Merge remote branch 'origin/master' into merge

Manual merge of arch/powerpc/kernel/smp.c and add missing scheduler_ipi()
call to arch/powerpc/platforms/cell/interrupt.c

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

749 files changed, 24786 insertions, 11163 deletions

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index c17cd4bb229..1b777b96049 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -328,8 +328,6 @@ sysrq.txt
 	- info on the magic SysRq key.
 telephony/
 	- directory with info on telephony (e.g. voice over IP) support.
-uml/
-	- directory with information about User Mode Linux.
 unicode.txt
 	- info on the Unicode character/font mapping used in Linux.
 unshare.txt
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 7564e88bfa4..e7be75b96e4 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -183,21 +183,21 @@ Description:	Discover and change clock speed of CPUs
 		to learn how to control the knobs.
 
 
-What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
-Date:      August 2008
+What:		/sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
+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://support.amd.com/us/Embedded_TechDocs/31116-Public-GH-BKDG_3-28_5-28-09.pdf	
-		for formatting information and other details on the
-		cache index disable.
-Users:    joachim.deguara@amd.com
+Contact:	discuss@x86-64.org
+Description:	Disable L3 cache indices
+
+		These files exist in every CPU's cache/index3 directory. Each
+		cache_disable_{0,1} file corresponds to one disable slot which
+		can be used to disable a cache index. Reading from these files
+		on a processor with this functionality will return the currently
+		disabled index for that node. There is one L3 structure per
+		node, or per internal node on MCM machines. Writing a valid
+		index to one of these files will cause the specificed cache
+		index to be disabled.
+
+		All AMD processors with L3 caches provide this functionality.
+		For details, see BKDGs at
+		http://developer.amd.com/documentation/guides/Pages/default.aspx
diff --git a/Documentation/ABI/testing/sysfs-firmware-dmi b/Documentation/ABI/testing/sysfs-firmware-dmi
index ba9da9503c2..c78f9ab01e5 100644
--- a/Documentation/ABI/testing/sysfs-firmware-dmi
+++ b/Documentation/ABI/testing/sysfs-firmware-dmi
@@ -14,14 +14,15 @@ Description:
 
 		DMI is structured as a large table of entries, where
 		each entry has a common header indicating the type and
-		length of the entry, as well as 'handle' that is
-		supposed to be unique amongst all entries.
+		length of the entry, as well as a firmware-provided
+		'handle' that is supposed to be unique amongst all
+		entries.
 
 		Some entries are required by the specification, but many
 		others are optional.  In general though, users should
 		never expect to find a specific entry type on their
 		system unless they know for certain what their firmware
-		is doing.  Machine to machine will vary.
+		is doing.  Machine to machine experiences will vary.
 
 		Multiple entries of the same type are allowed.  In order
 		to handle these duplicate entry types, each entry is
@@ -67,25 +68,24 @@ Description:
 			  and the two terminating nul characters.
 		type	: The type of the entry.  This value is the same
 			  as found in the directory name.  It indicates
-			  how the rest of the entry should be
-			  interpreted.
+			  how the rest of the entry should be interpreted.
 		instance: The instance ordinal of the entry for the
 			  given type.  This value is the same as found
 			  in the parent directory name.
-		position: The position of the entry within the entirety
-			  of the entirety.
+		position: The ordinal position (zero-based) of the entry
+			  within the entirety of the DMI entry table.
 
 		=== Entry Specialization ===
 
 		Some entry types may have other information available in
-		sysfs.
+		sysfs.  Not all types are specialized.
 
 		--- Type 15 - System Event Log ---
 
 		This entry allows the firmware to export a log of
 		events the system has taken.  This information is
 		typically backed by nvram, but the implementation
-		details are abstracted by this table.  This entries data
+		details are abstracted by this table.  This entry's data
 		is exported in the directory:
 
 		/sys/firmware/dmi/entries/15-0/system_event_log
diff --git a/Documentation/ABI/testing/sysfs-firmware-gsmi b/Documentation/ABI/testing/sysfs-firmware-gsmi
new file mode 100644
index 00000000000..0faa0aaf4b6
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-gsmi
@@ -0,0 +1,58 @@
+What:		/sys/firmware/gsmi
+Date:		March 2011
+Contact:	Mike Waychison <mikew@google.com>
+Description:
+		Some servers used internally at Google have firmware
+		that provides callback functionality via explicit SMI
+		triggers.  Some of the callbacks are similar to those
+		provided by the EFI runtime services page, but due to
+		historical reasons this different entry-point has been
+		used.
+
+		The gsmi driver implements the kernel's abstraction for
+		these firmware callbacks.  Currently, this functionality
+		is limited to handling the system event log and getting
+		access to EFI-style variables stored in nvram.
+
+		Layout:
+
+		/sys/firmware/gsmi/vars:
+
+			This directory has the same layout (and
+			underlying implementation as /sys/firmware/efi/vars.
+			See Documentation/ABI/*/sysfs-firmware-efi-vars
+			for more information on how to interact with
+			this structure.
+
+		/sys/firmware/gsmi/append_to_eventlog - write-only:
+
+			This file takes a binary blob and passes it onto
+			the firmware to be timestamped and appended to
+			the system eventlog.  The binary format is
+			interpreted by the firmware and may change from
+			platform to platform.  The only kernel-enforced
+			requirement is that the blob be prefixed with a
+			32bit host-endian type used as part of the
+			firmware call.
+
+		/sys/firmware/gsmi/clear_config - write-only:
+
+			Writing any value to this file will cause the
+			entire firmware configuration to be reset to
+			"factory defaults".  Callers should assume that
+			a reboot is required for the configuration to be
+			cleared.
+
+		/sys/firmware/gsmi/clear_eventlog - write-only:
+
+			This file is used to clear out a portion/the
+			whole of the system event log.  Values written
+			should be values between 1 and 100 inclusive (in
+			ASCII) representing the fraction of the log to
+			clear.  Not all platforms support fractional
+			clearing though, and this writes to this file
+			will error out if the firmware doesn't like your
+			submitted fraction.
+
+			Callers should assume that a reboot is needed
+			for this operation to complete.
diff --git a/Documentation/ABI/testing/sysfs-firmware-log b/Documentation/ABI/testing/sysfs-firmware-log
new file mode 100644
index 00000000000..9b58e7c5365
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-log
@@ -0,0 +1,7 @@
+What:		/sys/firmware/log
+Date:		February 2011
+Contact:	Mike Waychison <mikew@google.com>
+Description:
+		The /sys/firmware/log is a binary file that represents a
+		read-only copy of the firmware's log if one is
+		available.
diff --git a/Documentation/ABI/testing/sysfs-kernel-fscaps b/Documentation/ABI/testing/sysfs-kernel-fscaps
new file mode 100644
index 00000000000..50a3033b5e1
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-fscaps
@@ -0,0 +1,8 @@
+What:		/sys/kernel/fscaps
+Date:		February 2011
+KernelVersion:	2.6.38
+Contact:	Ludwig Nussel <ludwig.nussel@suse.de>
+Description
+		Shows whether file system capabilities are honored
+		when executing a binary
+
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 194ca446ac2..b464d12761b 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -158,3 +158,17 @@ Description:
 		successful, will make the kernel abort a subsequent transition
 		to a sleep state if any wakeup events are reported after the
 		write has returned.
+
+What:		/sys/power/reserved_size
+Date:		May 2011
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/reserved_size file allows user space to control
+		the amount of memory reserved for allocations made by device
+		drivers during the "device freeze" stage of hibernation.  It can
+		be written a string representing a non-negative integer that
+		will be used as the amount of memory to reserve for allocations
+		made by device drivers' "freeze" callbacks, in bytes.
+
+		Reading from this file will display the current value, which is
+		set to 1 MB by default.
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 36f63d4a0a0..b638e50cf8f 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -96,10 +96,10 @@ X!Iinclude/linux/kobject.h
 
   <chapter id="devdrivers">
      <title>Device drivers infrastructure</title>
+     <sect1><title>The Basic Device Driver-Model Structures </title>
+!Iinclude/linux/device.h
+     </sect1>
      <sect1><title>Device Drivers Base</title>
-<!--
-X!Iinclude/linux/device.h
--->
 !Edrivers/base/driver.c
 !Edrivers/base/core.c
 !Edrivers/base/class.c
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index fb10fd08c05..b3422341d65 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -191,8 +191,8 @@
 	<para>
 	Whenever an interrupt triggers, the lowlevel arch code calls into
 	the generic interrupt code by calling desc->handle_irq().
-	This highlevel IRQ handling function only uses desc->chip primitives
-	referenced by the assigned chip descriptor structure.
+	This highlevel IRQ handling function only uses desc->irq_data.chip
+	primitives referenced by the assigned chip descriptor structure.
 	</para>
     </sect1>
     <sect1 id="Highlevel_Driver_API">
@@ -206,11 +206,11 @@
 	  <listitem><para>enable_irq()</para></listitem>
 	  <listitem><para>disable_irq_nosync() (SMP only)</para></listitem>
 	  <listitem><para>synchronize_irq() (SMP only)</para></listitem>
-	  <listitem><para>set_irq_type()</para></listitem>
-	  <listitem><para>set_irq_wake()</para></listitem>
-	  <listitem><para>set_irq_data()</para></listitem>
-	  <listitem><para>set_irq_chip()</para></listitem>
-	  <listitem><para>set_irq_chip_data()</para></listitem>
+	  <listitem><para>irq_set_irq_type()</para></listitem>
+	  <listitem><para>irq_set_irq_wake()</para></listitem>
+	  <listitem><para>irq_set_handler_data()</para></listitem>
+	  <listitem><para>irq_set_chip()</para></listitem>
+	  <listitem><para>irq_set_chip_data()</para></listitem>
           </itemizedlist>
 	  See the autogenerated function documentation for details.
 	</para>
@@ -225,6 +225,8 @@
 	  <listitem><para>handle_fasteoi_irq</para></listitem>
 	  <listitem><para>handle_simple_irq</para></listitem>
 	  <listitem><para>handle_percpu_irq</para></listitem>
+	  <listitem><para>handle_edge_eoi_irq</para></listitem>
+	  <listitem><para>handle_bad_irq</para></listitem>
 	  </itemizedlist>
 	  The interrupt flow handlers (either predefined or architecture
 	  specific) are assigned to specific interrupts by the architecture
@@ -241,13 +243,13 @@
 		<programlisting>
 default_enable(struct irq_data *data)
 {
-	desc->chip->irq_unmask(data);
+	desc->irq_data.chip->irq_unmask(data);
 }
 
 default_disable(struct irq_data *data)
 {
 	if (!delay_disable(data))
-		desc->chip->irq_mask(data);
+		desc->irq_data.chip->irq_mask(data);
 }
 
 default_ack(struct irq_data *data)
@@ -284,9 +286,9 @@ noop(struct irq_data *data))
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->irq_mask();
-handle_IRQ_event(desc->action);
-desc->chip->irq_unmask();
+desc->irq_data.chip->irq_mask_ack();
+handle_irq_event(desc->action);
+desc->irq_data.chip->irq_unmask();
 		</programlisting>
 		</para>
 	    </sect3>
@@ -300,8 +302,8 @@ desc->chip->irq_unmask();
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
-desc->chip->irq_eoi();
+handle_irq_event(desc->action);
+desc->irq_data.chip->irq_eoi();
 		</programlisting>
 		</para>
 	    </sect3>
@@ -315,17 +317,17 @@ desc->chip->irq_eoi();
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
 if (desc->status &amp; running) {
-	desc->chip->irq_mask();
+	desc->irq_data.chip->irq_mask_ack();
 	desc->status |= pending | masked;
 	return;
 }
-desc->chip->irq_ack();
+desc->irq_data.chip->irq_ack();
 desc->status |= running;
 do {
 	if (desc->status &amp; masked)
-		desc->chip->irq_unmask();
+		desc->irq_data.chip->irq_unmask();
 	desc->status &amp;= ~pending;
-	handle_IRQ_event(desc->action);
+	handle_irq_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
 		</programlisting>
@@ -344,7 +346,7 @@ desc->status &amp;= ~running;
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
+handle_irq_event(desc->action);
 		</programlisting>
 		</para>
    	    </sect3>
@@ -362,12 +364,29 @@ handle_IRQ_event(desc->action);
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
-if (desc->chip->irq_eoi)
-        desc->chip->irq_eoi();
+if (desc->irq_data.chip->irq_ack)
+	desc->irq_data.chip->irq_ack();
+handle_irq_event(desc->action);
+if (desc->irq_data.chip->irq_eoi)
+        desc->irq_data.chip->irq_eoi();
 		</programlisting>
 		</para>
    	    </sect3>
+	    <sect3 id="EOI_Edge_IRQ_flow_handler">
+	 	<title>EOI Edge IRQ flow handler</title>
+		<para>
+		handle_edge_eoi_irq provides an abnomination of the edge
+		handler which is solely used to tame a badly wreckaged
+		irq controller on powerpc/cell.
+		</para>
+   	    </sect3>
+	    <sect3 id="BAD_IRQ_flow_handler">
+	 	<title>Bad IRQ flow handler</title>
+		<para>
+		handle_bad_irq is used for spurious interrupts which
+		have no real handler assigned..
+		</para>
+   	    </sect3>
 	</sect2>
 	<sect2 id="Quirks_and_optimizations">
 	<title>Quirks and optimizations</title>
@@ -410,6 +429,7 @@ if (desc->chip->irq_eoi)
 	  <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
 	  <listitem><para>irq_mask()</para></listitem>
 	  <listitem><para>irq_unmask()</para></listitem>
+	  <listitem><para>irq_eoi() - Optional, required for eoi flow handlers</para></listitem>
 	  <listitem><para>irq_retrigger() - Optional</para></listitem>
 	  <listitem><para>irq_set_type() - Optional</para></listitem>
 	  <listitem><para>irq_set_wake() - Optional</para></listitem>
@@ -424,32 +444,24 @@ if (desc->chip->irq_eoi)
   <chapter id="doirq">
      <title>__do_IRQ entry point</title>
      <para>
- 	The original implementation __do_IRQ() is an alternative entry
-	point for all types of interrupts.
+	The original implementation __do_IRQ() was an alternative entry
+	point for all types of interrupts. It not longer exists.
      </para>
      <para>
 	This handler turned out to be not suitable for all
 	interrupt hardware and was therefore reimplemented with split
-	functionality for egde/level/simple/percpu interrupts. This is not
+	functionality for edge/level/simple/percpu interrupts. This is not
 	only a functional optimization. It also shortens code paths for
 	interrupts.
       </para>
-      <para>
-	To make use of the split implementation, replace the call to
-	__do_IRQ by a call to desc->handle_irq() and associate
-        the appropriate handler function to desc->handle_irq().
-	In most cases the generic handler implementations should
-	be sufficient.
-     </para>
   </chapter>
 
   <chapter id="locking">
      <title>Locking on SMP</title>
      <para>
 	The locking of chip registers is up to the architecture that
-	defines the chip primitives. There is a chip->lock field that can be used
-	for serialization, but the generic layer does not touch it. The per-irq
-	structure is protected via desc->lock, by the generic layer.
+	defines the chip primitives. The per-irq structure is
+	protected via desc->lock, by the generic layer.
      </para>
   </chapter>
   <chapter id="structs">
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 71b6f500ddb..1d7a885761f 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -21,7 +21,7 @@ rcu.txt
 RTFP.txt
 	- List of RCU papers (bibliography) going back to 1980.
 stallwarn.txt
-	- RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
+	- RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress)
 torture.txt
 	- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 862c08ef1fd..4e959208f73 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -1,22 +1,25 @@
 Using RCU's CPU Stall Detector
 
-The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
-RCU's CPU stall detector, which detects conditions that unduly delay
-RCU grace periods.  The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a set of C preprocessor macros:
+The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
+detector, which detects conditions that unduly delay RCU grace periods.
+This module parameter enables CPU stall detection by default, but
+may be overridden via boot-time parameter or at runtime via sysfs.
+The stall detector's idea of what constitutes "unduly delayed" is
+controlled by a set of kernel configuration variables and cpp macros:
 
-RCU_SECONDS_TILL_STALL_CHECK
+CONFIG_RCU_CPU_STALL_TIMEOUT
 
-	This macro defines the period of time that RCU will wait from
-	the beginning of a grace period until it issues an RCU CPU
-	stall warning.	This time period is normally ten seconds.
+	This kernel configuration parameter defines the period of time
+	that RCU will wait from the beginning of a grace period until it
+	issues an RCU CPU stall warning.  This time period is normally
+	ten seconds.
 
 RCU_SECONDS_TILL_STALL_RECHECK
 
 	This macro defines the period of time that RCU will wait after
 	issuing a stall warning until it issues another stall warning
-	for the same stall.  This time period is normally set to thirty
-	seconds.
+	for the same stall.  This time period is normally set to three
+	times the check interval plus thirty seconds.
 
 RCU_STALL_RAT_DELAY
 
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 6a8c73f55b8..c078ad48f7a 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -10,34 +10,46 @@ for rcutree and next for rcutiny.
 
 CONFIG_TREE_RCU and CONFIG_TREE_PREEMPT_RCU debugfs Files and Formats
 
-These implementations of RCU provides five debugfs files under the
-top-level directory RCU: rcu/rcudata (which displays fields in struct
-rcu_data), rcu/rcudata.csv (which is a .csv spreadsheet version of
-rcu/rcudata), rcu/rcugp (which displays grace-period counters),
-rcu/rcuhier (which displays the struct rcu_node hierarchy), and
-rcu/rcu_pending (which displays counts of the reasons that the
-rcu_pending() function decided that there was core RCU work to do).
+These implementations of RCU provides several debugfs files under the
+top-level directory "rcu":
+
+rcu/rcudata:
+	Displays fields in struct rcu_data.
+rcu/rcudata.csv:
+	Comma-separated values spreadsheet version of rcudata.
+rcu/rcugp:
+	Displays grace-period counters.
+rcu/rcuhier:
+	Displays the struct rcu_node hierarchy.
+rcu/rcu_pending:
+	Displays counts of the reasons rcu_pending() decided that RCU had
+	work to do.
+rcu/rcutorture:
+	Displays rcutorture test progress.
+rcu/rcuboost:
+	Displays RCU boosting statistics.  Only present if
+	CONFIG_RCU_BOOST=y.
 
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu_sched:
-  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
+  0 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0
+  1 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0
+  2 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0
+  3 c=20942 g=20943 pq=1 pqc=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0
+  4 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0
+  5 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0
+  6 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0
+  7 c=20897 g=20897 pq=1 pqc=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0
 rcu_bh:
-  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
+  0 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0
+  1 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0
+  2 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0
+  3 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0
+  4 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0
+  5 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0
+  6 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0
+  7 c=1474 g=1474 pq=1 pqc=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0
 
 The first section lists the rcu_data structures for rcu_sched, the second
 for rcu_bh.  Note that CONFIG_TREE_PREEMPT_RCU kernels will have an
@@ -52,17 +64,18 @@ o	The number at the beginning of each line is the CPU number.
 	substantially larger than the number of actual CPUs.
 
 o	"c" is the count of grace periods that this CPU believes have
-	completed.  CPUs in dynticks idle mode may lag quite a ways
-	behind, for example, CPU 4 under "rcu_sched" above, which has
-	slept through the past 25 RCU grace periods.  It is not unusual
-	to see CPUs lagging by thousands of grace periods.
+	completed.  Offlined CPUs and CPUs in dynticks idle mode may
+	lag quite a ways behind, for example, CPU 6 under "rcu_sched"
+	above, which has been offline through not quite 40,000 RCU grace
+	periods.  It is not unusual to see CPUs lagging by thousands of
+	grace periods.
 
 o	"g" is the count of grace periods that this CPU believes have
-	started.  Again, CPUs in dynticks idle mode may lag behind.
-	If the "c" and "g" values are equal, this CPU has already
-	reported a quiescent state for the last RCU grace period that
-	it is aware of, otherwise, the CPU believes that it owes RCU a
-	quiescent state.
+	started.  Again, offlined CPUs and CPUs in dynticks idle mode
+	may lag behind.  If the "c" and "g" values are equal, this CPU
+	has already reported a quiescent state for the last RCU grace
+	period that it is aware of, otherwise, the CPU believes that it
+	owes RCU a quiescent state.
 
 o	"pq" indicates that this CPU has passed through a quiescent state
 	for the current grace period.  It is possible for "pq" to be
@@ -81,7 +94,8 @@ o	"pqc" indicates which grace period the last-observed quiescent
 	the next grace period!
 
 o	"qp" indicates that RCU still expects a quiescent state from
-	this CPU.
+	this CPU.  Offlined CPUs and CPUs in dyntick idle mode might
+	well have qp=1, which is OK: RCU is still ignoring them.
 
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
@@ -108,7 +122,7 @@ o	"df" is the number of times that some other CPU has forced a
 
 o	"of" is the number of times that some other CPU has forced a
 	quiescent state on behalf of this CPU due to this CPU being
-	offline.  In a perfect world, this might neve happen, but it
+	offline.  In a perfect world, this might never happen, but it
 	turns out that offlining and onlining a CPU can take several grace
 	periods, and so there is likely to be an extended period of time
 	when RCU believes that the CPU is online when it really is not.
@@ -125,6 +139,62 @@ o	"ql" is the number of RCU callbacks currently residing on
 	of what state they are in (new, waiting for grace period to
 	start, waiting for grace period to end, ready to invoke).
 
+o	"qs" gives an indication of the state of the callback queue
+	with four characters:
+
+	"N"	Indicates that there are callbacks queued that are not
+		ready to be handled by the next grace period, and thus
+		will be handled by the grace period following the next
+		one.
+
+	"R"	Indicates that there are callbacks queued that are
+		ready to be handled by the next grace period.
+
+	"W"	Indicates that there are callbacks queued that are
+		waiting on the current grace period.
+
+	"D"	Indicates that there are callbacks queued that have
+		already been handled by a prior grace period, and are
+		thus waiting to be invoked.  Note that callbacks in
+		the process of being invoked are not counted here.
+		Callbacks in the process of being invoked are those
+		that have been removed from the rcu_data structures
+		queues by rcu_do_batch(), but which have not yet been
+		invoked.
+
+	If there are no callbacks in a given one of the above states,
+	the corresponding character is replaced by ".".
+
+o	"kt" is the per-CPU kernel-thread state.  The digit preceding
+	the first slash is zero if there is no work pending and 1
+	otherwise.  The character between the first pair of slashes is
+	as follows:
+
+	"S"	The kernel thread is stopped, in other words, all
+		CPUs corresponding to this rcu_node structure are
+		offline.
+
+	"R"	The kernel thread is running.
+
+	"W"	The kernel thread is waiting because there is no work
+		for it to do.
+
+	"O"	The kernel thread is waiting because it has been
+		forced off of its designated CPU or because its
+		->cpus_allowed mask permits it to run on other than
+		its designated CPU.
+
+	"Y"	The kernel thread is yielding to avoid hogging CPU.
+
+	"?"	Unknown value, indicates a bug.
+
+	The number after the final slash is the CPU that the kthread
+	is actually running on.
+
+o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
+	the number of times that this CPU's per-CPU kthread has gone
+	through its loop servicing invoke_rcu_cpu_kthread() requests.
+
 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.
@@ -174,14 +244,14 @@ o	"gpnum" is the number of grace periods that have started.  It is
 The output of "cat rcu/rcuhier" looks as follows, with very long lines:
 
 c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6
-1/1 .>. 0:127 ^0    
-3/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
-3/3f .>. 0:5 ^0    2/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3    
+1/1 ..>. 0:127 ^0
+3/3 ..>. 0:35 ^0    0/0 ..>. 36:71 ^1    0/0 ..>. 72:107 ^2    0/0 ..>. 108:127 ^3
+3/3f ..>. 0:5 ^0    2/3 ..>. 6:11 ^1    0/0 ..>. 12:17 ^2    0/0 ..>. 18:23 ^3    0/0 ..>. 24:29 ^4    0/0 ..>. 30:35 ^5    0/0 ..>. 36:41 ^0    0/0 ..>. 42:47 ^1    0/0 ..>. 48:53 ^2    0/0 ..>. 54:59 ^3    0/0 ..>. 60:65 ^4    0/0 ..>. 66:71 ^5    0/0 ..>. 72:77 ^0    0/0 ..>. 78:83 ^1    0/0 ..>. 84:89 ^2    0/0 ..>. 90:95 ^3    0/0 ..>. 96:101 ^4    0/0 ..>. 102:107 ^5    0/0 ..>. 108:113 ^0    0/0 ..>. 114:119 ^1    0/0 ..>. 120:125 ^2    0/0 ..>. 126:127 ^3
 rcu_bh:
 c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0
-0/1 .>. 0:127 ^0    
-0/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
-0/3f .>. 0:5 ^0    0/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3
+0/1 ..>. 0:127 ^0
+0/3 ..>. 0:35 ^0    0/0 ..>. 36:71 ^1    0/0 ..>. 72:107 ^2    0/0 ..>. 108:127 ^3
+0/3f ..>. 0:5 ^0    0/3 ..>. 6:11 ^1    0/0 ..>. 12:17 ^2    0/0 ..>. 18:23 ^3    0/0 ..>. 24:29 ^4    0/0 ..>. 30:35 ^5    0/0 ..>. 36:41 ^0    0/0 ..>. 42:47 ^1    0/0 ..>. 48:53 ^2    0/0 ..>. 54:59 ^3    0/0 ..>. 60:65 ^4    0/0 ..>. 66:71 ^5    0/0 ..>. 72:77 ^0    0/0 ..>. 78:83 ^1    0/0 ..>. 84:89 ^2    0/0 ..>. 90:95 ^3    0/0 ..>. 96:101 ^4    0/0 ..>. 102:107 ^5    0/0 ..>. 108:113 ^0    0/0 ..>. 114:119 ^1    0/0 ..>. 120:125 ^2    0/0 ..>. 126:127 ^3
 
 This is once again split into "rcu_sched" and "rcu_bh" portions,
 and CONFIG_TREE_PREEMPT_RCU kernels will again have an additional
@@ -240,13 +310,20 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 		current grace period.
 
 	o	The characters separated by the ">" indicate the state
-		of the blocked-tasks lists.  A "T" preceding the ">"
+		of the blocked-tasks lists.  A "G" preceding the ">"
 		indicates that at least one task blocked in an RCU
 		read-side critical section blocks the current grace
-		period, while a "." preceding the ">" indicates otherwise.
-		The character following the ">" indicates similarly for
-		the next grace period.  A "T" should appear in this
-		field only for rcu-preempt.
+		period, while a "E" preceding the ">" indicates that
+		at least one task blocked in an RCU read-side critical
+		section blocks the current expedited grace period.
+		A "T" character following the ">" indicates that at
+		least one task is blocked within an RCU read-side
+		critical section, regardless of whether any current
+		grace period (expedited or normal) is inconvenienced.
+		A "." character appears if the corresponding condition
+		does not hold, so that "..>." indicates that no tasks
+		are blocked.  In contrast, "GE>T" indicates maximal
+		inconvenience from blocked tasks.
 
 	o	The numbers separated by the ":" are the range of CPUs
 		served by this struct rcu_node.  This can be helpful
@@ -328,6 +405,113 @@ o	"nn" is the number of times that this CPU needed nothing.  Alert
 	is due to short-circuit evaluation in rcu_pending().
 
 
+The output of "cat rcu/rcutorture" looks as follows:
+
+rcutorture test sequence: 0 (test in progress)
+rcutorture update version number: 615
+
+The first line shows the number of rcutorture tests that have completed
+since boot.  If a test is currently running, the "(test in progress)"
+string will appear as shown above.  The second line shows the number of
+update cycles that the current test has started, or zero if there is
+no test in progress.
+
+
+The output of "cat rcu/rcuboost" looks as follows:
+
+0:5 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=2f95 bt=300f
+     balk: nt=0 egt=989 bt=0 nb=0 ny=0 nos=16
+6:7 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=2f95 bt=300f
+     balk: nt=0 egt=225 bt=0 nb=0 ny=0 nos=6
+
+This information is output only for rcu_preempt.  Each two-line entry
+corresponds to a leaf rcu_node strcuture.  The fields are as follows:
+
+o	"n:m" is the CPU-number range for the corresponding two-line
+	entry.  In the sample output above, the first entry covers
+	CPUs zero through five and the second entry covers CPUs 6
+	and 7.
+
+o	"tasks=TNEB" gives the state of the various segments of the
+	rnp->blocked_tasks list:
+
+	"T"	This indicates that there are some tasks that blocked
+		while running on one of the corresponding CPUs while
+		in an RCU read-side critical section.
+
+	"N"	This indicates that some of the blocked tasks are preventing
+		the current normal (non-expedited) grace period from
+		completing.
+
+	"E"	This indicates that some of the blocked tasks are preventing
+		the current expedited grace period from completing.
+
+	"B"	This indicates that some of the blocked tasks are in
+		need of RCU priority boosting.
+
+	Each character is replaced with "." if the corresponding
+	condition does not hold.
+
+o	"kt" is the state of the RCU priority-boosting kernel
+	thread associated with the corresponding rcu_node structure.
+	The state can be one of the following:
+
+	"S"	The kernel thread is stopped, in other words, all
+		CPUs corresponding to this rcu_node structure are
+		offline.
+
+	"R"	The kernel thread is running.
+
+	"W"	The kernel thread is waiting because there is no work
+		for it to do.
+
+	"Y"	The kernel thread is yielding to avoid hogging CPU.
+
+	"?"	Unknown value, indicates a bug.
+
+o	"ntb" is the number of tasks boosted.
+
+o	"neb" is the number of tasks boosted in order to complete an
+	expedited grace period.
+
+o	"nnb" is the number of tasks boosted in order to complete a
+	normal (non-expedited) grace period.  When boosting a task
+	that was blocking both an expedited and a normal grace period,
+	it is counted against the expedited total above.
+
+o	"j" is the low-order 16 bits of the jiffies counter in
+	hexadecimal.
+
+o	"bt" is the low-order 16 bits of the value that the jiffies
+	counter will have when we next start boosting, assuming that
+	the current grace period does not end beforehand.  This is
+	also in hexadecimal.
+
+o	"balk: nt" counts the number of times we didn't boost (in
+	other words, we balked) even though it was time to boost because
+	there were no blocked tasks to boost.  This situation occurs
+	when there is one blocked task on one rcu_node structure and
+	none on some other rcu_node structure.
+
+o	"egt" counts the number of times we balked because although
+	there were blocked tasks, none of them were blocking the
+	current grace period, whether expedited or otherwise.
+
+o	"bt" counts the number of times we balked because boosting
+	had already been initiated for the current grace period.
+
+o	"nb" counts the number of times we balked because there
+	was at least one task blocking the current non-expedited grace
+	period that never had blocked.  If it is already running, it
+	just won't help to boost its priority!
+
+o	"ny" counts the number of times we balked because it was
+	not yet time to start boosting.
+
+o	"nos" counts the number of times we balked for other
+	reasons, e.g., the grace period ended first.
+
+
 CONFIG_TINY_RCU and CONFIG_TINY_PREEMPT_RCU debugfs Files and Formats
 
 These implementations of RCU provides a single debugfs file under the
@@ -394,9 +578,9 @@ o	"neb" is the number of expedited grace periods that have had
 o	"nnb" is the number of normal grace periods that have had
 	to resort to RCU priority boosting since boot.
 
-o	"j" is the low-order 12 bits of the jiffies counter in hexadecimal.
+o	"j" is the low-order 16 bits of the jiffies counter in hexadecimal.
 
-o	"bt" is the low-order 12 bits of the value that the jiffies counter
+o	"bt" is the low-order 16 bits of the value that the jiffies counter
 	will have at the next time that boosting is scheduled to begin.
 
 o	In the line beginning with "normal balk", the fields are as follows:
diff --git a/Documentation/driver-model/bus.txt b/Documentation/driver-model/bus.txt
index 5001b751162..6754b2df8aa 100644
--- a/Documentation/driver-model/bus.txt
+++ b/Documentation/driver-model/bus.txt
@@ -3,24 +3,7 @@ Bus Types
 
