static void trace_destroy_fields(struct ftrace_event_call *call)
+{
+	struct ftrace_event_field *field, *next;
 
-		if (call->enabled) {
-			call->enabled = 0;
-			call->unregfunc();
-		}
-		call++;
+	list_for_each_entry_safe(field, next, &call->fields, link) {
+		list_del(&field->link);
+		kfree(field->type);
+		kfree(field->name);
+		kfree(field);
 	}
 }
 
+#endif /* CONFIG_MODULES */
+
 static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
-
 	switch (enable) {
 	case 0:
 		if (call->enabled) {
 			call->enabled = 0;
+			tracing_stop_cmdline_record();
 			call->unregfunc();
 		}
 		break;
 	case 1:
 		if (!call->enabled) {
 			call->enabled = 1;
+			tracing_start_cmdline_record();
 			call->regfunc();
 		}
 		break;
 	}
 }
 
+static void ftrace_clear_events(void)
+{
+	struct ftrace_event_call *call;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		ftrace_event_enable_disable(call, 0);
+	}
+	mutex_unlock(&event_mutex);
+}
+
+/*
+ * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
+ */
+static int __ftrace_set_clr_event(const char *match, const char *sub,
+				  const char *event, int set)
+{
+	struct ftrace_event_call *call;
+	int ret = -EINVAL;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (match &&
+		    strcmp(match, call->name) != 0 &&
+		    strcmp(match, call->system) != 0)
+			continue;
+
+		if (sub && strcmp(sub, call->system) != 0)
+			continue;
+
+		if (event && strcmp(event, call->name) != 0)
+			continue;
+
+		ftrace_event_enable_disable(call, set);
+
+		ret = 0;
+	}
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
 static int ftrace_set_clr_event(char *buf, int set)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
 	char *event = NULL, *sub = NULL, *match;
-	int ret = -EINVAL;
 
 	/*
 	 * The buf format can be <subsystem>:<event-name>
@@ -117,30 +171,24 @@ static int ftrace_set_clr_event(char *buf, int set)
 			event = NULL;
 	}
 
-	mutex_lock(&event_mutex);
-	for_each_event(call) {
-
-		if (!call->name || !call->regfunc)
-			continue;
-
-		if (match &&
-		    strcmp(match, call->name) != 0 &&
-		    strcmp(match, call->system) != 0)
-			continue;
-
-		if (sub && strcmp(sub, call->system) != 0)
-			continue;
-
-		if (event && strcmp(event, call->name) != 0)
-			continue;
-
-		ftrace_event_enable_disable(call, set);
-
-		ret = 0;
-	}
-	mutex_unlock(&event_mutex);
+	return __ftrace_set_clr_event(match, sub, event, set);
+}
 
-	return ret;
+/**
+ * trace_set_clr_event - enable or disable an event
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @set: 1 to enable, 0 to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_set_clr_event(const char *system, const char *event, int set)
+{
+	return __ftrace_set_clr_event(NULL, system, event, set);
 }
 
 /* 128 should be much more than enough */
@@ -224,15 +272,17 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = m->private;
-	struct ftrace_event_call *next = call;
+	struct list_head *list = m->private;
+	struct ftrace_event_call *call;
 
 	(*pos)++;
 
 	for (;;) {
-		if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+		if (list == &ftrace_events)
 			return NULL;
 
+		call = list_entry(list, struct ftrace_event_call, list);
+
 		/*
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
@@ -240,45 +290,51 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		if (call->regfunc)
 			break;
 
-		call++;
-		next = call;
+		list = list->next;
 	}
 
-	m->private = ++next;
+	m->private = list->next;
 
 	return call;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&event_mutex);
+	if (*pos == 0)
+		m->private = ftrace_events.next;
 	return t_next(m, NULL, pos);
 }
 
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = m->private;
-	struct ftrace_event_call *next;
+	struct list_head *list = m->private;
+	struct ftrace_event_call *call;
 
 	(*pos)++;
 
  retry:
-	if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+	if (list == &ftrace_events)
 		return NULL;
 
+	call = list_entry(list, struct ftrace_event_call, list);
+
 	if (!call->enabled) {
-		call++;
+		list = list->next;
 		goto retry;
 	}
 
-	next = call;
-	m->private = ++next;
+	m->private = list->next;
 
 	return call;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&event_mutex);
+	if (*pos == 0)
+		m->private = ftrace_events.next;
 	return s_next(m, NULL, pos);
 }
 
@@ -295,12 +351,12 @@ static int t_show(struct seq_file *m, void *v)
 
 static void t_stop(struct seq_file *m, void *p)
 {
+	mutex_unlock(&event_mutex);
 }
 
 static int
 ftrace_event_seq_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	const struct seq_operations *seq_ops;
 
 	if ((file->f_mode & FMODE_WRITE) &&
@@ -308,13 +364,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
 		ftrace_clear_events();
 
 	seq_ops = inode->i_private;
-	ret = seq_open(file, seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = __start_ftrace_events;
-	}
-	return ret;
+	return seq_open(file, seq_ops);
 }
 
 static ssize_t
@@ -374,8 +424,93 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	return cnt;
 }
 
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+		   loff_t *ppos)
+{
+	const char set_to_char[4] = { '?', '0', '1', 'X' };
+	const char *system = filp->private_data;
+	struct ftrace_event_call *call;
+	char buf[2];
+	int set = 0;
+	int ret;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (system && strcmp(call->system, system) != 0)
+			continue;
+
+		/*
+		 * We need to find out if all the events are set
+		 * or if all events or cleared, or if we have
+		 * a mixture.
+		 */
+		set |= (1 << !!call->enabled);
+
+		/*
+		 * If we have a mixture, no need to look further.
+		 */
+		if (set == 3)
+			break;
+	}
+	mutex_unlock(&event_mutex);
+
+	buf[0] = set_to_char[set];
+	buf[1] = '\n';
+
+	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+
+	return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		    loff_t *ppos)
+{
+	const char *system = filp->private_data;
+	unsigned long val;
+	char buf[64];
+	ssize_t ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+	if (ret)
+		goto out;
+
+	ret = cnt;
+
+out:
+	*ppos += cnt;
+
+	return ret;
+}
+
+extern char *__bad_type_size(void);
+
 #undef FIELD
 #define FIELD(type, name)						\
+	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
 	#type, "common_" #name, offsetof(typeof(field), name),		\
 		sizeof(field.name)
 
@@ -391,7 +526,7 @@ static int trace_write_header(struct trace_seq *s)
 				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
 				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
 				"\n",
-				FIELD(unsigned char, type),
+				FIELD(unsigned short, type),
 				FIELD(unsigned char, flags),
 				FIELD(unsigned char, preempt_count),
 				FIELD(int, pid),
@@ -481,7 +616,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_preds(call->preds, s);
+	print_event_filter(call, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -494,38 +629,26 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
-	char buf[64], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
-	}
-
-	if (pred->clear) {
-		filter_free_preds(call);
-		filter_free_pred(pred);
-		return cnt;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	err = filter_add_pred(call, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
+	err = apply_event_filter(call, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
 
 	*ppos += cnt;
 
@@ -549,7 +672,7 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_preds(system->preds, s);
+	print_subsystem_event_filter(system, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -562,45 +685,56 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		       loff_t *ppos)
 {
 	struct event_subsystem *system = filp->private_data;
-	char buf[64], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
-	}
-
-	if (pred->clear) {
-		filter_free_subsystem_preds(system);
-		filter_free_pred(pred);
-		return cnt;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	err = filter_add_subsystem_pred(system, pred);
-	if (err < 0) {
-		filter_free_subsystem_preds(system);
-		filter_free_pred(pred);
+	err = apply_subsystem_event_filter(system, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
 
 	*ppos += cnt;
 
 	return cnt;
 }
 
+static ssize_t
+show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	func(s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -658,6 +792,17 @@ static const struct file_operations ftrace_subsystem_filter_fops = {
 	.write = subsystem_filter_write,
 };
 
+static const struct file_operations ftrace_system_enable_fops = {
+	.open = tracing_open_generic,
+	.read = system_enable_read,
+	.write = system_enable_write,
+};
+
+static const struct file_operations ftrace_show_header_fops = {
+	.open = tracing_open_generic,
+	.read = show_header,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -684,6 +829,7 @@ static struct dentry *
 event_subsystem_dir(const char *name, struct dentry *d_events)
 {
 	struct event_subsystem *system;
+	struct dentry *entry;
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
@@ -707,16 +853,46 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 		return d_events;
 	}
 
-	system->name = name;
+	system->name = kstrdup(name, GFP_KERNEL);
+	if (!system->name) {
+		debugfs_remove(system->entry);
+		kfree(system);
+		return d_events;
+	}
+
 	list_add(&system->list, &event_subsystems);
 
-	system->preds = NULL;
+	system->filter = NULL;
+
+	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+	if (!system->filter) {
+		pr_warning("Could not allocate filter for subsystem "
+			   "'%s'\n", name);
+		return system->entry;
+	}
+
+	entry = debugfs_create_file("filter", 0644, system->entry, system,
+				    &ftrace_subsystem_filter_fops);
+	if (!entry) {
+		kfree(system->filter);
+		system->filter = NULL;
+		pr_warning("Could not create debugfs "
+			   "'%s/filter' entry\n", name);
+	}
+
+	entry = trace_create_file("enable", 0644, system->entry,
+				  (void *)system->name,
+				  &ftrace_system_enable_fops);
 
 	return system->entry;
 }
 
 static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+		 const struct file_operations *id,
+		 const struct file_operations *enable,
+		 const struct file_operations *filter,
+		 const struct file_operations *format)
 {
 	struct dentry *entry;
 	int ret;
@@ -725,7 +901,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 	 * If the trace point header did not define TRACE_SYSTEM
 	 * then the system would be called "TRACE_SYSTEM".
 	 */
-	if (strcmp(call->system, "TRACE_SYSTEM") != 0)
+	if (strcmp(call->system, TRACE_SYSTEM) != 0)
 		d_events = event_subsystem_dir(call->system, d_events);
 
 	if (call->raw_init) {
@@ -744,21 +920,13 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 		return -1;
 	}
 
-	if (call->regfunc) {
-		entry = debugfs_create_file("enable", 0644, call->dir, call,
-					    &ftrace_enable_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs "
-				   "'%s/enable' entry\n", call->name);
-	}
+	if (call->regfunc)
+		entry = trace_create_file("enable", 0644, call->dir, call,
+					  enable);
 
-	if (call->id) {
-		entry = debugfs_create_file("id", 0444, call->dir, call,
-				&ftrace_event_id_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs '%s/id' entry\n",
-					call->name);
-	}
+	if (call->id)
+		entry = trace_create_file("id", 0444, call->dir, call,
+					  id);
 
 	if (call->define_fields) {
 		ret = call->define_fields();
@@ -767,32 +935,195 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 				   " events/%s\n", call->name);
 			return ret;
 		}
-		entry = debugfs_create_file("filter", 0644, call->dir, call,
-					    &ftrace_event_filter_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs "
-				   "'%s/filter' entry\n", call->name);
+		entry = trace_create_file("filter", 0644, call->dir, call,
+					  filter);
 	}
 
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;
 
-	entry = debugfs_create_file("format", 0444, call->dir, call,
-				    &ftrace_event_format_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'%s/format' entry\n", call->name);
+	entry = trace_create_file("format", 0444, call->dir, call,
+				  format);
+
+	return 0;
+}
+
+#define for_each_event(event, start, end)			\
+	for (event = start;					\
+	     (unsigned long)event < (unsigned long)end;		\
+	     event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+	struct list_head		list;
+	struct module			*mod;
+	struct file_operations		id;
+	struct file_operations		enable;
+	struct file_operations		format;
+	struct file_operations		filter;
+};
+
+static struct ftrace_module_file_ops *
+trace_create_file_ops(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops;
+
+	/*
+	 * This is a bit of a PITA. To allow for correct reference
+	 * counting, modules must "own" their file_operations.
+	 * To do this, we allocate the file operations that will be
+	 * used in the event directory.
+	 */
+
+	file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
+	if (!file_ops)
+		return NULL;
+
+	file_ops->mod = mod;
+
+	file_ops->id = ftrace_event_id_fops;
+	file_ops->id.owner = mod;
+
+	file_ops->enable = ftrace_enable_fops;
+	file_ops->enable.owner = mod;
+
+	file_ops->filter = ftrace_event_filter_fops;
+	file_ops->filter.owner = mod;
+
+	file_ops->format = ftrace_event_format_fops;
+	file_ops->format.owner = mod;
+
+	list_add(&file_ops->list, &ftrace_module_file_list);
+
+	return file_ops;
+}
+
+static void trace_module_add_events(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops = NULL;
+	struct ftrace_event_call *call, *start, *end;
+	struct dentry *d_events;
+
+	start = mod->trace_events;
+	end = mod->trace_events + mod->num_trace_events;
+
+	if (start == end)
+		return;
+
+	d_events = event_trace_events_dir();
+	if (!d_events)
+		return;
+
+	for_each_event(call, start, end) {
+		/* The linker may leave blanks */
+		if (!call->name)
+			continue;
+
+		/*
+		 * This module has events, create file ops for this module
+		 * if not already done.
+		 */
+		if (!file_ops) {
+			file_ops = trace_create_file_ops(mod);
+			if (!file_ops)
+				return;
+		}
+		call->mod = mod;
+		list_add(&call->list, &ftrace_events);
+		event_create_dir(call, d_events,
+				 &file_ops->id, &file_ops->enable,
+				 &file_ops->filter, &file_ops->format);
+	}
+}
+
+static void trace_module_remove_events(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops;
+	struct ftrace_event_call *call, *p;
+	bool found = false;
+
+	down_write(&trace_event_mutex);
+	list_for_each_entry_safe(call, p, &ftrace_events, list) {
+		if (call->mod == mod) {
+			found = true;
+			ftrace_event_enable_disable(call, 0);
+			if (call->event)
+				__unregister_ftrace_event(call->event);
+			debugfs_remove_recursive(call->dir);
+			list_del(&call->list);
+			trace_destroy_fields(call);
+			destroy_preds(call);
+		}
+	}
+
+	/* Now free the file_operations */
+	list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+		if (file_ops->mod == mod)
+			break;
+	}
+	if (&file_ops->list != &ftrace_module_file_list) {
+		list_del(&file_ops->list);
+		kfree(file_ops);
+	}
+
+	/*
+	 * It is safest to reset the ring buffer if the module being unloaded
+	 * registered any events.
+	 */
+	if (found)
+		tracing_reset_current_online_cpus();
+	up_write(&trace_event_mutex);
+}
+
+static int trace_module_notify(struct notifier_block *self,
+			       unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	mutex_lock(&event_mutex);
+	switch (val) {
+	case MODULE_STATE_COMING:
+		trace_module_add_events(mod);
+		break;
+	case MODULE_STATE_GOING:
+		trace_module_remove_events(mod);
+		break;
+	}
+	mutex_unlock(&event_mutex);
 
 	return 0;
 }
+#else
+static int trace_module_notify(struct notifier_block *self,
+			       unsigned long val, void *data)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block trace_module_nb = {
+	.notifier_call = trace_module_notify,
+	.priority = 0,
+};
+
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
 
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
+	struct ftrace_event_call *call;
 	struct dentry *d_tracer;
 	struct dentry *entry;
 	struct dentry *d_events;
+	int ret;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -816,13 +1147,243 @@ static __init int event_trace_init(void)
 	if (!d_events)
 		return 0;
 
-	for_each_event(call) {
+	/* ring buffer internal formats */
+	trace_create_file("header_page", 0444, d_events,
+			  ring_buffer_print_page_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("header_event", 0444, d_events,
+			  ring_buffer_print_entry_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("enable", 0644, d_events,
+			  NULL, &ftrace_system_enable_fops);
+
+	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-		event_create_dir(call, d_events);
+		list_add(&call->list, &ftrace_events);
+		event_create_dir(call, d_events, &ftrace_event_id_fops,
+				 &ftrace_enable_fops, &ftrace_event_filter_fops,
+				 &ftrace_event_format_fops);
 	}
 
+	ret = register_module_notifier(&trace_module_nb);
+	if (ret)
+		pr_warning("Failed to register trace events module notifier\n");
+
 	return 0;
 }
 fs_initcall(event_trace_init);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_SPINLOCK(test_spinlock_irq);
+static DEFINE_MUTEX(test_mutex);
+
+static __init void test_work(struct work_struct *dummy)
+{
+	spin_lock(&test_spinlock);
+	spin_lock_irq(&test_spinlock_irq);
+	udelay(1);
+	spin_unlock_irq(&test_spinlock_irq);
+	spin_unlock(&test_spinlock);
+
+	mutex_lock(&test_mutex);
+	msleep(1);
+	mutex_unlock(&test_mutex);
+}
+
+static __init int event_test_thread(void *unused)
+{
+	void *test_malloc;
+
+	test_malloc = kmalloc(1234, GFP_KERNEL);
+	if (!test_malloc)
+		pr_info("failed to kmalloc\n");
+
+	schedule_on_each_cpu(test_work);
+
+	kfree(test_malloc);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop())
+		schedule();
+
+	return 0;
+}
+
+/*
+ * Do various things that may trigger events.
+ */
+static __init void event_test_stuff(void)
+{
+	struct task_struct *test_thread;
+
+	test_thread = kthread_run(event_test_thread, NULL, "test-events");
+	msleep(1);
+	kthread_stop(test_thread);
+}
+
+/*
+ * For every trace event defined, we will test each trace point separately,
+ * and then by groups, and finally all trace points.
+ */
+static __init void event_trace_self_tests(void)
+{
+	struct ftrace_event_call *call;
+	struct event_subsystem *system;
+	int ret;
+
+	pr_info("Running tests on trace events:\n");
+
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		/* Only test those that have a regfunc */
+		if (!call->regfunc)
+			continue;
+
+		pr_info("Testing event %s: ", call->name);
+
+		/*
+		 * If an event is already enabled, someone is using
+		 * it and the self test should not be on.
+		 */
+		if (call->enabled) {
+			pr_warning("Enabled event during self test!\n");
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		ftrace_event_enable_disable(call, 1);
+		event_test_stuff();
+		ftrace_event_enable_disable(call, 0);
+
+		pr_cont("OK\n");
+	}
+
+	/* Now test at the sub system level */
+
+	pr_info("Running tests on trace event systems:\n");
+
+	list_for_each_entry(system, &event_subsystems, list) {
+
+		/* the ftrace system is special, skip it */
+		if (strcmp(system->name, "ftrace") == 0)
+			continue;
+
+		pr_info("Testing event system %s: ", system->name);
+
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+		if (WARN_ON_ONCE(ret)) {
+			pr_warning("error enabling system %s\n",
+				   system->name);
+			continue;
+		}
+
+		event_test_stuff();
+
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+		if (WARN_ON_ONCE(ret))
+			pr_warning("error disabling system %s\n",
+				   system->name);
+
+		pr_cont("OK\n");
+	}
+
+	/* Test with all events enabled */
+
+	pr_info("Running tests on all trace events:\n");
+	pr_info("Testing all events: ");
+
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+	if (WARN_ON_ONCE(ret)) {
+		pr_warning("error enabling all events\n");
+		return;
+	}
+
+	event_test_stuff();
+
+	/* reset sysname */
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+	if (WARN_ON_ONCE(ret)) {
+		pr_warning("error disabling all events\n");
+		return;
+	}
+
+	pr_cont("OK\n");
+}
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static DEFINE_PER_CPU(atomic_t, test_event_disable);
+
+static void
+function_test_events_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ring_buffer_event *event;
+	struct ftrace_entry *entry;
+	unsigned long flags;
+	long disabled;
+	int resched;
+	int cpu;
+	int pc;
+
+	pc = preempt_count();
+	resched = ftrace_preempt_disable();
+	cpu = raw_smp_processor_id();
+	disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+
+	if (disabled != 1)
+		goto out;
+
+	local_save_flags(flags);
+
+	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+						  flags, pc);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	entry->ip			= ip;
+	entry->parent_ip		= parent_ip;
+
+	trace_nowake_buffer_unlock_commit(event, flags, pc);
+
+ out:
+	atomic_dec(&per_cpu(test_event_disable, cpu));
+	ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __initdata  =
+{
+	.func = function_test_events_call,
+};
+
+static __init void event_trace_self_test_with_function(void)
+{
+	register_ftrace_function(&trace_ops);
+	pr_info("Running tests again, along with the function tracer\n");
+	event_trace_self_tests();
+	unregister_ftrace_function(&trace_ops);
+}
+#else
+static __init void event_trace_self_test_with_function(void)
+{
+}
+#endif
+
+static __init int event_trace_self_tests_init(void)
+{
+
+	event_trace_self_tests();
+
+	event_trace_self_test_with_function();
+
+	return 0;
+}
+
+late_initcall(event_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e03cbf1e38f..db6e54bdb59 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,119 +22,297 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/mutex.h>
 