 Definition
 ~~~~~~~~~~
-
-struct bus_type {
-	char			* name;
-
-	struct subsystem	subsys;
-	struct kset		drivers;
-	struct kset		devices;
-
-	struct bus_attribute	* bus_attrs;
-	struct device_attribute	* dev_attrs;
-	struct driver_attribute	* drv_attrs;
-
-	int		(*match)(struct device * dev, struct device_driver * drv);
-	int		(*hotplug) (struct device *dev, char **envp, 
-				    int num_envp, char *buffer, int buffer_size);
-	int		(*suspend)(struct device * dev, pm_message_t state);
-	int		(*resume)(struct device * dev);
-};
+See the kerneldoc for the struct bus_type.
 
 int bus_register(struct bus_type * bus);
 
diff --git a/Documentation/driver-model/class.txt b/Documentation/driver-model/class.txt
index 548505f14aa..1fefc480a80 100644
--- a/Documentation/driver-model/class.txt
+++ b/Documentation/driver-model/class.txt
@@ -27,22 +27,7 @@ The device class structure looks like:
 typedef int (*devclass_add)(struct device *);
 typedef void (*devclass_remove)(struct device *);
 
-struct device_class {
-	char			* name;
-	rwlock_t		lock;
-	u32			devnum;
-	struct list_head	node;
-
-	struct list_head	drivers;
-	struct list_head	intf_list;
-
-	struct driver_dir_entry	dir;
-	struct driver_dir_entry	device_dir;
-	struct driver_dir_entry	driver_dir;
-
-	devclass_add		add_device;
-	devclass_remove		remove_device;
-};
+See the kerneldoc for the struct class.
 
 A typical device class definition would look like: 
 
diff --git a/Documentation/driver-model/device.txt b/Documentation/driver-model/device.txt
index a124f3126b0..b2ff42685bc 100644
--- a/Documentation/driver-model/device.txt
+++ b/Documentation/driver-model/device.txt
@@ -2,96 +2,7 @@
 The Basic Device Structure
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-struct device {
-        struct list_head g_list;
-        struct list_head node;
-        struct list_head bus_list;
-        struct list_head driver_list;
-        struct list_head intf_list;
-        struct list_head children;
-        struct device   * parent;
-
-        char    name[DEVICE_NAME_SIZE];
-        char    bus_id[BUS_ID_SIZE];
-
-        spinlock_t      lock;
-        atomic_t        refcount;
-
-        struct bus_type * bus;
-        struct driver_dir_entry dir;
-
-	u32		class_num;
-
-        struct device_driver *driver;
-        void            *driver_data;
-        void            *platform_data;
-
-        u32             current_state;
-        unsigned char *saved_state;
-
-        void    (*release)(struct device * dev);
-};
-
-Fields 
-~~~~~~
-g_list:	Node in the global device list.
-
-node:	Node in device's parent's children list.
-
-bus_list: Node in device's bus's devices list.
-
-driver_list:   Node in device's driver's devices list.
-
-intf_list:     List of intf_data. There is one structure allocated for
-	       each interface that the device supports.
-
-children:      List of child devices.
-
-parent:        *** FIXME ***
-
-name:	       ASCII description of device. 
-	       Example: " 3Com Corporation 3c905 100BaseTX [Boomerang]"
-
-bus_id:	       ASCII representation of device's bus position. This 
-	       field should be a name unique across all devices on the
-	       bus type the device belongs to. 
-
-	       Example: PCI bus_ids are in the form of
-	       <bus number>:<slot number>.<function number> 
-	       This name is unique across all PCI devices in the system.
-
-lock:	       Spinlock for the device. 
-
-refcount:      Reference count on the device.
-
-bus:	       Pointer to struct bus_type that device belongs to.
-
-dir:	       Device's sysfs directory.
-
-class_num:     Class-enumerated value of the device.
-
-driver:	       Pointer to struct device_driver that controls the device.
-
-driver_data:   Driver-specific data.
-
-platform_data: Platform data specific to the device.
-
-	       Example:  for devices on custom boards, as typical of embedded
-	       and SOC based hardware, Linux often uses platform_data to point
-	       to board-specific structures describing devices and how they
-	       are wired.  That can include what ports are available, chip
-	       variants, which GPIO pins act in what additional roles, and so
-	       on.  This shrinks the "Board Support Packages" (BSPs) and
-	       minimizes board-specific #ifdefs in drivers.
-
-current_state: Current power state of the device.
-
-saved_state:   Pointer to saved state of the device. This is usable by
-	       the device driver controlling the device.
-
-release:       Callback to free the device after all references have 
-	       gone away. This should be set by the allocator of the 
-	       device (i.e. the bus driver that discovered the device).
+See the kerneldoc for the struct device.
 
 
 Programming Interface
diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt
index d2cd6fb8ba9..4421135826a 100644
--- a/Documentation/driver-model/driver.txt
+++ b/Documentation/driver-model/driver.txt
@@ -1,23 +1,7 @@
 
 Device Drivers
 
-struct device_driver {
-        char                    * name;
-        struct bus_type         * bus;
-
-        struct completion	unloaded;
-        struct kobject		kobj;
-        list_t                  devices;
-
-        struct module		*owner;
-
-        int     (*probe)        (struct device * dev);
-        int     (*remove)       (struct device * dev);
-
-        int     (*suspend)      (struct device * dev, pm_message_t state);
-        int     (*resume)       (struct device * dev);
-};
-
+See the kerneldoc for the struct device_driver.
 
 
 Allocation
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 492e81df296..f6a24e8aa11 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -460,14 +460,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 
 ----------------------------
 
-What:	The acpi_sleep=s4_nonvs command line option
-When:	2.6.37
-Files:	arch/x86/kernel/acpi/sleep.c
-Why:	superseded by acpi_sleep=nonvs
-Who:	Rafael J. Wysocki <rjw@sisk.pl>
-
-----------------------------
-
 What: 	PCI DMA unmap state API
 When:	August 2012
 Why:	PCI DMA unmap state API (include/linux/pci-dma.h) was replaced
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index b0b814d75ca..60740e8ecb3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -836,7 +836,6 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
-     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index b63301a0381..050d37fe6d4 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -11,14 +11,14 @@ for non English (read: Japanese) speakers and is not intended as a
 fork. So if you have any comments or updates for this file, please try
 to update the original English file first.
 
-Last Updated: 2008/10/24
+Last Updated: 2011/03/31
 ==================================
 �れ��
-linux-2.6.28/Documentation/HOWTO
+linux-2.6.38/Documentation/HOWTO
 �和訳��。
 
 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2008/10/24
+翻訳日： 2011/3/28
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： �倉�ん <nbh--mats at nifty dot com>
          �林 雅典�ん (Masanori Kobayasi) <zap03216 at nifty dot ne dot jp>
@@ -256,8 +256,8 @@ Linux カーãƒ�ルã�®é–‹ç™ºãƒ—ロセスã�¯ç�¾åœ¨å¹¾ã�¤ã�‹ã�®ç•°ã�ªã‚‹ãƒ¡ã‚¤ãƒ³ã‚
   - メイン� 2.6.x カー�ルツリー
   - 2.6.x.y -stable カー�ルツリー
   - 2.6.x -git カー�ルパッ�
-  - 2.6.x -mm カー�ルパッ�
   - サブシステム毎�カー�ルツリー�パッ�
+  - 統�テスト���� 2.6.x -next カー�ルツリー
 
 2.6.x カー�ルツリー
 -----------------
@@ -268,9 +268,9 @@ Linux カーãƒ�ルã�®é–‹ç™ºãƒ—ロセスã�¯ç�¾åœ¨å¹¾ã�¤ã�‹ã�®ç•°ã�ªã‚‹ãƒ¡ã‚¤ãƒ³ã‚
 
   - 新��カー�ル�リリース�れ�直後��2週間�特別期間�設�られ�
     ��期間中��メンテナ�� Linus �大��差分を�る�������。
-    ��よ��差分�通常 -mm カー�ル�数週間��れ���パッ���。
+    ��よ��差分�通常 -next カー�ル�数週間��れ���パッ���。
     大��変更� git(カー�ル�ソース管�ツール�詳細�
-    http://git.or.cz/  �照) を使���る��好���やり方����パッ
+    http://git-scm.com/  �照) を使���る��好���やり方����パッ
     �ファイル�形�����る��も�分��。
 
   - 2週間後�-rc1 カー�ル�リリース�れ���後��カー�ル全体�安定
@@ -333,86 +333,44 @@ git リãƒ�ジトリã�§ç®¡ç�†ã�•ã‚Œã�¦ã�„ã‚‹Linus ã�®ã‚«ãƒ¼ãƒ�ルツリーã�®æ¯Žæ
 れ� -rc カー�ル�比���パッ��大丈夫����も確�����自動的
 �生��れる���より実験的��。
 
-2.6.x -mm カー�ルパッ�
-------------------------
-
-Andrew Morton �よ��リリース�れる実験的�カー�ルパッ�群��。
-Andrew �個別�サブシステムカー�ルツリー�パッ�を全�集����
-linux-kernel メーリングリスト��集�れ�多数�パッ���時�一���
-����。
-��ツリー�新機能�パッ��検証�れる場��り��。�る期間�間パッ�
-� -mm �入��価値を証明�れ�ら�Andrew やサブシステムメンテナ��
-メインライン�入れるよ�� Linus �プッシュ���。
-
-メインカー�ルツリー���る��� Linus ��る�������新��パッ
-�� -mm ツリー�テスト�れる���強�推奨�れ����。マージウィン
-ドウ�開��� -mm ツリー��れ����パッ��メインライン�マージ�
-れる���困難��り��。
-
-�れら�カー�ル�安定��動作���システム���使�����切���
-り��ん��カー�ルブラン��中�もも��も動作�リスク�高�も���。
-
-も������カー�ル開発プロセス�支�を��������る���れ��
-����れら�カー�ルリリースをテスト�使��������も��題��
-れ����も�全��正��動作�����も�linux-kernel メーリングリ
-スト�フィード�ックを�供������。
-
-����他�実験的パッ��加����れら�カー�ル�通常リリース時点�
-メインライン� -git カー�ル���れる全��変更も�ん����。
-
--mm カー�ル�決���スケジュール��リリース�れ��ん����通常幾
-��� -mm カー�ル (1 �ら 3 �普通）��-rc カー�ル�間�リリース�
-れ��。
-
 サブシステム毎�カー�ルツリー�パッ�
 -------------------------------------------
 
-カー�ル�様々�領域�何�起���る�を見られるよ���る���多��
-カー�ルサブシステム開発者�彼ら�開発ツリーを公開�����。�れら�
-ツリー�説明��よ�� -mm カー�ルリリース�入れ込�れ��。
-
-以下������カー�ルツリー�中������リスト-
-
-  git ツリー-
-    - Kbuild �開発ツリー�Sam Ravnborg <sam@ravnborg.org>
-	git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
-
-    - ACPI �開発ツリー� Len Brown <len.brown@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
-
-    - Block �開発ツリー�Jens Axboe <axboe@suse.de>
-	git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
-
-    - DRM �開発ツリー�Dave Airlie <airlied@linux.ie>
-	git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
-
-    - ia64 �開発ツリー�Tony Luck <tony.luck@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
-
-    - infiniband, Roland Dreier <rolandd@cisco.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
-
-    - libata, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
-
-    - �ットワークドライ�, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
-
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
-	git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-
-    - x86, Ingo Molnar <mingo@elte.hu>
-	git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-
-  quilt ツリー-
-    - USB, ドライ�コア� I2C, Greg Kroah-Hartman <gregkh@suse.de>
-	kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+�れ�れ�カー�ルサブシステム�メンテナ�� --- ���多��カー�ル
+サブシステム�開発者�も --- �自�最新�開発状�をソースリ�ジトリ�
+公開�����。�����自分��異�る領域�カー�ル�何�起���る
+�を他�人�見られるよ��������。開発�早�進ん��る領域���
+開発者�自身�投稿���サブシステムカー�ルツリーを元����る�質�
+�れる�����投稿����進行中�他�作業�������られ��。
+
+大部分��れら�リ�ジトリ� git ツリー��。�����他� SCM や
+quilt シリーズ���公開�れ��るパッ�キューも使�れ����。�れら
+�サブシステムリ�ジトリ�アドレス� MAINTAINERS ファイル�リスト�れ
+����。�れら�多�� http://git.kernel.org/ ��照�る������
+�。
 
-  ��他�カー�ルツリー� http://git.kernel.org/ � MAINTAINERS ファ
-  イル�一覧表��り��。
+�案�れ�パッ����よ��サブシステムツリー�コミット�れる���メー
+リングリスト�事��レビュー���られ��（以下�対応�るセクションを
+�照）。�����カー�ルサブシステム�����レビュー� patchwork
+���ツール�よ��追跡�れ��。Patchwork � web インターフェイス�
+よ��パッ�投稿�表示�パッ���コメント付�や改訂���������
+メンテナ�パッ��対���レビュー中��付済��拒����よ��マーク
+を��る�������。大部分��れら� patchwork �サイト�
+http://patchwork.kernel.org/ �リスト�れ����。
+
+統�テスト���� 2.6.x -next カー�ルツリー
+---------------------------------------------
+
+サブシステムツリー�更新内容�メインライン� 2.6.x ツリー�マージ�れ
+る����れら�統�テスト�れる必���り��。��目的����実質的
+�全サブシステムツリー�ら��毎日プル�れ���る特別�テスト用�リ
+�ジトリ�存在���-
+       http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+       http://linux.f-seidel.de/linux-next/pmwiki/
+
+��やり方�よ���-next カー�ル�次�マージ機会��ん�も��メイン
+ラインカー�ル�マージ�れる��������展望を�供���。-next 
+カー�ル�実行テストを行�冒険好��テスター�大��歓迎�れ��
 
 �グレ�ート
 -------------
@@ -673,10 +631,9 @@ Linux カーãƒ�ルコミュニティã�¯ã€�一度ã�«å¤§é‡�ã�®ã‚³ãƒ¼ãƒ‰ã�®å¡Šã‚’å–
 �����らスタート������ら。
 
 Paolo Ciarrocchi �感��彼�彼�書�� "Development Process"
-(http://linux.tar.bz/articles/2.6-development_process)セクショ
-ンを��テキスト�原型��る��を許����れ���。
-Rundy Dunlap � Gerrit Huizenga �メーリングリスト�やる�����や�
-���������リストを�供���れ���。
+(http://lwn.net/Articles/94386/) セクションを��テキスト�原型��る
+��を許����れ���。Rundy Dunlap � Gerrit Huizenga �メーリング
+リスト�やる�����や����������リストを�供���れ���。
 以下�人々�レビュー�コメント�貢献�感�。
 Pat Mochel, Hanna Linder, Randy Dunlap, Kay Sievers,
 Vojtech Pavlik, Jan Kara, Josh Boyer, Kees Cook, Andrew Morton, Andi
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index cc85a927819..c603ef7b056 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -245,7 +245,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	acpi_sleep=	[HW,ACPI] Sleep options
 			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-				  old_ordering, s4_nonvs, sci_force_enable }
+				  old_ordering, nonvs, sci_force_enable }
 			See Documentation/power/video.txt for information on
 			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
@@ -1664,6 +1664,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			noexec=on: enable non-executable mappings (default)
 			noexec=off: disable non-executable mappings
 
+	nosmep		[X86]
+			Disable SMEP (Supervisor Mode Execution Protection)
+			even if it is supported by processor.
+
 	noexec32	[X86-64]
 			This affects only 32-bit executables.
 			noexec32=on: enable non-executable mappings (default)
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 1971bcf48a6..88880839ece 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -279,11 +279,15 @@ When the system goes into the standby or memory sleep state, the phases are:
 	time.)  Unlike the other suspend-related phases, during the prepare
 	phase the device tree is traversed top-down.
 
-	The prepare phase uses only a bus callback.  After the callback method
-	returns, no new children may be registered below the device.  The method
-	may also prepare the device or driver in some way for the upcoming
-	system power transition, but it should not put the device into a
-	low-power state.
+	In addition to that, if device drivers need to allocate additional
+	memory to be able to hadle device suspend correctly, that should be
+	done in the prepare phase.
+
+	After the prepare callback method returns, no new children may be
+	registered below the device.  The method may also prepare the device or
+	driver in some way for the upcoming system power transition (for
+	example, by allocating additional memory required for this purpose), but
+	it should not put the device into a low-power state.
 
     2.	The suspend methods should quiesce the device to stop it from performing
 	I/O.  They also may save the device registers and put it into the
diff --git a/Documentation/power/notifiers.txt b/Documentation/power/notifiers.txt
index cf980709122..c2a4a346c0d 100644
--- a/Documentation/power/notifiers.txt
+++ b/Documentation/power/notifiers.txt
@@ -1,46 +1,41 @@
 Suspend notifiers
-	(C) 2007 Rafael J. Wysocki <rjw@sisk.pl>, GPL
-
-There are some operations that device drivers may want to carry out in their
-.suspend() routines, but shouldn't, because they can cause the hibernation or
-suspend to fail. For example, a driver may want to allocate a substantial amount
-of memory (like 50 MB) in .suspend(), but that shouldn't be done after the
-swsusp's memory shrinker has run.
-
-Also, there may be some operations, that subsystems want to carry out before a
-hibernation/suspend or after a restore/resume, requiring the system to be fully
-functional, so the drivers' .suspend() and .resume() routines are not suitable
-for this purpose.  For example, device drivers may want to upload firmware to
-their devices after a restore from a hibernation image, but they cannot do it by
-calling request_firmware() from their .resume() routines (user land processes
-are frozen at this point).  The solution may be to load the firmware into
-memory before processes are frozen and upload it from there in the .resume()
-routine.  Of course, a hibernation notifier may be used for this purpose.
-
-The subsystems that have such needs can register suspend notifiers that will be
-called upon the following events by the suspend core:
+	(C) 2007-2011 Rafael J. Wysocki <rjw@sisk.pl>, GPL
+
+There are some operations that subsystems or drivers may want to carry out
+before hibernation/suspend or after restore/resume, but they require the system
+to be fully functional, so the drivers' and subsystems' .suspend() and .resume()
+or even .prepare() and .complete() callbacks are not suitable for this purpose.
+For example, device drivers may want to upload firmware to their devices after
+resume/restore, but they cannot do it by calling request_firmware() from their
+.resume() or .complete() routines (user land processes are frozen at these
+points).  The solution may be to load the firmware into memory before processes
+are frozen and upload it from there in the .resume() routine.
+A suspend/hibernation notifier may be used for this purpose.
+
+The subsystems or drivers having such needs can register suspend notifiers that
+will be called upon the following events by the PM core:
 
 PM_HIBERNATION_PREPARE	The system is going to hibernate or suspend, tasks will
 			be frozen immediately.
 
 PM_POST_HIBERNATION	The system memory state has been restored from a
-			hibernation image or an error occurred during the
-			hibernation.  Device drivers' .resume() callbacks have
+			hibernation image or an error occurred during
+			hibernation.  Device drivers' restore callbacks have
 			been executed and tasks have been thawed.
 
 PM_RESTORE_PREPARE	The system is going to restore a hibernation image.
-			If all goes well the restored kernel will issue a
+			If all goes well, the restored kernel will issue a
 			PM_POST_HIBERNATION notification.
 
-PM_POST_RESTORE		An error occurred during the hibernation restore.
-			Device drivers' .resume() callbacks have been executed
+PM_POST_RESTORE		An error occurred during restore from hibernation.
+			Device drivers' restore callbacks have been executed
 			and tasks have been thawed.
 
-PM_SUSPEND_PREPARE	The system is preparing for a suspend.
+PM_SUSPEND_PREPARE	The system is preparing for suspend.
 
 PM_POST_SUSPEND		The system has just resumed or an error occurred during
-			the suspend.	Device drivers' .resume() callbacks have
-			been executed and tasks have been thawed.
+			suspend.  Device drivers' resume callbacks have been
+			executed and tasks have been thawed.
 
 It is generally assumed that whatever the notifiers do for
 PM_HIBERNATION_PREPARE, should be undone for PM_POST_HIBERNATION.  Analogously,
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 6d27ab8d6e9..c83bd6b4e6e 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -120,7 +120,6 @@ format:
         field:unsigned char common_flags;       offset:2;       size:1; signed:0;
         field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
         field:int common_pid;   offset:4;       size:4; signed:1;
-        field:int common_lock_depth;    offset:8;       size:4; signed:1;
 
         field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
         field:int __probe_nargs;        offset:16;      size:4; signed:1;
diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX
new file mode 100644
index 00000000000..fe0251c4cfb
--- /dev/null
+++ b/Documentation/virtual/00-INDEX
@@ -0,0 +1,10 @@
+Virtualization support in the Linux kernel.
+
+00-INDEX
+	- this file.
+kvm/
+	- Kernel Virtual Machine.  See also http://linux-kvm.org
+lguest/
+	- Extremely simple hypervisor for experimental/educational use.
+uml/
+	- User Mode Linux, builds/runs Linux kernel as a userspace program.
diff --git a/Documentation/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 9bef4e4cec5..9bef4e4cec5 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
diff --git a/Documentation/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 882068538c9..882068538c9 100644
--- a/Documentation/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
diff --git a/Documentation/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 3b4cd3bf563..3b4cd3bf563 100644
--- a/Documentation/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
diff --git a/Documentation/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index f46aa58389c..f46aa58389c 100644
--- a/Documentation/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
diff --git a/Documentation/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index d079aed27e0..d079aed27e0 100644
--- a/Documentation/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
diff --git a/Documentation/kvm/ppc-pv.txt b/Documentation/virtual/kvm/ppc-pv.txt
index 3ab969c5904..3ab969c5904 100644
--- a/Documentation/kvm/ppc-pv.txt
+++ b/Documentation/virtual/kvm/ppc-pv.txt
diff --git a/Documentation/kvm/review-checklist.txt b/Documentation/virtual/kvm/review-checklist.txt
index 730475ae1b8..a850986ed68 100644
--- a/Documentation/kvm/review-checklist.txt
+++ b/Documentation/virtual/kvm/review-checklist.txt
@@ -7,7 +7,7 @@ Review checklist for kvm patches
 2.  Patches should be against kvm.git master branch.
 
 3.  If the patch introduces or modifies a new userspace API:
-    - the API must be documented in Documentation/kvm/api.txt
+    - the API must be documented in Documentation/virtual/kvm/api.txt
     - the API must be discoverable using KVM_CHECK_EXTENSION
 
 4.  New state must include support for save/restore.
diff --git a/Documentation/kvm/timekeeping.txt b/Documentation/virtual/kvm/timekeeping.txt
index df8946377cb..df8946377cb 100644
--- a/Documentation/kvm/timekeeping.txt
+++ b/Documentation/virtual/kvm/timekeeping.txt
diff --git a/Documentation/lguest/.gitignore b/Documentation/virtual/lguest/.gitignore
index 115587fd5f6..115587fd5f6 100644
--- a/Documentation/lguest/.gitignore
+++ b/Documentation/virtual/lguest/.gitignore
diff --git a/Documentation/lguest/Makefile b/Documentation/virtual/lguest/Makefile
index bebac6b4f33..bebac6b4f33 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/virtual/lguest/Makefile
diff --git a/Documentation/lguest/extract b/Documentation/virtual/lguest/extract
index 7730bb6e4b9..7730bb6e4b9 100644
--- a/Documentation/lguest/extract
+++ b/Documentation/virtual/lguest/extract
diff --git a/Documentation/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index d9da7e14853..d9da7e14853 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
diff --git a/Documentation/lguest/lguest.txt b/Documentation/virtual/lguest/lguest.txt
index dad99978a6a..bff0c554485 100644
--- a/Documentation/lguest/lguest.txt
+++ b/Documentation/virtual/lguest/lguest.txt
@@ -74,7 +74,8 @@ Running Lguest:
 
 - Run an lguest as root:
 
-      Documentation/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 --block=rootfile root=/dev/vda
+      Documentation/virtual/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
+        --block=rootfile root=/dev/vda
 
    Explanation:
     64: the amount of memory to use, in MB.
diff --git a/Documentation/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 9b7e1904db1..9b7e1904db1 100644
--- a/Documentation/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 092e596a130..c54b4f503e2 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -206,7 +206,7 @@ IOMMU (input/output memory management unit)
       (e.g. because you have < 3 GB memory).
       Kernel boot message: "PCI-DMA: Disabling IOMMU"
 
-   2. <arch/x86_64/kernel/pci-gart.c>: AMD GART based hardware IOMMU.
+   2. <arch/x86/kernel/amd_gart_64.c>: AMD GART based hardware IOMMU.
       Kernel boot message: "PCI-DMA: using GART IOMMU"
 
    3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used
diff --git a/Documentation/zh_CN/email-clients.txt b/Documentation/zh_CN/email-clients.txt
new file mode 100644
index 00000000000..5d65e323d06
--- /dev/null
+++ b/Documentation/zh_CN/email-clients.txt
@@ -0,0 +1,210 @@
+锘?Chinese translated version of Documentation/email-clients.txt
+
+If you have any comment or update to the content, please contact the
+original document maintainer directly.  However, if you have a problem
+communicating in English you can also ask the Chinese maintainer for
+help.  Contact the Chinese maintainer if this translation is outdated
+or if there is a problem with the translation.
+
+Chinese maintainer: Harry Wei <harryxiyou@gmail.com>
+---------------------------------------------------------------------
+Documentation/email-clients.txt ???涓????缈�??
+
+濡??????宠??�烘????存?版???????????瀹癸??璇风?存?ヨ??绯诲?????妗ｇ??�存?よ?????濡????浣?浣跨?ㄨ?辨??
+浜ゆ???????伴?剧??璇?锛?涔????浠ュ??涓???????�存?よ??姹???┿??濡???????缈�????存?�???????舵?????缈?
+璇?瀛???ㄩ??棰?锛?璇疯??绯讳腑??????�存?よ?????
+
+涓???????�存?よ??锛? �惧??濞?  Harry Wei <harryxiyou@gmail.com>
+涓???????缈�?????锛? �惧??濞?  Harry Wei <harryxiyou@gmail.com>
+涓?????????¤?????锛? Yinglin Luan <synmyth@gmail.com>
+		Xiaochen Wang <wangxiaochen0@gmail.com>
+		yaxinsn <yaxinsn@163.com>
+
+浠ヤ??涓烘?ｆ??
+---------------------------------------------------------------------
+
+Linux???浠跺?㈡?风?????缃?淇℃??
+======================================================================
+
+?????????缃?
+----------------------------------------------------------------------
+Linux?????歌ˉ涓???????�????浠惰?????浜ょ??锛????濂芥??�ヤ??浣?涓洪??浠朵????????宓?????????????浜?�存?よ??
+??ユ?堕??浠讹??浣???????浠�?????瀹规?煎??�?璇ユ??"text/plain"?????惰??锛????浠朵????????涓?璧???????锛?
+???涓鸿??浼?浣胯ˉ涓????寮???ㄩ?ㄥ????ㄨ??�鸿??绋?涓???????寰???伴?俱??
+
+??ㄦ?ュ?????Linux?????歌ˉ涓???????浠跺?㈡?风????ㄥ?????�ヤ????跺??璇ュ??浜?????????????濮???舵?????渚?濡?锛?
+浠?浠?涓???芥?瑰?????????????ゅ?惰〃绗???????绌烘?硷???????虫????ㄦ??涓?�????寮?澶存?????�?�俱??
+
+涓?瑕????�?"format=flowed"妯″????????�ヤ?????�???蜂??寮?璧蜂?????棰????浠ュ?????瀹崇?????�????
+
+涓?瑕?�╀????????浠跺?㈡?风??�?�??????ㄦ?㈣?????�???蜂??浼???�??浣????�ヤ?????
+
+???浠跺?㈡?风??涓???芥?瑰???????????瀛?绗????缂??????瑰?????瑕??????????�ヤ???????芥??ASCII??????UTF-8缂??????瑰??锛?
+濡????浣?浣跨??UTF-8缂??????瑰???????????浠讹????ｄ??浣?�?浼???垮??涓?浜??????藉????????瀛?绗???????棰????
+
+???浠跺?㈡?风??�?璇ュ舰???骞朵??淇???? References: ?????? In-Reply-To: ???棰?锛???ｄ??
+???浠惰??棰?��??浼?涓???????
+
+澶???�??甯?(?????????�寸??甯?)???甯�????界?ㄤ??�ヤ??锛????涓哄?惰〃绗?浼?�????涓虹┖??笺??浣跨??xclipboard, xclip
+??????xcutsel涔?�稿??浠ワ??浣???????濂芥??璇?涓?涓?????????垮??浣跨?ㄥ????�??甯????
+
+涓?瑕???ㄤ娇???PGP/GPG缃�????????浠朵腑??????�ヤ?????�???蜂??浣垮??寰?澶???????涓???借?诲??????????ㄤ??浣????�ヤ?????
+锛?�?涓????棰?�?璇ユ?????浠ヤ慨澶????锛?
+
+??ㄧ???????�??浠跺??�ㄥ?????�ヤ??涔????锛?�????宸�?????涓?涓?�ヤ?????涓?涓???????涓绘??锛?淇?瀛???ユ?跺?扮??
+???浠讹??�?�ヤ?????'patch'??戒护???涓?锛?濡??????????浜?锛????�??????�??浠跺??�ㄥ????????
+
+
+涓?浜????浠跺?㈡?风?????绀?
+----------------------------------------------------------------------
+�????�???轰??浜?璇?�????MUA???缃????绀猴?????浠ョ?ㄤ??�?Linux?????稿?????�ヤ?????�?浜?骞朵???????虫??
+?????????�?浠跺?????缃???�?????
+
+璇存??锛?
+TUI = 浠ユ?????涓哄?虹???????ㄦ?锋?ュ??
+GUI = ??惧舰?????㈢?ㄦ?锋?ュ??
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Alpine (TUI)
+
+???缃????椤癸??
+???"Sending Preferences"??ã„¥??é”›?
+
+- "Do Not Send Flowed Text"蹇?椤诲?????
+- "Strip Whitespace Before Sending"蹇?椤诲?抽??
+
+褰???????浠舵?讹????????�?璇ユ?惧?ㄨˉ涓?浼???虹?扮????版?癸????跺?????涓?CTRL-R�???????锛?浣挎??瀹????
+�ヤ?????浠跺????ュ?伴??浠朵腑???
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Evolution (GUI)
+
+涓?浜?寮????????????????浣跨?ㄥ????????�ヤ??
+
+褰??????╅??浠堕??椤癸??Preformat
+  浠?Format->Heading->Preformatted (Ctrl-7)??????宸ュ?锋??
+
+??跺??浣跨??锛?
+  Insert->Text File... (Alt-n x)?????ヨˉ涓????浠躲??
+
+浣?�????浠?"diff -Nru old.c new.c | xclip"锛???????Preformat锛???跺??浣跨?ㄤ腑??撮??�?�?绮?甯????
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Kmail (GUI)
+
+涓?浜?寮????????????????浣跨?ㄥ????????�ヤ?????
+
+榛?�よ?剧疆涓?涓?HTML??煎??????????????锛?涓?瑕??????ㄥ?????
+
+褰?涔????涓?�????浠�????跺??锛???ㄩ??椤逛?????涓?瑕??????╄????ㄦ?㈣????????涓????缂虹?瑰氨???浣???ㄩ??浠朵腑�???ョ??浠讳????????
+??戒??浼?�??????ㄦ?㈣??锛????�や??蹇?椤诲?ㄥ?????�ヤ??涔?????????ㄦ?㈣????????绠?????????规??�辨???????ㄨ????ㄦ?㈣????ヤ功??????浠讹??
+??跺?????瀹?淇?瀛?涓鸿??绋裤??涓????浣???ㄨ??绋夸腑???娆℃??寮?瀹?锛?瀹?宸茬????ㄩ?ㄨ????ㄦ?㈣??浜?锛???ｄ??浣???????浠惰?界?舵病???
+?????╄????ㄦ?㈣??锛?浣????�?涓?浼?澶�?诲凡???????????ㄦ?㈣?????
+
+??ㄩ??浠�??�????锛??????ヨˉ涓?涔????锛???�??甯哥?ㄧ??�ヤ??瀹????绗?锛?涓?涓?�?瀛????(---)???
+
+??跺?????"Message"????????＄??锛??????╂????ユ??浠讹????ョ????????浣????�ヤ?????浠躲??�????涓?涓?棰?澶???????椤癸??浣????浠?
+???�?瀹????缃?浣???????浠跺缓绔?宸ュ?锋????????锛?�????浠ュ甫涓?"insert file"??炬?????
+
+浣????浠ュ????ㄥ?伴??�?GPG???�伴??浠讹??浣???????宓?�ヤ?????濂戒??瑕?浣跨??GPG???��??浠????浣?涓哄??宓??????????绛惧??�ヤ??锛?
+褰?浠?GPG涓???????7浣?缂??????朵??浣夸??浠?????????�??澶???????
+
+濡????浣????瑕?浠ラ??浠�??褰㈠????????�ヤ??锛???ｄ??��?抽????瑰?婚??浠讹????跺?????涓?�???�??�????"Suggest automatic
+display"锛?�???峰??宓????浠舵?�?规??�╄?�???????般??
+
+褰?浣?瑕?淇?瀛?�?瑕?????????????宓???????�ヤ??锛?浣????浠ヤ??娑???????�ㄧ????奸????�?????�ヤ????????浠讹????跺????冲?婚?????
+"save as"???浣????浠ヤ娇??ㄤ??涓?娌℃????存?圭????????�ヤ????????浠讹??濡????瀹????浠ユ?ｇ‘???褰㈠??�???????褰?浣?�ｇ????ㄥ??
+???宸辩??�???ｄ??涓?瀵????锛???ｆ?舵病??????椤瑰??浠ヤ??瀛????浠?--宸茬?????涓?涓?�???风??bug�?姹???ュ?�??kmail???bugzilla
+骞朵??甯????�?�?浼?�?澶??????????浠舵??浠ュ?????瀵规??涓???ㄦ?峰??璇诲???????????�?淇?瀛????锛????浠ュ?????浣???虫?????浠跺????跺?�?朵????版?癸??
+浣?涓?寰?涓????浠?浠????????????逛负�?????????翠?????璇汇??
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Lotus Notes (GUI)
+
+涓?瑕?浣跨?ㄥ?????
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Mutt (TUI)
+
+寰?澶?Linux寮????浜哄??浣跨??mutt瀹㈡?风??锛????浠ヨ?????瀹????瀹?宸ヤ????????甯告??浜????
+
+Mutt涓????甯?缂?�????锛????浠ヤ??绠′??浣跨?ㄤ??涔?缂?�???ㄩ?戒??�?璇ュ甫????????ㄦ??�????澶у????扮??�???ㄩ?藉甫???
+涓?涓?"insert file"???椤癸??瀹????浠ラ??�?涓???瑰?????浠跺??瀹圭????瑰???????ユ??浠躲??
+
+'vim'浣?涓?mutt???缂?�????锛?
+  set editor="vi"
+
+  濡????浣跨??xclip锛???�?ヤ互涓???戒护
+  :set paste
+  ???涓????涔??????????shift-insert??????浣跨??
+  :r filename
+
+濡??????宠?????�ヤ??浣?涓哄??宓??????????
+(a)ttach宸ヤ?????寰?濂斤??涓?甯????"set paste"???
+
+???缃????椤癸??
+瀹?�?璇ヤ互榛?�よ?剧疆???褰㈠??宸ヤ?????
+??惰??锛????"send_charset"�剧疆涓?"us-ascii::utf-8"涔????涓?涓?涓???????涓绘?????
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Pine (TUI)
+
+Pine�???绘??涓?浜?绌烘?煎????????棰?锛?浣????�?浜???�?ㄥ??璇ラ?借??淇?澶?浜????
+
+濡???????浠ワ??璇蜂娇???alpine(pine???�ф?胯??)
+
+???缃????椤癸??
+- ???�?????????????瑕?娑???ゆ??绋???????
+- "no-strip-whitespace-before-send"???椤逛????????瑕???????
+
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Sylpheed (GUI)
+
+- ???宓??????????浠ュ??濂界??宸ヤ??锛???????浣跨?ㄩ??浠讹?????
+- ???��娇??ㄥ????ㄧ??缂?�???ㄣ??
+- 瀵逛?????褰?�?澶???堕??甯告?????
+- 濡???????�?non-SSL�???ワ?????娉?浣跨??TLS SMTP?????????
+- ??ㄧ?????�???ｄ腑???涓?涓?寰??????ㄧ??ruler bar???
+- �???�?????涓?娣诲????�??��??浼?�ｇ‘???浜?瑙ｆ?剧�??????
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Thunderbird (GUI)
+
+榛?�ゆ????典??锛?thunderbird寰?瀹规??????????????锛?浣????�????涓?浜???规?????浠ュ己??跺?????寰???�ソ???
+
+- ??ㄧ?ㄦ?峰????疯?剧疆???锛?�???????瀵诲??锛?涓?瑕???????"Compose messages in HTML format"???
+
+- 缂?�?浣????Thunderbird???缃?�剧疆??ヤ娇瀹?涓?瑕????�?浣跨??锛?user_pref("mailnews.wraplength", 0);
+
+- 缂?�?浣????Thunderbird???缃?�剧疆锛?浣垮??涓?瑕?浣跨??"format=flowed"??煎??锛?user_pref("mailnews.
+  send_plaintext_flowed", false);
+
+- 浣????瑕?浣?Thunderbird???涓洪???????煎????瑰??锛?
+  濡????榛?�ゆ????典??浣?涔??????????HTML??煎??锛???ｄ?????寰???俱??浠?浠?浠????棰???????涓????妗?涓???????"Preformat"??煎?????
+  濡????榛?�ゆ????典??浣?涔??????????????????煎??锛?浣?涓?寰????瀹???逛负HTML??煎??锛?浠?浠?浣?涓轰??娆℃?х??锛???ヤ功?????扮??娑????锛?
+  ??跺??寮哄?朵娇瀹??????版???????煎??锛???????瀹?��?????�????瑕?瀹???�??锛???ㄥ??淇＄????炬??涓?浣跨??shift?????ヤ娇瀹????涓?HTML
+  ??煎??锛???跺?????棰???????涓????妗?涓???????"Preformat"??煎?????
+
+- ???��娇??ㄥ????ㄧ??缂?�????锛?
+  ???瀵?Thunderbird???�ヤ?????绠?????????规??�辨??浣跨?ㄤ??涓?"external editor"??�??锛???跺??浣跨?ㄤ????????娆㈢??
+  $EDITOR??ヨ?诲???????????骞惰ˉ涓???版?????涓????瑕?瀹???�??锛????浠ヤ??�藉苟涓?瀹?�?�?涓???�??锛???跺??娣诲??涓?涓?浣跨?ㄥ?????
+  ??????View->Toolbars->Customize...??????褰?浣?涔????淇℃???????跺??浠?浠???瑰?诲??��??浠ヤ?????
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+TkRat (GUI)
+
+???浠ヤ娇??ㄥ?????浣跨??"Insert file..."??????澶???ㄧ??缂?�???ㄣ??
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Gmail (Web GUI)
+
+涓?瑕?浣跨?ㄥ????????�ヤ?????
+
+Gmail缃?椤�?㈡?风???????ㄥ?版????惰〃绗?�????涓虹┖??笺??
+
+??界?跺?惰〃绗?�????涓虹┖??奸??棰????浠ヨ??澶???ㄧ??�???ㄨВ??筹???????跺??�?浼?浣跨?ㄥ??�???㈣?????姣?�???????涓?78涓?瀛?绗????
+
+???涓?涓????棰????Gmail�?浼????浠讳??涓????ASCII???瀛?绗????淇℃????逛负base64缂???????瀹????涓?瑗垮????????娆ф床浜虹?????瀛????
+
+                                ###
diff --git a/MAINTAINERS b/MAINTAINERS
index 69f19f10314..8df8d2dfba2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -405,8 +405,8 @@ S:	Maintained
 F:	sound/oss/aedsp16.c
 
 AFFS FILE SYSTEM
-M:	Roman Zippel <zippel@linux-m68k.org>
-S:	Maintained
+L:	linux-fsdevel@vger.kernel.org
+S:	Orphan
 F:	Documentation/filesystems/affs.txt
 F:	fs/affs/
 
@@ -2946,8 +2946,8 @@ F:	drivers/block/cciss*
 F:	include/linux/cciss_ioctl.h
 
 HFS FILESYSTEM
-M:	Roman Zippel <zippel@linux-m68k.org>
-S:	Maintained
+L:	linux-fsdevel@vger.kernel.org
+S:	Orphan
 F:	Documentation/filesystems/hfs.txt
 F:	fs/hfs/
 
@@ -3814,7 +3814,7 @@ M:	Rusty Russell <rusty@rustcorp.com.au>
 L:	lguest@lists.ozlabs.org
 W:	http://lguest.ozlabs.org/
 S:	Odd Fixes
-F:	Documentation/lguest/
+F:	Documentation/virtual/lguest/
 F:	arch/x86/lguest/
 F:	drivers/lguest/
 F:	include/linux/lguest*.h
@@ -4001,7 +4001,6 @@ F:	arch/m32r/
 
 M68K ARCHITECTURE
 M:	Geert Uytterhoeven <geert@linux-m68k.org>
-M:	Roman Zippel <zippel@linux-m68k.org>
 L:	linux-m68k@lists.linux-m68k.org
 W:	http://www.linux-m68k.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k.git
@@ -6632,7 +6631,7 @@ L:	user-mode-linux-devel@lists.sourceforge.net
 L:	user-mode-linux-user@lists.sourceforge.net
 W:	http://user-mode-linux.sourceforge.net
 S:	Maintained
-F:	Documentation/uml/
+F:	Documentation/virtual/uml/
 F:	arch/um/
 F:	fs/hostfs/
 F:	fs/hppfs/
diff --git a/Makefile b/Makefile
index 41ea6fbec55..a0344a81a89 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 39
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
@@ -1268,6 +1268,7 @@ help:
 	@echo  '  make C=1   [targets] Check all c source with $$CHECK (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make W=1   [targets] Enable extra gcc checks'
+	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
 	@echo  ''
 	@echo  'Execute "make" or "make all" to build all targets marked with [*] '
 	@echo  'For further info see the ./README file'
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 42aa078a5e4..5a621c6d22a 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs)
 
 		switch (which) {
 		case IPI_RESCHEDULE:
-			/* Reschedule callback.  Everything to be done
-			   is done by the interrupt return path.  */
+			scheduler_ipi();
 			break;
 
 		case IPI_CALL_FUNC:
diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c
index 113085a7712..7aa4262ada7 100644
--- a/arch/arm/common/vic.c
+++ b/arch/arm/common/vic.c
@@ -22,17 +22,16 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/device.h>
 #include <linux/amba/bus.h>
 
 #include <asm/mach/irq.h>
 #include <asm/hardware/vic.h>
 
-#if defined(CONFIG_PM)
+#ifdef CONFIG_PM
 /**
  * struct vic_device - VIC PM device
- * @sysdev: The system device which is registered.
  * @irq: The IRQ number for the base of the VIC.
  * @base: The register base for the VIC.
  * @resume_sources: A bitmask of interrupts for resume.
@@ -43,8 +42,6 @@
  * @protect: Save for VIC_PROTECT.
  */
 struct vic_device {
-	struct sys_device sysdev;
-
 	void __iomem	*base;
 	int		irq;
 	u32		resume_sources;
@@ -59,11 +56,6 @@ struct vic_device {
 static struct vic_device vic_devices[CONFIG_ARM_VIC_NR];
 
 static int vic_id;
-
-static inline struct vic_device *to_vic(struct sys_device *sys)
-{
-	return container_of(sys, struct vic_device, sysdev);
-}
 #endif /* CONFIG_PM */
 
 /**
@@ -85,10 +77,9 @@ static void vic_init2(void __iomem *base)
 	writel(32, base + VIC_PL190_DEF_VECT_ADDR);
 }
 
-#if defined(CONFIG_PM)
-static int vic_class_resume(struct sys_device *dev)
+#ifdef CONFIG_PM
+static void resume_one_vic(struct vic_device *vic)
 {
-	struct vic_device *vic = to_vic(dev);
 	void __iomem *base = vic->base;
 
 	printk(KERN_DEBUG "%s: resuming vic at %p\n", __func__, base);
@@ -107,13 +98,18 @@ static int vic_class_resume(struct sys_device *dev)
 
 	writel(vic->soft_int, base + VIC_INT_SOFT);
 	writel(~vic->soft_int, base + VIC_INT_SOFT_CLEAR);
+}
 
-	return 0;
+static void vic_resume(void)
+{
+	int id;
+
+	for (id = vic_id - 1; id >= 0; id--)
+		resume_one_vic(vic_devices + id);
 }
 
-static int vic_class_suspend(struct sys_device *dev, pm_message_t state)
+static void suspend_one_vic(struct vic_device *vic)
 {
-	struct vic_device *vic = to_vic(dev);
 	void __iomem *base = vic->base;
 
 	printk(KERN_DEBUG "%s: suspending vic at %p\n", __func__, base);
@@ -128,14 +124,21 @@ static int vic_class_suspend(struct sys_device *dev, pm_message_t state)
 
 	writel(vic->resume_irqs, base + VIC_INT_ENABLE);
 	writel(~vic->resume_irqs, base + VIC_INT_ENABLE_CLEAR);
+}
+
+static int vic_suspend(void)
+{
+	int id;
+
+	for (id = 0; id < vic_id; id++)
+		suspend_one_vic(vic_devices + id);
 
 	return 0;
 }
 
-struct sysdev_class vic_class = {
-	.name		= "vic",
-	.suspend	= vic_class_suspend,
-	.resume		= vic_class_resume,
+struct syscore_ops vic_syscore_ops = {
+	.suspend	= vic_suspend,
+	.resume		= vic_resume,
 };
 
 /**
@@ -147,30 +150,8 @@ struct sysdev_class vic_class = {
 */
 static int __init vic_pm_init(void)
 {
-	struct vic_device *dev = vic_devices;
-	int err;
-	int id;
-
-	if (vic_id == 0)
-		return 0;
-
-	err = sysdev_class_register(&vic_class);
-	if (err) {
-		printk(KERN_ERR "%s: cannot register class\n", __func__);
-		return err;
-	}
-
-	for (id = 0; id < vic_id; id++, dev++) {
-		dev->sysdev.id = id;
-		dev->sysdev.cls = &vic_class;
-
-		err = sysdev_register(&dev->sysdev);
-		if (err) {
-			printk(KERN_ERR "%s: failed to register device\n",
-			       __func__);
-			return err;
-		}
-	}
+	if (vic_id > 0)
+		register_syscore_ops(&vic_syscore_ops);
 
 	return 0;
 }
diff --git a/arch/arm/include/asm/i8253.h b/arch/arm/include/asm/i8253.h
new file mode 100644
index 00000000000..70656b69d5c
--- /dev/null
+++ b/arch/arm/include/asm/i8253.h
@@ -0,0 +1,15 @@
+#ifndef __ASMARM_I8253_H
+#define __ASMARM_I8253_H
+
+/* i8253A PIT registers */
+#define PIT_MODE	0x43
+#define PIT_CH0		0x40
+
+#define PIT_LATCH	((PIT_TICK_RATE + HZ / 2) / HZ)
+
+extern raw_spinlock_t i8253_lock;
+
+#define outb_pit	outb_p
+#define inb_pit		inb_p
+
+#endif
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 883f6be5117..d5adaae5ee2 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -34,7 +34,6 @@
  *   timer interrupt which may be pending.
  */
 struct sys_timer {
-	struct sys_device	dev;
 	void			(*init)(void);
 	void			(*suspend)(void);
 	void			(*resume)(void);
diff --git a/arch/arm/kernel/leds.c b/arch/arm/kernel/leds.c
index 31a316c1777..0f107dcb034 100644
--- a/arch/arm/kernel/leds.c
+++ b/arch/arm/kernel/leds.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/leds.h>
 
@@ -69,36 +70,37 @@ static ssize_t leds_store(struct sys_device *dev,
 
 static SYSDEV_ATTR(event, 0200, NULL, leds_store);
 
-static int leds_suspend(struct sys_device *dev, pm_message_t state)
+static struct sysdev_class leds_sysclass = {
+	.name		= "leds",
+};
+
+static struct sys_device leds_device = {
+	.id		= 0,
+	.cls		= &leds_sysclass,
+};
+
+static int leds_suspend(void)
 {
 	leds_event(led_stop);
 	return 0;
 }
 
-static int leds_resume(struct sys_device *dev)
+static void leds_resume(void)
 {
 	leds_event(led_start);
-	return 0;
 }
 
-static int leds_shutdown(struct sys_device *dev)
+static void leds_shutdown(void)
 {
 	leds_event(led_halted);
-	return 0;
 }
 
-static struct sysdev_class leds_sysclass = {
-	.name		= "leds",
+static struct syscore_ops leds_syscore_ops = {
 	.shutdown	= leds_shutdown,
 	.suspend	= leds_suspend,
 	.resume		= leds_resume,
 };
 
-static struct sys_device leds_device = {
-	.id		= 0,
-	.cls		= &leds_sysclass,
-};
-
 static int __init leds_init(void)
 {
 	int ret;
@@ -107,6 +109,8 @@ static int __init leds_init(void)
 		ret = sysdev_register(&leds_device);
 	if (ret == 0)
 		ret = sysdev_create_file(&leds_device, &attr_event);
+	if (ret == 0)
+		register_syscore_ops(&leds_syscore_ops);
 	return ret;
 }
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index f29b8a29b17..007a0a950e7 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_RESCHEDULE:
-		/*
-		 * nothing more to do - eveything is
-		 * done on the interrupt return path
-		 */
+		scheduler_ipi();
 		break;
 
 	case IPI_CALL_FUNC:
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 1ff46cabc7e..cb634c3e28e 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -21,7 +21,7 @@
 #include <linux/timex.h>
 #include <linux/errno.h>
 #include <linux/profile.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 #include <linux/irq.h>
 
@@ -115,48 +115,37 @@ void timer_tick(void)
 #endif
 
 #if defined(CONFIG_PM) && !defined(CONFIG_GENERIC_CLOCKEVENTS)
-static int timer_suspend(struct sys_device *dev, pm_message_t state)
+static int timer_suspend(void)
 {
-	struct sys_timer *timer = container_of(dev, struct sys_timer, dev);
-
-	if (timer->suspend != NULL)
-		timer->suspend();
+	if (system_timer->suspend)
+		system_timer->suspend();
 
 	return 0;
 }
 
-static int timer_resume(struct sys_device *dev)
+static void timer_resume(void)
 {
-	struct sys_timer *timer = container_of(dev, struct sys_timer, dev);
-
-	if (timer->resume != NULL)
-		timer->resume();
-
-	return 0;
+	if (system_timer->resume)
+		system_timer->resume();
 }
 #else
 #define timer_suspend NULL
 #define timer_resume NULL
 #endif
 
-static struct sysdev_class timer_sysclass = {
-	.name		= "timer",
+static struct syscore_ops timer_syscore_ops = {
 	.suspend	= timer_suspend,
 	.resume		= timer_resume,
 };
 
-static int __init timer_init_sysfs(void)
+static int __init timer_init_syscore_ops(void)
 {
-	int ret = sysdev_class_register(&timer_sysclass);
-	if (ret == 0) {
-		system_timer->dev.cls = &timer_sysclass;
-		ret = sysdev_register(&system_timer->dev);
-	}
+	register_syscore_ops(&timer_syscore_ops);
 
-	return ret;
+	return 0;
 }
 
-device_initcall(timer_init_sysfs);
+device_initcall(timer_init_syscore_ops);
 
 void __init time_init(void)
 {
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3b54ad19d48..d52eec268b4 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -234,7 +234,6 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 
 	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
 	       str, err, ++die_counter);
-	sysfs_printk_last_file();
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
diff --git a/arch/arm/mach-davinci/cpufreq.c b/arch/arm/mach-davinci/cpufreq.c
index 0a95be1512b..41669ecc1f9 100644
--- a/arch/arm/mach-davinci/cpufreq.c
+++ b/arch/arm/mach-davinci/cpufreq.c
@@ -94,9 +94,7 @@ static int davinci_target(struct cpufreq_policy *policy,
 	if (freqs.old == freqs.new)
 		return ret;
 
-	cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER,
-			dev_driver_string(cpufreq.dev),
-			"transition: %u --> %u\n", freqs.old, freqs.new);
+	dev_dbg(&cpufreq.dev, "transition: %u --> %u\n", freqs.old, freqs.new);
 
 	ret = cpufreq_frequency_table_target(policy, pdata->freq_table,
 						freqs.new, relation, &idx);
diff --git a/arch/arm/mach-exynos4/pm.c b/arch/arm/mach-exynos4/pm.c
index 10d917d9e3a..8755ca8dd48 100644
--- a/arch/arm/mach-exynos4/pm.c
+++ b/arch/arm/mach-exynos4/pm.c
@@ -16,6 +16,7 @@
 
 #include <linux/init.h>
 #include <linux/suspend.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -372,7 +373,27 @@ void exynos4_scu_enable(void __iomem *scu_base)
 	flush_cache_all();
 }
 
-static int exynos4_pm_resume(struct sys_device *dev)
+static struct sysdev_driver exynos4_pm_driver = {
+	.add		= exynos4_pm_add,
+};
+
+static __init int exynos4_pm_drvinit(void)
+{
+	unsigned int tmp;
+
+	s3c_pm_init();
+
+	/* All wakeup disable */
+
+	tmp = __raw_readl(S5P_WAKEUP_MASK);
+	tmp |= ((0xFF << 8) | (0x1F << 1));
+	__raw_writel(tmp, S5P_WAKEUP_MASK);
+
+	return sysdev_driver_register(&exynos4_sysclass, &exynos4_pm_driver);
+}
+arch_initcall(exynos4_pm_drvinit);
+
+static void exynos4_pm_resume(void)
 {
 	/* For release retention */
 
@@ -394,27 +415,15 @@ static int exynos4_pm_resume(struct sys_device *dev)
 	/* enable L2X0*/
 	writel_relaxed(1, S5P_VA_L2CC + L2X0_CTRL);
 #endif
-
-	return 0;
 }
 
-static struct sysdev_driver exynos4_pm_driver = {
-	.add		= exynos4_pm_add,
+static struct syscore_ops exynos4_pm_syscore_ops = {
 	.resume		= exynos4_pm_resume,
 };
 
-static __init int exynos4_pm_drvinit(void)
+static __init int exynos4_pm_syscore_init(void)
 {
-	unsigned int tmp;
-
-	s3c_pm_init();
-
-	/* All wakeup disable */
-
-	tmp = __raw_readl(S5P_WAKEUP_MASK);
-	tmp |= ((0xFF << 8) | (0x1F << 1));
-	__raw_writel(tmp, S5P_WAKEUP_MASK);
-
-	return sysdev_driver_register(&exynos4_sysclass, &exynos4_pm_driver);
+	register_syscore_ops(&exynos4_pm_syscore_ops);
+	return 0;
 }
-arch_initcall(exynos4_pm_drvinit);
+arch_initcall(exynos4_pm_syscore_init);
diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig
index bdd257921cf..46adca068f2 100644
--- a/arch/arm/mach-footbridge/Kconfig
+++ b/arch/arm/mach-footbridge/Kconfig
@@ -4,6 +4,7 @@ menu "Footbridge Implementations"
 
 config ARCH_CATS
 	bool "CATS"
+	select CLKSRC_I8253
 	select FOOTBRIDGE_HOST
 	select ISA
 	select ISA_DMA
@@ -59,6 +60,7 @@ config ARCH_EBSA285_HOST
 
 config ARCH_NETWINDER
 	bool "NetWinder"
+	select CLKSRC_I8253
 	select FOOTBRIDGE_HOST
 	select ISA
 	select ISA_DMA
diff --git a/arch/arm/mach-footbridge/isa-timer.c b/arch/arm/mach-footbridge/isa-timer.c
index 441c6ce0d55..7020f1a3fec 100644
--- a/arch/arm/mach-footbridge/isa-timer.c
+++ b/arch/arm/mach-footbridge/isa-timer.c
@@ -10,53 +10,16 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/spinlock.h>
 #include <linux/timex.h>
 
 #include <asm/irq.h>
-
+#include <asm/i8253.h>
 #include <asm/mach/time.h>
 
 #include "common.h"
 
-#define PIT_MODE	0x43
-#define PIT_CH0		0x40
-
-#define PIT_LATCH	((PIT_TICK_RATE + HZ / 2) / HZ)
-
-static cycle_t pit_read(struct clocksource *cs)
-{
-	unsigned long flags;
-	static int old_count;
-	static u32 old_jifs;
-	int count;
-	u32 jifs;
-
-	raw_local_irq_save(flags);
-
-	jifs = jiffies;
-	outb_p(0x00, PIT_MODE);		/* latch the count */
-	count = inb_p(PIT_CH0);		/* read the latched count */
-	count |= inb_p(PIT_CH0) << 8;
-
-	if (count > old_count && jifs == old_jifs)
-		count = old_count;
-
-	old_count = count;
-	old_jifs = jifs;
-
-	raw_local_irq_restore(flags);
-
-	count = (PIT_LATCH - 1) - count;
-
-	return (cycle_t)(jifs * PIT_LATCH) + count;
-}
-
-static struct clocksource pit_cs = {
-	.name		= "pit",
-	.rating		= 110,
-	.read		= pit_read,
-	.mask		= CLOCKSOURCE_MASK(32),
-};
+DEFINE_RAW_SPINLOCK(i8253_lock);
 
 static void pit_set_mode(enum clock_event_mode mode,
 	struct clock_event_device *evt)
@@ -121,7 +84,7 @@ static void __init isa_timer_init(void)
 	pit_ce.max_delta_ns = clockevent_delta2ns(0x7fff, &pit_ce);
 	pit_ce.min_delta_ns = clockevent_delta2ns(0x000f, &pit_ce);
 
-	clocksource_register_hz(&pit_cs, PIT_TICK_RATE);
+	clocksource_i8253_init();
 
 	setup_irq(pit_ce.irq, &pit_timer_irq);
 	clockevents_register_device(&pit_ce);
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 980803ff348..d3e96451529 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -24,7 +24,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/kmi.h>
 #include <linux/clocksource.h>
@@ -180,13 +180,13 @@ static void __init ap_init_irq(void)
 #ifdef CONFIG_PM
 static unsigned long ic_irq_enable;
 
-static int irq_suspend(struct sys_device *dev, pm_message_t state)
+static int irq_suspend(void)
 {
 	ic_irq_enable = readl(VA_IC_BASE + IRQ_ENABLE);
 	return 0;
 }
 
-static int irq_resume(struct sys_device *dev)
+static void irq_resume(void)
 {
 	/* disable all irq sources */
 	writel(-1, VA_CMIC_BASE + IRQ_ENABLE_CLEAR);
@@ -194,33 +194,25 @@ static int irq_resume(struct sys_device *dev)
 	writel(-1, VA_IC_BASE + FIQ_ENABLE_CLEAR);
 
 	writel(ic_irq_enable, VA_IC_BASE + IRQ_ENABLE_SET);
-	return 0;
 }
 #else
 #define irq_suspend NULL
 #define irq_resume NULL
 #endif
 
-static struct sysdev_class irq_class = {
-	.name		= "irq",
+static struct syscore_ops irq_syscore_ops = {
 	.suspend	= irq_suspend,
 	.resume		= irq_resume,
 };
 
-static struct sys_device irq_device = {
-	.id	= 0,
-	.cls	= &irq_class,
-};
-
-static int __init irq_init_sysfs(void)
+static int __init irq_syscore_init(void)
 {
-	int ret = sysdev_class_register(&irq_class);
-	if (ret == 0)
-		ret = sysdev_register(&irq_device);
-	return ret;
+	register_syscore_ops(&irq_syscore_ops);
+
+	return 0;
 }
 
-device_initcall(irq_init_sysfs);
+device_initcall(irq_syscore_init);
 
 /*
  * Flash handling.
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index 6588c22b8a6..fe31d933f0e 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -24,75 +24,50 @@
 #ifdef CONFIG_PM_RUNTIME
 static int omap1_pm_runtime_suspend(struct device *dev)
 {
-	struct clk *iclk, *fclk;
-	int ret = 0;
+	int ret;
 
 	dev_dbg(dev, "%s\n", __func__);
 
 	ret = pm_generic_runtime_suspend(dev);
+	if (ret)
+		return ret;
 
-	fclk = clk_get(dev, "fck");
-	if (!IS_ERR(fclk)) {
-		clk_disable(fclk);
-		clk_put(fclk);
-	}
-
-	iclk = clk_get(dev, "ick");
-	if (!IS_ERR(iclk)) {
-		clk_disable(iclk);
-		clk_put(iclk);
+	ret = pm_runtime_clk_suspend(dev);
+	if (ret) {
+		pm_generic_runtime_resume(dev);
+		return ret;
 	}
 
 	return 0;
-};
+}
 
 static int omap1_pm_runtime_resume(struct device *dev)
 {
-	struct clk *iclk, *fclk;
-
 	dev_dbg(dev, "%s\n", __func__);
 
-	iclk = clk_get(dev, "ick");
-	if (!IS_ERR(iclk)) {
-		clk_enable(iclk);
-		clk_put(iclk);
-	}
+	pm_runtime_clk_resume(dev);
+	return pm_generic_runtime_resume(dev);
+}
 
-	fclk = clk_get(dev, "fck");
-	if (!IS_ERR(fclk)) {
-		clk_enable(fclk);
-		clk_put(fclk);
-	}
+static struct dev_power_domain default_power_domain = {
+	.ops = {
+		.runtime_suspend = omap1_pm_runtime_suspend,
+		.runtime_resume = omap1_pm_runtime_resume,
+		USE_PLATFORM_PM_SLEEP_OPS
+	},
+};
 
-	return pm_generic_runtime_resume(dev);
+static struct pm_clk_notifier_block platform_bus_notifier = {
+	.pwr_domain = &default_power_domain,
+	.con_ids = { "ick", "fck", NULL, },
 };
 
 static int __init omap1_pm_runtime_init(void)
 {
-	const struct dev_pm_ops *pm;
-	struct dev_pm_ops *omap_pm;
-
 	if (!cpu_class_is_omap1())
 		return -ENODEV;
 
-	pm = platform_bus_get_pm_ops();
-	if (!pm) {
-		pr_err("%s: unable to get dev_pm_ops from platform_bus\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	omap_pm = kmemdup(pm, sizeof(struct dev_pm_ops), GFP_KERNEL);
-	if (!omap_pm) {
-		pr_err("%s: unable to alloc memory for new dev_pm_ops\n",
-			__func__);
-		return -ENOMEM;
-	}
-
-	omap_pm->runtime_suspend = omap1_pm_runtime_suspend;
-	omap_pm->runtime_resume = omap1_pm_runtime_resume;
-
-	platform_bus_set_pm_ops(omap_pm);
+	pm_runtime_clk_add_notifier(&platform_bus_type, &platform_bus_notifier);
 
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 512b1520445..66dfbccacd2 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -59,10 +59,10 @@ endif
 # Power Management
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_ARCH_OMAP2)		+= pm24xx.o
-obj-$(CONFIG_ARCH_OMAP2)		+= sleep24xx.o pm_bus.o
+obj-$(CONFIG_ARCH_OMAP2)		+= sleep24xx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= pm34xx.o sleep34xx.o \
-					   cpuidle34xx.o pm_bus.o
-obj-$(CONFIG_ARCH_OMAP4)		+= pm44xx.o pm_bus.o
+					   cpuidle34xx.o
+obj-$(CONFIG_ARCH_OMAP4)		+= pm44xx.o
 obj-$(CONFIG_PM_DEBUG)			+= pm-debug.o
 obj-$(CONFIG_OMAP_SMARTREFLEX)          += sr_device.o smartreflex.o
 obj-$(CONFIG_OMAP_SMARTREFLEX_CLASS3)	+= smartreflex-class3.o
diff --git a/arch/arm/mach-omap2/pm_bus.c b/arch/arm/mach-omap2/pm_bus.c
deleted file mode 100644
index 5acd2ab298b..00000000000
--- a/arch/arm/mach-omap2/pm_bus.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * Runtime PM support code for OMAP
- *
- * Author: Kevin Hilman, Deep Root Systems, LLC
- *
- * Copyright (C) 2010 Texas Instruments, Inc.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <linux/pm_runtime.h>
-#include <linux/platform_device.h>
-#include <linux/mutex.h>
-
-#include <plat/omap_device.h>
-#include <plat/omap-pm.h>
-
-#ifdef CONFIG_PM_RUNTIME
-static int omap_pm_runtime_suspend(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	int r, ret = 0;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	ret = pm_generic_runtime_suspend(dev);
-
-	if (!ret && dev->parent == &omap_device_parent) {
-		r = omap_device_idle(pdev);
-		WARN_ON(r);
-	}
-
-	return ret;
-};
-
-static int omap_pm_runtime_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	int r;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	if (dev->parent == &omap_device_parent) {
-		r = omap_device_enable(pdev);
-		WARN_ON(r);
-	}
-
-	return pm_generic_runtime_resume(dev);
-};
-#else
-#define omap_pm_runtime_suspend NULL
-#define omap_pm_runtime_resume NULL
-#endif /* CONFIG_PM_RUNTIME */
-
-static int __init omap_pm_runtime_init(void)
-{
-	const struct dev_pm_ops *pm;
-	struct dev_pm_ops *omap_pm;
-
-	pm = platform_bus_get_pm_ops();
-	if (!pm) {
-		pr_err("%s: unable to get dev_pm_ops from platform_bus\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	omap_pm = kmemdup(pm, sizeof(struct dev_pm_ops), GFP_KERNEL);
-	if (!omap_pm) {
-		pr_err("%s: unable to alloc memory for new dev_pm_ops\n",
-			__func__);
-		return -ENOMEM;
-	}
-
-	omap_pm->runtime_suspend = omap_pm_runtime_suspend;
-	omap_pm->runtime_resume = omap_pm_runtime_resume;
-
-	platform_bus_set_pm_ops(omap_pm);
-
-	return 0;
-}
-core_initcall(omap_pm_runtime_init);
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index bfbecec6d05..810a982a66f 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -15,7 +15,6 @@
 
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
diff --git a/arch/arm/mach-pxa/clock-pxa2xx.c b/arch/arm/mach-pxa/clock-pxa2xx.c
index 1ce09044849..1d5859d9a0e 100644
--- a/arch/arm/mach-pxa/clock-pxa2xx.c
+++ b/arch/arm/mach-pxa/clock-pxa2xx.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/pxa2xx-regs.h>
 
@@ -33,32 +33,22 @@ const struct clkops clk_pxa2xx_cken_ops = {
 #ifdef CONFIG_PM
 static uint32_t saved_cken;
 
-static int pxa2xx_clock_suspend(struct sys_device *d, pm_message_t state)
+static int pxa2xx_clock_suspend(void)
 {
 	saved_cken = CKEN;
 	return 0;
 }
 
-static int pxa2xx_clock_resume(struct sys_device *d)
+static void pxa2xx_clock_resume(void)
 {
 	CKEN = saved_cken;
-	return 0;
 }
 #else
 #define pxa2xx_clock_suspend	NULL
 #define pxa2xx_clock_resume	NULL
 #endif
 
-struct sysdev_class pxa2xx_clock_sysclass = {
-	.name		= "pxa2xx-clock",
+struct syscore_ops pxa2xx_clock_syscore_ops = {
 	.suspend	= pxa2xx_clock_suspend,
 	.resume		= pxa2xx_clock_resume,
 };
-
-static int __init pxa2xx_clock_init(void)
-{
-	if (cpu_is_pxa2xx())
-		return sysdev_class_register(&pxa2xx_clock_sysclass);
-	return 0;
-}
-postcore_initcall(pxa2xx_clock_init);
diff --git a/arch/arm/mach-pxa/clock-pxa3xx.c b/arch/arm/mach-pxa/clock-pxa3xx.c
index 3f864cd0bd2..2a37a9a8f62 100644
--- a/arch/arm/mach-pxa/clock-pxa3xx.c
+++ b/arch/arm/mach-pxa/clock-pxa3xx.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/smemc.h>
 #include <mach/pxa3xx-regs.h>
@@ -182,7 +183,7 @@ const struct clkops clk_pxa3xx_pout_ops = {
 static uint32_t cken[2];
 static uint32_t accr;
 
-static int pxa3xx_clock_suspend(struct sys_device *d, pm_message_t state)
+static int pxa3xx_clock_suspend(void)
 {
 	cken[0] = CKENA;
 	cken[1] = CKENB;
@@ -190,28 +191,18 @@ static int pxa3xx_clock_suspend(struct sys_device *d, pm_message_t state)
 	return 0;
 }
 
-static int pxa3xx_clock_resume(struct sys_device *d)
+static void pxa3xx_clock_resume(void)
 {
 	ACCR = accr;
 	CKENA = cken[0];
 	CKENB = cken[1];
-	return 0;
 }
 #else
 #define pxa3xx_clock_suspend	NULL
 #define pxa3xx_clock_resume	NULL
 #endif
 
-struct sysdev_class pxa3xx_clock_sysclass = {
-	.name		= "pxa3xx-clock",
+struct syscore_ops pxa3xx_clock_syscore_ops = {
 	.suspend	= pxa3xx_clock_suspend,
 	.resume		= pxa3xx_clock_resume,
 };
-
-static int __init pxa3xx_clock_init(void)
-{
-	if (cpu_is_pxa3xx() || cpu_is_pxa95x())
-		return sysdev_class_register(&pxa3xx_clock_sysclass);
-	return 0;
-}
-postcore_initcall(pxa3xx_clock_init);
diff --git a/arch/arm/mach-pxa/clock.h b/arch/arm/mach-pxa/clock.h
index f9f349a21b5..1f2fb9c43f0 100644
--- a/arch/arm/mach-pxa/clock.h
+++ b/arch/arm/mach-pxa/clock.h
@@ -1,5 +1,5 @@
 #include <linux/clkdev.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 struct clkops {
 	void			(*enable)(struct clk *);
@@ -54,7 +54,7 @@ extern const struct clkops clk_pxa2xx_cken_ops;
 void clk_pxa2xx_cken_enable(struct clk *clk);
 void clk_pxa2xx_cken_disable(struct clk *clk);
 
-extern struct sysdev_class pxa2xx_clock_sysclass;
+extern struct syscore_ops pxa2xx_clock_syscore_ops;
 
 #if defined(CONFIG_PXA3xx) || defined(CONFIG_PXA95x)
 #define DEFINE_PXA3_CKEN(_name, _cken, _rate, _delay)	\
@@ -74,5 +74,6 @@ extern const struct clkops clk_pxa3xx_smemc_ops;
 extern void clk_pxa3xx_cken_enable(struct clk *);
 extern void clk_pxa3xx_cken_disable(struct clk *);
 
-extern struct sysdev_class pxa3xx_clock_sysclass;
+extern struct syscore_ops pxa3xx_clock_syscore_ops;
+
 #endif
diff --git a/arch/arm/mach-pxa/cm-x270.c b/arch/arm/mach-pxa/cm-x270.c
index b88d601a809..13518a70539 100644
--- a/arch/arm/mach-pxa/cm-x270.c
+++ b/arch/arm/mach-pxa/cm-x270.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c
index 8225e2e58c6..a1099678247 100644
--- a/arch/arm/mach-pxa/cm-x2xx.c
+++ b/arch/arm/mach-pxa/cm-x2xx.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
 
@@ -388,7 +388,7 @@ static inline void cmx2xx_init_display(void) {}
 #ifdef CONFIG_PM
 static unsigned long sleep_save_msc[10];
 
-static int cmx2xx_suspend(struct sys_device *dev, pm_message_t state)
+static int cmx2xx_suspend(void)
 {
 	cmx2xx_pci_suspend();
 
@@ -412,7 +412,7 @@ static int cmx2xx_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int cmx2xx_resume(struct sys_device *dev)
+static void cmx2xx_resume(void)
 {
 	cmx2xx_pci_resume();
 
@@ -420,27 +420,18 @@ static int cmx2xx_resume(struct sys_device *dev)
 	__raw_writel(sleep_save_msc[0], MSC0);
 	__raw_writel(sleep_save_msc[1], MSC1);
 	__raw_writel(sleep_save_msc[2], MSC2);
-
-	return 0;
 }
 
-static struct sysdev_class cmx2xx_pm_sysclass = {
-	.name = "pm",
+static struct syscore_ops cmx2xx_pm_syscore_ops = {
 	.resume = cmx2xx_resume,
 	.suspend = cmx2xx_suspend,
 };
 
-static struct sys_device cmx2xx_pm_device = {
-	.cls = &cmx2xx_pm_sysclass,
-};
-
 static int __init cmx2xx_pm_init(void)
 {
-	int error;
-	error = sysdev_class_register(&cmx2xx_pm_sysclass);
-	if (error == 0)
-		error = sysdev_register(&cmx2xx_pm_device);
-	return error;
+	register_syscore_ops(&cmx2xx_pm_syscore_ops);
+
+	return 0;
 }
 #else
 static int __init cmx2xx_pm_init(void) { return 0; }
diff --git a/arch/arm/mach-pxa/colibri-evalboard.c b/arch/arm/mach-pxa/colibri-evalboard.c
index 81c3c433e2d..d28e802e244 100644
--- a/arch/arm/mach-pxa/colibri-evalboard.c
+++ b/arch/arm/mach-pxa/colibri-evalboard.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/gpio.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa270-income.c b/arch/arm/mach-pxa/colibri-pxa270-income.c
index 44c1b77ece6..80538b8806e 100644
--- a/arch/arm/mach-pxa/colibri-pxa270-income.c
+++ b/arch/arm/mach-pxa/colibri-pxa270-income.c
@@ -22,7 +22,6 @@
 #include <linux/platform_device.h>
 #include <linux/pwm_backlight.h>
 #include <linux/i2c/pxa-i2c.h>
-#include <linux/sysdev.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 6fc5d328ba7..7545a48ed88 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -17,7 +17,6 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
 #include <linux/ucb1400.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/generic.h b/arch/arm/mach-pxa/generic.h
index a079d8baa45..e6c9344a95a 100644
--- a/arch/arm/mach-pxa/generic.h
+++ b/arch/arm/mach-pxa/generic.h
@@ -61,10 +61,10 @@ extern unsigned pxa3xx_get_clk_frequency_khz(int);
 #define pxa3xx_get_clk_frequency_khz(x)		(0)
 #endif
 
-extern struct sysdev_class pxa_irq_sysclass;
-extern struct sysdev_class pxa_gpio_sysclass;
-extern struct sysdev_class pxa2xx_mfp_sysclass;
-extern struct sysdev_class pxa3xx_mfp_sysclass;
+extern struct syscore_ops pxa_irq_syscore_ops;
+extern struct syscore_ops pxa_gpio_syscore_ops;
+extern struct syscore_ops pxa2xx_mfp_syscore_ops;
+extern struct syscore_ops pxa3xx_mfp_syscore_ops;
 
 void __init pxa_set_ffuart_info(void *info);
 void __init pxa_set_btuart_info(void *info);
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 6251e3f5c62..32ed551bf9c 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 
@@ -183,7 +183,7 @@ void __init pxa_init_irq(int irq_nr, set_wake_t fn)
 static unsigned long saved_icmr[MAX_INTERNAL_IRQS/32];
 static unsigned long saved_ipr[MAX_INTERNAL_IRQS];
 
-static int pxa_irq_suspend(struct sys_device *dev, pm_message_t state)
+static int pxa_irq_suspend(void)
 {
 	int i;
 
@@ -202,7 +202,7 @@ static int pxa_irq_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int pxa_irq_resume(struct sys_device *dev)
+static void pxa_irq_resume(void)
 {
 	int i;
 
@@ -218,22 +218,13 @@ static int pxa_irq_resume(struct sys_device *dev)
 			__raw_writel(saved_ipr[i], IRQ_BASE + IPR(i));
 
 	__raw_writel(1, IRQ_BASE + ICCR);
-	return 0;
 }
 #else
 #define pxa_irq_suspend		NULL
 #define pxa_irq_resume		NULL
 #endif
 
-struct sysdev_class pxa_irq_sysclass = {
-	.name		= "irq",
+struct syscore_ops pxa_irq_syscore_ops = {
 	.suspend	= pxa_irq_suspend,
 	.resume		= pxa_irq_resume,
 };
-
-static int __init pxa_irq_init(void)
-{
-	return sysdev_class_register(&pxa_irq_sysclass);
-}
-
-core_initcall(pxa_irq_init);
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index f5de541725b..6cf8180bf5b 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -15,7 +15,7 @@
 
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
@@ -159,30 +159,22 @@ static void __init lpd270_init_irq(void)
 
 
 #ifdef CONFIG_PM
-static int lpd270_irq_resume(struct sys_device *dev)
+static void lpd270_irq_resume(void)
 {
 	__raw_writew(lpd270_irq_enabled, LPD270_INT_MASK);
-	return 0;
 }
 
-static struct sysdev_class lpd270_irq_sysclass = {
-	.name = "cpld_irq",
+static struct syscore_ops lpd270_irq_syscore_ops = {
 	.resume = lpd270_irq_resume,
 };
 
-static struct sys_device lpd270_irq_device = {
-	.cls = &lpd270_irq_sysclass,
-};
-
 static int __init lpd270_irq_device_init(void)
 {
-	int ret = -ENODEV;
 	if (machine_is_logicpd_pxa270()) {
-		ret = sysdev_class_register(&lpd270_irq_sysclass);
-		if (ret == 0)
-			ret = sysdev_register(&lpd270_irq_device);
+		register_syscore_ops(&lpd270_irq_syscore_ops);
+		return 0;
 	}
-	return ret;
+	return -ENODEV;
 }
 
 device_initcall(lpd270_irq_device_init);
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 3ede978c83d..e10ddb82714 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/major.h>
 #include <linux/fb.h>
 #include <linux/interrupt.h>
@@ -176,31 +176,22 @@ static void __init lubbock_init_irq(void)
 
 #ifdef CONFIG_PM
 
-static int lubbock_irq_resume(struct sys_device *dev)
+static void lubbock_irq_resume(void)
 {
 	LUB_IRQ_MASK_EN = lubbock_irq_enabled;
-	return 0;
 }
 
-static struct sysdev_class lubbock_irq_sysclass = {
-	.name = "cpld_irq",
+static struct syscore_ops lubbock_irq_syscore_ops = {
 	.resume = lubbock_irq_resume,
 };
 
-static struct sys_device lubbock_irq_device = {
-	.cls = &lubbock_irq_sysclass,
-};
-
 static int __init lubbock_irq_device_init(void)
 {
-	int ret = -ENODEV;
-
 	if (machine_is_lubbock()) {
-		ret = sysdev_class_register(&lubbock_irq_sysclass);
-		if (ret == 0)
-			ret = sysdev_register(&lubbock_irq_device);
+		register_syscore_ops(&lubbock_irq_syscore_ops);
+		return 0;
 	}
-	return ret;
+	return -ENODEV;
 }
 
 device_initcall(lubbock_irq_device_init);
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index 95163baca29..3479e2b3b51 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -15,7 +15,7 @@
 
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
@@ -185,31 +185,21 @@ static void __init mainstone_init_irq(void)
 
 #ifdef CONFIG_PM
 
-static int mainstone_irq_resume(struct sys_device *dev)
+static void mainstone_irq_resume(void)
 {
 	MST_INTMSKENA = mainstone_irq_enabled;
-	return 0;
 }
 
-static struct sysdev_class mainstone_irq_sysclass = {
-	.name = "cpld_irq",
+static struct syscore_ops mainstone_irq_syscore_ops = {
 	.resume = mainstone_irq_resume,
 };
 
-static struct sys_device mainstone_irq_device = {
-	.cls = &mainstone_irq_sysclass,
-};
-
 static int __init mainstone_irq_device_init(void)
 {
-	int ret = -ENODEV;
+	if (machine_is_mainstone())
+		register_syscore_ops(&mainstone_irq_syscore_ops);
 
-	if (machine_is_mainstone()) {
-		ret = sysdev_class_register(&mainstone_irq_sysclass);
-		if (ret == 0)
-			ret = sysdev_register(&mainstone_irq_device);
-	}
-	return ret;
+	return 0;
 }
 
 device_initcall(mainstone_irq_device_init);
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 1d1419b7345..87ae3129f4f 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/gpio.h>
 #include <mach/pxa2xx-regs.h>
@@ -338,7 +338,7 @@ static unsigned long saved_gafr[2][4];
 static unsigned long saved_gpdr[4];
 static unsigned long saved_pgsr[4];
 
-static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state)
+static int pxa2xx_mfp_suspend(void)
 {
 	int i;
 
@@ -365,7 +365,7 @@ static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state)
 	return 0;
 }
 
-static int pxa2xx_mfp_resume(struct sys_device *d)
+static void pxa2xx_mfp_resume(void)
 {
 	int i;
 
@@ -376,15 +376,13 @@ static int pxa2xx_mfp_resume(struct sys_device *d)
 		PGSR(i) = saved_pgsr[i];
 	}
 	PSSR = PSSR_RDH | PSSR_PH;
-	return 0;
 }
 #else
 #define pxa2xx_mfp_suspend	NULL
 #define pxa2xx_mfp_resume	NULL
 #endif
 
-struct sysdev_class pxa2xx_mfp_sysclass = {
-	.name		= "mfp",
+struct syscore_ops pxa2xx_mfp_syscore_ops = {
 	.suspend	= pxa2xx_mfp_suspend,
 	.resume		= pxa2xx_mfp_resume,
 };
@@ -409,6 +407,6 @@ static int __init pxa2xx_mfp_init(void)
 	for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++)
 		gpdr_lpm[i] = GPDR(i * 32);
 
-	return sysdev_class_register(&pxa2xx_mfp_sysclass);
+	return 0;
 }
 postcore_initcall(pxa2xx_mfp_init);
diff --git a/arch/arm/mach-pxa/mfp-pxa3xx.c b/arch/arm/mach-pxa/mfp-pxa3xx.c
index 7a270eecd48..89863a01ecd 100644
--- a/arch/arm/mach-pxa/mfp-pxa3xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa3xx.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/hardware.h>
 #include <mach/mfp-pxa3xx.h>
@@ -31,13 +31,13 @@
  * a pull-down mode if they're an active low chip select, and we're
  * just entering standby.
  */
-static int pxa3xx_mfp_suspend(struct sys_device *d, pm_message_t state)
+static int pxa3xx_mfp_suspend(void)
 {
 	mfp_config_lpm();
 	return 0;
 }
 
-static int pxa3xx_mfp_resume(struct sys_device *d)
+static void pxa3xx_mfp_resume(void)
 {
 	mfp_config_run();
 
@@ -47,24 +47,13 @@ static int pxa3xx_mfp_resume(struct sys_device *d)
 	 * preserve them here in case they will be referenced later
 	 */
 	ASCR &= ~(ASCR_RDH | ASCR_D1S | ASCR_D2S | ASCR_D3S);
-	return 0;
 }
 #else
 #define pxa3xx_mfp_suspend	NULL