 #include "trace.h"
 #include "trace_output.h"
 
-static int filter_pred_64(struct filter_pred *pred, void *event)
+static DEFINE_MUTEX(filter_mutex);
+
+enum filter_op_ids
+{
+	OP_OR,
+	OP_AND,
+	OP_NE,
+	OP_EQ,
+	OP_LT,
+	OP_LE,
+	OP_GT,
+	OP_GE,
+	OP_NONE,
+	OP_OPEN_PAREN,
+};
+
+struct filter_op {
+	int id;
+	char *string;
+	int precedence;
+};
+
+static struct filter_op filter_ops[] = {
+	{ OP_OR, "||", 1 },
+	{ OP_AND, "&&", 2 },
+	{ OP_NE, "!=", 4 },
+	{ OP_EQ, "==", 4 },
+	{ OP_LT, "<", 5 },
+	{ OP_LE, "<=", 5 },
+	{ OP_GT, ">", 5 },
+	{ OP_GE, ">=", 5 },
+	{ OP_NONE, "OP_NONE", 0 },
+	{ OP_OPEN_PAREN, "(", 0 },
+};
+
+enum {
+	FILT_ERR_NONE,
+	FILT_ERR_INVALID_OP,
+	FILT_ERR_UNBALANCED_PAREN,
+	FILT_ERR_TOO_MANY_OPERANDS,
+	FILT_ERR_OPERAND_TOO_LONG,
+	FILT_ERR_FIELD_NOT_FOUND,
+	FILT_ERR_ILLEGAL_FIELD_OP,
+	FILT_ERR_ILLEGAL_INTVAL,
+	FILT_ERR_BAD_SUBSYS_FILTER,
+	FILT_ERR_TOO_MANY_PREDS,
+	FILT_ERR_MISSING_FIELD,
+	FILT_ERR_INVALID_FILTER,
+};
+
+static char *err_text[] = {
+	"No error",
+	"Invalid operator",
+	"Unbalanced parens",
+	"Too many operands",
+	"Operand too long",
+	"Field not found",
+	"Illegal operation for field type",
+	"Illegal integer value",
+	"Couldn't find or set field in one of a subsystem's events",
+	"Too many terms in predicate expression",
+	"Missing field name and/or value",
+	"Meaningless filter expression",
+};
+
+struct opstack_op {
+	int op;
+	struct list_head list;
+};
+
+struct postfix_elt {
+	int op;
+	char *operand;
+	struct list_head list;
+};
+
+struct filter_parse_state {
+	struct filter_op *ops;
+	struct list_head opstack;
+	struct list_head postfix;
+	int lasterr;
+	int lasterr_pos;
+
+	struct {
+		char *string;
+		unsigned int cnt;
+		unsigned int tail;
+	} infix;
+
+	struct {
+		char string[MAX_FILTER_STR_VAL];
+		int pos;
+		unsigned int tail;
+	} operand;
+};
+
+DEFINE_COMPARISON_PRED(s64);
+DEFINE_COMPARISON_PRED(u64);
+DEFINE_COMPARISON_PRED(s32);
+DEFINE_COMPARISON_PRED(u32);
+DEFINE_COMPARISON_PRED(s16);
+DEFINE_COMPARISON_PRED(u16);
+DEFINE_COMPARISON_PRED(s8);
+DEFINE_COMPARISON_PRED(u8);
+
+DEFINE_EQUALITY_PRED(64);
+DEFINE_EQUALITY_PRED(32);
+DEFINE_EQUALITY_PRED(16);
+DEFINE_EQUALITY_PRED(8);
+
+static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
+			   void *event __attribute((unused)),
+			   int val1, int val2)
+{
+	return val1 && val2;
+}
+
+static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
+			  void *event __attribute((unused)),
+			  int val1, int val2)
+{
+	return val1 || val2;
+}
+
+/* Filter predicate for fixed sized arrays of characters */
+static int filter_pred_string(struct filter_pred *pred, void *event,
+			      int val1, int val2)
 {
-	u64 *addr = (u64 *)(event + pred->offset);
-	u64 val = (u64)pred->val;
-	int match;
+	char *addr = (char *)(event + pred->offset);
+	int cmp, match;
+
+	cmp = strncmp(addr, pred->str_val, pred->str_len);
 
-	match = (val == *addr) ^ pred->not;
+	match = (!cmp) ^ pred->not;
 
 	return match;
 }
 
-static int filter_pred_32(struct filter_pred *pred, void *event)
+/*
+ * Filter predicate for dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry.
+ * Also each of these strings have a field in the entry which
+ * contains its offset from the beginning of the entry.
+ * We have then first to get this field, dereference it
+ * and add it to the address of the entry, and at last we have
+ * the address of the string.
+ */
+static int filter_pred_strloc(struct filter_pred *pred, void *event,
+			      int val1, int val2)
 {
-	u32 *addr = (u32 *)(event + pred->offset);
-	u32 val = (u32)pred->val;
-	int match;
+	int str_loc = *(int *)(event + pred->offset);
+	char *addr = (char *)(event + str_loc);
+	int cmp, match;
+
+	cmp = strncmp(addr, pred->str_val, pred->str_len);
 
-	match = (val == *addr) ^ pred->not;
+	match = (!cmp) ^ pred->not;
 
 	return match;
 }
 
-static int filter_pred_16(struct filter_pred *pred, void *event)
+static int filter_pred_none(struct filter_pred *pred, void *event,
+			    int val1, int val2)
+{
+	return 0;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
 {
-	u16 *addr = (u16 *)(event + pred->offset);
-	u16 val = (u16)pred->val;
-	int match;
+	struct event_filter *filter = call->filter;
+	int match, top = 0, val1 = 0, val2 = 0;
+	int stack[MAX_FILTER_PRED];
+	struct filter_pred *pred;
+	int i;
+
+	for (i = 0; i < filter->n_preds; i++) {
+		pred = filter->preds[i];
+		if (!pred->pop_n) {
+			match = pred->fn(pred, rec, val1, val2);
+			stack[top++] = match;
+			continue;
+		}
+		if (pred->pop_n > top) {
+			WARN_ON_ONCE(1);
+			return 0;
+		}
+		val1 = stack[--top];
+		val2 = stack[--top];
+		match = pred->fn(pred, rec, val1, val2);
+		stack[top++] = match;
+	}
 
-	match = (val == *addr) ^ pred->not;
+	return stack[--top];
+}
+EXPORT_SYMBOL_GPL(filter_match_preds);
 
-	return match;
+static void parse_error(struct filter_parse_state *ps, int err, int pos)
+{
+	ps->lasterr = err;
+	ps->lasterr_pos = pos;
 }
 
-static int filter_pred_8(struct filter_pred *pred, void *event)
+static void remove_filter_string(struct event_filter *filter)
 {
-	u8 *addr = (u8 *)(event + pred->offset);
-	u8 val = (u8)pred->val;
-	int match;
+	kfree(filter->filter_string);
+	filter->filter_string = NULL;
+}
 
-	match = (val == *addr) ^ pred->not;
+static int replace_filter_string(struct event_filter *filter,
+				 char *filter_string)
+{
+	kfree(filter->filter_string);
+	filter->filter_string = kstrdup(filter_string, GFP_KERNEL);
+	if (!filter->filter_string)
+		return -ENOMEM;
 
-	return match;
+	return 0;
 }
 
-static int filter_pred_string(struct filter_pred *pred, void *event)
+static int append_filter_string(struct event_filter *filter,
+				char *string)
 {
-	char *addr = (char *)(event + pred->offset);
-	int cmp, match;
+	int newlen;
+	char *new_filter_string;
 
-	cmp = strncmp(addr, pred->str_val, pred->str_len);
+	BUG_ON(!filter->filter_string);
+	newlen = strlen(filter->filter_string) + strlen(string) + 1;
+	new_filter_string = kmalloc(newlen, GFP_KERNEL);
+	if (!new_filter_string)
+		return -ENOMEM;
 
-	match = (!cmp) ^ pred->not;
+	strcpy(new_filter_string, filter->filter_string);
+	strcat(new_filter_string, string);
+	kfree(filter->filter_string);
+	filter->filter_string = new_filter_string;
 
-	return match;
+	return 0;
 }
 
-/* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+static void append_filter_err(struct filter_parse_state *ps,
+			      struct event_filter *filter)
 {
-	int i, matched, and_failed = 0;
-	struct filter_pred *pred;
+	int pos = ps->lasterr_pos;
+	char *buf, *pbuf;
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (call->preds[i]) {
-			pred = call->preds[i];
-			if (and_failed && !pred->or)
-				continue;
-			matched = pred->fn(pred, rec);
-			if (!matched && !pred->or) {
-				and_failed = 1;
-				continue;
-			} else if (matched && pred->or)
-				return 1;
-		} else
-			break;
-	}
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
+		return;
 
-	if (and_failed)
-		return 0;
+	append_filter_string(filter, "\n");
+	memset(buf, ' ', PAGE_SIZE);
+	if (pos > PAGE_SIZE - 128)
+		pos = 0;
+	buf[pos] = '^';
+	pbuf = &buf[pos] + 1;
 
-	return 1;
+	sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]);
+	append_filter_string(filter, buf);
+	free_page((unsigned long) buf);
 }
 
-void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	char *field_name;
-	struct filter_pred *pred;
-	int i;
+	struct event_filter *filter = call->filter;
 
-	if (!preds) {
+	mutex_lock(&filter_mutex);
+	if (filter->filter_string)
+		trace_seq_printf(s, "%s\n", filter->filter_string);
+	else
 		trace_seq_printf(s, "none\n");
-		return;
-	}
+	mutex_unlock(&filter_mutex);
+}
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (preds[i]) {
-			pred = preds[i];
-			field_name = pred->field_name;
-			if (i)
-				trace_seq_printf(s, pred->or ? "|| " : "&& ");
-			trace_seq_printf(s, "%s ", field_name);
-			trace_seq_printf(s, pred->not ? "!= " : "== ");
-			if (pred->str_val)
-				trace_seq_printf(s, "%s\n", pred->str_val);
-			else
-				trace_seq_printf(s, "%llu\n", pred->val);
-		} else
-			break;
-	}
+void print_subsystem_event_filter(struct event_subsystem *system,
+				  struct trace_seq *s)
+{
+	struct event_filter *filter = system->filter;
+
+	mutex_lock(&filter_mutex);
+	if (filter->filter_string)
+		trace_seq_printf(s, "%s\n", filter->filter_string);
+	else
+		trace_seq_printf(s, "none\n");
+	mutex_unlock(&filter_mutex);
 }
 
 static struct ftrace_event_field *
@@ -150,284 +328,828 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return NULL;
 }
 
-void filter_free_pred(struct filter_pred *pred)
+static void filter_free_pred(struct filter_pred *pred)
 {
 	if (!pred)
 		return;
 
 	kfree(pred->field_name);
-	kfree(pred->str_val);
 	kfree(pred);
 }
 
-void filter_free_preds(struct ftrace_event_call *call)
+static void filter_clear_pred(struct filter_pred *pred)
 {
-	int i;
+	kfree(pred->field_name);
+	pred->field_name = NULL;
+	pred->str_len = 0;
+}
 
-	if (call->preds) {
-		for (i = 0; i < MAX_FILTER_PRED; i++)
-			filter_free_pred(call->preds[i]);
-		kfree(call->preds);
-		call->preds = NULL;
+static int filter_set_pred(struct filter_pred *dest,
+			   struct filter_pred *src,
+			   filter_pred_fn_t fn)
+{
+	*dest = *src;
+	if (src->field_name) {
+		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
+		if (!dest->field_name)
+			return -ENOMEM;
 	}
+	dest->fn = fn;
+
+	return 0;
 }
 
-void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_disable_preds(struct ftrace_event_call *call)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
+	struct event_filter *filter = call->filter;
 	int i;
 
-	if (system->preds) {
-		for (i = 0; i < MAX_FILTER_PRED; i++)
-			filter_free_pred(system->preds[i]);
-		kfree(system->preds);
-		system->preds = NULL;
-	}
+	call->filter_active = 0;
+	filter->n_preds = 0;
 
-	events_for_each(call) {
-		if (!call->name || !call->regfunc)
-			continue;
+	for (i = 0; i < MAX_FILTER_PRED; i++)
+		filter->preds[i]->fn = filter_pred_none;
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+	struct event_filter *filter = call->filter;
+	int i;
 
-		if (!strcmp(call->system, system->name))
-			filter_free_preds(call);
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (filter->preds[i])
+			filter_free_pred(filter->preds[i]);
 	}
+	kfree(filter->preds);
+	kfree(filter);
+	call->filter = NULL;
 }
 
-static int __filter_add_pred(struct ftrace_event_call *call,
-			     struct filter_pred *pred)
+int init_preds(struct ftrace_event_call *call)
 {
+	struct event_filter *filter;
+	struct filter_pred *pred;
 	int i;
 
-	if (call->preds && !pred->compound)
-		filter_free_preds(call);
+	filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!call->filter)
+		return -ENOMEM;
 
-	if (!call->preds) {
-		call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-				      GFP_KERNEL);
-		if (!call->preds)
-			return -ENOMEM;
-	}
+	call->filter_active = 0;
+	filter->n_preds = 0;
+
+	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
+	if (!filter->preds)
+		goto oom;
 
 	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (!call->preds[i]) {
-			call->preds[i] = pred;
-			return 0;
+		pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+		if (!pred)
+			goto oom;
+		pred->fn = filter_pred_none;
+		filter->preds[i] = pred;
+	}
+
+	return 0;
+
+oom:
+	destroy_preds(call);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(init_preds);
+
+static void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+	struct event_filter *filter = system->filter;
+	struct ftrace_event_call *call;
+	int i;
+
+	if (filter->n_preds) {
+		for (i = 0; i < filter->n_preds; i++)
+			filter_free_pred(filter->preds[i]);
+		kfree(filter->preds);
+		filter->preds = NULL;
+		filter->n_preds = 0;
+	}
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->define_fields)
+			continue;
+
+		if (!strcmp(call->system, system->name)) {
+			filter_disable_preds(call);
+			remove_filter_string(call->filter);
 		}
 	}
+	mutex_unlock(&event_mutex);
+}
+
+static int filter_add_pred_fn(struct filter_parse_state *ps,
+			      struct ftrace_event_call *call,
+			      struct filter_pred *pred,
+			      filter_pred_fn_t fn)
+{
+	struct event_filter *filter = call->filter;
+	int idx, err;
+
+	if (filter->n_preds == MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
+	}
+
+	idx = filter->n_preds;
+	filter_clear_pred(filter->preds[idx]);
+	err = filter_set_pred(filter->preds[idx], pred, fn);
+	if (err)
+		return err;
 
-	return -ENOSPC;
+	filter->n_preds++;
+	call->filter_active = 1;
+
+	return 0;
 }
 
+enum {
+	FILTER_STATIC_STRING = 1,
+	FILTER_DYN_STRING
+};
+
 static int is_string_field(const char *type)
 {
+	if (strstr(type, "__data_loc") && strstr(type, "char"))
+		return FILTER_DYN_STRING;
+
 	if (strchr(type, '[') && strstr(type, "char"))
-		return 1;
+		return FILTER_STATIC_STRING;
 
 	return 0;
 }
 
-int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-	struct ftrace_event_field *field;
-
-	field = find_event_field(call, pred->field_name);
-	if (!field)
-		return -EINVAL;
+	if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+		return 0;
 
-	pred->offset = field->offset;
+	return 1;
+}
 
-	if (is_string_field(field->type)) {
-		if (!pred->str_val)
-			return -EINVAL;
-		pred->fn = filter_pred_string;
-		pred->str_len = field->size;
-		return __filter_add_pred(call, pred);
-	} else {
-		if (pred->str_val)
-			return -EINVAL;
-	}
+static filter_pred_fn_t select_comparison_fn(int op, int field_size,
+					     int field_is_signed)
+{
+	filter_pred_fn_t fn = NULL;
 
-	switch (field->size) {
+	switch (field_size) {
 	case 8:
-		pred->fn = filter_pred_64;
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_64;
+		else if (field_is_signed)
+			fn = filter_pred_s64;
+		else
+			fn = filter_pred_u64;
 		break;
 	case 4:
-		pred->fn = filter_pred_32;
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_32;
+		else if (field_is_signed)
+			fn = filter_pred_s32;
+		else
+			fn = filter_pred_u32;
 		break;
 	case 2:
-		pred->fn = filter_pred_16;
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_16;
+		else if (field_is_signed)
+			fn = filter_pred_s16;
+		else
+			fn = filter_pred_u16;
 		break;
 	case 1:
-		pred->fn = filter_pred_8;
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_8;
+		else if (field_is_signed)
+			fn = filter_pred_s8;
+		else
+			fn = filter_pred_u8;
 		break;
-	default:
-		return -EINVAL;
 	}
 
-	return __filter_add_pred(call, pred);
+	return fn;
 }
 
-static struct filter_pred *copy_pred(struct filter_pred *pred)
+static int filter_add_pred(struct filter_parse_state *ps,
+			   struct ftrace_event_call *call,
+			   struct filter_pred *pred)
 {
-	struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
-	if (!new_pred)
-		return NULL;
+	struct ftrace_event_field *field;
+	filter_pred_fn_t fn;
+	unsigned long long val;
+	int string_type;
+
+	pred->fn = filter_pred_none;
+
+	if (pred->op == OP_AND) {
+		pred->pop_n = 2;
+		return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+	} else if (pred->op == OP_OR) {
+		pred->pop_n = 2;
+		return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+	}
+
+	field = find_event_field(call, pred->field_name);
+	if (!field) {
+		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
+		return -EINVAL;
+	}
 
-	memcpy(new_pred, pred, sizeof(*pred));
+	pred->offset = field->offset;
 
-	if (pred->field_name) {
-		new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
-		if (!new_pred->field_name) {
-			kfree(new_pred);
-			return NULL;
-		}
+	if (!is_legal_op(field, pred->op)) {
+		parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0);
+		return -EINVAL;
 	}
 
-	if (pred->str_val) {
-		new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
-		if (!new_pred->str_val) {
-			filter_free_pred(new_pred);
-			return NULL;
+	string_type = is_string_field(field->type);
+	if (string_type) {
+		if (string_type == FILTER_STATIC_STRING)
+			fn = filter_pred_string;
+		else
+			fn = filter_pred_strloc;
+		pred->str_len = field->size;
+		if (pred->op == OP_NE)
+			pred->not = 1;
+		return filter_add_pred_fn(ps, call, pred, fn);
+	} else {
+		if (strict_strtoull(pred->str_val, 0, &val)) {
+			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
+			return -EINVAL;
 		}
+		pred->val = val;
+	}
+
+	fn = select_comparison_fn(pred->op, field->size, field->is_signed);
+	if (!fn) {
+		parse_error(ps, FILT_ERR_INVALID_OP, 0);
+		return -EINVAL;
 	}
 
-	return new_pred;
+	if (pred->op == OP_NE)
+		pred->not = 1;
+
+	return filter_add_pred_fn(ps, call, pred, fn);
 }
 
-int filter_add_subsystem_pred(struct event_subsystem *system,
-			      struct filter_pred *pred)
+static int filter_add_subsystem_pred(struct filter_parse_state *ps,
+				     struct event_subsystem *system,
+				     struct filter_pred *pred,
+				     char *filter_string)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
-	struct filter_pred *event_pred;
-	int i;
-
-	if (system->preds && !pred->compound)
-		filter_free_subsystem_preds(system);
+	struct event_filter *filter = system->filter;
+	struct ftrace_event_call *call;
+	int err = 0;
 
-	if (!system->preds) {
-		system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+	if (!filter->preds) {
+		filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
 					GFP_KERNEL);
-		if (!system->preds)
+
+		if (!filter->preds)
 			return -ENOMEM;
 	}
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (!system->preds[i]) {
-			system->preds[i] = pred;
-			break;
-		}
+	if (filter->n_preds == MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
 	}
 
-	if (i == MAX_FILTER_PRED)
-		return -ENOSPC;
+	filter->preds[filter->n_preds] = pred;
+	filter->n_preds++;
 
-	events_for_each(call) {
-		int err;
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
 
-		if (!call->name || !call->regfunc)
+		if (!call->define_fields)
 			continue;
 
 		if (strcmp(call->system, system->name))
 			continue;
 
-		if (!find_event_field(call, pred->field_name))
-			continue;
+		err = filter_add_pred(ps, call, pred);
+		if (err) {
+			mutex_unlock(&event_mutex);
+			filter_free_subsystem_preds(system);
+			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+			goto out;
+		}
+		replace_filter_string(call->filter, filter_string);
+	}
+	mutex_unlock(&event_mutex);
+out:
+	return err;
+}
 
-		event_pred = copy_pred(pred);
-		if (!event_pred)
-			goto oom;
+static void parse_init(struct filter_parse_state *ps,
+		       struct filter_op *ops,
+		       char *infix_string)
+{
+	memset(ps, '\0', sizeof(*ps));
 
-		err = filter_add_pred(call, event_pred);
-		if (err)
-			filter_free_pred(event_pred);
-		if (err == -ENOMEM)
-			goto oom;
+	ps->infix.string = infix_string;
+	ps->infix.cnt = strlen(infix_string);
+	ps->ops = ops;
+
+	INIT_LIST_HEAD(&ps->opstack);
+	INIT_LIST_HEAD(&ps->postfix);
+}
+
+static char infix_next(struct filter_parse_state *ps)
+{
+	ps->infix.cnt--;
+
+	return ps->infix.string[ps->infix.tail++];
+}
+
+static char infix_peek(struct filter_parse_state *ps)
+{
+	if (ps->infix.tail == strlen(ps->infix.string))
+		return 0;
+
+	return ps->infix.string[ps->infix.tail];
+}
+
+static void infix_advance(struct filter_parse_state *ps)
+{
+	ps->infix.cnt--;
+	ps->infix.tail++;
+}
+
+static inline int is_precedence_lower(struct filter_parse_state *ps,
+				      int a, int b)
+{
+	return ps->ops[a].precedence < ps->ops[b].precedence;
+}
+
+static inline int is_op_char(struct filter_parse_state *ps, char c)
+{
+	int i;
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (ps->ops[i].string[0] == c)
+			return 1;
 	}
 
 	return 0;
+}
 
-oom:
-	system->preds[i] = NULL;
-	return -ENOMEM;
+static int infix_get_op(struct filter_parse_state *ps, char firstc)
+{
+	char nextc = infix_peek(ps);
+	char opstr[3];
+	int i;
+
+	opstr[0] = firstc;
+	opstr[1] = nextc;
+	opstr[2] = '\0';
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (!strcmp(opstr, ps->ops[i].string)) {
+			infix_advance(ps);
+			return ps->ops[i].id;
+		}
+	}
+
+	opstr[1] = '\0';
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (!strcmp(opstr, ps->ops[i].string))
+			return ps->ops[i].id;
+	}
+
+	return OP_NONE;
 }
 
-int filter_parse(char **pbuf, struct filter_pred *pred)
+static inline void clear_operand_string(struct filter_parse_state *ps)
 {
-	char *tmp, *tok, *val_str = NULL;
-	int tok_n = 0;
+	memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL);
+	ps->operand.tail = 0;
+}
 
-	/* field ==/!= number, or/and field ==/!= number, number */
-	while ((tok = strsep(pbuf, " \n"))) {
-		if (tok_n == 0) {
-			if (!strcmp(tok, "0")) {
-				pred->clear = 1;
-				return 0;
-			} else if (!strcmp(tok, "&&")) {
-				pred->or = 0;
-				pred->compound = 1;
-			} else if (!strcmp(tok, "||")) {
-				pred->or = 1;
-				pred->compound = 1;
-			} else
-				pred->field_name = tok;
-			tok_n = 1;
+static inline int append_operand_char(struct filter_parse_state *ps, char c)
+{
+	if (ps->operand.tail == MAX_FILTER_STR_VAL - 1)
+		return -EINVAL;
+
+	ps->operand.string[ps->operand.tail++] = c;
+
+	return 0;
+}
+
+static int filter_opstack_push(struct filter_parse_state *ps, int op)
+{
+	struct opstack_op *opstack_op;
+
+	opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL);
+	if (!opstack_op)
+		return -ENOMEM;
+
+	opstack_op->op = op;
+	list_add(&opstack_op->list, &ps->opstack);
+
+	return 0;
+}
+
+static int filter_opstack_empty(struct filter_parse_state *ps)
+{
+	return list_empty(&ps->opstack);
+}
+
+static int filter_opstack_top(struct filter_parse_state *ps)
+{
+	struct opstack_op *opstack_op;
+
+	if (filter_opstack_empty(ps))
+		return OP_NONE;
+
+	opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+
+	return opstack_op->op;
+}
+
+static int filter_opstack_pop(struct filter_parse_state *ps)
+{
+	struct opstack_op *opstack_op;
+	int op;
+
+	if (filter_opstack_empty(ps))
+		return OP_NONE;
+
+	opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+	op = opstack_op->op;
+	list_del(&opstack_op->list);
+
+	kfree(opstack_op);
+
+	return op;
+}
+
+static void filter_opstack_clear(struct filter_parse_state *ps)
+{
+	while (!filter_opstack_empty(ps))
+		filter_opstack_pop(ps);
+}
+
+static char *curr_operand(struct filter_parse_state *ps)
+{
+	return ps->operand.string;
+}
+
+static int postfix_append_operand(struct filter_parse_state *ps, char *operand)
+{
+	struct postfix_elt *elt;
+
+	elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+	if (!elt)
+		return -ENOMEM;
+
+	elt->op = OP_NONE;
+	elt->operand = kstrdup(operand, GFP_KERNEL);
+	if (!elt->operand) {
+		kfree(elt);
+		return -ENOMEM;
+	}
+
+	list_add_tail(&elt->list, &ps->postfix);
+
+	return 0;
+}
+
+static int postfix_append_op(struct filter_parse_state *ps, int op)
+{
+	struct postfix_elt *elt;
+
+	elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+	if (!elt)
+		return -ENOMEM;
+
+	elt->op = op;
+	elt->operand = NULL;
+
+	list_add_tail(&elt->list, &ps->postfix);
+
+	return 0;
+}
+
+static void postfix_clear(struct filter_parse_state *ps)
+{
+	struct postfix_elt *elt;
+
+	while (!list_empty(&ps->postfix)) {
+		elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
+		kfree(elt->operand);
+		list_del(&elt->list);
+	}
+}
+
+static int filter_parse(struct filter_parse_state *ps)
+{
+	int in_string = 0;
+	int op, top_op;
+	char ch;
+
+	while ((ch = infix_next(ps))) {
+		if (ch == '"') {
+			in_string ^= 1;
 			continue;
 		}
-		if (tok_n == 1) {
-			if (!pred->field_name)
-				pred->field_name = tok;
-			else if (!strcmp(tok, "!="))
-				pred->not = 1;
-			else if (!strcmp(tok, "=="))
-				pred->not = 0;
-			else {
-				pred->field_name = NULL;
+
+		if (in_string)
+			goto parse_operand;
+
+		if (isspace(ch))
+			continue;
+
+		if (is_op_char(ps, ch)) {
+			op = infix_get_op(ps, ch);
+			if (op == OP_NONE) {
+				parse_error(ps, FILT_ERR_INVALID_OP, 0);
 				return -EINVAL;
 			}
-			tok_n = 2;
+
+			if (strlen(curr_operand(ps))) {
+				postfix_append_operand(ps, curr_operand(ps));
+				clear_operand_string(ps);
+			}
+
+			while (!filter_opstack_empty(ps)) {
+				top_op = filter_opstack_top(ps);
+				if (!is_precedence_lower(ps, top_op, op)) {
+					top_op = filter_opstack_pop(ps);
+					postfix_append_op(ps, top_op);
+					continue;
+				}
+				break;
+			}
+
+			filter_opstack_push(ps, op);
 			continue;
 		}
-		if (tok_n == 2) {
-			if (pred->compound) {
-				if (!strcmp(tok, "!="))
-					pred->not = 1;
-				else if (!strcmp(tok, "=="))
-					pred->not = 0;
-				else {
-					pred->field_name = NULL;
-					return -EINVAL;
-				}
-			} else {
-				val_str = tok;
-				break; /* done */
+
+		if (ch == '(') {
+			filter_opstack_push(ps, OP_OPEN_PAREN);
+			continue;
+		}
+
+		if (ch == ')') {
+			if (strlen(curr_operand(ps))) {
+				postfix_append_operand(ps, curr_operand(ps));
+				clear_operand_string(ps);
+			}
+
+			top_op = filter_opstack_pop(ps);
+			while (top_op != OP_NONE) {
+				if (top_op == OP_OPEN_PAREN)
+					break;
+				postfix_append_op(ps, top_op);
+				top_op = filter_opstack_pop(ps);
+			}
+			if (top_op == OP_NONE) {
+				parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+				return -EINVAL;
 			}
-			tok_n = 3;
 			continue;
 		}
-		if (tok_n == 3) {
-			val_str = tok;
-			break; /* done */
+parse_operand:
+		if (append_operand_char(ps, ch)) {
+			parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0);
+			return -EINVAL;
 		}
 	}
 
-	if (!val_str) {
-		pred->field_name = NULL;
-		return -EINVAL;
+	if (strlen(curr_operand(ps)))
+		postfix_append_operand(ps, curr_operand(ps));
+
+	while (!filter_opstack_empty(ps)) {
+		top_op = filter_opstack_pop(ps);
+		if (top_op == OP_NONE)
+			break;
+		if (top_op == OP_OPEN_PAREN) {
+			parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+			return -EINVAL;
+		}
+		postfix_append_op(ps, top_op);
 	}
 
-	pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
-	if (!pred->field_name)
-		return -ENOMEM;
+	return 0;
+}
 
-	pred->val = simple_strtoull(val_str, &tmp, 0);
-	if (tmp == val_str) {
-		pred->str_val = kstrdup(val_str, GFP_KERNEL);
-		if (!pred->str_val)
-			return -ENOMEM;
-	} else if (*tmp != '\0')
+static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+{
+	struct filter_pred *pred;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return NULL;
+
+	pred->field_name = kstrdup(operand1, GFP_KERNEL);
+	if (!pred->field_name) {
+		kfree(pred);
+		return NULL;
+	}
+
+	strcpy(pred->str_val, operand2);
+	pred->str_len = strlen(operand2);
+
+	pred->op = op;
+
+	return pred;
+}
+
+static struct filter_pred *create_logical_pred(int op)
+{
+	struct filter_pred *pred;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return NULL;
+
+	pred->op = op;
+
+	return pred;
+}
+
+static int check_preds(struct filter_parse_state *ps)
+{
+	int n_normal_preds = 0, n_logical_preds = 0;
+	struct postfix_elt *elt;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE)
+			continue;
+
+		if (elt->op == OP_AND || elt->op == OP_OR) {
+			n_logical_preds++;
+			continue;
+		}
+		n_normal_preds++;
+	}
+
+	if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+		parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
 		return -EINVAL;
+	}
 
 	return 0;
 }
 
+static int replace_preds(struct event_subsystem *system,
+			 struct ftrace_event_call *call,
+			 struct filter_parse_state *ps,
+			 char *filter_string)
+{
+	char *operand1 = NULL, *operand2 = NULL;
+	struct filter_pred *pred;
+	struct postfix_elt *elt;
+	int err;
+
+	err = check_preds(ps);
+	if (err)
+		return err;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE) {
+			if (!operand1)
+				operand1 = elt->operand;
+			else if (!operand2)
+				operand2 = elt->operand;
+			else {
+				parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
+				return -EINVAL;
+			}
+			continue;
+		}
+
+		if (elt->op == OP_AND || elt->op == OP_OR) {
+			pred = create_logical_pred(elt->op);
+			if (call) {
+				err = filter_add_pred(ps, call, pred);
+				filter_free_pred(pred);
+			} else
+				err = filter_add_subsystem_pred(ps, system,
+							pred, filter_string);
+			if (err)
+				return err;
+
+			operand1 = operand2 = NULL;
+			continue;
+		}
+
+		if (!operand1 || !operand2) {
+			parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+			return -EINVAL;
+		}
+
+		pred = create_pred(elt->op, operand1, operand2);
+		if (call) {
+			err = filter_add_pred(ps, call, pred);
+			filter_free_pred(pred);
+		} else
+			err = filter_add_subsystem_pred(ps, system, pred,
+							filter_string);
+		if (err)
+			return err;
+
+		operand1 = operand2 = NULL;
+	}
+
+	return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+	int err;
+
+	struct filter_parse_state *ps;
+
+	mutex_lock(&filter_mutex);
+
+	if (!strcmp(strstrip(filter_string), "0")) {
+		filter_disable_preds(call);
+		remove_filter_string(call->filter);
+		mutex_unlock(&filter_mutex);
+		return 0;
+	}
+
+	err = -ENOMEM;
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto out_unlock;
+
+	filter_disable_preds(call);
+	replace_filter_string(call->filter, filter_string);
+
+	parse_init(ps, filter_ops, filter_string);
+	err = filter_parse(ps);
+	if (err) {
+		append_filter_err(ps, call->filter);
+		goto out;
+	}
+
+	err = replace_preds(NULL, call, ps, filter_string);
+	if (err)
+		append_filter_err(ps, call->filter);
+
+out:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+out_unlock:
+	mutex_unlock(&filter_mutex);
+
+	return err;
+}
+
+int apply_subsystem_event_filter(struct event_subsystem *system,
+				 char *filter_string)
+{
+	int err;
+
+	struct filter_parse_state *ps;
+
+	mutex_lock(&filter_mutex);
+
+	if (!strcmp(strstrip(filter_string), "0")) {
+		filter_free_subsystem_preds(system);
+		remove_filter_string(system->filter);
+		mutex_unlock(&filter_mutex);
+		return 0;
+	}
+
+	err = -ENOMEM;
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto out_unlock;
+
+	filter_free_subsystem_preds(system);
+	replace_filter_string(system->filter, filter_string);
+
+	parse_init(ps, filter_ops, filter_string);
+	err = filter_parse(ps);
+	if (err) {
+		append_filter_err(ps, system->filter);
+		goto out;
+	}
+
+	err = replace_preds(system, NULL, ps, filter_string);
+	if (err)
+		append_filter_err(ps, system->filter);
+
+out:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+out_unlock:
+	mutex_unlock(&filter_mutex);
+
+	return err;
+}
 
diff --git a/kernel/trace/trace_events_stage_1.h b/kernel/trace/trace_events_stage_1.h
deleted file mode 100644
index 38985f9b379..00000000000
--- a/kernel/trace/trace_events_stage_1.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Stage 1 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * struct ftrace_raw_<call> {
- *	struct trace_entry		ent;
- *	<type>				<item>;
- *	<type2>				<item2>[<len>];
- *	[...]
- * };
- *
- * The <type> <item> is created by the __field(type, item) macro or
- * the __array(type2, item2, len) macro.
- * We simply do "type item;", and that will create the fields
- * in the structure.
- */
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)
-
-#undef __array
-#define __array(type, item, len)	type	item[len];
-
-#undef __field
-#define __field(type, item)		type	item;
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
-	struct ftrace_raw_##name {				\
-		struct trace_entry	ent;			\
-		tstruct						\
-	};							\
-	static struct ftrace_event_call event_##name
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
deleted file mode 100644
index d363c6672c6..00000000000
--- a/kernel/trace/trace_events_stage_2.h
+++ /dev/null
@@ -1,176 +0,0 @@
-/*
- * Stage 2 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * enum print_line_t
- * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
- * {
- *	struct trace_seq *s = &iter->seq;
- *	struct ftrace_raw_<call> *field; <-- defined in stage 1
- *	struct trace_entry *entry;
- *	int ret;
- *
- *	entry = iter->ent;
- *
- *	if (entry->type != event_<call>.id) {
- *		WARN_ON_ONCE(1);
- *		return TRACE_TYPE_UNHANDLED;
- *	}
- *
- *	field = (typeof(field))entry;
- *
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
- *	if (!ret)
- *		return TRACE_TYPE_PARTIAL_LINE;
- *
- *	return TRACE_TYPE_HANDLED;
- * }
- *
- * This is the method used to print the raw event to the trace
- * output format. Note, this is not needed if the data is read
- * in binary.
- */
-
-#undef __entry
-#define __entry field
-
-#undef TP_printk
-#define TP_printk(fmt, args...) fmt "\n", args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-enum print_line_t							\
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
-{									\
-	struct trace_seq *s = &iter->seq;				\
-	struct ftrace_raw_##call *field;				\
-	struct trace_entry *entry;					\
-	int ret;							\
-									\
-	entry = iter->ent;						\
-									\
-	if (entry->type != event_##call.id) {				\
-		WARN_ON_ONCE(1);					\
-		return TRACE_TYPE_UNHANDLED;				\
-	}								\
-									\
-	field = (typeof(field))entry;					\
-									\
-	ret = trace_seq_printf(s, #call ": " print);			\
-	if (!ret)							\
-		return TRACE_TYPE_PARTIAL_LINE;				\
-									\
-	return TRACE_TYPE_HANDLED;					\
-}
-	
-#include <trace/trace_event_types.h>
-
-/*
- * Setup the showing format of trace point.
- *
- * int
- * ftrace_format_##call(struct trace_seq *s)
- * {
- *	struct ftrace_raw_##call field;
- *	int ret;
- *
- *	ret = trace_seq_printf(s, #type " " #item ";"
- *			       " offset:%u; size:%u;\n",
- *			       offsetof(struct ftrace_raw_##call, item),
- *			       sizeof(field.type));
- *
- * }
- */
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef __field
-#define __field(type, item)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
-	if (!ret)							\
-		return 0;
-
-#undef __array
-#define __array(type, item, len)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
-	if (!ret)							\
-		return 0;
-
-#undef __entry
-#define __entry REC
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
-static int								\
-ftrace_format_##call(struct trace_seq *s)				\
-{									\
-	struct ftrace_raw_##call field;					\
-	int ret;							\
-									\
-	tstruct;							\
-									\
-	trace_seq_printf(s, "\nprint fmt: " print);			\
-									\
-	return ret;							\
-}
-
-#include <trace/trace_event_types.h>
-
-#undef __field
-#define __field(type, item)						\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item));			\
-	if (ret)							\
-		return ret;
-
-#undef __array
-#define __array(type, item, len)					\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item));			\
-	if (ret)							\
-		return ret;
-
-#define __common_field(type, item)					\
-	ret = trace_define_field(event_call, #type, "common_" #item,	\
-				 offsetof(typeof(field.ent), item),	\
-				 sizeof(field.ent.item));		\
-	if (ret)							\
-		return ret;
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
-int									\
-ftrace_define_fields_##call(void)					\
-{									\
-	struct ftrace_raw_##call field;					\
-	struct ftrace_event_call *event_call = &event_##call;		\
-	int ret;							\
-									\
-	__common_field(unsigned char, type);				\
-	__common_field(unsigned char, flags);				\
-	__common_field(unsigned char, preempt_count);			\
-	__common_field(int, pid);					\
-	__common_field(int, tgid);					\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
deleted file mode 100644
index 9d2fa78cecc..00000000000
--- a/kernel/trace/trace_events_stage_3.h
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Stage 3 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * static void ftrace_event_<call>(proto)
- * {
- *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(void)
- * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to  <call>");
- *	return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- *	unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- * For those macros defined with TRACE_FORMAT:
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- *	.name			= "<call>",
- *	.regfunc		= ftrace_reg_event_<call>,
- *	.unregfunc		= ftrace_unreg_event_<call>,
- * }
- *
- *
- * For those macros defined with TRACE_EVENT:
- *
- * static struct ftrace_event_call event_<call>;
- *
- * static void ftrace_raw_event_<call>(proto)
- * {
- *	struct ring_buffer_event *event;
- *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
- *	unsigned long irq_flags;
- *	int pc;
- *
- *	local_save_flags(irq_flags);
- *	pc = preempt_count();
- *
- *	event = trace_current_buffer_lock_reserve(event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
- *				  irq_flags, pc);
- *	if (!event)
- *		return;
- *	entry	= ring_buffer_event_data(event);
- *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
- *
- *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
- * }
- *
- * static int ftrace_raw_reg_event_<call>(void)
- * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- *	unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static struct trace_event ftrace_event_type_<call> = {
- *	.trace			= ftrace_raw_output_<call>, <-- stage 2
- * };
- *
- * static int ftrace_raw_init_event_<call>(void)
- * {
- *	int id;
- *
- *	id = register_ftrace_event(&ftrace_event_type_<call>);
- *	if (!id)
- *		return -ENODEV;
- *	event_<call>.id = id;
- *	return 0;
- * }
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- *	.name			= "<call>",
- *	.system			= "<system>",
- *	.raw_init		= ftrace_raw_init_event_<call>,
- *	.regfunc		= ftrace_reg_event_<call>,
- *	.unregfunc		= ftrace_unreg_event_<call>,
- *	.show_format		= ftrace_format_<call>,
- * }
- *
- */
-
-#undef TP_FMT
-#define TP_FMT(fmt, args...)	fmt "\n", ##args
-
-#ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)				\
-static void ftrace_profile_##call(proto)				\
-{									\
-	extern void perf_tpcounter_event(int);				\
-	perf_tpcounter_event(event_##call.id);				\
-}									\
-									\
-static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \
-{									\
-	int ret = 0;							\
-									\
-	if (!atomic_inc_return(&call->profile_count))			\
-		ret = register_trace_##call(ftrace_profile_##call);	\
-									\
-	return ret;							\
-}									\
-									\
-static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \
-{									\
-	if (atomic_add_negative(-1, &call->profile_count))		\
-		unregister_trace_##call(ftrace_profile_##call);		\
-}
-
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_count = ATOMIC_INIT(-1),				\
-	.profile_enable = ftrace_profile_enable_##call,			\
-	.profile_disable = ftrace_profile_disable_##call,
-
-#else
-#define _TRACE_PROFILE(call, proto, args)
-#define _TRACE_PROFILE_INIT(call)
-#endif
-
-#define _TRACE_FORMAT(call, proto, args, fmt)				\
-static void ftrace_event_##call(proto)					\
-{									\
-	event_trace_printk(_RET_IP_, #call ": " fmt);			\
-}									\
-									\
-static int ftrace_reg_event_##call(void)				\
-{									\
-	int ret;							\
-									\
-	ret = register_trace_##call(ftrace_event_##call);		\
-	if (ret)							\
-		pr_info("event trace: Could not activate trace point "	\
-			"probe to " #call "\n");			\
-	return ret;							\
-}									\
-									\
-static void ftrace_unreg_event_##call(void)				\
-{									\
-	unregister_trace_##call(ftrace_event_##call);			\
-}									\
-									\
-static struct ftrace_event_call event_##call;				\
-									\
-static int ftrace_init_event_##call(void)				\
-{									\
-	int id;								\
-									\
-	id = register_ftrace_event(NULL);				\
-	if (!id)							\
-		return -ENODEV;						\
-	event_##call.id = id;						\
-	return 0;							\
-}
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)				\
-_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt))		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name			= #call,				\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_init_event_##call,		\
-	.regfunc		= ftrace_reg_event_##call,		\
-	.unregfunc		= ftrace_unreg_event_##call,		\
-	_TRACE_PROFILE_INIT(call)					\
-}
-
-#undef __entry
-#define __entry entry
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
-									\
-static struct ftrace_event_call event_##call;				\
-									\
-static void ftrace_raw_event_##call(proto)				\
-{									\
-	struct ftrace_event_call *call = &event_##call;			\
-	struct ring_buffer_event *event;				\
-	struct ftrace_raw_##call *entry;				\
-	unsigned long irq_flags;					\
-	int pc;								\
-									\
-	local_save_flags(irq_flags);					\
-	pc = preempt_count();						\
-									\
-	event = trace_current_buffer_lock_reserve(event_##call.id,	\
-				  sizeof(struct ftrace_raw_##call),	\
-				  irq_flags, pc);			\
-	if (!event)							\
-		return;							\
-	entry	= ring_buffer_event_data(event);			\
-									\
-	assign;								\
-									\
-	if (call->preds && !filter_match_preds(call, entry))		\
-		ring_buffer_event_discard(event);			\
-									\
-	trace_nowake_buffer_unlock_commit(event, irq_flags, pc);	\
-									\
-}									\
-									\
-static int ftrace_raw_reg_event_##call(void)				\
-{									\
-	int ret;							\
-									\
-	ret = register_trace_##call(ftrace_raw_event_##call);		\
-	if (ret)							\
-		pr_info("event trace: Could not activate trace point "	\
-			"probe to " #call "\n");			\
-	return ret;							\
-}									\
-									\
-static void ftrace_raw_unreg_event_##call(void)				\
-{									\
-	unregister_trace_##call(ftrace_raw_event_##call);		\
-}									\
-									\
-static struct trace_event ftrace_event_type_##call = {			\
-	.trace			= ftrace_raw_output_##call,		\
-};									\
-									\
-static int ftrace_raw_init_event_##call(void)				\
-{									\
-	int id;								\
-									\
-	id = register_ftrace_event(&ftrace_event_type_##call);		\
-	if (!id)							\
-		return -ENODEV;						\
-	event_##call.id = id;						\
-	INIT_LIST_HEAD(&event_##call.fields);				\
-	return 0;							\
-}									\
-									\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name			= #call,				\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_raw_init_event_##call,		\
-	.regfunc		= ftrace_raw_reg_event_##call,		\
-	.unregfunc		= ftrace_raw_unreg_event_##call,	\
-	.show_format		= ftrace_format_##call,			\
-	.define_fields		= ftrace_define_fields_##call,		\
-	_TRACE_PROFILE_INIT(call)					\
-}
-
-#include <trace/trace_event_types.h>
-
-#undef _TRACE_PROFILE
-#undef _TRACE_PROFILE_INIT
-
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 07a22c33ebf..d06cf898dc8 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -19,8 +19,12 @@
 #undef TRACE_STRUCT
 #define TRACE_STRUCT(args...) args
 