 #define pxa3xx_mfp_resume	NULL
 #endif
 
-struct sysdev_class pxa3xx_mfp_sysclass = {
-	.name		= "mfp",
+struct syscore_ops pxa3xx_mfp_syscore_ops = {
 	.suspend	= pxa3xx_mfp_suspend,
-	.resume 	= pxa3xx_mfp_resume,
+	.resume		= pxa3xx_mfp_resume,
 };
-
-static int __init mfp_init_devicefs(void)
-{
-	if (cpu_is_pxa3xx())
-		return sysdev_class_register(&pxa3xx_mfp_sysclass);
-
-	return 0;
-}
-postcore_initcall(mfp_init_devicefs);
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index 23925db8ff7..e3470137c93 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -22,7 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/input.h>
 #include <linux/delay.h>
 #include <linux/gpio_keys.h>
@@ -488,7 +488,7 @@ static void install_bootstrap(void)
 }
 
 
-static int mioa701_sys_suspend(struct sys_device *sysdev, pm_message_t state)
+static int mioa701_sys_suspend(void)
 {
 	int i = 0, is_bt_on;
 	u32 *mem_resume_vector	= phys_to_virt(RESUME_VECTOR_ADDR);
@@ -514,7 +514,7 @@ static int mioa701_sys_suspend(struct sys_device *sysdev, pm_message_t state)
 	return 0;
 }
 
-static int mioa701_sys_resume(struct sys_device *sysdev)
+static void mioa701_sys_resume(void)
 {
 	int i = 0;
 	u32 *mem_resume_vector	= phys_to_virt(RESUME_VECTOR_ADDR);
@@ -527,43 +527,18 @@ static int mioa701_sys_resume(struct sys_device *sysdev)
 	*mem_resume_enabler = save_buffer[i++];
 	*mem_resume_bt	    = save_buffer[i++];
 	*mem_resume_unknown = save_buffer[i++];
-
-	return 0;
 }
 
-static struct sysdev_class mioa701_sysclass = {
-	.name = "mioa701",
-};
-
-static struct sys_device sysdev_bootstrap = {
-	.cls		= &mioa701_sysclass,
-};
-
-static struct sysdev_driver driver_bootstrap = {
-	.suspend	= &mioa701_sys_suspend,
-	.resume		= &mioa701_sys_resume,
+static struct syscore_ops mioa701_syscore_ops = {
+	.suspend	= mioa701_sys_suspend,
+	.resume		= mioa701_sys_resume,
 };
 
 static int __init bootstrap_init(void)
 {
-	int rc;
 	int save_size = mioa701_bootstrap_lg + (sizeof(u32) * 3);
 
-	rc = sysdev_class_register(&mioa701_sysclass);
-	if (rc) {
-		printk(KERN_ERR "Failed registering mioa701 sys class\n");
-		return -ENODEV;
-	}
-	rc = sysdev_register(&sysdev_bootstrap);
-	if (rc) {
-		printk(KERN_ERR "Failed registering mioa701 sys device\n");
-		return -ENODEV;
-	}
-	rc = sysdev_driver_register(&mioa701_sysclass, &driver_bootstrap);
-	if (rc) {
-		printk(KERN_ERR "Failed registering PMU sys driver\n");
-		return -ENODEV;
-	}
+	register_syscore_ops(&mioa701_syscore_ops);
 
 	save_buffer = kmalloc(save_size, GFP_KERNEL);
 	if (!save_buffer)
@@ -576,9 +551,7 @@ static int __init bootstrap_init(void)
 static void bootstrap_exit(void)
 {
 	kfree(save_buffer);
-	sysdev_driver_unregister(&mioa701_sysclass, &driver_bootstrap);
-	sysdev_unregister(&sysdev_bootstrap);
-	sysdev_class_unregister(&mioa701_sysclass);
+	unregister_syscore_ops(&mioa701_syscore_ops);
 
 	printk(KERN_CRIT "Unregistering mioa701 suspend will hang next"
 	       "resume !!!\n");
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index a6f898cbfac..4061ecddee7 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -24,7 +24,6 @@
 #include <linux/gpio.h>
 #include <linux/wm97xx.h>
 #include <linux/power_supply.h>
-#include <linux/sysdev.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index 8aadad55fbe..20d1b18b173 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -25,7 +25,6 @@
 #include <linux/pwm_backlight.h>
 #include <linux/gpio.h>
 #include <linux/power_supply.h>
-#include <linux/sysdev.h>
 #include <linux/w1-gpio.h>
 
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 3b8a4f37dbb..65f24f0b77e 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/gpio_keys.h>
@@ -233,9 +233,9 @@ static struct palmz72_resume_info palmz72_resume_info = {
 
 static unsigned long store_ptr;
 
-/* sys_device for Palm Zire 72 PM */
+/* syscore_ops for Palm Zire 72 PM */
 
-static int palmz72_pm_suspend(struct sys_device *dev, pm_message_t msg)
+static int palmz72_pm_suspend(void)
 {
 	/* setup the resume_info struct for the original bootloader */
 	palmz72_resume_info.resume_addr = (u32) cpu_resume;
@@ -249,31 +249,23 @@ static int palmz72_pm_suspend(struct sys_device *dev, pm_message_t msg)
 	return 0;
 }
 
-static int palmz72_pm_resume(struct sys_device *dev)
+static void palmz72_pm_resume(void)
 {
 	*PALMZ72_SAVE_DWORD = store_ptr;
-	return 0;
 }
 
-static struct sysdev_class palmz72_pm_sysclass = {
-	.name = "palmz72_pm",
+static struct syscore_ops palmz72_pm_syscore_ops = {
 	.suspend = palmz72_pm_suspend,
 	.resume = palmz72_pm_resume,
 };
 
-static struct sys_device palmz72_pm_device = {
-	.cls = &palmz72_pm_sysclass,
-};
-
 static int __init palmz72_pm_init(void)
 {
-	int ret = -ENODEV;
 	if (machine_is_palmz72()) {
-		ret = sysdev_class_register(&palmz72_pm_sysclass);
-		if (ret == 0)
-			ret = sysdev_register(&palmz72_pm_device);
+		register_syscore_ops(&palmz72_pm_syscore_ops);
+		return 0;
 	}
-	return ret;
+	return -ENODEV;
 }
 
 device_initcall(palmz72_pm_init);
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index a4af8c52d7e..fed363cec9c 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/suspend.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/irq.h>
 
 #include <asm/mach/map.h>
@@ -350,21 +350,9 @@ static struct platform_device *pxa25x_devices[] __initdata = {
 	&pxa_device_asoc_platform,
 };
 
-static struct sys_device pxa25x_sysdev[] = {
-	{
-		.cls	= &pxa_irq_sysclass,
-	}, {
-		.cls	= &pxa2xx_mfp_sysclass,
-	}, {
-		.cls	= &pxa_gpio_sysclass,
-	}, {
-		.cls	= &pxa2xx_clock_sysclass,
-	}
-};
-
 static int __init pxa25x_init(void)
 {
-	int i, ret = 0;
+	int ret = 0;
 
 	if (cpu_is_pxa25x()) {
 
@@ -377,11 +365,10 @@ static int __init pxa25x_init(void)
 
 		pxa25x_init_pm();
 
-		for (i = 0; i < ARRAY_SIZE(pxa25x_sysdev); i++) {
-			ret = sysdev_register(&pxa25x_sysdev[i]);
-			if (ret)
-				pr_err("failed to register sysdev[%d]\n", i);
-		}
+		register_syscore_ops(&pxa_irq_syscore_ops);
+		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
+		register_syscore_ops(&pxa_gpio_syscore_ops);
+		register_syscore_ops(&pxa2xx_clock_syscore_ops);
 
 		ret = platform_add_devices(pxa25x_devices,
 					   ARRAY_SIZE(pxa25x_devices));
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 909756eaf4b..2fecbec58d8 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -16,7 +16,7 @@
 #include <linux/init.h>
 #include <linux/suspend.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/i2c/pxa-i2c.h>
@@ -428,21 +428,9 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
-static struct sys_device pxa27x_sysdev[] = {
-	{
-		.cls	= &pxa_irq_sysclass,
-	}, {
-		.cls	= &pxa2xx_mfp_sysclass,
-	}, {
-		.cls	= &pxa_gpio_sysclass,
-	}, {
-		.cls	= &pxa2xx_clock_sysclass,
-	}
-};
-
 static int __init pxa27x_init(void)
 {
-	int i, ret = 0;
+	int ret = 0;
 
 	if (cpu_is_pxa27x()) {
 
@@ -455,11 +443,10 @@ static int __init pxa27x_init(void)
 
 		pxa27x_init_pm();
 
-		for (i = 0; i < ARRAY_SIZE(pxa27x_sysdev); i++) {
-			ret = sysdev_register(&pxa27x_sysdev[i]);
-			if (ret)
-				pr_err("failed to register sysdev[%d]\n", i);
-		}
+		register_syscore_ops(&pxa_irq_syscore_ops);
+		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
+		register_syscore_ops(&pxa_gpio_syscore_ops);
+		register_syscore_ops(&pxa2xx_clock_syscore_ops);
 
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 	}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 8dd10739115..8521d7d6f1d 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -20,7 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/i2c/pxa-i2c.h>
 
 #include <asm/mach/map.h>
@@ -427,21 +427,9 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
-static struct sys_device pxa3xx_sysdev[] = {
-	{
-		.cls	= &pxa_irq_sysclass,
-	}, {
-		.cls	= &pxa3xx_mfp_sysclass,
-	}, {
-		.cls	= &pxa_gpio_sysclass,
-	}, {
-		.cls	= &pxa3xx_clock_sysclass,
-	}
-};
-
 static int __init pxa3xx_init(void)
 {
-	int i, ret = 0;
+	int ret = 0;
 
 	if (cpu_is_pxa3xx()) {
 
@@ -462,11 +450,10 @@ static int __init pxa3xx_init(void)
 
 		pxa3xx_init_pm();
 
-		for (i = 0; i < ARRAY_SIZE(pxa3xx_sysdev); i++) {
-			ret = sysdev_register(&pxa3xx_sysdev[i]);
-			if (ret)
-				pr_err("failed to register sysdev[%d]\n", i);
-		}
+		register_syscore_ops(&pxa_irq_syscore_ops);
+		register_syscore_ops(&pxa3xx_mfp_syscore_ops);
+		register_syscore_ops(&pxa_gpio_syscore_ops);
+		register_syscore_ops(&pxa3xx_clock_syscore_ops);
 
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 	}
diff --git a/arch/arm/mach-pxa/pxa95x.c b/arch/arm/mach-pxa/pxa95x.c
index 23b229bd06e..ecc82a330fa 100644
--- a/arch/arm/mach-pxa/pxa95x.c
+++ b/arch/arm/mach-pxa/pxa95x.c
@@ -18,7 +18,7 @@
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/irq.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/hardware.h>
 #include <mach/gpio.h>
@@ -260,16 +260,6 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
-static struct sys_device pxa95x_sysdev[] = {
-	{
-		.cls	= &pxa_irq_sysclass,
-	}, {
-		.cls	= &pxa_gpio_sysclass,
-	}, {
-		.cls	= &pxa3xx_clock_sysclass,
-	}
-};
-
 static int __init pxa95x_init(void)
 {
 	int ret = 0, i;
@@ -293,11 +283,9 @@ static int __init pxa95x_init(void)
 		if ((ret = pxa_init_dma(IRQ_DMA, 32)))
 			return ret;
 
-		for (i = 0; i < ARRAY_SIZE(pxa95x_sysdev); i++) {
-			ret = sysdev_register(&pxa95x_sysdev[i]);
-			if (ret)
-				pr_err("failed to register sysdev[%d]\n", i);
-		}
+		register_syscore_ops(&pxa_irq_syscore_ops);
+		register_syscore_ops(&pxa_gpio_syscore_ops);
+		register_syscore_ops(&pxa3xx_clock_syscore_ops);
 
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 	}
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index cd1861351f7..d130f77b6d1 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -18,7 +18,6 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/sysdev.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-pxa/smemc.c b/arch/arm/mach-pxa/smemc.c
index 232b7316ec0..79923058d10 100644
--- a/arch/arm/mach-pxa/smemc.c
+++ b/arch/arm/mach-pxa/smemc.c
@@ -6,7 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/hardware.h>
 #include <mach/smemc.h>
@@ -16,7 +16,7 @@ static unsigned long msc[2];
 static unsigned long sxcnfg, memclkcfg;
 static unsigned long csadrcfg[4];
 
-static int pxa3xx_smemc_suspend(struct sys_device *dev, pm_message_t state)
+static int pxa3xx_smemc_suspend(void)
 {
 	msc[0] = __raw_readl(MSC0);
 	msc[1] = __raw_readl(MSC1);
@@ -30,7 +30,7 @@ static int pxa3xx_smemc_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int pxa3xx_smemc_resume(struct sys_device *dev)
+static void pxa3xx_smemc_resume(void)
 {
 	__raw_writel(msc[0], MSC0);
 	__raw_writel(msc[1], MSC1);
@@ -40,34 +40,19 @@ static int pxa3xx_smemc_resume(struct sys_device *dev)
 	__raw_writel(csadrcfg[1], CSADRCFG1);
 	__raw_writel(csadrcfg[2], CSADRCFG2);
 	__raw_writel(csadrcfg[3], CSADRCFG3);
-
-	return 0;
 }
 
-static struct sysdev_class smemc_sysclass = {
-	.name		= "smemc",
+static struct syscore_ops smemc_syscore_ops = {
 	.suspend	= pxa3xx_smemc_suspend,
 	.resume		= pxa3xx_smemc_resume,
 };
 
-static struct sys_device smemc_sysdev = {
-	.id		= 0,
-	.cls		= &smemc_sysclass,
-};
-
 static int __init smemc_init(void)
 {
-	int ret = 0;
+	if (cpu_is_pxa3xx())
+		register_syscore_ops(&smemc_syscore_ops);
 
-	if (cpu_is_pxa3xx()) {
-		ret = sysdev_class_register(&smemc_sysclass);
-		if (ret)
-			return ret;
-
-		ret = sysdev_register(&smemc_sysdev);
-	}
-
-	return ret;
+	return 0;
 }
 subsys_initcall(smemc_init);
 #endif
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index b9cfbebdfe9..687417a9369 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index b523f119e0f..903218eab56 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -44,6 +44,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/pxa25x.h>
 #include <mach/audio.h>
@@ -130,20 +131,19 @@ static u8 viper_hw_version(void)
 	return v1;
 }
 
-/* CPU sysdev */
-static int viper_cpu_suspend(struct sys_device *sysdev, pm_message_t state)
+/* CPU system core operations. */
+static int viper_cpu_suspend(void)
 {
 	viper_icr_set_bit(VIPER_ICR_R_DIS);
 	return 0;
 }
 
-static int viper_cpu_resume(struct sys_device *sysdev)
+static void viper_cpu_resume(void)
 {
 	viper_icr_clear_bit(VIPER_ICR_R_DIS);
-	return 0;
 }
 
-static struct sysdev_driver viper_cpu_sysdev_driver = {
+static struct syscore_ops viper_cpu_syscore_ops = {
 	.suspend	= viper_cpu_suspend,
 	.resume		= viper_cpu_resume,
 };
@@ -945,7 +945,7 @@ static void __init viper_init(void)
 	viper_init_vcore_gpios();
 	viper_init_cpufreq();
 
-	sysdev_driver_register(&cpu_sysdev_class, &viper_cpu_sysdev_driver);
+	register_syscore_ops(&viper_cpu_syscore_ops);
 
 	if (version) {
 		pr_info("viper: hardware v%di%d detected. "
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index f71d377c864..67bd41488bf 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -16,7 +16,6 @@
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/gpio.h>
-#include <linux/sysdev.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-s3c2410/irq.c b/arch/arm/mach-s3c2410/irq.c
index 5e2f3533205..2854129f8cc 100644
--- a/arch/arm/mach-s3c2410/irq.c
+++ b/arch/arm/mach-s3c2410/irq.c
@@ -23,38 +23,12 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <plat/cpu.h>
 #include <plat/pm.h>
 
-static int s3c2410_irq_add(struct sys_device *sysdev)
-{
-	return 0;
-}
-
-static struct sysdev_driver s3c2410_irq_driver = {
-	.add		= s3c2410_irq_add,
+struct syscore_ops s3c24xx_irq_syscore_ops = {
 	.suspend	= s3c24xx_irq_suspend,
 	.resume		= s3c24xx_irq_resume,
 };
-
-static int __init s3c2410_irq_init(void)
-{
-	return sysdev_driver_register(&s3c2410_sysclass, &s3c2410_irq_driver);
-}
-
-arch_initcall(s3c2410_irq_init);
-
-static struct sysdev_driver s3c2410a_irq_driver = {
-	.add		= s3c2410_irq_add,
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
-};
-
-static int __init s3c2410a_irq_init(void)
-{
-	return sysdev_driver_register(&s3c2410a_sysclass, &s3c2410a_irq_driver);
-}
-
-arch_initcall(s3c2410a_irq_init);
diff --git a/arch/arm/mach-s3c2410/mach-bast.c b/arch/arm/mach-s3c2410/mach-bast.c
index 2970ea9f7c2..1e2d536adda 100644
--- a/arch/arm/mach-s3c2410/mach-bast.c
+++ b/arch/arm/mach-s3c2410/mach-bast.c
@@ -17,7 +17,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/dm9000.h>
@@ -214,17 +214,16 @@ static struct s3c2410_uartcfg bast_uartcfgs[] __initdata = {
 /* NAND Flash on BAST board */
 
 #ifdef CONFIG_PM
-static int bast_pm_suspend(struct sys_device *sd, pm_message_t state)
+static int bast_pm_suspend(void)
 {
 	/* ensure that an nRESET is not generated on resume. */
 	gpio_direction_output(S3C2410_GPA(21), 1);
 	return 0;
 }
 
-static int bast_pm_resume(struct sys_device *sd)
+static void bast_pm_resume(void)
 {
 	s3c_gpio_cfgpin(S3C2410_GPA(21), S3C2410_GPA21_nRSTOUT);
-	return 0;
 }
 
 #else
@@ -232,16 +231,11 @@ static int bast_pm_resume(struct sys_device *sd)
 #define bast_pm_resume NULL
 #endif
 
-static struct sysdev_class bast_pm_sysclass = {
-	.name		= "mach-bast",
+static struct syscore_ops bast_pm_syscore_ops = {
 	.suspend	= bast_pm_suspend,
 	.resume		= bast_pm_resume,
 };
 
-static struct sys_device bast_pm_sysdev = {
-	.cls		= &bast_pm_sysclass,
-};
-
 static int smartmedia_map[] = { 0 };
 static int chip0_map[] = { 1 };
 static int chip1_map[] = { 2 };
@@ -642,8 +636,7 @@ static void __init bast_map_io(void)
 
 static void __init bast_init(void)
 {
-	sysdev_class_register(&bast_pm_sysclass);
-	sysdev_register(&bast_pm_sysdev);
+	register_syscore_ops(&bast_pm_syscore_ops);
 
 	s3c_i2c0_set_platdata(&bast_i2c_info);
 	s3c_nand_set_platdata(&bast_nand_info);
diff --git a/arch/arm/mach-s3c2410/pm.c b/arch/arm/mach-s3c2410/pm.c
index 725636fc4dc..4728f9aa7df 100644
--- a/arch/arm/mach-s3c2410/pm.c
+++ b/arch/arm/mach-s3c2410/pm.c
@@ -25,6 +25,7 @@
 #include <linux/errno.h>
 #include <linux/time.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
 
@@ -92,7 +93,7 @@ static void s3c2410_pm_prepare(void)
 	}
 }
 
-static int s3c2410_pm_resume(struct sys_device *dev)
+static void s3c2410_pm_resume(void)
 {
 	unsigned long tmp;
 
@@ -104,10 +105,12 @@ static int s3c2410_pm_resume(struct sys_device *dev)
 
 	if ( machine_is_aml_m5900() )
 		s3c2410_gpio_setpin(S3C2410_GPF(2), 0);
-
-	return 0;
 }
 
+struct syscore_ops s3c2410_pm_syscore_ops = {
+	.resume		= s3c2410_pm_resume,
+};
+
 static int s3c2410_pm_add(struct sys_device *dev)
 {
 	pm_cpu_prep = s3c2410_pm_prepare;
@@ -119,7 +122,6 @@ static int s3c2410_pm_add(struct sys_device *dev)
 #if defined(CONFIG_CPU_S3C2410)
 static struct sysdev_driver s3c2410_pm_driver = {
 	.add		= s3c2410_pm_add,
-	.resume		= s3c2410_pm_resume,
 };
 
 /* register ourselves */
@@ -133,7 +135,6 @@ arch_initcall(s3c2410_pm_drvinit);
 
 static struct sysdev_driver s3c2410a_pm_driver = {
 	.add		= s3c2410_pm_add,
-	.resume		= s3c2410_pm_resume,
 };
 
 static int __init s3c2410a_pm_drvinit(void)
@@ -147,7 +148,6 @@ arch_initcall(s3c2410a_pm_drvinit);
 #if defined(CONFIG_CPU_S3C2440)
 static struct sysdev_driver s3c2440_pm_driver = {
 	.add		= s3c2410_pm_add,
-	.resume		= s3c2410_pm_resume,
 };
 
 static int __init s3c2440_pm_drvinit(void)
@@ -161,7 +161,6 @@ arch_initcall(s3c2440_pm_drvinit);
 #if defined(CONFIG_CPU_S3C2442)
 static struct sysdev_driver s3c2442_pm_driver = {
 	.add		= s3c2410_pm_add,
-	.resume		= s3c2410_pm_resume,
 };
 
 static int __init s3c2442_pm_drvinit(void)
diff --git a/arch/arm/mach-s3c2410/s3c2410.c b/arch/arm/mach-s3c2410/s3c2410.c
index adc90a3c589..f1d3bd8f6f1 100644
--- a/arch/arm/mach-s3c2410/s3c2410.c
+++ b/arch/arm/mach-s3c2410/s3c2410.c
@@ -19,6 +19,7 @@
 #include <linux/gpio.h>
 #include <linux/clk.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
@@ -40,6 +41,7 @@
 #include <plat/devs.h>
 #include <plat/clock.h>
 #include <plat/pll.h>
+#include <plat/pm.h>
 
 #include <plat/gpio-core.h>
 #include <plat/gpio-cfg.h>
@@ -168,6 +170,9 @@ int __init s3c2410_init(void)
 {
 	printk("S3C2410: Initialising architecture\n");
 
+	register_syscore_ops(&s3c2410_pm_syscore_ops);
+	register_syscore_ops(&s3c24xx_irq_syscore_ops);
+
 	return sysdev_register(&s3c2410_sysdev);
 }
 
diff --git a/arch/arm/mach-s3c2412/irq.c b/arch/arm/mach-s3c2412/irq.c
index f3355d2ec63..1a1aa220972 100644
--- a/arch/arm/mach-s3c2412/irq.c
+++ b/arch/arm/mach-s3c2412/irq.c
@@ -202,8 +202,6 @@ static int s3c2412_irq_add(struct sys_device *sysdev)
 
 static struct sysdev_driver s3c2412_irq_driver = {
 	.add		= s3c2412_irq_add,
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
 };
 
 static int s3c2412_irq_init(void)
diff --git a/arch/arm/mach-s3c2412/mach-jive.c b/arch/arm/mach-s3c2412/mach-jive.c
index 923e01bdf01..85dcaeb9e62 100644
--- a/arch/arm/mach-s3c2412/mach-jive.c
+++ b/arch/arm/mach-s3c2412/mach-jive.c
@@ -17,7 +17,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
@@ -486,7 +486,7 @@ static struct s3c2410_udc_mach_info jive_udc_cfg __initdata = {
 /* Jive power management device */
 
 #ifdef CONFIG_PM
-static int jive_pm_suspend(struct sys_device *sd, pm_message_t state)
+static int jive_pm_suspend(void)
 {
 	/* Write the magic value u-boot uses to check for resume into
 	 * the INFORM0 register, and ensure INFORM1 is set to the
@@ -498,10 +498,9 @@ static int jive_pm_suspend(struct sys_device *sd, pm_message_t state)
 	return 0;
 }
 
-static int jive_pm_resume(struct sys_device *sd)
+static void jive_pm_resume(void)
 {
 	__raw_writel(0x0, S3C2412_INFORM0);
-	return 0;
 }
 
 #else
@@ -509,16 +508,11 @@ static int jive_pm_resume(struct sys_device *sd)
 #define jive_pm_resume NULL
 #endif
 
-static struct sysdev_class jive_pm_sysclass = {
-	.name		= "jive-pm",
+static struct syscore_ops jive_pm_syscore_ops = {
 	.suspend	= jive_pm_suspend,
 	.resume		= jive_pm_resume,
 };
 
-static struct sys_device jive_pm_sysdev = {
-	.cls		= &jive_pm_sysclass,
-};
-
 static void __init jive_map_io(void)
 {
 	s3c24xx_init_io(jive_iodesc, ARRAY_SIZE(jive_iodesc));
@@ -536,10 +530,9 @@ static void jive_power_off(void)
 
 static void __init jive_machine_init(void)
 {
-	/* register system devices for managing low level suspend */
+	/* register system core operations for managing low level suspend */
 
-	sysdev_class_register(&jive_pm_sysclass);
-	sysdev_register(&jive_pm_sysdev);
+	register_syscore_ops(&jive_pm_syscore_ops);
 
 	/* write our sleep configurations for the IO. Pull down all unused
 	 * IO, ensure that we have turned off all peripherals we do not
diff --git a/arch/arm/mach-s3c2412/pm.c b/arch/arm/mach-s3c2412/pm.c
index a7417c479ff..752b13a7b3d 100644
--- a/arch/arm/mach-s3c2412/pm.c
+++ b/arch/arm/mach-s3c2412/pm.c
@@ -17,6 +17,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 
@@ -86,13 +87,24 @@ static struct sleep_save s3c2412_sleep[] = {
 	SAVE_ITEM(S3C2413_GPJSLPCON),
 };
 
-static int s3c2412_pm_suspend(struct sys_device *dev, pm_message_t state)
+static struct sysdev_driver s3c2412_pm_driver = {
+	.add		= s3c2412_pm_add,
+};
+
+static __init int s3c2412_pm_init(void)
+{
+	return sysdev_driver_register(&s3c2412_sysclass, &s3c2412_pm_driver);
+}
+
+arch_initcall(s3c2412_pm_init);
+
+static int s3c2412_pm_suspend(void)
 {
 	s3c_pm_do_save(s3c2412_sleep, ARRAY_SIZE(s3c2412_sleep));
 	return 0;
 }
 
-static int s3c2412_pm_resume(struct sys_device *dev)
+static void s3c2412_pm_resume(void)
 {
 	unsigned long tmp;
 
@@ -102,18 +114,9 @@ static int s3c2412_pm_resume(struct sys_device *dev)
 	__raw_writel(tmp, S3C2412_PWRCFG);
 
 	s3c_pm_do_restore(s3c2412_sleep, ARRAY_SIZE(s3c2412_sleep));
-	return 0;
 }
 
-static struct sysdev_driver s3c2412_pm_driver = {
-	.add		= s3c2412_pm_add,
+struct syscore_ops s3c2412_pm_syscore_ops = {
 	.suspend	= s3c2412_pm_suspend,
 	.resume		= s3c2412_pm_resume,
 };
-
-static __init int s3c2412_pm_init(void)
-{
-	return sysdev_driver_register(&s3c2412_sysclass, &s3c2412_pm_driver);
-}
-
-arch_initcall(s3c2412_pm_init);
diff --git a/arch/arm/mach-s3c2412/s3c2412.c b/arch/arm/mach-s3c2412/s3c2412.c
index 4c6df51ddf3..ef0958d3e5c 100644
--- a/arch/arm/mach-s3c2412/s3c2412.c
+++ b/arch/arm/mach-s3c2412/s3c2412.c
@@ -19,6 +19,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
@@ -244,5 +245,8 @@ int __init s3c2412_init(void)
 {
 	printk("S3C2412: Initialising architecture\n");
 
+	register_syscore_ops(&s3c2412_pm_syscore_ops);
+	register_syscore_ops(&s3c24xx_irq_syscore_ops);
+
 	return sysdev_register(&s3c2412_sysdev);
 }
diff --git a/arch/arm/mach-s3c2416/irq.c b/arch/arm/mach-s3c2416/irq.c
index 77b38f2381c..28ad20d4244 100644
--- a/arch/arm/mach-s3c2416/irq.c
+++ b/arch/arm/mach-s3c2416/irq.c
@@ -236,8 +236,6 @@ static int __init s3c2416_irq_add(struct sys_device *sysdev)
 
 static struct sysdev_driver s3c2416_irq_driver = {
 	.add		= s3c2416_irq_add,
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
 };
 
 static int __init s3c2416_irq_init(void)
diff --git a/arch/arm/mach-s3c2416/pm.c b/arch/arm/mach-s3c2416/pm.c
index 4a04205b04d..41db2b21e21 100644
--- a/arch/arm/mach-s3c2416/pm.c
+++ b/arch/arm/mach-s3c2416/pm.c
@@ -11,6 +11,7 @@
 */
 
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -55,30 +56,26 @@ static int s3c2416_pm_add(struct sys_device *sysdev)
 	return 0;
 }
 
-static int s3c2416_pm_suspend(struct sys_device *dev, pm_message_t state)
+static struct sysdev_driver s3c2416_pm_driver = {
+	.add		= s3c2416_pm_add,
+};
+
+static __init int s3c2416_pm_init(void)
 {
-	return 0;
+	return sysdev_driver_register(&s3c2416_sysclass, &s3c2416_pm_driver);
 }
 
-static int s3c2416_pm_resume(struct sys_device *dev)
+arch_initcall(s3c2416_pm_init);
+
+
+static void s3c2416_pm_resume(void)
 {
 	/* unset the return-from-sleep amd inform flags */
 	__raw_writel(0x0, S3C2443_PWRMODE);
 	__raw_writel(0x0, S3C2412_INFORM0);
 	__raw_writel(0x0, S3C2412_INFORM1);
-
-	return 0;
 }
 
-static struct sysdev_driver s3c2416_pm_driver = {
-	.add		= s3c2416_pm_add,
-	.suspend	= s3c2416_pm_suspend,
+struct syscore_ops s3c2416_pm_syscore_ops = {
 	.resume		= s3c2416_pm_resume,
 };
-
-static __init int s3c2416_pm_init(void)
-{
-	return sysdev_driver_register(&s3c2416_sysclass, &s3c2416_pm_driver);
-}
-
-arch_initcall(s3c2416_pm_init);
diff --git a/arch/arm/mach-s3c2416/s3c2416.c b/arch/arm/mach-s3c2416/s3c2416.c
index ba7fd873743..494ce913dc9 100644
--- a/arch/arm/mach-s3c2416/s3c2416.c
+++ b/arch/arm/mach-s3c2416/s3c2416.c
@@ -32,6 +32,7 @@
 #include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 
@@ -54,6 +55,7 @@
 #include <plat/devs.h>
 #include <plat/cpu.h>
 #include <plat/sdhci.h>
+#include <plat/pm.h>
 
 #include <plat/iic-core.h>
 #include <plat/fb-core.h>
@@ -95,6 +97,9 @@ int __init s3c2416_init(void)
 
 	s3c_fb_setname("s3c2443-fb");
 
+	register_syscore_ops(&s3c2416_pm_syscore_ops);
+	register_syscore_ops(&s3c24xx_irq_syscore_ops);
+
 	return sysdev_register(&s3c2416_sysdev);
 }
 
diff --git a/arch/arm/mach-s3c2440/mach-osiris.c b/arch/arm/mach-s3c2440/mach-osiris.c
index 14dc6789775..d8853639331 100644
--- a/arch/arm/mach-s3c2440/mach-osiris.c
+++ b/arch/arm/mach-s3c2440/mach-osiris.c
@@ -17,7 +17,7 @@
 #include <linux/init.h>
 #include <linux/gpio.h>
 #include <linux/device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/serial_core.h>
 #include <linux/clk.h>
 #include <linux/i2c.h>
@@ -284,7 +284,7 @@ static struct platform_device osiris_pcmcia = {
 #ifdef CONFIG_PM
 static unsigned char pm_osiris_ctrl0;
 
-static int osiris_pm_suspend(struct sys_device *sd, pm_message_t state)
+static int osiris_pm_suspend(void)
 {
 	unsigned int tmp;
 
@@ -304,7 +304,7 @@ static int osiris_pm_suspend(struct sys_device *sd, pm_message_t state)
 	return 0;
 }
 
-static int osiris_pm_resume(struct sys_device *sd)
+static void osiris_pm_resume(void)
 {
 	if (pm_osiris_ctrl0 & OSIRIS_CTRL0_FIX8)
 		__raw_writeb(OSIRIS_CTRL1_FIX8, OSIRIS_VA_CTRL1);
@@ -312,8 +312,6 @@ static int osiris_pm_resume(struct sys_device *sd)
 	__raw_writeb(pm_osiris_ctrl0, OSIRIS_VA_CTRL0);
 
 	s3c_gpio_cfgpin(S3C2410_GPA(21), S3C2410_GPA21_nRSTOUT);
-
-	return 0;
 }
 
 #else
@@ -321,16 +319,11 @@ static int osiris_pm_resume(struct sys_device *sd)
 #define osiris_pm_resume NULL
 #endif
 
-static struct sysdev_class osiris_pm_sysclass = {
-	.name		= "mach-osiris",
+static struct syscore_ops osiris_pm_syscore_ops = {
 	.suspend	= osiris_pm_suspend,
 	.resume		= osiris_pm_resume,
 };
 
-static struct sys_device osiris_pm_sysdev = {
-	.cls		= &osiris_pm_sysclass,
-};
-
 /* Link for DVS driver to TPS65011 */
 
 static void osiris_tps_release(struct device *dev)
@@ -439,8 +432,7 @@ static void __init osiris_map_io(void)
 
 static void __init osiris_init(void)
 {
-	sysdev_class_register(&osiris_pm_sysclass);
-	sysdev_register(&osiris_pm_sysdev);
+	register_syscore_ops(&osiris_pm_syscore_ops);
 
 	s3c_i2c0_set_platdata(NULL);
 	s3c_nand_set_platdata(&osiris_nand_info);
diff --git a/arch/arm/mach-s3c2440/s3c2440.c b/arch/arm/mach-s3c2440/s3c2440.c
index f7663f731ea..ce99ff72838 100644
--- a/arch/arm/mach-s3c2440/s3c2440.c
+++ b/arch/arm/mach-s3c2440/s3c2440.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/gpio.h>
 #include <linux/clk.h>
 #include <linux/io.h>
@@ -33,6 +34,7 @@
 #include <plat/devs.h>
 #include <plat/cpu.h>
 #include <plat/s3c244x.h>
+#include <plat/pm.h>
 
 #include <plat/gpio-core.h>
 #include <plat/gpio-cfg.h>
@@ -51,6 +53,12 @@ int __init s3c2440_init(void)
 	s3c_device_wdt.resource[1].start = IRQ_S3C2440_WDT;
 	s3c_device_wdt.resource[1].end   = IRQ_S3C2440_WDT;
 
+	/* register suspend/resume handlers */
+
+	register_syscore_ops(&s3c2410_pm_syscore_ops);
+	register_syscore_ops(&s3c244x_pm_syscore_ops);
+	register_syscore_ops(&s3c24xx_irq_syscore_ops);
+
 	/* register our system device for everything else */
 
 	return sysdev_register(&s3c2440_sysdev);
diff --git a/arch/arm/mach-s3c2440/s3c2442.c b/arch/arm/mach-s3c2440/s3c2442.c
index ecf81354655..6224bad4d60 100644
--- a/arch/arm/mach-s3c2440/s3c2442.c
+++ b/arch/arm/mach-s3c2440/s3c2442.c
@@ -29,6 +29,7 @@
 #include <linux/err.h>
 #include <linux/device.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/mutex.h>
@@ -45,6 +46,7 @@
 #include <plat/clock.h>
 #include <plat/cpu.h>
 #include <plat/s3c244x.h>
+#include <plat/pm.h>
 
 #include <plat/gpio-core.h>
 #include <plat/gpio-cfg.h>
@@ -167,6 +169,10 @@ int __init s3c2442_init(void)
 {
 	printk("S3C2442: Initialising architecture\n");
 
+	register_syscore_ops(&s3c2410_pm_syscore_ops);
+	register_syscore_ops(&s3c244x_pm_syscore_ops);
+	register_syscore_ops(&s3c24xx_irq_syscore_ops);
+
 	return sysdev_register(&s3c2442_sysdev);
 }
 
diff --git a/arch/arm/mach-s3c2440/s3c244x-irq.c b/arch/arm/mach-s3c2440/s3c244x-irq.c
index de07c2feaa3..c63e8f26d90 100644
--- a/arch/arm/mach-s3c2440/s3c244x-irq.c
+++ b/arch/arm/mach-s3c2440/s3c244x-irq.c
@@ -116,8 +116,6 @@ static int s3c244x_irq_add(struct sys_device *sysdev)
 
 static struct sysdev_driver s3c2440_irq_driver = {
 	.add		= s3c244x_irq_add,
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
 };
 
 static int s3c2440_irq_init(void)
@@ -129,8 +127,6 @@ arch_initcall(s3c2440_irq_init);
 
 static struct sysdev_driver s3c2442_irq_driver = {
 	.add		= s3c244x_irq_add,
-	.suspend	= s3c24xx_irq_suspend,
-	.resume		= s3c24xx_irq_resume,
 };
 
 
diff --git a/arch/arm/mach-s3c2440/s3c244x.c b/arch/arm/mach-s3c2440/s3c244x.c
index 90c1707b9c9..7e8a23d2098 100644
--- a/arch/arm/mach-s3c2440/s3c244x.c
+++ b/arch/arm/mach-s3c2440/s3c244x.c
@@ -19,6 +19,7 @@
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 
@@ -134,45 +135,14 @@ void __init s3c244x_init_clocks(int xtal)
 	s3c2410_baseclk_add();
 }
 
-#ifdef CONFIG_PM
-
-static struct sleep_save s3c244x_sleep[] = {
-	SAVE_ITEM(S3C2440_DSC0),
-	SAVE_ITEM(S3C2440_DSC1),
-	SAVE_ITEM(S3C2440_GPJDAT),
-	SAVE_ITEM(S3C2440_GPJCON),
-	SAVE_ITEM(S3C2440_GPJUP)
-};
-
-static int s3c244x_suspend(struct sys_device *dev, pm_message_t state)
-{
-	s3c_pm_do_save(s3c244x_sleep, ARRAY_SIZE(s3c244x_sleep));
-	return 0;
-}
-
-static int s3c244x_resume(struct sys_device *dev)
-{
-	s3c_pm_do_restore(s3c244x_sleep, ARRAY_SIZE(s3c244x_sleep));
-	return 0;
-}
-
-#else
-#define s3c244x_suspend NULL
-#define s3c244x_resume  NULL
-#endif
-
 /* Since the S3C2442 and S3C2440 share  items, put both sysclasses here */
 
 struct sysdev_class s3c2440_sysclass = {
 	.name		= "s3c2440-core",
-	.suspend	= s3c244x_suspend,
-	.resume		= s3c244x_resume
 };
 
 struct sysdev_class s3c2442_sysclass = {
 	.name		= "s3c2442-core",
-	.suspend	= s3c244x_suspend,
-	.resume		= s3c244x_resume
 };
 
 /* need to register class before we actually register the device, and
@@ -194,3 +164,33 @@ static int __init s3c2442_core_init(void)
 }
 
 core_initcall(s3c2442_core_init);
+
+
+#ifdef CONFIG_PM
+static struct sleep_save s3c244x_sleep[] = {
+	SAVE_ITEM(S3C2440_DSC0),
+	SAVE_ITEM(S3C2440_DSC1),
+	SAVE_ITEM(S3C2440_GPJDAT),
+	SAVE_ITEM(S3C2440_GPJCON),
+	SAVE_ITEM(S3C2440_GPJUP)
+};
+
+static int s3c244x_suspend(void)
+{
+	s3c_pm_do_save(s3c244x_sleep, ARRAY_SIZE(s3c244x_sleep));
+	return 0;
+}
+
+static void s3c244x_resume(void)
+{
+	s3c_pm_do_restore(s3c244x_sleep, ARRAY_SIZE(s3c244x_sleep));
+}
+#else
+#define s3c244x_suspend NULL
+#define s3c244x_resume  NULL
+#endif
+
+struct syscore_ops s3c244x_pm_syscore_ops = {
+	.suspend	= s3c244x_suspend,
+	.resume		= s3c244x_resume,
+};
diff --git a/arch/arm/mach-s3c64xx/irq-pm.c b/arch/arm/mach-s3c64xx/irq-pm.c
index da1bec64b9d..8bec61e242c 100644
--- a/arch/arm/mach-s3c64xx/irq-pm.c
+++ b/arch/arm/mach-s3c64xx/irq-pm.c
@@ -13,7 +13,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/serial_core.h>
 #include <linux/irq.h>
@@ -54,7 +54,7 @@ static struct irq_grp_save {
 
 static u32 irq_uart_mask[CONFIG_SERIAL_SAMSUNG_UARTS];
 
-static int s3c64xx_irq_pm_suspend(struct sys_device *dev, pm_message_t state)
+static int s3c64xx_irq_pm_suspend(void)
 {
 	struct irq_grp_save *grp = eint_grp_save;
 	int i;
@@ -75,7 +75,7 @@ static int s3c64xx_irq_pm_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int s3c64xx_irq_pm_resume(struct sys_device *dev)
+static void s3c64xx_irq_pm_resume(void)
 {
 	struct irq_grp_save *grp = eint_grp_save;
 	int i;
@@ -94,18 +94,18 @@ static int s3c64xx_irq_pm_resume(struct sys_device *dev)
 	}
 
 	S3C_PMDBG("%s: IRQ configuration restored\n", __func__);
-	return 0;
 }
 
-static struct sysdev_driver s3c64xx_irq_driver = {
+struct syscore_ops s3c64xx_irq_syscore_ops = {
 	.suspend = s3c64xx_irq_pm_suspend,
 	.resume	 = s3c64xx_irq_pm_resume,
 };
 
-static int __init s3c64xx_irq_pm_init(void)
+static __init int s3c64xx_syscore_init(void)
 {
-	return sysdev_driver_register(&s3c64xx_sysclass, &s3c64xx_irq_driver);
-}
+	register_syscore_ops(&s3c64xx_irq_syscore_ops);
 
-arch_initcall(s3c64xx_irq_pm_init);
+	return 0;
+}
 
+core_initcall(s3c64xx_syscore_init);
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 549d7924fd4..24febae3d4c 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -16,6 +16,7 @@
 
 #include <linux/init.h>
 #include <linux/suspend.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 
 #include <plat/cpu.h>
@@ -140,7 +141,17 @@ static int s5pv210_pm_add(struct sys_device *sysdev)
 	return 0;
 }
 
-static int s5pv210_pm_resume(struct sys_device *dev)
+static struct sysdev_driver s5pv210_pm_driver = {
+	.add		= s5pv210_pm_add,
+};
+
+static __init int s5pv210_pm_drvinit(void)
+{
+	return sysdev_driver_register(&s5pv210_sysclass, &s5pv210_pm_driver);
+}
+arch_initcall(s5pv210_pm_drvinit);
+
+static void s5pv210_pm_resume(void)
 {
 	u32 tmp;
 
@@ -150,17 +161,15 @@ static int s5pv210_pm_resume(struct sys_device *dev)
 	__raw_writel(tmp , S5P_OTHERS);
 
 	s3c_pm_do_restore_core(s5pv210_core_save, ARRAY_SIZE(s5pv210_core_save));
-
-	return 0;
 }
 
-static struct sysdev_driver s5pv210_pm_driver = {
-	.add		= s5pv210_pm_add,
+static struct syscore_ops s5pv210_pm_syscore_ops = {
 	.resume		= s5pv210_pm_resume,
 };
 
-static __init int s5pv210_pm_drvinit(void)
+static __init int s5pv210_pm_syscore_init(void)
 {
-	return sysdev_driver_register(&s5pv210_sysclass, &s5pv210_pm_driver);
+	register_syscore_ops(&s5pv210_pm_syscore_ops);
+	return 0;
 }
-arch_initcall(s5pv210_pm_drvinit);
+arch_initcall(s5pv210_pm_syscore_init);
diff --git a/arch/arm/mach-sa1100/irq.c b/arch/arm/mach-sa1100/irq.c
index 423ddb3d65e..dfbf824a69f 100644
--- a/arch/arm/mach-sa1100/irq.c
+++ b/arch/arm/mach-sa1100/irq.c
@@ -14,7 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/ioport.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <mach/hardware.h>
 #include <asm/mach/irq.h>
@@ -234,7 +234,7 @@ static struct sa1100irq_state {
 	unsigned int	iccr;
 } sa1100irq_state;
 
-static int sa1100irq_suspend(struct sys_device *dev, pm_message_t state)
+static int sa1100irq_suspend(void)
 {
 	struct sa1100irq_state *st = &sa1100irq_state;
 
@@ -264,7 +264,7 @@ static int sa1100irq_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int sa1100irq_resume(struct sys_device *dev)
+static void sa1100irq_resume(void)
 {
 	struct sa1100irq_state *st = &sa1100irq_state;
 
@@ -277,24 +277,17 @@ static int sa1100irq_resume(struct sys_device *dev)
 
 		ICMR = st->icmr;
 	}
-	return 0;
 }
 
-static struct sysdev_class sa1100irq_sysclass = {
-	.name		= "sa11x0-irq",
+static struct syscore_ops sa1100irq_syscore_ops = {
 	.suspend	= sa1100irq_suspend,
 	.resume		= sa1100irq_resume,
 };
 
-static struct sys_device sa1100irq_device = {
-	.id		= 0,
-	.cls		= &sa1100irq_sysclass,
-};
-
 static int __init sa1100irq_init_devicefs(void)
 {
-	sysdev_class_register(&sa1100irq_sysclass);
-	return sysdev_register(&sa1100irq_device);
+	register_syscore_ops(&sa1100irq_syscore_ops);
+	return 0;
 }
 
 device_initcall(sa1100irq_init_devicefs);
diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c
index 94912d3944d..2d1b67a59e4 100644
--- a/arch/arm/mach-shmobile/pm_runtime.c
+++ b/arch/arm/mach-shmobile/pm_runtime.c
@@ -18,152 +18,41 @@
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
 #include <linux/bitmap.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_PM_RUNTIME
-#define BIT_ONCE 0
-#define BIT_ACTIVE 1
-#define BIT_CLK_ENABLED 2
 
-struct pm_runtime_data {
-	unsigned long flags;
-	struct clk *clk;
-};
-
-static void __devres_release(struct device *dev, void *res)
-{
-	struct pm_runtime_data *prd = res;
-
-	dev_dbg(dev, "__devres_release()\n");
-
-	if (test_bit(BIT_CLK_ENABLED, &prd->flags))
-		clk_disable(prd->clk);
-
-	if (test_bit(BIT_ACTIVE, &prd->flags))
-		clk_put(prd->clk);
-}
-
-static struct pm_runtime_data *__to_prd(struct device *dev)
-{
-	return devres_find(dev, __devres_release, NULL, NULL);
-}
-
-static void platform_pm_runtime_init(struct device *dev,
-				     struct pm_runtime_data *prd)
-{
-	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) {
-		prd->clk = clk_get(dev, NULL);
-		if (!IS_ERR(prd->clk)) {
-			set_bit(BIT_ACTIVE, &prd->flags);
-			dev_info(dev, "clocks managed by runtime pm\n");
-		}
-	}
-}
-
-static void platform_pm_runtime_bug(struct device *dev,
-				    struct pm_runtime_data *prd)
-{
-	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags))
-		dev_err(dev, "runtime pm suspend before resume\n");
-}
-
-int platform_pm_runtime_suspend(struct device *dev)
-{
-	struct pm_runtime_data *prd = __to_prd(dev);
-
-	dev_dbg(dev, "platform_pm_runtime_suspend()\n");
-
-	platform_pm_runtime_bug(dev, prd);
-
-	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
-		clk_disable(prd->clk);
-		clear_bit(BIT_CLK_ENABLED, &prd->flags);
-	}
-
-	return 0;
-}
-
-int platform_pm_runtime_resume(struct device *dev)
-{
-	struct pm_runtime_data *prd = __to_prd(dev);
-
-	dev_dbg(dev, "platform_pm_runtime_resume()\n");
-
-	platform_pm_runtime_init(dev, prd);
-
-	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
-		clk_enable(prd->clk);
-		set_bit(BIT_CLK_ENABLED, &prd->flags);
-	}
-
-	return 0;
-}
-
-int platform_pm_runtime_idle(struct device *dev)
+static int default_platform_runtime_idle(struct device *dev)
 {
 	/* suspend synchronously to disable clocks immediately */
 	return pm_runtime_suspend(dev);
 }
 
-static int platform_bus_notify(struct notifier_block *nb,
-			       unsigned long action, void *data)
-{
-	struct device *dev = data;
-	struct pm_runtime_data *prd;
-
-	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
-
-	if (action == BUS_NOTIFY_BIND_DRIVER) {
-		prd = devres_alloc(__devres_release, sizeof(*prd), GFP_KERNEL);
-		if (prd)
-			devres_add(dev, prd);
-		else
-			dev_err(dev, "unable to alloc memory for runtime pm\n");
-	}
-
-	return 0;
-}
-
-#else /* CONFIG_PM_RUNTIME */
-
-static int platform_bus_notify(struct notifier_block *nb,
-			       unsigned long action, void *data)
-{
-	struct device *dev = data;
-	struct clk *clk;
+static struct dev_power_domain default_power_domain = {
+	.ops = {
+		.runtime_suspend = pm_runtime_clk_suspend,
+		.runtime_resume = pm_runtime_clk_resume,
+		.runtime_idle = default_platform_runtime_idle,
+		USE_PLATFORM_PM_SLEEP_OPS
+	},
+};
 
-	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
+#define DEFAULT_PWR_DOMAIN_PTR	(&default_power_domain)
 
-	switch (action) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		clk = clk_get(dev, NULL);
-		if (!IS_ERR(clk)) {
-			clk_enable(clk);
-			clk_put(clk);
-			dev_info(dev, "runtime pm disabled, clock forced on\n");
-		}
-		break;
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		clk = clk_get(dev, NULL);
-		if (!IS_ERR(clk)) {
-			clk_disable(clk);
-			clk_put(clk);
-			dev_info(dev, "runtime pm disabled, clock forced off\n");
-		}
-		break;
-	}
+#else
 
-	return 0;
-}
+#define DEFAULT_PWR_DOMAIN_PTR	NULL
 
 #endif /* CONFIG_PM_RUNTIME */
 
-static struct notifier_block platform_bus_notifier = {
-	.notifier_call = platform_bus_notify
+static struct pm_clk_notifier_block platform_bus_notifier = {
+	.pwr_domain = DEFAULT_PWR_DOMAIN_PTR,
+	.con_ids = { NULL, },
 };
 
 static int __init sh_pm_runtime_init(void)
 {
-	bus_register_notifier(&platform_bus_type, &platform_bus_notifier);
+	pm_runtime_clk_add_notifier(&platform_bus_type, &platform_bus_notifier);
 	return 0;
 }
 core_initcall(sh_pm_runtime_init);
diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c
index d2adcdda23c..bd9e32187ea 100644
--- a/arch/arm/plat-omap/gpio.c
+++ b/arch/arm/plat-omap/gpio.c
@@ -17,7 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
@@ -1372,9 +1372,7 @@ static const struct dev_pm_ops omap_mpuio_dev_pm_ops = {
 	.resume_noirq = omap_mpuio_resume_noirq,
 };
 
-/* use platform_driver for this, now that there's no longer any
- * point to sys_device (other than not disturbing old code).
- */
+/* use platform_driver for this. */
 static struct platform_driver omap_mpuio_driver = {
 	.driver		= {
 		.name	= "mpuio",
@@ -1745,7 +1743,7 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
 }
 
 #if defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP2PLUS)
-static int omap_gpio_suspend(struct sys_device *dev, pm_message_t mesg)
+static int omap_gpio_suspend(void)
 {
 	int i;
 
@@ -1795,12 +1793,12 @@ static int omap_gpio_suspend(struct sys_device *dev, pm_message_t mesg)
 	return 0;
 }
 
-static int omap_gpio_resume(struct sys_device *dev)
+static void omap_gpio_resume(void)
 {
 	int i;
 
 	if (!cpu_class_is_omap2() && !cpu_is_omap16xx())
-		return 0;
+		return;
 
 	for (i = 0; i < gpio_bank_count; i++) {
 		struct gpio_bank *bank = &gpio_bank[i];
@@ -1836,21 +1834,13 @@ static int omap_gpio_resume(struct sys_device *dev)
 		__raw_writel(bank->saved_wakeup, wake_set);
 		spin_unlock_irqrestore(&bank->lock, flags);
 	}
-
-	return 0;
 }
 
-static struct sysdev_class omap_gpio_sysclass = {
-	.name		= "gpio",
+static struct syscore_ops omap_gpio_syscore_ops = {
 	.suspend	= omap_gpio_suspend,
 	.resume		= omap_gpio_resume,
 };
 
-static struct sys_device omap_gpio_device = {
-	.id		= 0,
-	.cls		= &omap_gpio_sysclass,
-};
-
 #endif
 
 #ifdef CONFIG_ARCH_OMAP2PLUS
@@ -2108,21 +2098,14 @@ postcore_initcall(omap_gpio_drv_reg);
 
 static int __init omap_gpio_sysinit(void)
 {
-	int ret = 0;
-
 	mpuio_init();
 
 #if defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP2PLUS)
-	if (cpu_is_omap16xx() || cpu_class_is_omap2()) {
-		if (ret == 0) {
-			ret = sysdev_class_register(&omap_gpio_sysclass);
-			if (ret == 0)
-				ret = sysdev_register(&omap_gpio_device);
-		}
-	}
+	if (cpu_is_omap16xx() || cpu_class_is_omap2())
+		register_syscore_ops(&omap_gpio_syscore_ops);
 #endif
 
-	return ret;
+	return 0;
 }
 
 arch_initcall(omap_gpio_sysinit);
diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c
index 9bbda9acb73..a37b8eb65b7 100644
--- a/arch/arm/plat-omap/omap_device.c
+++ b/arch/arm/plat-omap/omap_device.c
@@ -536,6 +536,28 @@ int omap_early_device_register(struct omap_device *od)
 	return 0;
 }
 
+static int _od_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+
+	return omap_device_idle(pdev);
+}
+
+static int _od_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+
+	return omap_device_enable(pdev);
+}
+
+static struct dev_power_domain omap_device_power_domain = {
+	.ops = {
+		.runtime_suspend = _od_runtime_suspend,
+		.runtime_resume = _od_runtime_resume,
+		USE_PLATFORM_PM_SLEEP_OPS
+	}
+};
+
 /**
  * omap_device_register - register an omap_device with one omap_hwmod
  * @od: struct omap_device * to register
@@ -549,6 +571,7 @@ int omap_device_register(struct omap_device *od)
 	pr_debug("omap_device: %s: registering\n", od->pdev.name);
 
 	od->pdev.dev.parent = &omap_device_parent;
+	od->pdev.dev.pwr_domain = &omap_device_power_domain;
 	return platform_device_register(&od->pdev);
 }
 
diff --git a/arch/arm/plat-pxa/gpio.c b/arch/arm/plat-pxa/gpio.c
index dce088f4567..48ebb9479b6 100644
--- a/arch/arm/plat-pxa/gpio.c
+++ b/arch/arm/plat-pxa/gpio.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/slab.h>
 
 #include <mach/gpio.h>
@@ -295,7 +295,7 @@ void __init pxa_init_gpio(int mux_irq, int start, int end, set_wake_t fn)
 }
 
 #ifdef CONFIG_PM
-static int pxa_gpio_suspend(struct sys_device *dev, pm_message_t state)
+static int pxa_gpio_suspend(void)
 {
 	struct pxa_gpio_chip *c;
 	int gpio;
@@ -312,7 +312,7 @@ static int pxa_gpio_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int pxa_gpio_resume(struct sys_device *dev)
+static void pxa_gpio_resume(void)
 {
 	struct pxa_gpio_chip *c;
 	int gpio;
@@ -326,22 +326,13 @@ static int pxa_gpio_resume(struct sys_device *dev)
 		__raw_writel(c->saved_gfer, c->regbase + GFER_OFFSET);
 		__raw_writel(c->saved_gpdr, c->regbase + GPDR_OFFSET);
 	}
-	return 0;
 }
 #else
 #define pxa_gpio_suspend	NULL
 #define pxa_gpio_resume		NULL
 #endif
 
-struct sysdev_class pxa_gpio_sysclass = {
-	.name		= "gpio",
+struct syscore_ops pxa_gpio_syscore_ops = {
 	.suspend	= pxa_gpio_suspend,
 	.resume		= pxa_gpio_resume,
 };
-
-static int __init pxa_gpio_init(void)
-{
-	return sysdev_class_register(&pxa_gpio_sysclass);
-}
-
-core_initcall(pxa_gpio_init);
diff --git a/arch/arm/plat-pxa/mfp.c b/arch/arm/plat-pxa/mfp.c
index a9aa5ad3f4e..be12eadcce2 100644
--- a/arch/arm/plat-pxa/mfp.c
+++ b/arch/arm/plat-pxa/mfp.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/sysdev.h>
 
 #include <plat/mfp.h>
 
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 27ea852e337..c10d10c56e2 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/io.h>
@@ -1195,19 +1195,12 @@ int s3c2410_dma_getposition(unsigned int channel, dma_addr_t *src, dma_addr_t *d
 
 EXPORT_SYMBOL(s3c2410_dma_getposition);
 
-static inline struct s3c2410_dma_chan *to_dma_chan(struct sys_device *dev)
-{
-	return container_of(dev, struct s3c2410_dma_chan, dev);
-}
-
-/* system device class */
+/* system core operations */
 
 #ifdef CONFIG_PM
 
-static int s3c2410_dma_suspend(struct sys_device *dev, pm_message_t state)
+static void s3c2410_dma_suspend_chan(s3c2410_dma_chan *cp)
 {
-	struct s3c2410_dma_chan *cp = to_dma_chan(dev);
-
 	printk(KERN_DEBUG "suspending dma channel %d\n", cp->number);
 
 	if (dma_rdreg(cp, S3C2410_DMA_DMASKTRIG) & S3C2410_DMASKTRIG_ON) {
@@ -1222,13 +1215,21 @@ static int s3c2410_dma_suspend(struct sys_device *dev, pm_message_t state)
 
 		s3c2410_dma_dostop(cp);
 	}
+}
+
+static int s3c2410_dma_suspend(void)
+{
+	struct s3c2410_dma_chan *cp = s3c2410_chans;
+	int channel;
+
+	for (channel = 0; channel < dma_channels; cp++, channel++)
+		s3c2410_dma_suspend_chan(cp);
 
 	return 0;
 }
 
-static int s3c2410_dma_resume(struct sys_device *dev)
+static void s3c2410_dma_resume_chan(struct s3c2410_dma_chan *cp)
 {
-	struct s3c2410_dma_chan *cp = to_dma_chan(dev);
 	unsigned int no = cp->number | DMACH_LOW_LEVEL;
 
 	/* restore channel's hardware configuration */
@@ -1249,13 +1250,21 @@ static int s3c2410_dma_resume(struct sys_device *dev)
 	return 0;
 }
 
+static void s3c2410_dma_resume(void)
+{
+	struct s3c2410_dma_chan *cp = s3c2410_chans + dma_channels - 1;
+	int channel;
+
+	for (channel = dma_channels - 1; channel >= 0; cp++, channel--)
+		s3c2410_dma_resume_chan(cp);
+}
+
 #else
 #define s3c2410_dma_suspend NULL
 #define s3c2410_dma_resume  NULL
 #endif /* CONFIG_PM */
 
-struct sysdev_class dma_sysclass = {
-	.name		= "s3c24xx-dma",
+struct syscore_ops dma_syscore_ops = {
 	.suspend	= s3c2410_dma_suspend,
 	.resume		= s3c2410_dma_resume,
 };
@@ -1269,39 +1278,14 @@ static void s3c2410_dma_cache_ctor(void *p)
 
 /* initialisation code */
 
-static int __init s3c24xx_dma_sysclass_init(void)
+static int __init s3c24xx_dma_syscore_init(void)
 {
-	int ret = sysdev_class_register(&dma_sysclass);
-
-	if (ret != 0)
-		printk(KERN_ERR "dma sysclass registration failed\n");
-
-	return ret;
-}
-
-core_initcall(s3c24xx_dma_sysclass_init);
-
-static int __init s3c24xx_dma_sysdev_register(void)
-{
-	struct s3c2410_dma_chan *cp = s3c2410_chans;
-	int channel, ret;
-
-	for (channel = 0; channel < dma_channels; cp++, channel++) {
-		cp->dev.cls = &dma_sysclass;
-		cp->dev.id  = channel;
-		ret = sysdev_register(&cp->dev);
-
-		if (ret) {
-			printk(KERN_ERR "error registering dev for dma %d\n",
-			       channel);
- 			return ret;
-		}
-	}
+	register_syscore_ops(&dma_syscore_ops);
 
 	return 0;
 }
 
-late_initcall(s3c24xx_dma_sysdev_register);
+late_initcall(s3c24xx_dma_syscore_init);
 
 int __init s3c24xx_dma_init(unsigned int channels, unsigned int irq,
 			    unsigned int stride)
diff --git a/arch/arm/plat-s3c24xx/irq-pm.c b/arch/arm/plat-s3c24xx/irq-pm.c
index c3624d89863..0efb2e2848c 100644
--- a/arch/arm/plat-s3c24xx/irq-pm.c
+++ b/arch/arm/plat-s3c24xx/irq-pm.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
 #include <linux/irq.h>
 
 #include <plat/cpu.h>
@@ -65,7 +64,7 @@ static unsigned long save_extint[3];
 static unsigned long save_eintflt[4];
 static unsigned long save_eintmask;
 
-int s3c24xx_irq_suspend(struct sys_device *dev, pm_message_t state)
+int s3c24xx_irq_suspend(void)
 {
 	unsigned int i;
 
@@ -81,7 +80,7 @@ int s3c24xx_irq_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-int s3c24xx_irq_resume(struct sys_device *dev)
+void s3c24xx_irq_resume(void)
 {
 	unsigned int i;
 
@@ -93,6 +92,4 @@ int s3c24xx_irq_resume(struct sys_device *dev)
 
 	s3c_pm_do_restore(irq_save, ARRAY_SIZE(irq_save));
 	__raw_writel(save_eintmask, S3C24XX_EINTMASK);
-
-	return 0;
 }
diff --git a/arch/arm/plat-s5p/irq-pm.c b/arch/arm/plat-s5p/irq-pm.c
index 5259ad458bc..327acb3a446 100644
--- a/arch/arm/plat-s5p/irq-pm.c
+++ b/arch/arm/plat-s5p/irq-pm.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
 
 #include <plat/cpu.h>
 #include <plat/irqs.h>
@@ -77,17 +76,15 @@ static struct sleep_save eint_save[] = {
 	SAVE_ITEM(S5P_EINT_MASK(3)),
 };
 
-int s3c24xx_irq_suspend(struct sys_device *dev, pm_message_t state)
+int s3c24xx_irq_suspend(void)
 {
 	s3c_pm_do_save(eint_save, ARRAY_SIZE(eint_save));
 
 	return 0;
 }
 
-int s3c24xx_irq_resume(struct sys_device *dev)
+void s3c24xx_irq_resume(void)
 {
 	s3c_pm_do_restore(eint_save, ARRAY_SIZE(eint_save));
-
-	return 0;
 }
 
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index cedfff51c82..3aedac0034b 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -68,6 +68,12 @@ extern void s3c24xx_init_uartdevs(char *name,
 struct sys_timer;
 extern struct sys_timer s3c24xx_timer;
 
+extern struct syscore_ops s3c2410_pm_syscore_ops;
+extern struct syscore_ops s3c2412_pm_syscore_ops;
+extern struct syscore_ops s3c2416_pm_syscore_ops;
+extern struct syscore_ops s3c244x_pm_syscore_ops;
+extern struct syscore_ops s3c64xx_irq_syscore_ops;
+
 /* system device classes */
 
 extern struct sysdev_class s3c2410_sysclass;
diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h
index 937cc2ace51..7fb6f6be8c8 100644
--- a/arch/arm/plat-samsung/include/plat/pm.h
+++ b/arch/arm/plat-samsung/include/plat/pm.h
@@ -103,14 +103,16 @@ extern void s3c_pm_do_restore_core(struct sleep_save *ptr, int count);
 
 #ifdef CONFIG_PM
 extern int s3c_irqext_wake(struct irq_data *data, unsigned int state);
-extern int s3c24xx_irq_suspend(struct sys_device *dev, pm_message_t state);
-extern int s3c24xx_irq_resume(struct sys_device *dev);
+extern int s3c24xx_irq_suspend(void);
+extern void s3c24xx_irq_resume(void);
 #else
 #define s3c_irqext_wake NULL
 #define s3c24xx_irq_suspend NULL
 #define s3c24xx_irq_resume  NULL
 #endif
 
+extern struct syscore_ops s3c24xx_irq_syscore_ops;
+
 /* PM debug functions */
 
 #ifdef CONFIG_SAMSUNG_PM_DEBUG
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index f74695075e6..f25e7ec8941 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -398,9 +398,9 @@ static void vfp_enable(void *unused)
 }
 
 #ifdef CONFIG_PM
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
-static int vfp_pm_suspend(struct sys_device *dev, pm_message_t state)
+static int vfp_pm_suspend(void)
 {
 	struct thread_info *ti = current_thread_info();
 	u32 fpexc = fmrx(FPEXC);
@@ -420,34 +420,25 @@ static int vfp_pm_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int vfp_pm_resume(struct sys_device *dev)
+static void vfp_pm_resume(void)
 {
 	/* ensure we have access to the vfp */
 	vfp_enable(NULL);
 
 	/* and disable it to ensure the next usage restores the state */
 	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
-
-	return 0;
 }
 
-static struct sysdev_class vfp_pm_sysclass = {
-	.name		= "vfp",
+static struct syscore_ops vfp_pm_syscore_ops = {
 	.suspend	= vfp_pm_suspend,
 	.resume		= vfp_pm_resume,
 };
 
-static struct sys_device vfp_pm_sysdev = {
-	.cls	= &vfp_pm_sysclass,
-};
-
 static void vfp_pm_init(void)
 {
-	sysdev_class_register(&vfp_pm_sysclass);
-	sysdev_register(&vfp_pm_sysdev);
+	register_syscore_ops(&vfp_pm_syscore_ops);
 }
 
-
 #else
 static inline void vfp_pm_init(void) { }
 #endif /* CONFIG_PM */
diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c
index 21ce35f33aa..3e3646186c9 100644
--- a/arch/avr32/mach-at32ap/intc.c
+++ b/arch/avr32/mach-at32ap/intc.c
@@ -12,7 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/platform_device.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/io.h>
 
@@ -21,7 +21,6 @@
 struct intc {
 	void __iomem		*regs;
 	struct irq_chip		chip;
-	struct sys_device	sysdev;
 #ifdef CONFIG_PM
 	unsigned long		suspend_ipr;
 	unsigned long		saved_ipr[64];
@@ -146,9 +145,8 @@ void intc_set_suspend_handler(unsigned long offset)
 	intc0.suspend_ipr = offset;
 }
 
-static int intc_suspend(struct sys_device *sdev, pm_message_t state)
+static int intc_suspend(void)
 {
-	struct intc *intc = container_of(sdev, struct intc, sysdev);
 	int i;
 
 	if (unlikely(!irqs_disabled())) {
@@ -156,28 +154,25 @@ static int intc_suspend(struct sys_device *sdev, pm_message_t state)
 		return -EINVAL;
 	}
 
-	if (unlikely(!intc->suspend_ipr)) {
+	if (unlikely(!intc0.suspend_ipr)) {
 		pr_err("intc_suspend: suspend_ipr not initialized\n");
 		return -EINVAL;
 	}
 
 	for (i = 0; i < 64; i++) {
-		intc->saved_ipr[i] = intc_readl(intc, INTPR0 + 4 * i);
-		intc_writel(intc, INTPR0 + 4 * i, intc->suspend_ipr);
+		intc0.saved_ipr[i] = intc_readl(&intc0, INTPR0 + 4 * i);
+		intc_writel(&intc0, INTPR0 + 4 * i, intc0.suspend_ipr);
 	}
 
 	return 0;
 }
 
-static int intc_resume(struct sys_device *sdev)
+static int intc_resume(void)
 {
-	struct intc *intc = container_of(sdev, struct intc, sysdev);
 	int i;
 
-	WARN_ON(!irqs_disabled());
-
 	for (i = 0; i < 64; i++)
-		intc_writel(intc, INTPR0 + 4 * i, intc->saved_ipr[i]);
+		intc_writel(&intc0, INTPR0 + 4 * i, intc0.saved_ipr[i]);
 
 	return 0;
 }
@@ -186,27 +181,18 @@ static int intc_resume(struct sys_device *sdev)
 #define intc_resume	NULL
 #endif
 
-static struct sysdev_class intc_class = {
-	.name		= "intc",
+static struct syscore_ops intc_syscore_ops = {
 	.suspend	= intc_suspend,
 	.resume		= intc_resume,
 };
 
-static int __init intc_init_sysdev(void)
+static int __init intc_init_syscore(void)
 {
-	int ret;
-
-	ret = sysdev_class_register(&intc_class);
-	if (ret)
-		return ret;
+	register_syscore_ops(&intc_syscore_ops);
 
-	intc0.sysdev.id = 0;
-	intc0.sysdev.cls = &intc_class;
-	ret = sysdev_register(&intc0.sysdev);
-
-	return ret;
+	return 0;
 }
-device_initcall(intc_init_sysdev);
+device_initcall(intc_init_syscore);
 
 unsigned long intc_get_pending(unsigned int group)
 {
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 0b5f72f17fd..401eb1d8e3b 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -12,7 +12,7 @@
 
 #include <linux/bitops.h>
 #include <linux/hardirq.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/pm.h>
 #include <linux/nmi.h>
 #include <linux/smp.h>
@@ -196,43 +196,31 @@ void touch_nmi_watchdog(void)
 
 /* Suspend/resume support */
 #ifdef CONFIG_PM
-static int nmi_wdt_suspend(struct sys_device *dev, pm_message_t state)
+static int nmi_wdt_suspend(void)
 {
 	nmi_wdt_stop();
 	return 0;
 }
 
-static int nmi_wdt_resume(struct sys_device *dev)
+static void nmi_wdt_resume(void)
 {
 	if (nmi_active)
 		nmi_wdt_start();
-	return 0;
 }
 
-static struct sysdev_class nmi_sysclass = {
-	.name		= DRV_NAME,
+static struct syscore_ops nmi_syscore_ops = {
 	.resume		= nmi_wdt_resume,
 	.suspend	= nmi_wdt_suspend,
 };
 
-static struct sys_device device_nmi_wdt = {
-	.id	= 0,
-	.cls	= &nmi_sysclass,
-};
-
-static int __init init_nmi_wdt_sysfs(void)
+static int __init init_nmi_wdt_syscore(void)
 {
-	int error;
-
-	if (!nmi_active)
-		return 0;
+	if (nmi_active)
+		register_syscore_ops(&nmi_syscore_ops);
 
-	error = sysdev_class_register(&nmi_sysclass);
-	if (!error)
-		error = sysdev_register(&device_nmi_wdt);
-	return error;
+	return 0;
 }
-late_initcall(init_nmi_wdt_sysfs);
+late_initcall(init_nmi_wdt_syscore);
 
 #endif	/* CONFIG_PM */
 
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index cdb4beb6bc8..9e9b60d969d 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -23,29 +23,6 @@
 #include <asm/gptimers.h>
 #include <asm/nmi.h>
 
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- *  basic equation:
- *		ns = cycles / (freq / ns_per_sec)
- *		ns = cycles * (ns_per_sec / freq)
- *		ns = cycles * (10^9 / (cpu_khz * 10^3))
- *		ns = cycles * (10^6 / cpu_khz)
- *
- *	Then we use scaling math (suggested by george@mvista.com) to get:
- *		ns = cycles * (10^6 * SC / cpu_khz) / SC
- *		ns = cycles * cyc2ns_scale / SC
- *
- *	And since SC is a constant power of two, we can convert the div
- *  into a shift.
- *
- *  We can use khz divisor instead of mhz to keep a better precision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- *  (mathieu.desnoyers@polymtl.ca)
- *
- *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
- */
-
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
 #if defined(CONFIG_CYCLES_CLOCKSOURCE)
 
@@ -63,7 +40,6 @@ static struct clocksource bfin_cs_cycles = {
 	.rating		= 400,
 	.read		= bfin_read_cycles,
 	.mask		= CLOCKSOURCE_MASK(64),
-	.shift		= CYC2NS_SCALE_FACTOR,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -75,10 +51,7 @@ static inline unsigned long long bfin_cs_cycles_sched_clock(void)
 
 static int __init bfin_cs_cycles_init(void)
 {
-	bfin_cs_cycles.mult = \
-		clocksource_hz2mult(get_cclk(), bfin_cs_cycles.shift);
-
-	if (clocksource_register(&bfin_cs_cycles))
+	if (clocksource_register_hz(&bfin_cs_cycles, get_cclk()))
 		panic("failed to register clocksource");
 
 	return 0;
@@ -111,7 +84,6 @@ static struct clocksource bfin_cs_gptimer0 = {
 	.rating		= 350,
 	.read		= bfin_read_gptimer0,
 	.mask		= CLOCKSOURCE_MASK(32),
-	.shift		= CYC2NS_SCALE_FACTOR,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -125,10 +97,7 @@ static int __init bfin_cs_gptimer0_init(void)
 {
 	setup_gptimer0();
 
-	bfin_cs_gptimer0.mult = \
-		clocksource_hz2mult(get_sclk(), bfin_cs_gptimer0.shift);
-
-	if (clocksource_register(&bfin_cs_gptimer0))
+	if (clocksource_register_hz(&bfin_cs_gptimer0, get_sclk()))
 		panic("failed to register clocksource");
 
 	return 0;
diff --git a/arch/blackfin/mach-common/dpmc.c b/arch/blackfin/mach-common/dpmc.c
index 382099fd556..5e4112e518a 100644
--- a/arch/blackfin/mach-common/dpmc.c
+++ b/arch/blackfin/mach-common/dpmc.c
@@ -19,9 +19,6 @@
 
 #define DRIVER_NAME "bfin dpmc"
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, DRIVER_NAME, msg)
-
 struct bfin_dpmc_platform_data *pdata;
 
 /**
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 8bce5ed031e..1fbd94c4445 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -177,6 +177,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	while (msg_queue->count) {
 		msg = &msg_queue->ipi_message[msg_queue->head];
 		switch (msg->type) {
+		case BFIN_IPI_RESCHEDULE:
+			scheduler_ipi();
+			break;
 		case BFIN_IPI_CALL_FUNC:
 			spin_unlock_irqrestore(&msg_queue->lock, flags);
 			ipi_call_function(cpu, msg);
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 4c9e3e1ba5d..66cc75657e2 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id)
 
 	ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi);
 
+	if (ipi.vector & IPI_SCHEDULE) {
+		scheduler_ipi();
+	}
 	if (ipi.vector & IPI_CALL) {
-	         func(info);
+		func(info);
 	}
 	if (ipi.vector & IPI_FLUSH_TLB) {
-		     if (flush_mm == FLUSH_ALL)
-			 __flush_tlb_all();
-		     else if (flush_vma == FLUSH_ALL)
+		if (flush_mm == FLUSH_ALL)
+			__flush_tlb_all();
+		else if (flush_vma == FLUSH_ALL)
 			__flush_tlb_mm(flush_mm);
-		     else
+		else
 			__flush_tlb_page(flush_vma, flush_addr);
 	}
 
diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
index 22f61526a8e..f09b174244d 100644
--- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
+++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
@@ -23,8 +23,6 @@
 #include <linux/acpi.h>
 #include <acpi/processor.h>
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg)
-
 MODULE_AUTHOR("Venkatesh Pallipadi");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
 MODULE_LICENSE("GPL");
@@ -47,12 +45,12 @@ processor_set_pstate (
 {
 	s64 retval;
 
-	dprintk("processor_set_pstate\n");
+	pr_debug("processor_set_pstate\n");
 
 	retval = ia64_pal_set_pstate((u64)value);
 
 	if (retval) {
-		dprintk("Failed to set freq to 0x%x, with error 0x%lx\n",
+		pr_debug("Failed to set freq to 0x%x, with error 0x%lx\n",
 		        value, retval);
 		return -ENODEV;
 	}
@@ -67,14 +65,14 @@ processor_get_pstate (
 	u64	pstate_index = 0;
 	s64 	retval;
 
-	dprintk("processor_get_pstate\n");
+	pr_debug("processor_get_pstate\n");
 
 	retval = ia64_pal_get_pstate(&pstate_index,
 	                             PAL_GET_PSTATE_TYPE_INSTANT);
 	*value = (u32) pstate_index;
 
 	if (retval)
-		dprintk("Failed to get current freq with "
+		pr_debug("Failed to get current freq with "
 			"error 0x%lx, idx 0x%x\n", retval, *value);
 
 	return (int)retval;
@@ -90,7 +88,7 @@ extract_clock (
 {
 	unsigned long i;
 
-	dprintk("extract_clock\n");
+	pr_debug("extract_clock\n");
 
 	for (i = 0; i < data->acpi_data.state_count; i++) {
 		if (value == data->acpi_data.states[i].status)
@@ -110,7 +108,7 @@ processor_get_freq (
 	cpumask_t		saved_mask;
 	unsigned long 		clock_freq;
 
-	dprintk("processor_get_freq\n");
+	pr_debug("processor_get_freq\n");
 
 	saved_mask = current->cpus_allowed;
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
@@ -148,7 +146,7 @@ processor_set_freq (
 	cpumask_t		saved_mask;
 	int			retval;
 
-	dprintk("processor_set_freq\n");
+	pr_debug("processor_set_freq\n");
 
 	saved_mask = current->cpus_allowed;
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
@@ -159,16 +157,16 @@ processor_set_freq (
 
 	if (state == data->acpi_data.state) {
 		if (unlikely(data->resume)) {
-			dprintk("Called after resume, resetting to P%d\n", state);
+			pr_debug("Called after resume, resetting to P%d\n", state);
 			data->resume = 0;
 		} else {
-			dprintk("Already at target state (P%d)\n", state);
+			pr_debug("Already at target state (P%d)\n", state);
 			retval = 0;
 			goto migrate_end;
 		}
 	}
 
-	dprintk("Transitioning from P%d to P%d\n",
+	pr_debug("Transitioning from P%d to P%d\n",
 		data->acpi_data.state, state);
 
 	/* cpufreq frequency struct */
@@ -186,7 +184,7 @@ processor_set_freq (
 
 	value = (u32) data->acpi_data.states[state].control;
 
-	dprintk("Transitioning to state: 0x%08x\n", value);
+	pr_debug("Transitioning to state: 0x%08x\n", value);
 
 	ret = processor_set_pstate(value);
 	if (ret) {
@@ -219,7 +217,7 @@ acpi_cpufreq_get (
 {
 	struct cpufreq_acpi_io *data = acpi_io_data[cpu];
 
-	dprintk("acpi_cpufreq_get\n");
+	pr_debug("acpi_cpufreq_get\n");
 
 	return processor_get_freq(data, cpu);
 }
@@ -235,7 +233,7 @@ acpi_cpufreq_target (
 	unsigned int next_state = 0;
 	unsigned int result = 0;
 
-	dprintk("acpi_cpufreq_setpolicy\n");
+	pr_debug("acpi_cpufreq_setpolicy\n");
 
 	result = cpufreq_frequency_table_target(policy,
 			data->freq_table, target_freq, relation, &next_state);
@@ -255,7 +253,7 @@ acpi_cpufreq_verify (
 	unsigned int result = 0;
 	struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu];
 
-	dprintk("acpi_cpufreq_verify\n");
+	pr_debug("acpi_cpufreq_verify\n");
 
 	result = cpufreq_frequency_table_verify(policy,
 			data->freq_table);
@@ -273,7 +271,7 @@ acpi_cpufreq_cpu_init (
 	struct cpufreq_acpi_io	*data;
 	unsigned int		result = 0;
 
-	dprintk("acpi_cpufreq_cpu_init\n");
+	pr_debug("acpi_cpufreq_cpu_init\n");
 
 	data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
 	if (!data)
@@ -288,7 +286,7 @@ acpi_cpufreq_cpu_init (
 
 	/* capability check */
 	if (data->acpi_data.state_count <= 1) {
-		dprintk("No P-States\n");
+		pr_debug("No P-States\n");
 		result = -ENODEV;
 		goto err_unreg;
 	}
@@ -297,7 +295,7 @@ acpi_cpufreq_cpu_init (
 					ACPI_ADR_SPACE_FIXED_HARDWARE) ||
 	    (data->acpi_data.status_register.space_id !=
 					ACPI_ADR_SPACE_FIXED_HARDWARE)) {
-		dprintk("Unsupported address space [%d, %d]\n",
+		pr_debug("Unsupported address space [%d, %d]\n",
 			(u32) (data->acpi_data.control_register.space_id),
 			(u32) (data->acpi_data.status_register.space_id));
 		result = -ENODEV;
@@ -348,7 +346,7 @@ acpi_cpufreq_cpu_init (
 	       "activated.\n", cpu);
 
 	for (i = 0; i < data->acpi_data.state_count; i++)
-		dprintk("     %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n",
+		pr_debug("     %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n",
 			(i == data->acpi_data.state?'*':' '), i,
 			(u32) data->acpi_data.states[i].core_frequency,
 			(u32) data->acpi_data.states[i].power,
@@ -383,7 +381,7 @@ acpi_cpufreq_cpu_exit (
 {
 	struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu];
 
-	dprintk("acpi_cpufreq_cpu_exit\n");
+	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
 		cpufreq_frequency_table_put_attr(policy->cpu);
@@ -418,7 +416,7 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 static int __init
 acpi_cpufreq_init (void)
 {
-	dprintk("acpi_cpufreq_init\n");
+	pr_debug("acpi_cpufreq_init\n");
 
  	return cpufreq_register_driver(&acpi_cpufreq_driver);
 }
@@ -427,7 +425,7 @@ acpi_cpufreq_init (void)
 static void __exit
 acpi_cpufreq_exit (void)
 {
-	dprintk("acpi_cpufreq_exit\n");
+	pr_debug("acpi_cpufreq_exit\n");
 
 	cpufreq_unregister_driver(&acpi_cpufreq_driver);
 	return;
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 1b811c61bdc..f64097b5118 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -31,8 +31,6 @@ static struct clocksource clocksource_cyclone = {
         .rating         = 300,
         .read           = read_cyclone,
         .mask           = (1LL << 40) - 1,
-        .mult           = 0, /*to be calculated*/
-        .shift          = 16,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -118,9 +116,7 @@ int __init init_cyclone_clock(void)
 	/* initialize last tick */
 	cyclone_mc = cyclone_timer;
 	clocksource_cyclone.fsys_mmio = cyclone_timer;
-	clocksource_cyclone.mult = clocksource_hz2mult(CYCLONE_TIMER_FREQ,
-						clocksource_cyclone.shift);
-	clocksource_register(&clocksource_cyclone);