+extern void __bad_type_size(void);
+
 #undef TRACE_FIELD
 #define TRACE_FIELD(type, item, assign)					\
+	if (sizeof(type) != sizeof(field.item))				\
+		__bad_type_size();					\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
 			       "offset:%u;\tsize:%u;\n",		\
 			       (unsigned int)offsetof(typeof(field), item), \
@@ -30,7 +34,7 @@
 
 
 #undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd)			\
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)			\
 	ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t"	\
 			       "offset:%u;\tsize:%u;\n",		\
 			       (unsigned int)offsetof(typeof(field), item), \
@@ -46,6 +50,9 @@
 	if (!ret)							\
 		return 0;
 
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
+	TRACE_FIELD(type, item, assign)
 
 #undef TP_RAW_FMT
 #define TP_RAW_FMT(args...) args
@@ -65,6 +72,22 @@ ftrace_format_##call(struct trace_seq *s)				\
 	return ret;							\
 }
 
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)				\
+static int								\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct args field;						\
+	int ret;							\
+									\
+	tstruct;							\
+									\
+	trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);		\
+									\
+	return ret;							\
+}
+
 #include "trace_event_types.h"
 
 #undef TRACE_ZERO_CHAR
@@ -78,6 +101,10 @@ ftrace_format_##call(struct trace_seq *s)				\
 #define TRACE_FIELD(type, item, assign)\
 	entry->item = assign;
 
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
+	TRACE_FIELD(type, item, assign)
+
 #undef TP_CMD
 #define TP_CMD(cmd...)	cmd
 
@@ -85,18 +112,95 @@ ftrace_format_##call(struct trace_seq *s)				\
 #define TRACE_ENTRY	entry
 
 #undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)	\
 	cmd;
 
 #undef TRACE_EVENT_FORMAT
 #define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+int ftrace_define_fields_##call(void);					\
+static int ftrace_raw_init_event_##call(void);				\
+									\
+struct ftrace_event_call __used						\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.id			= proto,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+};									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	INIT_LIST_HEAD(&event_##call.fields);				\
+	init_preds(&event_##call);					\
+	return 0;							\
+}									\
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)				\
 									\
-static struct ftrace_event_call __used					\
+struct ftrace_event_call __used						\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
 	.id			= proto,				\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.show_format		= ftrace_format_##call,			\
+};
+
+#include "trace_event_types.h"
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign)					\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed_type(type));	\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_SPECIAL
+#define TRACE_FIELD_SPECIAL(type, item, len, cmd)			\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0);		\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)			\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed);	\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_ZERO_CHAR
+#define TRACE_FIELD_ZERO_CHAR(item)
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct args field;						\
+	int ret;							\
+									\
+	__common_field(unsigned char, type, 0);				\
+	__common_field(unsigned char, flags, 0);			\
+	__common_field(unsigned char, preempt_count, 0);		\
+	__common_field(int, pid, 1);					\
+	__common_field(int, tgid, 1);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
 }
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)
+
 #include "trace_event_types.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d28687e7b3a..8b592418d8b 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -65,6 +65,12 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	if (!current->ret_stack)
 		return -EBUSY;
 
+	/*
+	 * We must make sure the ret_stack is tested before we read
+	 * anything else.
+	 */
+	smp_rmb();
+
 	/* The return trace stack is full */
 	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
 		atomic_inc(&current->trace_overrun);
@@ -78,13 +84,14 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
+	current->ret_stack[index].subtime = 0;
 	*depth = index;
 
 	return 0;
 }
 
 /* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 {
 	int index;
@@ -104,9 +111,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 	trace->calltime = current->ret_stack[index].calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = index;
-	barrier();
-	current->curr_ret_stack--;
-
 }
 
 /*
@@ -121,6 +125,8 @@ unsigned long ftrace_return_to_handler(void)
 	ftrace_pop_return_trace(&trace, &ret);
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
+	barrier();
+	current->curr_ret_stack--;
 
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
@@ -426,8 +432,8 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 {
 	unsigned long nsecs_rem = do_div(duration, 1000);
 	/* log10(ULONG_MAX) + '\0' */
@@ -464,12 +470,23 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+	int ret;
+
+	ret = trace_print_graph_duration(duration, s);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
 
 	ret = trace_seq_printf(s, "|  ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
-	return TRACE_TYPE_HANDLED;
 
+	return TRACE_TYPE_HANDLED;
 }
 
 /* Case of a leaf function on its call entry */
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 7bfdf4c2347..ca7d7c4d0c2 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -1,10 +1,9 @@
 /*
- * h/w branch tracer for x86 based on bts
+ * h/w branch tracer for x86 based on BTS
  *
  * Copyright (C) 2008-2009 Intel Corporation.
  * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
  */
-#include <linux/spinlock.h>
 #include <linux/kallsyms.h>
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
@@ -15,110 +14,119 @@
 
 #include <asm/ds.h>
 
-#include "trace.h"
 #include "trace_output.h"
+#include "trace.h"
 
 
-#define SIZEOF_BTS (1 << 13)
+#define BTS_BUFFER_SIZE (1 << 13)
 
-/*
- * The tracer lock protects the below per-cpu tracer array.
- * It needs to be held to:
- * - start tracing on all cpus
- * - stop tracing on all cpus
- * - start tracing on a single hotplug cpu
- * - stop tracing on a single hotplug cpu
- * - read the trace from all cpus
- * - read the trace from a single cpu
- */
-static DEFINE_SPINLOCK(bts_tracer_lock);
 static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
 
 #define this_tracer per_cpu(tracer, smp_processor_id())
-#define this_buffer per_cpu(buffer, smp_processor_id())
 
-static int __read_mostly trace_hw_branches_enabled;
+static int trace_hw_branches_enabled __read_mostly;
+static int trace_hw_branches_suspended __read_mostly;
 static struct trace_array *hw_branch_trace __read_mostly;
 
 
-/*
- * Start tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_start_cpu(void *arg)
+static void bts_trace_init_cpu(int cpu)
 {
-	if (this_tracer)
-		ds_release_bts(this_tracer);
-
-	this_tracer =
-		ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
-			       /* ovfl = */ NULL, /* th = */ (size_t)-1,
-			       BTS_KERNEL);
-	if (IS_ERR(this_tracer)) {
-		this_tracer = NULL;
-		return;
-	}
+	per_cpu(tracer, cpu) =
+		ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
+				   NULL, (size_t)-1, BTS_KERNEL);
+
+	if (IS_ERR(per_cpu(tracer, cpu)))
+		per_cpu(tracer, cpu) = NULL;
 }
 
-static void bts_trace_start(struct trace_array *tr)
+static int bts_trace_init(struct trace_array *tr)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
+
+	hw_branch_trace = tr;
+	trace_hw_branches_enabled = 0;
 
-	on_each_cpu(bts_trace_start_cpu, NULL, 1);
-	trace_hw_branches_enabled = 1;
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		bts_trace_init_cpu(cpu);
 
-	spin_unlock(&bts_tracer_lock);
+		if (likely(per_cpu(tracer, cpu)))
+			trace_hw_branches_enabled = 1;
+	}
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
+
+	/* If we could not enable tracing on a single cpu, we fail. */
+	return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
 }
 
-/*
- * Stop tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_stop_cpu(void *arg)
+static void bts_trace_reset(struct trace_array *tr)
 {
-	if (this_tracer) {
-		ds_release_bts(this_tracer);
-		this_tracer = NULL;
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (likely(per_cpu(tracer, cpu))) {
+			ds_release_bts(per_cpu(tracer, cpu));
+			per_cpu(tracer, cpu) = NULL;
+		}
 	}
+	trace_hw_branches_enabled = 0;
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
 }
 
-static void bts_trace_stop(struct trace_array *tr)
+static void bts_trace_start(struct trace_array *tr)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
 
-	trace_hw_branches_enabled = 0;
-	on_each_cpu(bts_trace_stop_cpu, NULL, 1);
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_resume_bts(per_cpu(tracer, cpu));
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
+}
 
-	spin_unlock(&bts_tracer_lock);
+static void bts_trace_stop(struct trace_array *tr)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_suspend_bts(per_cpu(tracer, cpu));
+	trace_hw_branches_suspended = 1;
+	put_online_cpus();
 }
 
 static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
 				     unsigned long action, void *hcpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-
-	spin_lock(&bts_tracer_lock);
-
-	if (!trace_hw_branches_enabled)
-		goto out;
+	int cpu = (long)hcpu;
 
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
-		smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
+		/* The notification is sent with interrupts enabled. */
+		if (trace_hw_branches_enabled) {
+			bts_trace_init_cpu(cpu);
+
+			if (trace_hw_branches_suspended &&
+			    likely(per_cpu(tracer, cpu)))
+				ds_suspend_bts(per_cpu(tracer, cpu));
+		}
 		break;
+
 	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
-		break;
+		/* The notification is sent with interrupts enabled. */
+		if (likely(per_cpu(tracer, cpu))) {
+			ds_release_bts(per_cpu(tracer, cpu));
+			per_cpu(tracer, cpu) = NULL;
+		}
 	}
 
- out:
-	spin_unlock(&bts_tracer_lock);
 	return NOTIFY_DONE;
 }
 
@@ -126,20 +134,6 @@ static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
 	.notifier_call = bts_hotcpu_handler
 };
 
-static int bts_trace_init(struct trace_array *tr)
-{
-	hw_branch_trace = tr;
-
-	bts_trace_start(tr);
-
-	return 0;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-	bts_trace_stop(tr);
-}
-
 static void bts_trace_print_header(struct seq_file *m)
 {
 	seq_puts(m, "# CPU#        TO  <-  FROM\n");
@@ -147,10 +141,10 @@ static void bts_trace_print_header(struct seq_file *m)
 
 static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
 {
+	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
 	struct trace_entry *entry = iter->ent;
 	struct trace_seq *seq = &iter->seq;
 	struct hw_branch_entry *it;
-	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
 
 	trace_assign_type(it, entry);
 
@@ -168,6 +162,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
 
 void trace_hw_branch(u64 from, u64 to)
 {
+	struct ftrace_event_call *call = &event_hw_branch;
 	struct trace_array *tr = hw_branch_trace;
 	struct ring_buffer_event *event;
 	struct hw_branch_entry *entry;
@@ -194,7 +189,8 @@ void trace_hw_branch(u64 from, u64 to)
 	entry->ent.type = TRACE_HW_BRANCHES;
 	entry->from = from;
 	entry->to   = to;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
@@ -224,11 +220,11 @@ static void trace_bts_at(const struct bts_trace *trace, void *at)
 /*
  * Collect the trace on the current cpu and write it into the ftrace buffer.
  *
- * pre: bts_tracer_lock must be locked
+ * pre: tracing must be suspended on the current cpu
  */
 static void trace_bts_cpu(void *arg)
 {
-	struct trace_array *tr = (struct trace_array *) arg;
+	struct trace_array *tr = (struct trace_array *)arg;
 	const struct bts_trace *trace;
 	unsigned char *at;
 
@@ -241,10 +237,9 @@ static void trace_bts_cpu(void *arg)
 	if (unlikely(!this_tracer))
 		return;
 
-	ds_suspend_bts(this_tracer);
 	trace = ds_read_bts(this_tracer);
 	if (!trace)
-		goto out;
+		return;
 
 	for (at = trace->ds.top; (void *)at < trace->ds.end;
 	     at += trace->ds.size)
@@ -253,18 +248,27 @@ static void trace_bts_cpu(void *arg)
 	for (at = trace->ds.begin; (void *)at < trace->ds.top;
 	     at += trace->ds.size)
 		trace_bts_at(trace, at);
-
-out:
-	ds_resume_bts(this_tracer);
 }
 
 static void trace_bts_prepare(struct trace_iterator *iter)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
 
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_suspend_bts(per_cpu(tracer, cpu));
+	/*
+	 * We need to collect the trace on the respective cpu since ftrace
+	 * implicitly adds the record for the current cpu.
+	 * Once that is more flexible, we could collect the data from any cpu.
+	 */
 	on_each_cpu(trace_bts_cpu, iter->tr, 1);
 
-	spin_unlock(&bts_tracer_lock);
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_resume_bts(per_cpu(tracer, cpu));
+	put_online_cpus();
 }
 
 static void trace_bts_close(struct trace_iterator *iter)
@@ -274,11 +278,11 @@ static void trace_bts_close(struct trace_iterator *iter)
 
 void trace_hw_branch_oops(void)
 {
-	spin_lock(&bts_tracer_lock);
-
-	trace_bts_cpu(hw_branch_trace);
-
-	spin_unlock(&bts_tracer_lock);
+	if (this_tracer) {
+		ds_suspend_bts_noirq(this_tracer);
+		trace_bts_cpu(hw_branch_trace);
+		ds_resume_bts_noirq(this_tracer);
+	}
 }
 
 struct tracer bts_tracer __read_mostly =
@@ -291,7 +295,10 @@ struct tracer bts_tracer __read_mostly =
 	.start		= bts_trace_start,
 	.stop		= bts_trace_stop,
 	.open		= trace_bts_prepare,
-	.close		= trace_bts_close
+	.close		= trace_bts_close,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_hw_branches,
+#endif /* CONFIG_FTRACE_SELFTEST */
 };
 
 __init static int init_bts_trace(void)
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 8e37fcddd8b..d53b45ed080 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,8 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <linux/time.h>
+
 #include <asm/atomic.h>
 
 #include "trace.h"
@@ -174,7 +176,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
 	struct mmiotrace_rw *rw;
 	struct trace_seq *s	= &iter->seq;
 	unsigned long long t	= ns2usecs(iter->ts);
-	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
 	unsigned secs		= (unsigned long)t;
 	int ret = 1;
 
@@ -221,7 +223,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter)
 	struct mmiotrace_map *m;
 	struct trace_seq *s	= &iter->seq;
 	unsigned long long t	= ns2usecs(iter->ts);
-	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
 	unsigned secs		= (unsigned long)t;
 	int ret;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 64b54a59c55..7938f3ae93e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -14,11 +14,25 @@
 /* must be a power of 2 */
 #define EVENT_HASHSIZE	128
 
-static DEFINE_MUTEX(trace_event_mutex);
+DECLARE_RWSEM(trace_event_mutex);
+
+DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
+EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
+
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
+void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+
+	s->buffer[len] = 0;
+	seq_puts(m, s->buffer);
+
+	trace_seq_init(s);
+}
+
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -84,6 +98,39 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+	int len = (PAGE_SIZE - 1) - s->len;
+	int ret;
+
+	if (!len)
+		return 0;
+
+	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (ret >= len)
+		return 0;
+
+	s->len += ret;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
 
 int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 {
@@ -201,6 +248,67 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
 	return 0;
 }
 