+	clocksource_register_hz(&clocksource_cyclone, CYCLONE_TIMER_FREQ);
 
 	return 0;
 }
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 5b704740f16..782c3a357f2 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -31,6 +31,7 @@
 #include <linux/irq.h>
 #include <linux/ratelimit.h>
 #include <linux/acpi.h>
+#include <linux/sched.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>
@@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector))) {
+			scheduler_ipi();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else {
 			ia64_setreg(_IA64_REG_CR_TPR, vector);
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 156ad803d5b..04440cc09b4 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -73,8 +73,6 @@ static struct clocksource clocksource_itc = {
 	.rating         = 350,
 	.read           = itc_get_cycles,
 	.mask           = CLOCKSOURCE_MASK(64),
-	.mult           = 0, /*to be calculated*/
-	.shift          = 16,
 	.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 #ifdef CONFIG_PARAVIRT
 	.resume		= paravirt_clocksource_resume,
@@ -365,11 +363,8 @@ ia64_init_itm (void)
 	ia64_cpu_local_tick();
 
 	if (!itc_clocksource) {
-		/* Sort out mult/shift values: */
-		clocksource_itc.mult =
-			clocksource_hz2mult(local_cpu_data->itc_freq,
-						clocksource_itc.shift);
-		clocksource_register(&clocksource_itc);
+		clocksource_register_hz(&clocksource_itc,
+						local_cpu_data->itc_freq);
 		itc_clocksource = &clocksource_itc;
 	}
 }
diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c
index 21d6f09e344..c34efda122e 100644
--- a/arch/ia64/sn/kernel/sn2/timer.c
+++ b/arch/ia64/sn/kernel/sn2/timer.c
@@ -33,8 +33,6 @@ static struct clocksource clocksource_sn2 = {
         .rating         = 450,
         .read           = read_sn2,
         .mask           = (1LL << 55) - 1,
-        .mult           = 0,
-        .shift          = 10,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -57,9 +55,7 @@ ia64_sn_udelay (unsigned long usecs)
 void __init sn_timer_init(void)
 {
 	clocksource_sn2.fsys_mmio = RTC_COUNTER_ADDR;
-	clocksource_sn2.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
-							clocksource_sn2.shift);
-	clocksource_register(&clocksource_sn2);
+	clocksource_register_hz(&clocksource_sn2, sn_rtc_cycles_per_second);
 
 	ia64_udelay = &ia64_sn_udelay;
 }
diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c
index 108bb858acf..b279e142c63 100644
--- a/arch/ia64/xen/irq_xen.c
+++ b/arch/ia64/xen/irq_xen.c
@@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt;
 static int xen_slab_ready;
 
 #ifdef CONFIG_SMP
+#include <linux/sched.h>
+
 /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ,
  * it ends up to issue several memory accesses upon percpu data and
  * thus adds unnecessary traffic to other paths.
@@ -99,7 +101,13 @@ static int xen_slab_ready;
 static irqreturn_t
 xen_dummy_handler(int irq, void *dev_id)
 {
+	return IRQ_HANDLED;
+}
 
+static irqreturn_t
+xen_resched_handler(int irq, void *dev_id)
+{
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
@@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = {
 };
 
 static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_dummy_handler,
+	.handler =	xen_resched_handler,
 	.flags =	IRQF_DISABLED,
 	.name =		"resched"
 };
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index 31cef20b299..fc10b39893d 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id)
  *
  * Description:  This routine executes on CPU which received
  *               'RESCHEDULE_IPI'.
- *               Rescheduling is processed at the exit of interrupt
- *               operation.
  *
  * Born on Date: 2002.02.05
  *
@@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id)
  *==========================================================================*/
 void smp_reschedule_interrupt(void)
 {
-	/* nothing to do */
+	scheduler_ipi();
 }
 
 /*==========================================================================*
diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c
index b995513d527..95022b04b62 100644
--- a/arch/m68k/atari/atakeyb.c
+++ b/arch/m68k/atari/atakeyb.c
@@ -36,13 +36,10 @@
 
 /* Hook for MIDI serial driver */
 void (*atari_MIDI_interrupt_hook) (void);
-/* Hook for mouse driver */
-void (*atari_mouse_interrupt_hook) (char *);
 /* Hook for keyboard inputdev  driver */
 void (*atari_input_keyboard_interrupt_hook) (unsigned char, char);
 /* Hook for mouse inputdev  driver */
 void (*atari_input_mouse_interrupt_hook) (char *);
-EXPORT_SYMBOL(atari_mouse_interrupt_hook);
 EXPORT_SYMBOL(atari_input_keyboard_interrupt_hook);
 EXPORT_SYMBOL(atari_input_mouse_interrupt_hook);
 
@@ -263,8 +260,8 @@ repeat:
 			kb_state.buf[kb_state.len++] = scancode;
 			if (kb_state.len == 3) {
 				kb_state.state = KEYBOARD;
-				if (atari_mouse_interrupt_hook)
-					atari_mouse_interrupt_hook(kb_state.buf);
+				if (atari_input_mouse_interrupt_hook)
+					atari_input_mouse_interrupt_hook(kb_state.buf);
 			}
 			break;
 
@@ -575,7 +572,7 @@ int atari_keyb_init(void)
 	kb_state.len = 0;
 
 	error = request_irq(IRQ_MFP_ACIA, atari_keyboard_interrupt,
-			    IRQ_TYPE_SLOW, "keyboard/mouse/MIDI",
+			    IRQ_TYPE_SLOW, "keyboard,mouse,MIDI",
 			    atari_keyboard_interrupt);
 	if (error)
 		return error;
diff --git a/arch/m68k/atari/stdma.c b/arch/m68k/atari/stdma.c
index 604329fafbb..ddbf43ca885 100644
--- a/arch/m68k/atari/stdma.c
+++ b/arch/m68k/atari/stdma.c
@@ -180,7 +180,7 @@ void __init stdma_init(void)
 {
 	stdma_isr = NULL;
 	if (request_irq(IRQ_MFP_FDC, stdma_int, IRQ_TYPE_SLOW | IRQF_SHARED,
-			"ST-DMA: floppy/ACSI/IDE/Falcon-SCSI", stdma_int))
+			"ST-DMA floppy,ACSI,IDE,Falcon-SCSI", stdma_int))
 		pr_err("Couldn't register ST-DMA interrupt\n");
 }
 
diff --git a/arch/m68k/include/asm/atarikb.h b/arch/m68k/include/asm/atarikb.h
index 546e7da5804..68f3622bf59 100644
--- a/arch/m68k/include/asm/atarikb.h
+++ b/arch/m68k/include/asm/atarikb.h
@@ -34,8 +34,6 @@ void ikbd_joystick_disable(void);
 
 /* Hook for MIDI serial driver */
 extern void (*atari_MIDI_interrupt_hook) (void);
-/* Hook for mouse driver */
-extern void (*atari_mouse_interrupt_hook) (char *);
 /* Hook for keyboard inputdev  driver */
 extern void (*atari_input_keyboard_interrupt_hook) (unsigned char, char);
 /* Hook for mouse inputdev  driver */
diff --git a/arch/m68k/include/asm/bitops_mm.h b/arch/m68k/include/asm/bitops_mm.h
index 9d69f6e6236..e9020f88a74 100644
--- a/arch/m68k/include/asm/bitops_mm.h
+++ b/arch/m68k/include/asm/bitops_mm.h
@@ -181,14 +181,15 @@ static inline int find_first_zero_bit(const unsigned long *vaddr,
 {
 	const unsigned long *p = vaddr;
 	int res = 32;
+	unsigned int words;
 	unsigned long num;
 
 	if (!size)
 		return 0;
 
-	size = (size + 31) >> 5;
+	words = (size + 31) >> 5;
 	while (!(num = ~*p++)) {
-		if (!--size)
+		if (!--words)
 			goto out;
 	}
 
@@ -196,7 +197,8 @@ static inline int find_first_zero_bit(const unsigned long *vaddr,
 			      : "=d" (res) : "d" (num & -num));
 	res ^= 31;
 out:
-	return ((long)p - (long)vaddr - 4) * 8 + res;
+	res += ((long)p - (long)vaddr - 4) * 8;
+	return res < size ? res : size;
 }
 
 static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
@@ -215,27 +217,32 @@ static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
 		/* Look for zero in first longword */
 		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
 				      : "=d" (res) : "d" (num & -num));
-		if (res < 32)
-			return offset + (res ^ 31);
+		if (res < 32) {
+			offset += res ^ 31;
+			return offset < size ? offset : size;
+		}
 		offset += 32;
+
+		if (offset >= size)
+			return size;
 	}
 	/* No zero yet, search remaining full bytes for a zero */
-	res = find_first_zero_bit(p, size - ((long)p - (long)vaddr) * 8);
-	return offset + res;
+	return offset + find_first_zero_bit(p, size - offset);
 }
 
 static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
 {
 	const unsigned long *p = vaddr;
 	int res = 32;
+	unsigned int words;
 	unsigned long num;
 
 	if (!size)
 		return 0;
 
-	size = (size + 31) >> 5;
+	words = (size + 31) >> 5;
 	while (!(num = *p++)) {
-		if (!--size)
+		if (!--words)
 			goto out;
 	}
 
@@ -243,7 +250,8 @@ static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
 			      : "=d" (res) : "d" (num & -num));
 	res ^= 31;
 out:
-	return ((long)p - (long)vaddr - 4) * 8 + res;
+	res += ((long)p - (long)vaddr - 4) * 8;
+	return res < size ? res : size;
 }
 
 static inline int find_next_bit(const unsigned long *vaddr, int size,
@@ -262,13 +270,17 @@ static inline int find_next_bit(const unsigned long *vaddr, int size,
 		/* Look for one in first longword */
 		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
 				      : "=d" (res) : "d" (num & -num));
-		if (res < 32)
-			return offset + (res ^ 31);
+		if (res < 32) {
+			offset += res ^ 31;
+			return offset < size ? offset : size;
+		}
 		offset += 32;
+
+		if (offset >= size)
+			return size;
 	}
 	/* No one yet, search remaining full bytes for a one */
-	res = find_first_bit(p, size - ((long)p - (long)vaddr) * 8);
-	return offset + res;
+	return offset + find_first_bit(p, size - offset);
 }
 
 /*
@@ -366,23 +378,25 @@ static inline int test_bit_le(int nr, const void *vaddr)
 static inline int find_first_zero_bit_le(const void *vaddr, unsigned size)
 {
 	const unsigned long *p = vaddr, *addr = vaddr;
-	int res;
+	int res = 0;
+	unsigned int words;
 
 	if (!size)
 		return 0;
 
-	size = (size >> 5) + ((size & 31) > 0);
-	while (*p++ == ~0UL)
-	{
-		if (--size == 0)
-			return (p - addr) << 5;
+	words = (size >> 5) + ((size & 31) > 0);
+	while (*p++ == ~0UL) {
+		if (--words == 0)
+			goto out;
 	}
 
 	--p;
 	for (res = 0; res < 32; res++)
 		if (!test_bit_le(res, p))
 			break;
-	return (p - addr) * 32 + res;
+out:
+	res += (p - addr) * 32;
+	return res < size ? res : size;
 }
 
 static inline unsigned long find_next_zero_bit_le(const void *addr,
@@ -400,10 +414,15 @@ static inline unsigned long find_next_zero_bit_le(const void *addr,
 		offset -= bit;
 		/* Look for zero in first longword */
 		for (res = bit; res < 32; res++)
-			if (!test_bit_le(res, p))
-				return offset + res;
+			if (!test_bit_le(res, p)) {
+				offset += res;
+				return offset < size ? offset : size;
+			}
 		p++;
 		offset += 32;
+
+		if (offset >= size)
+			return size;
 	}
 	/* No zero yet, search remaining full bytes for a zero */
 	return offset + find_first_zero_bit_le(p, size - offset);
@@ -412,22 +431,25 @@ static inline unsigned long find_next_zero_bit_le(const void *addr,
 static inline int find_first_bit_le(const void *vaddr, unsigned size)
 {
 	const unsigned long *p = vaddr, *addr = vaddr;
-	int res;
+	int res = 0;
+	unsigned int words;
 
 	if (!size)
 		return 0;
 
-	size = (size >> 5) + ((size & 31) > 0);
+	words = (size >> 5) + ((size & 31) > 0);
 	while (*p++ == 0UL) {
-		if (--size == 0)
-			return (p - addr) << 5;
+		if (--words == 0)
+			goto out;
 	}
 
 	--p;
 	for (res = 0; res < 32; res++)
 		if (test_bit_le(res, p))
 			break;
-	return (p - addr) * 32 + res;
+out:
+	res += (p - addr) * 32;
+	return res < size ? res : size;
 }
 
 static inline unsigned long find_next_bit_le(const void *addr,
@@ -445,10 +467,15 @@ static inline unsigned long find_next_bit_le(const void *addr,
 		offset -= bit;
 		/* Look for one in first longword */
 		for (res = bit; res < 32; res++)
-			if (test_bit_le(res, p))
-				return offset + res;
+			if (test_bit_le(res, p)) {
+				offset += res;
+				return offset < size ? offset : size;
+			}
 		p++;
 		offset += 32;
+
+		if (offset >= size)
+			return size;
 	}
 	/* No set bit yet, search remaining full bytes for a set bit */
 	return offset + find_first_bit_le(p, size - offset);
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 29e17907d9f..f3b649de2a1 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -22,7 +22,7 @@
 #define __NR_mknod		 14
 #define __NR_chmod		 15
 #define __NR_chown		 16
-#define __NR_break		 17
+/*#define __NR_break		 17*/
 #define __NR_oldstat		 18
 #define __NR_lseek		 19
 #define __NR_getpid		 20
@@ -36,11 +36,11 @@
 #define __NR_oldfstat		 28
 #define __NR_pause		 29
 #define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
+/*#define __NR_stty		 31*/
+/*#define __NR_gtty		 32*/
 #define __NR_access		 33
 #define __NR_nice		 34
-#define __NR_ftime		 35
+/*#define __NR_ftime		 35*/
 #define __NR_sync		 36
 #define __NR_kill		 37
 #define __NR_rename		 38
@@ -49,7 +49,7 @@
 #define __NR_dup		 41
 #define __NR_pipe		 42
 #define __NR_times		 43
-#define __NR_prof		 44
+/*#define __NR_prof		 44*/
 #define __NR_brk		 45
 #define __NR_setgid		 46
 #define __NR_getgid		 47
@@ -58,13 +58,13 @@
 #define __NR_getegid		 50
 #define __NR_acct		 51
 #define __NR_umount2		 52
-#define __NR_lock		 53
+/*#define __NR_lock		 53*/
 #define __NR_ioctl		 54
 #define __NR_fcntl		 55
-#define __NR_mpx		 56
+/*#define __NR_mpx		 56*/
 #define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
+/*#define __NR_ulimit		 58*/
+/*#define __NR_oldolduname	 59*/
 #define __NR_umask		 60
 #define __NR_chroot		 61
 #define __NR_ustat		 62
@@ -103,10 +103,10 @@
 #define __NR_fchown		 95
 #define __NR_getpriority	 96
 #define __NR_setpriority	 97
-#define __NR_profil		 98
+/*#define __NR_profil		 98*/
 #define __NR_statfs		 99
 #define __NR_fstatfs		100
-#define __NR_ioperm		101
+/*#define __NR_ioperm		101*/
 #define __NR_socketcall		102
 #define __NR_syslog		103
 #define __NR_setitimer		104
@@ -114,11 +114,11 @@
 #define __NR_stat		106
 #define __NR_lstat		107
 #define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		/* 110 */ not supported
+/*#define __NR_olduname		109*/
+/*#define __NR_iopl		110*/ /* not supported */
 #define __NR_vhangup		111
-#define __NR_idle		/* 112 */ Obsolete
-#define __NR_vm86		/* 113 */ not supported
+/*#define __NR_idle		112*/ /* Obsolete */
+/*#define __NR_vm86		113*/ /* not supported */
 #define __NR_wait4		114
 #define __NR_swapoff		115
 #define __NR_sysinfo		116
@@ -132,17 +132,17 @@
 #define __NR_adjtimex		124
 #define __NR_mprotect		125
 #define __NR_sigprocmask	126
-#define __NR_create_module	127
+/*#define __NR_create_module	127*/
 #define __NR_init_module	128
 #define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
+/*#define __NR_get_kernel_syms	130*/
 #define __NR_quotactl		131
 #define __NR_getpgid		132
 #define __NR_fchdir		133
 #define __NR_bdflush		134
 #define __NR_sysfs		135
 #define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
+/*#define __NR_afs_syscall	137*/ /* Syscall for Andrew File System */
 #define __NR_setfsuid		138
 #define __NR_setfsgid		139
 #define __NR__llseek		140
@@ -172,7 +172,7 @@
 #define __NR_setresuid		164
 #define __NR_getresuid		165
 #define __NR_getpagesize	166
-#define __NR_query_module	167
+/*#define __NR_query_module	167*/
 #define __NR_poll		168
 #define __NR_nfsservctl		169
 #define __NR_setresgid		170
@@ -193,8 +193,8 @@
 #define __NR_capset		185
 #define __NR_sigaltstack	186
 #define __NR_sendfile		187
-#define __NR_getpmsg		188	/* some people actually want streams */
-#define __NR_putpmsg		189	/* some people actually want streams */
+/*#define __NR_getpmsg		188*/	/* some people actually want streams */
+/*#define __NR_putpmsg		189*/	/* some people actually want streams */
 #define __NR_vfork		190
 #define __NR_ugetrlimit		191
 #define __NR_mmap2		192
@@ -223,6 +223,8 @@
 #define __NR_setfsuid32		215
 #define __NR_setfsgid32		216
 #define __NR_pivot_root		217
+/* 218*/
+/* 219*/
 #define __NR_getdents64		220
 #define __NR_gettid		221
 #define __NR_tkill		222
@@ -281,7 +283,7 @@
 #define __NR_mq_notify		275
 #define __NR_mq_getsetattr	276
 #define __NR_waitid		277
-#define __NR_vserver		278
+/*#define __NR_vserver		278*/
 #define __NR_add_key		279
 #define __NR_request_key	280
 #define __NR_keyctl		281
diff --git a/arch/m68k/kernel/Makefile_mm b/arch/m68k/kernel/Makefile_mm
index 55d5d6b680a..aced6780457 100644
--- a/arch/m68k/kernel/Makefile_mm
+++ b/arch/m68k/kernel/Makefile_mm
@@ -10,7 +10,7 @@ endif
 extra-y	+= vmlinux.lds
 
 obj-y	:= entry.o process.o traps.o ints.o signal.o ptrace.o module.o \
-	   sys_m68k.o time.o setup.o m68k_ksyms.o devres.o
+	   sys_m68k.o time.o setup.o m68k_ksyms.o devres.o syscalltable.o
 
 devres-y = ../../../kernel/irq/devres.o
 
diff --git a/arch/m68k/kernel/entry_mm.S b/arch/m68k/kernel/entry_mm.S
index 1359ee65957..bd0ec05263b 100644
--- a/arch/m68k/kernel/entry_mm.S
+++ b/arch/m68k/kernel/entry_mm.S
@@ -407,351 +407,3 @@ resume:
 
 	rts
 
-.data
-ALIGN
-sys_call_table:
-	.long sys_restart_syscall	/* 0 - old "setup()" system call, used for restarting */
-	.long sys_exit
-	.long sys_fork
-	.long sys_read
-	.long sys_write
-	.long sys_open		/* 5 */
-	.long sys_close
-	.long sys_waitpid
-	.long sys_creat
-	.long sys_link
-	.long sys_unlink	/* 10 */
-	.long sys_execve
-	.long sys_chdir
-	.long sys_time
-	.long sys_mknod
-	.long sys_chmod		/* 15 */
-	.long sys_chown16
-	.long sys_ni_syscall				/* old break syscall holder */
-	.long sys_stat
-	.long sys_lseek
-	.long sys_getpid	/* 20 */
-	.long sys_mount
-	.long sys_oldumount
-	.long sys_setuid16
-	.long sys_getuid16
-	.long sys_stime		/* 25 */
-	.long sys_ptrace
-	.long sys_alarm
-	.long sys_fstat
-	.long sys_pause
-	.long sys_utime		/* 30 */
-	.long sys_ni_syscall				/* old stty syscall holder */
-	.long sys_ni_syscall				/* old gtty syscall holder */
-	.long sys_access
-	.long sys_nice
-	.long sys_ni_syscall	/* 35 */	/* old ftime syscall holder */
-	.long sys_sync
-	.long sys_kill
-	.long sys_rename
-	.long sys_mkdir
-	.long sys_rmdir		/* 40 */
-	.long sys_dup
-	.long sys_pipe
-	.long sys_times
-	.long sys_ni_syscall				/* old prof syscall holder */
-	.long sys_brk		/* 45 */
-	.long sys_setgid16
-	.long sys_getgid16
-	.long sys_signal
-	.long sys_geteuid16
-	.long sys_getegid16	/* 50 */
-	.long sys_acct
-	.long sys_umount				/* recycled never used phys() */
-	.long sys_ni_syscall				/* old lock syscall holder */
-	.long sys_ioctl
-	.long sys_fcntl		/* 55 */
-	.long sys_ni_syscall				/* old mpx syscall holder */
-	.long sys_setpgid
-	.long sys_ni_syscall				/* old ulimit syscall holder */
-	.long sys_ni_syscall
-	.long sys_umask		/* 60 */
-	.long sys_chroot
-	.long sys_ustat
-	.long sys_dup2
-	.long sys_getppid
-	.long sys_getpgrp	/* 65 */
-	.long sys_setsid
-	.long sys_sigaction
-	.long sys_sgetmask
-	.long sys_ssetmask
-	.long sys_setreuid16	/* 70 */
-	.long sys_setregid16
-	.long sys_sigsuspend
-	.long sys_sigpending
-	.long sys_sethostname
-	.long sys_setrlimit	/* 75 */
-	.long sys_old_getrlimit
-	.long sys_getrusage
-	.long sys_gettimeofday
-	.long sys_settimeofday
-	.long sys_getgroups16	/* 80 */
-	.long sys_setgroups16
-	.long sys_old_select
-	.long sys_symlink
-	.long sys_lstat
-	.long sys_readlink	/* 85 */
-	.long sys_uselib
-	.long sys_swapon
-	.long sys_reboot
-	.long sys_old_readdir
-	.long sys_old_mmap	/* 90 */
-	.long sys_munmap
-	.long sys_truncate
-	.long sys_ftruncate
-	.long sys_fchmod
-	.long sys_fchown16	/* 95 */
-	.long sys_getpriority
-	.long sys_setpriority
-	.long sys_ni_syscall				/* old profil syscall holder */
-	.long sys_statfs
-	.long sys_fstatfs	/* 100 */
-	.long sys_ni_syscall				/* ioperm for i386 */
-	.long sys_socketcall
-	.long sys_syslog
-	.long sys_setitimer
-	.long sys_getitimer	/* 105 */
-	.long sys_newstat
-	.long sys_newlstat
-	.long sys_newfstat
-	.long sys_ni_syscall
-	.long sys_ni_syscall	/* 110 */	/* iopl for i386 */
-	.long sys_vhangup
-	.long sys_ni_syscall				/* obsolete idle() syscall */
-	.long sys_ni_syscall				/* vm86old for i386 */
-	.long sys_wait4
-	.long sys_swapoff	/* 115 */
-	.long sys_sysinfo
-	.long sys_ipc
-	.long sys_fsync
-	.long sys_sigreturn
-	.long sys_clone		/* 120 */
-	.long sys_setdomainname
-	.long sys_newuname
-	.long sys_cacheflush				/* modify_ldt for i386 */
-	.long sys_adjtimex
-	.long sys_mprotect	/* 125 */
-	.long sys_sigprocmask
-	.long sys_ni_syscall		/* old "create_module" */
-	.long sys_init_module
-	.long sys_delete_module
-	.long sys_ni_syscall	/* 130 - old "get_kernel_syms" */
-	.long sys_quotactl
-	.long sys_getpgid
-	.long sys_fchdir
-	.long sys_bdflush
-	.long sys_sysfs		/* 135 */
-	.long sys_personality
-	.long sys_ni_syscall				/* for afs_syscall */
-	.long sys_setfsuid16
-	.long sys_setfsgid16
-	.long sys_llseek	/* 140 */
-	.long sys_getdents
-	.long sys_select
-	.long sys_flock
-	.long sys_msync
-	.long sys_readv		/* 145 */
-	.long sys_writev
-	.long sys_getsid
-	.long sys_fdatasync
-	.long sys_sysctl
-	.long sys_mlock		/* 150 */
-	.long sys_munlock
-	.long sys_mlockall
-	.long sys_munlockall
-	.long sys_sched_setparam
-	.long sys_sched_getparam	/* 155 */
-	.long sys_sched_setscheduler
-	.long sys_sched_getscheduler
-	.long sys_sched_yield
-	.long sys_sched_get_priority_max
-	.long sys_sched_get_priority_min  /* 160 */
-	.long sys_sched_rr_get_interval
-	.long sys_nanosleep
-	.long sys_mremap
-	.long sys_setresuid16
-	.long sys_getresuid16	/* 165 */
-	.long sys_getpagesize
-	.long sys_ni_syscall		/* old sys_query_module */
-	.long sys_poll
-	.long sys_nfsservctl
-	.long sys_setresgid16	/* 170 */
-	.long sys_getresgid16
-	.long sys_prctl
-	.long sys_rt_sigreturn
-	.long sys_rt_sigaction
-	.long sys_rt_sigprocmask	/* 175 */
-	.long sys_rt_sigpending
-	.long sys_rt_sigtimedwait
-	.long sys_rt_sigqueueinfo
-	.long sys_rt_sigsuspend
-	.long sys_pread64	/* 180 */
-	.long sys_pwrite64
-	.long sys_lchown16;
-	.long sys_getcwd
-	.long sys_capget
-	.long sys_capset	/* 185 */
-	.long sys_sigaltstack
-	.long sys_sendfile
-	.long sys_ni_syscall				/* streams1 */
-	.long sys_ni_syscall				/* streams2 */
-	.long sys_vfork		/* 190 */
-	.long sys_getrlimit
-	.long sys_mmap2
-	.long sys_truncate64
-	.long sys_ftruncate64
-	.long sys_stat64	/* 195 */
-	.long sys_lstat64
-	.long sys_fstat64
-	.long sys_chown
-	.long sys_getuid
-	.long sys_getgid	/* 200 */
-	.long sys_geteuid
-	.long sys_getegid
-	.long sys_setreuid
-	.long sys_setregid
-	.long sys_getgroups	/* 205 */
-	.long sys_setgroups
-	.long sys_fchown
-	.long sys_setresuid
-	.long sys_getresuid
-	.long sys_setresgid	/* 210 */
-	.long sys_getresgid
-	.long sys_lchown
-	.long sys_setuid
-	.long sys_setgid
-	.long sys_setfsuid	/* 215 */
-	.long sys_setfsgid
-	.long sys_pivot_root
-	.long sys_ni_syscall
-	.long sys_ni_syscall
-	.long sys_getdents64	/* 220 */
-	.long sys_gettid
-	.long sys_tkill
-	.long sys_setxattr
-	.long sys_lsetxattr
-	.long sys_fsetxattr	/* 225 */
-	.long sys_getxattr
-	.long sys_lgetxattr
-	.long sys_fgetxattr
-	.long sys_listxattr
-	.long sys_llistxattr	/* 230 */
-	.long sys_flistxattr
-	.long sys_removexattr
-	.long sys_lremovexattr
-	.long sys_fremovexattr
-	.long sys_futex		/* 235 */
-	.long sys_sendfile64
-	.long sys_mincore
-	.long sys_madvise
-	.long sys_fcntl64
-	.long sys_readahead	/* 240 */
-	.long sys_io_setup
-	.long sys_io_destroy
-	.long sys_io_getevents
-	.long sys_io_submit
-	.long sys_io_cancel	/* 245 */
-	.long sys_fadvise64
-	.long sys_exit_group
-	.long sys_lookup_dcookie
-	.long sys_epoll_create
-	.long sys_epoll_ctl	/* 250 */
-	.long sys_epoll_wait
-	.long sys_remap_file_pages
-	.long sys_set_tid_address
-	.long sys_timer_create
-	.long sys_timer_settime	/* 255 */
-	.long sys_timer_gettime
-	.long sys_timer_getoverrun
-	.long sys_timer_delete
-	.long sys_clock_settime
-	.long sys_clock_gettime	/* 260 */
-	.long sys_clock_getres
-	.long sys_clock_nanosleep
-	.long sys_statfs64
-	.long sys_fstatfs64
-	.long sys_tgkill	/* 265 */
-	.long sys_utimes
-	.long sys_fadvise64_64
-	.long sys_mbind
-	.long sys_get_mempolicy
-	.long sys_set_mempolicy	/* 270 */
-	.long sys_mq_open
-	.long sys_mq_unlink
-	.long sys_mq_timedsend
-	.long sys_mq_timedreceive
-	.long sys_mq_notify	/* 275 */
-	.long sys_mq_getsetattr
-	.long sys_waitid
-	.long sys_ni_syscall	/* for sys_vserver */
-	.long sys_add_key
-	.long sys_request_key	/* 280 */
-	.long sys_keyctl
-	.long sys_ioprio_set
-	.long sys_ioprio_get
-	.long sys_inotify_init
-	.long sys_inotify_add_watch	/* 285 */
-	.long sys_inotify_rm_watch
-	.long sys_migrate_pages
-	.long sys_openat
-	.long sys_mkdirat
-	.long sys_mknodat		/* 290 */
-	.long sys_fchownat
-	.long sys_futimesat
-	.long sys_fstatat64
-	.long sys_unlinkat
-	.long sys_renameat		/* 295 */
-	.long sys_linkat
-	.long sys_symlinkat
-	.long sys_readlinkat
-	.long sys_fchmodat
-	.long sys_faccessat		/* 300 */
-	.long sys_ni_syscall		/* Reserved for pselect6 */
-	.long sys_ni_syscall		/* Reserved for ppoll */
-	.long sys_unshare
-	.long sys_set_robust_list
-	.long sys_get_robust_list	/* 305 */
-	.long sys_splice
-	.long sys_sync_file_range
-	.long sys_tee
-	.long sys_vmsplice
-	.long sys_move_pages		/* 310 */
-	.long sys_sched_setaffinity
-	.long sys_sched_getaffinity
-	.long sys_kexec_load
-	.long sys_getcpu
-	.long sys_epoll_pwait		/* 315 */
-	.long sys_utimensat
-	.long sys_signalfd
-	.long sys_timerfd_create
-	.long sys_eventfd
-	.long sys_fallocate		/* 320 */
-	.long sys_timerfd_settime
-	.long sys_timerfd_gettime
-	.long sys_signalfd4
-	.long sys_eventfd2
-	.long sys_epoll_create1		/* 325 */
-	.long sys_dup3
-	.long sys_pipe2
-	.long sys_inotify_init1
-	.long sys_preadv
-	.long sys_pwritev		/* 330 */
-	.long sys_rt_tgsigqueueinfo
-	.long sys_perf_event_open
-	.long sys_get_thread_area
-	.long sys_set_thread_area
-	.long sys_atomic_cmpxchg_32	/* 335 */
-	.long sys_atomic_barrier
-	.long sys_fanotify_init
-	.long sys_fanotify_mark
-	.long sys_prlimit64
-	.long sys_name_to_handle_at	/* 340 */
-	.long sys_open_by_handle_at
-	.long sys_clock_adjtime
-	.long sys_syncfs
-
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 9b8393d8adb..5909e392cb1 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/m68knommu/kernel/syscalltable.S
- *
  *  Copyright (C) 2002, Greg Ungerer (gerg@snapgear.com)
  *
  *  Based on older entry.S files, the following copyrights apply:
@@ -9,171 +7,176 @@
  *                      Kenneth Albanowski <kjahds@kjahds.com>,
  *  Copyright (C) 2000  Lineo Inc. (www.lineo.com) 
  *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Linux/m68k support by Hamish Macdonald
  */
 
 #include <linux/sys.h>
 #include <linux/linkage.h>
-#include <asm/unistd.h>
 
-.text
+#ifndef CONFIG_MMU
+#define sys_mmap2		sys_mmap_pgoff
+#endif
+
+.section .rodata
 ALIGN
 ENTRY(sys_call_table)
-	.long sys_restart_syscall	/* 0  -  old "setup()" system call */
+	.long sys_restart_syscall	/* 0 - old "setup()" system call, used for restarting */
 	.long sys_exit
 	.long sys_fork
 	.long sys_read
 	.long sys_write
-	.long sys_open		/* 5 */
+	.long sys_open			/* 5 */
 	.long sys_close
 	.long sys_waitpid
 	.long sys_creat
 	.long sys_link
-	.long sys_unlink	/* 10 */
+	.long sys_unlink		/* 10 */
 	.long sys_execve
 	.long sys_chdir
 	.long sys_time
 	.long sys_mknod
-	.long sys_chmod		/* 15 */
+	.long sys_chmod			/* 15 */
 	.long sys_chown16
-	.long sys_ni_syscall	/* old break syscall holder */
+	.long sys_ni_syscall		/* old break syscall holder */
 	.long sys_stat
 	.long sys_lseek
-	.long sys_getpid	/* 20 */
+	.long sys_getpid		/* 20 */
 	.long sys_mount
 	.long sys_oldumount
 	.long sys_setuid16
 	.long sys_getuid16
-	.long sys_stime		/* 25 */
+	.long sys_stime			/* 25 */
 	.long sys_ptrace
 	.long sys_alarm
 	.long sys_fstat
 	.long sys_pause
-	.long sys_utime		/* 30 */
-	.long sys_ni_syscall	/* old stty syscall holder */
-	.long sys_ni_syscall	/* old gtty syscall holder */
+	.long sys_utime			/* 30 */
+	.long sys_ni_syscall		/* old stty syscall holder */
+	.long sys_ni_syscall		/* old gtty syscall holder */
 	.long sys_access
 	.long sys_nice
-	.long sys_ni_syscall	/* 35 */ /* old ftime syscall holder */
+	.long sys_ni_syscall		/* 35 - old ftime syscall holder */
 	.long sys_sync
 	.long sys_kill
 	.long sys_rename
 	.long sys_mkdir
-	.long sys_rmdir		/* 40 */
+	.long sys_rmdir			/* 40 */
 	.long sys_dup
 	.long sys_pipe
 	.long sys_times
-	.long sys_ni_syscall	/* old prof syscall holder */
-	.long sys_brk		/* 45 */
+	.long sys_ni_syscall		/* old prof syscall holder */
+	.long sys_brk			/* 45 */
 	.long sys_setgid16
 	.long sys_getgid16
 	.long sys_signal
 	.long sys_geteuid16
-	.long sys_getegid16	/* 50 */
+	.long sys_getegid16		/* 50 */
 	.long sys_acct
-	.long sys_umount	/* recycled never used phys() */
-	.long sys_ni_syscall	/* old lock syscall holder */
+	.long sys_umount		/* recycled never used phys() */
+	.long sys_ni_syscall		/* old lock syscall holder */
 	.long sys_ioctl
-	.long sys_fcntl		/* 55 */
-	.long sys_ni_syscall	/* old mpx syscall holder */
+	.long sys_fcntl			/* 55 */
+	.long sys_ni_syscall		/* old mpx syscall holder */
 	.long sys_setpgid
-	.long sys_ni_syscall	/* old ulimit syscall holder */
+	.long sys_ni_syscall		/* old ulimit syscall holder */
 	.long sys_ni_syscall
-	.long sys_umask		/* 60 */
+	.long sys_umask			/* 60 */
 	.long sys_chroot
 	.long sys_ustat
 	.long sys_dup2
 	.long sys_getppid
-	.long sys_getpgrp	/* 65 */
+	.long sys_getpgrp		/* 65 */
 	.long sys_setsid
 	.long sys_sigaction
 	.long sys_sgetmask
 	.long sys_ssetmask
-	.long sys_setreuid16	/* 70 */
+	.long sys_setreuid16		/* 70 */
 	.long sys_setregid16
 	.long sys_sigsuspend
 	.long sys_sigpending
 	.long sys_sethostname
-	.long sys_setrlimit	/* 75 */
+	.long sys_setrlimit		/* 75 */
 	.long sys_old_getrlimit
 	.long sys_getrusage
 	.long sys_gettimeofday
 	.long sys_settimeofday
-	.long sys_getgroups16	/* 80 */
+	.long sys_getgroups16		/* 80 */
 	.long sys_setgroups16
 	.long sys_old_select
 	.long sys_symlink
 	.long sys_lstat
-	.long sys_readlink	/* 85 */
+	.long sys_readlink		/* 85 */
 	.long sys_uselib
-	.long sys_ni_syscall	/* sys_swapon */
+	.long sys_swapon
 	.long sys_reboot
 	.long sys_old_readdir
-	.long sys_old_mmap	/* 90 */
+	.long sys_old_mmap		/* 90 */
 	.long sys_munmap
 	.long sys_truncate
 	.long sys_ftruncate
 	.long sys_fchmod
-	.long sys_fchown16	/* 95 */
+	.long sys_fchown16		/* 95 */
 	.long sys_getpriority
 	.long sys_setpriority
-	.long sys_ni_syscall	/* old profil syscall holder */
+	.long sys_ni_syscall		/* old profil syscall holder */
 	.long sys_statfs
-	.long sys_fstatfs	/* 100 */
-	.long sys_ni_syscall	/* ioperm for i386 */
+	.long sys_fstatfs		/* 100 */
+	.long sys_ni_syscall		/* ioperm for i386 */
 	.long sys_socketcall
 	.long sys_syslog
 	.long sys_setitimer
-	.long sys_getitimer	/* 105 */
+	.long sys_getitimer		/* 105 */
 	.long sys_newstat
 	.long sys_newlstat
 	.long sys_newfstat
 	.long sys_ni_syscall
-	.long sys_ni_syscall	/* iopl for i386 */ /* 110 */
+	.long sys_ni_syscall		/* 110 - iopl for i386 */
 	.long sys_vhangup
-	.long sys_ni_syscall	/* obsolete idle() syscall */
-	.long sys_ni_syscall	/* vm86old for i386 */
+	.long sys_ni_syscall		/* obsolete idle() syscall */
+	.long sys_ni_syscall		/* vm86old for i386 */
 	.long sys_wait4
-	.long sys_ni_syscall	/* 115 */ /* sys_swapoff */
+	.long sys_swapoff		/* 115 */
 	.long sys_sysinfo
 	.long sys_ipc
 	.long sys_fsync
 	.long sys_sigreturn
-	.long sys_clone		/* 120 */
+	.long sys_clone			/* 120 */
 	.long sys_setdomainname
 	.long sys_newuname
-	.long sys_cacheflush	/* modify_ldt for i386 */
+	.long sys_cacheflush		/* modify_ldt for i386 */
 	.long sys_adjtimex
-	.long sys_ni_syscall	/* 125 */ /* sys_mprotect */
+	.long sys_mprotect		/* 125 */
 	.long sys_sigprocmask
-	.long sys_ni_syscall	/* old "creat_module" */
+	.long sys_ni_syscall		/* old "create_module" */
 	.long sys_init_module
 	.long sys_delete_module
-	.long sys_ni_syscall	/* 130: old "get_kernel_syms" */
+	.long sys_ni_syscall		/* 130 - old "get_kernel_syms" */
 	.long sys_quotactl
 	.long sys_getpgid
 	.long sys_fchdir
 	.long sys_bdflush
-	.long sys_sysfs		/* 135 */
+	.long sys_sysfs			/* 135 */
 	.long sys_personality
-	.long sys_ni_syscall	/* for afs_syscall */
+	.long sys_ni_syscall		/* for afs_syscall */
 	.long sys_setfsuid16
 	.long sys_setfsgid16
-	.long sys_llseek	/* 140 */
+	.long sys_llseek		/* 140 */
 	.long sys_getdents
 	.long sys_select
 	.long sys_flock
-	.long sys_ni_syscall	/* sys_msync */
-	.long sys_readv		/* 145 */
+	.long sys_msync
+	.long sys_readv			/* 145 */
 	.long sys_writev
 	.long sys_getsid
 	.long sys_fdatasync
 	.long sys_sysctl
-	.long sys_ni_syscall	/* 150 */ /* sys_mlock */
-	.long sys_ni_syscall	/* sys_munlock */
-	.long sys_ni_syscall	/* sys_mlockall */
-	.long sys_ni_syscall	/* sys_munlockall */
+	.long sys_mlock			/* 150 */
+	.long sys_munlock
+	.long sys_mlockall
+	.long sys_munlockall
 	.long sys_sched_setparam
-	.long sys_sched_getparam /* 155 */
+	.long sys_sched_getparam	/* 155 */
 	.long sys_sched_setscheduler
 	.long sys_sched_getscheduler
 	.long sys_sched_yield
@@ -181,124 +184,124 @@ ENTRY(sys_call_table)
 	.long sys_sched_get_priority_min  /* 160 */
 	.long sys_sched_rr_get_interval
 	.long sys_nanosleep
-	.long sys_ni_syscall	/* sys_mremap */
+	.long sys_mremap
 	.long sys_setresuid16
-	.long sys_getresuid16	/* 165 */
-	.long sys_getpagesize	/* sys_getpagesize */
-	.long sys_ni_syscall	/* old "query_module" */
+	.long sys_getresuid16		/* 165 */
+	.long sys_getpagesize
+	.long sys_ni_syscall		/* old "query_module" */
 	.long sys_poll
-	.long sys_ni_syscall	/* sys_nfsservctl */
-	.long sys_setresgid16	/* 170 */
+	.long sys_nfsservctl
+	.long sys_setresgid16		/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
 	.long sys_rt_sigreturn
 	.long sys_rt_sigaction
-	.long sys_rt_sigprocmask /* 175 */
+	.long sys_rt_sigprocmask	/* 175 */
 	.long sys_rt_sigpending
 	.long sys_rt_sigtimedwait
 	.long sys_rt_sigqueueinfo
 	.long sys_rt_sigsuspend
-	.long sys_pread64	/* 180 */
+	.long sys_pread64		/* 180 */
 	.long sys_pwrite64
 	.long sys_lchown16
 	.long sys_getcwd
 	.long sys_capget
-	.long sys_capset	/* 185 */
+	.long sys_capset		/* 185 */
 	.long sys_sigaltstack
 	.long sys_sendfile
-	.long sys_ni_syscall	/* streams1 */
-	.long sys_ni_syscall	/* streams2 */
-	.long sys_vfork		/* 190 */
+	.long sys_ni_syscall		/* streams1 */
+	.long sys_ni_syscall		/* streams2 */
+	.long sys_vfork			/* 190 */
 	.long sys_getrlimit
-	.long sys_mmap_pgoff
+	.long sys_mmap2
 	.long sys_truncate64
 	.long sys_ftruncate64
-	.long sys_stat64	/* 195 */
+	.long sys_stat64		/* 195 */
 	.long sys_lstat64
 	.long sys_fstat64
 	.long sys_chown
 	.long sys_getuid
-	.long sys_getgid	/* 200 */
+	.long sys_getgid		/* 200 */
 	.long sys_geteuid
 	.long sys_getegid
 	.long sys_setreuid
 	.long sys_setregid
-	.long sys_getgroups	/* 205 */
+	.long sys_getgroups		/* 205 */
 	.long sys_setgroups
 	.long sys_fchown
 	.long sys_setresuid
 	.long sys_getresuid
-	.long sys_setresgid	/* 210 */
+	.long sys_setresgid		/* 210 */
 	.long sys_getresgid
 	.long sys_lchown
 	.long sys_setuid
 	.long sys_setgid
-	.long sys_setfsuid	/* 215 */
+	.long sys_setfsuid		/* 215 */
 	.long sys_setfsgid
 	.long sys_pivot_root
 	.long sys_ni_syscall
 	.long sys_ni_syscall
-	.long sys_getdents64	/* 220 */
+	.long sys_getdents64		/* 220 */
 	.long sys_gettid
 	.long sys_tkill
 	.long sys_setxattr
 	.long sys_lsetxattr
-	.long sys_fsetxattr	/* 225 */
+	.long sys_fsetxattr		/* 225 */
 	.long sys_getxattr
 	.long sys_lgetxattr
 	.long sys_fgetxattr
 	.long sys_listxattr
-	.long sys_llistxattr	/* 230 */
+	.long sys_llistxattr		/* 230 */
 	.long sys_flistxattr
 	.long sys_removexattr
 	.long sys_lremovexattr
 	.long sys_fremovexattr
-	.long sys_futex		/* 235 */
+	.long sys_futex			/* 235 */
 	.long sys_sendfile64
-	.long sys_ni_syscall	/* sys_mincore */
-	.long sys_ni_syscall	/* sys_madvise */
+	.long sys_mincore
+	.long sys_madvise
 	.long sys_fcntl64
-	.long sys_readahead	/* 240 */
+	.long sys_readahead		/* 240 */
 	.long sys_io_setup
 	.long sys_io_destroy
 	.long sys_io_getevents
 	.long sys_io_submit
-	.long sys_io_cancel	/* 245 */
+	.long sys_io_cancel		/* 245 */
 	.long sys_fadvise64
 	.long sys_exit_group
 	.long sys_lookup_dcookie
 	.long sys_epoll_create
-	.long sys_epoll_ctl	/* 250 */
+	.long sys_epoll_ctl		/* 250 */
 	.long sys_epoll_wait
-	.long sys_ni_syscall	/* sys_remap_file_pages */
+	.long sys_remap_file_pages
 	.long sys_set_tid_address
 	.long sys_timer_create
-	.long sys_timer_settime	/* 255 */
+	.long sys_timer_settime		/* 255 */
 	.long sys_timer_gettime
 	.long sys_timer_getoverrun
 	.long sys_timer_delete
 	.long sys_clock_settime
-	.long sys_clock_gettime	/* 260 */
+	.long sys_clock_gettime		/* 260 */
 	.long sys_clock_getres
 	.long sys_clock_nanosleep
 	.long sys_statfs64
 	.long sys_fstatfs64
-	.long sys_tgkill	/* 265 */
+	.long sys_tgkill		/* 265 */
 	.long sys_utimes
 	.long sys_fadvise64_64
-	.long sys_mbind	
+	.long sys_mbind
 	.long sys_get_mempolicy
-	.long sys_set_mempolicy	/* 270 */
+	.long sys_set_mempolicy		/* 270 */
 	.long sys_mq_open
 	.long sys_mq_unlink
 	.long sys_mq_timedsend
 	.long sys_mq_timedreceive
-	.long sys_mq_notify	/* 275 */
+	.long sys_mq_notify		/* 275 */
 	.long sys_mq_getsetattr
 	.long sys_waitid
-	.long sys_ni_syscall	/* for sys_vserver */
+	.long sys_ni_syscall		/* for sys_vserver */
 	.long sys_add_key
-	.long sys_request_key	/* 280 */
+	.long sys_request_key		/* 280 */
 	.long sys_keyctl
 	.long sys_ioprio_set
 	.long sys_ioprio_get
@@ -319,8 +322,8 @@ ENTRY(sys_call_table)
 	.long sys_readlinkat
 	.long sys_fchmodat
 	.long sys_faccessat		/* 300 */
-	.long sys_ni_syscall		/* Reserved for pselect6 */
-	.long sys_ni_syscall		/* Reserved for ppoll */
+	.long sys_pselect6
+	.long sys_ppoll
 	.long sys_unshare
 	.long sys_set_robust_list
 	.long sys_get_robust_list	/* 305 */
@@ -363,7 +366,3 @@ ENTRY(sys_call_table)
 	.long sys_clock_adjtime
 	.long sys_syncfs
 
-	.rept NR_syscalls-(.-sys_call_table)/4
-		.long sys_ni_syscall
-	.endr
-
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index d8a214f11ac..e5550ce4e0e 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -217,16 +217,12 @@ static struct clocksource clocksource_microblaze = {
 	.rating		= 300,
 	.read		= microblaze_read,
 	.mask		= CLOCKSOURCE_MASK(32),
-	.shift		= 8, /* I can shift it */
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static int __init microblaze_clocksource_init(void)
 {
-	clocksource_microblaze.mult =
-			clocksource_hz2mult(timer_clock_freq,
-						clocksource_microblaze.shift);
-	if (clocksource_register(&clocksource_microblaze))
+	if (clocksource_register_hz(&clocksource_microblaze, timer_clock_freq))
 		panic("failed to register clocksource");
 
 	/* stop timer1 */
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index 7ff9b549204..aef6c917b45 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -11,6 +11,7 @@ platforms += dec
 platforms += emma
 platforms += jazz
 platforms += jz4740
+platforms += lantiq
 platforms += lasat
 platforms += loongson
 platforms += mipssim
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 351c80fbba7..cef1a854487 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -212,6 +212,24 @@ config MACH_JZ4740
 	select HAVE_PWM
 	select HAVE_CLK
 
+config LANTIQ
+	bool "Lantiq based platforms"
+	select DMA_NONCOHERENT
+	select IRQ_CPU
+	select CEVT_R4K
+	select CSRC_R4K
+	select SYS_HAS_CPU_MIPS32_R1
+	select SYS_HAS_CPU_MIPS32_R2
+	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_32BIT_KERNEL
+	select SYS_SUPPORTS_MULTITHREADING
+	select SYS_HAS_EARLY_PRINTK
+	select ARCH_REQUIRE_GPIOLIB
+	select SWAP_IO_SPACE
+	select BOOT_RAW
+	select HAVE_CLK
+	select MIPS_MACHINE
+
 config LASAT
 	bool "LASAT Networks platforms"
 	select CEVT_R4K
@@ -736,6 +754,33 @@ config CAVIUM_OCTEON_REFERENCE_BOARD
 		Hikari
 	  Say Y here for most Octeon reference boards.
 
+config NLM_XLR_BOARD
+	bool "Netlogic XLR/XLS based systems"
+	depends on EXPERIMENTAL
+	select BOOT_ELF32
+	select NLM_COMMON
+	select NLM_XLR
+	select SYS_HAS_CPU_XLR
+	select SYS_SUPPORTS_SMP
+	select HW_HAS_PCI
+	select SWAP_IO_SPACE
+	select SYS_SUPPORTS_32BIT_KERNEL
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select 64BIT_PHYS_ADDR
+	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_HIGHMEM
+	select DMA_COHERENT
+	select NR_CPUS_DEFAULT_32
+	select CEVT_R4K
+	select CSRC_R4K
+	select IRQ_CPU
+	select ZONE_DMA if 64BIT
+	select SYNC_R4K
+	select SYS_HAS_EARLY_PRINTK
+	help
+	  Support for systems based on Netlogic XLR and XLS processors.
+	  Say Y here if you have a XLR or XLS based board.
+
 endchoice
 
 source "arch/mips/alchemy/Kconfig"
@@ -743,6 +788,7 @@ source "arch/mips/ath79/Kconfig"
 source "arch/mips/bcm63xx/Kconfig"
 source "arch/mips/jazz/Kconfig"
 source "arch/mips/jz4740/Kconfig"
+source "arch/mips/lantiq/Kconfig"
 source "arch/mips/lasat/Kconfig"
 source "arch/mips/pmc-sierra/Kconfig"
 source "arch/mips/powertv/Kconfig"
@@ -752,6 +798,7 @@ source "arch/mips/txx9/Kconfig"
 source "arch/mips/vr41xx/Kconfig"
 source "arch/mips/cavium-octeon/Kconfig"
 source "arch/mips/loongson/Kconfig"
+source "arch/mips/netlogic/Kconfig"
 
 endmenu
 
@@ -1420,6 +1467,17 @@ config CPU_BMIPS5000
 	help
 	  Broadcom BMIPS5000 processors.
 
+config CPU_XLR
+	bool "Netlogic XLR SoC"
+	depends on SYS_HAS_CPU_XLR
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select CPU_SUPPORTS_64BIT_KERNEL
+	select CPU_SUPPORTS_HIGHMEM
+	select WEAK_ORDERING
+	select WEAK_REORDERING_BEYOND_LLSC
+	select CPU_SUPPORTS_HUGEPAGES
+	help
+	  Netlogic Microsystems XLR/XLS processors.
 endchoice
 
 if CPU_LOONGSON2F
@@ -1550,6 +1608,9 @@ config SYS_HAS_CPU_BMIPS4380
 config SYS_HAS_CPU_BMIPS5000
 	bool
 
+config SYS_HAS_CPU_XLR
+	bool
+
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
@@ -2334,6 +2395,7 @@ config MMU
 
 config I8253
 	bool
+	select CLKSRC_I8253
 	select MIPS_EXTERNAL_TIMER
 
 config ZONE_DMA32
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 53e3514ba10..884819cd060 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -191,6 +191,18 @@ endif
 #
 include $(srctree)/arch/mips/Kbuild.platforms
 
+#
+# NETLOGIC SOC Common (common)
+#
+cflags-$(CONFIG_NLM_COMMON)		+= -I$(srctree)/arch/mips/include/asm/mach-netlogic
+cflags-$(CONFIG_NLM_COMMON)		+= -I$(srctree)/arch/mips/include/asm/netlogic
+
+#
+# NETLOGIC XLR/XLS SoC, Simulator and boards
+#
+core-$(CONFIG_NLM_XLR)      		+= arch/mips/netlogic/xlr/
+load-$(CONFIG_NLM_XLR_BOARD)		+= 0xffffffff84000000
+
 cflags-y			+= -I$(srctree)/arch/mips/include/asm/mach-generic
 drivers-$(CONFIG_PCI)		+= arch/mips/pci/
 
diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c
index ca0506a8585..3a5abb54d50 100644
--- a/arch/mips/alchemy/common/dbdma.c
+++ b/arch/mips/alchemy/common/dbdma.c
@@ -36,7 +36,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/au1xxx_dbdma.h>
 
@@ -58,7 +58,8 @@ static DEFINE_SPINLOCK(au1xxx_dbdma_spin_lock);
 /* I couldn't find a macro that did this... */
 #define ALIGN_ADDR(x, a)	((((u32)(x)) + (a-1)) & ~(a-1))
 
-static dbdma_global_t *dbdma_gptr = (dbdma_global_t *)DDMA_GLOBAL_BASE;
+static dbdma_global_t *dbdma_gptr =
+			(dbdma_global_t *)KSEG1ADDR(AU1550_DBDMA_CONF_PHYS_ADDR);
 static int dbdma_initialized;
 
 static dbdev_tab_t dbdev_tab[] = {
@@ -299,7 +300,7 @@ u32 au1xxx_dbdma_chan_alloc(u32 srcid, u32 destid,
 	if (ctp != NULL) {
 		memset(ctp, 0, sizeof(chan_tab_t));
 		ctp->chan_index = chan = i;
-		dcp = DDMA_CHANNEL_BASE;
+		dcp = KSEG1ADDR(AU1550_DBDMA_PHYS_ADDR);
 		dcp += (0x0100 * chan);
 		ctp->chan_ptr = (au1x_dma_chan_t *)dcp;
 		cp = (au1x_dma_chan_t *)dcp;
@@ -958,105 +959,75 @@ u32 au1xxx_dbdma_put_dscr(u32 chanid, au1x_ddma_desc_t *dscr)
 }
 
 
-struct alchemy_dbdma_sysdev {
-	struct sys_device sysdev;
-	u32 pm_regs[NUM_DBDMA_CHANS + 1][6];
-};
+static unsigned long alchemy_dbdma_pm_data[NUM_DBDMA_CHANS + 1][6];
 
-static int alchemy_dbdma_suspend(struct sys_device *dev,
-				 pm_message_t state)
+static int alchemy_dbdma_suspend(void)
 {
-	struct alchemy_dbdma_sysdev *sdev =
-		container_of(dev, struct alchemy_dbdma_sysdev, sysdev);
 	int i;
-	u32 addr;
+	void __iomem *addr;
 
-	addr = DDMA_GLOBAL_BASE;
-	sdev->pm_regs[0][0] = au_readl(addr + 0x00);
-	sdev->pm_regs[0][1] = au_readl(addr + 0x04);
-	sdev->pm_regs[0][2] = au_readl(addr + 0x08);
-	sdev->pm_regs[0][3] = au_readl(addr + 0x0c);
+	addr = (void __iomem *)KSEG1ADDR(AU1550_DBDMA_CONF_PHYS_ADDR);
+	alchemy_dbdma_pm_data[0][0] = __raw_readl(addr + 0x00);
+	alchemy_dbdma_pm_data[0][1] = __raw_readl(addr + 0x04);
+	alchemy_dbdma_pm_data[0][2] = __raw_readl(addr + 0x08);
+	alchemy_dbdma_pm_data[0][3] = __raw_readl(addr + 0x0c);
 
 	/* save channel configurations */
-	for (i = 1, addr = DDMA_CHANNEL_BASE; i <= NUM_DBDMA_CHANS; i++) {
-		sdev->pm_regs[i][0] = au_readl(addr + 0x00);
-		sdev->pm_regs[i][1] = au_readl(addr + 0x04);
-		sdev->pm_regs[i][2] = au_readl(addr + 0x08);
-		sdev->pm_regs[i][3] = au_readl(addr + 0x0c);
-		sdev->pm_regs[i][4] = au_readl(addr + 0x10);
-		sdev->pm_regs[i][5] = au_readl(addr + 0x14);
+	addr = (void __iomem *)KSEG1ADDR(AU1550_DBDMA_PHYS_ADDR);
+	for (i = 1; i <= NUM_DBDMA_CHANS; i++) {
+		alchemy_dbdma_pm_data[i][0] = __raw_readl(addr + 0x00);
+		alchemy_dbdma_pm_data[i][1] = __raw_readl(addr + 0x04);
+		alchemy_dbdma_pm_data[i][2] = __raw_readl(addr + 0x08);
+		alchemy_dbdma_pm_data[i][3] = __raw_readl(addr + 0x0c);
+		alchemy_dbdma_pm_data[i][4] = __raw_readl(addr + 0x10);
+		alchemy_dbdma_pm_data[i][5] = __raw_readl(addr + 0x14);
 
 		/* halt channel */
-		au_writel(sdev->pm_regs[i][0] & ~1, addr + 0x00);
-		au_sync();
-		while (!(au_readl(addr + 0x14) & 1))
-			au_sync();
+		__raw_writel(alchemy_dbdma_pm_data[i][0] & ~1, addr + 0x00);
+		wmb();
+		while (!(__raw_readl(addr + 0x14) & 1))
+			wmb();
 
 		addr += 0x100;	/* next channel base */
 	}
 	/* disable channel interrupts */
-	au_writel(0, DDMA_GLOBAL_BASE + 0x0c);
-	au_sync();
+	addr = (void __iomem *)KSEG1ADDR(AU1550_DBDMA_CONF_PHYS_ADDR);
+	__raw_writel(0, addr + 0x0c);
+	wmb();
 
 	return 0;
 }
 
-static int alchemy_dbdma_resume(struct sys_device *dev)
+static void alchemy_dbdma_resume(void)
 {
-	struct alchemy_dbdma_sysdev *sdev =
-		container_of(dev, struct alchemy_dbdma_sysdev, sysdev);
 	int i;
-	u32 addr;
+	void __iomem *addr;
 
-	addr = DDMA_GLOBAL_BASE;
-	au_writel(sdev->pm_regs[0][0], addr + 0x00);
-	au_writel(sdev->pm_regs[0][1], addr + 0x04);
-	au_writel(sdev->pm_regs[0][2], addr + 0x08);
-	au_writel(sdev->pm_regs[0][3], addr + 0x0c);
+	addr = (void __iomem *)KSEG1ADDR(AU1550_DBDMA_CONF_PHYS_ADDR);
+	__raw_writel(alchemy_dbdma_pm_data[0][0], addr + 0x00);
+	__raw_writel(alchemy_dbdma_pm_data[0][1], addr + 0x04);
+	__raw_writel(alchemy_dbdma_pm_data[0][2], addr + 0x08);
+	__raw_writel(alchemy_dbdma_pm_data[0][3], addr + 0x0c);
 
 	/* restore channel configurations */
-	for (i = 1, addr = DDMA_CHANNEL_BASE; i <= NUM_DBDMA_CHANS; i++) {
-		au_writel(sdev->pm_regs[i][0], addr + 0x00);
-		au_writel(sdev->pm_regs[i][1], addr + 0x04);
-		au_writel(sdev->pm_regs[i][2], addr + 0x08);
-		au_writel(sdev->pm_regs[i][3], addr + 0x0c);
-		au_writel(sdev->pm_regs[i][4], addr + 0x10);
-		au_writel(sdev->pm_regs[i][5], addr + 0x14);
-		au_sync();
+	addr = (void __iomem *)KSEG1ADDR(AU1550_DBDMA_PHYS_ADDR);
+	for (i = 1; i <= NUM_DBDMA_CHANS; i++) {
+		__raw_writel(alchemy_dbdma_pm_data[i][0], addr + 0x00);
+		__raw_writel(alchemy_dbdma_pm_data[i][1], addr + 0x04);
+		__raw_writel(alchemy_dbdma_pm_data[i][2], addr + 0x08);
+		__raw_writel(alchemy_dbdma_pm_data[i][3], addr + 0x0c);
+		__raw_writel(alchemy_dbdma_pm_data[i][4], addr + 0x10);
+		__raw_writel(alchemy_dbdma_pm_data[i][5], addr + 0x14);
+		wmb();
 		addr += 0x100;	/* next channel base */
 	}
-
-	return 0;
 }
 
-static struct sysdev_class alchemy_dbdma_sysdev_class = {
-	.name		= "dbdma",
+static struct syscore_ops alchemy_dbdma_syscore_ops = {
 	.suspend	= alchemy_dbdma_suspend,
 	.resume		= alchemy_dbdma_resume,
 };
 
-static int __init alchemy_dbdma_sysdev_init(void)
-{
-	struct alchemy_dbdma_sysdev *sdev;
-	int ret;
-
-	ret = sysdev_class_register(&alchemy_dbdma_sysdev_class);
-	if (ret)
-		return ret;
-
-	sdev = kzalloc(sizeof(struct alchemy_dbdma_sysdev), GFP_KERNEL);
-	if (!sdev)
-		return -ENOMEM;
-
-	sdev->sysdev.id = -1;
-	sdev->sysdev.cls = &alchemy_dbdma_sysdev_class;
-	ret = sysdev_register(&sdev->sysdev);
-	if (ret)
-		kfree(sdev);
-
-	return ret;
-}
-
 static int __init au1xxx_dbdma_init(void)
 {
 	int irq_nr, ret;
@@ -1084,11 +1055,7 @@ static int __init au1xxx_dbdma_init(void)
 	else {
 		dbdma_initialized = 1;
 		printk(KERN_INFO "Alchemy DBDMA initialized\n");
-		ret = alchemy_dbdma_sysdev_init();
-		if (ret) {
-			printk(KERN_ERR "DBDMA PM init failed\n");
-			ret = 0;
-		}
+		register_syscore_ops(&alchemy_dbdma_syscore_ops);
 	}
 
 	return ret;
diff --git a/arch/mips/alchemy/common/dma.c b/arch/mips/alchemy/common/dma.c
index d5278877891..347980e79a8 100644
--- a/arch/mips/alchemy/common/dma.c
+++ b/arch/mips/alchemy/common/dma.c
@@ -58,6 +58,9 @@
  * returned from request_dma.
  */
 
+/* DMA Channel register block spacing */
+#define DMA_CHANNEL_LEN		0x00000100
+
 DEFINE_SPINLOCK(au1000_dma_spin_lock);
 
 struct dma_chan au1000_dma_table[NUM_AU1000_DMA_CHANNELS] = {
@@ -77,22 +80,23 @@ static const struct dma_dev {
 	unsigned int fifo_addr;
 	unsigned int dma_mode;
 } dma_dev_table[DMA_NUM_DEV] = {
-	{UART0_ADDR + UART_TX, 0},
-	{UART0_ADDR + UART_RX, 0},
-	{0, 0},
-	{0, 0},
-	{AC97C_DATA, DMA_DW16 },          /* coherent */
-	{AC97C_DATA, DMA_DR | DMA_DW16 }, /* coherent */
-	{UART3_ADDR + UART_TX, DMA_DW8 | DMA_NC},
-	{UART3_ADDR + UART_RX, DMA_DR | DMA_DW8 | DMA_NC},
-	{USBD_EP0RD, DMA_DR | DMA_DW8 | DMA_NC},
-	{USBD_EP0WR, DMA_DW8 | DMA_NC},
-	{USBD_EP2WR, DMA_DW8 | DMA_NC},
-	{USBD_EP3WR, DMA_DW8 | DMA_NC},
-	{USBD_EP4RD, DMA_DR | DMA_DW8 | DMA_NC},
-	{USBD_EP5RD, DMA_DR | DMA_DW8 | DMA_NC},
-	{I2S_DATA, DMA_DW32 | DMA_NC},
-	{I2S_DATA, DMA_DR | DMA_DW32 | DMA_NC}
+	{ AU1000_UART0_PHYS_ADDR + 0x04, DMA_DW8 },		/* UART0_TX */
+	{ AU1000_UART0_PHYS_ADDR + 0x00, DMA_DW8 | DMA_DR },	/* UART0_RX */
+	{ 0, 0 },	/* DMA_REQ0 */
+	{ 0, 0 },	/* DMA_REQ1 */
+	{ AU1000_AC97_PHYS_ADDR + 0x08, DMA_DW16 },		/* AC97 TX c */
+	{ AU1000_AC97_PHYS_ADDR + 0x08, DMA_DW16 | DMA_DR },	/* AC97 RX c */
+	{ AU1000_UART3_PHYS_ADDR + 0x04, DMA_DW8 | DMA_NC },	/* UART3_TX */
+	{ AU1000_UART3_PHYS_ADDR + 0x00, DMA_DW8 | DMA_NC | DMA_DR }, /* UART3_RX */
+	{ AU1000_USBD_PHYS_ADDR + 0x00, DMA_DW8 | DMA_NC | DMA_DR }, /* EP0RD */
+	{ AU1000_USBD_PHYS_ADDR + 0x04, DMA_DW8 | DMA_NC }, /* EP0WR */
+	{ AU1000_USBD_PHYS_ADDR + 0x08, DMA_DW8 | DMA_NC }, /* EP2WR */
+	{ AU1000_USBD_PHYS_ADDR + 0x0c, DMA_DW8 | DMA_NC }, /* EP3WR */
+	{ AU1000_USBD_PHYS_ADDR + 0x10, DMA_DW8 | DMA_NC | DMA_DR }, /* EP4RD */
+	{ AU1000_USBD_PHYS_ADDR + 0x14, DMA_DW8 | DMA_NC | DMA_DR }, /* EP5RD */
+	/* on Au1500, these 2 are DMA_REQ2/3 (GPIO208/209) instead! */
+	{ AU1000_I2S_PHYS_ADDR + 0x00, DMA_DW32 | DMA_NC},	/* I2S TX */
+	{ AU1000_I2S_PHYS_ADDR + 0x00, DMA_DW32 | DMA_NC | DMA_DR}, /* I2S RX */
 };
 
 int au1000_dma_read_proc(char *buf, char **start, off_t fpos,
@@ -123,10 +127,10 @@ int au1000_dma_read_proc(char *buf, char **start, off_t fpos,
 
 /* Device FIFO addresses and default DMA modes - 2nd bank */
 static const struct dma_dev dma_dev_table_bank2[DMA_NUM_DEV_BANK2] = {
-	{ SD0_XMIT_FIFO, DMA_DS | DMA_DW8 },		/* coherent */
-	{ SD0_RECV_FIFO, DMA_DS | DMA_DR | DMA_DW8 },	/* coherent */
-	{ SD1_XMIT_FIFO, DMA_DS | DMA_DW8 },		/* coherent */
-	{ SD1_RECV_FIFO, DMA_DS | DMA_DR | DMA_DW8 }	/* coherent */
+	{ AU1100_SD0_PHYS_ADDR + 0x00, DMA_DS | DMA_DW8 },		/* coherent */
+	{ AU1100_SD0_PHYS_ADDR + 0x04, DMA_DS | DMA_DW8 | DMA_DR },	/* coherent */
+	{ AU1100_SD1_PHYS_ADDR + 0x00, DMA_DS | DMA_DW8 },		/* coherent */
+	{ AU1100_SD1_PHYS_ADDR + 0x04, DMA_DS | DMA_DW8 | DMA_DR }	/* coherent */
 };
 
 void dump_au1000_dma_channel(unsigned int dmanr)
@@ -202,7 +206,7 @@ int request_au1000_dma(int dev_id, const char *dev_str,
 	}
 
 	/* fill it in */
-	chan->io = DMA_CHANNEL_BASE + i * DMA_CHANNEL_LEN;
+	chan->io = KSEG1ADDR(AU1000_DMA_PHYS_ADDR) + i * DMA_CHANNEL_LEN;
 	chan->dev_id = dev_id;
 	chan->dev_str = dev_str;
 	chan->fifo_addr = dev->fifo_addr;
diff --git a/arch/mips/alchemy/common/irq.c b/arch/mips/alchemy/common/irq.c
index 55dd7c88851..8b60ba0675e 100644
--- a/arch/mips/alchemy/common/irq.c
+++ b/arch/mips/alchemy/common/irq.c
@@ -30,7 +30,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/slab.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
@@ -39,6 +39,36 @@
 #include <asm/mach-pb1x00/pb1000.h>
 #endif
 
+/* Interrupt Controller register offsets */
+#define IC_CFG0RD	0x40
+#define IC_CFG0SET	0x40
+#define IC_CFG0CLR	0x44
+#define IC_CFG1RD	0x48
+#define IC_CFG1SET	0x48
+#define IC_CFG1CLR	0x4C
+#define IC_CFG2RD	0x50
+#define IC_CFG2SET	0x50
+#define IC_CFG2CLR	0x54
+#define IC_REQ0INT	0x54
+#define IC_SRCRD	0x58
+#define IC_SRCSET	0x58
+#define IC_SRCCLR	0x5C
+#define IC_REQ1INT	0x5C
+#define IC_ASSIGNRD	0x60
+#define IC_ASSIGNSET	0x60
+#define IC_ASSIGNCLR	0x64
+#define IC_WAKERD	0x68
+#define IC_WAKESET	0x68
+#define IC_WAKECLR	0x6C
+#define IC_MASKRD	0x70
+#define IC_MASKSET	0x70
+#define IC_MASKCLR	0x74
+#define IC_RISINGRD	0x78
+#define IC_RISINGCLR	0x78
+#define IC_FALLINGRD	0x7C
+#define IC_FALLINGCLR	0x7C
+#define IC_TESTBIT	0x80
+
 static int au1x_ic_settype(struct irq_data *d, unsigned int flow_type);
 
 /* NOTE on interrupt priorities: The original writers of this code said:
@@ -221,89 +251,101 @@ struct au1xxx_irqmap au1200_irqmap[] __initdata = {
 static void au1x_ic0_unmask(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC0_INT_BASE;
-	au_writel(1 << bit, IC0_MASKSET);
-	au_writel(1 << bit, IC0_WAKESET);
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
+
+	__raw_writel(1 << bit, base + IC_MASKSET);
+	__raw_writel(1 << bit, base + IC_WAKESET);
+	wmb();
 }
 
 static void au1x_ic1_unmask(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC1_INT_BASE;
-	au_writel(1 << bit, IC1_MASKSET);
-	au_writel(1 << bit, IC1_WAKESET);
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
+
+	__raw_writel(1 << bit, base + IC_MASKSET);
+	__raw_writel(1 << bit, base + IC_WAKESET);
 
 /* very hacky. does the pb1000 cpld auto-disable this int?
  * nowhere in the current kernel sources is it disabled.	--mlau
  */
 #if defined(CONFIG_MIPS_PB1000)
 	if (d->irq == AU1000_GPIO15_INT)
-		au_writel(0x4000, PB1000_MDR); /* enable int */
+		__raw_writel(0x4000, (void __iomem *)PB1000_MDR); /* enable int */
 #endif
-	au_sync();
+	wmb();
 }
 
 static void au1x_ic0_mask(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC0_INT_BASE;
-	au_writel(1 << bit, IC0_MASKCLR);
-	au_writel(1 << bit, IC0_WAKECLR);
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
+
+	__raw_writel(1 << bit, base + IC_MASKCLR);
+	__raw_writel(1 << bit, base + IC_WAKECLR);
+	wmb();
 }
 
 static void au1x_ic1_mask(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC1_INT_BASE;
-	au_writel(1 << bit, IC1_MASKCLR);
-	au_writel(1 << bit, IC1_WAKECLR);
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
+
+	__raw_writel(1 << bit, base + IC_MASKCLR);
+	__raw_writel(1 << bit, base + IC_WAKECLR);
+	wmb();
 }
 
 static void au1x_ic0_ack(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC0_INT_BASE;
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
 
 	/*
 	 * This may assume that we don't get interrupts from
 	 * both edges at once, or if we do, that we don't care.
 	 */
-	au_writel(1 << bit, IC0_FALLINGCLR);
-	au_writel(1 << bit, IC0_RISINGCLR);
-	au_sync();
+	__raw_writel(1 << bit, base + IC_FALLINGCLR);
+	__raw_writel(1 << bit, base + IC_RISINGCLR);
+	wmb();
 }
 
 static void au1x_ic1_ack(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC1_INT_BASE;
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
 
 	/*
 	 * This may assume that we don't get interrupts from
 	 * both edges at once, or if we do, that we don't care.
 	 */
-	au_writel(1 << bit, IC1_FALLINGCLR);
-	au_writel(1 << bit, IC1_RISINGCLR);
-	au_sync();
+	__raw_writel(1 << bit, base + IC_FALLINGCLR);
+	__raw_writel(1 << bit, base + IC_RISINGCLR);
+	wmb();
 }
 
 static void au1x_ic0_maskack(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC0_INT_BASE;
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
 
-	au_writel(1 << bit, IC0_WAKECLR);
-	au_writel(1 << bit, IC0_MASKCLR);
-	au_writel(1 << bit, IC0_RISINGCLR);
-	au_writel(1 << bit, IC0_FALLINGCLR);
-	au_sync();
+	__raw_writel(1 << bit, base + IC_WAKECLR);
+	__raw_writel(1 << bit, base + IC_MASKCLR);
+	__raw_writel(1 << bit, base + IC_RISINGCLR);
+	__raw_writel(1 << bit, base + IC_FALLINGCLR);
+	wmb();
 }
 
 static void au1x_ic1_maskack(struct irq_data *d)
 {
 	unsigned int bit = d->irq - AU1000_INTC1_INT_BASE;
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
 
-	au_writel(1 << bit, IC1_WAKECLR);
-	au_writel(1 << bit, IC1_MASKCLR);
-	au_writel(1 << bit, IC1_RISINGCLR);
-	au_writel(1 << bit, IC1_FALLINGCLR);
-	au_sync();
+	__raw_writel(1 << bit, base + IC_WAKECLR);
+	__raw_writel(1 << bit, base + IC_MASKCLR);
+	__raw_writel(1 << bit, base + IC_RISINGCLR);
+	__raw_writel(1 << bit, base + IC_FALLINGCLR);
+	wmb();
 }
 
 static int au1x_ic1_setwake(struct irq_data *d, unsigned int on)
@@ -318,13 +360,13 @@ static int au1x_ic1_setwake(struct irq_data *d, unsigned int on)
 		return -EINVAL;
 
 	local_irq_save(flags);
-	wakemsk = au_readl(SYS_WAKEMSK);
+	wakemsk = __raw_readl((void __iomem *)SYS_WAKEMSK);
 	if (on)
 		wakemsk |= 1 << bit;
 	else
 		wakemsk &= ~(1 << bit);
-	au_writel(wakemsk, SYS_WAKEMSK);
-	au_sync();
+	__raw_writel(wakemsk, (void __iomem *)SYS_WAKEMSK);
+	wmb();
 	local_irq_restore(flags);
 
 	return 0;
@@ -356,81 +398,74 @@ static struct irq_chip au1x_ic1_chip = {
 static int au1x_ic_settype(struct irq_data *d, unsigned int flow_type)
 {
 	struct irq_chip *chip;
-	unsigned long icr[6];
-	unsigned int bit, ic, irq = d->irq;
+	unsigned int bit, irq = d->irq;
 	irq_flow_handler_t handler = NULL;
 	unsigned char *name = NULL;
+	void __iomem *base;
 	int ret;
 
 	if (irq >= AU1000_INTC1_INT_BASE) {
 		bit = irq - AU1000_INTC1_INT_BASE;
 		chip = &au1x_ic1_chip;
-		ic = 1;
+		base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
 	} else {
 		bit = irq - AU1000_INTC0_INT_BASE;
 		chip = &au1x_ic0_chip;
-		ic = 0;
+		base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
 	}
 
 	if (bit > 31)
 		return -EINVAL;
 
-	icr[0] = ic ? IC1_CFG0SET : IC0_CFG0SET;
-	icr[1] = ic ? IC1_CFG1SET : IC0_CFG1SET;
-	icr[2] = ic ? IC1_CFG2SET : IC0_CFG2SET;
-	icr[3] = ic ? IC1_CFG0CLR : IC0_CFG0CLR;
-	icr[4] = ic ? IC1_CFG1CLR : IC0_CFG1CLR;
-	icr[5] = ic ? IC1_CFG2CLR : IC0_CFG2CLR;
-
 	ret = 0;
 
 	switch (flow_type) {	/* cfgregs 2:1:0 */
 	case IRQ_TYPE_EDGE_RISING:	/* 0:0:1 */
-		au_writel(1 << bit, icr[5]);
-		au_writel(1 << bit, icr[4]);
-		au_writel(1 << bit, icr[0]);
+		__raw_writel(1 << bit, base + IC_CFG2CLR);
+		__raw_writel(1 << bit, base + IC_CFG1CLR);
+		__raw_writel(1 << bit, base + IC_CFG0SET);
 		handler = handle_edge_irq;
 		name = "riseedge";
 		break;
 	case IRQ_TYPE_EDGE_FALLING:	/* 0:1:0 */
-		au_writel(1 << bit, icr[5]);
-		au_writel(1 << bit, icr[1]);
-		au_writel(1 << bit, icr[3]);
+		__raw_writel(1 << bit, base + IC_CFG2CLR);
+		__raw_writel(1 << bit, base + IC_CFG1SET);
+		__raw_writel(1 << bit, base + IC_CFG0CLR);
 		handler = handle_edge_irq;
 		name = "falledge";
 		break;
 	case IRQ_TYPE_EDGE_BOTH:	/* 0:1:1 */
-		au_writel(1 << bit, icr[5]);
-		au_writel(1 << bit, icr[1]);
-		au_writel(1 << bit, icr[0]);
+		__raw_writel(1 << bit, base + IC_CFG2CLR);
+		__raw_writel(1 << bit, base + IC_CFG1SET);
+		__raw_writel(1 << bit, base + IC_CFG0SET);
 		handler = handle_edge_irq;
 		name = "bothedge";
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:	/* 1:0:1 */
-		au_writel(1 << bit, icr[2]);
-		au_writel(1 << bit, icr[4]);
-		au_writel(1 << bit, icr[0]);
+		__raw_writel(1 << bit, base + IC_CFG2SET);
+		__raw_writel(1 << bit, base + IC_CFG1CLR);
+		__raw_writel(1 << bit, base + IC_CFG0SET);
 		handler = handle_level_irq;
 		name = "hilevel";
 		break;
 	case IRQ_TYPE_LEVEL_LOW:	/* 1:1:0 */
-		au_writel(1 << bit, icr[2]);
-		au_writel(1 << bit, icr[1]);
-		au_writel(1 << bit, icr[3]);
+		__raw_writel(1 << bit, base + IC_CFG2SET);
+		__raw_writel(1 << bit, base + IC_CFG1SET);
+		__raw_writel(1 << bit, base + IC_CFG0CLR);
 		handler = handle_level_irq;
 		name = "lowlevel";
 		break;
 	case IRQ_TYPE_NONE:		/* 0:0:0 */
-		au_writel(1 << bit, icr[5]);
-		au_writel(1 << bit, icr[4]);
-		au_writel(1 << bit, icr[3]);
+		__raw_writel(1 << bit, base + IC_CFG2CLR);
+		__raw_writel(1 << bit, base + IC_CFG1CLR);
+		__raw_writel(1 << bit, base + IC_CFG0CLR);
 		break;
 	default:
 		ret = -EINVAL;
 	}
 	__irq_set_chip_handler_name_locked(d->irq, chip, handler, name);
 
-	au_sync();
+	wmb();
 
 	return ret;
 }
@@ -444,21 +479,21 @@ asmlinkage void plat_irq_dispatch(void)
 		off = MIPS_CPU_IRQ_BASE + 7;
 		goto handle;
 	} else if (pending & CAUSEF_IP2) {
-		s = IC0_REQ0INT;
+		s = KSEG1ADDR(AU1000_IC0_PHYS_ADDR) + IC_REQ0INT;
 		off = AU1000_INTC0_INT_BASE;
 	} else if (pending & CAUSEF_IP3) {
-		s = IC0_REQ1INT;
+		s = KSEG1ADDR(AU1000_IC0_PHYS_ADDR) + IC_REQ1INT;
 		off = AU1000_INTC0_INT_BASE;
 	} else if (pending & CAUSEF_IP4) {
-		s = IC1_REQ0INT;
+		s = KSEG1ADDR(AU1000_IC1_PHYS_ADDR) + IC_REQ0INT;
 		off = AU1000_INTC1_INT_BASE;
 	} else if (pending & CAUSEF_IP5) {
-		s = IC1_REQ1INT;
+		s = KSEG1ADDR(AU1000_IC1_PHYS_ADDR) + IC_REQ1INT;
 		off = AU1000_INTC1_INT_BASE;
 	} else
 		goto spurious;
 
-	s = au_readl(s);
+	s = __raw_readl((void __iomem *)s);
 	if (unlikely(!s)) {
 spurious:
 		spurious_interrupt();
@@ -469,48 +504,42 @@ handle:
 	do_IRQ(off);
 }
 
+
+static inline void ic_init(void __iomem *base)
+{
+	/* initialize interrupt controller to a safe state */
+	__raw_writel(0xffffffff, base + IC_CFG0CLR);
+	__raw_writel(0xffffffff, base + IC_CFG1CLR);
+	__raw_writel(0xffffffff, base + IC_CFG2CLR);
+	__raw_writel(0xffffffff, base + IC_MASKCLR);
+	__raw_writel(0xffffffff, base + IC_ASSIGNCLR);
+	__raw_writel(0xffffffff, base + IC_WAKECLR);
+	__raw_writel(0xffffffff, base + IC_SRCSET);
+	__raw_writel(0xffffffff, base + IC_FALLINGCLR);
+	__raw_writel(0xffffffff, base + IC_RISINGCLR);
+	__raw_writel(0x00000000, base + IC_TESTBIT);
+	wmb();
+}
+
 static void __init au1000_init_irq(struct au1xxx_irqmap *map)
 {
 	unsigned int bit, irq_nr;
-	int i;
-
-	/*
-	 * Initialize interrupt controllers to a safe state.
-	 */
-	au_writel(0xffffffff, IC0_CFG0CLR);
-	au_writel(0xffffffff, IC0_CFG1CLR);
-	au_writel(0xffffffff, IC0_CFG2CLR);
-	au_writel(0xffffffff, IC0_MASKCLR);
-	au_writel(0xffffffff, IC0_ASSIGNCLR);
-	au_writel(0xffffffff, IC0_WAKECLR);
-	au_writel(0xffffffff, IC0_SRCSET);
-	au_writel(0xffffffff, IC0_FALLINGCLR);
-	au_writel(0xffffffff, IC0_RISINGCLR);
-	au_writel(0x00000000, IC0_TESTBIT);
-
-	au_writel(0xffffffff, IC1_CFG0CLR);
-	au_writel(0xffffffff, IC1_CFG1CLR);
-	au_writel(0xffffffff, IC1_CFG2CLR);
-	au_writel(0xffffffff, IC1_MASKCLR);
-	au_writel(0xffffffff, IC1_ASSIGNCLR);
-	au_writel(0xffffffff, IC1_WAKECLR);
-	au_writel(0xffffffff, IC1_SRCSET);
-	au_writel(0xffffffff, IC1_FALLINGCLR);
-	au_writel(0xffffffff, IC1_RISINGCLR);
-	au_writel(0x00000000, IC1_TESTBIT);
+	void __iomem *base;
 
+	ic_init((void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR));
+	ic_init((void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR));
 	mips_cpu_irq_init();
 
 	/* register all 64 possible IC0+IC1 irq sources as type "none".
 	 * Use set_irq_type() to set edge/level behaviour at runtime.
 	 */
-	for (i = AU1000_INTC0_INT_BASE;
-	     (i < AU1000_INTC0_INT_BASE + 32); i++)
-		au1x_ic_settype(irq_get_irq_data(i), IRQ_TYPE_NONE);
+	for (irq_nr = AU1000_INTC0_INT_BASE;
+	     (irq_nr < AU1000_INTC0_INT_BASE + 32); irq_nr++)
+		au1x_ic_settype(irq_get_irq_data(irq_nr), IRQ_TYPE_NONE);
 
-	for (i = AU1000_INTC1_INT_BASE;
-	     (i < AU1000_INTC1_INT_BASE + 32); i++)
-		au1x_ic_settype(irq_get_irq_data(i), IRQ_TYPE_NONE);
+	for (irq_nr = AU1000_INTC1_INT_BASE;
+	     (irq_nr < AU1000_INTC1_INT_BASE + 32); irq_nr++)
+		au1x_ic_settype(irq_get_irq_data(irq_nr), IRQ_TYPE_NONE);
 
 	/*
 	 * Initialize IC0, which is fixed per processor.
@@ -520,13 +549,13 @@ static void __init au1000_init_irq(struct au1xxx_irqmap *map)
 
 		if (irq_nr >= AU1000_INTC1_INT_BASE) {
 			bit = irq_nr - AU1000_INTC1_INT_BASE;
-			if (map->im_request)
-				au_writel(1 << bit, IC1_ASSIGNSET);
+			base = (void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR);
 		} else {
 			bit = irq_nr - AU1000_INTC0_INT_BASE;
-			if (map->im_request)
-				au_writel(1 << bit, IC0_ASSIGNSET);
+			base = (void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR);
 		}
+		if (map->im_request)
+			__raw_writel(1 << bit, base + IC_ASSIGNSET);
 
 		au1x_ic_settype(irq_get_irq_data(irq_nr), map->im_type);
 		++map;
@@ -556,90 +585,62 @@ void __init arch_init_irq(void)
 	}
 }
 
-struct alchemy_ic_sysdev {
-	struct sys_device sysdev;
-	void __iomem *base;
-	unsigned long pmdata[7];
-};
 
-static int alchemy_ic_suspend(struct sys_device *dev, pm_message_t state)
-{
-	struct alchemy_ic_sysdev *icdev =
-			container_of(dev, struct alchemy_ic_sysdev, sysdev);
+static unsigned long alchemy_ic_pmdata[7 * 2];
 
-	icdev->pmdata[0] = __raw_readl(icdev->base + IC_CFG0RD);
-	icdev->pmdata[1] = __raw_readl(icdev->base + IC_CFG1RD);
-	icdev->pmdata[2] = __raw_readl(icdev->base + IC_CFG2RD);
-	icdev->pmdata[3] = __raw_readl(icdev->base + IC_SRCRD);
-	icdev->pmdata[4] = __raw_readl(icdev->base + IC_ASSIGNRD);
-	icdev->pmdata[5] = __raw_readl(icdev->base + IC_WAKERD);
-	icdev->pmdata[6] = __raw_readl(icdev->base + IC_MASKRD);
-
-	return 0;
+static inline void alchemy_ic_suspend_one(void __iomem *base, unsigned long *d)
+{
+	d[0] = __raw_readl(base + IC_CFG0RD);
+	d[1] = __raw_readl(base + IC_CFG1RD);
+	d[2] = __raw_readl(base + IC_CFG2RD);
+	d[3] = __raw_readl(base + IC_SRCRD);
+	d[4] = __raw_readl(base + IC_ASSIGNRD);
+	d[5] = __raw_readl(base + IC_WAKERD);
+	d[6] = __raw_readl(base + IC_MASKRD);
+	ic_init(base);		/* shut it up too while at it */
 }
 
-static int alchemy_ic_resume(struct sys_device *dev)
+static inline void alchemy_ic_resume_one(void __iomem *base, unsigned long *d)
 {
-	struct alchemy_ic_sysdev *icdev =
-			container_of(dev, struct alchemy_ic_sysdev, sysdev);
-
-	__raw_writel(0xffffffff, icdev->base + IC_MASKCLR);
-	__raw_writel(0xffffffff, icdev->base + IC_CFG0CLR);
-	__raw_writel(0xffffffff, icdev->base + IC_CFG1CLR);
-	__raw_writel(0xffffffff, icdev->base + IC_CFG2CLR);
-	__raw_writel(0xffffffff, icdev->base + IC_SRCCLR);
-	__raw_writel(0xffffffff, icdev->base + IC_ASSIGNCLR);
-	__raw_writel(0xffffffff, icdev->base + IC_WAKECLR);
-	__raw_writel(0xffffffff, icdev->base + IC_RISINGCLR);
-	__raw_writel(0xffffffff, icdev->base + IC_FALLINGCLR);
-	__raw_writel(0x00000000, icdev->base + IC_TESTBIT);
-	wmb();
-	__raw_writel(icdev->pmdata[0], icdev->base + IC_CFG0SET);
-	__raw_writel(icdev->pmdata[1], icdev->base + IC_CFG1SET);
-	__raw_writel(icdev->pmdata[2], icdev->base + IC_CFG2SET);
-	__raw_writel(icdev->pmdata[3], icdev->base + IC_SRCSET);
-	__raw_writel(icdev->pmdata[4], icdev->base + IC_ASSIGNSET);
-	__raw_writel(icdev->pmdata[5], icdev->base + IC_WAKESET);
+	ic_init(base);
+
+	__raw_writel(d[0], base + IC_CFG0SET);
+	__raw_writel(d[1], base + IC_CFG1SET);
+	__raw_writel(d[2], base + IC_CFG2SET);
+	__raw_writel(d[3], base + IC_SRCSET);
+	__raw_writel(d[4], base + IC_ASSIGNSET);
+	__raw_writel(d[5], base + IC_WAKESET);
 	wmb();
 
-	__raw_writel(icdev->pmdata[6], icdev->base + IC_MASKSET);
+	__raw_writel(d[6], base + IC_MASKSET);
 	wmb();
+}
 
+static int alchemy_ic_suspend(void)
+{
+	alchemy_ic_suspend_one((void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR),
+			       alchemy_ic_pmdata);
+	alchemy_ic_suspend_one((void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR),
+			       &alchemy_ic_pmdata[7]);
 	return 0;
 }
 
-static struct sysdev_class alchemy_ic_sysdev_class = {
-	.name		= "ic",
+static void alchemy_ic_resume(void)
+{
+	alchemy_ic_resume_one((void __iomem *)KSEG1ADDR(AU1000_IC1_PHYS_ADDR),
+			      &alchemy_ic_pmdata[7]);
+	alchemy_ic_resume_one((void __iomem *)KSEG1ADDR(AU1000_IC0_PHYS_ADDR),
+			      alchemy_ic_pmdata);
+}
+
+static struct syscore_ops alchemy_ic_syscore_ops = {
 	.suspend	= alchemy_ic_suspend,
 	.resume		= alchemy_ic_resume,
 };
 
-static int __init alchemy_ic_sysdev_init(void)
+static int __init alchemy_ic_pm_init(void)
 {
-	struct alchemy_ic_sysdev *icdev;
-	unsigned long icbase[2] = { IC0_PHYS_ADDR, IC1_PHYS_ADDR };
-	int err, i;
-
-	err = sysdev_class_register(&alchemy_ic_sysdev_class);
-	if (err)
-		return err;
-
-	for (i = 0; i < 2; i++) {
-		icdev = kzalloc(sizeof(struct alchemy_ic_sysdev), GFP_KERNEL);
-		if (!icdev)
-			return -ENOMEM;
-
-		icdev->base = ioremap(icbase[i], 0x1000);
-
-		icdev->sysdev.id = i;
-		icdev->sysdev.cls = &alchemy_ic_sysdev_class;
-		err = sysdev_register(&icdev->sysdev);
-		if (err) {
-			kfree(icdev);
-			return err;
-		}
-	}
-
+	register_syscore_ops(&alchemy_ic_syscore_ops);
 	return 0;
 }
-device_initcall(alchemy_ic_sysdev_init);
+device_initcall(alchemy_ic_pm_init);
diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c
index 9e7814db3d0..3b2c18b1434 100644
--- a/arch/mips/alchemy/common/platform.c
+++ b/arch/mips/alchemy/common/platform.c
@@ -13,9 +13,10 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
-#include <linux/init.h>
+#include <linux/slab.h>
 
 #include <asm/mach-au1x00/au1xxx.h>
 #include <asm/mach-au1x00/au1xxx_dbdma.h>
@@ -30,21 +31,12 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 #ifdef CONFIG_SERIAL_8250
 	switch (state) {
 	case 0:
-		if ((__raw_readl(port->membase + UART_MOD_CNTRL) & 3) != 3) {
-			/* power-on sequence as suggested in the databooks */
-			__raw_writel(0, port->membase + UART_MOD_CNTRL);
-			wmb();
-			__raw_writel(1, port->membase + UART_MOD_CNTRL);
-			wmb();
-		}
-		__raw_writel(3, port->membase + UART_MOD_CNTRL); /* full on */
-		wmb();
+		alchemy_uart_enable(CPHYSADDR(port->membase));
 		serial8250_do_pm(port, state, old_state);
 		break;
 	case 3:		/* power off */
 		serial8250_do_pm(port, state, old_state);
-		__raw_writel(0, port->membase + UART_MOD_CNTRL);
-		wmb();
+		alchemy_uart_disable(CPHYSADDR(port->membase));
 		break;
 	default:
 		serial8250_do_pm(port, state, old_state);
@@ -65,38 +57,60 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 		.pm		= alchemy_8250_pm,		\
 	}
 
-static struct plat_serial8250_port au1x00_uart_data[] = {
-#if defined(CONFIG_SOC_AU1000)
-	PORT(UART0_PHYS_ADDR, AU1000_UART0_INT),
-	PORT(UART1_PHYS_ADDR, AU1000_UART1_INT),
-	PORT(UART2_PHYS_ADDR, AU1000_UART2_INT),
-	PORT(UART3_PHYS_ADDR, AU1000_UART3_INT),
-#elif defined(CONFIG_SOC_AU1500)
-	PORT(UART0_PHYS_ADDR, AU1500_UART0_INT),
-	PORT(UART3_PHYS_ADDR, AU1500_UART3_INT),
-#elif defined(CONFIG_SOC_AU1100)
-	PORT(UART0_PHYS_ADDR, AU1100_UART0_INT),
-	PORT(UART1_PHYS_ADDR, AU1100_UART1_INT),
-	PORT(UART3_PHYS_ADDR, AU1100_UART3_INT),
-#elif defined(CONFIG_SOC_AU1550)
-	PORT(UART0_PHYS_ADDR, AU1550_UART0_INT),
-	PORT(UART1_PHYS_ADDR, AU1550_UART1_INT),
-	PORT(UART3_PHYS_ADDR, AU1550_UART3_INT),
-#elif defined(CONFIG_SOC_AU1200)
-	PORT(UART0_PHYS_ADDR, AU1200_UART0_INT),
-	PORT(UART1_PHYS_ADDR, AU1200_UART1_INT),
-#endif
-	{ },
+static struct plat_serial8250_port au1x00_uart_data[][4] __initdata = {
+	[ALCHEMY_CPU_AU1000] = {
+		PORT(AU1000_UART0_PHYS_ADDR, AU1000_UART0_INT),
+		PORT(AU1000_UART1_PHYS_ADDR, AU1000_UART1_INT),
+		PORT(AU1000_UART2_PHYS_ADDR, AU1000_UART2_INT),
+		PORT(AU1000_UART3_PHYS_ADDR, AU1000_UART3_INT),
+	},
+	[ALCHEMY_CPU_AU1500] = {
+		PORT(AU1000_UART0_PHYS_ADDR, AU1500_UART0_INT),
+		PORT(AU1000_UART3_PHYS_ADDR, AU1500_UART3_INT),
+	},
+	[ALCHEMY_CPU_AU1100] = {
+		PORT(AU1000_UART0_PHYS_ADDR, AU1100_UART0_INT),
+		PORT(AU1000_UART1_PHYS_ADDR, AU1100_UART1_INT),
+		PORT(AU1000_UART3_PHYS_ADDR, AU1100_UART3_INT),
+	},
+	[ALCHEMY_CPU_AU1550] = {
+		PORT(AU1000_UART0_PHYS_ADDR, AU1550_UART0_INT),
+		PORT(AU1000_UART1_PHYS_ADDR, AU1550_UART1_INT),
+		PORT(AU1000_UART3_PHYS_ADDR, AU1550_UART3_INT),
+	},
+	[ALCHEMY_CPU_AU1200] = {
+		PORT(AU1000_UART0_PHYS_ADDR, AU1200_UART0_INT),
+		PORT(AU1000_UART1_PHYS_ADDR, AU1200_UART1_INT),
+	},
 };
 
 static struct platform_device au1xx0_uart_device = {
 	.name			= "serial8250",
 	.id			= PLAT8250_DEV_AU1X00,
-	.dev			= {
-		.platform_data	= au1x00_uart_data,
-	},
 };
 
+static void __init alchemy_setup_uarts(int ctype)
+{
+	unsigned int uartclk = get_au1x00_uart_baud_base() * 16;
+	int s = sizeof(struct plat_serial8250_port);
+	int c = alchemy_get_uarts(ctype);
+	struct plat_serial8250_port *ports;
+
+	ports = kzalloc(s * (c + 1), GFP_KERNEL);
+	if (!ports) {
+		printk(KERN_INFO "Alchemy: no memory for UART data\n");
+		return;
+	}
+	memcpy(ports, au1x00_uart_data[ctype], s * c);
+	au1xx0_uart_device.dev.platform_data = ports;
+
+	/* Fill up uartclk. */
+	for (s = 0; s < c; s++)
+		ports[s].uartclk = uartclk;
+	if (platform_device_register(&au1xx0_uart_device))
+		printk(KERN_INFO "Alchemy: failed to register UARTs\n");
+}
+
 /* OHCI (USB full speed host controller) */
 static struct resource au1xxx_usb_ohci_resources[] = {
 	[0] = {
@@ -269,8 +283,8 @@ extern struct au1xmmc_platform_data au1xmmc_platdata[2];
 
 static struct resource au1200_mmc0_resources[] = {
 	[0] = {
-		.start          = SD0_PHYS_ADDR,
-		.end            = SD0_PHYS_ADDR + 0x7ffff,
+		.start          = AU1100_SD0_PHYS_ADDR,
+		.end            = AU1100_SD0_PHYS_ADDR + 0xfff,
 		.flags          = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -305,8 +319,8 @@ static struct platform_device au1200_mmc0_device = {
 #ifndef CONFIG_MIPS_DB1200
 static struct resource au1200_mmc1_resources[] = {
 	[0] = {
-		.start          = SD1_PHYS_ADDR,
-		.end            = SD1_PHYS_ADDR + 0x7ffff,
+		.start          = AU1100_SD1_PHYS_ADDR,
+		.end            = AU1100_SD1_PHYS_ADDR + 0xfff,
 		.flags          = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -359,15 +373,16 @@ static struct platform_device pbdb_smbus_device = {
 #endif
 
 /* Macro to help defining the Ethernet MAC resources */
+#define MAC_RES_COUNT	3	/* MAC regs base, MAC enable reg, MAC INT */
 #define MAC_RES(_base, _enable, _irq)			\
 	{						\
-		.start	= CPHYSADDR(_base),		\
-		.end	= CPHYSADDR(_base + 0xffff),	\
+		.start	= _base,			\
+		.end	= _base + 0xffff,		\
 		.flags	= IORESOURCE_MEM,		\
 	},						\
 	{						\
-		.start	= CPHYSADDR(_enable),		\
-		.end	= CPHYSADDR(_enable + 0x3),	\
+		.start	= _enable,			\
+		.end	= _enable + 0x3,		\
 		.flags	= IORESOURCE_MEM,		\
 	},						\
 	{						\
@@ -376,19 +391,29 @@ static struct platform_device pbdb_smbus_device = {
 		.flags	= IORESOURCE_IRQ		\
 	}
 
-static struct resource au1xxx_eth0_resources[] = {
-#if defined(CONFIG_SOC_AU1000)
-	MAC_RES(AU1000_ETH0_BASE, AU1000_MAC0_ENABLE, AU1000_MAC0_DMA_INT),
-#elif defined(CONFIG_SOC_AU1100)
-	MAC_RES(AU1100_ETH0_BASE, AU1100_MAC0_ENABLE, AU1100_MAC0_DMA_INT),
-#elif defined(CONFIG_SOC_AU1550)
-	MAC_RES(AU1550_ETH0_BASE, AU1550_MAC0_ENABLE, AU1550_MAC0_DMA_INT),
-#elif defined(CONFIG_SOC_AU1500)
-	MAC_RES(AU1500_ETH0_BASE, AU1500_MAC0_ENABLE, AU1500_MAC0_DMA_INT),
-#endif
+static struct resource au1xxx_eth0_resources[][MAC_RES_COUNT] __initdata = {
+	[ALCHEMY_CPU_AU1000] = {
+		MAC_RES(AU1000_MAC0_PHYS_ADDR,
+			AU1000_MACEN_PHYS_ADDR,
+			AU1000_MAC0_DMA_INT)
+	},
+	[ALCHEMY_CPU_AU1500] = {
+		MAC_RES(AU1500_MAC0_PHYS_ADDR,
+			AU1500_MACEN_PHYS_ADDR,
+			AU1500_MAC0_DMA_INT)
+	},
+	[ALCHEMY_CPU_AU1100] = {
+		MAC_RES(AU1000_MAC0_PHYS_ADDR,
+			AU1000_MACEN_PHYS_ADDR,
+			AU1100_MAC0_DMA_INT)
+	},
+	[ALCHEMY_CPU_AU1550] = {
+		MAC_RES(AU1000_MAC0_PHYS_ADDR,
+			AU1000_MACEN_PHYS_ADDR,
+			AU1550_MAC0_DMA_INT)
+	},
 };
 
-
 static struct au1000_eth_platform_data au1xxx_eth0_platform_data = {
 	.phy1_search_mac0 = 1,
 };
@@ -396,20 +421,26 @@ static struct au1000_eth_platform_data au1xxx_eth0_platform_data = {
 static struct platform_device au1xxx_eth0_device = {
 	.name		= "au1000-eth",
 	.id		= 0,
-	.num_resources	= ARRAY_SIZE(au1xxx_eth0_resources),
-	.resource	= au1xxx_eth0_resources,
+	.num_resources	= MAC_RES_COUNT,
 	.dev.platform_data = &au1xxx_eth0_platform_data,
 };
 
-#ifndef CONFIG_SOC_AU1100
-static struct resource au1xxx_eth1_resources[] = {
-#if defined(CONFIG_SOC_AU1000)
-	MAC_RES(AU1000_ETH1_BASE, AU1000_MAC1_ENABLE, AU1000_MAC1_DMA_INT),
-#elif defined(CONFIG_SOC_AU1550)
-	MAC_RES(AU1550_ETH1_BASE, AU1550_MAC1_ENABLE, AU1550_MAC1_DMA_INT),
-#elif defined(CONFIG_SOC_AU1500)
-	MAC_RES(AU1500_ETH1_BASE, AU1500_MAC1_ENABLE, AU1500_MAC1_DMA_INT),
-#endif
+static struct resource au1xxx_eth1_resources[][MAC_RES_COUNT] __initdata = {
+	[ALCHEMY_CPU_AU1000] = {
+		MAC_RES(AU1000_MAC1_PHYS_ADDR,
+			AU1000_MACEN_PHYS_ADDR + 4,
+			AU1000_MAC1_DMA_INT)
+	},
+	[ALCHEMY_CPU_AU1500] = {
+		MAC_RES(AU1500_MAC1_PHYS_ADDR,
+			AU1500_MACEN_PHYS_ADDR + 4,
+			AU1500_MAC1_DMA_INT)
+	},
+	[ALCHEMY_CPU_AU1550] = {
+		MAC_RES(AU1000_MAC1_PHYS_ADDR,
+			AU1000_MACEN_PHYS_ADDR + 4,
+			AU1550_MAC1_DMA_INT)
+	},
 };
 
 static struct au1000_eth_platform_data au1xxx_eth1_platform_data = {
@@ -419,11 +450,9 @@ static struct au1000_eth_platform_data au1xxx_eth1_platform_data = {
 static struct platform_device au1xxx_eth1_device = {
 	.name		= "au1000-eth",
 	.id		= 1,
-	.num_resources	= ARRAY_SIZE(au1xxx_eth1_resources),
-	.resource	= au1xxx_eth1_resources,
+	.num_resources	= MAC_RES_COUNT,
 	.dev.platform_data = &au1xxx_eth1_platform_data,
 };
-#endif
 
 void __init au1xxx_override_eth_cfg(unsigned int port,
 			struct au1000_eth_platform_data *eth_data)
@@ -434,15 +463,65 @@ void __init au1xxx_override_eth_cfg(unsigned int port,
 	if (port == 0)
 		memcpy(&au1xxx_eth0_platform_data, eth_data,
 			sizeof(struct au1000_eth_platform_data));
-#ifndef CONFIG_SOC_AU1100
 	else
 		memcpy(&au1xxx_eth1_platform_data, eth_data,
 			sizeof(struct au1000_eth_platform_data));
-#endif
+}
+
+static void __init alchemy_setup_macs(int ctype)
+{
+	int ret, i;
+	unsigned char ethaddr[6];
+	struct resource *macres;
+
+	/* Handle 1st MAC */
+	if (alchemy_get_macs(ctype) < 1)
+		return;
+
+	macres = kmalloc(sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
+	if (!macres) {
+		printk(KERN_INFO "Alchemy: no memory for MAC0 resources\n");
+		return;
+	}
+	memcpy(macres, au1xxx_eth0_resources[ctype],
+	       sizeof(struct resource) * MAC_RES_COUNT);
+	au1xxx_eth0_device.resource = macres;
+
+	i = prom_get_ethernet_addr(ethaddr);
+	if (!i && !is_valid_ether_addr(au1xxx_eth0_platform_data.mac))
+		memcpy(au1xxx_eth0_platform_data.mac, ethaddr, 6);
+
+	ret = platform_device_register(&au1xxx_eth0_device);
+	if (!ret)
+		printk(KERN_INFO "Alchemy: failed to register MAC0\n");
+
+
+	/* Handle 2nd MAC */
+	if (alchemy_get_macs(ctype) < 2)
+		return;
+
+	macres = kmalloc(sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
+	if (!macres) {
+		printk(KERN_INFO "Alchemy: no memory for MAC1 resources\n");
+		return;
+	}
+	memcpy(macres, au1xxx_eth1_resources[ctype],
+	       sizeof(struct resource) * MAC_RES_COUNT);
+	au1xxx_eth1_device.resource = macres;
+
+	ethaddr[5] += 1;	/* next addr for 2nd MAC */
+	if (!i && !is_valid_ether_addr(au1xxx_eth1_platform_data.mac))
+		memcpy(au1xxx_eth1_platform_data.mac, ethaddr, 6);
+
+	/* Register second MAC if enabled in pinfunc */
+	if (!(au_readl(SYS_PINFUNC) & (u32)SYS_PF_NI2)) {
+		ret = platform_device_register(&au1xxx_eth1_device);
+		if (ret)
+			printk(KERN_INFO "Alchemy: failed to register MAC1\n");
+	}
 }
 
 static struct platform_device *au1xxx_platform_devices[] __initdata = {
-	&au1xx0_uart_device,
 	&au1xxx_usb_ohci_device,
 #ifdef CONFIG_FB_AU1100
 	&au1100_lcd_device,
@@ -460,36 +539,17 @@ static struct platform_device *au1xxx_platform_devices[] __initdata = {
 #ifdef SMBUS_PSC_BASE
 	&pbdb_smbus_device,
 #endif
-	&au1xxx_eth0_device,
 };
 
 static int __init au1xxx_platform_init(void)
 {
-	unsigned int uartclk = get_au1x00_uart_baud_base() * 16;
-	int err, i;
-	unsigned char ethaddr[6];
+	int err, ctype = alchemy_get_cputype();
 
-	/* Fill up uartclk. */
-	for (i = 0; au1x00_uart_data[i].flags; i++)
-		au1x00_uart_data[i].uartclk = uartclk;
-
-	/* use firmware-provided mac addr if available and necessary */
-	i = prom_get_ethernet_addr(ethaddr);
-	if (!i && !is_valid_ether_addr(au1xxx_eth0_platform_data.mac))
-		memcpy(au1xxx_eth0_platform_data.mac, ethaddr, 6);
+	alchemy_setup_uarts(ctype);
+	alchemy_setup_macs(ctype);
 
 	err = platform_add_devices(au1xxx_platform_devices,
 				   ARRAY_SIZE(au1xxx_platform_devices));
-#ifndef CONFIG_SOC_AU1100
-	ethaddr[5] += 1;	/* next addr for 2nd MAC */
-	if (!i && !is_valid_ether_addr(au1xxx_eth1_platform_data.mac))
-		memcpy(au1xxx_eth1_platform_data.mac, ethaddr, 6);
-
-	/* Register second MAC if enabled in pinfunc */
-	if (!err && !(au_readl(SYS_PINFUNC) & (u32)SYS_PF_NI2))
-		err = platform_device_register(&au1xxx_eth1_device);
-#endif
-
 	return err;
 }
 
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 561e5da2658..1b887c86841 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -52,8 +52,6 @@ void __init plat_mem_setup(void)
 	/* this is faster than wasting cycles trying to approximate it */
 	preset_lpj = (est_freq >> 1) / HZ;
 
-	board_setup();  /* board specific setup */
-
 	if (au1xxx_cpu_needs_config_od())
 		/* Various early Au1xx0 errata corrected by this */
 		set_c0_config(1 << 19); /* Set Config[OD] */
@@ -61,6 +59,8 @@ void __init plat_mem_setup(void)
 		/* Clear to obtain best system bus performance */
 		clear_c0_config(1 << 19); /* Clear Config[OD] */
 
+	board_setup();  /* board specific setup */
+
 	/* IO/MEM resources. */
 	set_io_port_base(0);
 	ioport_resource.start = IOPORT_RESOURCE_START;
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index 2aecb2fdf98..d5da6adbf63 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -141,8 +141,7 @@ static int __init alchemy_time_init(unsigned int m2int)
 		goto cntr_err;
 
 	/* register counter1 clocksource and event device */
-	clocksource_set_clock(&au1x_counter1_clocksource, 32768);
-	clocksource_register(&au1x_counter1_clocksource);
+	clocksource_register_hz(&au1x_counter1_clocksource, 32768);
 
 	cd->shift = 32;
 	cd->mult = div_sc(32768, NSEC_PER_SEC, cd->shift);
diff --git a/arch/mips/alchemy/devboards/db1200/setup.c b/arch/mips/alchemy/devboards/db1200/setup.c
index 4a8980027ec..1dac4f27d33 100644
--- a/arch/mips/alchemy/devboards/db1200/setup.c
+++ b/arch/mips/alchemy/devboards/db1200/setup.c
@@ -23,6 +23,13 @@ void __init board_setup(void)
 	unsigned long freq0, clksrc, div, pfc;
 	unsigned short whoami;
 
+	/* Set Config[OD] (disable overlapping bus transaction):
+	 * This gets rid of a _lot_ of spurious interrupts (especially
+	 * wrt. IDE); but incurs ~10% performance hit in some
+	 * cpu-bound applications.
+	 */
+	set_c0_config(1 << 19);
+
 	bcsr_init(DB1200_BCSR_PHYS_ADDR,
 		  DB1200_BCSR_PHYS_ADDR + DB1200_BCSR_HEXLED_OFS);
 
diff --git a/arch/mips/alchemy/devboards/pb1000/board_setup.c b/arch/mips/alchemy/devboards/pb1000/board_setup.c
index 2d85c4b5be0..e64fdcbf75d 100644
--- a/arch/mips/alchemy/devboards/pb1000/board_setup.c
+++ b/arch/mips/alchemy/devboards/pb1000/board_setup.c
@@ -65,7 +65,7 @@ void __init board_setup(void)
 
 	/* Set AUX clock to 12 MHz * 8 = 96 MHz */
 	au_writel(8, SYS_AUXPLL);
-	au_writel(0, SYS_PINSTATERD);
+	alchemy_gpio1_input_enable();
 	udelay(100);
 
 #if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/mips/alchemy/devboards/pb1500/board_setup.c b/arch/mips/alchemy/devboards/pb1500/board_setup.c
index 83f46215eb0..3b4fa320696 100644
--- a/arch/mips/alchemy/devboards/pb1500/board_setup.c
+++ b/arch/mips/alchemy/devboards/pb1500/board_setup.c
@@ -56,7 +56,7 @@ void __init board_setup(void)
 	sys_clksrc = sys_freqctrl = pin_func = 0;
 	/* Set AUX clock to 12 MHz * 8 = 96 MHz */
 	au_writel(8, SYS_AUXPLL);
-	au_writel(0, SYS_PINSTATERD);
+	alchemy_gpio1_input_enable();
 	udelay(100);
 
 	/* GPIO201 is input for PCMCIA card detect */
diff --git a/arch/mips/alchemy/devboards/prom.c b/arch/mips/alchemy/devboards/prom.c
index baeb2138505..e5306b56da6 100644
--- a/arch/mips/alchemy/devboards/prom.c
+++ b/arch/mips/alchemy/devboards/prom.c
@@ -62,5 +62,5 @@ void __init prom_init(void)
 
 void prom_putchar(unsigned char c)
 {
-    alchemy_uart_putchar(UART0_PHYS_ADDR, c);
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/gpr/board_setup.c b/arch/mips/alchemy/gpr/board_setup.c
index ad2e3f13793..5f8f0691ed2 100644
--- a/arch/mips/alchemy/gpr/board_setup.c
+++ b/arch/mips/alchemy/gpr/board_setup.c
@@ -36,9 +36,6 @@
 
 #include <prom.h>
 
-#define UART1_ADDR	KSEG1ADDR(UART1_PHYS_ADDR)
-#define UART3_ADDR	KSEG1ADDR(UART3_PHYS_ADDR)
-
 char irq_tab_alchemy[][5] __initdata = {
 	[0] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff },
 };
@@ -67,18 +64,15 @@ static void gpr_power_off(void)
 
 void __init board_setup(void)
 {
-	printk(KERN_INFO "Tarpeze ITS GPR board\n");
+	printk(KERN_INFO "Trapeze ITS GPR board\n");
 
 	pm_power_off = gpr_power_off;
 	_machine_halt = gpr_power_off;
 	_machine_restart = gpr_reset;
 
-	/* Enable UART3 */
-	au_writel(0x1, UART3_ADDR + UART_MOD_CNTRL);/* clock enable (CE) */
-	au_writel(0x3, UART3_ADDR + UART_MOD_CNTRL); /* CE and "enable" */
-	/* Enable UART1 */
-	au_writel(0x1, UART1_ADDR + UART_MOD_CNTRL); /* clock enable (CE) */
-	au_writel(0x3, UART1_ADDR + UART_MOD_CNTRL); /* CE and "enable" */
+	/* Enable UART1/3 */
+	alchemy_uart_enable(AU1000_UART3_PHYS_ADDR);
+	alchemy_uart_enable(AU1000_UART1_PHYS_ADDR);
 
 	/* Take away Reset of UMTS-card */
 	alchemy_gpio_direction_output(215, 1);
diff --git a/arch/mips/alchemy/gpr/init.c b/arch/mips/alchemy/gpr/init.c
index f044f4c541d..229aafae680 100644
--- a/arch/mips/alchemy/gpr/init.c
+++ b/arch/mips/alchemy/gpr/init.c
@@ -59,5 +59,5 @@ void __init prom_init(void)
 
 void prom_putchar(unsigned char c)
 {
-	alchemy_uart_putchar(UART0_PHYS_ADDR, c);
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/mtx-1/board_setup.c b/arch/mips/alchemy/mtx-1/board_setup.c
index cf436ab679a..3ae984cf98c 100644
--- a/arch/mips/alchemy/mtx-1/board_setup.c
+++ b/arch/mips/alchemy/mtx-1/board_setup.c
@@ -87,7 +87,7 @@ void __init board_setup(void)
 	au_writel(SYS_PF_NI2, SYS_PINFUNC);
 
 	/* Initialize GPIO */
-	au_writel(0xFFFFFFFF, SYS_TRIOUTCLR);
+	au_writel(~0, KSEG1ADDR(AU1000_SYS_PHYS_ADDR) + SYS_TRIOUTCLR);
 	alchemy_gpio_direction_output(0, 0);	/* Disable M66EN (PCI 66MHz) */
 	alchemy_gpio_direction_output(3, 1);	/* Disable PCI CLKRUN# */
 	alchemy_gpio_direction_output(1, 1);	/* Enable EXT_IO3 */
diff --git a/arch/mips/alchemy/mtx-1/init.c b/arch/mips/alchemy/mtx-1/init.c
index f8d25575fa0..2e81cc7f342 100644
--- a/arch/mips/alchemy/mtx-1/init.c
+++ b/arch/mips/alchemy/mtx-1/init.c
@@ -62,5 +62,5 @@ void __init prom_init(void)
 
 void prom_putchar(unsigned char c)
 {
-	alchemy_uart_putchar(UART0_PHYS_ADDR, c);
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/mtx-1/platform.c b/arch/mips/alchemy/mtx-1/platform.c
index 956f946218c..55628e390fd 100644
--- a/arch/mips/alchemy/mtx-1/platform.c
+++ b/arch/mips/alchemy/mtx-1/platform.c
@@ -53,8 +53,8 @@ static struct platform_device mtx1_button = {
 
 static struct resource mtx1_wdt_res[] = {
 	[0] = {
-		.start	= 15,
-		.end	= 15,
+		.start	= 215,
+		.end	= 215,
 		.name	= "mtx1-wdt-gpio",
 		.flags	= IORESOURCE_IRQ,
 	}
diff --git a/arch/mips/alchemy/xxs1500/board_setup.c b/arch/mips/alchemy/xxs1500/board_setup.c
index febfb0fb089..81e57fad07a 100644
--- a/arch/mips/alchemy/xxs1500/board_setup.c
+++ b/arch/mips/alchemy/xxs1500/board_setup.c
@@ -66,13 +66,10 @@ void __init board_setup(void)
 	au_writel(pin_func, SYS_PINFUNC);
 
 	/* Enable UART */
-	au_writel(0x01, UART3_ADDR + UART_MOD_CNTRL); /* clock enable (CE) */
-	mdelay(10);
-	au_writel(0x03, UART3_ADDR + UART_MOD_CNTRL); /* CE and "enable" */
-	mdelay(10);
-
-	/* Enable DTR = USB power up */
-	au_writel(0x01, UART3_ADDR + UART_MCR); /* UART_MCR_DTR is 0x01??? */
+	alchemy_uart_enable(AU1000_UART3_PHYS_ADDR);
+	/* Enable DTR (MCR bit 0) = USB power up */
+	__raw_writel(1, (void __iomem *)KSEG1ADDR(AU1000_UART3_PHYS_ADDR + 0x18));
+	wmb();
 
 #ifdef CONFIG_PCI
 #if defined(__MIPSEB__)
diff --git a/arch/mips/alchemy/xxs1500/init.c b/arch/mips/alchemy/xxs1500/init.c
index 34a90a4bb6f..0ee02cfa989 100644
--- a/arch/mips/alchemy/xxs1500/init.c
+++ b/arch/mips/alchemy/xxs1500/init.c
@@ -59,5 +59,5 @@ void __init prom_init(void)
 
 void prom_putchar(unsigned char c)
 {
-	alchemy_uart_putchar(UART0_PHYS_ADDR, c);
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index e5b6615731e..54db815bc86 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -3,6 +3,7 @@
  *
  * Copyright (C) 2005 Broadcom Corporation
  * Copyright (C) 2006 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2010-2011 Hauke Mehrtens <hauke@hauke-m.de>
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -23,7 +24,7 @@
 static char nvram_buf[NVRAM_SPACE];
 
 /* Probe for NVRAM header */
-static void __init early_nvram_init(void)
+static void early_nvram_init(void)
 {
 	struct ssb_mipscore *mcore = &ssb_bcm47xx.mipscore;
 	struct nvram_header *header;
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index c95f90bf734..73b529b5743 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -3,6 +3,7 @@
  *  Copyright (C) 2006 Felix Fietkau <nbd@openwrt.org>
  *  Copyright (C) 2006 Michael Buesch <mb@bu3sch.de>
  *  Copyright (C) 2010 Waldemar Brodkorb <wbx@openadk.org>
+ *  Copyright (C) 2010-2011 Hauke Mehrtens <hauke@hauke-m.de>
  *
  *  This program is free software; you can redistribute  it and/or modify it
  *  under  the terms of  the GNU General  Public License as published by the
@@ -57,10 +58,49 @@ static void bcm47xx_machine_halt(void)
 }
 
 #define READ_FROM_NVRAM(_outvar, name, buf) \
-	if (nvram_getenv(name, buf, sizeof(buf)) >= 0)\
+	if (nvram_getprefix(prefix, name, buf, sizeof(buf)) >= 0)\
 		sprom->_outvar = simple_strtoul(buf, NULL, 0);
 
-static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
+#define READ_FROM_NVRAM2(_outvar, name1, name2, buf) \
+	if (nvram_getprefix(prefix, name1, buf, sizeof(buf)) >= 0 || \
+	    nvram_getprefix(prefix, name2, buf, sizeof(buf)) >= 0)\
+		sprom->_outvar = simple_strtoul(buf, NULL, 0);
+
+static inline int nvram_getprefix(const char *prefix, char *name,
+				  char *buf, int len)
+{
+	if (prefix) {
+		char key[100];
+
+		snprintf(key, sizeof(key), "%s%s", prefix, name);
+		return nvram_getenv(key, buf, len);
+	}
+
+	return nvram_getenv(name, buf, len);
+}
+
+static u32 nvram_getu32(const char *name, char *buf, int len)
+{
+	int rv;
+	char key[100];
+	u16 var0, var1;
+
+	snprintf(key, sizeof(key), "%s0", name);
+	rv = nvram_getenv(key, buf, len);
+	/* return 0 here so this looks like unset */
+	if (rv < 0)
+		return 0;
+	var0 = simple_strtoul(buf, NULL, 0);
+
+	snprintf(key, sizeof(key), "%s1", name);
+	rv = nvram_getenv(key, buf, len);
+	if (rv < 0)
+		return 0;
+	var1 = simple_strtoul(buf, NULL, 0);
+	return var1 << 16 | var0;
+}
+
+static void bcm47xx_fill_sprom(struct ssb_sprom *sprom, const char *prefix)
 {
 	char buf[100];
 	u32 boardflags;
@@ -69,11 +109,12 @@ static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
 
 	sprom->revision = 1; /* Fallback: Old hardware does not define this. */
 	READ_FROM_NVRAM(revision, "sromrev", buf);
-	if (nvram_getenv("il0macaddr", buf, sizeof(buf)) >= 0)
+	if (nvram_getprefix(prefix, "il0macaddr", buf, sizeof(buf)) >= 0 ||
+	    nvram_getprefix(prefix, "macaddr", buf, sizeof(buf)) >= 0)
 		nvram_parse_macaddr(buf, sprom->il0mac);
-	if (nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
+	if (nvram_getprefix(prefix, "et0macaddr", buf, sizeof(buf)) >= 0)
 		nvram_parse_macaddr(buf, sprom->et0mac);
-	if (nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
+	if (nvram_getprefix(prefix, "et1macaddr", buf, sizeof(buf)) >= 0)
 		nvram_parse_macaddr(buf, sprom->et1mac);
 	READ_FROM_NVRAM(et0phyaddr, "et0phyaddr", buf);
 	READ_FROM_NVRAM(et1phyaddr, "et1phyaddr", buf);
@@ -95,20 +136,36 @@ static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
 	READ_FROM_NVRAM(pa1hib0, "pa1hib0", buf);
 	READ_FROM_NVRAM(pa1hib2, "pa1hib1", buf);
 	READ_FROM_NVRAM(pa1hib1, "pa1hib2", buf);
-	READ_FROM_NVRAM(gpio0, "wl0gpio0", buf);
-	READ_FROM_NVRAM(gpio1, "wl0gpio1", buf);
-	READ_FROM_NVRAM(gpio2, "wl0gpio2", buf);
-	READ_FROM_NVRAM(gpio3, "wl0gpio3", buf);
-	READ_FROM_NVRAM(maxpwr_bg, "pa0maxpwr", buf);
-	READ_FROM_NVRAM(maxpwr_al, "pa1lomaxpwr", buf);
-	READ_FROM_NVRAM(maxpwr_a, "pa1maxpwr", buf);
-	READ_FROM_NVRAM(maxpwr_ah, "pa1himaxpwr", buf);
-	READ_FROM_NVRAM(itssi_a, "pa1itssit", buf);
-	READ_FROM_NVRAM(itssi_bg, "pa0itssit", buf);
+	READ_FROM_NVRAM2(gpio0, "ledbh0", "wl0gpio0", buf);
+	READ_FROM_NVRAM2(gpio1, "ledbh1", "wl0gpio1", buf);
+	READ_FROM_NVRAM2(gpio2, "ledbh2", "wl0gpio2", buf);
+	READ_FROM_NVRAM2(gpio3, "ledbh3", "wl0gpio3", buf);
+	READ_FROM_NVRAM2(maxpwr_bg, "maxp2ga0", "pa0maxpwr", buf);
+	READ_FROM_NVRAM2(maxpwr_al, "maxp5gla0", "pa1lomaxpwr", buf);
+	READ_FROM_NVRAM2(maxpwr_a, "maxp5ga0", "pa1maxpwr", buf);
+	READ_FROM_NVRAM2(maxpwr_ah, "maxp5gha0", "pa1himaxpwr", buf);
+	READ_FROM_NVRAM2(itssi_bg, "itt5ga0", "pa0itssit", buf);
+	READ_FROM_NVRAM2(itssi_a, "itt2ga0", "pa1itssit", buf);
 	READ_FROM_NVRAM(tri2g, "tri2g", buf);
 	READ_FROM_NVRAM(tri5gl, "tri5gl", buf);
 	READ_FROM_NVRAM(tri5g, "tri5g", buf);
 	READ_FROM_NVRAM(tri5gh, "tri5gh", buf);
+	READ_FROM_NVRAM(txpid2g[0], "txpid2ga0", buf);
+	READ_FROM_NVRAM(txpid2g[1], "txpid2ga1", buf);
+	READ_FROM_NVRAM(txpid2g[2], "txpid2ga2", buf);
+	READ_FROM_NVRAM(txpid2g[3], "txpid2ga3", buf);
+	READ_FROM_NVRAM(txpid5g[0], "txpid5ga0", buf);
+	READ_FROM_NVRAM(txpid5g[1], "txpid5ga1", buf);
+	READ_FROM_NVRAM(txpid5g[2], "txpid5ga2", buf);
+	READ_FROM_NVRAM(txpid5g[3], "txpid5ga3", buf);
+	READ_FROM_NVRAM(txpid5gl[0], "txpid5gla0", buf);
+	READ_FROM_NVRAM(txpid5gl[1], "txpid5gla1", buf);
+	READ_FROM_NVRAM(txpid5gl[2], "txpid5gla2", buf);
+	READ_FROM_NVRAM(txpid5gl[3], "txpid5gla3", buf);
+	READ_FROM_NVRAM(txpid5gh[0], "txpid5gha0", buf);
+	READ_FROM_NVRAM(txpid5gh[1], "txpid5gha1", buf);
+	READ_FROM_NVRAM(txpid5gh[2], "txpid5gha2", buf);
+	READ_FROM_NVRAM(txpid5gh[3], "txpid5gha3", buf);
 	READ_FROM_NVRAM(rxpo2g, "rxpo2g", buf);
 	READ_FROM_NVRAM(rxpo5g, "rxpo5g", buf);
 	READ_FROM_NVRAM(rssisav2g, "rssisav2g", buf);
@@ -120,19 +177,27 @@ static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
 	READ_FROM_NVRAM(rssismf5g, "rssismf5g", buf);
 	READ_FROM_NVRAM(bxa5g, "bxa5g", buf);
 	READ_FROM_NVRAM(cck2gpo, "cck2gpo", buf);
-	READ_FROM_NVRAM(ofdm2gpo, "ofdm2gpo", buf);
-	READ_FROM_NVRAM(ofdm5glpo, "ofdm5glpo", buf);
-	READ_FROM_NVRAM(ofdm5gpo, "ofdm5gpo", buf);
-	READ_FROM_NVRAM(ofdm5ghpo, "ofdm5ghpo", buf);
 
-	if (nvram_getenv("boardflags", buf, sizeof(buf)) >= 0) {
+	sprom->ofdm2gpo = nvram_getu32("ofdm2gpo", buf, sizeof(buf));
+	sprom->ofdm5glpo = nvram_getu32("ofdm5glpo", buf, sizeof(buf));
+	sprom->ofdm5gpo = nvram_getu32("ofdm5gpo", buf, sizeof(buf));
+	sprom->ofdm5ghpo = nvram_getu32("ofdm5ghpo", buf, sizeof(buf));
+
+	READ_FROM_NVRAM(antenna_gain.ghz24.a0, "ag0", buf);
+	READ_FROM_NVRAM(antenna_gain.ghz24.a1, "ag1", buf);
+	READ_FROM_NVRAM(antenna_gain.ghz24.a2, "ag2", buf);
+	READ_FROM_NVRAM(antenna_gain.ghz24.a3, "ag3", buf);
+	memcpy(&sprom->antenna_gain.ghz5, &sprom->antenna_gain.ghz24,
+	       sizeof(sprom->antenna_gain.ghz5));
+
+	if (nvram_getprefix(prefix, "boardflags", buf, sizeof(buf)) >= 0) {
 		boardflags = simple_strtoul(buf, NULL, 0);
 		if (boardflags) {
 			sprom->boardflags_lo = (boardflags & 0x0000FFFFU);
 			sprom->boardflags_hi = (boardflags & 0xFFFF0000U) >> 16;
 		}
 	}
-	if (nvram_getenv("boardflags2", buf, sizeof(buf)) >= 0) {
+	if (nvram_getprefix(prefix, "boardflags2", buf, sizeof(buf)) >= 0) {
 		boardflags = simple_strtoul(buf, NULL, 0);
 		if (boardflags) {
 			sprom->boardflags2_lo = (boardflags & 0x0000FFFFU);
@@ -141,6 +206,22 @@ static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
 	}
 }
 
+int bcm47xx_get_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
+{
+	char prefix[10];
+
+	if (bus->bustype == SSB_BUSTYPE_PCI) {
+		snprintf(prefix, sizeof(prefix), "pci/%u/%u/",
+			 bus->host_pci->bus->number + 1,
+			 PCI_SLOT(bus->host_pci->devfn));
+		bcm47xx_fill_sprom(out, prefix);
+		return 0;
+	} else {
+		printk(KERN_WARNING "bcm47xx: unable to fill SPROM for given bustype.\n");
+		return -EINVAL;
+	}
+}
+
 static int bcm47xx_get_invariants(struct ssb_bus *bus,
 				   struct ssb_init_invariants *iv)
 {
@@ -158,7 +239,7 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus,
 	if (nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.rev = (u16)simple_strtoul(buf, NULL, 0);
 
-	bcm47xx_fill_sprom(&iv->sprom);
+	bcm47xx_fill_sprom(&iv->sprom, NULL);
 
 	if (nvram_getenv("cardbus", buf, sizeof(buf)) >= 0)
 		iv->has_cardbus_slot = !!simple_strtoul(buf, NULL, 10);
@@ -172,6 +253,11 @@ void __init plat_mem_setup(void)
 	char buf[100];
 	struct ssb_mipscore *mcore;
 
+	err = ssb_arch_register_fallback_sprom(&bcm47xx_get_sprom);
+	if (err)
+		printk(KERN_WARNING "bcm47xx: someone else already registered"
+			" a ssb SPROM callback handler (err %d)\n", err);
+
 	err = ssb_bus_ssbbus_register(&ssb_bcm47xx, SSB_ENUM_BASE,
 				      bcm47xx_get_invariants);
 	if (err)
diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index 8dba8cfb752..40b223b603b 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -643,6 +643,17 @@ static struct ssb_sprom bcm63xx_sprom = {
 	.boardflags_lo		= 0x2848,
 	.boardflags_hi		= 0x0000,
 };
+
+int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out)
+{
+	if (bus->bustype == SSB_BUSTYPE_PCI) {
+		memcpy(out, &bcm63xx_sprom, sizeof(struct ssb_sprom));
+		return 0;
+	} else {
+		printk(KERN_ERR PFX "unable to fill SPROM for given bustype.\n");
+		return -EINVAL;
+	}
+}
 #endif
 
 /*
@@ -793,8 +804,9 @@ void __init board_prom_init(void)
 	if (!board_get_mac_address(bcm63xx_sprom.il0mac)) {
 		memcpy(bcm63xx_sprom.et0mac, bcm63xx_sprom.il0mac, ETH_ALEN);
 		memcpy(bcm63xx_sprom.et1mac, bcm63xx_sprom.il0mac, ETH_ALEN);
-		if (ssb_arch_set_fallback_sprom(&bcm63xx_sprom) < 0)
-			printk(KERN_ERR "failed to register fallback SPROM\n");
+		if (ssb_arch_register_fallback_sprom(
+				&bcm63xx_get_fallback_sprom) < 0)
+			printk(KERN_ERR PFX "failed to register fallback SPROM\n");
 	}
 #endif
 }
diff --git a/arch/mips/boot/compressed/uart-alchemy.c b/arch/mips/boot/compressed/uart-alchemy.c
index 1bff22fa089..eb063e6dead 100644
--- a/arch/mips/boot/compressed/uart-alchemy.c
+++ b/arch/mips/boot/compressed/uart-alchemy.c
@@ -3,5 +3,5 @@
 void putc(char c)
 {
 	/* all current (Jan. 2010) in-kernel boards */
-	alchemy_uart_putchar(UART0_PHYS_ADDR, c);
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index 26bf71130bf..29d56afbb02 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -105,8 +105,7 @@ unsigned long long notrace sched_clock(void)
 void __init plat_time_init(void)
 {
 	clocksource_mips.rating = 300;
-	clocksource_set_clock(&clocksource_mips, octeon_get_clock_rate());
-	clocksource_register(&clocksource_mips);
+	clocksource_register_hz(&clocksource_mips, octeon_get_clock_rate());
 }
 
 static u64 octeon_udelay_factor;
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 0707fae3f0e..2d9028f1474 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -288,7 +288,6 @@ void octeon_user_io_init(void)
 	union octeon_cvmemctl cvmmemctl;
 	union cvmx_iob_fau_timeout fau_timeout;
 	union cvmx_pow_nw_tim nm_tim;
-	uint64_t cvmctl;
 
 	/* Get the current settings for CP0_CVMMEMCTL_REG */
 	cvmmemctl.u64 = read_c0_cvmmemctl();
@@ -392,12 +391,6 @@ void octeon_user_io_init(void)
 			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE,
 			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE * 128);
 
-	/* Move the performance counter interrupts to IRQ 6 */
-	cvmctl = read_c0_cvmctl();
-	cvmctl &= ~(7 << 7);
-	cvmctl |= 6 << 7;
-	write_c0_cvmctl(cvmctl);
-
 	/* Set a default for the hardware timeouts */
 	fau_timeout.u64 = 0;
 	fau_timeout.s.tout_val = 0xfff;
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index ba78b21cc8d..8b606423bbd 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -37,13 +37,15 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 	uint64_t action;
 
 	/* Load the mailbox register to figure out what we're supposed to do */
-	action = cvmx_read_csr(CVMX_CIU_MBOX_CLRX(coreid));
+	action = cvmx_read_csr(CVMX_CIU_MBOX_CLRX(coreid)) & 0xffff;
 
 	/* Clear the mailbox to clear the interrupt */
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action);
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	/* Check if we've been told to flush the icache */
 	if (action & SMP_ICACHE_FLUSH)
@@ -200,16 +202,15 @@ void octeon_prepare_cpus(unsigned int max_cpus)
 	if (labi->labi_signature != LABI_SIGNATURE)
 		panic("The bootloader version on this board is incorrect.");
 #endif
-
-	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffffffff);
+	/*
+	 * Only the low order mailbox bits are used for IPIs, leave
+	 * the other bits alone.
+	 */
+	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffff);
 	if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED,
-			"mailbox0", mailbox_interrupt)) {
+			"SMP-IPI", mailbox_interrupt)) {
 		panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n");
 	}
-	if (request_irq(OCTEON_IRQ_MBOX1, mailbox_interrupt, IRQF_DISABLED,
-			"mailbox1", mailbox_interrupt)) {
-		panic("Cannot request_irq(OCTEON_IRQ_MBOX1)\n");
-	}
 }
 
 /**
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 167c1d07b80..b6acd2f256b 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -86,8 +86,8 @@ CONFIG_NET_SCHED=y
 CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_BT=m
-CONFIG_BT_L2CAP=m
-CONFIG_BT_SCO=m
+CONFIG_BT_L2CAP=y
+CONFIG_BT_SCO=y
 CONFIG_BT_RFCOMM=m
 CONFIG_BT_RFCOMM_TTY=y
 CONFIG_BT_BNEP=m
@@ -329,7 +329,7 @@ CONFIG_USB_LED=m
 CONFIG_USB_GADGET=m
 CONFIG_USB_GADGET_M66592=y
 CONFIG_MMC=m
-CONFIG_LEDS_CLASS=m
+CONFIG_LEDS_CLASS=y
 CONFIG_STAGING=y
 # CONFIG_STAGING_EXCLUDE_BUILD is not set
 CONFIG_FB_SM7XX=y
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 7270f3183bd..5527abbb7de 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -374,7 +374,7 @@ CONFIG_FB_CIRRUS=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_HID=m
-CONFIG_LEDS_CLASS=m
+CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_TRIGGER_TIMER=m
 CONFIG_LEDS_TRIGGER_IDE_DISK=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=m
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index a97a42c6b2c..37862b2ce36 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -225,8 +225,8 @@ CONFIG_TOSHIBA_FIR=m
 CONFIG_VLSI_FIR=m
 CONFIG_MCS_FIR=m
 CONFIG_BT=m
-CONFIG_BT_L2CAP=m
-CONFIG_BT_SCO=m
+CONFIG_BT_L2CAP=y
+CONFIG_BT_SCO=y
 CONFIG_BT_RFCOMM=m
 CONFIG_BT_RFCOMM_TTY=y
 CONFIG_BT_BNEP=m
diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig
new file mode 100644
index 00000000000..e4b399fdaa6
--- /dev/null
+++ b/arch/mips/configs/nlm_xlr_defconfig
@@ -0,0 +1,574 @@
+CONFIG_NLM_XLR_BOARD=y
+CONFIG_HIGHMEM=y
+CONFIG_KSM=y
+CONFIG_DEFAULT_MMAP_MIN_ADDR=65536
+CONFIG_SMP=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_KEXEC=y
+CONFIG_EXPERIMENTAL=y
+CONFIG_CROSS_COMPILE="mips64-unknown-linux-gnu-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_NAMESPACES=y
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="usr/dev_file_list usr/rootfs"
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_INITRAMFS_COMPRESSION_GZIP=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_ELF_CORE is not set
+# CONFIG_PCSPKR_PLATFORM is not set
+# CONFIG_PERF_EVENTS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_BLK_DEV_INTEGRITY=y
+CONFIG_BINFMT_MISC=m
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_DEBUG=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_NET_KEY=m
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_NET_IPIP=m
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+CONFIG_INET_XFRM_MODE_TRANSPORT=m
+CONFIG_INET_XFRM_MODE_TUNNEL=m
+CONFIG_INET_XFRM_MODE_BEET=m
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TCP_CONG_HSTCP=m
+CONFIG_TCP_CONG_HYBLA=m
+CONFIG_TCP_CONG_SCALABLE=m
+CONFIG_TCP_CONG_LP=m
+CONFIG_TCP_CONG_VENO=m
+CONFIG_TCP_CONG_YEAH=m
+CONFIG_TCP_CONG_ILLINOIS=m
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_INET6_AH=m
+CONFIG_INET6_ESP=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_INET6_XFRM_MODE_TRANSPORT=m
+CONFIG_INET6_XFRM_MODE_TUNNEL=m
+CONFIG_INET6_XFRM_MODE_BEET=m
+CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_SIT=m
+CONFIG_IPV6_TUNNEL=m
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CONNTRACK_AMANDA=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_H323=m
+CONFIG_NF_CONNTRACK_IRC=m
+CONFIG_NF_CONNTRACK_NETBIOS_NS=m
+CONFIG_NF_CONNTRACK_PPTP=m
+CONFIG_NF_CONNTRACK_SANE=m
+CONFIG_NF_CONNTRACK_SIP=m
+CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_CT_NETLINK=m
+CONFIG_NETFILTER_TPROXY=m
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
+CONFIG_NETFILTER_XT_TARGET_DSCP=m
+CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NFLOG=m
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
+CONFIG_NETFILTER_XT_TARGET_TRACE=m
+CONFIG_NETFILTER_XT_TARGET_SECMARK=m
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
+CONFIG_NETFILTER_XT_MATCH_COMMENT=m
+CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NETFILTER_XT_MATCH_DSCP=m
+CONFIG_NETFILTER_XT_MATCH_ESP=m
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
+CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NETFILTER_XT_MATCH_LIMIT=m
+CONFIG_NETFILTER_XT_MATCH_MAC=m
+CONFIG_NETFILTER_XT_MATCH_MARK=m
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_OSF=m
+CONFIG_NETFILTER_XT_MATCH_OWNER=m
+CONFIG_NETFILTER_XT_MATCH_POLICY=m
+CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
+CONFIG_NETFILTER_XT_MATCH_QUOTA=m
+CONFIG_NETFILTER_XT_MATCH_RATEEST=m
+CONFIG_NETFILTER_XT_MATCH_REALM=m
+CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
+CONFIG_NETFILTER_XT_MATCH_STATE=m
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
+CONFIG_NETFILTER_XT_MATCH_STRING=m
+CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_TIME=m
+CONFIG_NETFILTER_XT_MATCH_U32=m
+CONFIG_IP_VS=m
+CONFIG_IP_VS_IPV6=y
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
+CONFIG_IP_VS_LC=m
+CONFIG_IP_VS_WLC=m
+CONFIG_IP_VS_LBLC=m
+CONFIG_IP_VS_LBLCR=m
+CONFIG_IP_VS_DH=m
+CONFIG_IP_VS_SH=m
+CONFIG_IP_VS_SED=m
+CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_FTP=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_IP_NF_QUEUE=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_MATCH_AH=m
+CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_TTL=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_LOG=m
+CONFIG_IP_NF_TARGET_ULOG=m
+CONFIG_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_TARGET_NETMAP=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_TARGET_CLUSTERIP=m
+CONFIG_IP_NF_TARGET_ECN=m
+CONFIG_IP_NF_TARGET_TTL=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_SECURITY=m
+CONFIG_IP_NF_ARPTABLES=m
+CONFIG_IP_NF_ARPFILTER=m
+CONFIG_IP_NF_ARP_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_QUEUE=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_MATCH_AH=m
+CONFIG_IP6_NF_MATCH_EUI64=m
+CONFIG_IP6_NF_MATCH_FRAG=m
+CONFIG_IP6_NF_MATCH_OPTS=m
+CONFIG_IP6_NF_MATCH_HL=m
+CONFIG_IP6_NF_MATCH_IPV6HEADER=m
+CONFIG_IP6_NF_MATCH_MH=m
+CONFIG_IP6_NF_MATCH_RT=m
+CONFIG_IP6_NF_TARGET_HL=m
+CONFIG_IP6_NF_TARGET_LOG=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_RAW=m
+CONFIG_IP6_NF_SECURITY=m
+CONFIG_DECNET_NF_GRABULATOR=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_BROUTE=m
+CONFIG_BRIDGE_EBT_T_FILTER=m
+CONFIG_BRIDGE_EBT_T_NAT=m
+CONFIG_BRIDGE_EBT_802_3=m
+CONFIG_BRIDGE_EBT_AMONG=m
+CONFIG_BRIDGE_EBT_ARP=m
+CONFIG_BRIDGE_EBT_IP=m
+CONFIG_BRIDGE_EBT_IP6=m
+CONFIG_BRIDGE_EBT_LIMIT=m
+CONFIG_BRIDGE_EBT_MARK=m
+CONFIG_BRIDGE_EBT_PKTTYPE=m
+CONFIG_BRIDGE_EBT_STP=m
+CONFIG_BRIDGE_EBT_VLAN=m
+CONFIG_BRIDGE_EBT_ARPREPLY=m
+CONFIG_BRIDGE_EBT_DNAT=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE_EBT_REDIRECT=m
+CONFIG_BRIDGE_EBT_SNAT=m
+CONFIG_BRIDGE_EBT_LOG=m
+CONFIG_BRIDGE_EBT_ULOG=m
+CONFIG_BRIDGE_EBT_NFLOG=m
+CONFIG_IP_DCCP=m
+CONFIG_RDS=m
+CONFIG_RDS_TCP=m
+CONFIG_TIPC=m
+CONFIG_ATM=m
+CONFIG_ATM_CLIP=m
+CONFIG_ATM_LANE=m
+CONFIG_ATM_MPOA=m
+CONFIG_ATM_BR2684=m
+CONFIG_BRIDGE=m
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+CONFIG_DECNET=m
+CONFIG_LLC2=m
+CONFIG_IPX=m
+CONFIG_ATALK=m
+CONFIG_DEV_APPLETALK=m
+CONFIG_IPDDP=m
+CONFIG_IPDDP_ENCAP=y
+CONFIG_IPDDP_DECAP=y
+CONFIG_X25=m
+CONFIG_LAPB=m
+CONFIG_ECONET=m
+CONFIG_ECONET_AUNUDP=y
+CONFIG_ECONET_NATIVE=y
+CONFIG_WAN_ROUTER=m
+CONFIG_PHONET=m
+CONFIG_IEEE802154=m
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CBQ=m
+CONFIG_NET_SCH_HTB=m
+CONFIG_NET_SCH_HFSC=m
+CONFIG_NET_SCH_ATM=m
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_MULTIQ=m
+CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_SFQ=m
+CONFIG_NET_SCH_TEQL=m
+CONFIG_NET_SCH_TBF=m
+CONFIG_NET_SCH_GRED=m
+CONFIG_NET_SCH_DSMARK=m
+CONFIG_NET_SCH_NETEM=m
+CONFIG_NET_SCH_DRR=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_TCINDEX=m
+CONFIG_NET_CLS_ROUTE4=m
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_CLS_U32_MARK=y
+CONFIG_NET_CLS_RSVP=m
+CONFIG_NET_CLS_RSVP6=m
+CONFIG_NET_CLS_FLOW=m
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_CMP=m
+CONFIG_NET_EMATCH_NBYTE=m
+CONFIG_NET_EMATCH_U32=m
+CONFIG_NET_EMATCH_META=m
+CONFIG_NET_EMATCH_TEXT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_GACT_PROB=y
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_ACT_SIMP=m
+CONFIG_NET_ACT_SKBEDIT=m
+CONFIG_DCB=y
+CONFIG_NET_PKTGEN=m
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+CONFIG_CONNECTOR=y
+CONFIG_MTD=m
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_NBD=m
+CONFIG_BLK_DEV_OSD=m
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_CDROM_PKTCDVD=y
+CONFIG_MISC_DEVICES=y
+CONFIG_RAID_ATTRS=m
+CONFIG_SCSI=y
+CONFIG_SCSI_TGT=m
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=m
+CONFIG_CHR_DEV_OSST=m
+CONFIG_BLK_DEV_SR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_CHR_DEV_SCH=m
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+CONFIG_SCSI_SCAN_ASYNC=y
+CONFIG_SCSI_SPI_ATTRS=m
+CONFIG_SCSI_FC_TGT_ATTRS=y
+CONFIG_SCSI_SAS_LIBSAS=m
+CONFIG_SCSI_SRP_ATTRS=m
+CONFIG_SCSI_SRP_TGT_ATTRS=y
+CONFIG_ISCSI_TCP=m
+CONFIG_LIBFCOE=m
+CONFIG_SCSI_DEBUG=m
+CONFIG_SCSI_DH=y
+CONFIG_SCSI_DH_RDAC=m
+CONFIG_SCSI_DH_HP_SW=m
+CONFIG_SCSI_DH_EMC=m
+CONFIG_SCSI_DH_ALUA=m
+CONFIG_SCSI_OSD_INITIATOR=m
+CONFIG_SCSI_OSD_ULD=m
+# CONFIG_INPUT_MOUSEDEV is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_EVBUG=m
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO_I8042 is not set
+CONFIG_SERIO_SERPORT=m
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIO_RAW=m
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
+CONFIG_LEGACY_PTY_COUNT=0
+CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_N_HDLC=m
+# CONFIG_DEVKMEM is not set
+CONFIG_STALDRV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=48
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_TIMERIOMEM=m
+CONFIG_RAW_DRIVER=m
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_UIO=y
+CONFIG_UIO_PDRV=m
+CONFIG_UIO_PDRV_GENIRQ=m
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
+CONFIG_OCFS2_FS=m
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_NILFS2_FS=m
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_QFMT_V1=m
+CONFIG_QFMT_V2=m
+CONFIG_AUTOFS4_FS=m
+CONFIG_FUSE_FS=y
+CONFIG_CUSE=m
+CONFIG_FSCACHE=m
+CONFIG_FSCACHE_STATS=y
+CONFIG_FSCACHE_HISTOGRAM=y
+CONFIG_CACHEFILES=m
+CONFIG_ISO9660_FS=m
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=m
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=m
+CONFIG_NTFS_FS=m
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_CONFIGFS_FS=y
+CONFIG_ADFS_FS=m
+CONFIG_AFFS_FS=m
+CONFIG_ECRYPT_FS=y
+CONFIG_HFS_FS=m
+CONFIG_HFSPLUS_FS=m
+CONFIG_BEFS_FS=m
+CONFIG_BFS_FS=m
+CONFIG_EFS_FS=m
+CONFIG_CRAMFS=m
+CONFIG_SQUASHFS=m
+CONFIG_VXFS_FS=m
+CONFIG_MINIX_FS=m
+CONFIG_OMFS_FS=m
+CONFIG_HPFS_FS=m
+CONFIG_QNX4FS_FS=m
+CONFIG_ROMFS_FS=m
+CONFIG_SYSV_FS=m
+CONFIG_UFS_FS=m
+CONFIG_EXOFS_FS=m
+CONFIG_NFS_FS=m
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_FSCACHE=y
+CONFIG_NFSD=m
+CONFIG_NFSD_V3_ACL=y
+CONFIG_NFSD_V4=y
+CONFIG_CIFS=m
+CONFIG_CIFS_WEAK_PW_HASH=y
+CONFIG_CIFS_UPCALL=y
+CONFIG_CIFS_XATTR=y
+CONFIG_CIFS_POSIX=y
+CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_EXPERIMENTAL=y
+CONFIG_NCP_FS=m
+CONFIG_NCPFS_PACKET_SIGNING=y
+CONFIG_NCPFS_IOCTL_LOCKING=y
+CONFIG_NCPFS_STRONG=y
+CONFIG_NCPFS_NFS_NS=y
+CONFIG_NCPFS_OS2_NS=y
+CONFIG_NCPFS_NLS=y
+CONFIG_NCPFS_EXTRAS=y
+CONFIG_CODA_FS=m
+CONFIG_AFS_FS=m
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ACORN_PARTITION=y
+CONFIG_ACORN_PARTITION_ICS=y
+CONFIG_ACORN_PARTITION_RISCIX=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_ATARI_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_LDM_PARTITION=y
+CONFIG_SGI_PARTITION=y
+CONFIG_ULTRIX_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+CONFIG_SYSV68_PARTITION=y
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="cp437"
+CONFIG_NLS_CODEPAGE_437=m
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=m
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=m
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=m
+CONFIG_NLS_ISO8859_1=m
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=m
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_SCHED_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_KGDB=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=0
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SMACK=y
+CONFIG_SECURITY_TOMOYO=y
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_CCM=m
+CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_XCBC=m
+CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_FCRYPT=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_ZLIB=m
+CONFIG_CRYPTO_LZO=m
+CONFIG_CRC_CCITT=m
+CONFIG_CRC7=m
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 86877539c6e..34c0d3cb116 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -33,6 +33,7 @@
 #define PRID_COMP_TOSHIBA	0x070000
 #define PRID_COMP_LSI		0x080000
 #define PRID_COMP_LEXRA		0x0b0000
+#define PRID_COMP_NETLOGIC	0x0c0000
 #define PRID_COMP_CAVIUM	0x0d0000
 #define PRID_COMP_INGENIC	0xd00000
 
@@ -142,6 +143,31 @@
 #define PRID_IMP_JZRISC        0x0200
 
 /*
+ * These are the PRID's for when 23:16 == PRID_COMP_NETLOGIC
+ */
+#define PRID_IMP_NETLOGIC_XLR732	0x0000
+#define PRID_IMP_NETLOGIC_XLR716	0x0200
+#define PRID_IMP_NETLOGIC_XLR532	0x0900
+#define PRID_IMP_NETLOGIC_XLR308	0x0600
+#define PRID_IMP_NETLOGIC_XLR532C	0x0800
+#define PRID_IMP_NETLOGIC_XLR516C	0x0a00
+#define PRID_IMP_NETLOGIC_XLR508C	0x0b00
+#define PRID_IMP_NETLOGIC_XLR308C	0x0f00
+#define PRID_IMP_NETLOGIC_XLS608	0x8000
+#define PRID_IMP_NETLOGIC_XLS408	0x8800
+#define PRID_IMP_NETLOGIC_XLS404	0x8c00
+#define PRID_IMP_NETLOGIC_XLS208	0x8e00
+#define PRID_IMP_NETLOGIC_XLS204	0x8f00
+#define PRID_IMP_NETLOGIC_XLS108	0xce00
+#define PRID_IMP_NETLOGIC_XLS104	0xcf00
+#define PRID_IMP_NETLOGIC_XLS616B	0x4000
+#define PRID_IMP_NETLOGIC_XLS608B	0x4a00
+#define PRID_IMP_NETLOGIC_XLS416B	0x4400
+#define PRID_IMP_NETLOGIC_XLS412B	0x4c00
+#define PRID_IMP_NETLOGIC_XLS408B	0x4e00
+#define PRID_IMP_NETLOGIC_XLS404B	0x4f00
+
+/*
  * Definitions for 7:0 on legacy processors
  */
 
@@ -234,6 +260,7 @@ enum cpu_type_enum {
 	 */
 	CPU_5KC, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
 	CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2,
+	CPU_XLR,
 
 	CPU_LAST
 };
diff --git a/arch/mips/include/asm/i8253.h b/arch/mips/include/asm/i8253.h
index 48bb8237299..9ad011366f7 100644
--- a/arch/mips/include/asm/i8253.h
+++ b/arch/mips/include/asm/i8253.h
@@ -12,8 +12,13 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
+#define PIT_LATCH		LATCH
+
 extern raw_spinlock_t i8253_lock;
 
 extern void setup_pit_timer(void);
 
+#define inb_pit inb_p
+#define outb_pit outb_p
+
 #endif /* __ASM_I8253_H */
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 7622ccf7507..1881b316ca4 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -20,16 +20,18 @@
 #define WORD_INSN ".word"
 #endif
 
-#define JUMP_LABEL(key, label)						\
-	do {								\
-		asm goto("1:\tnop\n\t"					\
-			"nop\n\t"					\
-			".pushsection __jump_table,  \"a\"\n\t"		\
-			WORD_INSN " 1b, %l[" #label "], %0\n\t"		\
-			".popsection\n\t"				\
-			: :  "i" (key) :  : label);			\
-	} while (0)
-
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\tnop\n\t"
+		"nop\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		WORD_INSN " 1b, %l[l_yes], %0\n\t"
+		".popsection\n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index a6976619160..f260ebed713 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -161,6 +161,45 @@ static inline int alchemy_get_cputype(void)
 	return ALCHEMY_CPU_UNKNOWN;
 }
 
+/* return number of uarts on a given cputype */
+static inline int alchemy_get_uarts(int type)
+{
+	switch (type) {
+	case ALCHEMY_CPU_AU1000:
+		return 4;
+	case ALCHEMY_CPU_AU1500:
+	case ALCHEMY_CPU_AU1200:
+		return 2;
+	case ALCHEMY_CPU_AU1100:
+	case ALCHEMY_CPU_AU1550:
+		return 3;
+	}
+	return 0;
+}
+
+/* enable an UART block if it isn't already */
+static inline void alchemy_uart_enable(u32 uart_phys)
+{
+	void __iomem *addr = (void __iomem *)KSEG1ADDR(uart_phys);
+
+	/* reset, enable clock, deassert reset */
+	if ((__raw_readl(addr + 0x100) & 3) != 3) {
+		__raw_writel(0, addr + 0x100);
+		wmb();
+		__raw_writel(1, addr + 0x100);
+		wmb();
+	}
+	__raw_writel(3, addr + 0x100);
+	wmb();
+}
+
+static inline void alchemy_uart_disable(u32 uart_phys)
+{
+	void __iomem *addr = (void __iomem *)KSEG1ADDR(uart_phys);
+	__raw_writel(0, addr + 0x100);	/* UART_MOD_CNTRL */
+	wmb();
+}
+
 static inline void alchemy_uart_putchar(u32 uart_phys, u8 c)
 {
 	void __iomem *base = (void __iomem *)KSEG1ADDR(uart_phys);
@@ -180,6 +219,20 @@ static inline void alchemy_uart_putchar(u32 uart_phys, u8 c)
 	wmb();
 }
 
+/* return number of ethernet MACs on a given cputype */
+static inline int alchemy_get_macs(int type)
+{
+	switch (type) {
+	case ALCHEMY_CPU_AU1000:
+	case ALCHEMY_CPU_AU1500:
+	case ALCHEMY_CPU_AU1550:
+		return 2;
+	case ALCHEMY_CPU_AU1100:
+		return 1;
+	}
+	return 0;
+}
+
 /* arch/mips/au1000/common/clocks.c */
 extern void set_au1x00_speed(unsigned int new_freq);
 extern unsigned int get_au1x00_speed(void);
@@ -630,38 +683,42 @@ enum soc_au1200_ints {
 
 /*
  * Physical base addresses for integrated peripherals
+ * 0..au1000 1..au1500 2..au1100 3..au1550 4..au1200
  */
 
+#define AU1000_AC97_PHYS_ADDR		0x10000000 /* 012 */
+#define AU1000_USBD_PHYS_ADDR		0x10200000 /* 0123 */
+#define AU1000_IC0_PHYS_ADDR		0x10400000 /* 01234 */
+#define AU1000_MAC0_PHYS_ADDR		0x10500000 /* 023 */
+#define AU1000_MAC1_PHYS_ADDR		0x10510000 /* 023 */
+#define AU1000_MACEN_PHYS_ADDR		0x10520000 /* 023 */
+#define AU1100_SD0_PHYS_ADDR		0x10600000 /* 24 */
+#define AU1100_SD1_PHYS_ADDR		0x10680000 /* 24 */
+#define AU1000_I2S_PHYS_ADDR		0x11000000 /* 02 */
+#define AU1500_MAC0_PHYS_ADDR		0x11500000 /* 1 */
+#define AU1500_MAC1_PHYS_ADDR		0x11510000 /* 1 */
+#define AU1500_MACEN_PHYS_ADDR		0x11520000 /* 1 */
+#define AU1000_UART0_PHYS_ADDR		0x11100000 /* 01234 */
+#define AU1000_UART1_PHYS_ADDR		0x11200000 /* 0234 */
+#define AU1000_UART2_PHYS_ADDR		0x11300000 /* 0 */
+#define AU1000_UART3_PHYS_ADDR		0x11400000 /* 0123 */
+#define AU1500_GPIO2_PHYS_ADDR		0x11700000 /* 1234 */
+#define AU1000_IC1_PHYS_ADDR		0x11800000 /* 01234 */
+#define AU1000_SYS_PHYS_ADDR		0x11900000 /* 01234 */
+#define AU1000_DMA_PHYS_ADDR		0x14002000 /* 012 */
+#define AU1550_DBDMA_PHYS_ADDR		0x14002000 /* 34 */
+#define AU1550_DBDMA_CONF_PHYS_ADDR	0x14003000 /* 34 */
+#define AU1000_MACDMA0_PHYS_ADDR	0x14004000 /* 0123 */
+#define AU1000_MACDMA1_PHYS_ADDR	0x14004200 /* 0123 */
+
+
 #ifdef CONFIG_SOC_AU1000
 #define	MEM_PHYS_ADDR		0x14000000
 #define	STATIC_MEM_PHYS_ADDR	0x14001000
-#define	DMA0_PHYS_ADDR		0x14002000
-#define	DMA1_PHYS_ADDR		0x14002100
-#define	DMA2_PHYS_ADDR		0x14002200
-#define	DMA3_PHYS_ADDR		0x14002300
-#define	DMA4_PHYS_ADDR		0x14002400
-#define	DMA5_PHYS_ADDR		0x14002500
-#define	DMA6_PHYS_ADDR		0x14002600
-#define	DMA7_PHYS_ADDR		0x14002700
-#define	IC0_PHYS_ADDR		0x10400000
-#define	IC1_PHYS_ADDR		0x11800000
-#define	AC97_PHYS_ADDR		0x10000000
 #define	USBH_PHYS_ADDR		0x10100000
-#define	USBD_PHYS_ADDR		0x10200000
 #define	IRDA_PHYS_ADDR		0x10300000
-#define	MAC0_PHYS_ADDR		0x10500000
-#define	MAC1_PHYS_ADDR		0x10510000
-#define	MACEN_PHYS_ADDR		0x10520000
-#define	MACDMA0_PHYS_ADDR	0x14004000
-#define	MACDMA1_PHYS_ADDR	0x14004200
-#define	I2S_PHYS_ADDR		0x11000000
-#define	UART0_PHYS_ADDR		0x11100000
-#define	UART1_PHYS_ADDR		0x11200000
-#define	UART2_PHYS_ADDR		0x11300000
-#define	UART3_PHYS_ADDR		0x11400000
 #define	SSI0_PHYS_ADDR		0x11600000
 #define	SSI1_PHYS_ADDR		0x11680000
-#define	SYS_PHYS_ADDR		0x11900000
 #define PCMCIA_IO_PHYS_ADDR	0xF00000000ULL
 #define PCMCIA_ATTR_PHYS_ADDR	0xF40000000ULL
 #define PCMCIA_MEM_PHYS_ADDR	0xF80000000ULL
@@ -672,30 +729,8 @@ enum soc_au1200_ints {
 #ifdef CONFIG_SOC_AU1500
 #define	MEM_PHYS_ADDR		0x14000000
 #define	STATIC_MEM_PHYS_ADDR	0x14001000
-#define	DMA0_PHYS_ADDR		0x14002000
-#define	DMA1_PHYS_ADDR		0x14002100
-#define	DMA2_PHYS_ADDR		0x14002200
-#define	DMA3_PHYS_ADDR		0x14002300
-#define	DMA4_PHYS_ADDR		0x14002400
-#define	DMA5_PHYS_ADDR		0x14002500
-#define	DMA6_PHYS_ADDR		0x14002600
-#define	DMA7_PHYS_ADDR		0x14002700
-#define	IC0_PHYS_ADDR		0x10400000
-#define	IC1_PHYS_ADDR		0x11800000
-#define	AC97_PHYS_ADDR		0x10000000
 #define	USBH_PHYS_ADDR		0x10100000
-#define	USBD_PHYS_ADDR		0x10200000
 #define PCI_PHYS_ADDR		0x14005000
-#define	MAC0_PHYS_ADDR		0x11500000
-#define	MAC1_PHYS_ADDR		0x11510000
-#define	MACEN_PHYS_ADDR		0x11520000
-#define	MACDMA0_PHYS_ADDR	0x14004000
-#define	MACDMA1_PHYS_ADDR	0x14004200
-#define	I2S_PHYS_ADDR		0x11000000
-#define	UART0_PHYS_ADDR		0x11100000
-#define	UART3_PHYS_ADDR		0x11400000
-#define GPIO2_PHYS_ADDR		0x11700000
-#define	SYS_PHYS_ADDR		0x11900000
 #define PCI_MEM_PHYS_ADDR	0x400000000ULL
 #define PCI_IO_PHYS_ADDR	0x500000000ULL
 #define PCI_CONFIG0_PHYS_ADDR	0x600000000ULL
@@ -710,34 +745,10 @@ enum soc_au1200_ints {
 #ifdef CONFIG_SOC_AU1100
 #define	MEM_PHYS_ADDR		0x14000000
 #define	STATIC_MEM_PHYS_ADDR	0x14001000
-#define	DMA0_PHYS_ADDR		0x14002000
-#define	DMA1_PHYS_ADDR		0x14002100
-#define	DMA2_PHYS_ADDR		0x14002200
-#define	DMA3_PHYS_ADDR		0x14002300
-#define	DMA4_PHYS_ADDR		0x14002400
-#define	DMA5_PHYS_ADDR		0x14002500
-#define	DMA6_PHYS_ADDR		0x14002600
-#define	DMA7_PHYS_ADDR		0x14002700
-#define	IC0_PHYS_ADDR		0x10400000
-#define SD0_PHYS_ADDR		0x10600000
-#define SD1_PHYS_ADDR		0x10680000
-#define	IC1_PHYS_ADDR		0x11800000
-#define	AC97_PHYS_ADDR		0x10000000
 #define	USBH_PHYS_ADDR		0x10100000
-#define	USBD_PHYS_ADDR		0x10200000
 #define	IRDA_PHYS_ADDR		0x10300000
-#define	MAC0_PHYS_ADDR		0x10500000
-#define	MACEN_PHYS_ADDR		0x10520000
-#define	MACDMA0_PHYS_ADDR	0x14004000
-#define	MACDMA1_PHYS_ADDR	0x14004200
-#define	I2S_PHYS_ADDR		0x11000000
-#define	UART0_PHYS_ADDR		0x11100000
-#define	UART1_PHYS_ADDR		0x11200000
-#define	UART3_PHYS_ADDR		0x11400000
 #define	SSI0_PHYS_ADDR		0x11600000
 #define	SSI1_PHYS_ADDR		0x11680000
-#define GPIO2_PHYS_ADDR		0x11700000
-#define	SYS_PHYS_ADDR		0x11900000
 #define LCD_PHYS_ADDR		0x15000000
 #define PCMCIA_IO_PHYS_ADDR	0xF00000000ULL
 #define PCMCIA_ATTR_PHYS_ADDR	0xF40000000ULL
@@ -749,22 +760,8 @@ enum soc_au1200_ints {
 #ifdef CONFIG_SOC_AU1550
 #define	MEM_PHYS_ADDR		0x14000000
 #define	STATIC_MEM_PHYS_ADDR	0x14001000
-#define	IC0_PHYS_ADDR		0x10400000
-#define	IC1_PHYS_ADDR		0x11800000
 #define	USBH_PHYS_ADDR		0x14020000
-#define	USBD_PHYS_ADDR		0x10200000
 #define PCI_PHYS_ADDR		0x14005000
-#define	MAC0_PHYS_ADDR		0x10500000
-#define	MAC1_PHYS_ADDR		0x10510000
-#define	MACEN_PHYS_ADDR		0x10520000
-#define	MACDMA0_PHYS_ADDR	0x14004000
-#define	MACDMA1_PHYS_ADDR	0x14004200
-#define	UART0_PHYS_ADDR		0x11100000
-#define	UART1_PHYS_ADDR		0x11200000
-#define	UART3_PHYS_ADDR		0x11400000
-#define GPIO2_PHYS_ADDR		0x11700000
-#define	SYS_PHYS_ADDR		0x11900000
-#define	DDMA_PHYS_ADDR		0x14002000
 #define PE_PHYS_ADDR		0x14008000
 #define PSC0_PHYS_ADDR		0x11A00000
 #define PSC1_PHYS_ADDR		0x11B00000
@@ -786,19 +783,10 @@ enum soc_au1200_ints {
 #define	STATIC_MEM_PHYS_ADDR	0x14001000
 #define AES_PHYS_ADDR		0x10300000
 #define CIM_PHYS_ADDR		0x14004000
-#define	IC0_PHYS_ADDR		0x10400000
-#define	IC1_PHYS_ADDR		0x11800000
 #define USBM_PHYS_ADDR		0x14020000
 #define	USBH_PHYS_ADDR		0x14020100
-#define	UART0_PHYS_ADDR		0x11100000
-#define	UART1_PHYS_ADDR		0x11200000
-#define GPIO2_PHYS_ADDR		0x11700000
-#define	SYS_PHYS_ADDR		0x11900000
-#define	DDMA_PHYS_ADDR		0x14002000
 #define PSC0_PHYS_ADDR	 	0x11A00000
 #define PSC1_PHYS_ADDR	 	0x11B00000
-#define SD0_PHYS_ADDR		0x10600000
-#define SD1_PHYS_ADDR		0x10680000
 #define LCD_PHYS_ADDR		0x15000000
 #define SWCNT_PHYS_ADDR		0x1110010C
 #define MAEFE_PHYS_ADDR		0x14012000
@@ -835,183 +823,43 @@ enum soc_au1200_ints {
 #endif
 
 
-/* Interrupt Controller register offsets */
-#define IC_CFG0RD		0x40
-#define IC_CFG0SET		0x40
-#define IC_CFG0CLR		0x44
-#define IC_CFG1RD		0x48
-#define IC_CFG1SET		0x48
-#define IC_CFG1CLR		0x4C
-#define IC_CFG2RD		0x50
-#define IC_CFG2SET		0x50
-#define IC_CFG2CLR		0x54
-#define IC_REQ0INT		0x54
-#define IC_SRCRD		0x58
-#define IC_SRCSET		0x58
-#define IC_SRCCLR		0x5C
-#define IC_REQ1INT		0x5C
-#define IC_ASSIGNRD		0x60
-#define IC_ASSIGNSET		0x60
-#define IC_ASSIGNCLR		0x64
-#define IC_WAKERD		0x68
-#define IC_WAKESET		0x68
-#define IC_WAKECLR		0x6C
-#define IC_MASKRD		0x70
-#define IC_MASKSET		0x70
-#define IC_MASKCLR		0x74
-#define IC_RISINGRD		0x78
-#define IC_RISINGCLR		0x78
-#define IC_FALLINGRD		0x7C
-#define IC_FALLINGCLR		0x7C
-#define IC_TESTBIT		0x80
-
-
-/* Interrupt Controller 0 */
-#define IC0_CFG0RD		0xB0400040
-#define IC0_CFG0SET		0xB0400040
-#define IC0_CFG0CLR		0xB0400044
-
-#define IC0_CFG1RD		0xB0400048
-#define IC0_CFG1SET		0xB0400048
-#define IC0_CFG1CLR		0xB040004C
-
-#define IC0_CFG2RD		0xB0400050
-#define IC0_CFG2SET		0xB0400050
-#define IC0_CFG2CLR		0xB0400054
-
-#define IC0_REQ0INT		0xB0400054
-#define IC0_SRCRD		0xB0400058
-#define IC0_SRCSET		0xB0400058
-#define IC0_SRCCLR		0xB040005C
-#define IC0_REQ1INT		0xB040005C
-
-#define IC0_ASSIGNRD		0xB0400060
-#define IC0_ASSIGNSET		0xB0400060
-#define IC0_ASSIGNCLR		0xB0400064
-
-#define IC0_WAKERD		0xB0400068
-#define IC0_WAKESET		0xB0400068
-#define IC0_WAKECLR		0xB040006C
-
-#define IC0_MASKRD		0xB0400070
-#define IC0_MASKSET		0xB0400070
-#define IC0_MASKCLR		0xB0400074
-
-#define IC0_RISINGRD		0xB0400078
-#define IC0_RISINGCLR		0xB0400078
-#define IC0_FALLINGRD		0xB040007C
-#define IC0_FALLINGCLR		0xB040007C
-
-#define IC0_TESTBIT		0xB0400080
-
-/* Interrupt Controller 1 */
-#define IC1_CFG0RD		0xB1800040
-#define IC1_CFG0SET		0xB1800040
-#define IC1_CFG0CLR		0xB1800044
-
-#define IC1_CFG1RD		0xB1800048
-#define IC1_CFG1SET		0xB1800048
-#define IC1_CFG1CLR		0xB180004C
-
-#define IC1_CFG2RD		0xB1800050
-#define IC1_CFG2SET		0xB1800050
-#define IC1_CFG2CLR		0xB1800054
-
-#define IC1_REQ0INT		0xB1800054
-#define IC1_SRCRD		0xB1800058
-#define IC1_SRCSET		0xB1800058
-#define IC1_SRCCLR		0xB180005C
-#define IC1_REQ1INT		0xB180005C
-
-#define IC1_ASSIGNRD            0xB1800060
-#define IC1_ASSIGNSET           0xB1800060
-#define IC1_ASSIGNCLR           0xB1800064
-
-#define IC1_WAKERD		0xB1800068
-#define IC1_WAKESET		0xB1800068
-#define IC1_WAKECLR		0xB180006C
-
-#define IC1_MASKRD		0xB1800070
-#define IC1_MASKSET		0xB1800070
-#define IC1_MASKCLR		0xB1800074
-
-#define IC1_RISINGRD		0xB1800078
-#define IC1_RISINGCLR		0xB1800078
-#define IC1_FALLINGRD		0xB180007C
-#define IC1_FALLINGCLR		0xB180007C
-
-#define IC1_TESTBIT		0xB1800080
 
 
 /* Au1000 */
 #ifdef CONFIG_SOC_AU1000
 
-#define UART0_ADDR		0xB1100000
-#define UART3_ADDR		0xB1400000
-
 #define USB_OHCI_BASE		0x10100000	/* phys addr for ioremap */
 #define USB_HOST_CONFIG 	0xB017FFFC
 #define FOR_PLATFORM_C_USB_HOST_INT AU1000_USB_HOST_INT
-
-#define AU1000_ETH0_BASE	0xB0500000
-#define AU1000_ETH1_BASE	0xB0510000
-#define AU1000_MAC0_ENABLE	0xB0520000
-#define AU1000_MAC1_ENABLE	0xB0520004
-#define NUM_ETH_INTERFACES 2
 #endif /* CONFIG_SOC_AU1000 */
 
 /* Au1500 */
 #ifdef CONFIG_SOC_AU1500
 
-#define UART0_ADDR		0xB1100000
-#define UART3_ADDR		0xB1400000
-
 #define USB_OHCI_BASE		0x10100000	/* phys addr for ioremap */
 #define USB_HOST_CONFIG 	0xB017fffc
 #define FOR_PLATFORM_C_USB_HOST_INT AU1500_USB_HOST_INT
-
-#define AU1500_ETH0_BASE	0xB1500000
-#define AU1500_ETH1_BASE	0xB1510000
-#define AU1500_MAC0_ENABLE	0xB1520000
-#define AU1500_MAC1_ENABLE	0xB1520004
-#define NUM_ETH_INTERFACES 2
 #endif /* CONFIG_SOC_AU1500 */
 
 /* Au1100 */
 #ifdef CONFIG_SOC_AU1100
 
-#define UART0_ADDR		0xB1100000
-#define UART3_ADDR		0xB1400000
-
 #define USB_OHCI_BASE		0x10100000	/* phys addr for ioremap */
 #define USB_HOST_CONFIG 	0xB017FFFC
 #define FOR_PLATFORM_C_USB_HOST_INT AU1100_USB_HOST_INT
-
-#define AU1100_ETH0_BASE	0xB0500000
-#define AU1100_MAC0_ENABLE	0xB0520000
-#define NUM_ETH_INTERFACES 1
 #endif /* CONFIG_SOC_AU1100 */
 
 #ifdef CONFIG_SOC_AU1550
-#define UART0_ADDR		0xB1100000
 
 #define USB_OHCI_BASE		0x14020000	/* phys addr for ioremap */
 #define USB_OHCI_LEN		0x00060000
 #define USB_HOST_CONFIG 	0xB4027ffc
 #define FOR_PLATFORM_C_USB_HOST_INT AU1550_USB_HOST_INT
-
-#define AU1550_ETH0_BASE	0xB0500000
-#define AU1550_ETH1_BASE	0xB0510000
-#define AU1550_MAC0_ENABLE	0xB0520000
-#define AU1550_MAC1_ENABLE	0xB0520004
-#define NUM_ETH_INTERFACES 2
 #endif /* CONFIG_SOC_AU1550 */
 
 
 #ifdef CONFIG_SOC_AU1200
 
-#define UART0_ADDR		0xB1100000
-
 #define USB_UOC_BASE		0x14020020
 #define USB_UOC_LEN		0x20
 #define USB_OHCI_BASE		0x14020100
@@ -1504,22 +1352,6 @@ enum soc_au1200_ints {
 #define SYS_PINFUNC_S1B 	(1 << 2)
 #endif
 
-#define SYS_TRIOUTRD		0xB1900100
-#define SYS_TRIOUTCLR		0xB1900100
-#define SYS_OUTPUTRD		0xB1900108
-#define SYS_OUTPUTSET		0xB1900108
-#define SYS_OUTPUTCLR		0xB190010C
-#define SYS_PINSTATERD		0xB1900110
-#define SYS_PININPUTEN		0xB1900110
-
-/* GPIO2, Au1500, Au1550 only */
-#define GPIO2_BASE		0xB1700000
-#define GPIO2_DIR		(GPIO2_BASE + 0)
-#define GPIO2_OUTPUT		(GPIO2_BASE + 8)
-#define GPIO2_PINSTATE		(GPIO2_BASE + 0xC)
-#define GPIO2_INTENABLE 	(GPIO2_BASE + 0x10)
-#define GPIO2_ENABLE		(GPIO2_BASE + 0x14)
-
 /* Power Management */
 #define SYS_SCRATCH0		0xB1900018
 #define SYS_SCRATCH1		0xB190001C
@@ -1635,12 +1467,6 @@ enum soc_au1200_ints {
 #  define AC97C_RS		(1 << 1)
 #  define AC97C_CE		(1 << 0)
 
-/* Secure Digital (SD) Controller */
-#define SD0_XMIT_FIFO	0xB0600000
-#define SD0_RECV_FIFO	0xB0600004
-#define SD1_XMIT_FIFO	0xB0680000
-#define SD1_RECV_FIFO	0xB0680004
-
 #if defined(CONFIG_SOC_AU1500) || defined(CONFIG_SOC_AU1550)
 /* Au1500 PCI Controller */
 #define Au1500_CFG_BASE 	0xB4005000	/* virtual, KSEG1 addr */
diff --git a/arch/mips/include/asm/mach-au1x00/au1000_dma.h b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
index c333b4e1cd4..59f5b55b220 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000_dma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000_dma.h
@@ -37,10 +37,6 @@
 
 #define NUM_AU1000_DMA_CHANNELS	8
 
-/* DMA Channel Base Addresses */
-#define DMA_CHANNEL_BASE	0xB4002000
-#define DMA_CHANNEL_LEN		0x00000100
-
 /* DMA Channel Register Offsets */
 #define DMA_MODE_SET		0x00000000
 #define DMA_MODE_READ		DMA_MODE_SET
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
index c8a553a36ba..2fdacfe85e2 100644
--- a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
@@ -37,14 +37,6 @@
 
 #ifndef _LANGUAGE_ASSEMBLY
 
-/*
- * The DMA base addresses.
- * The channels are every 256 bytes (0x0100) from the channel 0 base.
- * Interrupt status/enable is bits 15:0 for channels 15 to zero.
- */
-#define DDMA_GLOBAL_BASE	0xb4003000
-#define DDMA_CHANNEL_BASE	0xb4002000
-
 typedef volatile struct dbdma_global {
 	u32	ddma_config;
 	u32	ddma_intstat;
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
index 62d2f136d94..1f41a522906 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
@@ -24,6 +24,23 @@
 
 #define MAKE_IRQ(intc, off)	(AU1000_INTC##intc##_INT_BASE + (off))
 
+/* GPIO1 registers within SYS_ area */
+#define SYS_TRIOUTRD		0x100
+#define SYS_TRIOUTCLR		0x100
+#define SYS_OUTPUTRD		0x108
+#define SYS_OUTPUTSET		0x108
+#define SYS_OUTPUTCLR		0x10C
+#define SYS_PINSTATERD		0x110
+#define SYS_PININPUTEN		0x110
+
+/* register offsets within GPIO2 block */
+#define GPIO2_DIR		0x00
+#define GPIO2_OUTPUT		0x08
+#define GPIO2_PINSTATE		0x0C
+#define GPIO2_INTENABLE		0x10
+#define GPIO2_ENABLE		0x14
+
+struct gpio;
 
 static inline int au1000_gpio1_to_irq(int gpio)
 {
@@ -200,23 +217,26 @@ static inline int au1200_irq_to_gpio(int irq)
  */
 static inline void alchemy_gpio1_set_value(int gpio, int v)
 {
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
 	unsigned long mask = 1 << (gpio - ALCHEMY_GPIO1_BASE);
 	unsigned long r = v ? SYS_OUTPUTSET : SYS_OUTPUTCLR;
-	au_writel(mask, r);
-	au_sync();
+	__raw_writel(mask, base + r);
+	wmb();
 }
 
 static inline int alchemy_gpio1_get_value(int gpio)
 {
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
 	unsigned long mask = 1 << (gpio - ALCHEMY_GPIO1_BASE);