+const char *
+ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+		       unsigned long flags,
+		       const struct trace_print_flags *flag_array)
+{
+	unsigned long mask;
+	const char *str;
+	const char *ret = p->buffer + p->len;
+	int i;
+
+	for (i = 0;  flag_array[i].name && flags; i++) {
+
+		mask = flag_array[i].mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		str = flag_array[i].name;
+		flags &= ~mask;
+		if (p->len && delim)
+			trace_seq_puts(p, delim);
+		trace_seq_puts(p, str);
+	}
+
+	/* check for left over flags */
+	if (flags) {
+		if (p->len && delim)
+			trace_seq_puts(p, delim);
+		trace_seq_printf(p, "0x%lx", flags);
+	}
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_flags_seq);
+
+const char *
+ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+			 const struct trace_print_flags *symbol_array)
+{
+	int i;
+	const char *ret = p->buffer + p->len;
+
+	for (i = 0;  symbol_array[i].name; i++) {
+
+		if (val != symbol_array[i].mask)
+			continue;
+
+		trace_seq_puts(p, symbol_array[i].name);
+		break;
+	}
+
+	if (!p->len)
+		trace_seq_printf(p, "0x%lx", val);
+		
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
@@ -311,17 +419,20 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 
 		if (ip == ULONG_MAX || !ret)
 			break;
-		if (i && ret)
-			ret = trace_seq_puts(s, " <- ");
+		if (ret)
+			ret = trace_seq_puts(s, " => ");
 		if (!ip) {
 			if (ret)
 				ret = trace_seq_puts(s, "??");
+			if (ret)
+				ret = trace_seq_puts(s, "\n");
 			continue;
 		}
 		if (!ret)
 			break;
 		if (ret)
 			ret = seq_print_user_ip(s, mm, ip, sym_flags);
+		ret = trace_seq_puts(s, "\n");
 	}
 
 	if (mm)
@@ -455,6 +566,7 @@ static int task_state_char(unsigned long state)
  * @type: the type of event to look for
  *
  * Returns an event of type @type otherwise NULL
+ * Called with trace_event_read_lock() held.
  */
 struct trace_event *ftrace_find_event(int type)
 {
@@ -464,7 +576,7 @@ struct trace_event *ftrace_find_event(int type)
 
 	key = type & (EVENT_HASHSIZE - 1);
 
-	hlist_for_each_entry_rcu(event, n, &event_hash[key], node) {
+	hlist_for_each_entry(event, n, &event_hash[key], node) {
 		if (event->type == type)
 			return event;
 	}
@@ -472,6 +584,46 @@ struct trace_event *ftrace_find_event(int type)
 	return NULL;
 }
 
+static LIST_HEAD(ftrace_event_list);
+
+static int trace_search_list(struct list_head **list)
+{
+	struct trace_event *e;
+	int last = __TRACE_LAST_TYPE;
+
+	if (list_empty(&ftrace_event_list)) {
+		*list = &ftrace_event_list;
+		return last + 1;
+	}
+
+	/*
+	 * We used up all possible max events,
+	 * lets see if somebody freed one.
+	 */
+	list_for_each_entry(e, &ftrace_event_list, list) {
+		if (e->type != last + 1)
+			break;
+		last++;
+	}
+
+	/* Did we used up all 65 thousand events??? */
+	if ((last + 1) > FTRACE_MAX_EVENT)
+		return 0;
+
+	*list = &e->list;
+	return last + 1;
+}
+
+void trace_event_read_lock(void)
+{
+	down_read(&trace_event_mutex);
+}
+
+void trace_event_read_unlock(void)
+{
+	up_read(&trace_event_mutex);
+}
+
 /**
  * register_ftrace_event - register output for an event type
  * @event: the event type to register
@@ -492,22 +644,42 @@ int register_ftrace_event(struct trace_event *event)
 	unsigned key;
 	int ret = 0;
 
-	mutex_lock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
 
-	if (!event) {
-		ret = next_event_type++;
+	if (WARN_ON(!event))
 		goto out;
-	}
 
-	if (!event->type)
-		event->type = next_event_type++;
-	else if (event->type > __TRACE_LAST_TYPE) {
+	INIT_LIST_HEAD(&event->list);
+
+	if (!event->type) {
+		struct list_head *list = NULL;
+
+		if (next_event_type > FTRACE_MAX_EVENT) {
+
+			event->type = trace_search_list(&list);
+			if (!event->type)
+				goto out;
+
+		} else {
+			
+			event->type = next_event_type++;
+			list = &ftrace_event_list;
+		}
+
+		if (WARN_ON(ftrace_find_event(event->type)))
+			goto out;
+
+		list_add_tail(&event->list, list);
+
+	} else if (event->type > __TRACE_LAST_TYPE) {
 		printk(KERN_WARNING "Need to add type to trace.h\n");
 		WARN_ON(1);
-	}
-
-	if (ftrace_find_event(event->type))
 		goto out;
+	} else {
+		/* Is this event already used */
+		if (ftrace_find_event(event->type))
+			goto out;
+	}
 
 	if (event->trace == NULL)
 		event->trace = trace_nop_print;
@@ -520,14 +692,25 @@ int register_ftrace_event(struct trace_event *event)
 
 	key = event->type & (EVENT_HASHSIZE - 1);
 
-	hlist_add_head_rcu(&event->node, &event_hash[key]);
+	hlist_add_head(&event->node, &event_hash[key]);
 
 	ret = event->type;
  out:
-	mutex_unlock(&trace_event_mutex);
+	up_write(&trace_event_mutex);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(register_ftrace_event);
+
+/*
+ * Used by module code with the trace_event_mutex held for write.
+ */
+int __unregister_ftrace_event(struct trace_event *event)
+{
+	hlist_del(&event->node);
+	list_del(&event->list);
+	return 0;
+}
 
 /**
  * unregister_ftrace_event - remove a no longer used event
@@ -535,12 +718,13 @@ int register_ftrace_event(struct trace_event *event)
  */
 int unregister_ftrace_event(struct trace_event *event)
 {
-	mutex_lock(&trace_event_mutex);
-	hlist_del(&event->node);
-	mutex_unlock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
+	__unregister_ftrace_event(event);
+	up_write(&trace_event_mutex);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(unregister_ftrace_event);
 
 /*
  * Standard events
@@ -833,14 +1017,16 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
+	if (!trace_seq_puts(s, "<stack trace>\n"))
+		goto partial;
 	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		if (i) {
-			if (!trace_seq_puts(s, " <= "))
-				goto partial;
+		if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
+			break;
+		if (!trace_seq_puts(s, " => "))
+			goto partial;
 
-			if (!seq_print_ip_sym(s, field->caller[i], flags))
-				goto partial;
-		}
+		if (!seq_print_ip_sym(s, field->caller[i], flags))
+			goto partial;
 		if (!trace_seq_puts(s, "\n"))
 			goto partial;
 	}
@@ -868,10 +1054,10 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!seq_print_userip_objs(field, s, flags))
+	if (!trace_seq_puts(s, "<user stack trace>\n"))
 		goto partial;
 
-	if (!trace_seq_putc(s, '\n'))
+	if (!seq_print_userip_objs(field, s, flags))
 		goto partial;
 
 	return TRACE_TYPE_HANDLED;
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index e0bde39c2dd..d38bec4a9c3 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -1,41 +1,17 @@
 #ifndef __TRACE_EVENTS_H
 #define __TRACE_EVENTS_H
 
+#include <linux/trace_seq.h>
 #include "trace.h"
 
-typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
-					      int flags);
-
-struct trace_event {
-	struct hlist_node	node;
-	int			type;
-	trace_print_func	trace;
-	trace_print_func	raw;
-	trace_print_func	hex;
-	trace_print_func	binary;
-};
-
 extern enum print_line_t
 trace_print_bprintk_msg_only(struct trace_iterator *iter);
 extern enum print_line_t
 trace_print_printk_msg_only(struct trace_iterator *iter);
 
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern int
-trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
 extern int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
-				 size_t cnt);
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
-extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
-				size_t len);
-extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
-extern int trace_seq_path(struct trace_seq *s, struct path *path);
 extern int seq_print_userip_objs(const struct userstack_entry *entry,
 				 struct trace_seq *s, unsigned long sym_flags);
 extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
@@ -44,13 +20,17 @@ extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 extern int trace_print_context(struct trace_iterator *iter);
 extern int trace_print_lat_context(struct trace_iterator *iter);
 
+extern void trace_event_read_lock(void);
+extern void trace_event_read_unlock(void);
 extern struct trace_event *ftrace_find_event(int type);
-extern int register_ftrace_event(struct trace_event *event);
-extern int unregister_ftrace_event(struct trace_event *event);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
 					 int flags);
 
+/* used by module unregistering */
+extern int __unregister_ftrace_event(struct trace_event *event);
+extern struct rw_semaphore trace_event_mutex;
+
 #define MAX_MEMHEX_BYTES	8
 #define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
 
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 118439709fb..8a30d9874cd 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -36,6 +36,7 @@ static void probe_power_start(struct power_trace *it, unsigned int type,
 
 static void probe_power_end(struct power_trace *it)
 {
+	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
@@ -54,7 +55,8 @@ static void probe_power_end(struct power_trace *it)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -62,6 +64,7 @@ static void probe_power_end(struct power_trace *it)
 static void probe_power_mark(struct power_trace *it, unsigned int type,
 				unsigned int level)
 {
+	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
@@ -84,7 +87,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index eb81556107f..9bece9687b6 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -245,17 +245,13 @@ static const struct file_operations ftrace_formats_fops = {
 static __init int init_trace_printk_function_export(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
 		return 0;
 
-	entry = debugfs_create_file("printk_formats", 0444, d_tracer,
+	trace_create_file("printk_formats", 0444, d_tracer,
 				    NULL, &ftrace_formats_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'printk_formats' entry\n");
 
 	return 0;
 }
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 9117cea6f1a..a98106dd979 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -10,7 +10,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 
@@ -29,13 +29,13 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	int cpu;
 	int pc;
 
-	if (!sched_ref || sched_stopped)
+	if (unlikely(!sched_ref))
 		return;
 
 	tracing_record_cmdline(prev);
 	tracing_record_cmdline(next);
 
-	if (!tracer_enabled)
+	if (!tracer_enabled || sched_stopped)
 		return;
 
 	pc = preempt_count();
@@ -56,15 +56,15 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 	unsigned long flags;
 	int cpu, pc;
 
-	if (!likely(tracer_enabled))
+	if (unlikely(!sched_ref))
 		return;
 
-	pc = preempt_count();
 	tracing_record_cmdline(current);
 
-	if (sched_stopped)
+	if (!tracer_enabled || sched_stopped)
 		return;
 
+	pc = preempt_count();
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = ctx_trace->data[cpu];
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5bc00e8f153..eacb2722517 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -15,7 +15,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 
@@ -138,9 +138,6 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 
 	pc = preempt_count();
 
-	/* The task we are waiting for is waking up */
-	data = wakeup_trace->data[wakeup_cpu];
-
 	/* disable local data, not wakeup_cpu data */
 	cpu = raw_smp_processor_id();
 	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
@@ -154,6 +151,9 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	if (unlikely(!tracer_enabled || next != wakeup_task))
 		goto out_unlock;
 
+	/* The task we are waiting for is waking up */
+	data = wakeup_trace->data[wakeup_cpu];
+
 	trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 08f4eb2763d..00dd6485bdd 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -16,6 +16,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
+	case TRACE_HW_BRANCHES:
 		return 1;
 	}
 	return 0;
@@ -188,6 +189,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 #else
 # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
 #endif /* CONFIG_DYNAMIC_FTRACE */
+
 /*
  * Simple verification test of ftrace function tracer.
  * Enable ftrace, sleep 1/10 second, and then read the trace
@@ -749,3 +751,59 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 	return ret;
 }
 #endif /* CONFIG_BRANCH_TRACER */
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+int
+trace_selftest_startup_hw_branches(struct tracer *trace,
+				   struct trace_array *tr)
+{
+	struct trace_iterator *iter;
+	struct tracer tracer;
+	unsigned long count;
+	int ret;
+
+	if (!trace->open) {
+		printk(KERN_CONT "missing open function...");
+		return -1;
+	}
+
+	ret = tracer_init(trace, tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
+	/*
+	 * The hw-branch tracer needs to collect the trace from the various
+	 * cpu trace buffers - before tracing is stopped.
+	 */
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return -ENOMEM;
+
+	memcpy(&tracer, trace, sizeof(tracer));
+
+	iter->trace = &tracer;
+	iter->tr = tr;
+	iter->pos = -1;
+	mutex_init(&iter->mutex);
+
+	trace->open(iter);
+
+	mutex_destroy(&iter->mutex);
+	kfree(iter);
+
+	tracing_stop();
+
+	ret = trace_test_buffer(tr, &count);
+	trace->reset(tr);
+	tracing_start();
+
+	if (!ret && !count) {
+		printk(KERN_CONT "no entries found..");
+		ret = -1;
+	}
+
+	return ret;
+}
+#endif /* CONFIG_HW_BRANCH_TRACER */
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c750f65f966..2d7aebd71db 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -265,7 +265,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries);
+			   max_stack_trace.nr_entries - 1);
 
 		if (!stack_tracer_enabled && !max_stack_size)
 			print_disabled(m);
@@ -352,19 +352,14 @@ __setup("stacktrace", enable_stacktrace);
 static __init int stack_trace_init(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
-				    &max_stack_size, &stack_max_size_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+	trace_create_file("stack_max_size", 0644, d_tracer,
+			&max_stack_size, &stack_max_size_fops);
 
-	entry = debugfs_create_file("stack_trace", 0444, d_tracer,
-				    NULL, &stack_trace_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'stack_trace' entry\n");
+	trace_create_file("stack_trace", 0444, d_tracer,
+			NULL, &stack_trace_fops);
 
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index acdebd771a9..c00643733f4 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -1,7 +1,7 @@
 /*
  * Infrastructure for statistic tracing (histogram output).
  *
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Based on the code from trace_branch.c which is
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
@@ -10,22 +10,27 @@
 
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/debugfs.h>
 #include "trace_stat.h"
 #include "trace.h"
 
 
-/* List of stat entries from a tracer */
-struct trace_stat_list {
-	struct list_head	list;
+/*
+ * List of stat red-black nodes from a tracer
+ * We use a such tree to sort quickly the stat
+ * entries from the tracer.
+ */
+struct stat_node {
+	struct rb_node		node;
 	void			*stat;
 };
 
 /* A stat session is the stats output in one file */
-struct tracer_stat_session {
+struct stat_session {
 	struct list_head	session_list;
 	struct tracer_stat	*ts;
-	struct list_head	stat_list;
+	struct rb_root		stat_root;
 	struct mutex		stat_mutex;
 	struct dentry		*file;
 };
@@ -37,18 +42,48 @@ static DEFINE_MUTEX(all_stat_sessions_mutex);
 /* The root directory for all stat files */
 static struct dentry		*stat_dir;
 
+/*
+ * Iterate through the rbtree using a post order traversal path
+ * to release the next node.
+ * It won't necessary release one at each iteration
+ * but it will at least advance closer to the next one
+ * to be released.
+ */
+static struct rb_node *release_next(struct rb_node *node)
+{
+	struct stat_node *snode;
+	struct rb_node *parent = rb_parent(node);
+
+	if (node->rb_left)
+		return node->rb_left;
+	else if (node->rb_right)
+		return node->rb_right;
+	else {
+		if (!parent)
+			;
+		else if (parent->rb_left == node)
+			parent->rb_left = NULL;
+		else
+			parent->rb_right = NULL;
+
+		snode = container_of(node, struct stat_node, node);
+		kfree(snode);
+
+		return parent;
+	}
+}
 
-static void reset_stat_session(struct tracer_stat_session *session)
+static void reset_stat_session(struct stat_session *session)
 {
-	struct trace_stat_list *node, *next;
+	struct rb_node *node = session->stat_root.rb_node;
 
-	list_for_each_entry_safe(node, next, &session->stat_list, list)
-		kfree(node);
+	while (node)
+		node = release_next(node);
 
-	INIT_LIST_HEAD(&session->stat_list);
+	session->stat_root = RB_ROOT;
 }
 
-static void destroy_session(struct tracer_stat_session *session)
+static void destroy_session(struct stat_session *session)
 {
 	debugfs_remove(session->file);
 	reset_stat_session(session);
@@ -56,25 +91,60 @@ static void destroy_session(struct tracer_stat_session *session)
 	kfree(session);
 }
 
+typedef int (*cmp_stat_t)(void *, void *);
+
+static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct stat_node *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->stat = stat;
+
+	/*
+	 * Figure out where to put new node
+	 * This is a descendent sorting
+	 */
+	while (*new) {
+		struct stat_node *this;
+		int result;
+
+		this = container_of(*new, struct stat_node, node);
+		result = cmp(data->stat, this->stat);
+
+		parent = *new;
+		if (result >= 0)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+	return 0;
+}
+
 /*
  * For tracers that don't provide a stat_cmp callback.
- * This one will force an immediate insertion on tail of
- * the list.
+ * This one will force an insertion as right-most node
+ * in the rbtree.
  */
 static int dummy_cmp(void *p1, void *p2)
 {
-	return 1;
+	return -1;
 }
 
 /*
- * Initialize the stat list at each trace_stat file opening.
+ * Initialize the stat rbtree at each trace_stat file opening.
  * All of these copies and sorting are required on all opening
  * since the stats could have changed between two file sessions.
  */
-static int stat_seq_init(struct tracer_stat_session *session)
+static int stat_seq_init(struct stat_session *session)
 {
-	struct trace_stat_list *iter_entry, *new_entry;
 	struct tracer_stat *ts = session->ts;
+	struct rb_root *root = &session->stat_root;
 	void *stat;
 	int ret = 0;
 	int i;
@@ -85,29 +155,16 @@ static int stat_seq_init(struct tracer_stat_session *session)
 	if (!ts->stat_cmp)
 		ts->stat_cmp = dummy_cmp;
 
-	stat = ts->stat_start();
+	stat = ts->stat_start(ts);
 	if (!stat)
 		goto exit;
 
-	/*
-	 * The first entry. Actually this is the second, but the first
-	 * one (the stat_list head) is pointless.
-	 */
-	new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
-	if (!new_entry) {
-		ret = -ENOMEM;
+	ret = insert_stat(root, stat, ts->stat_cmp);
+	if (ret)
 		goto exit;
-	}
-
-	INIT_LIST_HEAD(&new_entry->list);
-
-	list_add(&new_entry->list, &session->stat_list);
-
-	new_entry->stat = stat;
 
 	/*
-	 * Iterate over the tracer stat entries and store them in a sorted
-	 * list.
+	 * Iterate over the tracer stat entries and store them in an rbtree.
 	 */
 	for (i = 1; ; i++) {
 		stat = ts->stat_next(stat, i);
@@ -116,36 +173,16 @@ static int stat_seq_init(struct tracer_stat_session *session)
 		if (!stat)
 			break;
 
-		new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
-		if (!new_entry) {
-			ret = -ENOMEM;
-			goto exit_free_list;
-		}
-
-		INIT_LIST_HEAD(&new_entry->list);
-		new_entry->stat = stat;
-
-		list_for_each_entry_reverse(iter_entry, &session->stat_list,
-				list) {
-
-			/* Insertion with a descendent sorting */
-			if (ts->stat_cmp(iter_entry->stat,
-					new_entry->stat) >= 0) {
-
-				list_add(&new_entry->list, &iter_entry->list);
-				break;
-			}
-		}
-
-		/* The current larger value */
-		if (list_empty(&new_entry->list))
-			list_add(&new_entry->list, &session->stat_list);
+		ret = insert_stat(root, stat, ts->stat_cmp);
+		if (ret)
+			goto exit_free_rbtree;
 	}
+
 exit:
 	mutex_unlock(&session->stat_mutex);
 	return ret;
 
-exit_free_list:
+exit_free_rbtree:
 	reset_stat_session(session);
 	mutex_unlock(&session->stat_mutex);
 	return ret;
@@ -154,38 +191,51 @@ exit_free_list:
 
 static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
+	struct rb_node *node;
+	int i;
 
-	/* Prevent from tracer switch or stat_list modification */
+	/* Prevent from tracer switch or rbtree modification */
 	mutex_lock(&session->stat_mutex);
 
 	/* If we are in the beginning of the file, print the headers */
-	if (!*pos && session->ts->stat_headers)
+	if (!*pos && session->ts->stat_headers) {
+		(*pos)++;
 		return SEQ_START_TOKEN;
+	}
 
-	return seq_list_start(&session->stat_list, *pos);
+	node = rb_first(&session->stat_root);
+	for (i = 0; node && i < *pos; i++)
+		node = rb_next(node);
+
+	(*pos)++;
+
+	return node;
 }
 
 static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
+	struct rb_node *node = p;
+
+	(*pos)++;
 
 	if (p == SEQ_START_TOKEN)
-		return seq_list_start(&session->stat_list, *pos);
+		return rb_first(&session->stat_root);
 
-	return seq_list_next(p, &session->stat_list, pos);
+	return rb_next(node);
 }
 
 static void stat_seq_stop(struct seq_file *s, void *p)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
 	mutex_unlock(&session->stat_mutex);
 }
 
 static int stat_seq_show(struct seq_file *s, void *v)
 {
-	struct tracer_stat_session *session = s->private;
-	struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list);
+	struct stat_session *session = s->private;
+	struct stat_node *l = container_of(v, struct stat_node, node);
 
 	if (v == SEQ_START_TOKEN)
 		return session->ts->stat_headers(s);
@@ -205,7 +255,7 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	struct tracer_stat_session *session = inode->i_private;
+	struct stat_session *session = inode->i_private;
 
 	ret = seq_open(file, &trace_stat_seq_ops);
 	if (!ret) {
@@ -218,11 +268,11 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
 }
 