-	return au_readl(SYS_PINSTATERD) & mask;
+	return __raw_readl(base + SYS_PINSTATERD) & mask;
 }
 
 static inline int alchemy_gpio1_direction_input(int gpio)
 {
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
 	unsigned long mask = 1 << (gpio - ALCHEMY_GPIO1_BASE);
-	au_writel(mask, SYS_TRIOUTCLR);
-	au_sync();
+	__raw_writel(mask, base + SYS_TRIOUTCLR);
+	wmb();
 	return 0;
 }
 
@@ -257,27 +277,31 @@ static inline int alchemy_gpio1_to_irq(int gpio)
  */
 static inline void __alchemy_gpio2_mod_dir(int gpio, int to_out)
 {
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
 	unsigned long mask = 1 << (gpio - ALCHEMY_GPIO2_BASE);
-	unsigned long d = au_readl(GPIO2_DIR);
+	unsigned long d = __raw_readl(base + GPIO2_DIR);
+
 	if (to_out)
 		d |= mask;
 	else
 		d &= ~mask;
-	au_writel(d, GPIO2_DIR);
-	au_sync();
+	__raw_writel(d, base + GPIO2_DIR);
+	wmb();
 }
 
 static inline void alchemy_gpio2_set_value(int gpio, int v)
 {
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
 	unsigned long mask;
 	mask = ((v) ? 0x00010001 : 0x00010000) << (gpio - ALCHEMY_GPIO2_BASE);
-	au_writel(mask, GPIO2_OUTPUT);
-	au_sync();
+	__raw_writel(mask, base + GPIO2_OUTPUT);
+	wmb();
 }
 
 static inline int alchemy_gpio2_get_value(int gpio)
 {
-	return au_readl(GPIO2_PINSTATE) & (1 << (gpio - ALCHEMY_GPIO2_BASE));
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
+	return __raw_readl(base + GPIO2_PINSTATE) & (1 << (gpio - ALCHEMY_GPIO2_BASE));
 }
 
 static inline int alchemy_gpio2_direction_input(int gpio)
@@ -329,21 +353,23 @@ static inline int alchemy_gpio2_to_irq(int gpio)
  */
 static inline void alchemy_gpio1_input_enable(void)
 {
-	au_writel(0, SYS_PININPUTEN);	/* the write op is key */
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
+	__raw_writel(0, base + SYS_PININPUTEN);	/* the write op is key */
+	wmb();
 }
 
 /* GPIO2 shared interrupts and control */
 
 static inline void __alchemy_gpio2_mod_int(int gpio2, int en)
 {
-	unsigned long r = au_readl(GPIO2_INTENABLE);
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
+	unsigned long r = __raw_readl(base + GPIO2_INTENABLE);
 	if (en)
 		r |= 1 << gpio2;
 	else
 		r &= ~(1 << gpio2);
-	au_writel(r, GPIO2_INTENABLE);
-	au_sync();
+	__raw_writel(r, base + GPIO2_INTENABLE);
+	wmb();
 }
 
 /**
@@ -418,10 +444,11 @@ static inline void alchemy_gpio2_disable_int(int gpio2)
  */
 static inline void alchemy_gpio2_enable(void)
 {
-	au_writel(3, GPIO2_ENABLE);	/* reset, clock enabled */
-	au_sync();
-	au_writel(1, GPIO2_ENABLE);	/* clock enabled */
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
+	__raw_writel(3, base + GPIO2_ENABLE);	/* reset, clock enabled */
+	wmb();
+	__raw_writel(1, base + GPIO2_ENABLE);	/* clock enabled */
+	wmb();
 }
 
 /**
@@ -431,8 +458,9 @@ static inline void alchemy_gpio2_enable(void)
  */
 static inline void alchemy_gpio2_disable(void)
 {
-	au_writel(2, GPIO2_ENABLE);	/* reset, clock disabled */
-	au_sync();
+	void __iomem *base = (void __iomem *)KSEG1ADDR(AU1500_GPIO2_PHYS_ADDR);
+	__raw_writel(2, base + GPIO2_ENABLE);	/* reset, clock disabled */
+	wmb();
 }
 
 /**********************************************************************/
@@ -556,6 +584,16 @@ static inline void gpio_set_value(int gpio, int v)
 	alchemy_gpio_set_value(gpio, v);
 }
 
+static inline int gpio_get_value_cansleep(unsigned gpio)
+{
+	return gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value_cansleep(unsigned gpio, int value)
+{
+	gpio_set_value(gpio, value);
+}
+
 static inline int gpio_is_valid(int gpio)
 {
 	return alchemy_gpio_is_valid(gpio);
@@ -581,10 +619,50 @@ static inline int gpio_request(unsigned gpio, const char *label)
 	return 0;
 }
 
+static inline int gpio_request_one(unsigned gpio,
+					unsigned long flags, const char *label)
+{
+	return 0;
+}
+
+static inline int gpio_request_array(struct gpio *array, size_t num)
+{
+	return 0;
+}
+
 static inline void gpio_free(unsigned gpio)
 {
 }
 
+static inline void gpio_free_array(struct gpio *array, size_t num)
+{
+}
+
+static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
+{
+	return -ENOSYS;
+}
+
+static inline int gpio_export(unsigned gpio, bool direction_may_change)
+{
+	return -ENOSYS;
+}
+
+static inline int gpio_export_link(struct device *dev, const char *name,
+				   unsigned gpio)
+{
+	return -ENOSYS;
+}
+
+static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
+{
+	return -ENOSYS;
+}
+
+static inline void gpio_unexport(unsigned gpio)
+{
+}
+
 #endif	/* !CONFIG_ALCHEMY_GPIO_INDIRECT */
 
 
diff --git a/arch/mips/include/asm/mach-bcm47xx/nvram.h b/arch/mips/include/asm/mach-bcm47xx/nvram.h
index 9759588ba3c..184d5ecb5f5 100644
--- a/arch/mips/include/asm/mach-bcm47xx/nvram.h
+++ b/arch/mips/include/asm/mach-bcm47xx/nvram.h
@@ -39,8 +39,16 @@ extern int nvram_getenv(char *name, char *val, size_t val_len);
 
 static inline void nvram_parse_macaddr(char *buf, u8 *macaddr)
 {
-	sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &macaddr[0], &macaddr[1],
-	       &macaddr[2], &macaddr[3], &macaddr[4], &macaddr[5]);
+	if (strchr(buf, ':'))
+		sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &macaddr[0],
+			&macaddr[1], &macaddr[2], &macaddr[3], &macaddr[4],
+			&macaddr[5]);
+	else if (strchr(buf, '-'))
+		sscanf(buf, "%hhx-%hhx-%hhx-%hhx-%hhx-%hhx", &macaddr[0],
+			&macaddr[1], &macaddr[2], &macaddr[3], &macaddr[4],
+			&macaddr[5]);
+	else
+		printk(KERN_WARNING "Can not parse mac address: %s\n", buf);
 }
 
 #endif
diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index 0b2b5eb22e9..dedef7d2b01 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -63,6 +63,11 @@
 	# CN30XX Disable instruction prefetching
 	or  v0, v0, 0x2000
 skip:
+	# First clear off CvmCtl[IPPCI] bit and move the performance
+	# counters interrupt to IRQ 6
+	li	v1, ~(7 << 7)
+	and	v0, v0, v1
+	ori	v0, v0, (6 << 7)
 	# Write the cavium control register
 	dmtc0   v0, CP0_CVMCTL_REG
 	sync
diff --git a/arch/mips/include/asm/mach-lantiq/lantiq.h b/arch/mips/include/asm/mach-lantiq/lantiq.h
new file mode 100644
index 00000000000..ce2f02929d2
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/lantiq.h
@@ -0,0 +1,63 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+#ifndef _LANTIQ_H__
+#define _LANTIQ_H__
+
+#include <linux/irq.h>
+
+/* generic reg access functions */
+#define ltq_r32(reg)		__raw_readl(reg)
+#define ltq_w32(val, reg)	__raw_writel(val, reg)
+#define ltq_w32_mask(clear, set, reg)	\
+	ltq_w32((ltq_r32(reg) & ~(clear)) | (set), reg)
+#define ltq_r8(reg)		__raw_readb(reg)
+#define ltq_w8(val, reg)	__raw_writeb(val, reg)
+
+/* register access macros for EBU and CGU */
+#define ltq_ebu_w32(x, y)	ltq_w32((x), ltq_ebu_membase + (y))
+#define ltq_ebu_r32(x)		ltq_r32(ltq_ebu_membase + (x))
+#define ltq_cgu_w32(x, y)	ltq_w32((x), ltq_cgu_membase + (y))
+#define ltq_cgu_r32(x)		ltq_r32(ltq_cgu_membase + (x))
+
+extern __iomem void *ltq_ebu_membase;
+extern __iomem void *ltq_cgu_membase;
+
+extern unsigned int ltq_get_cpu_ver(void);
+extern unsigned int ltq_get_soc_type(void);
+
+/* clock speeds */
+#define CLOCK_60M	60000000
+#define CLOCK_83M	83333333
+#define CLOCK_111M	111111111
+#define CLOCK_133M	133333333
+#define CLOCK_167M	166666667
+#define CLOCK_200M	200000000
+#define CLOCK_266M	266666666
+#define CLOCK_333M	333333333
+#define CLOCK_400M	400000000
+
+/* spinlock all ebu i/o */
+extern spinlock_t ebu_lock;
+
+/* some irq helpers */
+extern void ltq_disable_irq(struct irq_data *data);
+extern void ltq_mask_and_ack_irq(struct irq_data *data);
+extern void ltq_enable_irq(struct irq_data *data);
+
+/* find out what caused the last cpu reset */
+extern int ltq_reset_cause(void);
+#define LTQ_RST_CAUSE_WDTRST	0x20
+
+#define IOPORT_RESOURCE_START	0x10000000
+#define IOPORT_RESOURCE_END	0xffffffff
+#define IOMEM_RESOURCE_START	0x10000000
+#define IOMEM_RESOURCE_END	0xffffffff
+#define LTQ_FLASH_START		0x10000000
+#define LTQ_FLASH_MAX		0x04000000
+
+#endif
diff --git a/arch/mips/include/asm/mach-lantiq/lantiq_platform.h b/arch/mips/include/asm/mach-lantiq/lantiq_platform.h
new file mode 100644
index 00000000000..a305f1d0259
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/lantiq_platform.h
@@ -0,0 +1,53 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LANTIQ_PLATFORM_H__
+#define _LANTIQ_PLATFORM_H__
+
+#include <linux/mtd/partitions.h>
+#include <linux/socket.h>
+
+/* struct used to pass info to the pci core */
+enum {
+	PCI_CLOCK_INT = 0,
+	PCI_CLOCK_EXT
+};
+
+#define PCI_EXIN0	0x0001
+#define PCI_EXIN1	0x0002
+#define PCI_EXIN2	0x0004
+#define PCI_EXIN3	0x0008
+#define PCI_EXIN4	0x0010
+#define PCI_EXIN5	0x0020
+#define PCI_EXIN_MAX	6
+
+#define PCI_GNT1	0x0040
+#define PCI_GNT2	0x0080
+#define PCI_GNT3	0x0100
+#define PCI_GNT4	0x0200
+
+#define PCI_REQ1	0x0400
+#define PCI_REQ2	0x0800
+#define PCI_REQ3	0x1000
+#define PCI_REQ4	0x2000
+#define PCI_REQ_SHIFT	10
+#define PCI_REQ_MASK	0xf
+
+struct ltq_pci_data {
+	int clock;
+	int gpio;
+	int irq[16];
+};
+
+/* struct used to pass info to network drivers */
+struct ltq_eth_data {
+	struct sockaddr mac;
+	int mii_mode;
+};
+
+#endif
diff --git a/arch/mips/include/asm/mach-lantiq/war.h b/arch/mips/include/asm/mach-lantiq/war.h
new file mode 100644
index 00000000000..01b08ef368d
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/war.h
@@ -0,0 +1,24 @@
+/*
+ * 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.
+ *
+ */
+#ifndef __ASM_MIPS_MACH_LANTIQ_WAR_H
+#define __ASM_MIPS_MACH_LANTIQ_WAR_H
+
+#define R4600_V1_INDEX_ICACHEOP_WAR     0
+#define R4600_V1_HIT_CACHEOP_WAR        0
+#define R4600_V2_HIT_CACHEOP_WAR        0
+#define R5432_CP0_INTERRUPT_WAR         0
+#define BCM1250_M3_WAR                  0
+#define SIBYTE_1956_WAR                 0
+#define MIPS4K_ICACHE_REFILL_WAR        0
+#define MIPS_CACHE_SYNC_WAR             0
+#define TX49XX_ICACHE_INDEX_INV_WAR     0
+#define RM9000_CDEX_SMP_WAR             0
+#define ICACHE_REFILLS_WORKAROUND_WAR   0
+#define R10000_LLSC_WAR                 0
+#define MIPS34K_MISSED_ITLB_WAR         0
+
+#endif
diff --git a/arch/mips/include/asm/mach-lantiq/xway/irq.h b/arch/mips/include/asm/mach-lantiq/xway/irq.h
new file mode 100644
index 00000000000..a1471d2dd0d
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/xway/irq.h
@@ -0,0 +1,18 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef __LANTIQ_IRQ_H
+#define __LANTIQ_IRQ_H
+
+#include <lantiq_irq.h>
+
+#define NR_IRQS 256
+
+#include_next <irq.h>
+
+#endif
diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h
new file mode 100644
index 00000000000..b4465a888e2
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h
@@ -0,0 +1,66 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LANTIQ_XWAY_IRQ_H__
+#define _LANTIQ_XWAY_IRQ_H__
+
+#define INT_NUM_IRQ0		8
+#define INT_NUM_IM0_IRL0	(INT_NUM_IRQ0 + 0)
+#define INT_NUM_IM1_IRL0	(INT_NUM_IRQ0 + 32)
+#define INT_NUM_IM2_IRL0	(INT_NUM_IRQ0 + 64)
+#define INT_NUM_IM3_IRL0	(INT_NUM_IRQ0 + 96)
+#define INT_NUM_IM4_IRL0	(INT_NUM_IRQ0 + 128)
+#define INT_NUM_IM_OFFSET	(INT_NUM_IM1_IRL0 - INT_NUM_IM0_IRL0)
+
+#define LTQ_ASC_TIR(x)		(INT_NUM_IM3_IRL0 + (x * 8))
+#define LTQ_ASC_RIR(x)		(INT_NUM_IM3_IRL0 + (x * 8) + 1)
+#define LTQ_ASC_EIR(x)		(INT_NUM_IM3_IRL0 + (x * 8) + 2)
+
+#define LTQ_ASC_ASE_TIR		INT_NUM_IM2_IRL0
+#define LTQ_ASC_ASE_RIR		(INT_NUM_IM2_IRL0 + 2)
+#define LTQ_ASC_ASE_EIR		(INT_NUM_IM2_IRL0 + 3)
+
+#define LTQ_SSC_TIR		(INT_NUM_IM0_IRL0 + 15)
+#define LTQ_SSC_RIR		(INT_NUM_IM0_IRL0 + 14)
+#define LTQ_SSC_EIR		(INT_NUM_IM0_IRL0 + 16)
+
+#define LTQ_MEI_DYING_GASP_INT	(INT_NUM_IM1_IRL0 + 21)
+#define LTQ_MEI_INT		(INT_NUM_IM1_IRL0 + 23)
+
+#define LTQ_TIMER6_INT		(INT_NUM_IM1_IRL0 + 23)
+#define LTQ_USB_INT		(INT_NUM_IM1_IRL0 + 22)
+#define LTQ_USB_OC_INT		(INT_NUM_IM4_IRL0 + 23)
+
+#define MIPS_CPU_TIMER_IRQ		7
+
+#define LTQ_DMA_CH0_INT		(INT_NUM_IM2_IRL0)
+#define LTQ_DMA_CH1_INT		(INT_NUM_IM2_IRL0 + 1)
+#define LTQ_DMA_CH2_INT		(INT_NUM_IM2_IRL0 + 2)
+#define LTQ_DMA_CH3_INT		(INT_NUM_IM2_IRL0 + 3)
+#define LTQ_DMA_CH4_INT		(INT_NUM_IM2_IRL0 + 4)
+#define LTQ_DMA_CH5_INT		(INT_NUM_IM2_IRL0 + 5)
+#define LTQ_DMA_CH6_INT		(INT_NUM_IM2_IRL0 + 6)
+#define LTQ_DMA_CH7_INT		(INT_NUM_IM2_IRL0 + 7)
+#define LTQ_DMA_CH8_INT		(INT_NUM_IM2_IRL0 + 8)
+#define LTQ_DMA_CH9_INT		(INT_NUM_IM2_IRL0 + 9)
+#define LTQ_DMA_CH10_INT	(INT_NUM_IM2_IRL0 + 10)
+#define LTQ_DMA_CH11_INT	(INT_NUM_IM2_IRL0 + 11)
+#define LTQ_DMA_CH12_INT	(INT_NUM_IM2_IRL0 + 25)
+#define LTQ_DMA_CH13_INT	(INT_NUM_IM2_IRL0 + 26)
+#define LTQ_DMA_CH14_INT	(INT_NUM_IM2_IRL0 + 27)
+#define LTQ_DMA_CH15_INT	(INT_NUM_IM2_IRL0 + 28)
+#define LTQ_DMA_CH16_INT	(INT_NUM_IM2_IRL0 + 29)
+#define LTQ_DMA_CH17_INT	(INT_NUM_IM2_IRL0 + 30)
+#define LTQ_DMA_CH18_INT	(INT_NUM_IM2_IRL0 + 16)
+#define LTQ_DMA_CH19_INT	(INT_NUM_IM2_IRL0 + 21)
+
+#define LTQ_PPE_MBOX_INT	(INT_NUM_IM2_IRL0 + 24)
+
+#define INT_NUM_IM4_IRL14	(INT_NUM_IM4_IRL0 + 14)
+
+#endif
diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h
new file mode 100644
index 00000000000..8a3c6be669d
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h
@@ -0,0 +1,141 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_XWAY_H__
+#define _LTQ_XWAY_H__
+
+#ifdef CONFIG_SOC_TYPE_XWAY
+
+#include <lantiq.h>
+
+/* Chip IDs */
+#define SOC_ID_DANUBE1		0x129
+#define SOC_ID_DANUBE2		0x12B
+#define SOC_ID_TWINPASS		0x12D
+#define SOC_ID_AMAZON_SE	0x152
+#define SOC_ID_ARX188		0x16C
+#define SOC_ID_ARX168		0x16D
+#define SOC_ID_ARX182		0x16F
+
+/* SoC Types */
+#define SOC_TYPE_DANUBE		0x01
+#define SOC_TYPE_TWINPASS	0x02
+#define SOC_TYPE_AR9		0x03
+#define SOC_TYPE_VR9		0x04
+#define SOC_TYPE_AMAZON_SE	0x05
+
+/* ASC0/1 - serial port */
+#define LTQ_ASC0_BASE_ADDR	0x1E100400
+#define LTQ_ASC1_BASE_ADDR	0x1E100C00
+#define LTQ_ASC_SIZE		0x400
+
+/* RCU - reset control unit */
+#define LTQ_RCU_BASE_ADDR	0x1F203000
+#define LTQ_RCU_SIZE		0x1000
+
+/* GPTU - general purpose timer unit */
+#define LTQ_GPTU_BASE_ADDR	0x18000300
+#define LTQ_GPTU_SIZE		0x100
+
+/* EBU - external bus unit */
+#define LTQ_EBU_GPIO_START	0x14000000
+#define LTQ_EBU_GPIO_SIZE	0x1000
+
+#define LTQ_EBU_BASE_ADDR	0x1E105300
+#define LTQ_EBU_SIZE		0x100
+
+#define LTQ_EBU_BUSCON0		0x0060
+#define LTQ_EBU_PCC_CON		0x0090
+#define LTQ_EBU_PCC_IEN		0x00A4
+#define LTQ_EBU_PCC_ISTAT	0x00A0
+#define LTQ_EBU_BUSCON1		0x0064
+#define LTQ_EBU_ADDRSEL1	0x0024
+#define EBU_WRDIS		0x80000000
+
+/* CGU - clock generation unit */
+#define LTQ_CGU_BASE_ADDR	0x1F103000
+#define LTQ_CGU_SIZE		0x1000
+
+/* ICU - interrupt control unit */
+#define LTQ_ICU_BASE_ADDR	0x1F880200
+#define LTQ_ICU_SIZE		0x100
+
+/* EIU - external interrupt unit */
+#define LTQ_EIU_BASE_ADDR	0x1F101000
+#define LTQ_EIU_SIZE		0x1000
+
+/* PMU - power management unit */
+#define LTQ_PMU_BASE_ADDR	0x1F102000
+#define LTQ_PMU_SIZE		0x1000
+
+#define PMU_DMA			0x0020
+#define PMU_USB			0x8041
+#define PMU_LED			0x0800
+#define PMU_GPT			0x1000
+#define PMU_PPE			0x2000
+#define PMU_FPI			0x4000
+#define PMU_SWITCH		0x10000000
+
+/* ETOP - ethernet */
+#define LTQ_ETOP_BASE_ADDR	0x1E180000
+#define LTQ_ETOP_SIZE		0x40000
+
+/* DMA */
+#define LTQ_DMA_BASE_ADDR	0x1E104100
+#define LTQ_DMA_SIZE		0x800
+
+/* PCI */
+#define PCI_CR_BASE_ADDR	0x1E105400
+#define PCI_CR_SIZE		0x400
+
+/* WDT */
+#define LTQ_WDT_BASE_ADDR	0x1F8803F0
+#define LTQ_WDT_SIZE		0x10
+
+/* STP - serial to parallel conversion unit */
+#define LTQ_STP_BASE_ADDR	0x1E100BB0
+#define LTQ_STP_SIZE		0x40
+
+/* GPIO */
+#define LTQ_GPIO0_BASE_ADDR	0x1E100B10
+#define LTQ_GPIO1_BASE_ADDR	0x1E100B40
+#define LTQ_GPIO2_BASE_ADDR	0x1E100B70
+#define LTQ_GPIO_SIZE		0x30
+
+/* SSC */
+#define LTQ_SSC_BASE_ADDR	0x1e100800
+#define LTQ_SSC_SIZE		0x100
+
+/* MEI - dsl core */
+#define LTQ_MEI_BASE_ADDR	0x1E116000
+
+/* DEU - data encryption unit */
+#define LTQ_DEU_BASE_ADDR	0x1E103100
+
+/* MPS - multi processor unit (voice) */
+#define LTQ_MPS_BASE_ADDR	(KSEG1 + 0x1F107000)
+#define LTQ_MPS_CHIPID		((u32 *)(LTQ_MPS_BASE_ADDR + 0x0344))
+
+/* request a non-gpio and set the PIO config */
+extern int  ltq_gpio_request(unsigned int pin, unsigned int alt0,
+	unsigned int alt1, unsigned int dir, const char *name);
+extern void ltq_pmu_enable(unsigned int module);
+extern void ltq_pmu_disable(unsigned int module);
+
+static inline int ltq_is_ar9(void)
+{
+	return (ltq_get_soc_type() == SOC_TYPE_AR9);
+}
+
+static inline int ltq_is_vr9(void)
+{
+	return (ltq_get_soc_type() == SOC_TYPE_VR9);
+}
+
+#endif /* CONFIG_SOC_TYPE_XWAY */
+#endif /* _LTQ_XWAY_H__ */
diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h
new file mode 100644
index 00000000000..872943a4b90
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h
@@ -0,0 +1,60 @@
+/*
+ *   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., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
+ *
+ *   Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef LTQ_DMA_H__
+#define LTQ_DMA_H__
+
+#define LTQ_DESC_SIZE		0x08	/* each descriptor is 64bit */
+#define LTQ_DESC_NUM		0x40	/* 64 descriptors / channel */
+
+#define LTQ_DMA_OWN		BIT(31)	/* owner bit */
+#define LTQ_DMA_C		BIT(30) /* complete bit */
+#define LTQ_DMA_SOP		BIT(29) /* start of packet */
+#define LTQ_DMA_EOP		BIT(28) /* end of packet */
+#define LTQ_DMA_TX_OFFSET(x)	((x & 0x1f) << 23) /* data bytes offset */
+#define LTQ_DMA_RX_OFFSET(x)	((x & 0x7) << 23) /* data bytes offset */
+#define LTQ_DMA_SIZE_MASK	(0xffff) /* the size field is 16 bit */
+
+struct ltq_dma_desc {
+	u32 ctl;
+	u32 addr;
+};
+
+struct ltq_dma_channel {
+	int nr;				/* the channel number */
+	int irq;			/* the mapped irq */
+	int desc;			/* the current descriptor */
+	struct ltq_dma_desc *desc_base;	/* the descriptor base */
+	int phys;			/* physical addr */
+};
+
+enum {
+	DMA_PORT_ETOP = 0,
+	DMA_PORT_DEU,
+};
+
+extern void ltq_dma_enable_irq(struct ltq_dma_channel *ch);
+extern void ltq_dma_disable_irq(struct ltq_dma_channel *ch);
+extern void ltq_dma_ack_irq(struct ltq_dma_channel *ch);
+extern void ltq_dma_open(struct ltq_dma_channel *ch);
+extern void ltq_dma_close(struct ltq_dma_channel *ch);
+extern void ltq_dma_alloc_tx(struct ltq_dma_channel *ch);
+extern void ltq_dma_alloc_rx(struct ltq_dma_channel *ch);
+extern void ltq_dma_free(struct ltq_dma_channel *ch);
+extern void ltq_dma_init_port(int p);
+
+#endif
diff --git a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h
new file mode 100644
index 00000000000..3b728275b9b
--- /dev/null
+++ b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h
@@ -0,0 +1,47 @@
+/*
+ * 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) 2011 Netlogic Microsystems
+ * Copyright (C) 2003 Ralf Baechle
+ */
+#ifndef __ASM_MACH_NETLOGIC_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_NETLOGIC_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_4kex		1
+#define cpu_has_4k_cache	1
+#define cpu_has_watch		1
+#define cpu_has_mips16		0
+#define cpu_has_counter		1
+#define cpu_has_divec		1
+#define cpu_has_vce		0
+#define cpu_has_cache_cdex_p	0
+#define cpu_has_cache_cdex_s	0
+#define cpu_has_prefetch	1
+#define cpu_has_mcheck		1
+#define cpu_has_ejtag		1
+
+#define cpu_has_llsc		1
+#define cpu_has_vtag_icache	0
+#define cpu_has_dc_aliases	0
+#define cpu_has_ic_fills_f_dc	0
+#define cpu_has_dsp		0
+#define cpu_has_mipsmt		0
+#define cpu_has_userlocal	0
+#define cpu_icache_snoops_remote_store	0
+
+#define cpu_has_nofpuex		0
+#define cpu_has_64bits		1
+
+#define cpu_has_mips32r1	1
+#define cpu_has_mips32r2	0
+#define cpu_has_mips64r1	1
+#define cpu_has_mips64r2	0
+
+#define cpu_has_inclusive_pcaches	0
+
+#define cpu_dcache_line_size()	32
+#define cpu_icache_line_size()	32
+
+#endif /* __ASM_MACH_NETLOGIC_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-netlogic/irq.h b/arch/mips/include/asm/mach-netlogic/irq.h
new file mode 100644
index 00000000000..b5902458e7c
--- /dev/null
+++ b/arch/mips/include/asm/mach-netlogic/irq.h
@@ -0,0 +1,14 @@
+/*
+ * 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) 2011 Netlogic Microsystems.
+ */
+#ifndef __ASM_NETLOGIC_IRQ_H
+#define __ASM_NETLOGIC_IRQ_H
+
+#define NR_IRQS			64
+#define MIPS_CPU_IRQ_BASE	0
+
+#endif /* __ASM_NETLOGIC_IRQ_H */
diff --git a/arch/mips/include/asm/mach-netlogic/war.h b/arch/mips/include/asm/mach-netlogic/war.h
new file mode 100644
index 00000000000..22da8932735
--- /dev/null
+++ b/arch/mips/include/asm/mach-netlogic/war.h
@@ -0,0 +1,26 @@
+/*
+ * 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) 2011 Netlogic Microsystems.
+ * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org>
+ */
+#ifndef __ASM_MIPS_MACH_NLM_WAR_H
+#define __ASM_MIPS_MACH_NLM_WAR_H
+
+#define R4600_V1_INDEX_ICACHEOP_WAR	0
+#define R4600_V1_HIT_CACHEOP_WAR	0
+#define R4600_V2_HIT_CACHEOP_WAR	0
+#define R5432_CP0_INTERRUPT_WAR		0
+#define BCM1250_M3_WAR			0
+#define SIBYTE_1956_WAR			0
+#define MIPS4K_ICACHE_REFILL_WAR	0
+#define MIPS_CACHE_SYNC_WAR		0
+#define TX49XX_ICACHE_INDEX_INV_WAR	0
+#define RM9000_CDEX_SMP_WAR		0
+#define ICACHE_REFILLS_WORKAROUND_WAR	0
+#define R10000_LLSC_WAR			0
+#define MIPS34K_MISSED_ITLB_WAR		0
+
+#endif /* __ASM_MIPS_MACH_NLM_WAR_H */
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index d94085a3eaf..bc01a02cacd 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -118,6 +118,8 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_PROC_FAMILY "LOONGSON2 "
 #elif defined CONFIG_CPU_CAVIUM_OCTEON
 #define MODULE_PROC_FAMILY "OCTEON "
+#elif defined CONFIG_CPU_XLR
+#define MODULE_PROC_FAMILY "XLR "
 #else
 #error MODULE_PROC_FAMILY undefined for your processor configuration
 #endif
diff --git a/arch/mips/include/asm/netlogic/interrupt.h b/arch/mips/include/asm/netlogic/interrupt.h
new file mode 100644
index 00000000000..a85aadb6cfd
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/interrupt.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_INTERRUPT_H
+#define _ASM_NLM_INTERRUPT_H
+
+/* Defines for the IRQ numbers */
+
+#define IRQ_IPI_SMP_FUNCTION	3
+#define IRQ_IPI_SMP_RESCHEDULE	4
+#define IRQ_MSGRING		6
+#define IRQ_TIMER		7
+
+#endif
diff --git a/arch/mips/include/asm/netlogic/mips-extns.h b/arch/mips/include/asm/netlogic/mips-extns.h
new file mode 100644
index 00000000000..8c53d0ba4bf
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/mips-extns.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_MIPS_EXTS_H
+#define _ASM_NLM_MIPS_EXTS_H
+
+/*
+ * XLR and XLP interrupt request and interrupt mask registers
+ */
+#define read_c0_eirr()		__read_64bit_c0_register($9, 6)
+#define read_c0_eimr()		__read_64bit_c0_register($9, 7)
+#define write_c0_eirr(val)	__write_64bit_c0_register($9, 6, val)
+
+/*
+ * Writing EIMR in 32 bit is a special case, the lower 8 bit of the
+ * EIMR is shadowed in the status register, so we cannot save and
+ * restore status register for split read.
+ */
+#define write_c0_eimr(val)						\
+do {									\
+	if (sizeof(unsigned long) == 4)	{				\
+		unsigned long __flags;					\
+									\
+		local_irq_save(__flags);				\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dsll\t%L0, %L0, 32\n\t"			\
+			"dsrl\t%L0, %L0, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
+			"or\t%L0, %L0, %M0\n\t"				\
+			"dmtc0\t%L0, $9, 7\n\t"				\
+			".set\tmips0"					\
+			: : "r" (val));					\
+		__flags = (__flags & 0xffff00ff) | (((val) & 0xff) << 8);\
+		local_irq_restore(__flags);				\
+	} else								\
+		__write_64bit_c0_register($9, 7, (val));		\
+} while (0)
+
+static inline int hard_smp_processor_id(void)
+{
+	return __read_32bit_c0_register($15, 1) & 0x3ff;
+}
+
+#endif /*_ASM_NLM_MIPS_EXTS_H */
diff --git a/arch/mips/include/asm/netlogic/psb-bootinfo.h b/arch/mips/include/asm/netlogic/psb-bootinfo.h
new file mode 100644
index 00000000000..6878307f0ee
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/psb-bootinfo.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NETLOGIC_BOOTINFO_H
+#define _ASM_NETLOGIC_BOOTINFO_H
+
+struct psb_info {
+	uint64_t boot_level;
+	uint64_t io_base;
+	uint64_t output_device;
+	uint64_t uart_print;
+	uint64_t led_output;
+	uint64_t init;
+	uint64_t exit;
+	uint64_t warm_reset;
+	uint64_t wakeup;
+	uint64_t online_cpu_map;
+	uint64_t master_reentry_sp;
+	uint64_t master_reentry_gp;
+	uint64_t master_reentry_fn;
+	uint64_t slave_reentry_fn;
+	uint64_t magic_dword;
+	uint64_t uart_putchar;
+	uint64_t size;
+	uint64_t uart_getchar;
+	uint64_t nmi_handler;
+	uint64_t psb_version;
+	uint64_t mac_addr;
+	uint64_t cpu_frequency;
+	uint64_t board_version;
+	uint64_t malloc;
+	uint64_t free;
+	uint64_t global_shmem_addr;
+	uint64_t global_shmem_size;
+	uint64_t psb_os_cpu_map;
+	uint64_t userapp_cpu_map;
+	uint64_t wakeup_os;
+	uint64_t psb_mem_map;
+	uint64_t board_major_version;
+	uint64_t board_minor_version;
+	uint64_t board_manf_revision;
+	uint64_t board_serial_number;
+	uint64_t psb_physaddr_map;
+	uint64_t xlr_loaderip_config;
+	uint64_t bldr_envp;
+	uint64_t avail_mem_map;
+};
+
+enum {
+	NETLOGIC_IO_SPACE = 0x10,
+	PCIX_IO_SPACE,
+	PCIX_CFG_SPACE,
+	PCIX_MEMORY_SPACE,
+	HT_IO_SPACE,
+	HT_CFG_SPACE,
+	HT_MEMORY_SPACE,
+	SRAM_SPACE,
+	FLASH_CONTROLLER_SPACE
+};
+
+#define NLM_MAX_ARGS	64
+#define NLM_MAX_ENVS	32
+
+/* This is what netlboot passes and linux boot_mem_map is subtly different */
+#define NLM_BOOT_MEM_MAP_MAX	32
+struct nlm_boot_mem_map {
+	int nr_map;
+	struct nlm_boot_mem_map_entry {
+		uint64_t addr;		/* start of memory segment */
+		uint64_t size;		/* size of memory segment */
+		uint32_t type;		/* type of memory segment */
+	} map[NLM_BOOT_MEM_MAP_MAX];
+};
+
+/* Pointer to saved boot loader info */
+extern struct psb_info nlm_prom_info;
+
+#endif
diff --git a/arch/mips/include/asm/netlogic/xlr/gpio.h b/arch/mips/include/asm/netlogic/xlr/gpio.h
new file mode 100644
index 00000000000..51f6ad4aeb1
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/gpio.h
@@ -0,0 +1,73 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_GPIO_H
+#define _ASM_NLM_GPIO_H
+
+#define NETLOGIC_GPIO_INT_EN_REG		0
+#define NETLOGIC_GPIO_INPUT_INVERSION_REG	1
+#define NETLOGIC_GPIO_IO_DIR_REG		2
+#define NETLOGIC_GPIO_IO_DATA_WR_REG		3
+#define NETLOGIC_GPIO_IO_DATA_RD_REG		4
+
+#define NETLOGIC_GPIO_SWRESET_REG		8
+#define NETLOGIC_GPIO_DRAM1_CNTRL_REG		9
+#define NETLOGIC_GPIO_DRAM1_RATIO_REG		10
+#define NETLOGIC_GPIO_DRAM1_RESET_REG		11
+#define NETLOGIC_GPIO_DRAM1_STATUS_REG		12
+#define NETLOGIC_GPIO_DRAM2_CNTRL_REG		13
+#define NETLOGIC_GPIO_DRAM2_RATIO_REG		14
+#define NETLOGIC_GPIO_DRAM2_RESET_REG		15
+#define NETLOGIC_GPIO_DRAM2_STATUS_REG		16
+
+#define NETLOGIC_GPIO_PWRON_RESET_CFG_REG	21
+#define NETLOGIC_GPIO_BIST_ALL_GO_STATUS_REG	24
+#define NETLOGIC_GPIO_BIST_CPU_GO_STATUS_REG	25
+#define NETLOGIC_GPIO_BIST_DEV_GO_STATUS_REG	26
+
+#define NETLOGIC_GPIO_FUSE_BANK_REG		35
+#define NETLOGIC_GPIO_CPU_RESET_REG		40
+#define NETLOGIC_GPIO_RNG_REG			43
+
+#define NETLOGIC_PWRON_RESET_PCMCIA_BOOT	17
+#define NETLOGIC_GPIO_LED_BITMAP	0x1700000
+#define NETLOGIC_GPIO_LED_0_SHIFT		20
+#define NETLOGIC_GPIO_LED_1_SHIFT		24
+
+#define NETLOGIC_GPIO_LED_OUTPUT_CODE_RESET	0x01
+#define NETLOGIC_GPIO_LED_OUTPUT_CODE_HARD_RESET 0x02
+#define NETLOGIC_GPIO_LED_OUTPUT_CODE_SOFT_RESET 0x03
+#define NETLOGIC_GPIO_LED_OUTPUT_CODE_MAIN	0x04
+
+#endif
diff --git a/arch/mips/include/asm/netlogic/xlr/iomap.h b/arch/mips/include/asm/netlogic/xlr/iomap.h
new file mode 100644
index 00000000000..2e3a4dd5304
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/iomap.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_IOMAP_H
+#define _ASM_NLM_IOMAP_H
+
+#define DEFAULT_NETLOGIC_IO_BASE           CKSEG1ADDR(0x1ef00000)
+#define NETLOGIC_IO_DDR2_CHN0_OFFSET       0x01000
+#define NETLOGIC_IO_DDR2_CHN1_OFFSET       0x02000
+#define NETLOGIC_IO_DDR2_CHN2_OFFSET       0x03000
+#define NETLOGIC_IO_DDR2_CHN3_OFFSET       0x04000
+#define NETLOGIC_IO_PIC_OFFSET             0x08000
+#define NETLOGIC_IO_UART_0_OFFSET          0x14000
+#define NETLOGIC_IO_UART_1_OFFSET          0x15100
+
+#define NETLOGIC_IO_SIZE                   0x1000
+
+#define NETLOGIC_IO_BRIDGE_OFFSET          0x00000
+
+#define NETLOGIC_IO_RLD2_CHN0_OFFSET       0x05000
+#define NETLOGIC_IO_RLD2_CHN1_OFFSET       0x06000
+
+#define NETLOGIC_IO_SRAM_OFFSET            0x07000
+
+#define NETLOGIC_IO_PCIX_OFFSET            0x09000
+#define NETLOGIC_IO_HT_OFFSET              0x0A000
+
+#define NETLOGIC_IO_SECURITY_OFFSET        0x0B000
+
+#define NETLOGIC_IO_GMAC_0_OFFSET          0x0C000
+#define NETLOGIC_IO_GMAC_1_OFFSET          0x0D000
+#define NETLOGIC_IO_GMAC_2_OFFSET          0x0E000
+#define NETLOGIC_IO_GMAC_3_OFFSET          0x0F000
+
+/* XLS devices */
+#define NETLOGIC_IO_GMAC_4_OFFSET          0x20000
+#define NETLOGIC_IO_GMAC_5_OFFSET          0x21000
+#define NETLOGIC_IO_GMAC_6_OFFSET          0x22000
+#define NETLOGIC_IO_GMAC_7_OFFSET          0x23000
+
+#define NETLOGIC_IO_PCIE_0_OFFSET          0x1E000
+#define NETLOGIC_IO_PCIE_1_OFFSET          0x1F000
+#define NETLOGIC_IO_SRIO_0_OFFSET          0x1E000
+#define NETLOGIC_IO_SRIO_1_OFFSET          0x1F000
+
+#define NETLOGIC_IO_USB_0_OFFSET           0x24000
+#define NETLOGIC_IO_USB_1_OFFSET           0x25000
+
+#define NETLOGIC_IO_COMP_OFFSET            0x1D000
+/* end XLS devices */
+
+/* XLR devices */
+#define NETLOGIC_IO_SPI4_0_OFFSET          0x10000
+#define NETLOGIC_IO_XGMAC_0_OFFSET         0x11000
+#define NETLOGIC_IO_SPI4_1_OFFSET          0x12000
+#define NETLOGIC_IO_XGMAC_1_OFFSET         0x13000
+/* end XLR devices */
+
+#define NETLOGIC_IO_I2C_0_OFFSET           0x16000
+#define NETLOGIC_IO_I2C_1_OFFSET           0x17000
+
+#define NETLOGIC_IO_GPIO_OFFSET            0x18000
+#define NETLOGIC_IO_FLASH_OFFSET           0x19000
+#define NETLOGIC_IO_TB_OFFSET              0x1C000
+
+#define NETLOGIC_CPLD_OFFSET               KSEG1ADDR(0x1d840000)
+
+/*
+ * Base Address (Virtual) of the PCI Config address space
+ * For now, choose 256M phys in kseg1 = 0xA0000000 + (1<<28)
+ * Config space spans 256 (num of buses) * 256 (num functions) * 256 bytes
+ * ie 1<<24 = 16M
+ */
+#define DEFAULT_PCI_CONFIG_BASE         0x18000000
+#define DEFAULT_HT_TYPE0_CFG_BASE       0x16000000
+#define DEFAULT_HT_TYPE1_CFG_BASE       0x17000000
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+typedef volatile __u32 nlm_reg_t;
+extern unsigned long netlogic_io_base;
+
+/* FIXME read once in write_reg */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define netlogic_read_reg(base, offset)		((base)[(offset)])
+#define netlogic_write_reg(base, offset, value)	((base)[(offset)] = (value))
+#else
+#define netlogic_read_reg(base, offset)		(be32_to_cpu((base)[(offset)]))
+#define netlogic_write_reg(base, offset, value) \
+				((base)[(offset)] = cpu_to_be32((value)))
+#endif
+
+#define netlogic_read_reg_le32(base, offset) (le32_to_cpu((base)[(offset)]))
+#define netlogic_write_reg_le32(base, offset, value) \
+				((base)[(offset)] = cpu_to_le32((value)))
+#define netlogic_io_mmio(offset) ((nlm_reg_t *)(netlogic_io_base+(offset)))
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/mips/include/asm/netlogic/xlr/pic.h b/arch/mips/include/asm/netlogic/xlr/pic.h
new file mode 100644
index 00000000000..5cceb746f08
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/pic.h
@@ -0,0 +1,231 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_XLR_PIC_H
+#define _ASM_NLM_XLR_PIC_H
+
+#define PIC_CLKS_PER_SEC		66666666ULL
+/* PIC hardware interrupt numbers */
+#define PIC_IRT_WD_INDEX		0
+#define PIC_IRT_TIMER_0_INDEX		1
+#define PIC_IRT_TIMER_1_INDEX		2
+#define PIC_IRT_TIMER_2_INDEX		3
+#define PIC_IRT_TIMER_3_INDEX		4
+#define PIC_IRT_TIMER_4_INDEX		5
+#define PIC_IRT_TIMER_5_INDEX		6
+#define PIC_IRT_TIMER_6_INDEX		7
+#define PIC_IRT_TIMER_7_INDEX		8
+#define PIC_IRT_CLOCK_INDEX		PIC_IRT_TIMER_7_INDEX
+#define PIC_IRT_UART_0_INDEX		9
+#define PIC_IRT_UART_1_INDEX		10
+#define PIC_IRT_I2C_0_INDEX		11
+#define PIC_IRT_I2C_1_INDEX		12
+#define PIC_IRT_PCMCIA_INDEX		13
+#define PIC_IRT_GPIO_INDEX		14
+#define PIC_IRT_HYPER_INDEX		15
+#define PIC_IRT_PCIX_INDEX		16
+/* XLS */
+#define PIC_IRT_CDE_INDEX		15
+#define PIC_IRT_BRIDGE_TB_XLS_INDEX	16
+/* XLS */
+#define PIC_IRT_GMAC0_INDEX		17
+#define PIC_IRT_GMAC1_INDEX		18
+#define PIC_IRT_GMAC2_INDEX		19
+#define PIC_IRT_GMAC3_INDEX		20
+#define PIC_IRT_XGS0_INDEX		21
+#define PIC_IRT_XGS1_INDEX		22
+#define PIC_IRT_HYPER_FATAL_INDEX	23
+#define PIC_IRT_PCIX_FATAL_INDEX	24
+#define PIC_IRT_BRIDGE_AERR_INDEX	25
+#define PIC_IRT_BRIDGE_BERR_INDEX	26
+#define PIC_IRT_BRIDGE_TB_XLR_INDEX	27
+#define PIC_IRT_BRIDGE_AERR_NMI_INDEX	28
+/* XLS */
+#define PIC_IRT_GMAC4_INDEX		21
+#define PIC_IRT_GMAC5_INDEX		22
+#define PIC_IRT_GMAC6_INDEX		23
+#define PIC_IRT_GMAC7_INDEX		24
+#define PIC_IRT_BRIDGE_ERR_INDEX	25
+#define PIC_IRT_PCIE_LINK0_INDEX	26
+#define PIC_IRT_PCIE_LINK1_INDEX	27
+#define PIC_IRT_PCIE_LINK2_INDEX	23
+#define PIC_IRT_PCIE_LINK3_INDEX	24
+#define PIC_IRT_PCIE_XLSB0_LINK2_INDEX	28
+#define PIC_IRT_PCIE_XLSB0_LINK3_INDEX	29
+#define PIC_IRT_SRIO_LINK0_INDEX	26
+#define PIC_IRT_SRIO_LINK1_INDEX	27
+#define PIC_IRT_SRIO_LINK2_INDEX	28
+#define PIC_IRT_SRIO_LINK3_INDEX	29
+#define PIC_IRT_PCIE_INT_INDEX		28
+#define PIC_IRT_PCIE_FATAL_INDEX	29
+#define PIC_IRT_GPIO_B_INDEX		30
+#define PIC_IRT_USB_INDEX		31
+/* XLS */
+#define PIC_NUM_IRTS			32
+
+
+#define PIC_CLOCK_TIMER			7
+
+/* PIC Registers */
+#define PIC_CTRL			0x00
+#define PIC_IPI				0x04
+#define PIC_INT_ACK			0x06
+
+#define WD_MAX_VAL_0			0x08
+#define WD_MAX_VAL_1			0x09
+#define WD_MASK_0			0x0a
+#define WD_MASK_1			0x0b
+#define WD_HEARBEAT_0			0x0c
+#define WD_HEARBEAT_1			0x0d
+
+#define PIC_IRT_0_BASE			0x40
+#define PIC_IRT_1_BASE			0x80
+#define PIC_TIMER_MAXVAL_0_BASE		0x100
+#define PIC_TIMER_MAXVAL_1_BASE		0x110
+#define PIC_TIMER_COUNT_0_BASE		0x120
+#define PIC_TIMER_COUNT_1_BASE		0x130
+
+#define PIC_IRT_0(picintr)      (PIC_IRT_0_BASE + (picintr))
+#define PIC_IRT_1(picintr)	(PIC_IRT_1_BASE + (picintr))
+
+#define PIC_TIMER_MAXVAL_0(i)	(PIC_TIMER_MAXVAL_0_BASE + (i))
+#define PIC_TIMER_MAXVAL_1(i)	(PIC_TIMER_MAXVAL_1_BASE + (i))
+#define PIC_TIMER_COUNT_0(i)	(PIC_TIMER_COUNT_0_BASE + (i))
+#define PIC_TIMER_COUNT_1(i)	(PIC_TIMER_COUNT_0_BASE + (i))
+
+/*
+ * Mapping between hardware interrupt numbers and IRQs on CPU
+ * we use a simple scheme to map PIC interrupts 0-31 to IRQs
+ * 8-39. This leaves the IRQ 0-7 for cpu interrupts like
+ * count/compare and FMN
+ */
+#define PIC_IRQ_BASE            8
+#define PIC_INTR_TO_IRQ(i)      (PIC_IRQ_BASE + (i))
+#define PIC_IRQ_TO_INTR(i)      ((i) - PIC_IRQ_BASE)
+
+#define PIC_IRT_FIRST_IRQ	PIC_IRQ_BASE
+#define PIC_WD_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_WD_INDEX)
+#define PIC_TIMER_0_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_0_INDEX)
+#define PIC_TIMER_1_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_1_INDEX)
+#define PIC_TIMER_2_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_2_INDEX)
+#define PIC_TIMER_3_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_3_INDEX)
+#define PIC_TIMER_4_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_4_INDEX)
+#define PIC_TIMER_5_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_5_INDEX)
+#define PIC_TIMER_6_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_6_INDEX)
+#define PIC_TIMER_7_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_TIMER_7_INDEX)
+#define PIC_CLOCK_IRQ		(PIC_TIMER_7_IRQ)
+#define PIC_UART_0_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_UART_0_INDEX)
+#define PIC_UART_1_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_UART_1_INDEX)
+#define PIC_I2C_0_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_I2C_0_INDEX)
+#define PIC_I2C_1_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_I2C_1_INDEX)
+#define PIC_PCMCIA_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_PCMCIA_INDEX)
+#define PIC_GPIO_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GPIO_INDEX)
+#define PIC_HYPER_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_HYPER_INDEX)
+#define PIC_PCIX_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_PCIX_INDEX)
+/* XLS */
+#define PIC_CDE_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_CDE_INDEX)
+#define PIC_BRIDGE_TB_XLS_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_TB_XLS_INDEX)
+/* end XLS */
+#define PIC_GMAC_0_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC0_INDEX)
+#define PIC_GMAC_1_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC1_INDEX)
+#define PIC_GMAC_2_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC2_INDEX)
+#define PIC_GMAC_3_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC3_INDEX)
+#define PIC_XGS_0_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_XGS0_INDEX)
+#define PIC_XGS_1_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_XGS1_INDEX)
+#define PIC_HYPER_FATAL_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_HYPER_FATAL_INDEX)
+#define PIC_PCIX_FATAL_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIX_FATAL_INDEX)
+#define PIC_BRIDGE_AERR_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_AERR_INDEX)
+#define PIC_BRIDGE_BERR_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_BERR_INDEX)
+#define PIC_BRIDGE_TB_XLR_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_TB_XLR_INDEX)
+#define PIC_BRIDGE_AERR_NMI_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_AERR_NMI_INDEX)
+/* XLS defines */
+#define PIC_GMAC_4_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC4_INDEX)
+#define PIC_GMAC_5_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC5_INDEX)
+#define PIC_GMAC_6_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC6_INDEX)
+#define PIC_GMAC_7_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GMAC7_INDEX)
+#define PIC_BRIDGE_ERR_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_BRIDGE_ERR_INDEX)
+#define PIC_PCIE_LINK0_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_LINK0_INDEX)
+#define PIC_PCIE_LINK1_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_LINK1_INDEX)
+#define PIC_PCIE_LINK2_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_LINK2_INDEX)
+#define PIC_PCIE_LINK3_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_LINK3_INDEX)
+#define PIC_PCIE_XLSB0_LINK2_IRQ PIC_INTR_TO_IRQ(PIC_IRT_PCIE_XLSB0_LINK2_INDEX)
+#define PIC_PCIE_XLSB0_LINK3_IRQ PIC_INTR_TO_IRQ(PIC_IRT_PCIE_XLSB0_LINK3_INDEX)
+#define PIC_SRIO_LINK0_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_SRIO_LINK0_INDEX)
+#define PIC_SRIO_LINK1_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_SRIO_LINK1_INDEX)
+#define PIC_SRIO_LINK2_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_SRIO_LINK2_INDEX)
+#define PIC_SRIO_LINK3_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_SRIO_LINK3_INDEX)
+#define PIC_PCIE_INT_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_INT__INDEX)
+#define PIC_PCIE_FATAL_IRQ	PIC_INTR_TO_IRQ(PIC_IRT_PCIE_FATAL_INDEX)
+#define PIC_GPIO_B_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_GPIO_B_INDEX)
+#define PIC_USB_IRQ		PIC_INTR_TO_IRQ(PIC_IRT_USB_INDEX)
+#define PIC_IRT_LAST_IRQ	PIC_USB_IRQ
+/* end XLS */
+
+#ifndef __ASSEMBLY__
+static inline void pic_send_ipi(u32 ipi)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+
+	netlogic_write_reg(mmio, PIC_IPI, ipi);
+}
+
+static inline u32 pic_read_control(void)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+
+	return netlogic_read_reg(mmio, PIC_CTRL);
+}
+
+static inline void pic_write_control(u32 control)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+
+	netlogic_write_reg(mmio, PIC_CTRL, control);
+}
+
+static inline void pic_update_control(u32 control)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+
+	netlogic_write_reg(mmio, PIC_CTRL,
+		(control | netlogic_read_reg(mmio, PIC_CTRL)));
+}
+
+#define PIC_IRQ_IS_EDGE_TRIGGERED(irq)	(((irq) >= PIC_TIMER_0_IRQ) && \
+					((irq) <= PIC_TIMER_7_IRQ))
+#define PIC_IRQ_IS_IRT(irq)		(((irq) >= PIC_IRT_FIRST_IRQ) && \
+					((irq) <= PIC_IRT_LAST_IRQ))
+#endif
+
+#endif /* _ASM_NLM_XLR_PIC_H */
diff --git a/arch/mips/include/asm/netlogic/xlr/xlr.h b/arch/mips/include/asm/netlogic/xlr/xlr.h
new file mode 100644
index 00000000000..3e6372692a0
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/xlr.h
@@ -0,0 +1,75 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _ASM_NLM_XLR_H
+#define _ASM_NLM_XLR_H
+
+/* Platform UART functions */
+struct uart_port;
+unsigned int nlm_xlr_uart_in(struct uart_port *, int);
+void nlm_xlr_uart_out(struct uart_port *, int, int);
+
+/* SMP support functions */
+struct irq_desc;
+void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc);
+void nlm_smp_resched_ipi_handler(unsigned int irq, struct irq_desc *desc);
+int nlm_wakeup_secondary_cpus(u32 wakeup_mask);
+void nlm_smp_irq_init(void);
+void nlm_boot_smp_nmi(void);
+void prom_pre_boot_secondary_cpus(void);
+
+extern struct plat_smp_ops nlm_smp_ops;
+extern unsigned long nlm_common_ebase;
+
+/* XLS B silicon "Rook" */
+static inline unsigned int nlm_chip_is_xls_b(void)
+{
+	uint32_t prid = read_c0_prid();
+
+	return ((prid & 0xf000) == 0x4000);
+}
+
+/*
+ *  XLR chip types
+ */
+ /* The XLS product line has chip versions 0x[48c]? */
+static inline unsigned int nlm_chip_is_xls(void)
+{
+	uint32_t prid = read_c0_prid();
+
+	return ((prid & 0xf000) == 0x8000 || (prid & 0xf000) == 0x4000 ||
+		(prid & 0xf000) == 0xc000);
+}
+
+#endif /* _ASM_NLM_XLR_H */
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 9f1b8dba2c8..de39b1f343e 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -141,7 +141,8 @@ extern int ptrace_set_watch_regs(struct task_struct *child,
 #define instruction_pointer(regs) ((regs)->cp0_epc)
 #define profile_pc(regs) instruction_pointer(regs)
 
-extern asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit);
+extern asmlinkage void syscall_trace_enter(struct pt_regs *regs);
+extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
 extern NORET_TYPE void die(const char *, struct pt_regs *) ATTRIB_NORET;
 
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index d71160de4d1..97f8bf6639e 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -149,6 +149,9 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define _TIF_FPUBOUND		(1<<TIF_FPUBOUND)
 #define _TIF_LOAD_WATCH		(1<<TIF_LOAD_WATCH)
 
+/* work to do in syscall_trace_leave() */
+#define _TIF_WORK_SYSCALL_EXIT	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT)
+
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK		(0x0000ffef &				\
 					~(_TIF_SECCOMP | _TIF_SYSCALL_AUDIT))
diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
index c7f1bfef157..bc14447e69b 100644
--- a/arch/mips/include/asm/time.h
+++ b/arch/mips/include/asm/time.h
@@ -84,12 +84,6 @@ static inline int init_mips_clocksource(void)
 #endif
 }
 
-static inline void clocksource_set_clock(struct clocksource *cs,
-					 unsigned int clock)
-{
-	clocksource_calc_mult_shift(cs, clock, 4);
-}
-
 static inline void clockevent_set_clock(struct clock_event_device *cd,
 					unsigned int clock)
 {
diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c
index 6a9e14dab91..d97cfbf882f 100644
--- a/arch/mips/jz4740/setup.c
+++ b/arch/mips/jz4740/setup.c
@@ -1,5 +1,6 @@
 /*
  *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
+ *  Copyright (C) 2011, Maarten ter Huurne <maarten@treewalker.org>
  *  JZ4740 setup code
  *
  *  This program is free software; you can redistribute it and/or modify it
@@ -14,13 +15,44 @@
  */
 
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 
+#include <asm/bootinfo.h>
+
+#include <asm/mach-jz4740/base.h>
+
 #include "reset.h"
 
+
+#define JZ4740_EMC_SDRAM_CTRL 0x80
+
+
+static void __init jz4740_detect_mem(void)
+{
+	void __iomem *jz_emc_base;
+	u32 ctrl, bus, bank, rows, cols;
+	phys_t size;
+
+	jz_emc_base = ioremap(JZ4740_EMC_BASE_ADDR, 0x100);
+	ctrl = readl(jz_emc_base + JZ4740_EMC_SDRAM_CTRL);
+	bus = 2 - ((ctrl >> 31) & 1);
+	bank = 1 + ((ctrl >> 19) & 1);
+	cols = 8 + ((ctrl >> 26) & 7);
+	rows = 11 + ((ctrl >> 20) & 3);
+	printk(KERN_DEBUG
+		"SDRAM preconfigured: bus:%u bank:%u rows:%u cols:%u\n",
+		bus, bank, rows, cols);
+	iounmap(jz_emc_base);
+
+	size = 1 << (bus + bank + cols + rows);
+	add_memory_region(0, size, BOOT_MEM_RAM);
+}
+
 void __init plat_mem_setup(void)
 {
 	jz4740_reset_init();
+	jz4740_detect_mem();
 }
 
 const char *get_system_type(void)
diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c
index eaa853a54af..f83c2dd07a2 100644
--- a/arch/mips/jz4740/time.c
+++ b/arch/mips/jz4740/time.c
@@ -121,8 +121,7 @@ void __init plat_time_init(void)
 
 	clockevents_register_device(&jz4740_clockevent);
 
-	clocksource_set_clock(&jz4740_clocksource, clk_rate);
-	ret = clocksource_register(&jz4740_clocksource);
+	ret = clocksource_register_hz(&jz4740_clocksource, clk_rate);
 
 	if (ret)
 		printk(KERN_ERR "Failed to register clocksource: %d\n", ret);
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index cedee2bcbd1..83bba332bbf 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_CPU_TX39XX)	+= r2300_fpu.o r2300_switch.o
 obj-$(CONFIG_CPU_TX49XX)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_VR41XX)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= octeon_switch.o
+obj-$(CONFIG_CPU_XLR)		+= r4k_fpu.o r4k_switch.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP_UP)		+= smp-up.o
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index 0b7377361e2..f0ab92a1b05 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -51,8 +51,7 @@ void __init txx9_clocksource_init(unsigned long baseaddr,
 {
 	struct txx9_tmr_reg __iomem *tmrptr;
 
-	clocksource_set_clock(&txx9_clocksource.cs, TIMER_CLK(imbusclk));
-	clocksource_register(&txx9_clocksource.cs);
+	clocksource_register_hz(&txx9_clocksource.cs, TIMER_CLK(imbusclk));
 
 	tmrptr = ioremap(baseaddr, sizeof(struct txx9_tmr_reg));
 	__raw_writel(TCR_BASE, &tmrptr->tcr);
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index f65d4c8c65a..bb133d10b14 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -291,6 +291,12 @@ static inline int cpu_has_confreg(void)
 #endif
 }
 
+static inline void set_elf_platform(int cpu, const char *plat)
+{
+	if (cpu == 0)
+		__elf_platform = plat;
+}
+
 /*
  * Get the FPU Implementation/Revision.
  */
@@ -614,6 +620,16 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 	case PRID_IMP_LOONGSON2:
 		c->cputype = CPU_LOONGSON2;
 		__cpu_name[cpu] = "ICT Loongson-2";
+
+		switch (c->processor_id & PRID_REV_MASK) {
+		case PRID_REV_LOONGSON2E:
+			set_elf_platform(cpu, "loongson2e");
+			break;
+		case PRID_REV_LOONGSON2F:
+			set_elf_platform(cpu, "loongson2f");
+			break;
+		}
+
 		c->isa_level = MIPS_CPU_ISA_III;
 		c->options = R4K_OPTS |
 			     MIPS_CPU_FPU | MIPS_CPU_LLSC |
@@ -911,12 +927,14 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 	case PRID_IMP_BMIPS32_REV8:
 		c->cputype = CPU_BMIPS32;
 		__cpu_name[cpu] = "Broadcom BMIPS32";
+		set_elf_platform(cpu, "bmips32");
 		break;
 	case PRID_IMP_BMIPS3300:
 	case PRID_IMP_BMIPS3300_ALT:
 	case PRID_IMP_BMIPS3300_BUG:
 		c->cputype = CPU_BMIPS3300;
 		__cpu_name[cpu] = "Broadcom BMIPS3300";
+		set_elf_platform(cpu, "bmips3300");
 		break;
 	case PRID_IMP_BMIPS43XX: {
 		int rev = c->processor_id & 0xff;
@@ -925,15 +943,18 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 				rev <= PRID_REV_BMIPS4380_HI) {
 			c->cputype = CPU_BMIPS4380;
 			__cpu_name[cpu] = "Broadcom BMIPS4380";
+			set_elf_platform(cpu, "bmips4380");
 		} else {
 			c->cputype = CPU_BMIPS4350;
 			__cpu_name[cpu] = "Broadcom BMIPS4350";
+			set_elf_platform(cpu, "bmips4350");
 		}
 		break;
 	}
 	case PRID_IMP_BMIPS5000:
 		c->cputype = CPU_BMIPS5000;
 		__cpu_name[cpu] = "Broadcom BMIPS5000";
+		set_elf_platform(cpu, "bmips5000");
 		c->options |= MIPS_CPU_ULRI;
 		break;
 	}
@@ -956,14 +977,12 @@ static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_CAVIUM_OCTEON_PLUS;
 		__cpu_name[cpu] = "Cavium Octeon+";
 platform:
-		if (cpu == 0)
-			__elf_platform = "octeon";
+		set_elf_platform(cpu, "octeon");
 		break;
 	case PRID_IMP_CAVIUM_CN63XX:
 		c->cputype = CPU_CAVIUM_OCTEON2;
 		__cpu_name[cpu] = "Cavium Octeon II";
-		if (cpu == 0)
-			__elf_platform = "octeon2";
+		set_elf_platform(cpu, "octeon2");
 		break;
 	default:
 		printk(KERN_INFO "Unknown Octeon chip!\n");
@@ -988,6 +1007,59 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	}
 }
 
+static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
+{
+	decode_configs(c);
+
+	c->options = (MIPS_CPU_TLB       |
+			MIPS_CPU_4KEX    |
+			MIPS_CPU_COUNTER |
+			MIPS_CPU_DIVEC   |
+			MIPS_CPU_WATCH   |
+			MIPS_CPU_EJTAG   |
+			MIPS_CPU_LLSC);
+
+	switch (c->processor_id & 0xff00) {
+	case PRID_IMP_NETLOGIC_XLR732:
+	case PRID_IMP_NETLOGIC_XLR716:
+	case PRID_IMP_NETLOGIC_XLR532:
+	case PRID_IMP_NETLOGIC_XLR308:
+	case PRID_IMP_NETLOGIC_XLR532C:
+	case PRID_IMP_NETLOGIC_XLR516C:
+	case PRID_IMP_NETLOGIC_XLR508C:
+	case PRID_IMP_NETLOGIC_XLR308C:
+		c->cputype = CPU_XLR;
+		__cpu_name[cpu] = "Netlogic XLR";
+		break;
+
+	case PRID_IMP_NETLOGIC_XLS608:
+	case PRID_IMP_NETLOGIC_XLS408:
+	case PRID_IMP_NETLOGIC_XLS404:
+	case PRID_IMP_NETLOGIC_XLS208:
+	case PRID_IMP_NETLOGIC_XLS204:
+	case PRID_IMP_NETLOGIC_XLS108:
+	case PRID_IMP_NETLOGIC_XLS104:
+	case PRID_IMP_NETLOGIC_XLS616B:
+	case PRID_IMP_NETLOGIC_XLS608B:
+	case PRID_IMP_NETLOGIC_XLS416B:
+	case PRID_IMP_NETLOGIC_XLS412B:
+	case PRID_IMP_NETLOGIC_XLS408B:
+	case PRID_IMP_NETLOGIC_XLS404B:
+		c->cputype = CPU_XLR;
+		__cpu_name[cpu] = "Netlogic XLS";
+		break;
+
+	default:
+		printk(KERN_INFO "Unknown Netlogic chip id [%02x]!\n",
+		       c->processor_id);
+		c->cputype = CPU_XLR;
+		break;
+	}
+
+	c->isa_level = MIPS_CPU_ISA_M64R1;
+	c->tlbsize = ((read_c0_config1() >> 25) & 0x3f) + 1;
+}
+
 #ifdef CONFIG_64BIT
 /* For use by uaccess.h */
 u64 __ua_limit;
@@ -1035,6 +1107,9 @@ __cpuinit void cpu_probe(void)
 	case PRID_COMP_INGENIC:
 		cpu_probe_ingenic(c, cpu);
 		break;
+	case PRID_COMP_NETLOGIC:
+		cpu_probe_netlogic(c, cpu);
+		break;
 	}
 
 	BUG_ON(!__cpu_name[cpu]);
diff --git a/arch/mips/kernel/csrc-bcm1480.c b/arch/mips/kernel/csrc-bcm1480.c
index 51489f8a825..f96f99c794a 100644
--- a/arch/mips/kernel/csrc-bcm1480.c
+++ b/arch/mips/kernel/csrc-bcm1480.c
@@ -49,6 +49,5 @@ void __init sb1480_clocksource_init(void)
 
 	plldiv = G_BCM1480_SYS_PLL_DIV(__raw_readq(IOADDR(A_SCD_SYSTEM_CFG)));
 	zbbus = ((plldiv >> 1) * 50000000) + ((plldiv & 1) * 25000000);
-	clocksource_set_clock(cs, zbbus);
-	clocksource_register(cs);
+	clocksource_register_hz(cs, zbbus);
 }
diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c
index 23da108506b..46bd7fa98d6 100644
--- a/arch/mips/kernel/csrc-ioasic.c
+++ b/arch/mips/kernel/csrc-ioasic.c
@@ -59,7 +59,5 @@ void __init dec_ioasic_clocksource_init(void)
 	printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq);
 
 	clocksource_dec.rating = 200 + freq / 10000000;
-	clocksource_set_clock(&clocksource_dec, freq);
-
-	clocksource_register(&clocksource_dec);
+	clocksource_register_hz(&clocksource_dec, freq);
 }
diff --git a/arch/mips/kernel/csrc-powertv.c b/arch/mips/kernel/csrc-powertv.c
index a27c16c8690..2e7c5232da8 100644
--- a/arch/mips/kernel/csrc-powertv.c
+++ b/arch/mips/kernel/csrc-powertv.c
@@ -78,9 +78,7 @@ static void __init powertv_c0_hpt_clocksource_init(void)
 
 	clocksource_mips.rating = 200 + mips_hpt_frequency / 10000000;
 
-	clocksource_set_clock(&clocksource_mips, mips_hpt_frequency);
-
-	clocksource_register(&clocksource_mips);
+	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 }
 
 /**
@@ -130,43 +128,16 @@ static struct clocksource clocksource_tim_c = {
 /**
  * powertv_tim_c_clocksource_init - set up a clock source for the TIM_C clock
  *
- * The hard part here is coming up with a constant k and shift s such that
- * the 48-bit TIM_C value multiplied by k doesn't overflow and that value,
- * when shifted right by s, yields the corresponding number of nanoseconds.
  * We know that TIM_C counts at 27 MHz/8, so each cycle corresponds to
- * 1 / (27,000,000/8) seconds. Multiply that by a billion and you get the
- * number of nanoseconds. Since the TIM_C value has 48 bits and the math is
- * done in 64 bits, avoiding an overflow means that k must be less than
- * 64 - 48 = 16 bits.
+ * 1 / (27,000,000/8) seconds.
  */
 static void __init powertv_tim_c_clocksource_init(void)
 {
-	int			prescale;
-	unsigned long		dividend;
-	unsigned long		k;
-	int			s;
-	const int		max_k_bits = (64 - 48) - 1;
-	const unsigned long	billion = 1000000000;
 	const unsigned long	counts_per_second = 27000000 / 8;
 
-	prescale = BITS_PER_LONG - ilog2(billion) - 1;
-	dividend = billion << prescale;
-	k = dividend / counts_per_second;
-	s = ilog2(k) - max_k_bits;
-
-	if (s < 0)
-		s = prescale;
-
-	else {
-		k >>= s;
-		s += prescale;
-	}
-
-	clocksource_tim_c.mult = k;
-	clocksource_tim_c.shift = s;
 	clocksource_tim_c.rating = 200;
 
-	clocksource_register(&clocksource_tim_c);
+	clocksource_register_hz(&clocksource_tim_c, counts_per_second);
 	tim_c = (struct tim_c *) asic_reg_addr(tim_ch);
 }
 
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index e95a3cd48ee..decd1fa38d5 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -30,9 +30,7 @@ int __init init_r4k_clocksource(void)
 	/* Calculate a somewhat reasonable rating value */
 	clocksource_mips.rating = 200 + mips_hpt_frequency / 10000000;
 
-	clocksource_set_clock(&clocksource_mips, mips_hpt_frequency);
-
-	clocksource_register(&clocksource_mips);
+	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
 	return 0;
 }
diff --git a/arch/mips/kernel/csrc-sb1250.c b/arch/mips/kernel/csrc-sb1250.c
index d14d3d1907f..e9606d90768 100644
--- a/arch/mips/kernel/csrc-sb1250.c
+++ b/arch/mips/kernel/csrc-sb1250.c
@@ -65,6 +65,5 @@ void __init sb1250_clocksource_init(void)
 		     IOADDR(A_SCD_TIMER_REGISTER(SB1250_HPT_NUM,
 						 R_SCD_TIMER_CFG)));
 
-	clocksource_set_clock(cs, V_SCD_TIMER_FREQ);
-	clocksource_register(cs);
+	clocksource_register_hz(cs, V_SCD_TIMER_FREQ);
 }
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index ffa331029e0..37acfa036d4 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -167,14 +167,13 @@ work_notifysig:				# deal with pending signals and
 FEXPORT(syscall_exit_work_partial)
 	SAVE_STATIC
 syscall_exit_work:
-	li	t0, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t0, _TIF_WORK_SYSCALL_EXIT
 	and	t0, a2			# a2 is preloaded with TI_FLAGS
 	beqz	t0, work_pending	# trace bit set?
-	local_irq_enable		# could let do_syscall_trace()
+	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
 	move	a0, sp
-	li	a1, 1
-	jal	do_syscall_trace
+	jal	syscall_trace_leave
 	b	resume_userspace
 
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT)
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index 2392a7a296d..391221b6a6a 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -125,87 +125,11 @@ void __init setup_pit_timer(void)
 	setup_irq(0, &irq0);
 }
 
-/*
- * Since the PIT overflows every tick, its not very useful
- * to just read by itself. So use jiffies to emulate a free
- * running counter:
- */
-static cycle_t pit_read(struct clocksource *cs)
-{
-	unsigned long flags;
-	int count;
-	u32 jifs;
-	static int old_count;
-	static u32 old_jifs;
-
-	raw_spin_lock_irqsave(&i8253_lock, flags);
-	/*
-	 * Although our caller may have the read side of xtime_lock,
-	 * this is now a seqlock, and we are cheating in this routine
-	 * by having side effects on state that we cannot undo if
-	 * there is a collision on the seqlock and our caller has to
-	 * retry.  (Namely, old_jifs and old_count.)  So we must treat
-	 * jiffies as volatile despite the lock.  We read jiffies
-	 * before latching the timer count to guarantee that although
-	 * the jiffies value might be older than the count (that is,
-	 * the counter may underflow between the last point where
-	 * jiffies was incremented and the point where we latch the
-	 * count), it cannot be newer.
-	 */
-	jifs = jiffies;
-	outb_p(0x00, PIT_MODE);	/* latch the count ASAP */
-	count = inb_p(PIT_CH0);	/* read the latched count */
-	count |= inb_p(PIT_CH0) << 8;
-
-	/* VIA686a test code... reset the latch if count > max + 1 */
-	if (count > LATCH) {
-		outb_p(0x34, PIT_MODE);
-		outb_p(LATCH & 0xff, PIT_CH0);
-		outb(LATCH >> 8, PIT_CH0);
-		count = LATCH - 1;
-	}
-
-	/*
-	 * It's possible for count to appear to go the wrong way for a
-	 * couple of reasons:
-	 *
-	 *  1. The timer counter underflows, but we haven't handled the
-	 *     resulting interrupt and incremented jiffies yet.
-	 *  2. Hardware problem with the timer, not giving us continuous time,
-	 *     the counter does small "jumps" upwards on some Pentium systems,
-	 *     (see c't 95/10 page 335 for Neptun bug.)
-	 *
-	 * Previous attempts to handle these cases intelligently were
-	 * buggy, so we just do the simple thing now.
-	 */
-	if (count > old_count && jifs == old_jifs) {
-		count = old_count;
-	}
-	old_count = count;
-	old_jifs = jifs;
-
-	raw_spin_unlock_irqrestore(&i8253_lock, flags);
-
-	count = (LATCH - 1) - count;
-
-	return (cycle_t)(jifs * LATCH) + count;
-}
-
-static struct clocksource clocksource_pit = {
-	.name	= "pit",
-	.rating = 110,
-	.read	= pit_read,
-	.mask	= CLOCKSOURCE_MASK(32),
-	.mult	= 0,
-	.shift	= 20,
-};
-
 static int __init init_pit_clocksource(void)
 {
 	if (num_possible_cpus() > 1) /* PIT does not scale! */
 		return 0;
 
-	clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20);
-	return clocksource_register(&clocksource_pit);
+	return clocksource_i8253_init();
 }
 arch_initcall(init_pit_clocksource);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 584e6b55c86..4e6ea1ffad4 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -533,15 +533,10 @@ static inline int audit_arch(void)
  * Notification of system call entry/exit
  * - triggered by current->work.syscall_trace
  */
-asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
+asmlinkage void syscall_trace_enter(struct pt_regs *regs)
 {
 	/* do the secure computing check first */
-	if (!entryexit)
-		secure_computing(regs->regs[2]);
-
-	if (unlikely(current->audit_context) && entryexit)
-		audit_syscall_exit(AUDITSC_RESULT(regs->regs[7]),
-		                   -regs->regs[2]);
+	secure_computing(regs->regs[2]);
 
 	if (!(current->ptrace & PT_PTRACED))
 		goto out;
@@ -565,8 +560,40 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
 	}
 
 out:
-	if (unlikely(current->audit_context) && !entryexit)
+	if (unlikely(current->audit_context))
 		audit_syscall_entry(audit_arch(), regs->regs[2],
 				    regs->regs[4], regs->regs[5],
 				    regs->regs[6], regs->regs[7]);
 }
+
+/*
+ * Notification of system call entry/exit
+ * - triggered by current->work.syscall_trace
+ */
+asmlinkage void syscall_trace_leave(struct pt_regs *regs)
+{
+	if (unlikely(current->audit_context))
+		audit_syscall_exit(AUDITSC_RESULT(regs->regs[7]),
+		                   -regs->regs[2]);
+
+	if (!(current->ptrace & PT_PTRACED))
+		return;
+
+	if (!test_thread_flag(TIF_SYSCALL_TRACE))
+		return;
+
+	/* The 0x80 provides a way for the tracing parent to distinguish
+	   between a syscall stop and SIGTRAP delivery */
+	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ?
+	                         0x80 : 0));
+
+	/*
+	 * this isn't the same as continuing with a signal, but it will do
+	 * for normal use.  strace only continues with a signal if the
+	 * stopping signal is not SIGTRAP.  -brl
+	 */
+	if (current->exit_code) {
+		send_sig(current->exit_code, current, 1);
+		current->exit_code = 0;
+	}
+}
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 7f1377eb22d..7a8e1dd7f6f 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -88,8 +88,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	li	a1, 0
-	jal	do_syscall_trace
+	jal	syscall_trace_enter
 
 	move	t0, s0
 	RESTORE_STATIC
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 7c0ef7f128b..2d31c83224f 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -91,8 +91,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	li	a1, 0
-	jal	do_syscall_trace
+	jal	syscall_trace_enter
 
 	move	t0, s0
 	RESTORE_STATIC
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index de6c5563bea..38a0503b9a4 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -89,8 +89,7 @@ n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	li	a1, 0
-	jal	do_syscall_trace
+	jal	syscall_trace_enter
 
 	move	t0, s0
 	RESTORE_STATIC
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index b0541dda883..91ea5e4041d 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -123,8 +123,7 @@ trace_a_syscall:
 
 	move	s0, t2			# Save syscall pointer
 	move	a0, sp
-	li	a1, 0
-	jal	do_syscall_trace
+	jal	syscall_trace_enter
 
 	move	t0, s0
 	RESTORE_STATIC
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 5a88cc4ccd5..cedac463374 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi)
 
 static void ipi_resched_interrupt(void)
 {
-	/* Return from interrupt should be enough to cause scheduler check */
+	scheduler_ipi();
 }
 
 static void ipi_call_interrupt(void)
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 58beabf50b3..d02765708dd 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -10,12 +10,9 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/linkage.h>
-#include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/smp.h>
-#include <linux/mman.h>
 #include <linux/ptrace.h>
-#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/syscalls.h>
 #include <linux/file.h>
@@ -25,11 +22,9 @@
 #include <linux/msg.h>
 #include <linux/shm.h>
 #include <linux/compiler.h>
-#include <linux/module.h>
 #include <linux/ipc.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
-#include <linux/random.h>
 #include <linux/elf.h>
 
 #include <asm/asm.h>
@@ -66,121 +61,6 @@ out:
 	return res;
 }
 
-unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
-
-EXPORT_SYMBOL(shm_align_mask);
-
-#define COLOUR_ALIGN(addr,pgoff)				\
-	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
-
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
-	unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct vm_area_struct * vmm;
-	int do_color_align;
-	unsigned long task_size;
-
-#ifdef CONFIG_32BIT
-	task_size = TASK_SIZE;
-#else /* Must be CONFIG_64BIT*/
-	task_size = test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE;
-#endif
-
-	if (len > task_size)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		/* Even MAP_FIXED mappings must reside within task_size.  */
-		if (task_size - len < addr)
-			return -EINVAL;
-
-		/*
-		 * We do not accept a shared mapping if it would violate
-		 * cache aliasing constraints.
-		 */
-		if ((flags & MAP_SHARED) &&
-		    ((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
-			return -EINVAL;
-		return addr;
-	}
-
-	do_color_align = 0;
-	if (filp || (flags & MAP_SHARED))
-		do_color_align = 1;
-	if (addr) {
-		if (do_color_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-		else
-			addr = PAGE_ALIGN(addr);
-		vmm = find_vma(current->mm, addr);
-		if (task_size - len >= addr &&
-		    (!vmm || addr + len <= vmm->vm_start))
-			return addr;
-	}
-	addr = current->mm->mmap_base;
-	if (do_color_align)
-		addr = COLOUR_ALIGN(addr, pgoff);
-	else
-		addr = PAGE_ALIGN(addr);
-
-	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
-		/* At this point:  (!vmm || addr < vmm->vm_end). */
-		if (task_size - len < addr)
-			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
-			return addr;
-		addr = vmm->vm_end;
-		if (do_color_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-	}
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE) {
-		random_factor = get_random_int();
-		random_factor = random_factor << PAGE_SHIFT;
-		if (TASK_IS_32BIT_ADDR)
-			random_factor &= 0xfffffful;
-		else
-			random_factor &= 0xffffffful;
-	}
-
-	mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-	mm->get_unmapped_area = arch_get_unmapped_area;
-	mm->unmap_area = arch_unmap_area;
-}
-
-static inline unsigned long brk_rnd(void)
-{
-	unsigned long rnd = get_random_int();
-
-	rnd = rnd << PAGE_SHIFT;
-	/* 8MB for 32bit, 256MB for 64bit */
-	if (TASK_IS_32BIT_ADDR)
-		rnd = rnd & 0x7ffffful;
-	else
-		rnd = rnd & 0xffffffful;
-
-	return rnd;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long base = mm->brk;
-	unsigned long ret;
-
-	ret = PAGE_ALIGN(base + brk_rnd());
-
-	if (ret < mm->brk)
-		return mm->brk;
-
-	return ret;
-}
-
 SYSCALL_DEFINE6(mips_mmap, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags, unsigned long,
 	fd, off_t, offset)
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index e4b0b0bec03..cd2ca544454 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -68,6 +68,7 @@ SECTIONS
 	RODATA
 
 	/* writeable */
+	_sdata = .;				/* Start of data section */
 	.data : {	/* Data */
 		. = . + DATAOFFSET;		/* for CONFIG_MAPPED_KERNEL */
 
diff --git a/arch/mips/lantiq/Kconfig b/arch/mips/lantiq/Kconfig
new file mode 100644
index 00000000000..3fccf210451
--- /dev/null
+++ b/arch/mips/lantiq/Kconfig
@@ -0,0 +1,23 @@
+if LANTIQ
+
+config SOC_TYPE_XWAY
+	bool
+	default n
+
+choice
+	prompt "SoC Type"
+	default SOC_XWAY
+
+config SOC_AMAZON_SE
+	bool "Amazon SE"
+	select SOC_TYPE_XWAY
+
+config SOC_XWAY
+	bool "XWAY"
+	select SOC_TYPE_XWAY
+	select HW_HAS_PCI
+endchoice
+
+source "arch/mips/lantiq/xway/Kconfig"
+
+endif
diff --git a/arch/mips/lantiq/Makefile b/arch/mips/lantiq/Makefile
new file mode 100644
index 00000000000..e5dae0e24b0
--- /dev/null
+++ b/arch/mips/lantiq/Makefile
@@ -0,0 +1,11 @@
+# Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+#
+# 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.
+
+obj-y := irq.o setup.o clk.o prom.o devices.o
+
+obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+
+obj-$(CONFIG_SOC_TYPE_XWAY) += xway/
diff --git a/arch/mips/lantiq/Platform b/arch/mips/lantiq/Platform
new file mode 100644
index 00000000000..f3dff05722d
--- /dev/null
+++ b/arch/mips/lantiq/Platform
@@ -0,0 +1,8 @@
+#
+# Lantiq
+#
+
+platform-$(CONFIG_LANTIQ)	+= lantiq/
+cflags-$(CONFIG_LANTIQ)		+= -I$(srctree)/arch/mips/include/asm/mach-lantiq
+load-$(CONFIG_LANTIQ)		= 0xffffffff80002000
+cflags-$(CONFIG_SOC_TYPE_XWAY)	+= -I$(srctree)/arch/mips/include/asm/mach-lantiq/xway
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
new file mode 100644
index 00000000000..94560899d13
--- /dev/null
+++ b/arch/mips/lantiq/clk.c
@@ -0,0 +1,140 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 Thomas Langer <thomas.langer@lantiq.com>
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/list.h>
+
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/div64.h>
+
+#include <lantiq_soc.h>
+
+#include "clk.h"
+
+struct clk {
+	const char *name;