 /*
- * Avoid consuming memory with our now useless list.
+ * Avoid consuming memory with our now useless rbtree.
  */
 static int tracing_stat_release(struct inode *i, struct file *f)
 {
-	struct tracer_stat_session *session = i->i_private;
+	struct stat_session *session = i->i_private;
 
 	mutex_lock(&session->stat_mutex);
 	reset_stat_session(session);
@@ -251,7 +301,7 @@ static int tracing_stat_init(void)
 	return 0;
 }
 
-static int init_stat_file(struct tracer_stat_session *session)
+static int init_stat_file(struct stat_session *session)
 {
 	if (!stat_dir && tracing_stat_init())
 		return -ENODEV;
@@ -266,7 +316,7 @@ static int init_stat_file(struct tracer_stat_session *session)
 
 int register_stat_tracer(struct tracer_stat *trace)
 {
-	struct tracer_stat_session *session, *node, *tmp;
+	struct stat_session *session, *node;
 	int ret;
 
 	if (!trace)
@@ -277,7 +327,7 @@ int register_stat_tracer(struct tracer_stat *trace)
 
 	/* Already registered? */
 	mutex_lock(&all_stat_sessions_mutex);
-	list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
+	list_for_each_entry(node, &all_stat_sessions, session_list) {
 		if (node->ts == trace) {
 			mutex_unlock(&all_stat_sessions_mutex);
 			return -EINVAL;
@@ -286,15 +336,13 @@ int register_stat_tracer(struct tracer_stat *trace)
 	mutex_unlock(&all_stat_sessions_mutex);
 
 	/* Init the session */
-	session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL);
+	session = kzalloc(sizeof(*session), GFP_KERNEL);
 	if (!session)
 		return -ENOMEM;
 
 	session->ts = trace;
 	INIT_LIST_HEAD(&session->session_list);
-	INIT_LIST_HEAD(&session->stat_list);
 	mutex_init(&session->stat_mutex);
-	session->file = NULL;
 
 	ret = init_stat_file(session);
 	if (ret) {
@@ -312,7 +360,7 @@ int register_stat_tracer(struct tracer_stat *trace)
 
 void unregister_stat_tracer(struct tracer_stat *trace)
 {
-	struct tracer_stat_session *node, *tmp;
+	struct stat_session *node, *tmp;
 
 	mutex_lock(&all_stat_sessions_mutex);
 	list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 202274cf7f3..f3546a2cd82 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -12,7 +12,7 @@ struct tracer_stat {
 	/* The name of your stat file */
 	const char		*name;
 	/* Iteration over statistic entries */
-	void			*(*stat_start)(void);
+	void			*(*stat_start)(struct tracer_stat *trace);
 	void			*(*stat_next)(void *prev, int idx);
 	/* Compare two entries for stats sorting */
 	int			(*stat_cmp)(void *p1, void *p2);
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 91fd19c2149..e04b76cc238 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -321,11 +321,7 @@ static const struct file_operations sysprof_sample_fops = {
 
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
 {
-	struct dentry *entry;
 
-	entry = debugfs_create_file("sysprof_sample_period", 0644,
+	trace_create_file("sysprof_sample_period", 0644,
 			d_tracer, NULL, &sysprof_sample_fops);
-	if (entry)
-		return;
-	pr_warning("Could not create debugfs 'sysprof_sample_period' entry\n");
 }
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 797201e4a13..97fcea4acce 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -6,7 +6,7 @@
  */
 
 
-#include <trace/workqueue.h>
+#include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
 #include "trace_stat.h"
@@ -16,8 +16,6 @@
 /* A cpu workqueue thread */
 struct cpu_workqueue_stats {
 	struct list_head            list;
-/* Useful to know if we print the cpu headers */
-	bool		            first_entry;
 	int		            cpu;
 	pid_t			    pid;
 /* Can be inserted from interrupt or user context, need to be atomic */
@@ -47,12 +45,11 @@ probe_workqueue_insertion(struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
-	struct cpu_workqueue_stats *node, *next;
+	struct cpu_workqueue_stats *node;
 	unsigned long flags;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
-							list) {
+	list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
 		if (node->pid == wq_thread->pid) {
 			atomic_inc(&node->inserted);
 			goto found;
@@ -69,12 +66,11 @@ probe_workqueue_execution(struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
-	struct cpu_workqueue_stats *node, *next;
+	struct cpu_workqueue_stats *node;
 	unsigned long flags;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
-							list) {
+	list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
 		if (node->pid == wq_thread->pid) {
 			node->executed++;
 			goto found;
@@ -105,8 +101,6 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 	cws->pid = wq_thread->pid;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (list_empty(&workqueue_cpu_stat(cpu)->list))
-		cws->first_entry = true;
 	list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list);
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 }
@@ -152,7 +146,7 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
 	return ret;
 }
 
-static void *workqueue_stat_start(void)
+static void *workqueue_stat_start(struct tracer_stat *trace)
 {
 	int cpu;
 	void *ret = NULL;
@@ -191,16 +185,9 @@ static void *workqueue_stat_next(void *prev, int idx)
 static int workqueue_stat_show(struct seq_file *s, void *p)
 {
 	struct cpu_workqueue_stats *cws = p;
-	unsigned long flags;
-	int cpu = cws->cpu;
 	struct pid *pid;
 	struct task_struct *tsk;
 
-	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
-		seq_printf(s, "\n");
-	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
-
 	pid = find_get_pid(cws->pid);
 	if (pid) {
 		tsk = get_pid_task(pid, PIDTYPE_PID);
diff --git a/kernel/wait.c b/kernel/wait.c
index 42a2dbc181c..ea7c3b4275c 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -154,7 +154,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_common(q, mode, 1, 0, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f71fb2a0895..0668795d881 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -33,7 +33,8 @@
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
-#include <trace/workqueue.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
 
 /*
  * The per-CPU workqueue (if single thread, we always use the first
@@ -124,8 +125,6 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
 }
 
-DEFINE_TRACE(workqueue_insertion);
-
 static void insert_work(struct cpu_workqueue_struct *cwq,
 			struct work_struct *work, struct list_head *head)
 {
@@ -262,8 +261,6 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
-DEFINE_TRACE(workqueue_execution);
-
 static void run_workqueue(struct cpu_workqueue_struct *cwq)
 {
 	spin_lock_irq(&cwq->lock);
@@ -753,8 +750,6 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
 	return cwq;
 }
 
-DEFINE_TRACE(workqueue_creation);
-
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
@@ -860,8 +855,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 }
 EXPORT_SYMBOL_GPL(__create_workqueue_key);
 
-DEFINE_TRACE(workqueue_destruction);
-
 static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 {
 	/*
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 1f71b97de0f..eb23aaa0c7b 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -119,6 +119,12 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 }
 EXPORT_SYMBOL(alloc_cpumask_var_node);
 
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
+{
+	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
+}
+EXPORT_SYMBOL(zalloc_cpumask_var_node);
+
 /**
  * alloc_cpumask_var - allocate a struct cpumask
  * @mask: pointer to cpumask_var_t where the cpumask is returned
@@ -135,6 +141,12 @@ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 }
 EXPORT_SYMBOL(alloc_cpumask_var);
 
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
+}
+EXPORT_SYMBOL(zalloc_cpumask_var);
+
 /**
  * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
  * @mask: pointer to cpumask_var_t where the cpumask is returned
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 69da09a085a..ad65fc0317d 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -23,9 +23,11 @@
 #include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
 
@@ -85,6 +87,7 @@ static u32 show_num_errors = 1;
 
 static u32 num_free_entries;
 static u32 min_free_entries;
+static u32 nr_total_entries;
 
 /* number of preallocated entries requested by kernel cmdline */
 static u32 req_entries;
@@ -97,6 +100,16 @@ static struct dentry *show_all_errors_dent  __read_mostly;
 static struct dentry *show_num_errors_dent  __read_mostly;
 static struct dentry *num_free_entries_dent __read_mostly;
 static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent           __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN	64
+
+static char                  current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver                    __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
 
 static const char *type2name[4] = { "single", "page",
 				    "scather-gather", "coherent" };
@@ -104,6 +117,11 @@ static const char *type2name[4] = { "single", "page",
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
 				   "DMA_FROM_DEVICE", "DMA_NONE" };
 
+/* little merge helper - remove it after the merge window */
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
+
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
  * here because all these variables are exported to debugfs. Some of them even
@@ -121,15 +139,54 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 {
 #ifdef CONFIG_STACKTRACE
 	if (entry) {
-		printk(KERN_WARNING "Mapped at:\n");
+		pr_warning("Mapped at:\n");
 		print_stack_trace(&entry->stacktrace, 0);
 	}
 #endif
 }
 
+static bool driver_filter(struct device *dev)
+{
+	struct device_driver *drv;
+	unsigned long flags;
+	bool ret;
+
+	/* driver filter off */
+	if (likely(!current_driver_name[0]))
+		return true;
+
+	/* driver filter on and initialized */
+	if (current_driver && dev->driver == current_driver)
+		return true;
+
+	if (current_driver || !current_driver_name[0])
+		return false;
+
+	/* driver filter on but not yet initialized */
+	drv = get_driver(dev->driver);
+	if (!drv)
+		return false;
+
+	/* lock to protect against change of current_driver_name */
+	read_lock_irqsave(&driver_name_lock, flags);
+
+	ret = false;
+	if (drv->name &&
+	    strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+		current_driver = drv;
+		ret = true;
+	}
+
+	read_unlock_irqrestore(&driver_name_lock, flags);
+	put_driver(drv);
+
+	return ret;
+}
+
 #define err_printk(dev, entry, format, arg...) do {		\
 		error_count += 1;				\
-		if (show_all_errors || show_num_errors > 0) {	\
+		if (driver_filter(dev) &&			\
+		    (show_all_errors || show_num_errors > 0)) {	\
 			WARN(1, "%s %s: " format,		\
 			     dev_driver_string(dev),		\
 			     dev_name(dev) , ## arg);		\
@@ -185,15 +242,50 @@ static void put_hash_bucket(struct hash_bucket *bucket,
 static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
 						struct dma_debug_entry *ref)
 {
-	struct dma_debug_entry *entry;
+	struct dma_debug_entry *entry, *ret = NULL;
+	int matches = 0, match_lvl, last_lvl = 0;
 
 	list_for_each_entry(entry, &bucket->list, list) {
-		if ((entry->dev_addr == ref->dev_addr) &&
-		    (entry->dev == ref->dev))
+		if ((entry->dev_addr != ref->dev_addr) ||
+		    (entry->dev != ref->dev))
+			continue;
+
+		/*
+		 * Some drivers map the same physical address multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therfore we implement a
+		 * best-fit algorithm here which returns the entry from
+		 * the hash which fits best to the reference value
+		 * instead of the first-fit.
+		 */
+		matches += 1;
+		match_lvl = 0;
+		entry->size      == ref->size      ? ++match_lvl : match_lvl;
+		entry->type      == ref->type      ? ++match_lvl : match_lvl;
+		entry->direction == ref->direction ? ++match_lvl : match_lvl;
+
+		if (match_lvl == 3) {
+			/* perfect-fit - return the result */
 			return entry;
+		} else if (match_lvl > last_lvl) {
+			/*
+			 * We found an entry that fits better then the
+			 * previous one
+			 */
+			last_lvl = match_lvl;
+			ret      = entry;
+		}
 	}
 
-	return NULL;
+	/*
+	 * If we have multiple matches but no perfect-fit, just return
+	 * NULL.
+	 */
+	ret = (matches == 1) ? ret : NULL;
+
+	return ret;
 }
 
 /*
@@ -257,6 +349,21 @@ static void add_dma_entry(struct dma_debug_entry *entry)
 	put_hash_bucket(bucket, &flags);
 }
 
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+	struct dma_debug_entry *entry;
+
+	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+	list_del(&entry->list);
+	memset(entry, 0, sizeof(*entry));
+
+	num_free_entries -= 1;
+	if (num_free_entries < min_free_entries)
+		min_free_entries = num_free_entries;
+
+	return entry;
+}
+
 /* struct dma_entry allocator
  *
  * The next two functions implement the allocator for
@@ -270,15 +377,12 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	spin_lock_irqsave(&free_entries_lock, flags);
 
 	if (list_empty(&free_entries)) {
-		printk(KERN_ERR "DMA-API: debugging out of memory "
-				"- disabling\n");
+		pr_err("DMA-API: debugging out of memory - disabling\n");
 		global_disable = true;
 		goto out;
 	}
 
-	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
-	list_del(&entry->list);
-	memset(entry, 0, sizeof(*entry));
+	entry = __dma_entry_alloc();
 
 #ifdef CONFIG_STACKTRACE
 	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
@@ -286,9 +390,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	entry->stacktrace.skip = 2;
 	save_stack_trace(&entry->stacktrace);
 #endif
-	num_free_entries -= 1;
-	if (num_free_entries < min_free_entries)
-		min_free_entries = num_free_entries;
 
 out:
 	spin_unlock_irqrestore(&free_entries_lock, flags);
@@ -310,6 +411,53 @@ static void dma_entry_free(struct dma_debug_entry *entry)
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 }
 
+int dma_debug_resize_entries(u32 num_entries)
+{
+	int i, delta, ret = 0;
+	unsigned long flags;
+	struct dma_debug_entry *entry;
+	LIST_HEAD(tmp);
+
+	spin_lock_irqsave(&free_entries_lock, flags);
+
+	if (nr_total_entries < num_entries) {
+		delta = num_entries - nr_total_entries;
+
+		spin_unlock_irqrestore(&free_entries_lock, flags);
+
+		for (i = 0; i < delta; i++) {
+			entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+			if (!entry)
+				break;
+
+			list_add_tail(&entry->list, &tmp);
+		}
+
+		spin_lock_irqsave(&free_entries_lock, flags);
+
+		list_splice(&tmp, &free_entries);
+		nr_total_entries += i;
+		num_free_entries += i;
+	} else {
+		delta = nr_total_entries - num_entries;
+
+		for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+			entry = __dma_entry_alloc();
+			kfree(entry);
+		}
+
+		nr_total_entries -= i;
+	}
+
+	if (nr_total_entries != num_entries)
+		ret = 1;
+
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_debug_resize_entries);
+
 /*
  * DMA-API debugging init code
  *
@@ -334,8 +482,7 @@ static int prealloc_memory(u32 num_entries)
 	num_free_entries = num_entries;
 	min_free_entries = num_entries;
 
-	printk(KERN_INFO "DMA-API: preallocated %d debug entries\n",
-			num_entries);
+	pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
 
 	return 0;
 
@@ -349,11 +496,102 @@ out_err:
 	return -ENOMEM;
 }
 
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN + 1];
+	unsigned long flags;
+	int len;
+
+	if (!current_driver_name[0])
+		return 0;
+
+	/*
+	 * We can't copy to userspace directly because current_driver_name can
+	 * only be read under the driver_name_lock with irqs disabled. So
+	 * create a temporary copy first.
+	 */
+	read_lock_irqsave(&driver_name_lock, flags);
+	len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+	read_unlock_irqrestore(&driver_name_lock, flags);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN];
+	unsigned long flags;
+	size_t len;
+	int i;
+
+	/*
+	 * We can't copy from userspace directly. Access to
+	 * current_driver_name is protected with a write_lock with irqs
+	 * disabled. Since copy_from_user can fault and may sleep we
+	 * need to copy to temporary buffer first
+	 */
+	len = min(count, (size_t)(NAME_MAX_LEN - 1));
+	if (copy_from_user(buf, userbuf, len))
+		return -EFAULT;
+
+	buf[len] = 0;
+
+	write_lock_irqsave(&driver_name_lock, flags);
+
+	/*
+	 * Now handle the string we got from userspace very carefully.
+	 * The rules are:
+	 *         - only use the first token we got
+	 *         - token delimiter is everything looking like a space
+	 *           character (' ', '\n', '\t' ...)
+	 *
+	 */
+	if (!isalnum(buf[0])) {
+		/*
+		 * If the first character userspace gave us is not
+		 * alphanumerical then assume the filter should be
+		 * switched off.
+		 */
+		if (current_driver_name[0])
+			pr_info("DMA-API: switching off dma-debug driver filter\n");
+		current_driver_name[0] = 0;
+		current_driver = NULL;
+		goto out_unlock;
+	}
+
+	/*
+	 * Now parse out the first token and use it as the name for the
+	 * driver to filter for.
+	 */
+	for (i = 0; i < NAME_MAX_LEN; ++i) {
+		current_driver_name[i] = buf[i];
+		if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+			break;
+	}
+	current_driver_name[i] = 0;
+	current_driver = NULL;
+
+	pr_info("DMA-API: enable driver filter for driver [%s]\n",
+		current_driver_name);
+
+out_unlock:
+	write_unlock_irqrestore(&driver_name_lock, flags);
+
+	return count;
+}
+
+const struct file_operations filter_fops = {
+	.read  = filter_read,
+	.write = filter_write,
+};
+
 static int dma_debug_fs_init(void)
 {
 	dma_debug_dent = debugfs_create_dir("dma-api", NULL);
 	if (!dma_debug_dent) {
-		printk(KERN_ERR "DMA-API: can not create debugfs directory\n");
+		pr_err("DMA-API: can not create debugfs directory\n");
 		return -ENOMEM;
 	}
 
@@ -392,6 +630,11 @@ static int dma_debug_fs_init(void)
 	if (!min_free_entries_dent)
 		goto out_err;
 
+	filter_dent = debugfs_create_file("driver_filter", 0644,
+					  dma_debug_dent, NULL, &filter_fops);
+	if (!filter_dent)
+		goto out_err;
+
 	return 0;
 
 out_err:
@@ -400,9 +643,64 @@ out_err:
 	return -ENOMEM;
 }
 
+static int device_dma_allocations(struct device *dev)
+{
+	struct dma_debug_entry *entry;
+	unsigned long flags;
+	int count = 0, i;
+
+	local_irq_save(flags);
+
+	for (i = 0; i < HASH_SIZE; ++i) {
+		spin_lock(&dma_entry_hash[i].lock);
+		list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+			if (entry->dev == dev)
+				count += 1;
+		}
+		spin_unlock(&dma_entry_hash[i].lock);
+	}
+
+	local_irq_restore(flags);
+
+	return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb,
+				    unsigned long action, void *data)
+{
+	struct device *dev = data;
+	int count;
+
+
+	switch (action) {
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		count = device_dma_allocations(dev);
+		if (count == 0)
+			break;
+		err_printk(dev, NULL, "DMA-API: device driver has pending "
+				"DMA allocations while released from device "
+				"[count=%d]\n", count);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 void dma_debug_add_bus(struct bus_type *bus)
 {
-	/* FIXME: register notifier */
+	struct notifier_block *nb;
+
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (nb == NULL) {
+		pr_err("dma_debug_add_bus: out of memory\n");
+		return;
+	}
+
+	nb->notifier_call = dma_debug_device_change;
+
+	bus_register_notifier(bus, nb);
 }
 
 /*
@@ -421,8 +719,7 @@ void dma_debug_init(u32 num_entries)
 	}
 
 	if (dma_debug_fs_init() != 0) {
-		printk(KERN_ERR "DMA-API: error creating debugfs entries "
-				"- disabling\n");
+		pr_err("DMA-API: error creating debugfs entries - disabling\n");
 		global_disable = true;
 
 		return;
@@ -432,14 +729,15 @@ void dma_debug_init(u32 num_entries)
 		num_entries = req_entries;
 
 	if (prealloc_memory(num_entries) != 0) {
-		printk(KERN_ERR "DMA-API: debugging out of memory error "
-				"- disabled\n");
+		pr_err("DMA-API: debugging out of memory error - disabled\n");
 		global_disable = true;
 
 		return;
 	}
 
-	printk(KERN_INFO "DMA-API: debugging enabled by kernel config\n");
+	nr_total_entries = num_free_entries;
+
+	pr_info("DMA-API: debugging enabled by kernel config\n");
 }
 
 static __init int dma_debug_cmdline(char *str)
@@ -448,8 +746,7 @@ static __init int dma_debug_cmdline(char *str)
 		return -EINVAL;
 
 	if (strncmp(str, "off", 3) == 0) {
-		printk(KERN_INFO "DMA-API: debugging disabled on kernel "
-				 "command line\n");
+		pr_info("DMA-API: debugging disabled on kernel command line\n");
 		global_disable = true;
 	}
 