+	unsigned long rate;
+	unsigned long (*get_rate) (void);
+};
+
+static struct clk *cpu_clk;
+static int cpu_clk_cnt;
+
+/* lantiq socs have 3 static clocks */
+static struct clk cpu_clk_generic[] = {
+	{
+		.name = "cpu",
+		.get_rate = ltq_get_cpu_hz,
+	}, {
+		.name = "fpi",
+		.get_rate = ltq_get_fpi_hz,
+	}, {
+		.name = "io",
+		.get_rate = ltq_get_io_region_clock,
+	},
+};
+
+static struct resource ltq_cgu_resource = {
+	.name	= "cgu",
+	.start	= LTQ_CGU_BASE_ADDR,
+	.end	= LTQ_CGU_BASE_ADDR + LTQ_CGU_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+/* remapped clock register range */
+void __iomem *ltq_cgu_membase;
+
+void clk_init(void)
+{
+	cpu_clk = cpu_clk_generic;
+	cpu_clk_cnt = ARRAY_SIZE(cpu_clk_generic);
+}
+
+static inline int clk_good(struct clk *clk)
+{
+	return clk && !IS_ERR(clk);
+}
+
+unsigned long clk_get_rate(struct clk *clk)
+{
+	if (unlikely(!clk_good(clk)))
+		return 0;
+
+	if (clk->rate != 0)
+		return clk->rate;
+
+	if (clk->get_rate != NULL)
+		return clk->get_rate();
+
+	return 0;
+}
+EXPORT_SYMBOL(clk_get_rate);
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	int i;
+
+	for (i = 0; i < cpu_clk_cnt; i++)
+		if (!strcmp(id, cpu_clk[i].name))
+			return &cpu_clk[i];
+	BUG();
+	return ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL(clk_get);
+
+void clk_put(struct clk *clk)
+{
+	/* not used */
+}
+EXPORT_SYMBOL(clk_put);
+
+static inline u32 ltq_get_counter_resolution(void)
+{
+	u32 res;
+
+	__asm__ __volatile__(
+		".set   push\n"
+		".set   mips32r2\n"
+		"rdhwr  %0, $3\n"
+		".set pop\n"
+		: "=&r" (res)
+		: /* no input */
+		: "memory");
+
+	return res;
+}
+
+void __init plat_time_init(void)
+{
+	struct clk *clk;
+
+	if (insert_resource(&iomem_resource, &ltq_cgu_resource) < 0)
+		panic("Failed to insert cgu memory\n");
+
+	if (request_mem_region(ltq_cgu_resource.start,
+			resource_size(&ltq_cgu_resource), "cgu") < 0)
+		panic("Failed to request cgu memory\n");
+
+	ltq_cgu_membase = ioremap_nocache(ltq_cgu_resource.start,
+				resource_size(&ltq_cgu_resource));
+	if (!ltq_cgu_membase) {
+		pr_err("Failed to remap cgu memory\n");
+		unreachable();
+	}
+	clk = clk_get(0, "cpu");
+	mips_hpt_frequency = clk_get_rate(clk) / ltq_get_counter_resolution();
+	write_c0_compare(read_c0_count());
+	clk_put(clk);
+}
diff --git a/arch/mips/lantiq/clk.h b/arch/mips/lantiq/clk.h
new file mode 100644
index 00000000000..3328925f2c3
--- /dev/null
+++ b/arch/mips/lantiq/clk.h
@@ -0,0 +1,18 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_CLK_H__
+#define _LTQ_CLK_H__
+
+extern void clk_init(void);
+
+extern unsigned long ltq_get_cpu_hz(void);
+extern unsigned long ltq_get_fpi_hz(void);
+extern unsigned long ltq_get_io_region_clock(void);
+
+#endif
diff --git a/arch/mips/lantiq/devices.c b/arch/mips/lantiq/devices.c
new file mode 100644
index 00000000000..7b82c34cb16
--- /dev/null
+++ b/arch/mips/lantiq/devices.c
@@ -0,0 +1,122 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/platform_device.h>
+#include <linux/leds.h>
+#include <linux/etherdevice.h>
+#include <linux/reboot.h>
+#include <linux/time.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+
+#include <asm/bootinfo.h>
+#include <asm/irq.h>
+
+#include <lantiq_soc.h>
+
+#include "devices.h"
+
+/* nor flash */
+static struct resource ltq_nor_resource = {
+	.name	= "nor",
+	.start	= LTQ_FLASH_START,
+	.end	= LTQ_FLASH_START + LTQ_FLASH_MAX - 1,
+	.flags  = IORESOURCE_MEM,
+};
+
+static struct platform_device ltq_nor = {
+	.name		= "ltq_nor",
+	.resource	= &ltq_nor_resource,
+	.num_resources	= 1,
+};
+
+void __init ltq_register_nor(struct physmap_flash_data *data)
+{
+	ltq_nor.dev.platform_data = data;
+	platform_device_register(&ltq_nor);
+}
+
+/* watchdog */
+static struct resource ltq_wdt_resource = {
+	.name	= "watchdog",
+	.start  = LTQ_WDT_BASE_ADDR,
+	.end    = LTQ_WDT_BASE_ADDR + LTQ_WDT_SIZE - 1,
+	.flags  = IORESOURCE_MEM,
+};
+
+void __init ltq_register_wdt(void)
+{
+	platform_device_register_simple("ltq_wdt", 0, &ltq_wdt_resource, 1);
+}
+
+/* asc ports */
+static struct resource ltq_asc0_resources[] = {
+	{
+		.name	= "asc0",
+		.start  = LTQ_ASC0_BASE_ADDR,
+		.end    = LTQ_ASC0_BASE_ADDR + LTQ_ASC_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	},
+	IRQ_RES(tx, LTQ_ASC_TIR(0)),
+	IRQ_RES(rx, LTQ_ASC_RIR(0)),
+	IRQ_RES(err, LTQ_ASC_EIR(0)),
+};
+
+static struct resource ltq_asc1_resources[] = {
+	{
+		.name	= "asc1",
+		.start  = LTQ_ASC1_BASE_ADDR,
+		.end    = LTQ_ASC1_BASE_ADDR + LTQ_ASC_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	},
+	IRQ_RES(tx, LTQ_ASC_TIR(1)),
+	IRQ_RES(rx, LTQ_ASC_RIR(1)),
+	IRQ_RES(err, LTQ_ASC_EIR(1)),
+};
+
+void __init ltq_register_asc(int port)
+{
+	switch (port) {
+	case 0:
+		platform_device_register_simple("ltq_asc", 0,
+			ltq_asc0_resources, ARRAY_SIZE(ltq_asc0_resources));
+		break;
+	case 1:
+		platform_device_register_simple("ltq_asc", 1,
+			ltq_asc1_resources, ARRAY_SIZE(ltq_asc1_resources));
+		break;
+	default:
+		break;
+	}
+}
+
+#ifdef CONFIG_PCI
+/* pci */
+static struct platform_device ltq_pci = {
+	.name		= "ltq_pci",
+	.num_resources	= 0,
+};
+
+void __init ltq_register_pci(struct ltq_pci_data *data)
+{
+	ltq_pci.dev.platform_data = data;
+	platform_device_register(&ltq_pci);
+}
+#else
+void __init ltq_register_pci(struct ltq_pci_data *data)
+{
+	pr_err("kernel is compiled without PCI support\n");
+}
+#endif
diff --git a/arch/mips/lantiq/devices.h b/arch/mips/lantiq/devices.h
new file mode 100644
index 00000000000..2947bb19a52
--- /dev/null
+++ b/arch/mips/lantiq/devices.h
@@ -0,0 +1,23 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_DEVICES_H__
+#define _LTQ_DEVICES_H__
+
+#include <lantiq_platform.h>
+#include <linux/mtd/physmap.h>
+
+#define IRQ_RES(resname, irq) \
+	{.name = #resname, .start = (irq), .flags = IORESOURCE_IRQ}
+
+extern void ltq_register_nor(struct physmap_flash_data *data);
+extern void ltq_register_wdt(void);
+extern void ltq_register_asc(int port);
+extern void ltq_register_pci(struct ltq_pci_data *data);
+
+#endif
diff --git a/arch/mips/lantiq/early_printk.c b/arch/mips/lantiq/early_printk.c
new file mode 100644
index 00000000000..972e05f8763
--- /dev/null
+++ b/arch/mips/lantiq/early_printk.c
@@ -0,0 +1,33 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+
+#include <lantiq.h>
+#include <lantiq_soc.h>
+
+/* no ioremap possible at this early stage, lets use KSEG1 instead  */
+#define LTQ_ASC_BASE	KSEG1ADDR(LTQ_ASC1_BASE_ADDR)
+#define ASC_BUF		1024
+#define LTQ_ASC_FSTAT	((u32 *)(LTQ_ASC_BASE + 0x0048))
+#define LTQ_ASC_TBUF	((u32 *)(LTQ_ASC_BASE + 0x0020))
+#define TXMASK		0x3F00
+#define TXOFFSET	8
+
+void prom_putchar(char c)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	do { } while ((ltq_r32(LTQ_ASC_FSTAT) & TXMASK) >> TXOFFSET);
+	if (c == '\n')
+		ltq_w32('\r', LTQ_ASC_TBUF);
+	ltq_w32(c, LTQ_ASC_TBUF);
+	local_irq_restore(flags);
+}
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
new file mode 100644
index 00000000000..fc89795cafd
--- /dev/null
+++ b/arch/mips/lantiq/irq.c
@@ -0,0 +1,326 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ * Copyright (C) 2010 Thomas Langer <thomas.langer@lantiq.com>
+ */
+
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+
+#include <asm/bootinfo.h>
+#include <asm/irq_cpu.h>
+
+#include <lantiq_soc.h>
+#include <irq.h>
+
+/* register definitions */
+#define LTQ_ICU_IM0_ISR		0x0000
+#define LTQ_ICU_IM0_IER		0x0008
+#define LTQ_ICU_IM0_IOSR	0x0010
+#define LTQ_ICU_IM0_IRSR	0x0018
+#define LTQ_ICU_IM0_IMR		0x0020
+#define LTQ_ICU_IM1_ISR		0x0028
+#define LTQ_ICU_OFFSET		(LTQ_ICU_IM1_ISR - LTQ_ICU_IM0_ISR)
+
+#define LTQ_EIU_EXIN_C		0x0000
+#define LTQ_EIU_EXIN_INIC	0x0004
+#define LTQ_EIU_EXIN_INEN	0x000C
+
+/* irq numbers used by the external interrupt unit (EIU) */
+#define LTQ_EIU_IR0		(INT_NUM_IM4_IRL0 + 30)
+#define LTQ_EIU_IR1		(INT_NUM_IM3_IRL0 + 31)
+#define LTQ_EIU_IR2		(INT_NUM_IM1_IRL0 + 26)
+#define LTQ_EIU_IR3		INT_NUM_IM1_IRL0
+#define LTQ_EIU_IR4		(INT_NUM_IM1_IRL0 + 1)
+#define LTQ_EIU_IR5		(INT_NUM_IM1_IRL0 + 2)
+#define LTQ_EIU_IR6		(INT_NUM_IM2_IRL0 + 30)
+
+#define MAX_EIU			6
+
+/* irqs generated by device attached to the EBU need to be acked in
+ * a special manner
+ */
+#define LTQ_ICU_EBU_IRQ		22
+
+#define ltq_icu_w32(x, y)	ltq_w32((x), ltq_icu_membase + (y))
+#define ltq_icu_r32(x)		ltq_r32(ltq_icu_membase + (x))
+
+#define ltq_eiu_w32(x, y)	ltq_w32((x), ltq_eiu_membase + (y))
+#define ltq_eiu_r32(x)		ltq_r32(ltq_eiu_membase + (x))
+
+static unsigned short ltq_eiu_irq[MAX_EIU] = {
+	LTQ_EIU_IR0,
+	LTQ_EIU_IR1,
+	LTQ_EIU_IR2,
+	LTQ_EIU_IR3,
+	LTQ_EIU_IR4,
+	LTQ_EIU_IR5,
+};
+
+static struct resource ltq_icu_resource = {
+	.name	= "icu",
+	.start	= LTQ_ICU_BASE_ADDR,
+	.end	= LTQ_ICU_BASE_ADDR + LTQ_ICU_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct resource ltq_eiu_resource = {
+	.name	= "eiu",
+	.start	= LTQ_EIU_BASE_ADDR,
+	.end	= LTQ_EIU_BASE_ADDR + LTQ_ICU_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static void __iomem *ltq_icu_membase;
+static void __iomem *ltq_eiu_membase;
+
+void ltq_disable_irq(struct irq_data *d)
+{
+	u32 ier = LTQ_ICU_IM0_IER;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	ier += LTQ_ICU_OFFSET * (irq_nr / INT_NUM_IM_OFFSET);
+	irq_nr %= INT_NUM_IM_OFFSET;
+	ltq_icu_w32(ltq_icu_r32(ier) & ~(1 << irq_nr), ier);
+}
+
+void ltq_mask_and_ack_irq(struct irq_data *d)
+{
+	u32 ier = LTQ_ICU_IM0_IER;
+	u32 isr = LTQ_ICU_IM0_ISR;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	ier += LTQ_ICU_OFFSET * (irq_nr / INT_NUM_IM_OFFSET);
+	isr += LTQ_ICU_OFFSET * (irq_nr / INT_NUM_IM_OFFSET);
+	irq_nr %= INT_NUM_IM_OFFSET;
+	ltq_icu_w32(ltq_icu_r32(ier) & ~(1 << irq_nr), ier);
+	ltq_icu_w32((1 << irq_nr), isr);
+}
+
+static void ltq_ack_irq(struct irq_data *d)
+{
+	u32 isr = LTQ_ICU_IM0_ISR;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	isr += LTQ_ICU_OFFSET * (irq_nr / INT_NUM_IM_OFFSET);
+	irq_nr %= INT_NUM_IM_OFFSET;
+	ltq_icu_w32((1 << irq_nr), isr);
+}
+
+void ltq_enable_irq(struct irq_data *d)
+{
+	u32 ier = LTQ_ICU_IM0_IER;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	ier += LTQ_ICU_OFFSET  * (irq_nr / INT_NUM_IM_OFFSET);
+	irq_nr %= INT_NUM_IM_OFFSET;
+	ltq_icu_w32(ltq_icu_r32(ier) | (1 << irq_nr), ier);
+}
+
+static unsigned int ltq_startup_eiu_irq(struct irq_data *d)
+{
+	int i;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	ltq_enable_irq(d);
+	for (i = 0; i < MAX_EIU; i++) {
+		if (irq_nr == ltq_eiu_irq[i]) {
+			/* low level - we should really handle set_type */
+			ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_C) |
+				(0x6 << (i * 4)), LTQ_EIU_EXIN_C);
+			/* clear all pending */
+			ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INIC) & ~(1 << i),
+				LTQ_EIU_EXIN_INIC);
+			/* enable */
+			ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INEN) | (1 << i),
+				LTQ_EIU_EXIN_INEN);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void ltq_shutdown_eiu_irq(struct irq_data *d)
+{
+	int i;
+	int irq_nr = d->irq - INT_NUM_IRQ0;
+
+	ltq_disable_irq(d);
+	for (i = 0; i < MAX_EIU; i++) {
+		if (irq_nr == ltq_eiu_irq[i]) {
+			/* disable */
+			ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INEN) & ~(1 << i),
+				LTQ_EIU_EXIN_INEN);
+			break;
+		}
+	}
+}
+
+static struct irq_chip ltq_irq_type = {
+	"icu",
+	.irq_enable = ltq_enable_irq,
+	.irq_disable = ltq_disable_irq,
+	.irq_unmask = ltq_enable_irq,
+	.irq_ack = ltq_ack_irq,
+	.irq_mask = ltq_disable_irq,
+	.irq_mask_ack = ltq_mask_and_ack_irq,
+};
+
+static struct irq_chip ltq_eiu_type = {
+	"eiu",
+	.irq_startup = ltq_startup_eiu_irq,
+	.irq_shutdown = ltq_shutdown_eiu_irq,
+	.irq_enable = ltq_enable_irq,
+	.irq_disable = ltq_disable_irq,
+	.irq_unmask = ltq_enable_irq,
+	.irq_ack = ltq_ack_irq,
+	.irq_mask = ltq_disable_irq,
+	.irq_mask_ack = ltq_mask_and_ack_irq,
+};
+
+static void ltq_hw_irqdispatch(int module)
+{
+	u32 irq;
+
+	irq = ltq_icu_r32(LTQ_ICU_IM0_IOSR + (module * LTQ_ICU_OFFSET));
+	if (irq == 0)
+		return;
+
+	/* silicon bug causes only the msb set to 1 to be valid. all
+	 * other bits might be bogus
+	 */
+	irq = __fls(irq);
+	do_IRQ((int)irq + INT_NUM_IM0_IRL0 + (INT_NUM_IM_OFFSET * module));
+
+	/* if this is a EBU irq, we need to ack it or get a deadlock */
+	if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0))
+		ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_ISTAT) | 0x10,
+			LTQ_EBU_PCC_ISTAT);
+}
+
+#define DEFINE_HWx_IRQDISPATCH(x)					\
+	static void ltq_hw ## x ## _irqdispatch(void)			\
+	{								\
+		ltq_hw_irqdispatch(x);					\
+	}
+DEFINE_HWx_IRQDISPATCH(0)
+DEFINE_HWx_IRQDISPATCH(1)
+DEFINE_HWx_IRQDISPATCH(2)
+DEFINE_HWx_IRQDISPATCH(3)
+DEFINE_HWx_IRQDISPATCH(4)
+
+static void ltq_hw5_irqdispatch(void)
+{
+	do_IRQ(MIPS_CPU_TIMER_IRQ);
+}
+
+asmlinkage void plat_irq_dispatch(void)
+{
+	unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
+	unsigned int i;
+
+	if (pending & CAUSEF_IP7) {
+		do_IRQ(MIPS_CPU_TIMER_IRQ);
+		goto out;
+	} else {
+		for (i = 0; i < 5; i++) {
+			if (pending & (CAUSEF_IP2 << i)) {
+				ltq_hw_irqdispatch(i);
+				goto out;
+			}
+		}
+	}
+	pr_alert("Spurious IRQ: CAUSE=0x%08x\n", read_c0_status());
+
+out:
+	return;
+}
+
+static struct irqaction cascade = {
+	.handler = no_action,
+	.flags = IRQF_DISABLED,
+	.name = "cascade",
+};
+
+void __init arch_init_irq(void)
+{
+	int i;
+
+	if (insert_resource(&iomem_resource, &ltq_icu_resource) < 0)
+		panic("Failed to insert icu memory\n");
+
+	if (request_mem_region(ltq_icu_resource.start,
+			resource_size(&ltq_icu_resource), "icu") < 0)
+		panic("Failed to request icu memory\n");
+
+	ltq_icu_membase = ioremap_nocache(ltq_icu_resource.start,
+				resource_size(&ltq_icu_resource));
+	if (!ltq_icu_membase)
+		panic("Failed to remap icu memory\n");
+
+	if (insert_resource(&iomem_resource, &ltq_eiu_resource) < 0)
+		panic("Failed to insert eiu memory\n");
+
+	if (request_mem_region(ltq_eiu_resource.start,
+			resource_size(&ltq_eiu_resource), "eiu") < 0)
+		panic("Failed to request eiu memory\n");
+
+	ltq_eiu_membase = ioremap_nocache(ltq_eiu_resource.start,
+				resource_size(&ltq_eiu_resource));
+	if (!ltq_eiu_membase)
+		panic("Failed to remap eiu memory\n");
+
+	/* make sure all irqs are turned off by default */
+	for (i = 0; i < 5; i++)
+		ltq_icu_w32(0, LTQ_ICU_IM0_IER + (i * LTQ_ICU_OFFSET));
+
+	/* clear all possibly pending interrupts */
+	ltq_icu_w32(~0, LTQ_ICU_IM0_ISR + (i * LTQ_ICU_OFFSET));
+
+	mips_cpu_irq_init();
+
+	for (i = 2; i <= 6; i++)
+		setup_irq(i, &cascade);
+
+	if (cpu_has_vint) {
+		pr_info("Setting up vectored interrupts\n");
+		set_vi_handler(2, ltq_hw0_irqdispatch);
+		set_vi_handler(3, ltq_hw1_irqdispatch);
+		set_vi_handler(4, ltq_hw2_irqdispatch);
+		set_vi_handler(5, ltq_hw3_irqdispatch);
+		set_vi_handler(6, ltq_hw4_irqdispatch);
+		set_vi_handler(7, ltq_hw5_irqdispatch);
+	}
+
+	for (i = INT_NUM_IRQ0;
+		i <= (INT_NUM_IRQ0 + (5 * INT_NUM_IM_OFFSET)); i++)
+		if ((i == LTQ_EIU_IR0) || (i == LTQ_EIU_IR1) ||
+			(i == LTQ_EIU_IR2))
+			irq_set_chip_and_handler(i, &ltq_eiu_type,
+				handle_level_irq);
+		/* EIU3-5 only exist on ar9 and vr9 */
+		else if (((i == LTQ_EIU_IR3) || (i == LTQ_EIU_IR4) ||
+			(i == LTQ_EIU_IR5)) && (ltq_is_ar9() || ltq_is_vr9()))
+			irq_set_chip_and_handler(i, &ltq_eiu_type,
+				handle_level_irq);
+		else
+			irq_set_chip_and_handler(i, &ltq_irq_type,
+				handle_level_irq);
+
+#if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC)
+	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
+		IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
+#else
+	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 |
+		IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
+#endif
+}
+
+unsigned int __cpuinit get_c0_compare_int(void)
+{
+	return CP0_LEGACY_COMPARE_IRQ;
+}
diff --git a/arch/mips/lantiq/machtypes.h b/arch/mips/lantiq/machtypes.h
new file mode 100644
index 00000000000..7e01b8c484e
--- /dev/null
+++ b/arch/mips/lantiq/machtypes.h
@@ -0,0 +1,20 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LANTIQ_MACH_H__
+#define _LANTIQ_MACH_H__
+
+#include <asm/mips_machine.h>
+
+enum lantiq_mach_type {
+	LTQ_MACH_GENERIC = 0,
+	LTQ_MACH_EASY50712,	/* Danube evaluation board */
+	LTQ_MACH_EASY50601,	/* Amazon SE evaluation board */
+};
+
+#endif
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
new file mode 100644
index 00000000000..56ba007bf1e
--- /dev/null
+++ b/arch/mips/lantiq/prom.c
@@ -0,0 +1,71 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <asm/bootinfo.h>
+#include <asm/time.h>
+
+#include <lantiq.h>
+
+#include "prom.h"
+#include "clk.h"
+
+static struct ltq_soc_info soc_info;
+
+unsigned int ltq_get_cpu_ver(void)
+{
+	return soc_info.rev;
+}
+EXPORT_SYMBOL(ltq_get_cpu_ver);
+
+unsigned int ltq_get_soc_type(void)
+{
+	return soc_info.type;
+}
+EXPORT_SYMBOL(ltq_get_soc_type);
+
+const char *get_system_type(void)
+{
+	return soc_info.sys_type;
+}
+
+void prom_free_prom_memory(void)
+{
+}
+
+static void __init prom_init_cmdline(void)
+{
+	int argc = fw_arg0;
+	char **argv = (char **) KSEG1ADDR(fw_arg1);
+	int i;
+
+	for (i = 0; i < argc; i++) {
+		char *p = (char *)  KSEG1ADDR(argv[i]);
+
+		if (p && *p) {
+			strlcat(arcs_cmdline, p, sizeof(arcs_cmdline));
+			strlcat(arcs_cmdline, " ", sizeof(arcs_cmdline));
+		}
+	}
+}
+
+void __init prom_init(void)
+{
+	struct clk *clk;
+
+	ltq_soc_detect(&soc_info);
+	clk_init();
+	clk = clk_get(0, "cpu");
+	snprintf(soc_info.sys_type, LTQ_SYS_TYPE_LEN - 1, "%s rev1.%d",
+		soc_info.name, soc_info.rev);
+	clk_put(clk);
+	soc_info.sys_type[LTQ_SYS_TYPE_LEN - 1] = '\0';
+	pr_info("SoC: %s\n", soc_info.sys_type);
+	prom_init_cmdline();
+}
diff --git a/arch/mips/lantiq/prom.h b/arch/mips/lantiq/prom.h
new file mode 100644
index 00000000000..b4229d94280
--- /dev/null
+++ b/arch/mips/lantiq/prom.h
@@ -0,0 +1,25 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_PROM_H__
+#define _LTQ_PROM_H__
+
+#define LTQ_SYS_TYPE_LEN	0x100
+
+struct ltq_soc_info {
+	unsigned char *name;
+	unsigned int rev;
+	unsigned int partnum;
+	unsigned int type;
+	unsigned char sys_type[LTQ_SYS_TYPE_LEN];
+};
+
+extern void ltq_soc_detect(struct ltq_soc_info *i);
+extern void ltq_soc_setup(void);
+
+#endif
diff --git a/arch/mips/lantiq/setup.c b/arch/mips/lantiq/setup.c
new file mode 100644
index 00000000000..9b8af77ed0f
--- /dev/null
+++ b/arch/mips/lantiq/setup.c
@@ -0,0 +1,66 @@
+/*
+ *  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.
+ *
+ * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <asm/bootinfo.h>
+
+#include <lantiq_soc.h>
+
+#include "machtypes.h"
+#include "devices.h"
+#include "prom.h"
+
+void __init plat_mem_setup(void)
+{
+	/* assume 16M as default incase uboot fails to pass proper ramsize */
+	unsigned long memsize = 16;
+	char **envp = (char **) KSEG1ADDR(fw_arg2);
+
+	ioport_resource.start = IOPORT_RESOURCE_START;
+	ioport_resource.end = IOPORT_RESOURCE_END;
+	iomem_resource.start = IOMEM_RESOURCE_START;
+	iomem_resource.end = IOMEM_RESOURCE_END;
+
+	set_io_port_base((unsigned long) KSEG1);
+
+	while (*envp) {
+		char *e = (char *)KSEG1ADDR(*envp);
+		if (!strncmp(e, "memsize=", 8)) {
+			e += 8;
+			if (strict_strtoul(e, 0, &memsize))
+				pr_warn("bad memsize specified\n");
+		}
+		envp++;
+	}
+	memsize *= 1024 * 1024;
+	add_memory_region(0x00000000, memsize, BOOT_MEM_RAM);
+}
+
+static int __init
+lantiq_setup(void)
+{
+	ltq_soc_setup();
+	mips_machine_setup();
+	return 0;
+}
+
+arch_initcall(lantiq_setup);
+
+static void __init
+lantiq_generic_init(void)
+{
+	/* Nothing to do */
+}
+
+MIPS_MACHINE(LTQ_MACH_GENERIC,
+	     "Generic",
+	     "Generic Lantiq based board",
+	     lantiq_generic_init);
diff --git a/arch/mips/lantiq/xway/Kconfig b/arch/mips/lantiq/xway/Kconfig
new file mode 100644
index 00000000000..2b857de3662
--- /dev/null
+++ b/arch/mips/lantiq/xway/Kconfig
@@ -0,0 +1,23 @@
+if SOC_XWAY
+
+menu "MIPS Machine"
+
+config LANTIQ_MACH_EASY50712
+	bool "Easy50712 - Danube"
+	default y
+
+endmenu
+
+endif
+
+if SOC_AMAZON_SE
+
+menu "MIPS Machine"
+
+config LANTIQ_MACH_EASY50601
+	bool "Easy50601 - Amazon SE"
+	default y
+
+endmenu
+
+endif
diff --git a/arch/mips/lantiq/xway/Makefile b/arch/mips/lantiq/xway/Makefile
new file mode 100644
index 00000000000..c517f2e7756
--- /dev/null
+++ b/arch/mips/lantiq/xway/Makefile
@@ -0,0 +1,7 @@
+obj-y := pmu.o ebu.o reset.o gpio.o gpio_stp.o gpio_ebu.o devices.o dma.o
+
+obj-$(CONFIG_SOC_XWAY) += clk-xway.o prom-xway.o setup-xway.o
+obj-$(CONFIG_SOC_AMAZON_SE) += clk-ase.o prom-ase.o setup-ase.o
+
+obj-$(CONFIG_LANTIQ_MACH_EASY50712) += mach-easy50712.o
+obj-$(CONFIG_LANTIQ_MACH_EASY50601) += mach-easy50601.o
diff --git a/arch/mips/lantiq/xway/clk-ase.c b/arch/mips/lantiq/xway/clk-ase.c
new file mode 100644
index 00000000000..22d823acd53
--- /dev/null
+++ b/arch/mips/lantiq/xway/clk-ase.c
@@ -0,0 +1,48 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/clk.h>
+
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/div64.h>
+
+#include <lantiq_soc.h>
+
+/* cgu registers */
+#define LTQ_CGU_SYS	0x0010
+
+unsigned int ltq_get_io_region_clock(void)
+{
+	return CLOCK_133M;
+}
+EXPORT_SYMBOL(ltq_get_io_region_clock);
+
+unsigned int ltq_get_fpi_bus_clock(int fpi)
+{
+	return CLOCK_133M;
+}
+EXPORT_SYMBOL(ltq_get_fpi_bus_clock);
+
+unsigned int ltq_get_cpu_hz(void)
+{
+	if (ltq_cgu_r32(LTQ_CGU_SYS) & (1 << 5))
+		return CLOCK_266M;
+	else
+		return CLOCK_133M;
+}
+EXPORT_SYMBOL(ltq_get_cpu_hz);
+
+unsigned int ltq_get_fpi_hz(void)
+{
+	return CLOCK_133M;
+}
+EXPORT_SYMBOL(ltq_get_fpi_hz);
diff --git a/arch/mips/lantiq/xway/clk-xway.c b/arch/mips/lantiq/xway/clk-xway.c
new file mode 100644
index 00000000000..ddd39593c58
--- /dev/null
+++ b/arch/mips/lantiq/xway/clk-xway.c
@@ -0,0 +1,223 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/clk.h>
+
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/div64.h>
+
+#include <lantiq_soc.h>
+
+static unsigned int ltq_ram_clocks[] = {
+	CLOCK_167M, CLOCK_133M, CLOCK_111M, CLOCK_83M };
+#define DDR_HZ ltq_ram_clocks[ltq_cgu_r32(LTQ_CGU_SYS) & 0x3]
+
+#define BASIC_FREQUENCY_1	35328000
+#define BASIC_FREQUENCY_2	36000000
+#define BASIS_REQUENCY_USB	12000000
+
+#define GET_BITS(x, msb, lsb) \
+	(((x) & ((1 << ((msb) + 1)) - 1)) >> (lsb))
+
+#define LTQ_CGU_PLL0_CFG	0x0004
+#define LTQ_CGU_PLL1_CFG	0x0008
+#define LTQ_CGU_PLL2_CFG	0x000C
+#define LTQ_CGU_SYS		0x0010
+#define LTQ_CGU_UPDATE		0x0014
+#define LTQ_CGU_IF_CLK		0x0018
+#define LTQ_CGU_OSC_CON		0x001C
+#define LTQ_CGU_SMD		0x0020
+#define LTQ_CGU_CT1SR		0x0028
+#define LTQ_CGU_CT2SR		0x002C
+#define LTQ_CGU_PCMCR		0x0030
+#define LTQ_CGU_PCI_CR		0x0034
+#define LTQ_CGU_PD_PC		0x0038
+#define LTQ_CGU_FMR		0x003C
+
+#define CGU_PLL0_PHASE_DIVIDER_ENABLE	\
+	(ltq_cgu_r32(LTQ_CGU_PLL0_CFG) & (1 << 31))
+#define CGU_PLL0_BYPASS			\
+	(ltq_cgu_r32(LTQ_CGU_PLL0_CFG) & (1 << 30))
+#define CGU_PLL0_CFG_DSMSEL		\
+	(ltq_cgu_r32(LTQ_CGU_PLL0_CFG) & (1 << 28))
+#define CGU_PLL0_CFG_FRAC_EN		\
+	(ltq_cgu_r32(LTQ_CGU_PLL0_CFG) & (1 << 27))
+#define CGU_PLL1_SRC			\
+	(ltq_cgu_r32(LTQ_CGU_PLL1_CFG) & (1 << 31))
+#define CGU_PLL2_PHASE_DIVIDER_ENABLE	\
+	(ltq_cgu_r32(LTQ_CGU_PLL2_CFG) & (1 << 20))
+#define CGU_SYS_FPI_SEL			(1 << 6)
+#define CGU_SYS_DDR_SEL			0x3
+#define CGU_PLL0_SRC			(1 << 29)
+
+#define CGU_PLL0_CFG_PLLK	GET_BITS(ltq_cgu_r32(LTQ_CGU_PLL0_CFG), 26, 17)
+#define CGU_PLL0_CFG_PLLN	GET_BITS(ltq_cgu_r32(LTQ_CGU_PLL0_CFG), 12, 6)
+#define CGU_PLL0_CFG_PLLM	GET_BITS(ltq_cgu_r32(LTQ_CGU_PLL0_CFG), 5, 2)
+#define CGU_PLL2_SRC		GET_BITS(ltq_cgu_r32(LTQ_CGU_PLL2_CFG), 18, 17)
+#define CGU_PLL2_CFG_INPUT_DIV	GET_BITS(ltq_cgu_r32(LTQ_CGU_PLL2_CFG), 16, 13)
+
+static unsigned int ltq_get_pll0_fdiv(void);
+
+static inline unsigned int get_input_clock(int pll)
+{
+	switch (pll) {
+	case 0:
+		if (ltq_cgu_r32(LTQ_CGU_PLL0_CFG) & CGU_PLL0_SRC)
+			return BASIS_REQUENCY_USB;
+		else if (CGU_PLL0_PHASE_DIVIDER_ENABLE)
+			return BASIC_FREQUENCY_1;
+		else
+			return BASIC_FREQUENCY_2;
+	case 1:
+		if (CGU_PLL1_SRC)
+			return BASIS_REQUENCY_USB;
+		else if (CGU_PLL0_PHASE_DIVIDER_ENABLE)
+			return BASIC_FREQUENCY_1;
+		else
+			return BASIC_FREQUENCY_2;
+	case 2:
+		switch (CGU_PLL2_SRC) {
+		case 0:
+			return ltq_get_pll0_fdiv();
+		case 1:
+			return CGU_PLL2_PHASE_DIVIDER_ENABLE ?
+				BASIC_FREQUENCY_1 :
+				BASIC_FREQUENCY_2;
+		case 2:
+			return BASIS_REQUENCY_USB;
+		}
+	default:
+		return 0;
+	}
+}
+
+static inline unsigned int cal_dsm(int pll, unsigned int num, unsigned int den)
+{
+	u64 res, clock = get_input_clock(pll);
+
+	res = num * clock;
+	do_div(res, den);
+	return res;
+}
+
+static inline unsigned int mash_dsm(int pll, unsigned int M, unsigned int N,
+	unsigned int K)
+{
+	unsigned int num = ((N + 1) << 10) + K;
+	unsigned int den = (M + 1) << 10;
+
+	return cal_dsm(pll, num, den);
+}
+
+static inline unsigned int ssff_dsm_1(int pll, unsigned int M, unsigned int N,
+	unsigned int K)
+{
+	unsigned int num = ((N + 1) << 11) + K + 512;
+	unsigned int den = (M + 1) << 11;
+
+	return cal_dsm(pll, num, den);
+}
+
+static inline unsigned int ssff_dsm_2(int pll, unsigned int M, unsigned int N,
+	unsigned int K)
+{
+	unsigned int num = K >= 512 ?
+		((N + 1) << 12) + K - 512 : ((N + 1) << 12) + K + 3584;
+	unsigned int den = (M + 1) << 12;
+
+	return cal_dsm(pll, num, den);
+}
+
+static inline unsigned int dsm(int pll, unsigned int M, unsigned int N,
+	unsigned int K, unsigned int dsmsel, unsigned int phase_div_en)
+{
+	if (!dsmsel)
+		return mash_dsm(pll, M, N, K);
+	else if (!phase_div_en)
+		return mash_dsm(pll, M, N, K);
+	else
+		return ssff_dsm_2(pll, M, N, K);
+}
+
+static inline unsigned int ltq_get_pll0_fosc(void)
+{
+	if (CGU_PLL0_BYPASS)
+		return get_input_clock(0);
+	else
+		return !CGU_PLL0_CFG_FRAC_EN
+			? dsm(0, CGU_PLL0_CFG_PLLM, CGU_PLL0_CFG_PLLN, 0,
+				CGU_PLL0_CFG_DSMSEL,
+				CGU_PLL0_PHASE_DIVIDER_ENABLE)
+			: dsm(0, CGU_PLL0_CFG_PLLM, CGU_PLL0_CFG_PLLN,
+				CGU_PLL0_CFG_PLLK, CGU_PLL0_CFG_DSMSEL,
+				CGU_PLL0_PHASE_DIVIDER_ENABLE);
+}
+
+static unsigned int ltq_get_pll0_fdiv(void)
+{
+	unsigned int div = CGU_PLL2_CFG_INPUT_DIV + 1;
+
+	return (ltq_get_pll0_fosc() + (div >> 1)) / div;
+}
+
+unsigned int ltq_get_io_region_clock(void)
+{
+	unsigned int ret = ltq_get_pll0_fosc();
+
+	switch (ltq_cgu_r32(LTQ_CGU_PLL2_CFG) & CGU_SYS_DDR_SEL) {
+	default:
+	case 0:
+		return (ret + 1) / 2;
+	case 1:
+		return (ret * 2 + 2) / 5;
+	case 2:
+		return (ret + 1) / 3;
+	case 3:
+		return (ret + 2) / 4;
+	}
+}
+EXPORT_SYMBOL(ltq_get_io_region_clock);
+
+unsigned int ltq_get_fpi_bus_clock(int fpi)
+{
+	unsigned int ret = ltq_get_io_region_clock();
+
+	if ((fpi == 2) && (ltq_cgu_r32(LTQ_CGU_SYS) & CGU_SYS_FPI_SEL))
+		ret >>= 1;
+	return ret;
+}
+EXPORT_SYMBOL(ltq_get_fpi_bus_clock);
+
+unsigned int ltq_get_cpu_hz(void)
+{
+	switch (ltq_cgu_r32(LTQ_CGU_SYS) & 0xc) {
+	case 0:
+		return CLOCK_333M;
+	case 4:
+		return DDR_HZ;
+	case 8:
+		return DDR_HZ << 1;
+	default:
+		return DDR_HZ >> 1;
+	}
+}
+EXPORT_SYMBOL(ltq_get_cpu_hz);
+
+unsigned int ltq_get_fpi_hz(void)
+{
+	unsigned int ddr_clock = DDR_HZ;
+
+	if (ltq_cgu_r32(LTQ_CGU_SYS) & 0x40)
+		return ddr_clock >> 1;
+	return ddr_clock;
+}
+EXPORT_SYMBOL(ltq_get_fpi_hz);
diff --git a/arch/mips/lantiq/xway/devices.c b/arch/mips/lantiq/xway/devices.c
new file mode 100644
index 00000000000..e09e789dfc2
--- /dev/null
+++ b/arch/mips/lantiq/xway/devices.c
@@ -0,0 +1,121 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/mtd/physmap.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/platform_device.h>
+#include <linux/leds.h>
+#include <linux/etherdevice.h>
+#include <linux/reboot.h>
+#include <linux/time.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+
+#include <asm/bootinfo.h>
+#include <asm/irq.h>
+
+#include <lantiq_soc.h>
+#include <lantiq_irq.h>
+#include <lantiq_platform.h>
+
+#include "devices.h"
+
+/* gpio */
+static struct resource ltq_gpio_resource[] = {
+	{
+		.name	= "gpio0",
+		.start  = LTQ_GPIO0_BASE_ADDR,
+		.end    = LTQ_GPIO0_BASE_ADDR + LTQ_GPIO_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	}, {
+		.name	= "gpio1",
+		.start  = LTQ_GPIO1_BASE_ADDR,
+		.end    = LTQ_GPIO1_BASE_ADDR + LTQ_GPIO_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	}, {
+		.name	= "gpio2",
+		.start  = LTQ_GPIO2_BASE_ADDR,
+		.end    = LTQ_GPIO2_BASE_ADDR + LTQ_GPIO_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	}
+};
+
+void __init ltq_register_gpio(void)
+{
+	platform_device_register_simple("ltq_gpio", 0,
+		&ltq_gpio_resource[0], 1);
+	platform_device_register_simple("ltq_gpio", 1,
+		&ltq_gpio_resource[1], 1);
+
+	/* AR9 and VR9 have an extra gpio block */
+	if (ltq_is_ar9() || ltq_is_vr9()) {
+		platform_device_register_simple("ltq_gpio", 2,
+			&ltq_gpio_resource[2], 1);
+	}
+}
+
+/* serial to parallel conversion */
+static struct resource ltq_stp_resource = {
+	.name   = "stp",
+	.start  = LTQ_STP_BASE_ADDR,
+	.end    = LTQ_STP_BASE_ADDR + LTQ_STP_SIZE - 1,
+	.flags  = IORESOURCE_MEM,
+};
+
+void __init ltq_register_gpio_stp(void)
+{
+	platform_device_register_simple("ltq_stp", 0, &ltq_stp_resource, 1);
+}
+
+/* asc ports - amazon se has its own serial mapping */
+static struct resource ltq_ase_asc_resources[] = {
+	{
+		.name	= "asc0",
+		.start  = LTQ_ASC1_BASE_ADDR,
+		.end    = LTQ_ASC1_BASE_ADDR + LTQ_ASC_SIZE - 1,
+		.flags  = IORESOURCE_MEM,
+	},
+	IRQ_RES(tx, LTQ_ASC_ASE_TIR),
+	IRQ_RES(rx, LTQ_ASC_ASE_RIR),
+	IRQ_RES(err, LTQ_ASC_ASE_EIR),
+};
+
+void __init ltq_register_ase_asc(void)
+{
+	platform_device_register_simple("ltq_asc", 0,
+		ltq_ase_asc_resources, ARRAY_SIZE(ltq_ase_asc_resources));
+}
+
+/* ethernet */
+static struct resource ltq_etop_resources = {
+	.name	= "etop",
+	.start	= LTQ_ETOP_BASE_ADDR,
+	.end	= LTQ_ETOP_BASE_ADDR + LTQ_ETOP_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct platform_device ltq_etop = {
+	.name		= "ltq_etop",
+	.resource	= &ltq_etop_resources,
+	.num_resources	= 1,
+};
+
+void __init
+ltq_register_etop(struct ltq_eth_data *eth)
+{
+	if (eth) {
+		ltq_etop.dev.platform_data = eth;
+		platform_device_register(&ltq_etop);
+	}
+}
diff --git a/arch/mips/lantiq/xway/devices.h b/arch/mips/lantiq/xway/devices.h
new file mode 100644
index 00000000000..e90493471bc
--- /dev/null
+++ b/arch/mips/lantiq/xway/devices.h
@@ -0,0 +1,20 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_DEVICES_XWAY_H__
+#define _LTQ_DEVICES_XWAY_H__
+
+#include "../devices.h"
+#include <linux/phy.h>
+
+extern void ltq_register_gpio(void);
+extern void ltq_register_gpio_stp(void);
+extern void ltq_register_ase_asc(void);
+extern void ltq_register_etop(struct ltq_eth_data *eth);
+
+#endif
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
new file mode 100644
index 00000000000..4278a459d6c
--- /dev/null
+++ b/arch/mips/lantiq/xway/dma.c
@@ -0,0 +1,253 @@
+/*
+ *   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., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
+ *
+ *   Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/dma-mapping.h>
+
+#include <lantiq_soc.h>
+#include <xway_dma.h>
+
+#define LTQ_DMA_CTRL		0x10
+#define LTQ_DMA_CPOLL		0x14
+#define LTQ_DMA_CS		0x18
+#define LTQ_DMA_CCTRL		0x1C
+#define LTQ_DMA_CDBA		0x20
+#define LTQ_DMA_CDLEN		0x24
+#define LTQ_DMA_CIS		0x28
+#define LTQ_DMA_CIE		0x2C
+#define LTQ_DMA_PS		0x40
+#define LTQ_DMA_PCTRL		0x44
+#define LTQ_DMA_IRNEN		0xf4
+
+#define DMA_DESCPT		BIT(3)		/* descriptor complete irq */
+#define DMA_TX			BIT(8)		/* TX channel direction */
+#define DMA_CHAN_ON		BIT(0)		/* channel on / off bit */
+#define DMA_PDEN		BIT(6)		/* enable packet drop */
+#define DMA_CHAN_RST		BIT(1)		/* channel on / off bit */
+#define DMA_RESET		BIT(0)		/* channel on / off bit */
+#define DMA_IRQ_ACK		0x7e		/* IRQ status register */
+#define DMA_POLL		BIT(31)		/* turn on channel polling */
+#define DMA_CLK_DIV4		BIT(6)		/* polling clock divider */
+#define DMA_2W_BURST		BIT(1)		/* 2 word burst length */
+#define DMA_MAX_CHANNEL		20		/* the soc has 20 channels */
+#define DMA_ETOP_ENDIANESS	(0xf << 8) /* endianess swap etop channels */
+#define DMA_WEIGHT	(BIT(17) | BIT(16))	/* default channel wheight */
+
+#define ltq_dma_r32(x)			ltq_r32(ltq_dma_membase + (x))
+#define ltq_dma_w32(x, y)		ltq_w32(x, ltq_dma_membase + (y))
+#define ltq_dma_w32_mask(x, y, z)	ltq_w32_mask(x, y, \
+						ltq_dma_membase + (z))
+
+static struct resource ltq_dma_resource = {
+	.name	= "dma",
+	.start	= LTQ_DMA_BASE_ADDR,
+	.end	= LTQ_DMA_BASE_ADDR + LTQ_DMA_SIZE - 1,
+	.flags  = IORESOURCE_MEM,
+};
+
+static void __iomem *ltq_dma_membase;
+
+void
+ltq_dma_enable_irq(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32_mask(0, 1 << ch->nr, LTQ_DMA_IRNEN);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_enable_irq);
+
+void
+ltq_dma_disable_irq(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32_mask(1 << ch->nr, 0, LTQ_DMA_IRNEN);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_disable_irq);
+
+void
+ltq_dma_ack_irq(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32(DMA_IRQ_ACK, LTQ_DMA_CIS);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_ack_irq);
+
+void
+ltq_dma_open(struct ltq_dma_channel *ch)
+{
+	unsigned long flag;
+
+	local_irq_save(flag);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32_mask(0, DMA_CHAN_ON, LTQ_DMA_CCTRL);
+	ltq_dma_enable_irq(ch);
+	local_irq_restore(flag);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_open);
+
+void
+ltq_dma_close(struct ltq_dma_channel *ch)
+{
+	unsigned long flag;
+
+	local_irq_save(flag);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32_mask(DMA_CHAN_ON, 0, LTQ_DMA_CCTRL);
+	ltq_dma_disable_irq(ch);
+	local_irq_restore(flag);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_close);
+
+static void
+ltq_dma_alloc(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	ch->desc = 0;
+	ch->desc_base = dma_alloc_coherent(NULL,
+				LTQ_DESC_NUM * LTQ_DESC_SIZE,
+				&ch->phys, GFP_ATOMIC);
+	memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE);
+
+	local_irq_save(flags);
+	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
+	ltq_dma_w32(ch->phys, LTQ_DMA_CDBA);
+	ltq_dma_w32(LTQ_DESC_NUM, LTQ_DMA_CDLEN);
+	ltq_dma_w32_mask(DMA_CHAN_ON, 0, LTQ_DMA_CCTRL);
+	wmb();
+	ltq_dma_w32_mask(0, DMA_CHAN_RST, LTQ_DMA_CCTRL);
+	while (ltq_dma_r32(LTQ_DMA_CCTRL) & DMA_CHAN_RST)
+		;
+	local_irq_restore(flags);
+}
+
+void
+ltq_dma_alloc_tx(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	ltq_dma_alloc(ch);
+
+	local_irq_save(flags);
+	ltq_dma_w32(DMA_DESCPT, LTQ_DMA_CIE);
+	ltq_dma_w32_mask(0, 1 << ch->nr, LTQ_DMA_IRNEN);
+	ltq_dma_w32(DMA_WEIGHT | DMA_TX, LTQ_DMA_CCTRL);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_alloc_tx);
+
+void
+ltq_dma_alloc_rx(struct ltq_dma_channel *ch)
+{
+	unsigned long flags;
+
+	ltq_dma_alloc(ch);
+
+	local_irq_save(flags);
+	ltq_dma_w32(DMA_DESCPT, LTQ_DMA_CIE);
+	ltq_dma_w32_mask(0, 1 << ch->nr, LTQ_DMA_IRNEN);
+	ltq_dma_w32(DMA_WEIGHT, LTQ_DMA_CCTRL);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_alloc_rx);
+
+void
+ltq_dma_free(struct ltq_dma_channel *ch)
+{
+	if (!ch->desc_base)
+		return;
+	ltq_dma_close(ch);
+	dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE,
+		ch->desc_base, ch->phys);
+}
+EXPORT_SYMBOL_GPL(ltq_dma_free);
+
+void
+ltq_dma_init_port(int p)
+{
+	ltq_dma_w32(p, LTQ_DMA_PS);
+	switch (p) {
+	case DMA_PORT_ETOP:
+		/*
+		 * Tell the DMA engine to swap the endianess of data frames and
+		 * drop packets if the channel arbitration fails.
+		 */
+		ltq_dma_w32_mask(0, DMA_ETOP_ENDIANESS | DMA_PDEN,
+			LTQ_DMA_PCTRL);
+		break;
+
+	case DMA_PORT_DEU:
+		ltq_dma_w32((DMA_2W_BURST << 4) | (DMA_2W_BURST << 2),
+			LTQ_DMA_PCTRL);
+		break;
+
+	default:
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ltq_dma_init_port);
+
+int __init
+ltq_dma_init(void)
+{
+	int i;
+
+	/* insert and request the memory region */
+	if (insert_resource(&iomem_resource, &ltq_dma_resource) < 0)
+		panic("Failed to insert dma memory\n");
+
+	if (request_mem_region(ltq_dma_resource.start,
+			resource_size(&ltq_dma_resource), "dma") < 0)
+		panic("Failed to request dma memory\n");
+
+	/* remap dma register range */
+	ltq_dma_membase = ioremap_nocache(ltq_dma_resource.start,
+				resource_size(&ltq_dma_resource));
+	if (!ltq_dma_membase)
+		panic("Failed to remap dma memory\n");
+
+	/* power up and reset the dma engine */
+	ltq_pmu_enable(PMU_DMA);
+	ltq_dma_w32_mask(0, DMA_RESET, LTQ_DMA_CTRL);
+
+	/* disable all interrupts */
+	ltq_dma_w32(0, LTQ_DMA_IRNEN);
+
+	/* reset/configure each channel */
+	for (i = 0; i < DMA_MAX_CHANNEL; i++) {
+		ltq_dma_w32(i, LTQ_DMA_CS);
+		ltq_dma_w32(DMA_CHAN_RST, LTQ_DMA_CCTRL);
+		ltq_dma_w32(DMA_POLL | DMA_CLK_DIV4, LTQ_DMA_CPOLL);
+		ltq_dma_w32_mask(DMA_CHAN_ON, 0, LTQ_DMA_CCTRL);
+	}
+	return 0;
+}
+
+postcore_initcall(ltq_dma_init);
diff --git a/arch/mips/lantiq/xway/ebu.c b/arch/mips/lantiq/xway/ebu.c
new file mode 100644
index 00000000000..66eb52fa50a
--- /dev/null
+++ b/arch/mips/lantiq/xway/ebu.c
@@ -0,0 +1,53 @@
+/*
+ *  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.
+ *
+ *  EBU - the external bus unit attaches PCI, NOR and NAND
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/ioport.h>
+
+#include <lantiq_soc.h>
+
+/* all access to the ebu must be locked */
+DEFINE_SPINLOCK(ebu_lock);
+EXPORT_SYMBOL_GPL(ebu_lock);
+
+static struct resource ltq_ebu_resource = {
+	.name	= "ebu",
+	.start	= LTQ_EBU_BASE_ADDR,
+	.end	= LTQ_EBU_BASE_ADDR + LTQ_EBU_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+/* remapped base addr of the clock unit and external bus unit */
+void __iomem *ltq_ebu_membase;
+
+static int __init lantiq_ebu_init(void)
+{
+	/* insert and request the memory region */
+	if (insert_resource(&iomem_resource, &ltq_ebu_resource) < 0)
+		panic("Failed to insert ebu memory\n");
+
+	if (request_mem_region(ltq_ebu_resource.start,
+			resource_size(&ltq_ebu_resource), "ebu") < 0)
+		panic("Failed to request ebu memory\n");
+
+	/* remap ebu register range */
+	ltq_ebu_membase = ioremap_nocache(ltq_ebu_resource.start,
+				resource_size(&ltq_ebu_resource));
+	if (!ltq_ebu_membase)
+		panic("Failed to remap ebu memory\n");
+
+	/* make sure to unprotect the memory region where flash is located */
+	ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_BUSCON0) & ~EBU_WRDIS, LTQ_EBU_BUSCON0);
+	return 0;
+}
+
+postcore_initcall(lantiq_ebu_init);
diff --git a/arch/mips/lantiq/xway/gpio.c b/arch/mips/lantiq/xway/gpio.c
new file mode 100644
index 00000000000..a321451a545
--- /dev/null
+++ b/arch/mips/lantiq/xway/gpio.c
@@ -0,0 +1,195 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+
+#include <lantiq_soc.h>
+
+#define LTQ_GPIO_OUT		0x00
+#define LTQ_GPIO_IN		0x04
+#define LTQ_GPIO_DIR		0x08
+#define LTQ_GPIO_ALTSEL0	0x0C
+#define LTQ_GPIO_ALTSEL1	0x10
+#define LTQ_GPIO_OD		0x14
+
+#define PINS_PER_PORT		16
+#define MAX_PORTS		3
+
+#define ltq_gpio_getbit(m, r, p)	(!!(ltq_r32(m + r) & (1 << p)))
+#define ltq_gpio_setbit(m, r, p)	ltq_w32_mask(0, (1 << p), m + r)
+#define ltq_gpio_clearbit(m, r, p)	ltq_w32_mask((1 << p), 0, m + r)
+
+struct ltq_gpio {
+	void __iomem *membase;
+	struct gpio_chip chip;
+};
+
+static struct ltq_gpio ltq_gpio_port[MAX_PORTS];
+
+int gpio_to_irq(unsigned int gpio)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(gpio_to_irq);
+
+int irq_to_gpio(unsigned int gpio)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(irq_to_gpio);
+
+int ltq_gpio_request(unsigned int pin, unsigned int alt0,
+	unsigned int alt1, unsigned int dir, const char *name)
+{
+	int id = 0;
+
+	if (pin >= (MAX_PORTS * PINS_PER_PORT))
+		return -EINVAL;
+	if (gpio_request(pin, name)) {
+		pr_err("failed to setup lantiq gpio: %s\n", name);
+		return -EBUSY;
+	}
+	if (dir)
+		gpio_direction_output(pin, 1);
+	else
+		gpio_direction_input(pin);
+	while (pin >= PINS_PER_PORT) {
+		pin -= PINS_PER_PORT;
+		id++;
+	}
+	if (alt0)
+		ltq_gpio_setbit(ltq_gpio_port[id].membase,
+			LTQ_GPIO_ALTSEL0, pin);
+	else
+		ltq_gpio_clearbit(ltq_gpio_port[id].membase,
+			LTQ_GPIO_ALTSEL0, pin);
+	if (alt1)
+		ltq_gpio_setbit(ltq_gpio_port[id].membase,
+			LTQ_GPIO_ALTSEL1, pin);
+	else
+		ltq_gpio_clearbit(ltq_gpio_port[id].membase,
+			LTQ_GPIO_ALTSEL1, pin);
+	return 0;
+}
+EXPORT_SYMBOL(ltq_gpio_request);
+
+static void ltq_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
+{
+	struct ltq_gpio *ltq_gpio = container_of(chip, struct ltq_gpio, chip);
+
+	if (value)
+		ltq_gpio_setbit(ltq_gpio->membase, LTQ_GPIO_OUT, offset);
+	else
+		ltq_gpio_clearbit(ltq_gpio->membase, LTQ_GPIO_OUT, offset);
+}
+
+static int ltq_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct ltq_gpio *ltq_gpio = container_of(chip, struct ltq_gpio, chip);
+
+	return ltq_gpio_getbit(ltq_gpio->membase, LTQ_GPIO_IN, offset);
+}
+
+static int ltq_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
+{
+	struct ltq_gpio *ltq_gpio = container_of(chip, struct ltq_gpio, chip);
+
+	ltq_gpio_clearbit(ltq_gpio->membase, LTQ_GPIO_OD, offset);
+	ltq_gpio_clearbit(ltq_gpio->membase, LTQ_GPIO_DIR, offset);
+
+	return 0;
+}
+
+static int ltq_gpio_direction_output(struct gpio_chip *chip,
+	unsigned int offset, int value)
+{
+	struct ltq_gpio *ltq_gpio = container_of(chip, struct ltq_gpio, chip);
+
+	ltq_gpio_setbit(ltq_gpio->membase, LTQ_GPIO_OD, offset);
+	ltq_gpio_setbit(ltq_gpio->membase, LTQ_GPIO_DIR, offset);
+	ltq_gpio_set(chip, offset, value);
+
+	return 0;
+}
+
+static int ltq_gpio_req(struct gpio_chip *chip, unsigned offset)
+{
+	struct ltq_gpio *ltq_gpio = container_of(chip, struct ltq_gpio, chip);
+
+	ltq_gpio_clearbit(ltq_gpio->membase, LTQ_GPIO_ALTSEL0, offset);
+	ltq_gpio_clearbit(ltq_gpio->membase, LTQ_GPIO_ALTSEL1, offset);
+	return 0;
+}
+
+static int ltq_gpio_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	if (pdev->id >= MAX_PORTS) {
+		dev_err(&pdev->dev, "invalid gpio port %d\n",
+			pdev->id);
+		return -EINVAL;
+	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "failed to get memory for gpio port %d\n",
+			pdev->id);
+		return -ENOENT;
+	}
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		resource_size(res), dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev,
+			"failed to request memory for gpio port %d\n",
+			pdev->id);
+		return -EBUSY;
+	}
+	ltq_gpio_port[pdev->id].membase = devm_ioremap_nocache(&pdev->dev,
+		res->start, resource_size(res));
+	if (!ltq_gpio_port[pdev->id].membase) {
+		dev_err(&pdev->dev, "failed to remap memory for gpio port %d\n",
+			pdev->id);
+		return -ENOMEM;
+	}
+	ltq_gpio_port[pdev->id].chip.label = "ltq_gpio";
+	ltq_gpio_port[pdev->id].chip.direction_input = ltq_gpio_direction_input;
+	ltq_gpio_port[pdev->id].chip.direction_output =
+		ltq_gpio_direction_output;
+	ltq_gpio_port[pdev->id].chip.get = ltq_gpio_get;
+	ltq_gpio_port[pdev->id].chip.set = ltq_gpio_set;
+	ltq_gpio_port[pdev->id].chip.request = ltq_gpio_req;
+	ltq_gpio_port[pdev->id].chip.base = PINS_PER_PORT * pdev->id;
+	ltq_gpio_port[pdev->id].chip.ngpio = PINS_PER_PORT;
+	platform_set_drvdata(pdev, &ltq_gpio_port[pdev->id]);
+	return gpiochip_add(&ltq_gpio_port[pdev->id].chip);
+}
+
+static struct platform_driver
+ltq_gpio_driver = {
+	.probe = ltq_gpio_probe,
+	.driver = {
+		.name = "ltq_gpio",
+		.owner = THIS_MODULE,
+	},
+};
+
+int __init ltq_gpio_init(void)
+{
+	int ret = platform_driver_register(&ltq_gpio_driver);
+
+	if (ret)
+		pr_info("ltq_gpio : Error registering platfom driver!");
+	return ret;
+}
+
+postcore_initcall(ltq_gpio_init);
diff --git a/arch/mips/lantiq/xway/gpio_ebu.c b/arch/mips/lantiq/xway/gpio_ebu.c
new file mode 100644
index 00000000000..a479355abdb
--- /dev/null
+++ b/arch/mips/lantiq/xway/gpio_ebu.c
@@ -0,0 +1,126 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/platform_device.h>
+#include <linux/mutex.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+
+#include <lantiq_soc.h>
+
+/*
+ * By attaching hardware latches to the EBU it is possible to create output
+ * only gpios. This driver configures a special memory address, which when
+ * written to outputs 16 bit to the latches.
+ */
+
+#define LTQ_EBU_BUSCON	0x1e7ff		/* 16 bit access, slowest timing */
+#define LTQ_EBU_WP	0x80000000	/* write protect bit */
+
+/* we keep a shadow value of the last value written to the ebu */
+static int ltq_ebu_gpio_shadow = 0x0;
+static void __iomem *ltq_ebu_gpio_membase;
+
+static void ltq_ebu_apply(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ebu_lock, flags);
+	ltq_ebu_w32(LTQ_EBU_BUSCON, LTQ_EBU_BUSCON1);
+	*((__u16 *)ltq_ebu_gpio_membase) = ltq_ebu_gpio_shadow;
+	ltq_ebu_w32(LTQ_EBU_BUSCON | LTQ_EBU_WP, LTQ_EBU_BUSCON1);
+	spin_unlock_irqrestore(&ebu_lock, flags);
+}
+
+static void ltq_ebu_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	if (value)
+		ltq_ebu_gpio_shadow |= (1 << offset);
+	else
+		ltq_ebu_gpio_shadow &= ~(1 << offset);
+	ltq_ebu_apply();
+}
+
+static int ltq_ebu_direction_output(struct gpio_chip *chip, unsigned offset,
+	int value)
+{
+	ltq_ebu_set(chip, offset, value);
+
+	return 0;
+}
+
+static struct gpio_chip ltq_ebu_chip = {
+	.label = "ltq_ebu",
+	.direction_output = ltq_ebu_direction_output,
+	.set = ltq_ebu_set,
+	.base = 72,
+	.ngpio = 16,
+	.can_sleep = 1,
+	.owner = THIS_MODULE,
+};
+
+static int ltq_ebu_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	if (!res) {
+		dev_err(&pdev->dev, "failed to get memory resource\n");
+		return -ENOENT;
+	}
+
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		resource_size(res), dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev, "failed to request memory resource\n");
+		return -EBUSY;
+	}
+
+	ltq_ebu_gpio_membase = devm_ioremap_nocache(&pdev->dev, res->start,
+		resource_size(res));
+	if (!ltq_ebu_gpio_membase) {
+		dev_err(&pdev->dev, "Failed to ioremap mem region\n");
+		return -ENOMEM;
+	}
+
+	/* grab the default shadow value passed form the platform code */
+	ltq_ebu_gpio_shadow = (unsigned int) pdev->dev.platform_data;
+
+	/* tell the ebu controller which memory address we will be using */
+	ltq_ebu_w32(pdev->resource->start | 0x1, LTQ_EBU_ADDRSEL1);
+
+	/* write protect the region */
+	ltq_ebu_w32(LTQ_EBU_BUSCON | LTQ_EBU_WP, LTQ_EBU_BUSCON1);
+
+	ret = gpiochip_add(&ltq_ebu_chip);
+	if (!ret)
+		ltq_ebu_apply();
+	return ret;
+}
+
+static struct platform_driver ltq_ebu_driver = {
+	.probe = ltq_ebu_probe,
+	.driver = {
+		.name = "ltq_ebu",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init ltq_ebu_init(void)
+{
+	int ret = platform_driver_register(&ltq_ebu_driver);
+
+	if (ret)
+		pr_info("ltq_ebu : Error registering platfom driver!");
+	return ret;
+}
+
+postcore_initcall(ltq_ebu_init);
diff --git a/arch/mips/lantiq/xway/gpio_stp.c b/arch/mips/lantiq/xway/gpio_stp.c
new file mode 100644
index 00000000000..67d59d69034
--- /dev/null
+++ b/arch/mips/lantiq/xway/gpio_stp.c
@@ -0,0 +1,157 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2007 John Crispin <blogic@openwrt.org>
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/platform_device.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+
+#include <lantiq_soc.h>
+
+#define LTQ_STP_CON0		0x00
+#define LTQ_STP_CON1		0x04
+#define LTQ_STP_CPU0		0x08
+#define LTQ_STP_CPU1		0x0C
+#define LTQ_STP_AR		0x10
+
+#define LTQ_STP_CON_SWU		(1 << 31)
+#define LTQ_STP_2HZ		0
+#define LTQ_STP_4HZ		(1 << 23)
+#define LTQ_STP_8HZ		(2 << 23)
+#define LTQ_STP_10HZ		(3 << 23)
+#define LTQ_STP_SPEED_MASK	(0xf << 23)
+#define LTQ_STP_UPD_FPI		(1 << 31)
+#define LTQ_STP_UPD_MASK	(3 << 30)
+#define LTQ_STP_ADSL_SRC	(3 << 24)
+
+#define LTQ_STP_GROUP0		(1 << 0)
+
+#define LTQ_STP_RISING		0
+#define LTQ_STP_FALLING		(1 << 26)
+#define LTQ_STP_EDGE_MASK	(1 << 26)
+
+#define ltq_stp_r32(reg)	__raw_readl(ltq_stp_membase + reg)
+#define ltq_stp_w32(val, reg)	__raw_writel(val, ltq_stp_membase + reg)
+#define ltq_stp_w32_mask(clear, set, reg) \
+		ltq_w32((ltq_r32(ltq_stp_membase + reg) & ~(clear)) | (set), \
+		ltq_stp_membase + (reg))
+
+static int ltq_stp_shadow = 0xffff;
+static void __iomem *ltq_stp_membase;
+
+static void ltq_stp_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	if (value)
+		ltq_stp_shadow |= (1 << offset);
+	else
+		ltq_stp_shadow &= ~(1 << offset);
+	ltq_stp_w32(ltq_stp_shadow, LTQ_STP_CPU0);
+}
+
+static int ltq_stp_direction_output(struct gpio_chip *chip, unsigned offset,
+	int value)
+{
+	ltq_stp_set(chip, offset, value);
+
+	return 0;
+}
+
+static struct gpio_chip ltq_stp_chip = {
+	.label = "ltq_stp",
+	.direction_output = ltq_stp_direction_output,
+	.set = ltq_stp_set,
+	.base = 48,
+	.ngpio = 24,
+	.can_sleep = 1,
+	.owner = THIS_MODULE,
+};
+
+static int ltq_stp_hw_init(void)
+{
+	/* the 3 pins used to control the external stp */
+	ltq_gpio_request(4, 1, 0, 1, "stp-st");
+	ltq_gpio_request(5, 1, 0, 1, "stp-d");
+	ltq_gpio_request(6, 1, 0, 1, "stp-sh");
+
+	/* sane defaults */
+	ltq_stp_w32(0, LTQ_STP_AR);
+	ltq_stp_w32(0, LTQ_STP_CPU0);
+	ltq_stp_w32(0, LTQ_STP_CPU1);
+	ltq_stp_w32(LTQ_STP_CON_SWU, LTQ_STP_CON0);
+	ltq_stp_w32(0, LTQ_STP_CON1);
+
+	/* rising or falling edge */
+	ltq_stp_w32_mask(LTQ_STP_EDGE_MASK, LTQ_STP_FALLING, LTQ_STP_CON0);
+
+	/* per default stp 15-0 are set */
+	ltq_stp_w32_mask(0, LTQ_STP_GROUP0, LTQ_STP_CON1);
+
+	/* stp are update periodically by the FPI bus */
+	ltq_stp_w32_mask(LTQ_STP_UPD_MASK, LTQ_STP_UPD_FPI, LTQ_STP_CON1);
+
+	/* set stp update speed */
+	ltq_stp_w32_mask(LTQ_STP_SPEED_MASK, LTQ_STP_8HZ, LTQ_STP_CON1);
+
+	/* tell the hardware that pin (led) 0 and 1 are controlled
+	 *  by the dsl arc
+	 */
+	ltq_stp_w32_mask(0, LTQ_STP_ADSL_SRC, LTQ_STP_CON0);
+
+	ltq_pmu_enable(PMU_LED);
+	return 0;
+}
+
+static int __devinit ltq_stp_probe(struct platform_device *pdev)
+{
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	int ret = 0;
+
+	if (!res)
+		return -ENOENT;
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		resource_size(res), dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev, "failed to request STP memory\n");
+		return -EBUSY;
+	}
+	ltq_stp_membase = devm_ioremap_nocache(&pdev->dev, res->start,
+		resource_size(res));
+	if (!ltq_stp_membase) {
+		dev_err(&pdev->dev, "failed to remap STP memory\n");
+		return -ENOMEM;
+	}
+	ret = gpiochip_add(&ltq_stp_chip);
+	if (!ret)
+		ret = ltq_stp_hw_init();
+
+	return ret;
+}
+
+static struct platform_driver ltq_stp_driver = {
+	.probe = ltq_stp_probe,
+	.driver = {
+		.name = "ltq_stp",
+		.owner = THIS_MODULE,
+	},
+};
+
+int __init ltq_stp_init(void)
+{
+	int ret = platform_driver_register(&ltq_stp_driver);
+
+	if (ret)
+		pr_info("ltq_stp: error registering platfom driver");
+	return ret;
+}
+
+postcore_initcall(ltq_stp_init);
diff --git a/arch/mips/lantiq/xway/mach-easy50601.c b/arch/mips/lantiq/xway/mach-easy50601.c
new file mode 100644
index 00000000000..d5aaf637ab1
--- /dev/null
+++ b/arch/mips/lantiq/xway/mach-easy50601.c
@@ -0,0 +1,57 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <linux/input.h>
+
+#include <lantiq.h>
+
+#include "../machtypes.h"
+#include "devices.h"
+
+static struct mtd_partition easy50601_partitions[] = {
+	{
+		.name	= "uboot",
+		.offset	= 0x0,
+		.size	= 0x10000,
+	},
+	{
+		.name	= "uboot_env",
+		.offset	= 0x10000,
+		.size	= 0x10000,
+	},
+	{
+		.name	= "linux",
+		.offset	= 0x20000,
+		.size	= 0xE0000,
+	},
+	{
+		.name	= "rootfs",
+		.offset	= 0x100000,
+		.size	= 0x300000,
+	},
+};
+
+static struct physmap_flash_data easy50601_flash_data = {
+	.nr_parts	= ARRAY_SIZE(easy50601_partitions),
+	.parts		= easy50601_partitions,
+};
+
+static void __init easy50601_init(void)
+{
+	ltq_register_nor(&easy50601_flash_data);
+}
+
+MIPS_MACHINE(LTQ_MACH_EASY50601,
+			"EASY50601",
+			"EASY50601 Eval Board",
+			easy50601_init);
diff --git a/arch/mips/lantiq/xway/mach-easy50712.c b/arch/mips/lantiq/xway/mach-easy50712.c
new file mode 100644
index 00000000000..ea5027b3239
--- /dev/null
+++ b/arch/mips/lantiq/xway/mach-easy50712.c
@@ -0,0 +1,74 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <linux/input.h>
+#include <linux/phy.h>
+
+#include <lantiq_soc.h>
+#include <irq.h>
+
+#include "../machtypes.h"
+#include "devices.h"
+
+static struct mtd_partition easy50712_partitions[] = {
+	{
+		.name	= "uboot",
+		.offset	= 0x0,
+		.size	= 0x10000,
+	},
+	{
+		.name	= "uboot_env",
+		.offset	= 0x10000,
+		.size	= 0x10000,
+	},
+	{
+		.name	= "linux",
+		.offset	= 0x20000,
+		.size	= 0xe0000,
+	},
+	{
+		.name	= "rootfs",
+		.offset	= 0x100000,
+		.size	= 0x300000,
+	},
+};
+
+static struct physmap_flash_data easy50712_flash_data = {
+	.nr_parts	= ARRAY_SIZE(easy50712_partitions),
+	.parts		= easy50712_partitions,
+};
+
+static struct ltq_pci_data ltq_pci_data = {
+	.clock	= PCI_CLOCK_INT,
+	.gpio	= PCI_GNT1 | PCI_REQ1,
+	.irq	= {
+		[14] = INT_NUM_IM0_IRL0 + 22,
+	},
+};
+
+static struct ltq_eth_data ltq_eth_data = {
+	.mii_mode = PHY_INTERFACE_MODE_MII,
+};
+
+static void __init easy50712_init(void)
+{
+	ltq_register_gpio_stp();
+	ltq_register_nor(&easy50712_flash_data);
+	ltq_register_pci(&ltq_pci_data);
+	ltq_register_etop(&ltq_eth_data);
+}
+
+MIPS_MACHINE(LTQ_MACH_EASY50712,
+	     "EASY50712",
+	     "EASY50712 Eval Board",
+	      easy50712_init);
diff --git a/arch/mips/lantiq/xway/pmu.c b/arch/mips/lantiq/xway/pmu.c
new file mode 100644
index 00000000000..9d69f01e352
--- /dev/null
+++ b/arch/mips/lantiq/xway/pmu.c
@@ -0,0 +1,70 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/ioport.h>
+
+#include <lantiq_soc.h>
+
+/* PMU - the power management unit allows us to turn part of the core
+ * on and off
+ */
+
+/* the enable / disable registers */
+#define LTQ_PMU_PWDCR	0x1C
+#define LTQ_PMU_PWDSR	0x20
+
+#define ltq_pmu_w32(x, y)	ltq_w32((x), ltq_pmu_membase + (y))
+#define ltq_pmu_r32(x)		ltq_r32(ltq_pmu_membase + (x))
+
+static struct resource ltq_pmu_resource = {
+	.name	= "pmu",
+	.start	= LTQ_PMU_BASE_ADDR,
+	.end	= LTQ_PMU_BASE_ADDR + LTQ_PMU_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static void __iomem *ltq_pmu_membase;
+
+void ltq_pmu_enable(unsigned int module)
+{
+	int err = 1000000;
+
+	ltq_pmu_w32(ltq_pmu_r32(LTQ_PMU_PWDCR) & ~module, LTQ_PMU_PWDCR);
+	do {} while (--err && (ltq_pmu_r32(LTQ_PMU_PWDSR) & module));
+
+	if (!err)
+		panic("activating PMU module failed!\n");
+}
+EXPORT_SYMBOL(ltq_pmu_enable);
+
+void ltq_pmu_disable(unsigned int module)
+{
+	ltq_pmu_w32(ltq_pmu_r32(LTQ_PMU_PWDCR) | module, LTQ_PMU_PWDCR);
+}
+EXPORT_SYMBOL(ltq_pmu_disable);
+
+int __init ltq_pmu_init(void)
+{
+	if (insert_resource(&iomem_resource, &ltq_pmu_resource) < 0)
+		panic("Failed to insert pmu memory\n");
+
+	if (request_mem_region(ltq_pmu_resource.start,
+			resource_size(&ltq_pmu_resource), "pmu") < 0)
+		panic("Failed to request pmu memory\n");
+
+	ltq_pmu_membase = ioremap_nocache(ltq_pmu_resource.start,
+				resource_size(&ltq_pmu_resource));
+	if (!ltq_pmu_membase)
+		panic("Failed to remap pmu memory\n");
+	return 0;
+}
+
+core_initcall(ltq_pmu_init);
diff --git a/arch/mips/lantiq/xway/prom-ase.c b/arch/mips/lantiq/xway/prom-ase.c
new file mode 100644
index 00000000000..abe49f4db57
--- /dev/null
+++ b/arch/mips/lantiq/xway/prom-ase.c
@@ -0,0 +1,39 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <asm/bootinfo.h>
+#include <asm/time.h>
+
+#include <lantiq_soc.h>
+
+#include "../prom.h"
+
+#define SOC_AMAZON_SE	"Amazon_SE"
+
+#define PART_SHIFT	12
+#define PART_MASK	0x0FFFFFFF
+#define REV_SHIFT	28
+#define REV_MASK	0xF0000000
+
+void __init ltq_soc_detect(struct ltq_soc_info *i)
+{
+	i->partnum = (ltq_r32(LTQ_MPS_CHIPID) & PART_MASK) >> PART_SHIFT;
+	i->rev = (ltq_r32(LTQ_MPS_CHIPID) & REV_MASK) >> REV_SHIFT;
+	switch (i->partnum) {
+	case SOC_ID_AMAZON_SE:
+		i->name = SOC_AMAZON_SE;
+		i->type = SOC_TYPE_AMAZON_SE;
+		break;
+
+	default:
+		unreachable();
+		break;
+	}
+}
diff --git a/arch/mips/lantiq/xway/prom-xway.c b/arch/mips/lantiq/xway/prom-xway.c
new file mode 100644
index 00000000000..1686692ac24
--- /dev/null
+++ b/arch/mips/lantiq/xway/prom-xway.c
@@ -0,0 +1,54 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <asm/bootinfo.h>
+#include <asm/time.h>
+
+#include <lantiq_soc.h>
+
+#include "../prom.h"
+
+#define SOC_DANUBE	"Danube"
+#define SOC_TWINPASS	"Twinpass"
+#define SOC_AR9		"AR9"
+
+#define PART_SHIFT	12
+#define PART_MASK	0x0FFFFFFF
+#define REV_SHIFT	28
+#define REV_MASK	0xF0000000
+
+void __init ltq_soc_detect(struct ltq_soc_info *i)
+{
+	i->partnum = (ltq_r32(LTQ_MPS_CHIPID) & PART_MASK) >> PART_SHIFT;
+	i->rev = (ltq_r32(LTQ_MPS_CHIPID) & REV_MASK) >> REV_SHIFT;
+	switch (i->partnum) {
+	case SOC_ID_DANUBE1:
+	case SOC_ID_DANUBE2:
+		i->name = SOC_DANUBE;
+		i->type = SOC_TYPE_DANUBE;
+		break;
+
+	case SOC_ID_TWINPASS:
+		i->name = SOC_TWINPASS;
+		i->type = SOC_TYPE_DANUBE;
+		break;
+
+	case SOC_ID_ARX188:
+	case SOC_ID_ARX168:
+	case SOC_ID_ARX182:
+		i->name = SOC_AR9;
+		i->type = SOC_TYPE_AR9;
+		break;
+
+	default:
+		unreachable();
+		break;
+	}
+}
diff --git a/arch/mips/lantiq/xway/reset.c b/arch/mips/lantiq/xway/reset.c
new file mode 100644
index 00000000000..a1be36d0e49
--- /dev/null
+++ b/arch/mips/lantiq/xway/reset.c
@@ -0,0 +1,91 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/pm.h>
+#include <linux/module.h>
+#include <asm/reboot.h>
+
+#include <lantiq_soc.h>
+
+#define ltq_rcu_w32(x, y)	ltq_w32((x), ltq_rcu_membase + (y))
+#define ltq_rcu_r32(x)		ltq_r32(ltq_rcu_membase + (x))
+
+/* register definitions */
+#define LTQ_RCU_RST		0x0010
+#define LTQ_RCU_RST_ALL		0x40000000
+
+#define LTQ_RCU_RST_STAT	0x0014
+#define LTQ_RCU_STAT_SHIFT	26
+
+static struct resource ltq_rcu_resource = {
+	.name   = "rcu",
+	.start  = LTQ_RCU_BASE_ADDR,
+	.end    = LTQ_RCU_BASE_ADDR + LTQ_RCU_SIZE - 1,
+	.flags  = IORESOURCE_MEM,
+};
+
+/* remapped base addr of the reset control unit */
+static void __iomem *ltq_rcu_membase;
+
+/* This function is used by the watchdog driver */
+int ltq_reset_cause(void)
+{
+	u32 val = ltq_rcu_r32(LTQ_RCU_RST_STAT);
+	return val >> LTQ_RCU_STAT_SHIFT;
+}
+EXPORT_SYMBOL_GPL(ltq_reset_cause);
+
+static void ltq_machine_restart(char *command)
+{
+	pr_notice("System restart\n");
+	local_irq_disable();
+	ltq_rcu_w32(ltq_rcu_r32(LTQ_RCU_RST) | LTQ_RCU_RST_ALL, LTQ_RCU_RST);
+	unreachable();
+}
+
+static void ltq_machine_halt(void)
+{
+	pr_notice("System halted.\n");
+	local_irq_disable();
+	unreachable();
+}
+
+static void ltq_machine_power_off(void)
+{
+	pr_notice("Please turn off the power now.\n");
+	local_irq_disable();
+	unreachable();
+}
+
+static int __init mips_reboot_setup(void)
+{
+	/* insert and request the memory region */
+	if (insert_resource(&iomem_resource, &ltq_rcu_resource) < 0)
+		panic("Failed to insert rcu memory\n");
+
+	if (request_mem_region(ltq_rcu_resource.start,
+			resource_size(&ltq_rcu_resource), "rcu") < 0)
+		panic("Failed to request rcu memory\n");
+
+	/* remap rcu register range */
+	ltq_rcu_membase = ioremap_nocache(ltq_rcu_resource.start,
+				resource_size(&ltq_rcu_resource));
+	if (!ltq_rcu_membase)
+		panic("Failed to remap rcu memory\n");
+
+	_machine_restart = ltq_machine_restart;
+	_machine_halt = ltq_machine_halt;
+	pm_power_off = ltq_machine_power_off;
+
+	return 0;
+}
+
+arch_initcall(mips_reboot_setup);
diff --git a/arch/mips/lantiq/xway/setup-ase.c b/arch/mips/lantiq/xway/setup-ase.c
new file mode 100644
index 00000000000..f6f326798a3
--- /dev/null
+++ b/arch/mips/lantiq/xway/setup-ase.c
@@ -0,0 +1,19 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#include <lantiq_soc.h>
+
+#include "../prom.h"
+#include "devices.h"
+
+void __init ltq_soc_setup(void)
+{
+	ltq_register_ase_asc();
+	ltq_register_gpio();
+	ltq_register_wdt();
+}
diff --git a/arch/mips/lantiq/xway/setup-xway.c b/arch/mips/lantiq/xway/setup-xway.c
new file mode 100644
index 00000000000..c292f643a85
--- /dev/null
+++ b/arch/mips/lantiq/xway/setup-xway.c
@@ -0,0 +1,20 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#include <lantiq_soc.h>
+
+#include "../prom.h"
+#include "devices.h"
+
+void __init ltq_soc_setup(void)
+{
+	ltq_register_asc(0);
+	ltq_register_asc(1);
+	ltq_register_gpio();
+	ltq_register_wdt();
+}
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 2adead5a8a3..b2cad4fd5fc 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX49XX)	+= dump_tlb.o
 obj-$(CONFIG_CPU_VR41XX)	+= dump_tlb.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= dump_tlb.o
+obj-$(CONFIG_CPU_XLR)		+= dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
 obj-y += ashldi3.o ashrdi3.o cmpdi2.o lshrdi3.o ucmpdi2.o
diff --git a/arch/mips/loongson/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson/common/cs5536/cs5536_mfgpt.c
index 8c807c96519..0cb1b9760e3 100644
--- a/arch/mips/loongson/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson/common/cs5536/cs5536_mfgpt.c
@@ -201,8 +201,6 @@ static struct clocksource clocksource_mfgpt = {
 	.rating = 120, /* Functional for real use, but not desired */
 	.read = mfgpt_read,
 	.mask = CLOCKSOURCE_MASK(32),
-	.mult = 0,
-	.shift = 22,
 };
 
 int __init init_mfgpt_clocksource(void)
@@ -210,8 +208,7 @@ int __init init_mfgpt_clocksource(void)
 	if (num_possible_cpus() > 1)	/* MFGPT does not scale! */
 		return 0;
 
-	clocksource_mfgpt.mult = clocksource_hz2mult(MFGPT_TICK_RATE, 22);
-	return clocksource_register(&clocksource_mfgpt);
+	return clocksource_register_hz(&clocksource_mfgpt, MFGPT_TICK_RATE);
 }
 
 arch_initcall(init_mfgpt_clocksource);
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index d679c772d08..4d8c1623eee 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,7 +3,8 @@
 #
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
-				   init.o tlbex.o tlbex-fault.o uasm.o page.o
+				   init.o mmap.o tlbex.o tlbex-fault.o uasm.o \
+				   page.o
 
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
@@ -29,6 +30,7 @@ obj-$(CONFIG_CPU_TX39XX)	+= c-tx39.o tlb-r3k.o
 obj-$(CONFIG_CPU_TX49XX)	+= c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_VR41XX)	+= c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= c-octeon.o cex-oct.o tlb-r4k.o
+obj-$(CONFIG_CPU_XLR)		+= c-r4k.o tlb-r4k.o cex-gen.o
 
 obj-$(CONFIG_IP22_CPU_SCACHE)	+= sc-ip22.o
 obj-$(CONFIG_R5000_CPU_SCACHE)  += sc-r5k.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 71bddf8f7d2..d9bc5d3593b 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1006,6 +1006,7 @@ static void __cpuinit probe_pcache(void)
 	case CPU_25KF:
 	case CPU_SB1:
 	case CPU_SB1A:
+	case CPU_XLR:
 		c->dcache.flags |= MIPS_CACHE_PINDEX;
 		break;
 
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
new file mode 100644
index 00000000000..ae3c20a9556
--- /dev/null
+++ b/arch/mips/mm/mmap.c
@@ -0,0 +1,122 @@
+/*
+ * 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) 2011 Wind River Systems,
+ *   written by Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+
+unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
+
+EXPORT_SYMBOL(shm_align_mask);
+
+#define COLOUR_ALIGN(addr,pgoff)				\
+	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
+	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
+
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+	unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct vm_area_struct * vmm;
+	int do_color_align;
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		/* Even MAP_FIXED mappings must reside within TASK_SIZE.  */
+		if (TASK_SIZE - len < addr)
+			return -EINVAL;
+
+		/*
+		 * We do not accept a shared mapping if it would violate
+		 * cache aliasing constraints.
+		 */
+		if ((flags & MAP_SHARED) &&
+		    ((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
+			return -EINVAL;
+		return addr;
+	}
+
+	do_color_align = 0;
+	if (filp || (flags & MAP_SHARED))
+		do_color_align = 1;
+	if (addr) {
+		if (do_color_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+		vmm = find_vma(current->mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vmm || addr + len <= vmm->vm_start))
+			return addr;
+	}
+	addr = current->mm->mmap_base;
+	if (do_color_align)
+		addr = COLOUR_ALIGN(addr, pgoff);
+	else
+		addr = PAGE_ALIGN(addr);
+
+	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
+		/* At this point:  (!vmm || addr < vmm->vm_end). */
+		if (TASK_SIZE - len < addr)
+			return -ENOMEM;
+		if (!vmm || addr + len <= vmm->vm_start)
+			return addr;
+		addr = vmm->vm_end;
+		if (do_color_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+	}
+}
+
+void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE) {
+		random_factor = get_random_int();
+		random_factor = random_factor << PAGE_SHIFT;
+		if (TASK_IS_32BIT_ADDR)
+			random_factor &= 0xfffffful;
+		else
+			random_factor &= 0xffffffful;
+	}
+
+	mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
+	mm->get_unmapped_area = arch_get_unmapped_area;
+	mm->unmap_area = arch_unmap_area;
+}
+
+static inline unsigned long brk_rnd(void)
+{
+	unsigned long rnd = get_random_int();
+
+	rnd = rnd << PAGE_SHIFT;
+	/* 8MB for 32bit, 256MB for 64bit */
+	if (TASK_IS_32BIT_ADDR)
+		rnd = rnd & 0x7ffffful;
+	else
+		rnd = rnd & 0xffffffful;
+
+	return rnd;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long base = mm->brk;
+	unsigned long ret;
+
+	ret = PAGE_ALIGN(base + brk_rnd());
+
+	if (ret < mm->brk)
+		return mm->brk;
+
+	return ret;
+}
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index f5734c2c809..424ed4b92e6 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -404,6 +404,7 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_5KC:
 	case CPU_TX49XX:
 	case CPU_PR4450:
+	case CPU_XLR:
 		uasm_i_nop(p);
 		tlbw(p);
 		break;
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index e85c977328d..1d36c511a7a 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -308,6 +308,8 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
+	scheduler_ipi();
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
new file mode 100644
index 00000000000..a5ca743613f
--- /dev/null
+++ b/arch/mips/netlogic/Kconfig
@@ -0,0 +1,5 @@
+config NLM_COMMON
+	bool
+
+config NLM_XLR
+	bool
diff --git a/arch/mips/netlogic/xlr/Makefile b/arch/mips/netlogic/xlr/Makefile
new file mode 100644
index 00000000000..9bd3f731f62
--- /dev/null
+++ b/arch/mips/netlogic/xlr/Makefile
@@ -0,0 +1,5 @@
+obj-y				+= setup.o platform.o irq.o setup.o time.o
+obj-$(CONFIG_SMP)		+= smp.o smpboot.o
+obj-$(CONFIG_EARLY_PRINTK)	+= xlr_console.o
+
+EXTRA_CFLAGS			+= -Werror
diff --git a/arch/mips/netlogic/xlr/irq.c b/arch/mips/netlogic/xlr/irq.c
new file mode 100644
index 00000000000..1446d58e364
--- /dev/null
+++ b/arch/mips/netlogic/xlr/irq.c
@@ -0,0 +1,300 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+
+#include <asm/mipsregs.h>
+
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/pic.h>
+#include <asm/netlogic/xlr/xlr.h>
+