@@ -723,15 +1020,15 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		entry->type           = dma_debug_sg;
 		entry->dev            = dev;
 		entry->paddr          = sg_phys(s);
-		entry->size           = s->length;
-		entry->dev_addr       = s->dma_address;
+		entry->size           = sg_dma_len(s);
+		entry->dev_addr       = sg_dma_address(s);
 		entry->direction      = direction;
 		entry->sg_call_ents   = nents;
 		entry->sg_mapped_ents = mapped_ents;
 
 		if (!PageHighMem(sg_page(s))) {
 			check_for_stack(dev, sg_virt(s));
-			check_for_illegal_area(dev, sg_virt(s), s->length);
+			check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
 		}
 
 		add_dma_entry(entry);
@@ -739,13 +1036,33 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(debug_dma_map_sg);
 
+static int get_nr_mapped_entries(struct device *dev, struct scatterlist *s)
+{
+	struct dma_debug_entry *entry, ref;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+	int mapped_ents;
+
+	ref.dev      = dev;
+	ref.dev_addr = sg_dma_address(s);
+	ref.size     = sg_dma_len(s),
+
+	bucket       = get_hash_bucket(&ref, &flags);
+	entry        = hash_bucket_find(bucket, &ref);
+	mapped_ents  = 0;
+
+	if (entry)
+		mapped_ents = entry->sg_mapped_ents;
+	put_hash_bucket(bucket, &flags);
+
+	return mapped_ents;
+}
+
 void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			int nelems, int dir)
 {
-	struct dma_debug_entry *entry;
 	struct scatterlist *s;
 	int mapped_ents = 0, i;
-	unsigned long flags;
 
 	if (unlikely(global_disable))
 		return;
@@ -756,8 +1073,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			.type           = dma_debug_sg,
 			.dev            = dev,
 			.paddr          = sg_phys(s),
-			.dev_addr       = s->dma_address,
-			.size           = s->length,
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
 			.direction      = dir,
 			.sg_call_ents   = 0,
 		};
@@ -765,14 +1082,9 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		if (mapped_ents && i >= mapped_ents)
 			break;
 
-		if (mapped_ents == 0) {
-			struct hash_bucket *bucket;
+		if (!i) {
 			ref.sg_call_ents = nelems;
-			bucket = get_hash_bucket(&ref, &flags);
-			entry = hash_bucket_find(bucket, &ref);
-			if (entry)
-				mapped_ents = entry->sg_mapped_ents;
-			put_hash_bucket(bucket, &flags);
+			mapped_ents = get_nr_mapped_entries(dev, s);
 		}
 
 		check_unmap(&ref);
@@ -874,14 +1186,20 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 			       int nelems, int direction)
 {
 	struct scatterlist *s;
-	int i;
+	int mapped_ents = 0, i;
 
 	if (unlikely(global_disable))
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
-		check_sync(dev, s->dma_address, s->dma_length, 0,
-				direction, true);
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, s);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+			   direction, true);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
@@ -890,15 +1208,39 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				  int nelems, int direction)
 {
 	struct scatterlist *s;
-	int i;
+	int mapped_ents = 0, i;
 
 	if (unlikely(global_disable))
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
-		check_sync(dev, s->dma_address, s->dma_length, 0,
-				direction, false);
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, s);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+			   direction, false);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
 
+static int __init dma_debug_driver_setup(char *str)
+{
+	int i;
+
+	for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+		current_driver_name[i] = *str;
+		if (*str == 0)
+			break;
+	}
+
+	if (current_driver_name[0])
+		pr_info("DMA-API: enable driver filter for driver [%s]\n",
+			current_driver_name);
+
+
+	return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 2b0b5a7d2ce..bffe6d7ef9d 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -60,8 +60,8 @@ enum dma_sync_target {
 int swiotlb_force;
 
 /*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in unmap_single and
+ * sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
 static char *io_tlb_start, *io_tlb_end;
@@ -129,7 +129,7 @@ dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
 {
 	return baddr;
 }
@@ -140,9 +140,15 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 	return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
 }
 
-static void *swiotlb_bus_to_virt(dma_addr_t address)
+void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
 {
-	return phys_to_virt(swiotlb_bus_to_phys(address));
+	return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
+}
+
+int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
+					       dma_addr_t addr, size_t size)
+{
+	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
 }
 
 int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -309,10 +315,10 @@ cleanup1:
 	return -ENOMEM;
 }
 
-static int
+static inline int
 address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 {
-	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+	return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
 }
 
 static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -341,7 +347,7 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
 		unsigned long flags;
 
 		while (size) {
-			sz = min(PAGE_SIZE - offset, size);
+			sz = min_t(size_t, PAGE_SIZE - offset, size);
 
 			local_irq_save(flags);
 			buffer = kmap_atomic(pfn_to_page(pfn),
@@ -476,7 +482,7 @@ found:
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
 static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
@@ -560,7 +566,6 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 				   size)) {
 		/*
 		 * The allocated memory isn't reachable by the device.
-		 * Fall back on swiotlb_map_single().
 		 */
 		free_pages((unsigned long) ret, order);
 		ret = NULL;
@@ -568,9 +573,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (!ret) {
 		/*
 		 * We are either out of memory or the device can't DMA
-		 * to GFP_DMA memory; fall back on
-		 * swiotlb_map_single(), which will grab memory from
-		 * the lowest available address range.
+		 * to GFP_DMA memory; fall back on map_single(), which
+		 * will grab memory from the lowest available address range.
 		 */
 		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (!ret)
@@ -587,7 +591,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		       (unsigned long long)dev_addr);
 
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+		do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
 		return NULL;
 	}
 	*dma_handle = dev_addr;
@@ -604,7 +608,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		free_pages((unsigned long) vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+		do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
@@ -634,7 +638,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
  */
 dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    unsigned long offset, size_t size,
@@ -642,18 +646,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    struct dma_attrs *attrs)
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
-	void *ptr = page_address(page) + offset;
 	dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
 	/*
-	 * If the pointer passed in happens to be in the device's DMA window,
+	 * If the address happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
 	if (!address_needs_mapping(dev, dev_addr, size) &&
-	    !range_needs_mapping(virt_to_phys(ptr), size))
+	    !range_needs_mapping(phys, size))
 		return dev_addr;
 
 	/*
@@ -679,23 +682,35 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call.  All
+ * match what was provided for in a previous swiotlb_map_page call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			 size_t size, int dir)
+{
+	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	if (is_swiotlb_buffer(dma_addr)) {
+		do_unmap_single(hwdev, dma_addr, size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(dma_addr, size);
+}
+
 void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 			size_t size, enum dma_data_direction dir,
 			struct dma_attrs *attrs)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
-		unmap_single(hwdev, dma_addr, size, dir);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+	unmap_single(hwdev, dev_addr, size, dir);
 }
 EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
@@ -703,7 +718,7 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
  *
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
  * using the cpu, yet do not wish to teardown the dma mapping, you must
  * call this function before doing so.  At the next point you give the dma
  * address back to the card, you must first perform a
@@ -713,13 +728,19 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
+	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
+
+	if (is_swiotlb_buffer(dma_addr)) {
 		sync_single(hwdev, dma_addr, size, dir, target);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(dma_addr, size);
 }
 
 void
@@ -746,13 +767,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 			  unsigned long offset, size_t size,
 			  int dir, int target)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset;
-
-	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
-		sync_single(hwdev, dma_addr, size, dir, target);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+	swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
 }
 
 void
@@ -777,7 +792,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_single
+ * This is the scatter-gather version of the above swiotlb_map_page
  * interface.  Here the scatter gather list elements are each tagged with the
  * appropriate dma address and length.  They are obtained via
  * sg_dma_{address,length}(SG).
@@ -788,7 +803,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
  *       The routine returns the number of addr/length pairs actually
  *       used, at most nents.
  *
- * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
  * same here.
  */
 int
@@ -836,7 +851,7 @@ EXPORT_SYMBOL(swiotlb_map_sg);
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
  */
 void
 swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
@@ -847,13 +862,9 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 
 	BUG_ON(dir == DMA_NONE);
 
-	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
-			unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
-				     sg->dma_length, dir);
-		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
-	}
+	for_each_sg(sgl, sg, nelems, i)
+		unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
 
@@ -879,15 +890,9 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
 	struct scatterlist *sg;
 	int i;
 
-	BUG_ON(dir == DMA_NONE);
-
-	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
-			sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
+	for_each_sg(sgl, sg, nelems, i)
+		swiotlb_sync_single(hwdev, sg->dma_address,
 				    sg->dma_length, dir, target);
-		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
-	}
 }
 
 void
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7536acea135..756ccafa9ce 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -408,6 +408,8 @@ enum format_type {
 	FORMAT_TYPE_LONG_LONG,
 	FORMAT_TYPE_ULONG,
 	FORMAT_TYPE_LONG,
+	FORMAT_TYPE_UBYTE,
+	FORMAT_TYPE_BYTE,
 	FORMAT_TYPE_USHORT,
 	FORMAT_TYPE_SHORT,
 	FORMAT_TYPE_UINT,
@@ -573,12 +575,15 @@ static char *string(char *buf, char *end, char *s, struct printf_spec spec)
 }
 
 static char *symbol_string(char *buf, char *end, void *ptr,
-				struct printf_spec spec)
+				struct printf_spec spec, char ext)
 {
 	unsigned long value = (unsigned long) ptr;
 #ifdef CONFIG_KALLSYMS
 	char sym[KSYM_SYMBOL_LEN];
-	sprint_symbol(sym, value);
+	if (ext != 'f')
+		sprint_symbol(sym, value);
+	else
+		kallsyms_lookup(value, NULL, NULL, NULL, sym);
 	return string(buf, end, sym, spec);
 #else
 	spec.field_width = 2*sizeof(void *);
@@ -690,7 +695,8 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr,
  *
  * Right now we handle:
  *
- * - 'F' For symbolic function descriptor pointers
+ * - 'F' For symbolic function descriptor pointers with offset
+ * - 'f' For simple symbolic function names without offset
  * - 'S' For symbolic direct pointers
  * - 'R' For a struct resource pointer, it prints the range of
  *       addresses (not the name nor the flags)
@@ -713,10 +719,11 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 
 	switch (*fmt) {
 	case 'F':
+	case 'f':
 		ptr = dereference_function_descriptor(ptr);
 		/* Fallthrough */
 	case 'S':
-		return symbol_string(buf, end, ptr, spec);
+		return symbol_string(buf, end, ptr, spec, *fmt);
 	case 'R':
 		return resource_string(buf, end, ptr, spec);
 	case 'm':
@@ -853,11 +860,15 @@ qualifier:
 	spec->qualifier = -1;
 	if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
 	    *fmt == 'Z' || *fmt == 'z' || *fmt == 't') {
-		spec->qualifier = *fmt;
-		++fmt;
-		if (spec->qualifier == 'l' && *fmt == 'l') {
-			spec->qualifier = 'L';
-			++fmt;
+		spec->qualifier = *fmt++;
+		if (unlikely(spec->qualifier == *fmt)) {
+			if (spec->qualifier == 'l') {
+				spec->qualifier = 'L';
+				++fmt;
+			} else if (spec->qualifier == 'h') {
+				spec->qualifier = 'H';
+				++fmt;
+			}
 		}
 	}
 
@@ -919,6 +930,11 @@ qualifier:
 		spec->type = FORMAT_TYPE_SIZE_T;
 	} else if (spec->qualifier == 't') {
 		spec->type = FORMAT_TYPE_PTRDIFF;
+	} else if (spec->qualifier == 'H') {
+		if (spec->flags & SIGN)
+			spec->type = FORMAT_TYPE_BYTE;
+		else
+			spec->type = FORMAT_TYPE_UBYTE;
 	} else if (spec->qualifier == 'h') {
 		if (spec->flags & SIGN)
 			spec->type = FORMAT_TYPE_SHORT;
@@ -943,7 +959,8 @@ qualifier:
  *
  * This function follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  *
  * The return value is the number of characters which would
@@ -1087,6 +1104,12 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			case FORMAT_TYPE_PTRDIFF:
 				num = va_arg(args, ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+				num = (unsigned char) va_arg(args, int);
+				break;
+			case FORMAT_TYPE_BYTE:
+				num = (signed char) va_arg(args, int);
+				break;
 			case FORMAT_TYPE_USHORT:
 				num = (unsigned short) va_arg(args, int);
 				break;
@@ -1363,6 +1386,10 @@ do {									\
 			case FORMAT_TYPE_PTRDIFF:
 				save_arg(ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+			case FORMAT_TYPE_BYTE:
+				save_arg(char);
+				break;
 			case FORMAT_TYPE_USHORT:
 			case FORMAT_TYPE_SHORT:
 				save_arg(short);
@@ -1391,7 +1418,8 @@ EXPORT_SYMBOL_GPL(vbin_printf);
  *
  * The format follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  * %n is ignored
  *
@@ -1538,6 +1566,12 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 			case FORMAT_TYPE_PTRDIFF:
 				num = get_arg(ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+				num = get_arg(unsigned char);
+				break;
+			case FORMAT_TYPE_BYTE:
+				num = get_arg(signed char);
+				break;
 			case FORMAT_TYPE_USHORT:
 				num = get_arg(unsigned short);
 				break;
diff --git a/mm/bounce.c b/mm/bounce.c
index e590272fe7a..65f5e17e411 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -14,16 +14,15 @@
 #include <linux/hash.h>
 #include <linux/highmem.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/block.h>
+
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
 
 static mempool_t *page_pool, *isa_page_pool;
 
-DEFINE_TRACE(block_bio_bounce);
-
 #ifdef CONFIG_HIGHMEM
 static __init int init_emergency_pool(void)
 {
diff --git a/mm/mlock.c b/mm/mlock.c
index cbe9e0581b7..ac130433c7d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -629,52 +629,43 @@ void user_shm_unlock(size_t size, struct user_struct *user)
 	free_uid(user);
 }
 
-void *alloc_locked_buffer(size_t size)
+int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+			  size_t size)
 {
-	unsigned long rlim, vm, pgsz;
-	void *buffer = NULL;
+	unsigned long lim, vm, pgsz;
+	int error = -ENOMEM;
 
 	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
-
-	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->total_vm + pgsz;
-	if (rlim < vm)
-		goto out;
+	down_write(&mm->mmap_sem);
 
-	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->locked_vm + pgsz;
-	if (rlim < vm)
+	lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->total_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	buffer = kzalloc(size, GFP_KERNEL);
-	if (!buffer)
+	lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->locked_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	current->mm->total_vm  += pgsz;
-	current->mm->locked_vm += pgsz;
+	mm->total_vm  += pgsz;
+	mm->locked_vm += pgsz;
 
+	error = 0;
  out:
-	up_write(&current->mm->mmap_sem);
-	return buffer;
+	up_write(&mm->mmap_sem);
+	return error;
 }
 
-void release_locked_buffer(void *buffer, size_t size)
+void refund_locked_memory(struct mm_struct *mm, size_t size)
 {
 	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
-
-	current->mm->total_vm  -= pgsz;
-	current->mm->locked_vm -= pgsz;
-
-	up_write(&current->mm->mmap_sem);
-}
+	down_write(&mm->mmap_sem);
 
-void free_locked_buffer(void *buffer, size_t size)
-{
-	release_locked_buffer(buffer, size);
+	mm->total_vm  -= pgsz;
+	mm->locked_vm -= pgsz;
 
-	kfree(buffer);
+	up_write(&mm->mmap_sem);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fe753ecf2aa..474c7e9dd51 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -149,10 +149,6 @@ static unsigned long __meminitdata dma_reserve;
   static int __meminitdata nr_nodemap_entries;
   static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
   static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-  static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
-  static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
   static unsigned long __initdata required_kernelcore;
   static unsigned long __initdata required_movablecore;
   static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
@@ -3103,64 +3099,6 @@ void __init sparse_memory_present_with_active_regions(int nid)
 }
 
 /**
- * push_node_boundaries - Push node boundaries to at least the requested boundary
- * @nid: The nid of the node to push the boundary for
- * @start_pfn: The start pfn of the node
- * @end_pfn: The end pfn of the node
- *
- * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
- * time. Specifically, on x86_64, SRAT will report ranges that can potentially
- * be hotplugged even though no physical memory exists. This function allows
- * an arch to push out the node boundaries so mem_map is allocated that can
- * be used later.
- */
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering push_node_boundaries(%u, %lu, %lu)\n",
-			nid, start_pfn, end_pfn);
-
-	/* Initialise the boundary for this node if necessary */
-	if (node_boundary_end_pfn[nid] == 0)
-		node_boundary_start_pfn[nid] = -1UL;
-
-	/* Update the boundaries */
-	if (node_boundary_start_pfn[nid] > start_pfn)
-		node_boundary_start_pfn[nid] = start_pfn;
-	if (node_boundary_end_pfn[nid] < end_pfn)
-		node_boundary_end_pfn[nid] = end_pfn;
-}
-
-/* If necessary, push the node boundary out for reserve hotadd */
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering account_node_boundary(%u, %lu, %lu)\n",
-			nid, *start_pfn, *end_pfn);
-
-	/* Return if boundary information has not been provided */
-	if (node_boundary_end_pfn[nid] == 0)
-		return;
-
-	/* Check the boundaries and update if necessary */
-	if (node_boundary_start_pfn[nid] < *start_pfn)
-		*start_pfn = node_boundary_start_pfn[nid];
-	if (node_boundary_end_pfn[nid] > *end_pfn)
-		*end_pfn = node_boundary_end_pfn[nid];
-}
-#else
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn) {}
-
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn) {}
-#endif
-
-
-/**
  * get_pfn_range_for_nid - Return the start and end page frames for a node
  * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
  * @start_pfn: Passed by reference. On return, it will have the node start_pfn.
@@ -3185,9 +3123,6 @@ void __meminit get_pfn_range_for_nid(unsigned int nid,
 
 	if (*start_pfn == -1UL)
 		*start_pfn = 0;
-
-	/* Push the node boundaries out if requested */
-	account_node_boundary(nid, start_pfn, end_pfn);
 }
 
 /*
@@ -3793,10 +3728,6 @@ void __init remove_all_active_ranges(void)
 {
 	memset(early_node_map, 0, sizeof(early_node_map));
 	nr_nodemap_entries = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-	memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
-	memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
 }
 
 /* Compare two active node_active_regions */
diff --git a/mm/percpu.c b/mm/percpu.c
index 1aa5d8fbca1..c0b2c1a76e8 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -23,7 +23,7 @@
  * Allocation is done in offset-size areas of single unit space.  Ie,
  * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
  * c1:u1, c1:u2 and c1:u3.  Percpu access can be done by configuring
- * percpu base registers UNIT_SIZE apart.
+ * percpu base registers pcpu_unit_size apart.
  *
  * There are usually many small percpu allocations many of them as
  * small as 4 bytes.  The allocator organizes chunks into lists
@@ -38,8 +38,8 @@
  * region and negative allocated.  Allocation inside a chunk is done
  * by scanning this map sequentially and serving the first matching
  * entry.  This is mostly copied from the percpu_modalloc() allocator.
- * Chunks are also linked into a rb tree to ease address to chunk
- * mapping during free.
+ * Chunks can be determined from the address using the index field
+ * in the page struct. The index field contains a pointer to the chunk.
  *
  * To use this allocator, arch code should do the followings.
  *
@@ -61,7 +61,6 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/pfn.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
@@ -88,7 +87,6 @@
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
-	struct rb_node		rb_node;	/* key is chunk->vm->addr */
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	struct vm_struct	*vm;		/* mapped vmalloc region */
@@ -110,9 +108,21 @@ static size_t pcpu_chunk_struct_size __read_mostly;
 void *pcpu_base_addr __read_mostly;
 EXPORT_SYMBOL_GPL(pcpu_base_addr);
 
-/* optional reserved chunk, only accessible for reserved allocations */
+/*
+ * The first chunk which always exists.  Note that unlike other
+ * chunks, this one can be allocated and mapped in several different
+ * ways and thus often doesn't live in the vmalloc area.
+ */
+static struct pcpu_chunk *pcpu_first_chunk;
+
+/*
+ * Optional reserved chunk.  This chunk reserves part of the first
+ * chunk and serves it for reserved allocations.  The amount of
+ * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
+ * area doesn't exist, the following variables contain NULL and 0
+ * respectively.
+ */
 static struct pcpu_chunk *pcpu_reserved_chunk;
-/* offset limit of the reserved chunk */
 static int pcpu_reserved_chunk_limit;
 
 /*
@@ -121,7 +131,7 @@ static int pcpu_reserved_chunk_limit;
  * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
  * protects allocation/reclaim paths, chunks and chunk->page arrays.
  * The latter is a spinlock and protects the index data structures -
- * chunk slots, rbtree, chunks and area maps in chunks.
+ * chunk slots, chunks and area maps in chunks.
  *
  * During allocation, pcpu_alloc_mutex is kept locked all the time and
  * pcpu_lock is grabbed and released as necessary.  All actual memory
@@ -140,7 +150,6 @@ static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
 static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
-static struct rb_root pcpu_addr_root = RB_ROOT;	/* chunks by address */
 
 /* reclaim work to release fully free chunks, scheduled from free path */
 static void pcpu_reclaim(struct work_struct *work);
@@ -191,6 +200,18 @@ static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
 	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
 }
 
+/* set the pointer to a chunk in a page struct */
+static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
+{
+	page->index = (unsigned long)pcpu;
+}
+
+/* obtain pointer to a chunk from a page struct */
+static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
+{
+	return (struct pcpu_chunk *)page->index;
+}
+
 /**
  * pcpu_mem_alloc - allocate memory
  * @size: bytes to allocate
@@ -257,93 +278,26 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
 	}
 }
 
-static struct rb_node **pcpu_chunk_rb_search(void *addr,
-					     struct rb_node **parentp)
-{
-	struct rb_node **p = &pcpu_addr_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct pcpu_chunk *chunk;
-
-	while (*p) {
-		parent = *p;
-		chunk = rb_entry(parent, struct pcpu_chunk, rb_node);
-
-		if (addr < chunk->vm->addr)
-			p = &(*p)->rb_left;
-		else if (addr > chunk->vm->addr)
-			p = &(*p)->rb_right;
-		else
-			break;
-	}
-
-	if (parentp)
-		*parentp = parent;
-	return p;
-}
-
 /**
- * pcpu_chunk_addr_search - search for chunk containing specified address
- * @addr: address to search for
- *
- * Look for chunk which might contain @addr.  More specifically, it
- * searchs for the chunk with the highest start address which isn't
- * beyond @addr.
- *
- * CONTEXT:
- * pcpu_lock.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
  *
  * RETURNS:
  * The address of the found chunk.
  */
 static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 {
-	struct rb_node *n, *parent;
-	struct pcpu_chunk *chunk;
+	void *first_start = pcpu_first_chunk->vm->addr;
 
-	/* is it in the reserved chunk? */
-	if (pcpu_reserved_chunk) {
-		void *start = pcpu_reserved_chunk->vm->addr;
-
-		if (addr >= start && addr < start + pcpu_reserved_chunk_limit)
+	/* is it in the first chunk? */
+	if (addr >= first_start && addr < first_start + pcpu_chunk_size) {
+		/* is it in the reserved area? */
+		if (addr < first_start + pcpu_reserved_chunk_limit)
 			return pcpu_reserved_chunk;
+		return pcpu_first_chunk;
 	}
 
-	/* nah... search the regular ones */
-	n = *pcpu_chunk_rb_search(addr, &parent);
-	if (!n) {
-		/* no exactly matching chunk, the parent is the closest */
-		n = parent;
-		BUG_ON(!n);
-	}
-	chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-
-	if (addr < chunk->vm->addr) {
-		/* the parent was the next one, look for the previous one */
-		n = rb_prev(n);
-		BUG_ON(!n);
-		chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-	}
-
-	return chunk;
-}
-
-/**
- * pcpu_chunk_addr_insert - insert chunk into address rb tree
- * @new: chunk to insert
- *
- * Insert @new into address rb tree.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
-{
-	struct rb_node **p, *parent;
-
-	p = pcpu_chunk_rb_search(new->vm->addr, &parent);
-	BUG_ON(*p);
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &pcpu_addr_root);
+	return pcpu_get_page_chunk(vmalloc_to_page(addr));
 }
 
 /**
@@ -755,6 +709,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 						  alloc_mask, 0);
 			if (!*pagep)
 				goto err;
+			pcpu_set_page_chunk(*pagep, chunk);
 		}
 	}
 
@@ -879,7 +834,6 @@ restart:
 
 	spin_lock_irq(&pcpu_lock);
 	pcpu_chunk_relocate(chunk, -1);
-	pcpu_chunk_addr_insert(chunk);
 	goto restart;
 
 area_found:
@@ -968,7 +922,6 @@ static void pcpu_reclaim(struct work_struct *work)
 		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
 			continue;
 
-		rb_erase(&chunk->rb_node, &pcpu_addr_root);
 		list_move(&chunk->list, &todo);
 	}
 
@@ -1147,7 +1100,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 
 	if (reserved_size) {
 		schunk->free_size = reserved_size;
-		pcpu_reserved_chunk = schunk;	/* not for dynamic alloc */
+		pcpu_reserved_chunk = schunk;
+		pcpu_reserved_chunk_limit = static_size + reserved_size;
 	} else {
 		schunk->free_size = dyn_size;
 		dyn_size = 0;			/* dynamic area covered */
@@ -1158,8 +1112,6 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	if (schunk->free_size)
 		schunk->map[schunk->map_used++] = schunk->free_size;
 
-	pcpu_reserved_chunk_limit = static_size + schunk->free_size;
-
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
 		dchunk = alloc_bootmem(sizeof(struct pcpu_chunk));
@@ -1226,13 +1178,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	}
 
 	/* link the first chunk in */
-	if (!dchunk) {
-		pcpu_chunk_relocate(schunk, -1);
-		pcpu_chunk_addr_insert(schunk);
-	} else {
-		pcpu_chunk_relocate(dchunk, -1);
-		pcpu_chunk_addr_insert(dchunk);
-	}
+	pcpu_first_chunk = dchunk ?: schunk;
+	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* we're done */
 	pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
diff --git a/mm/slab.c b/mm/slab.c
index 9a90b00d2f9..f85831da908 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -102,7 +102,7 @@
 #include	<linux/cpu.h>
 #include	<linux/sysctl.h>
 #include	<linux/module.h>
-#include	<trace/kmemtrace.h>
+#include	<linux/kmemtrace.h>
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
 #include	<linux/uaccess.h>
diff --git a/mm/slob.c b/mm/slob.c
index f92e66d558b..9b1737b0787 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -66,7 +66,7 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <asm/atomic.h>
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index 65ffda5934b..5e805a6fe36 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -17,7 +17,7 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
diff --git a/mm/util.c b/mm/util.c
index 55bef160b9f..abc65aa7cdf 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,9 +4,11 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
-#include <linux/tracepoint.h>
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
 /**
  * kstrdup - allocate space for and copy an existing string
  * @s: the string to duplicate
@@ -255,13 +257,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
 /* Tracepoints definitions. */
-DEFINE_TRACE(kmalloc);
-DEFINE_TRACE(kmem_cache_alloc);
-DEFINE_TRACE(kmalloc_node);
-DEFINE_TRACE(kmem_cache_alloc_node);
-DEFINE_TRACE(kfree);
-DEFINE_TRACE(kmem_cache_free);
-
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
 EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9fd0dc3cca9..b75b6cea49d 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -23,7 +23,7 @@
 #include <linux/bitops.h>
 #include <net/genetlink.h>
 
-#include <trace/skb.h>
+#include <trace/events/skb.h>
 
 #include <asm/unaligned.h>
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index c8fb45665e4..499a67eaf3a 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -19,11 +19,11 @@
 #include <linux/workqueue.h>
 #include <linux/netlink.h>
 #include <linux/net_dropmon.h>
-#include <trace/skb.h>
 
 #include <asm/unaligned.h>
 #include <asm/bitops.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/skb.h>
 
-DEFINE_TRACE(kfree_skb);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e505b5392e1..c2e4fb8f354 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -65,7 +65,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
-#include <trace/skb.h>
+#include <trace/events/skb.h>
 
 #include "kmap_skb.h"
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index cc29b44b150..e5becb92b3e 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -167,6 +167,9 @@ static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
 	struct tcf_exts e;
 	int err;
 
+	if (!tca[TCA_OPTIONS])
+		return -EINVAL;
+
 	if (head == NULL) {
 		if (!handle)
 			return -EINVAL;
diff --git a/samples/Kconfig b/samples/Kconfig
index 4b02f5a0e65..b75d28cba3f 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -19,6 +19,12 @@ config SAMPLE_TRACEPOINTS
 	help
 	  This build tracepoints example modules.
 
+config SAMPLE_TRACE_EVENTS
+	tristate "Build trace_events examples -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This build trace event example modules.
+
 config SAMPLE_KOBJECT
 	tristate "Build kobject examples"
 	help
diff --git a/samples/Makefile b/samples/Makefile
index 10eaca89fe1..13e4b470b53 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -1,3 +1,3 @@
 # Makefile for Linux samples code
 
-obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/ tracepoints/
+obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/ tracepoints/ trace_events/
diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile
new file mode 100644
index 00000000000..0d428dc6728
--- /dev/null
+++ b/samples/trace_events/Makefile
@@ -0,0 +1,6 @@
+# builds the trace events example kernel modules;
+# then to use one (as root):  insmod <module_name.ko>
+
+CFLAGS_trace-events-sample.o := -I$(src)
+
+obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
new file mode 100644
index 00000000000..aabc4e97091
--- /dev/null
+++ b/samples/trace_events/trace-events-sample.c
@@ -0,0 +1,52 @@
+#include <linux/module.h>
+#include <linux/kthread.h>
+
+/*
+ * Any file that uses trace points, must include the header.
+ * But only one file, must include the header by defining
+ * CREATE_TRACE_POINTS first.  This will make the C code that
+ * creates the handles for the trace points.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace-events-sample.h"
+
+
+static void simple_thread_func(int cnt)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(HZ);
+	trace_foo_bar("hello", cnt);
+}
+
+static int simple_thread(void *arg)
+{
+	int cnt = 0;
+
+	while (!kthread_should_stop())
+		simple_thread_func(cnt++);
+
+	return 0;
+}
+
+static struct task_struct *simple_tsk;
+
+static int __init trace_event_init(void)
+{
+	simple_tsk = kthread_run(simple_thread, NULL, "event-sample");
+	if (IS_ERR(simple_tsk))
+		return -1;
+
+	return 0;
+}
+
+static void __exit trace_event_exit(void)
+{
+	kthread_stop(simple_tsk);
+}
+
+module_init(trace_event_init);
+module_exit(trace_event_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("trace-events-sample");
+MODULE_LICENSE("GPL");
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
new file mode 100644
index 00000000000..128a897687c
--- /dev/null
+++ b/samples/trace_events/trace-events-sample.h
@@ -0,0 +1,129 @@
+/*
+ * Notice that this file is not protected like a normal header.
+ * We also must allow for rereading of this file. The
+ *
+ *  || defined(TRACE_HEADER_MULTI_READ)
+ *
+ * serves this purpose.
+ */
+#if !defined(_TRACE_EVENT_SAMPLE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENT_SAMPLE_H
+
+/*
+ * All trace headers should include tracepoint.h, until we finally
+ * make it into a standard header.
+ */
+#include <linux/tracepoint.h>
+
+/*
+ * If TRACE_SYSTEM is defined, that will be the directory created
+ * in the ftrace directory under /debugfs/tracing/events/<system>
+ *
+ * The define_trace.h belowe will also look for a file name of
+ * TRACE_SYSTEM.h where TRACE_SYSTEM is what is defined here.
+ *
+ * If you want a different system than file name, you can override
+ * the header name by defining TRACE_INCLUDE_FILE
+ *
+ * If this file was called, goofy.h, then we would define:
+ *
+ * #define TRACE_INCLUDE_FILE goofy
+ *
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sample
+
+/*
+ * The TRACE_EVENT macro is broken up into 5 parts.
+ *
+ * name: name of the trace point. This is also how to enable the tracepoint.
+ *   A function called trace_foo_bar() will be created.
+ *
+ * proto: the prototype of the function trace_foo_bar()
+ *   Here it is trace_foo_bar(char *foo, int bar).
+ *
+ * args:  must match the arguments in the prototype.
+ *    Here it is simply "foo, bar".
+ *
+ * struct:  This defines the way the data will be stored in the ring buffer.
+ *    There are currently two types of elements. __field and __array.
+ *    a __field is broken up into (type, name). Where type can be any
+ *    type but an array.
+ *    For an array. there are three fields. (type, name, size). The
+ *    type of elements in the array, the name of the field and the size
+ *    of the array.
+ *
+ *    __array( char, foo, 10) is the same as saying   char foo[10].
+ *
+ * fast_assign: This is a C like function that is used to store the items
+ *    into the ring buffer.
+ *
+ * printk: This is a way to print out the data in pretty print. This is
+ *    useful if the system crashes and you are logging via a serial line,
+ *    the data can be printed to the console using this "printk" method.
+ *
+ * Note, that for both the assign and the printk, __entry is the handler
+ * to the data structure in the ring buffer, and is defined by the
+ * TP_STRUCT__entry.
+ */
+TRACE_EVENT(foo_bar,
+
+	TP_PROTO(char *foo, int bar),
+
+	TP_ARGS(foo, bar),
+
+	TP_STRUCT__entry(
+		__array(	char,	foo,    10		)
+		__field(	int,	bar			)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->foo, foo, 10);
+		__entry->bar	= bar;
+	),
+
+	TP_printk("foo %s %d", __entry->foo, __entry->bar)
+);
+#endif
+
+/***** NOTICE! The #if protection ends here. *****/
+
+
+/*
+ * There are several ways I could have done this. If I left out the
+ * TRACE_INCLUDE_PATH, then it would default to the kernel source
+ * include/trace/events directory.
+ *
+ * I could specify a path from the define_trace.h file back to this
+ * file.
+ *
+ * #define TRACE_INCLUDE_PATH ../../samples/trace_events
+ *
+ * But I chose to simply make it use the current directory and then in
+ * the Makefile I added:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)/samples/trace_events/
+ *
+ * This will make sure the current path is part of the include
+ * structure for our file so that we can find it.
+ *
+ * I could have made only the top level directory the include:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)
+ *
+ * And then let the path to this directory be the TRACE_INCLUDE_PATH:
+ *
+ * #define TRACE_INCLUDE_PATH samples/trace_events
+ *
+ * But then if something defines "samples" or "trace_events" then we
+ * could risk that being converted too, and give us an unexpected
+ * result.
+ */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+/*
+ * TRACE_INCLUDE_FILE is not needed if the filename and TRACE_SYSTEM are equal
+ */
+#define TRACE_INCLUDE_FILE trace-events-sample
+#include <trace/define_trace.h>
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index cba61ca403c..2b706617c89 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -188,20 +188,34 @@ cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@
 # ---------------------------------------------------------------------------
 
 quiet_cmd_gzip = GZIP    $@
-cmd_gzip = gzip -f -9 < $< > $@
+cmd_gzip = (cat $(filter-out FORCE,$^) | gzip -f -9 > $@) || \
+	(rm -f $@ ; false)
 
 
 # Bzip2
 # ---------------------------------------------------------------------------
 
-# Bzip2 does not include size in file... so we have to fake that
-size_append=$(CONFIG_SHELL) $(srctree)/scripts/bin_size
-
-quiet_cmd_bzip2 = BZIP2    $@
-cmd_bzip2 = (bzip2 -9 < $< && $(size_append) $<) > $@ || (rm -f $@ ; false)
+# Bzip2 and LZMA do not include size in file... so we have to fake that;
+# append the size as a 32-bit littleendian number as gzip does.
+size_append = echo -ne $(shell						\
+dec_size=0;								\
+for F in $1; do								\
+	fsize=$$(stat -c "%s" $$F);					\
+	dec_size=$$(expr $$dec_size + $$fsize);				\
+done;									\
+printf "%08x" $$dec_size |						\
+	sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g'	\
+)
+
+quiet_cmd_bzip2 = BZIP2   $@
+cmd_bzip2 = (cat $(filter-out FORCE,$^) | \
+	bzip2 -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+	(rm -f $@ ; false)
 
 # Lzma
 # ---------------------------------------------------------------------------
 
 quiet_cmd_lzma = LZMA    $@
-cmd_lzma = (lzma -9 -c $< && $(size_append) $<) >$@ || (rm -f $@ ; false)
+cmd_lzma = (cat $(filter-out FORCE,$^) | \
+	lzma -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+	(rm -f $@ ; false)
diff --git a/scripts/bin_size b/scripts/bin_size
deleted file mode 100644
index 43e1b360cee..00000000000
--- a/scripts/bin_size
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-
-if [ $# = 0 ] ; then
-   echo Usage: $0 file
-fi
-
-size_dec=`stat -c "%s" $1`
-size_hex_echo_string=`printf "%08x" $size_dec |
-     sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g'`
-/bin/echo -ne $size_hex_echo_string
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 3208a3a7e7f..acd8c4a8e3e 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1828,6 +1828,25 @@ sub reset_state {
     $state = 0;
 }
 
+sub tracepoint_munge($) {
+	my $file = shift;
+	my $tracepointname = 0;
+	my $tracepointargs = 0;
+
+	if($prototype =~ m/TRACE_EVENT\((.*?),/) {
+		$tracepointname = $1;
+	}
+	if($prototype =~ m/TP_PROTO\((.*?)\)/) {
+		$tracepointargs = $1;
+	}
+	if (($tracepointname eq 0) || ($tracepointargs eq 0)) {
+		print STDERR "Warning(${file}:$.): Unrecognized tracepoint format: \n".
+			     "$prototype\n";
+	} else {
+		$prototype = "static inline void trace_$tracepointname($tracepointargs)";
+	}
+}
+
 sub syscall_munge() {
 	my $void = 0;
 
@@ -1882,6 +1901,9 @@ sub process_state3_function($$) {
 	if ($prototype =~ /SYSCALL_DEFINE/) {
 		syscall_munge();
 	}
+	if ($prototype =~ /TRACE_EVENT/) {
+		tracepoint_munge($file);
+	}
 	dump_function($prototype, $file);
 	reset_state();
     }
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 409596eca12..0fae7da0529 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -26,7 +26,7 @@
 # which will also be the location of that section after final link.
 # e.g.
 #
-#  .section ".text.sched"
+#  .section ".sched.text", "ax"
 #  .globl my_func
 #  my_func:
 #        [...]
@@ -39,7 +39,7 @@
 #        [...]
 #
 # Both relocation offsets for the mcounts in the above example will be
-# offset from .text.sched. If we make another file called tmp.s with:
+# offset from .sched.text. If we make another file called tmp.s with:
 #
 #  .section __mcount_loc
 #  .quad  my_func + 0x5
@@ -51,7 +51,7 @@
 # But this gets hard if my_func is not globl (a static function).
 # In such a case we have:
 #
-#  .section ".text.sched"
+#  .section ".sched.text", "ax"
 #  my_func:
 #        [...]
 #        call mcount  (offset: 0x5)
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index ffbe259700b..510186f0b72 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -84,8 +84,8 @@ static void *ima_measurements_next(struct seq_file *m, void *v, loff_t *pos)
 	 * against concurrent list-extension
 	 */
 	rcu_read_lock();
-	qe = list_entry(rcu_dereference(qe->later.next),
-			struct ima_queue_entry, later);
+	qe = list_entry_rcu(qe->later.next,
+			    struct ima_queue_entry, later);
 	rcu_read_unlock();
 	(*pos)++;
 
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index e03a7e19c73..11d2cb19d7a 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -734,8 +734,8 @@ static void smk_netlbladdr_insert(struct smk_netlbladdr *new)
 		return;
 	}
 
-	m = list_entry(rcu_dereference(smk_netlbladdr_list.next),
-			 struct smk_netlbladdr, list);
+	m = list_entry_rcu(smk_netlbladdr_list.next,
+			   struct smk_netlbladdr, list);
 
 	/* the comparison '>' is a bit hacky, but works */
 	if (new->smk_mask.s_addr > m->smk_mask.s_addr) {
@@ -748,8 +748,8 @@ static void smk_netlbladdr_insert(struct smk_netlbladdr *new)
 			list_add_rcu(&new->list, &m->list);
 			return;
 		}
-		m_next = list_entry(rcu_dereference(m->list.next),
-				 struct smk_netlbladdr, list);
+		m_next = list_entry_rcu(m->list.next,
+					struct smk_netlbladdr, list);
 		if (new->smk_mask.s_addr > m_next->smk_mask.s_addr) {
 			list_add_rcu(&new->list, &m->list);
 			return;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1ecbe2391c8..4d0dd390aa5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2301,10 +2301,11 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 
 	bad_pfn = page_to_pfn(bad_page);
 
-	if (!alloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
 	}
+	cpumask_clear(cpus_hardware_enabled);
 
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
author	Ingo Molnar <mingo@elte.hu>	2009-06-11 17:55:42 +0200
committer	Ingo Molnar <mingo@elte.hu>	2009-06-11 17:55:42 +0200
commit	940010c5a314a7bd9b498593bc6ba1718ac5aec5 (patch)
tree	d141e08ced08c40c6a8e3ab2cdecde5ff14e560f
parent	8dc8e5e8bc0ce00b0f656bf972f67cd8a72759e5 (diff)
parent	991ec02cdca33b03a132a0cacfe6f0aa0be9aa8d (diff)