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/mips-extns.h>
+
+static u64 nlm_irq_mask;
+static DEFINE_SPINLOCK(nlm_pic_lock);
+
+static void xlr_pic_enable(struct irq_data *d)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+	unsigned long flags;
+	nlm_reg_t reg;
+	int irq = d->irq;
+
+	WARN(!PIC_IRQ_IS_IRT(irq), "Bad irq %d", irq);
+
+	spin_lock_irqsave(&nlm_pic_lock, flags);
+	reg = netlogic_read_reg(mmio, PIC_IRT_1_BASE + irq - PIC_IRQ_BASE);
+	netlogic_write_reg(mmio, PIC_IRT_1_BASE + irq - PIC_IRQ_BASE,
+			  reg | (1 << 6) | (1 << 30) | (1 << 31));
+	spin_unlock_irqrestore(&nlm_pic_lock, flags);
+}
+
+static void xlr_pic_mask(struct irq_data *d)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+	unsigned long flags;
+	nlm_reg_t reg;
+	int irq = d->irq;
+
+	WARN(!PIC_IRQ_IS_IRT(irq), "Bad irq %d", irq);
+
+	spin_lock_irqsave(&nlm_pic_lock, flags);
+	reg = netlogic_read_reg(mmio, PIC_IRT_1_BASE + irq - PIC_IRQ_BASE);
+	netlogic_write_reg(mmio, PIC_IRT_1_BASE + irq - PIC_IRQ_BASE,
+			  reg | (1 << 6) | (1 << 30) | (0 << 31));
+	spin_unlock_irqrestore(&nlm_pic_lock, flags);
+}
+
+#ifdef CONFIG_PCI
+/* Extra ACK needed for XLR on chip PCI controller */
+static void xlr_pci_ack(struct irq_data *d)
+{
+	nlm_reg_t *pci_mmio = netlogic_io_mmio(NETLOGIC_IO_PCIX_OFFSET);
+
+	netlogic_read_reg(pci_mmio, (0x140 >> 2));
+}
+
+/* Extra ACK needed for XLS on chip PCIe controller */
+static void xls_pcie_ack(struct irq_data *d)
+{
+	nlm_reg_t *pcie_mmio_le = netlogic_io_mmio(NETLOGIC_IO_PCIE_1_OFFSET);
+
+	switch (d->irq) {
+	case PIC_PCIE_LINK0_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x90 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_LINK1_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x94 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_LINK2_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x190 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_LINK3_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x194 >> 2), 0xffffffff);
+		break;
+	}
+}
+
+/* For XLS B silicon, the 3,4 PCI interrupts are different */
+static void xls_pcie_ack_b(struct irq_data *d)
+{
+	nlm_reg_t *pcie_mmio_le = netlogic_io_mmio(NETLOGIC_IO_PCIE_1_OFFSET);
+
+	switch (d->irq) {
+	case PIC_PCIE_LINK0_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x90 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_LINK1_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x94 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_XLSB0_LINK2_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x190 >> 2), 0xffffffff);
+		break;
+	case PIC_PCIE_XLSB0_LINK3_IRQ:
+		netlogic_write_reg(pcie_mmio_le, (0x194 >> 2), 0xffffffff);
+		break;
+	}
+}
+#endif
+
+static void xlr_pic_ack(struct irq_data *d)
+{
+	unsigned long flags;
+	nlm_reg_t *mmio;
+	int irq = d->irq;
+	void *hd = irq_data_get_irq_handler_data(d);
+
+	WARN(!PIC_IRQ_IS_IRT(irq), "Bad irq %d", irq);
+
+	if (hd) {
+		void (*extra_ack)(void *) = hd;
+		extra_ack(d);
+	}
+	mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+	spin_lock_irqsave(&nlm_pic_lock, flags);
+	netlogic_write_reg(mmio, PIC_INT_ACK, (1 << (irq - PIC_IRQ_BASE)));
+	spin_unlock_irqrestore(&nlm_pic_lock, flags);
+}
+
+/*
+ * This chip definition handles interrupts routed thru the XLR
+ * hardware PIC, currently IRQs 8-39 are mapped to hardware intr
+ * 0-31 wired the XLR PIC
+ */
+static struct irq_chip xlr_pic = {
+	.name		= "XLR-PIC",
+	.irq_enable	= xlr_pic_enable,
+	.irq_mask	= xlr_pic_mask,
+	.irq_ack	= xlr_pic_ack,
+};
+
+static void rsvd_irq_handler(struct irq_data *d)
+{
+	WARN(d->irq >= PIC_IRQ_BASE, "Bad irq %d", d->irq);
+}
+
+/*
+ * Chip definition for CPU originated interrupts(timer, msg) and
+ * IPIs
+ */
+struct irq_chip nlm_cpu_intr = {
+	.name		= "XLR-CPU-INTR",
+	.irq_enable	= rsvd_irq_handler,
+	.irq_mask	= rsvd_irq_handler,
+	.irq_ack	= rsvd_irq_handler,
+};
+
+void __init init_xlr_irqs(void)
+{
+	nlm_reg_t *mmio = netlogic_io_mmio(NETLOGIC_IO_PIC_OFFSET);
+	uint32_t thread_mask = 1;
+	int level, i;
+
+	pr_info("Interrupt thread mask [%x]\n", thread_mask);
+	for (i = 0; i < PIC_NUM_IRTS; i++) {
+		level = PIC_IRQ_IS_EDGE_TRIGGERED(i);
+
+		/* Bind all PIC irqs to boot cpu */
+		netlogic_write_reg(mmio, PIC_IRT_0_BASE + i, thread_mask);
+
+		/*
+		 * Use local scheduling and high polarity for all IRTs
+		 * Invalidate all IRTs, by default
+		 */
+		netlogic_write_reg(mmio, PIC_IRT_1_BASE + i,
+				(level << 30) | (1 << 6) | (PIC_IRQ_BASE + i));
+	}
+
+	/* Make all IRQs as level triggered by default */
+	for (i = 0; i < NR_IRQS; i++) {
+		if (PIC_IRQ_IS_IRT(i))
+			irq_set_chip_and_handler(i, &xlr_pic, handle_level_irq);
+		else
+			irq_set_chip_and_handler(i, &nlm_cpu_intr,
+						handle_level_irq);
+	}
+#ifdef CONFIG_SMP
+	irq_set_chip_and_handler(IRQ_IPI_SMP_FUNCTION, &nlm_cpu_intr,
+			 nlm_smp_function_ipi_handler);
+	irq_set_chip_and_handler(IRQ_IPI_SMP_RESCHEDULE, &nlm_cpu_intr,
+			 nlm_smp_resched_ipi_handler);
+	nlm_irq_mask |=
+	    ((1ULL << IRQ_IPI_SMP_FUNCTION) | (1ULL << IRQ_IPI_SMP_RESCHEDULE));
+#endif
+
+#ifdef CONFIG_PCI
+	/*
+	 * For PCI interrupts, we need to ack the PIC controller too, overload
+	 * irq handler data to do this
+	 */
+	if (nlm_chip_is_xls()) {
+		if (nlm_chip_is_xls_b()) {
+			irq_set_handler_data(PIC_PCIE_LINK0_IRQ,
+							xls_pcie_ack_b);
+			irq_set_handler_data(PIC_PCIE_LINK1_IRQ,
+							xls_pcie_ack_b);
+			irq_set_handler_data(PIC_PCIE_XLSB0_LINK2_IRQ,
+							xls_pcie_ack_b);
+			irq_set_handler_data(PIC_PCIE_XLSB0_LINK3_IRQ,
+							xls_pcie_ack_b);
+		} else {
+			irq_set_handler_data(PIC_PCIE_LINK0_IRQ, xls_pcie_ack);
+			irq_set_handler_data(PIC_PCIE_LINK1_IRQ, xls_pcie_ack);
+			irq_set_handler_data(PIC_PCIE_LINK2_IRQ, xls_pcie_ack);
+			irq_set_handler_data(PIC_PCIE_LINK3_IRQ, xls_pcie_ack);
+		}
+	} else {
+		/* XLR PCI controller ACK */
+		irq_set_handler_data(PIC_PCIE_XLSB0_LINK3_IRQ, xlr_pci_ack);
+	}
+#endif
+	/* unmask all PIC related interrupts. If no handler is installed by the
+	 * drivers, it'll just ack the interrupt and return
+	 */
+	for (i = PIC_IRT_FIRST_IRQ; i <= PIC_IRT_LAST_IRQ; i++)
+		nlm_irq_mask |= (1ULL << i);
+
+	nlm_irq_mask |= (1ULL << IRQ_TIMER);
+}
+
+void __init arch_init_irq(void)
+{
+	/* Initialize the irq descriptors */
+	init_xlr_irqs();
+	write_c0_eimr(nlm_irq_mask);
+}
+
+void __cpuinit nlm_smp_irq_init(void)
+{
+	/* set interrupt mask for non-zero cpus */
+	write_c0_eimr(nlm_irq_mask);
+}
+
+asmlinkage void plat_irq_dispatch(void)
+{
+	uint64_t eirr;
+	int i;
+
+	eirr = read_c0_eirr() & read_c0_eimr();
+	if (!eirr)
+		return;
+
+	/* no need of EIRR here, writing compare clears interrupt */
+	if (eirr & (1 << IRQ_TIMER)) {
+		do_IRQ(IRQ_TIMER);
+		return;
+	}
+
+	/* use dcltz: optimize below code */
+	for (i = 63; i != -1; i--) {
+		if (eirr & (1ULL << i))
+			break;
+	}
+	if (i == -1) {
+		pr_err("no interrupt !!\n");
+		return;
+	}
+
+	/* Ack eirr */
+	write_c0_eirr(1ULL << i);
+
+	do_IRQ(i);
+}
diff --git a/arch/mips/netlogic/xlr/platform.c b/arch/mips/netlogic/xlr/platform.c
new file mode 100644
index 00000000000..609ec253464
--- /dev/null
+++ b/arch/mips/netlogic/xlr/platform.c
@@ -0,0 +1,98 @@
+/*
+ * Copyright 2011, Netlogic Microsystems.
+ * Copyright 2004, Matt Porter <mporter@kernel.crashing.org>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/resource.h>
+#include <linux/serial_8250.h>
+#include <linux/serial_reg.h>
+
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/pic.h>
+#include <asm/netlogic/xlr/xlr.h>
+
+unsigned int nlm_xlr_uart_in(struct uart_port *p, int offset)
+{
+	nlm_reg_t *mmio;
+	unsigned int value;
+
+	/* XLR uart does not need any mapping of regs */
+	mmio = (nlm_reg_t *)(p->membase + (offset << p->regshift));
+	value = netlogic_read_reg(mmio, 0);
+
+	/* See XLR/XLS errata */
+	if (offset == UART_MSR)
+		value ^= 0xF0;
+	else if (offset == UART_MCR)
+		value ^= 0x3;
+
+	return value;
+}
+
+void nlm_xlr_uart_out(struct uart_port *p, int offset, int value)
+{
+	nlm_reg_t *mmio;
+
+	/* XLR uart does not need any mapping of regs */
+	mmio = (nlm_reg_t *)(p->membase + (offset << p->regshift));
+
+	/* See XLR/XLS errata */
+	if (offset == UART_MSR)
+		value ^= 0xF0;
+	else if (offset == UART_MCR)
+		value ^= 0x3;
+
+	netlogic_write_reg(mmio, 0, value);
+}
+
+#define PORT(_irq)					\
+	{						\
+		.irq		= _irq,			\
+		.regshift	= 2,			\
+		.iotype		= UPIO_MEM32,		\
+		.flags		= (UPF_SKIP_TEST |	\
+			 UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF),\
+		.uartclk	= PIC_CLKS_PER_SEC,	\
+		.type		= PORT_16550A,		\
+		.serial_in	= nlm_xlr_uart_in,	\
+		.serial_out	= nlm_xlr_uart_out,	\
+	}
+
+static struct plat_serial8250_port xlr_uart_data[] = {
+	PORT(PIC_UART_0_IRQ),
+	PORT(PIC_UART_1_IRQ),
+	{},
+};
+
+static struct platform_device uart_device = {
+	.name		= "serial8250",
+	.id		= PLAT8250_DEV_PLATFORM,
+	.dev = {
+		.platform_data = xlr_uart_data,
+	},
+};
+
+static int __init nlm_uart_init(void)
+{
+	nlm_reg_t *mmio;
+
+	mmio = netlogic_io_mmio(NETLOGIC_IO_UART_0_OFFSET);
+	xlr_uart_data[0].membase = (void __iomem *)mmio;
+	xlr_uart_data[0].mapbase = CPHYSADDR((unsigned long)mmio);
+
+	mmio = netlogic_io_mmio(NETLOGIC_IO_UART_1_OFFSET);
+	xlr_uart_data[1].membase = (void __iomem *)mmio;
+	xlr_uart_data[1].mapbase = CPHYSADDR((unsigned long)mmio);
+
+	return platform_device_register(&uart_device);
+}
+
+arch_initcall(nlm_uart_init);
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
new file mode 100644
index 00000000000..482802569e7
--- /dev/null
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -0,0 +1,188 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/serial_8250.h>
+#include <linux/pm.h>
+
+#include <asm/reboot.h>
+#include <asm/time.h>
+#include <asm/bootinfo.h>
+#include <asm/smp-ops.h>
+
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/psb-bootinfo.h>
+
+#include <asm/netlogic/xlr/xlr.h>
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/pic.h>
+#include <asm/netlogic/xlr/gpio.h>
+
+unsigned long netlogic_io_base = (unsigned long)(DEFAULT_NETLOGIC_IO_BASE);
+unsigned long nlm_common_ebase = 0x0;
+struct psb_info nlm_prom_info;
+
+static void nlm_early_serial_setup(void)
+{
+	struct uart_port s;
+	nlm_reg_t *uart_base;
+
+	uart_base = netlogic_io_mmio(NETLOGIC_IO_UART_0_OFFSET);
+	memset(&s, 0, sizeof(s));
+	s.flags		= ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST;
+	s.iotype	= UPIO_MEM32;
+	s.regshift	= 2;
+	s.irq		= PIC_UART_0_IRQ;
+	s.uartclk	= PIC_CLKS_PER_SEC;
+	s.serial_in	= nlm_xlr_uart_in;
+	s.serial_out	= nlm_xlr_uart_out;
+	s.mapbase	= (unsigned long)uart_base;
+	s.membase	= (unsigned char __iomem *)uart_base;
+	early_serial_setup(&s);
+}
+
+static void nlm_linux_exit(void)
+{
+	nlm_reg_t *mmio;
+
+	mmio = netlogic_io_mmio(NETLOGIC_IO_GPIO_OFFSET);
+	/* trigger a chip reset by writing 1 to GPIO_SWRESET_REG */
+	netlogic_write_reg(mmio, NETLOGIC_GPIO_SWRESET_REG, 1);
+	for ( ; ; )
+		cpu_wait();
+}
+
+void __init plat_mem_setup(void)
+{
+	panic_timeout	= 5;
+	_machine_restart = (void (*)(char *))nlm_linux_exit;
+	_machine_halt	= nlm_linux_exit;
+	pm_power_off	= nlm_linux_exit;
+}
+
+const char *get_system_type(void)
+{
+	return "Netlogic XLR/XLS Series";
+}
+
+void __init prom_free_prom_memory(void)
+{
+	/* Nothing yet */
+}
+
+static void build_arcs_cmdline(int *argv)
+{
+	int i, remain, len;
+	char *arg;
+
+	remain = sizeof(arcs_cmdline) - 1;
+	arcs_cmdline[0] = '\0';
+	for (i = 0; argv[i] != 0; i++) {
+		arg = (char *)(long)argv[i];
+		len = strlen(arg);
+		if (len + 1 > remain)
+			break;
+		strcat(arcs_cmdline, arg);
+		strcat(arcs_cmdline, " ");
+		remain -=  len + 1;
+	}
+
+	/* Add the default options here */
+	if ((strstr(arcs_cmdline, "console=")) == NULL) {
+		arg = "console=ttyS0,38400 ";
+		len = strlen(arg);
+		if (len > remain)
+			goto fail;
+		strcat(arcs_cmdline, arg);
+		remain -= len;
+	}
+#ifdef CONFIG_BLK_DEV_INITRD
+	if ((strstr(arcs_cmdline, "rdinit=")) == NULL) {
+		arg = "rdinit=/sbin/init ";
+		len = strlen(arg);
+		if (len > remain)
+			goto fail;
+		strcat(arcs_cmdline, arg);
+		remain -= len;
+	}
+#endif
+	return;
+fail:
+	panic("Cannot add %s, command line too big!", arg);
+}
+
+static void prom_add_memory(void)
+{
+	struct nlm_boot_mem_map *bootm;
+	u64 start, size;
+	u64 pref_backup = 512;  /* avoid pref walking beyond end */
+	int i;
+
+	bootm = (void *)(long)nlm_prom_info.psb_mem_map;
+	for (i = 0; i < bootm->nr_map; i++) {
+		if (bootm->map[i].type != BOOT_MEM_RAM)
+			continue;
+		start = bootm->map[i].addr;
+		size   = bootm->map[i].size;
+
+		/* Work around for using bootloader mem */
+		if (i == 0 && start == 0 && size == 0x0c000000)
+			size = 0x0ff00000;
+
+		add_memory_region(start, size - pref_backup, BOOT_MEM_RAM);
+	}
+}
+
+void __init prom_init(void)
+{
+	int *argv, *envp;		/* passed as 32 bit ptrs */
+	struct psb_info *prom_infop;
+
+	/* truncate to 32 bit and sign extend all args */
+	argv = (int *)(long)(int)fw_arg1;
+	envp = (int *)(long)(int)fw_arg2;
+	prom_infop = (struct psb_info *)(long)(int)fw_arg3;
+
+	nlm_prom_info = *prom_infop;
+
+	nlm_early_serial_setup();
+	build_arcs_cmdline(argv);
+	nlm_common_ebase = read_c0_ebase() & (~((1 << 12) - 1));
+	prom_add_memory();
+
+#ifdef CONFIG_SMP
+	nlm_wakeup_secondary_cpus(nlm_prom_info.online_cpu_map);
+	register_smp_ops(&nlm_smp_ops);
+#endif
+}
diff --git a/arch/mips/netlogic/xlr/smp.c b/arch/mips/netlogic/xlr/smp.c
new file mode 100644
index 00000000000..b495a7f1433
--- /dev/null
+++ b/arch/mips/netlogic/xlr/smp.c
@@ -0,0 +1,225 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+
+#include <asm/mmu_context.h>
+
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/mips-extns.h>
+
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/pic.h>
+#include <asm/netlogic/xlr/xlr.h>
+
+void core_send_ipi(int logical_cpu, unsigned int action)
+{
+	int cpu = cpu_logical_map(logical_cpu);
+	u32 tid = cpu & 0x3;
+	u32 pid = (cpu >> 2) & 0x07;
+	u32 ipi = (tid << 16) | (pid << 20);
+
+	if (action & SMP_CALL_FUNCTION)
+		ipi |= IRQ_IPI_SMP_FUNCTION;
+	else if (action & SMP_RESCHEDULE_YOURSELF)
+		ipi |= IRQ_IPI_SMP_RESCHEDULE;
+	else
+		return;
+
+	pic_send_ipi(ipi);
+}
+
+void nlm_send_ipi_single(int cpu, unsigned int action)
+{
+	core_send_ipi(cpu, action);
+}
+
+void nlm_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mask) {
+		core_send_ipi(cpu, action);
+	}
+}
+
+/* IRQ_IPI_SMP_FUNCTION Handler */
+void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc)
+{
+	smp_call_function_interrupt();
+}
+
+/* IRQ_IPI_SMP_RESCHEDULE  handler */
+void nlm_smp_resched_ipi_handler(unsigned int irq, struct irq_desc *desc)
+{
+	set_need_resched();
+}
+
+void nlm_common_ipi_handler(int irq, struct pt_regs *regs)
+{
+	if (irq == IRQ_IPI_SMP_FUNCTION) {
+		smp_call_function_interrupt();
+	} else {
+		/* Announce that we are for reschduling */
+		set_need_resched();
+	}
+}
+
+/*
+ * Called before going into mips code, early cpu init
+ */
+void nlm_early_init_secondary(void)
+{
+	write_c0_ebase((uint32_t)nlm_common_ebase);
+	/* TLB partition here later */
+}
+
+/*
+ * Code to run on secondary just after probing the CPU
+ */
+static void __cpuinit nlm_init_secondary(void)
+{
+	nlm_smp_irq_init();
+}
+
+void nlm_smp_finish(void)
+{
+#ifdef notyet
+	nlm_common_msgring_cpu_init();
+#endif
+}
+
+void nlm_cpus_done(void)
+{
+}
+
+/*
+ * Boot all other cpus in the system, initialize them, and bring them into
+ * the boot function
+ */
+int nlm_cpu_unblock[NR_CPUS];
+int nlm_cpu_ready[NR_CPUS];
+unsigned long nlm_next_gp;
+unsigned long nlm_next_sp;
+cpumask_t phys_cpu_present_map;
+
+void nlm_boot_secondary(int logical_cpu, struct task_struct *idle)
+{
+	unsigned long gp = (unsigned long)task_thread_info(idle);
+	unsigned long sp = (unsigned long)__KSTK_TOS(idle);
+	int cpu = cpu_logical_map(logical_cpu);
+
+	nlm_next_sp = sp;
+	nlm_next_gp = gp;
+
+	/* barrier */
+	__sync();
+	nlm_cpu_unblock[cpu] = 1;
+}
+
+void __init nlm_smp_setup(void)
+{
+	unsigned int boot_cpu;
+	int num_cpus, i;
+
+	boot_cpu = hard_smp_processor_id();
+	cpus_clear(phys_cpu_present_map);
+
+	cpu_set(boot_cpu, phys_cpu_present_map);
+	__cpu_number_map[boot_cpu] = 0;
+	__cpu_logical_map[0] = boot_cpu;
+	cpu_set(0, cpu_possible_map);
+
+	num_cpus = 1;
+	for (i = 0; i < NR_CPUS; i++) {
+		if (nlm_cpu_ready[i]) {
+			cpu_set(i, phys_cpu_present_map);
+			__cpu_number_map[i] = num_cpus;
+			__cpu_logical_map[num_cpus] = i;
+			cpu_set(num_cpus, cpu_possible_map);
+			++num_cpus;
+		}
+	}
+
+	pr_info("Phys CPU present map: %lx, possible map %lx\n",
+		(unsigned long)phys_cpu_present_map.bits[0],
+		(unsigned long)cpu_possible_map.bits[0]);
+
+	pr_info("Detected %i Slave CPU(s)\n", num_cpus);
+}
+
+void nlm_prepare_cpus(unsigned int max_cpus)
+{
+}
+
+struct plat_smp_ops nlm_smp_ops = {
+	.send_ipi_single	= nlm_send_ipi_single,
+	.send_ipi_mask		= nlm_send_ipi_mask,
+	.init_secondary		= nlm_init_secondary,
+	.smp_finish		= nlm_smp_finish,
+	.cpus_done		= nlm_cpus_done,
+	.boot_secondary		= nlm_boot_secondary,
+	.smp_setup		= nlm_smp_setup,
+	.prepare_cpus		= nlm_prepare_cpus,
+};
+
+unsigned long secondary_entry_point;
+
+int nlm_wakeup_secondary_cpus(u32 wakeup_mask)
+{
+	unsigned int tid, pid, ipi, i, boot_cpu;
+	void *reset_vec;
+
+	secondary_entry_point = (unsigned long)prom_pre_boot_secondary_cpus;
+	reset_vec = (void *)CKSEG1ADDR(0x1fc00000);
+	memcpy(reset_vec, nlm_boot_smp_nmi, 0x80);
+	boot_cpu = hard_smp_processor_id();
+
+	for (i = 0; i < NR_CPUS; i++) {
+		if (i == boot_cpu)
+			continue;
+		if (wakeup_mask & (1u << i)) {
+			tid = i & 0x3;
+			pid = (i >> 2) & 0x7;
+			ipi = (tid << 16) | (pid << 20) | (1 << 8);
+			pic_send_ipi(ipi);
+		}
+	}
+
+	return 0;
+}
diff --git a/arch/mips/netlogic/xlr/smpboot.S b/arch/mips/netlogic/xlr/smpboot.S
new file mode 100644
index 00000000000..b8e074402c9
--- /dev/null
+++ b/arch/mips/netlogic/xlr/smpboot.S
@@ -0,0 +1,94 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/regdef.h>
+#include <asm/mipsregs.h>
+
+
+/* Don't jump to linux function from Bootloader stack. Change it
+ * here. Kernel might allocate bootloader memory before all the CPUs are
+ * brought up (eg: Inode cache region) and we better don't overwrite this
+ * memory
+ */
+NESTED(prom_pre_boot_secondary_cpus, 16, sp)
+	.set	mips64
+	mfc0	t0, $15, 1	# read ebase
+	andi	t0, 0x1f	# t0 has the processor_id()
+	sll	t0, 2		# offset in cpu array
+
+	PTR_LA	t1, nlm_cpu_ready # mark CPU ready
+	PTR_ADDU t1, t0
+	li	t2, 1
+	sw	t2, 0(t1)
+
+	PTR_LA	t1, nlm_cpu_unblock
+	PTR_ADDU t1, t0
+1:	lw	t2, 0(t1)	# wait till unblocked
+	beqz	t2, 1b
+	nop
+
+	PTR_LA	t1, nlm_next_sp
+	PTR_L	sp, 0(t1)
+	PTR_LA	t1, nlm_next_gp
+	PTR_L	gp, 0(t1)
+
+	PTR_LA	t0, nlm_early_init_secondary
+	jalr	t0
+	nop
+
+	PTR_LA	t0, smp_bootstrap
+	jr	t0
+	nop
+END(prom_pre_boot_secondary_cpus)
+
+NESTED(nlm_boot_smp_nmi, 0, sp)
+	.set push
+	.set noat
+	.set mips64
+	.set noreorder
+
+	/* Clear the  NMI and BEV bits */
+	MFC0	k0, CP0_STATUS
+	li 	k1, 0xffb7ffff
+	and	k0, k0, k1
+	MTC0	k0, CP0_STATUS
+
+	PTR_LA  k1, secondary_entry_point
+	PTR_L	k0, 0(k1)
+	jr	k0
+	nop
+	.set pop
+END(nlm_boot_smp_nmi)
diff --git a/arch/mips/netlogic/xlr/time.c b/arch/mips/netlogic/xlr/time.c
new file mode 100644
index 00000000000..0d81b262593
--- /dev/null
+++ b/arch/mips/netlogic/xlr/time.c
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/init.h>
+
+#include <asm/time.h>
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/psb-bootinfo.h>
+
+unsigned int __cpuinit get_c0_compare_int(void)
+{
+	return IRQ_TIMER;
+}
+
+void __init plat_time_init(void)
+{
+	mips_hpt_frequency = nlm_prom_info.cpu_frequency;
+	pr_info("MIPS counter frequency [%ld]\n",
+		(unsigned long)mips_hpt_frequency);
+}
diff --git a/arch/mips/netlogic/xlr/xlr_console.c b/arch/mips/netlogic/xlr/xlr_console.c
new file mode 100644
index 00000000000..759df069220
--- /dev/null
+++ b/arch/mips/netlogic/xlr/xlr_console.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/types.h>
+#include <asm/netlogic/xlr/iomap.h>
+
+void prom_putchar(char c)
+{
+	nlm_reg_t *mmio;
+
+	mmio = netlogic_io_mmio(NETLOGIC_IO_UART_0_OFFSET);
+	while (netlogic_read_reg(mmio, 0x5) == 0)
+		;
+	netlogic_write_reg(mmio, 0x0, c);
+}
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index c9209ca6c8e..4df87993744 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_SIBYTE_SB1250)	+= fixup-sb1250.o pci-sb1250.o
 obj-$(CONFIG_SIBYTE_BCM112X)	+= fixup-sb1250.o pci-sb1250.o
 obj-$(CONFIG_SIBYTE_BCM1x80)	+= pci-bcm1480.o pci-bcm1480ht.o
 obj-$(CONFIG_SNI_RM)		+= fixup-sni.o ops-sni.o
+obj-$(CONFIG_SOC_XWAY)		+= pci-lantiq.o ops-lantiq.o
 obj-$(CONFIG_TANBAC_TB0219)	+= fixup-tb0219.o
 obj-$(CONFIG_TANBAC_TB0226)	+= fixup-tb0226.o
 obj-$(CONFIG_TANBAC_TB0287)	+= fixup-tb0287.o
@@ -55,6 +56,7 @@ obj-$(CONFIG_ZAO_CAPCELLA)	+= fixup-capcella.o
 obj-$(CONFIG_WR_PPMC)		+= fixup-wrppmc.o
 obj-$(CONFIG_MIKROTIK_RB532)	+= pci-rc32434.o ops-rc32434.o fixup-rc32434.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= pci-octeon.o pcie-octeon.o
+obj-$(CONFIG_NLM_XLR)		+= pci-xlr.o
 
 ifdef CONFIG_PCI_MSI
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= msi-octeon.o
diff --git a/arch/mips/pci/ops-lantiq.c b/arch/mips/pci/ops-lantiq.c
new file mode 100644
index 00000000000..1f2afb55cc7
--- /dev/null
+++ b/arch/mips/pci/ops-lantiq.c
@@ -0,0 +1,116 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/mm.h>
+#include <asm/addrspace.h>
+#include <linux/vmalloc.h>
+
+#include <lantiq_soc.h>
+
+#include "pci-lantiq.h"
+
+#define LTQ_PCI_CFG_BUSNUM_SHF 16
+#define LTQ_PCI_CFG_DEVNUM_SHF 11
+#define LTQ_PCI_CFG_FUNNUM_SHF 8
+
+#define PCI_ACCESS_READ  0
+#define PCI_ACCESS_WRITE 1
+
+static int ltq_pci_config_access(unsigned char access_type, struct pci_bus *bus,
+	unsigned int devfn, unsigned int where, u32 *data)
+{
+	unsigned long cfg_base;
+	unsigned long flags;
+	u32 temp;
+
+	/* we support slot from 0 to 15 dev_fn & 0x68 (AD29) is the
+	   SoC itself */
+	if ((bus->number != 0) || ((devfn & 0xf8) > 0x78)
+		|| ((devfn & 0xf8) == 0) || ((devfn & 0xf8) == 0x68))
+		return 1;
+
+	spin_lock_irqsave(&ebu_lock, flags);
+
+	cfg_base = (unsigned long) ltq_pci_mapped_cfg;
+	cfg_base |= (bus->number << LTQ_PCI_CFG_BUSNUM_SHF) | (devfn <<
+			LTQ_PCI_CFG_FUNNUM_SHF) | (where & ~0x3);
+
+	/* Perform access */
+	if (access_type == PCI_ACCESS_WRITE) {
+		ltq_w32(swab32(*data), ((u32 *)cfg_base));
+	} else {
+		*data = ltq_r32(((u32 *)(cfg_base)));
+		*data = swab32(*data);
+	}
+	wmb();
+
+	/* clean possible Master abort */
+	cfg_base = (unsigned long) ltq_pci_mapped_cfg;
+	cfg_base |= (0x0 << LTQ_PCI_CFG_FUNNUM_SHF) + 4;
+	temp = ltq_r32(((u32 *)(cfg_base)));
+	temp = swab32(temp);
+	cfg_base = (unsigned long) ltq_pci_mapped_cfg;
+	cfg_base |= (0x68 << LTQ_PCI_CFG_FUNNUM_SHF) + 4;
+	ltq_w32(temp, ((u32 *)cfg_base));
+
+	spin_unlock_irqrestore(&ebu_lock, flags);
+
+	if (((*data) == 0xffffffff) && (access_type == PCI_ACCESS_READ))
+		return 1;
+
+	return 0;
+}
+
+int ltq_pci_read_config_dword(struct pci_bus *bus, unsigned int devfn,
+	int where, int size, u32 *val)
+{
+	u32 data = 0;
+
+	if (ltq_pci_config_access(PCI_ACCESS_READ, bus, devfn, where, &data))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (size == 1)
+		*val = (data >> ((where & 3) << 3)) & 0xff;
+	else if (size == 2)
+		*val = (data >> ((where & 3) << 3)) & 0xffff;
+	else
+		*val = data;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+int ltq_pci_write_config_dword(struct pci_bus *bus, unsigned int devfn,
+	int where, int size, u32 val)
+{
+	u32 data = 0;
+
+	if (size == 4) {
+		data = val;
+	} else {
+		if (ltq_pci_config_access(PCI_ACCESS_READ, bus,
+				devfn, where, &data))
+			return PCIBIOS_DEVICE_NOT_FOUND;
+
+		if (size == 1)
+			data = (data & ~(0xff << ((where & 3) << 3))) |
+				(val << ((where & 3) << 3));
+		else if (size == 2)
+			data = (data & ~(0xffff << ((where & 3) << 3))) |
+				(val << ((where & 3) << 3));
+	}
+
+	if (ltq_pci_config_access(PCI_ACCESS_WRITE, bus, devfn, where, &data))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	return PCIBIOS_SUCCESSFUL;
+}
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
new file mode 100644
index 00000000000..603d7493e96
--- /dev/null
+++ b/arch/mips/pci/pci-lantiq.c
@@ -0,0 +1,297 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/platform_device.h>
+
+#include <asm/pci.h>
+#include <asm/gpio.h>
+#include <asm/addrspace.h>
+
+#include <lantiq_soc.h>
+#include <lantiq_irq.h>
+#include <lantiq_platform.h>
+
+#include "pci-lantiq.h"
+
+#define LTQ_PCI_CFG_BASE		0x17000000
+#define LTQ_PCI_CFG_SIZE		0x00008000
+#define LTQ_PCI_MEM_BASE		0x18000000
+#define LTQ_PCI_MEM_SIZE		0x02000000
+#define LTQ_PCI_IO_BASE			0x1AE00000
+#define LTQ_PCI_IO_SIZE			0x00200000
+
+#define PCI_CR_FCI_ADDR_MAP0		0x00C0
+#define PCI_CR_FCI_ADDR_MAP1		0x00C4
+#define PCI_CR_FCI_ADDR_MAP2		0x00C8
+#define PCI_CR_FCI_ADDR_MAP3		0x00CC
+#define PCI_CR_FCI_ADDR_MAP4		0x00D0
+#define PCI_CR_FCI_ADDR_MAP5		0x00D4
+#define PCI_CR_FCI_ADDR_MAP6		0x00D8
+#define PCI_CR_FCI_ADDR_MAP7		0x00DC
+#define PCI_CR_CLK_CTRL			0x0000
+#define PCI_CR_PCI_MOD			0x0030
+#define PCI_CR_PC_ARB			0x0080
+#define PCI_CR_FCI_ADDR_MAP11hg		0x00E4
+#define PCI_CR_BAR11MASK		0x0044
+#define PCI_CR_BAR12MASK		0x0048
+#define PCI_CR_BAR13MASK		0x004C
+#define PCI_CS_BASE_ADDR1		0x0010
+#define PCI_CR_PCI_ADDR_MAP11		0x0064
+#define PCI_CR_FCI_BURST_LENGTH		0x00E8
+#define PCI_CR_PCI_EOI			0x002C
+#define PCI_CS_STS_CMD			0x0004
+
+#define PCI_MASTER0_REQ_MASK_2BITS	8
+#define PCI_MASTER1_REQ_MASK_2BITS	10
+#define PCI_MASTER2_REQ_MASK_2BITS	12
+#define INTERNAL_ARB_ENABLE_BIT		0
+
+#define LTQ_CGU_IFCCR		0x0018
+#define LTQ_CGU_PCICR		0x0034
+
+#define ltq_pci_w32(x, y)	ltq_w32((x), ltq_pci_membase + (y))
+#define ltq_pci_r32(x)		ltq_r32(ltq_pci_membase + (x))
+
+#define ltq_pci_cfg_w32(x, y)	ltq_w32((x), ltq_pci_mapped_cfg + (y))
+#define ltq_pci_cfg_r32(x)	ltq_r32(ltq_pci_mapped_cfg + (x))
+
+struct ltq_pci_gpio_map {
+	int pin;
+	int alt0;
+	int alt1;
+	int dir;
+	char *name;
+};
+
+/* the pci core can make use of the following gpios */
+static struct ltq_pci_gpio_map ltq_pci_gpio_map[] = {
+	{ 0, 1, 0, 0, "pci-exin0" },
+	{ 1, 1, 0, 0, "pci-exin1" },
+	{ 2, 1, 0, 0, "pci-exin2" },
+	{ 39, 1, 0, 0, "pci-exin3" },
+	{ 10, 1, 0, 0, "pci-exin4" },
+	{ 9, 1, 0, 0, "pci-exin5" },
+	{ 30, 1, 0, 1, "pci-gnt1" },
+	{ 23, 1, 0, 1, "pci-gnt2" },
+	{ 19, 1, 0, 1, "pci-gnt3" },
+	{ 38, 1, 0, 1, "pci-gnt4" },
+	{ 29, 1, 0, 0, "pci-req1" },
+	{ 31, 1, 0, 0, "pci-req2" },
+	{ 3, 1, 0, 0, "pci-req3" },
+	{ 37, 1, 0, 0, "pci-req4" },
+};
+
+__iomem void *ltq_pci_mapped_cfg;
+static __iomem void *ltq_pci_membase;
+
+int (*ltqpci_plat_dev_init)(struct pci_dev *dev) = NULL;
+
+/* Since the PCI REQ pins can be reused for other functionality, make it
+   possible to exclude those from interpretation by the PCI controller */
+static int ltq_pci_req_mask = 0xf;
+
+static int *ltq_pci_irq_map;
+
+struct pci_ops ltq_pci_ops = {
+	.read	= ltq_pci_read_config_dword,
+	.write	= ltq_pci_write_config_dword
+};
+
+static struct resource pci_io_resource = {
+	.name	= "pci io space",
+	.start	= LTQ_PCI_IO_BASE,
+	.end	= LTQ_PCI_IO_BASE + LTQ_PCI_IO_SIZE - 1,
+	.flags	= IORESOURCE_IO
+};
+
+static struct resource pci_mem_resource = {
+	.name	= "pci memory space",
+	.start	= LTQ_PCI_MEM_BASE,
+	.end	= LTQ_PCI_MEM_BASE + LTQ_PCI_MEM_SIZE - 1,
+	.flags	= IORESOURCE_MEM
+};
+
+static struct pci_controller ltq_pci_controller = {
+	.pci_ops	= &ltq_pci_ops,
+	.mem_resource	= &pci_mem_resource,
+	.mem_offset	= 0x00000000UL,
+	.io_resource	= &pci_io_resource,
+	.io_offset	= 0x00000000UL,
+};
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	if (ltqpci_plat_dev_init)
+		return ltqpci_plat_dev_init(dev);
+
+	return 0;
+}
+
+static u32 ltq_calc_bar11mask(void)
+{
+	u32 mem, bar11mask;
+
+	/* BAR11MASK value depends on available memory on system. */
+	mem = num_physpages * PAGE_SIZE;
+	bar11mask = (0x0ffffff0 & ~((1 << (fls(mem) - 1)) - 1)) | 8;
+
+	return bar11mask;
+}
+
+static void ltq_pci_setup_gpio(int gpio)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(ltq_pci_gpio_map); i++) {
+		if (gpio & (1 << i)) {
+			ltq_gpio_request(ltq_pci_gpio_map[i].pin,
+				ltq_pci_gpio_map[i].alt0,
+				ltq_pci_gpio_map[i].alt1,
+				ltq_pci_gpio_map[i].dir,
+				ltq_pci_gpio_map[i].name);
+		}
+	}
+	ltq_gpio_request(21, 0, 0, 1, "pci-reset");
+	ltq_pci_req_mask = (gpio >> PCI_REQ_SHIFT) & PCI_REQ_MASK;
+}
+
+static int __devinit ltq_pci_startup(struct ltq_pci_data *conf)
+{
+	u32 temp_buffer;
+
+	/* set clock to 33Mhz */
+	ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) & ~0xf00000, LTQ_CGU_IFCCR);
+	ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) | 0x800000, LTQ_CGU_IFCCR);
+
+	/* external or internal clock ? */
+	if (conf->clock) {
+		ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) & ~(1 << 16),
+			LTQ_CGU_IFCCR);
+		ltq_cgu_w32((1 << 30), LTQ_CGU_PCICR);
+	} else {
+		ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) | (1 << 16),
+			LTQ_CGU_IFCCR);
+		ltq_cgu_w32((1 << 31) | (1 << 30), LTQ_CGU_PCICR);
+	}
+
+	/* setup pci clock and gpis used by pci */
+	ltq_pci_setup_gpio(conf->gpio);
+
+	/* enable auto-switching between PCI and EBU */
+	ltq_pci_w32(0xa, PCI_CR_CLK_CTRL);
+
+	/* busy, i.e. configuration is not done, PCI access has to be retried */
+	ltq_pci_w32(ltq_pci_r32(PCI_CR_PCI_MOD) & ~(1 << 24), PCI_CR_PCI_MOD);
+	wmb();
+	/* BUS Master/IO/MEM access */
+	ltq_pci_cfg_w32(ltq_pci_cfg_r32(PCI_CS_STS_CMD) | 7, PCI_CS_STS_CMD);
+
+	/* enable external 2 PCI masters */
+	temp_buffer = ltq_pci_r32(PCI_CR_PC_ARB);
+	temp_buffer &= (~(ltq_pci_req_mask << 16));
+	/* enable internal arbiter */
+	temp_buffer |= (1 << INTERNAL_ARB_ENABLE_BIT);
+	/* enable internal PCI master reqest */
+	temp_buffer &= (~(3 << PCI_MASTER0_REQ_MASK_2BITS));
+
+	/* enable EBU request */
+	temp_buffer &= (~(3 << PCI_MASTER1_REQ_MASK_2BITS));
+
+	/* enable all external masters request */
+	temp_buffer &= (~(3 << PCI_MASTER2_REQ_MASK_2BITS));
+	ltq_pci_w32(temp_buffer, PCI_CR_PC_ARB);
+	wmb();
+
+	/* setup BAR memory regions */
+	ltq_pci_w32(0x18000000, PCI_CR_FCI_ADDR_MAP0);
+	ltq_pci_w32(0x18400000, PCI_CR_FCI_ADDR_MAP1);
+	ltq_pci_w32(0x18800000, PCI_CR_FCI_ADDR_MAP2);
+	ltq_pci_w32(0x18c00000, PCI_CR_FCI_ADDR_MAP3);
+	ltq_pci_w32(0x19000000, PCI_CR_FCI_ADDR_MAP4);
+	ltq_pci_w32(0x19400000, PCI_CR_FCI_ADDR_MAP5);
+	ltq_pci_w32(0x19800000, PCI_CR_FCI_ADDR_MAP6);
+	ltq_pci_w32(0x19c00000, PCI_CR_FCI_ADDR_MAP7);
+	ltq_pci_w32(0x1ae00000, PCI_CR_FCI_ADDR_MAP11hg);
+	ltq_pci_w32(ltq_calc_bar11mask(), PCI_CR_BAR11MASK);
+	ltq_pci_w32(0, PCI_CR_PCI_ADDR_MAP11);
+	ltq_pci_w32(0, PCI_CS_BASE_ADDR1);
+	/* both TX and RX endian swap are enabled */
+	ltq_pci_w32(ltq_pci_r32(PCI_CR_PCI_EOI) | 3, PCI_CR_PCI_EOI);
+	wmb();
+	ltq_pci_w32(ltq_pci_r32(PCI_CR_BAR12MASK) | 0x80000000,
+		PCI_CR_BAR12MASK);
+	ltq_pci_w32(ltq_pci_r32(PCI_CR_BAR13MASK) | 0x80000000,
+		PCI_CR_BAR13MASK);
+	/*use 8 dw burst length */
+	ltq_pci_w32(0x303, PCI_CR_FCI_BURST_LENGTH);
+	ltq_pci_w32(ltq_pci_r32(PCI_CR_PCI_MOD) | (1 << 24), PCI_CR_PCI_MOD);
+	wmb();
+
+	/* setup irq line */
+	ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_CON) | 0xc, LTQ_EBU_PCC_CON);
+	ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_IEN) | 0x10, LTQ_EBU_PCC_IEN);
+
+	/* toggle reset pin */
+	__gpio_set_value(21, 0);
+	wmb();
+	mdelay(1);
+	__gpio_set_value(21, 1);
+	return 0;
+}
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	if (ltq_pci_irq_map[slot])
+		return ltq_pci_irq_map[slot];
+	printk(KERN_ERR "lq_pci: trying to map irq for unknown slot %d\n",
+		slot);
+
+	return 0;
+}
+
+static int __devinit ltq_pci_probe(struct platform_device *pdev)
+{
+	struct ltq_pci_data *ltq_pci_data =
+		(struct ltq_pci_data *) pdev->dev.platform_data;
+	pci_probe_only = 0;
+	ltq_pci_irq_map = ltq_pci_data->irq;
+	ltq_pci_membase = ioremap_nocache(PCI_CR_BASE_ADDR, PCI_CR_SIZE);
+	ltq_pci_mapped_cfg =
+		ioremap_nocache(LTQ_PCI_CFG_BASE, LTQ_PCI_CFG_BASE);
+	ltq_pci_controller.io_map_base =
+		(unsigned long)ioremap(LTQ_PCI_IO_BASE, LTQ_PCI_IO_SIZE - 1);
+	ltq_pci_startup(ltq_pci_data);
+	register_pci_controller(&ltq_pci_controller);
+
+	return 0;
+}
+
+static struct platform_driver
+ltq_pci_driver = {
+	.probe = ltq_pci_probe,
+	.driver = {
+		.name = "ltq_pci",
+		.owner = THIS_MODULE,
+	},
+};
+
+int __init pcibios_init(void)
+{
+	int ret = platform_driver_register(&ltq_pci_driver);
+	if (ret)
+		printk(KERN_INFO "ltq_pci: Error registering platfom driver!");
+	return ret;
+}
+
+arch_initcall(pcibios_init);
diff --git a/arch/mips/pci/pci-lantiq.h b/arch/mips/pci/pci-lantiq.h
new file mode 100644
index 00000000000..66bf6cd6be3
--- /dev/null
+++ b/arch/mips/pci/pci-lantiq.h
@@ -0,0 +1,18 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#ifndef _LTQ_PCI_H__
+#define _LTQ_PCI_H__
+
+extern __iomem void *ltq_pci_mapped_cfg;
+extern int ltq_pci_read_config_dword(struct pci_bus *bus,
+	unsigned int devfn, int where, int size, u32 *val);
+extern int ltq_pci_write_config_dword(struct pci_bus *bus,
+	unsigned int devfn, int where, int size, u32 val);
+
+#endif
diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c
new file mode 100644
index 00000000000..38fece16c43
--- /dev/null
+++ b/arch/mips/pci/pci-xlr.c
@@ -0,0 +1,214 @@
+/*
+ * Copyright 2003-2011 NetLogic Microsystems, Inc. (NetLogic). All rights
+ * reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the NetLogic
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY NETLOGIC ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL NETLOGIC OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/console.h>
+
+#include <asm/io.h>
+
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/pic.h>
+#include <asm/netlogic/xlr/xlr.h>
+
+static void *pci_config_base;
+
+#define	pci_cfg_addr(bus, devfn, off) (((bus) << 16) | ((devfn) << 8) | (off))
+
+/* PCI ops */
+static inline u32 pci_cfg_read_32bit(struct pci_bus *bus, unsigned int devfn,
+	int where)
+{
+	u32 data;
+	u32 *cfgaddr;
+
+	cfgaddr = (u32 *)(pci_config_base +
+			pci_cfg_addr(bus->number, devfn, where & ~3));
+	data = *cfgaddr;
+	return cpu_to_le32(data);
+}
+
+static inline void pci_cfg_write_32bit(struct pci_bus *bus, unsigned int devfn,
+	int where, u32 data)
+{
+	u32 *cfgaddr;
+
+	cfgaddr = (u32 *)(pci_config_base +
+			pci_cfg_addr(bus->number, devfn, where & ~3));
+	*cfgaddr = cpu_to_le32(data);
+}
+
+static int nlm_pcibios_read(struct pci_bus *bus, unsigned int devfn,
+	int where, int size, u32 *val)
+{
+	u32 data;
+
+	if ((size == 2) && (where & 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	else if ((size == 4) && (where & 3))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	data = pci_cfg_read_32bit(bus, devfn, where);
+
+	if (size == 1)
+		*val = (data >> ((where & 3) << 3)) & 0xff;
+	else if (size == 2)
+		*val = (data >> ((where & 3) << 3)) & 0xffff;
+	else
+		*val = data;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+
+static int nlm_pcibios_write(struct pci_bus *bus, unsigned int devfn,
+		int where, int size, u32 val)
+{
+	u32 data;
+
+	if ((size == 2) && (where & 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	else if ((size == 4) && (where & 3))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	data = pci_cfg_read_32bit(bus, devfn, where);
+
+	if (size == 1)
+		data = (data & ~(0xff << ((where & 3) << 3))) |
+			(val << ((where & 3) << 3));
+	else if (size == 2)
+		data = (data & ~(0xffff << ((where & 3) << 3))) |
+			(val << ((where & 3) << 3));
+	else
+		data = val;
+
+	pci_cfg_write_32bit(bus, devfn, where, data);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+struct pci_ops nlm_pci_ops = {
+	.read  = nlm_pcibios_read,
+	.write = nlm_pcibios_write
+};
+
+static struct resource nlm_pci_mem_resource = {
+	.name           = "XLR PCI MEM",
+	.start          = 0xd0000000UL,	/* 256MB PCI mem @ 0xd000_0000 */
+	.end            = 0xdfffffffUL,
+	.flags          = IORESOURCE_MEM,
+};
+
+static struct resource nlm_pci_io_resource = {
+	.name           = "XLR IO MEM",
+	.start          = 0x10000000UL,	/* 16MB PCI IO @ 0x1000_0000 */
+	.end            = 0x100fffffUL,
+	.flags          = IORESOURCE_IO,
+};
+
+struct pci_controller nlm_pci_controller = {
+	.index          = 0,
+	.pci_ops        = &nlm_pci_ops,
+	.mem_resource   = &nlm_pci_mem_resource,
+	.mem_offset     = 0x00000000UL,
+	.io_resource    = &nlm_pci_io_resource,
+	.io_offset      = 0x00000000UL,
+};
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	if (!nlm_chip_is_xls())
+		return	PIC_PCIX_IRQ;	/* for XLR just one IRQ*/
+
+	/*
+	 * For XLS PCIe, there is an IRQ per Link, find out which
+	 * link the device is on to assign interrupts
+	*/
+	if (dev->bus->self == NULL)
+		return 0;
+
+	switch	(dev->bus->self->devfn) {
+	case 0x0:
+		return PIC_PCIE_LINK0_IRQ;
+	case 0x8:
+		return PIC_PCIE_LINK1_IRQ;
+	case 0x10:
+		if (nlm_chip_is_xls_b())
+			return PIC_PCIE_XLSB0_LINK2_IRQ;
+		else
+			return PIC_PCIE_LINK2_IRQ;
+	case 0x18:
+		if (nlm_chip_is_xls_b())
+			return PIC_PCIE_XLSB0_LINK3_IRQ;
+		else
+			return PIC_PCIE_LINK3_IRQ;
+	}
+	WARN(1, "Unexpected devfn %d\n", dev->bus->self->devfn);
+	return 0;
+}
+
+/* Do platform specific device initialization at pci_enable_device() time */
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	return 0;
+}
+
+static int __init pcibios_init(void)
+{
+	/* PSB assigns PCI resources */
+	pci_probe_only = 1;
+	pci_config_base = ioremap(DEFAULT_PCI_CONFIG_BASE, 16 << 20);
+
+	/* Extend IO port for memory mapped io */
+	ioport_resource.start =  0;
+	ioport_resource.end   = ~0;
+
+	set_io_port_base(CKSEG1);
+	nlm_pci_controller.io_map_base = CKSEG1;
+
+	pr_info("Registering XLR/XLS PCIX/PCIE Controller.\n");
+	register_pci_controller(&nlm_pci_controller);
+
+	return 0;
+}
+
+arch_initcall(pcibios_init);
+
+struct pci_fixup pcibios_fixups[] = {
+	{0}
+};
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index efc9e889b34..2608752898c 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -55,6 +55,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 
 	case 1:
@@ -63,6 +65,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 	}
 }
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 0a04603d577..b18b04e4857 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void)
 #ifdef CONFIG_SMP
 	if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
 		smp_call_function_interrupt();
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index a152538d3c9..ef74f3267f9 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -66,18 +66,7 @@ static int rt_next_event(unsigned long delta, struct clock_event_device *evt)
 static void rt_set_mode(enum clock_event_mode mode,
 		struct clock_event_device *evt)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		/* The only mode supported */
-		break;
-
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do  */
-		break;
-	}
+	/* Nothing to do ...  */
 }
 
 int rt_timer_irq;
@@ -174,8 +163,7 @@ static void __init hub_rt_clocksource_init(void)
 {
 	struct clocksource *cs = &hub_rt_clocksource;
 
-	clocksource_set_clock(cs, CYCLES_PER_SEC);
-	clocksource_register(cs);
+	clocksource_register_hz(cs, CYCLES_PER_SEC);
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 47b347c992e..d667875be56 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	__raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index c00a5cb1128..38e7f6bd792 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 226c826a219..83fb2791223 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -494,14 +494,11 @@ void smp_send_stop(void)
  * @irq: The interrupt number.
  * @dev_id: The device ID.
  *
- * We need do nothing here, since the scheduling will be effected on our way
- * back through entry.S.
- *
  * Returns IRQ_HANDLED to indicate we handled the interrupt successfully.
  */
 static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id)
 {
-	/* do nothing */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 69d63d354ef..828305f19cf 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id)
 				
 			case IPI_RESCHEDULE:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu);
-				/*
-				 * Reschedule callback.  Everything to be
-				 * done is done by the interrupt return path.
-				 */
+				scheduler_ipi();
 				break;
 
 			case IPI_CALL_FUNC:
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 664bee6622e..df18989e78d 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -3,7 +3,6 @@
 #ifdef __KERNEL__
 
 #include <linux/irq.h>
-#include <linux/sysdev.h>
 #include <asm/dcr.h>
 #include <asm/msi_bitmap.h>
 
@@ -321,8 +320,6 @@ struct mpic
 	/* link */
 	struct mpic		*next;
 
-	struct sys_device	sysdev;
-
 #ifdef CONFIG_PM
 	struct mpic_irq_save	*save_data;
 #endif
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index dd1973fed30..4a6f2ec7e76 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -119,7 +119,7 @@ static irqreturn_t call_function_action(int irq, void *data)
 
 static irqreturn_t reschedule_action(int irq, void *data)
 {
-	/* we just need the return path side effect of checking need_resched */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
@@ -224,7 +224,7 @@ irqreturn_t smp_ipi_demux(void)
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
 			generic_smp_call_function_interrupt();
 		if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE)))
-			reschedule_action(0, NULL); /* upcoming sched hook */
+			scheduler_ipi();
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE)))
 			generic_smp_call_function_single_interrupt();
 		if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK)))
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 06b9d457d0a..b13306b0d92 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -143,7 +143,6 @@ int die(const char *str, struct pt_regs *regs, long err)
 #endif
 		printk("%s\n", ppc_md.name ? ppc_md.name : "");
 
-		sysfs_printk_last_file();
 		if (notify_die(DIE_OOPS, str, regs, err, 255,
 			       SIGSEGV) == NOTIFY_STOP)
 			return 1;
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 6a58744d66c..449c08c1586 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -201,7 +201,7 @@ static irqreturn_t iic_ipi_action(int irq, void *dev_id)
 		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
-		/* Upcoming sched hook */
+		scheduler_ipi();
 		break;
 	case PPC_MSG_CALL_FUNC_SINGLE:
 		generic_smp_call_function_single_interrupt();
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index acfaccea5f4..3675da73623 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -32,6 +32,7 @@
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/linux_logo.h>
+#include <linux/syscore_ops.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
 #include <asm/spu_csa.h>
@@ -521,18 +522,8 @@ void spu_init_channels(struct spu *spu)
 }
 EXPORT_SYMBOL_GPL(spu_init_channels);
 
-static int spu_shutdown(struct sys_device *sysdev)
-{
-	struct spu *spu = container_of(sysdev, struct spu, sysdev);
-
-	spu_free_irqs(spu);
-	spu_destroy_spu(spu);
-	return 0;
-}
-
 static struct sysdev_class spu_sysdev_class = {
 	.name = "spu",
-	.shutdown = spu_shutdown,
 };
 
 int spu_add_sysdev_attr(struct sysdev_attribute *attr)
@@ -797,6 +788,22 @@ static inline void crash_register_spus(struct list_head *list)
 }
 #endif
 
+static void spu_shutdown(void)
+{
+	struct spu *spu;
+
+	mutex_lock(&spu_full_list_mutex);
+	list_for_each_entry(spu, &spu_full_list, full_list) {
+		spu_free_irqs(spu);
+		spu_destroy_spu(spu);
+	}
+	mutex_unlock(&spu_full_list_mutex);
+}
+
+static struct syscore_ops spu_syscore_ops = {
+	.shutdown = spu_shutdown,
+};
+
 static int __init init_spu_base(void)
 {
 	int i, ret = 0;
@@ -830,6 +837,7 @@ static int __init init_spu_base(void)
 	crash_register_spus(&spu_full_list);
 	mutex_unlock(&spu_full_list_mutex);
 	spu_add_sysdev_attr(&attr_stat);
+	register_syscore_ops(&spu_syscore_ops);
 
 	spu_init_affinity();
 
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 360260d1352..9089b042119 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -21,7 +21,7 @@
 #include <linux/signal.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/adb.h>
 #include <linux/pmu.h>
 #include <linux/module.h>
@@ -674,7 +674,7 @@ not_found:
 	return viaint;
 }
 
-static int pmacpic_suspend(struct sys_device *sysdev, pm_message_t state)
+static int pmacpic_suspend(void)
 {
 	int viaint = pmacpic_find_viaint();
 
@@ -695,7 +695,7 @@ static int pmacpic_suspend(struct sys_device *sysdev, pm_message_t state)
         return 0;
 }
 
-static int pmacpic_resume(struct sys_device *sysdev)
+static void pmacpic_resume(void)
 {
 	int i;
 
@@ -706,39 +706,19 @@ static int pmacpic_resume(struct sys_device *sysdev)
 	for (i = 0; i < max_real_irqs; ++i)
 		if (test_bit(i, sleep_save_mask))
 			pmac_unmask_irq(irq_get_irq_data(i));
-
-	return 0;
 }
 
-#endif /* CONFIG_PM && CONFIG_PPC32 */
-
-static struct sysdev_class pmacpic_sysclass = {
-	.name = "pmac_pic",
+static struct syscore_ops pmacpic_syscore_ops = {
+	.suspend	= pmacpic_suspend,
+	.resume		= pmacpic_resume,
 };
 
-static struct sys_device device_pmacpic = {
-	.id		= 0,
-	.cls		= &pmacpic_sysclass,
-};
-
-static struct sysdev_driver driver_pmacpic = {
-#if defined(CONFIG_PM) && defined(CONFIG_PPC32)
-	.suspend	= &pmacpic_suspend,
-	.resume		= &pmacpic_resume,
-#endif /* CONFIG_PM && CONFIG_PPC32 */
-};
-
-static int __init init_pmacpic_sysfs(void)
+static int __init init_pmacpic_syscore(void)
 {
-#ifdef CONFIG_PPC32
-	if (max_irqs == 0)
-		return -ENODEV;
-#endif
-	printk(KERN_DEBUG "Registering pmac pic with sysfs...\n");
-	sysdev_class_register(&pmacpic_sysclass);
-	sysdev_register(&device_pmacpic);
-	sysdev_driver_register(&pmacpic_sysclass, &driver_pmacpic);
+	register_syscore_ops(&pmacpic_syscore_ops);
 	return 0;
 }
-machine_subsys_initcall(powermac, init_pmacpic_sysfs);
 
+machine_subsys_initcall(powermac, init_pmacpic_syscore);
+
+#endif /* CONFIG_PM && CONFIG_PPC32 */
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index f0ece79f9be..7367d17364c 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -18,7 +18,7 @@
 #include <linux/stddef.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/device.h>
 #include <linux/bootmem.h>
 #include <linux/spinlock.h>
@@ -900,7 +900,7 @@ static struct {
 	u32 sercr;
 } ipic_saved_state;
 
-static int ipic_suspend(struct sys_device *sdev, pm_message_t state)
+static int ipic_suspend(void)
 {
 	struct ipic *ipic = primary_ipic;
 
@@ -931,7 +931,7 @@ static int ipic_suspend(struct sys_device *sdev, pm_message_t state)
 	return 0;
 }
 
-static int ipic_resume(struct sys_device *sdev)
+static void ipic_resume(void)
 {
 	struct ipic *ipic = primary_ipic;
 
@@ -947,44 +947,26 @@ static int ipic_resume(struct sys_device *sdev)
 	ipic_write(ipic->regs, IPIC_SECNR, ipic_saved_state.secnr);
 	ipic_write(ipic->regs, IPIC_SERMR, ipic_saved_state.sermr);
 	ipic_write(ipic->regs, IPIC_SERCR, ipic_saved_state.sercr);
-
-	return 0;
 }
 #else
 #define ipic_suspend NULL
 #define ipic_resume NULL
 #endif
 
-static struct sysdev_class ipic_sysclass = {
-	.name = "ipic",
+static struct syscore_ops ipic_syscore_ops = {
 	.suspend = ipic_suspend,
 	.resume = ipic_resume,
 };
 
-static struct sys_device device_ipic = {
-	.id		= 0,
-	.cls		= &ipic_sysclass,
-};
-
-static int __init init_ipic_sysfs(void)
+static int __init init_ipic_syscore(void)
 {
-	int rc;
-
 	if (!primary_ipic || !primary_ipic->regs)
 		return -ENODEV;
-	printk(KERN_DEBUG "Registering ipic with sysfs...\n");
 
-	rc = sysdev_class_register(&ipic_sysclass);
-	if (rc) {
-		printk(KERN_ERR "Failed registering ipic sys class\n");
-		return -ENODEV;
-	}
-	rc = sysdev_register(&device_ipic);
-	if (rc) {
-		printk(KERN_ERR "Failed registering ipic sys device\n");
-		return -ENODEV;
-	}
+	printk(KERN_DEBUG "Registering ipic system core operations\n");
+	register_syscore_ops(&ipic_syscore_ops);
+
 	return 0;
 }
 
-subsys_initcall(init_ipic_sysfs);
+subsys_initcall(init_ipic_syscore);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 57e954142c7..3a8de5bb628 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -28,6 +28,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/ptrace.h>
 #include <asm/signal.h>
@@ -1793,9 +1794,8 @@ void mpic_reset_core(int cpu)
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PM
-static int mpic_suspend(struct sys_device *dev, pm_message_t state)
+static void mpic_suspend_one(struct mpic *mpic)
 {
-	struct mpic *mpic = container_of(dev, struct mpic, sysdev);
 	int i;
 
 	for (i = 0; i < mpic->num_sources; i++) {
@@ -1804,13 +1804,22 @@ static int mpic_suspend(struct sys_device *dev, pm_message_t state)
 		mpic->save_data[i].dest =
 			mpic_irq_read(i, MPIC_INFO(IRQ_DESTINATION));
 	}
+}
+
+static int mpic_suspend(void)
+{
+	struct mpic *mpic = mpics;
+
+	while (mpic) {
+		mpic_suspend_one(mpic);
+		mpic = mpic->next;
+	}
 
 	return 0;
 }
 
-static int mpic_resume(struct sys_device *dev)
+static void mpic_resume_one(struct mpic *mpic)
 {
-	struct mpic *mpic = container_of(dev, struct mpic, sysdev);
 	int i;
 
 	for (i = 0; i < mpic->num_sources; i++) {
@@ -1837,33 +1846,28 @@ static int mpic_resume(struct sys_device *dev)
 	}
 #endif
 	} /* end for loop */
+}
 
-	return 0;
+static void mpic_resume(void)
+{
+	struct mpic *mpic = mpics;
+
+	while (mpic) {
+		mpic_resume_one(mpic);
+		mpic = mpic->next;
+	}
 }
-#endif
 
-static struct sysdev_class mpic_sysclass = {
-#ifdef CONFIG_PM
+static struct syscore_ops mpic_syscore_ops = {
 	.resume = mpic_resume,
 	.suspend = mpic_suspend,
-#endif
-	.name = "mpic",
 };
 
 static int mpic_init_sys(void)
 {
-	struct mpic *mpic = mpics;
-	int error, id = 0;
-
-	error = sysdev_class_register(&mpic_sysclass);
-
-	while (mpic && !error) {
-		mpic->sysdev.cls = &mpic_sysclass;
-		mpic->sysdev.id = id++;
-		error = sysdev_register(&mpic->sysdev);
-		mpic = mpic->next;
-	}
-	return error;
+	register_syscore_ops(&mpic_syscore_ops);
+	return 0;
 }
 
 device_initcall(mpic_init_sys);
+#endif
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 2508a6f3158..4a7f14079e0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -88,6 +88,7 @@ config S390
 	select HAVE_KERNEL_XZ
 	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
+	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h
index 43a5c78046d..3e20383d092 100644
--- a/arch/s390/include/asm/cacheflush.h
+++ b/arch/s390/include/asm/cacheflush.h
@@ -11,5 +11,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable);
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
 
 #endif /* _S390_CACHEFLUSH_H */
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 3c29be4836e..b7931faaef6 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -11,15 +11,13 @@ struct dyn_arch_ftrace { };
 
 #ifdef CONFIG_64BIT
 #define MCOUNT_INSN_SIZE  12
-#define MCOUNT_OFFSET	   8
 #else
 #define MCOUNT_INSN_SIZE  20
-#define MCOUNT_OFFSET	   4
 #endif
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
-	return addr - MCOUNT_OFFSET;
+	return addr;
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
new file mode 100644
index 00000000000..95a6cf2b5b6
--- /dev/null
+++ b/arch/s390/include/asm/jump_label.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_S390_JUMP_LABEL_H
+#define _ASM_S390_JUMP_LABEL_H
+
+#include <linux/types.h>
+
+#define JUMP_LABEL_NOP_SIZE 6
+
+#ifdef CONFIG_64BIT
+#define ASM_PTR ".quad"
+#define ASM_ALIGN ".balign 8"
+#else
+#define ASM_PTR ".long"
+#define ASM_ALIGN ".balign 4"
+#endif
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("0:	brcl 0,0\n"
+		".pushsection __jump_table, \"aw\"\n"
+		ASM_ALIGN "\n"
+		ASM_PTR " 0b, %l[label], %0\n"
+		".popsection\n"
+		: : "X" (key) : : label);
+	return false;
+label:
+	return true;
+}
+
+typedef unsigned long jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 64230bc392f..5ff15dacb57 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -23,7 +23,7 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o \
 	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
 	    s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o \
-	    vdso.o vtime.o sysinfo.o nmi.o sclp.o
+	    vdso.o vtime.o sysinfo.o nmi.o sclp.o jump_label.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
new file mode 100644
index 00000000000..44cc06bedf7
--- /dev/null
+++ b/arch/s390/kernel/jump_label.c
@@ -0,0 +1,59 @@
+/*
+ * Jump label s390 support
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <linux/jump_label.h>
+#include <asm/ipl.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+struct insn {
+	u16 opcode;
+	s32 offset;
+} __packed;
+
+struct insn_args {
+	unsigned long *target;
+	struct insn *insn;
+	ssize_t size;
+};
+
+static int __arch_jump_label_transform(void *data)
+{
+	struct insn_args *args = data;
+	int rc;
+
+	rc = probe_kernel_write(args->target, args->insn, args->size);
+	WARN_ON_ONCE(rc < 0);
+	return 0;
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	struct insn_args args;
+	struct insn insn;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		/* brcl 15,offset */
+		insn.opcode = 0xc0f4;
+		insn.offset = (entry->target - entry->code) >> 1;
+	} else {
+		/* brcl 0,0 */
+		insn.opcode = 0xc004;
+		insn.offset = 0;
+	}
+
+	args.target = (void *) entry->code;
+	args.insn = &insn;
+	args.size = JUMP_LABEL_NOP_SIZE;
+
+	stop_machine(__arch_jump_label_transform, &args, NULL);
+}
+
+#endif
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 63a97db83f9..63c7d9ff220 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++;
 	/*
 	 * handle bit signal external calls
-	 *
-	 * For the ec_schedule signal we have to do nothing. All the work
-	 * is done automatically when we return from the interrupt.
 	 */
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
+	if (test_bit(ec_schedule, &bits))
+		scheduler_ipi();
+
 	if (test_bit(ec_call_function, &bits))
 		generic_smp_call_function_interrupt();
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 0607e4b14b2..f05edcc3bef 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -54,3 +54,8 @@ int set_memory_nx(unsigned long addr, int numpages)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(set_memory_nx);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	return 0;
+}
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 4b89da248d1..bc439de48cd 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -24,7 +24,6 @@ config SUPERH
 	select RTC_LIB
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
-	select ARCH_NO_SYSDEV_OPS
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
index e71a531f1e3..77ec0e7b8dd 100644
--- a/arch/sh/configs/apsh4ad0a_defconfig
+++ b/arch/sh/configs/apsh4ad0a_defconfig
@@ -48,7 +48,6 @@ CONFIG_PREEMPT=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
 CONFIG_PM_DEBUG=y
-CONFIG_PM_VERBOSE=y
 CONFIG_PM_RUNTIME=y
 CONFIG_CPU_IDLE=y
 CONFIG_NET=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index dc4a2eb6a61..c41650572d7 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -83,7 +83,6 @@ CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
 CONFIG_PM_DEBUG=y
-CONFIG_PM_VERBOSE=y
 CONFIG_PM_RUNTIME=y
 CONFIG_CPU_IDLE=y
 CONFIG_NET=y
diff --git a/arch/sh/kernel/cpu/shmobile/pm_runtime.c b/arch/sh/kernel/cpu/shmobile/pm_runtime.c
index 6dcb8166a64..22db127afa7 100644
--- a/arch/sh/kernel/cpu/shmobile/pm_runtime.c
+++ b/arch/sh/kernel/cpu/shmobile/pm_runtime.c
@@ -139,7 +139,7 @@ void platform_pm_runtime_suspend_idle(void)
 	queue_work(pm_wq, &hwblk_work);
 }
 
-int platform_pm_runtime_suspend(struct device *dev)
+static int default_platform_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct pdev_archdata *ad = &pdev->archdata;
@@ -147,7 +147,7 @@ int platform_pm_runtime_suspend(struct device *dev)
 	int hwblk = ad->hwblk_id;
 	int ret = 0;
 
-	dev_dbg(dev, "platform_pm_runtime_suspend() [%d]\n", hwblk);
+	dev_dbg(dev, "%s() [%d]\n", __func__, hwblk);
 
 	/* ignore off-chip platform devices */
 	if (!hwblk)
@@ -183,20 +183,20 @@ int platform_pm_runtime_suspend(struct device *dev)
 	mutex_unlock(&ad->mutex);
 
 out:
-	dev_dbg(dev, "platform_pm_runtime_suspend() [%d] returns %d\n",
-		hwblk, ret);
+	dev_dbg(dev, "%s() [%d] returns %d\n",
+		 __func__, hwblk, ret);
 
 	return ret;
 }
 
-int platform_pm_runtime_resume(struct device *dev)
+static int default_platform_runtime_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct pdev_archdata *ad = &pdev->archdata;
 	int hwblk = ad->hwblk_id;
 	int ret = 0;
 
-	dev_dbg(dev, "platform_pm_runtime_resume() [%d]\n", hwblk);
+	dev_dbg(dev, "%s() [%d]\n", __func__, hwblk);
 
 	/* ignore off-chip platform devices */
 	if (!hwblk)
@@ -228,19 +228,19 @@ int platform_pm_runtime_resume(struct device *dev)
 	 */
 	mutex_unlock(&ad->mutex);
 out:
-	dev_dbg(dev, "platform_pm_runtime_resume() [%d] returns %d\n",
-		hwblk, ret);
+	dev_dbg(dev, "%s() [%d] returns %d\n",
+		__func__, hwblk, ret);
 
 	return ret;
 }
 
-int platform_pm_runtime_idle(struct device *dev)
+static int default_platform_runtime_idle(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	int hwblk = pdev->archdata.hwblk_id;
 	int ret = 0;
 
-	dev_dbg(dev, "platform_pm_runtime_idle() [%d]\n", hwblk);
+	dev_dbg(dev, "%s() [%d]\n", __func__, hwblk);
 
 	/* ignore off-chip platform devices */
 	if (!hwblk)
@@ -252,10 +252,19 @@ int platform_pm_runtime_idle(struct device *dev)
 	/* suspend synchronously to disable clocks immediately */
 	ret = pm_runtime_suspend(dev);
 out:
-	dev_dbg(dev, "platform_pm_runtime_idle() [%d] done!\n", hwblk);
+	dev_dbg(dev, "%s() [%d] done!\n", __func__, hwblk);
 	return ret;
 }
 
+static struct dev_power_domain default_power_domain = {
+	.ops = {
+		.runtime_suspend = default_platform_runtime_suspend,
+		.runtime_resume = default_platform_runtime_resume,
+		.runtime_idle = default_platform_runtime_idle,
+		USE_PLATFORM_PM_SLEEP_OPS
+	},
+};
+
 static int platform_bus_notify(struct notifier_block *nb,
 			       unsigned long action, void *data)
 {
@@ -276,6 +285,7 @@ static int platform_bus_notify(struct notifier_block *nb,
 		hwblk_disable(hwblk_info, hwblk);
 		/* make sure driver re-inits itself once */
 		__set_bit(PDEV_ARCHDATA_FLAG_INIT, &pdev->archdata.flags);
+		dev->pwr_domain = &default_power_domain;
 		break;
 	/* TODO: add BUS_NOTIFY_BIND_DRIVER and increase idle count */
 	case BUS_NOTIFY_BOUND_DRIVER:
@@ -289,6 +299,7 @@ static int platform_bus_notify(struct notifier_block *nb,
 		__set_bit(PDEV_ARCHDATA_FLAG_INIT, &pdev->archdata.flags);
 		break;
 	case BUS_NOTIFY_DEL_DEVICE:
+		dev->pwr_domain = NULL;
 		break;
 	}
 	return 0;
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 509b36b4511..6207561ea34 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case SMP_MSG_RESCHEDULE:
+		scheduler_ipi();
 		break;
 	case SMP_MSG_FUNCTION_SINGLE:
 		generic_smp_call_function_single_interrupt();
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 3484c2f65ab..b51a17104b5 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -87,7 +87,6 @@ void die(const char * str, struct pt_regs * regs, long err)
 	bust_spinlocks(1);
 
 	printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
-	sysfs_printk_last_file();
 	print_modules();
 	show_regs(regs);
 
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 427d4684e0d..fc73a82366f 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -7,17 +7,20 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:\n\t"				\
-			 "nop\n\t"				\
-			 "nop\n\t"				\
-			 ".pushsection __jump_table,  \"a\"\n\t"\
-			 ".align 4\n\t"				\
-			 ".word 1b, %l[" #label "], %c0\n\t"	\
-			 ".popsection \n\t"			\
-			 : :  "i" (key) :  : label);\
-	} while (0)
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+		asm goto("1:\n\t"
+			 "nop\n\t"
+			 "nop\n\t"
+			 ".pushsection __jump_table,  \"aw\"\n\t"
+			 ".align 4\n\t"
+			 ".word 1b, %l[l_yes], %c0\n\t"
+			 ".popsection \n\t"
+			 : :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 1c79f32734a..8b9c556d630 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -65,6 +65,10 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define smt_capable()				(sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
-#define cpu_coregroup_mask(cpu)			(&cpu_core_map[cpu])
+extern cpumask_t cpu_core_map[NR_CPUS];
+static inline const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+        return &cpu_core_map[cpu];
+}
 
 #endif /* _ASM_SPARC64_TOPOLOGY_H */
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 850a1360c0d..442286d8343 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -129,7 +129,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 };
 
 void smp_send_reschedule(int cpu)
 {
-	/* See sparc64 */
+	/*
+	 * XXX missing reschedule IPI, see scheduler_ipi()
+	 */
 }
 
 void smp_send_stop(void)
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 3e94a8c2323..9478da7fdb3 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu)
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	scheduler_ipi();
 }
 
 /* This is a nop because we capture all other cpus
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index a4293102ef8..c52224d5ed4 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end)
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	/*
-	 * Nothing to do here; when we return from interrupt, the
-	 * rescheduling will occur there. But do bump the interrupt
-	 * profiler count in the meantime.
-	 */
 	__get_cpu_var(irq_stat).irq_resched_count++;
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 106bf27e2a9..eefb107d2d7 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -173,7 +173,7 @@ void IPI_handler(int cpu)
 			break;
 
 		case 'R':
-			set_tsk_need_resched(current);
+			scheduler_ipi();
 			break;
 
 		case 'S':
diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c
index 2aa30a364bb..d4efa7d679f 100644
--- a/arch/unicore32/kernel/irq.c
+++ b/arch/unicore32/kernel/irq.c
@@ -23,7 +23,7 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/gpio.h>
 
 #include <asm/system.h>
@@ -237,7 +237,7 @@ static struct puv3_irq_state {
 	unsigned int	iccr;
 } puv3_irq_state;
 
-static int puv3_irq_suspend(struct sys_device *dev, pm_message_t state)
+static int puv3_irq_suspend(void)
 {
 	struct puv3_irq_state *st = &puv3_irq_state;
 
@@ -265,7 +265,7 @@ static int puv3_irq_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int puv3_irq_resume(struct sys_device *dev)
+static void puv3_irq_resume(void)
 {
 	struct puv3_irq_state *st = &puv3_irq_state;
 
@@ -278,27 +278,20 @@ static int puv3_irq_resume(struct sys_device *dev)
 
 		writel(st->icmr, INTC_ICMR);
 	}
-	return 0;
 }
 
-static struct sysdev_class puv3_irq_sysclass = {
-	.name		= "pkunity-irq",
+static struct syscore_ops puv3_irq_syscore_ops = {
 	.suspend	= puv3_irq_suspend,
 	.resume		= puv3_irq_resume,
 };
 
-static struct sys_device puv3_irq_device = {
-	.id		= 0,
-	.cls		= &puv3_irq_sysclass,
-};
-
-static int __init puv3_irq_init_devicefs(void)
+static int __init puv3_irq_init_syscore(void)
 {
-	sysdev_class_register(&puv3_irq_sysclass);
-	return sysdev_register(&puv3_irq_device);
+	register_syscore_ops(&puv3_irq_syscore_ops);
+	return 0;
 }
 
-device_initcall(puv3_irq_init_devicefs);
+device_initcall(puv3_irq_init_syscore);
 
 void __init init_IRQ(void)
 {
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 254e36fa951..b9a26465e72 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -192,7 +192,6 @@ static int __die(const char *str, int err, struct thread_info *thread,
 
 	printk(KERN_EMERG "Internal error: %s: %x [#%d]\n",
 	       str, err, ++die_counter);
-	sysfs_printk_last_file();
 
 	/* trap and error numbers are mostly meaningless on UniCore */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, \
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc6c53a95bf..4168e5d8632 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -8,6 +8,7 @@ config 64BIT
 
 config X86_32
 	def_bool !64BIT
+	select CLKSRC_I8253
 
 config X86_64
 	def_bool 64BIT
@@ -71,7 +72,6 @@ config X86
 	select GENERIC_IRQ_SHOW
 	select IRQ_FORCED_THREADING
 	select USE_GENERIC_SMP_HELPERS if SMP
-	select ARCH_NO_SYSDEV_OPS
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -112,7 +112,14 @@ config MMU
 	def_bool y
 
 config ZONE_DMA
-	def_bool y
+	bool "DMA memory allocation support" if EXPERT
+	default y
+	help
+	  DMA memory allocation support allows devices with less than 32-bit
+	  addressing to allocate within the first 16MB of address space.
+	  Disable if no such devices will be used.
+
+	  If unsure, say Y.
 
 config SBUS
 	bool
@@ -365,17 +372,6 @@ config X86_UV
 # Following is an alphabetically sorted list of 32 bit extended platforms
 # Please maintain the alphabetic order if and when there are additions
 
-config X86_ELAN
-	bool "AMD Elan"
-	depends on X86_32
-	depends on X86_EXTENDED_PLATFORM
-	---help---
-	  Select this for an AMD Elan processor.
-
-	  Do not use this option for K6/Athlon/Opteron processors!
-
-	  If unsure, choose "PC-compatible" instead.
-
 config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
@@ -690,6 +686,7 @@ config AMD_IOMMU
 	bool "AMD IOMMU support"
 	select SWIOTLB
 	select PCI_MSI
+	select PCI_IOV
 	depends on X86_64 && PCI && ACPI
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in
@@ -1174,7 +1171,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 config AMD_NUMA
 	def_bool y
 	prompt "Old style AMD Opteron NUMA detection"
-	depends on X86_64 && NUMA && PCI
+	depends on NUMA && PCI
 	---help---
 	  Enable AMD NUMA node topology detection.  You should say Y here if
 	  you have a multi processor AMD system. This uses an old method to
@@ -1201,7 +1198,7 @@ config NODES_SPAN_OTHER_NODES
 
 config NUMA_EMU
 	bool "NUMA emulation"
-	depends on X86_64 && NUMA
+	depends on NUMA
 	---help---
 	  Enable NUMA emulation. A flat machine will be split
 	  into virtual nodes when booted with "numa=fake=N", where N is the
@@ -1223,6 +1220,10 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
+config HAVE_ARCH_ALLOC_REMAP
+	def_bool y
+	depends on X86_32 && NUMA
+
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
@@ -1231,13 +1232,9 @@ config NEED_NODE_MEMMAP_SIZE
 	def_bool y
 	depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool y
@@ -1247,20 +1244,16 @@ config ARCH_DISCONTIGMEM_DEFAULT
 	def_bool y
 	depends on NUMA && X86_32
 
-config ARCH_PROC_KCORE_TEXT
-	def_bool y
-	depends on X86_64 && PROC_KCORE
-
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool y
+	depends on X86_64
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SPARSEMEM_ENABLE
@@ -1269,6 +1262,10 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+	depends on X86_64 && PROC_KCORE
+
 config ILLEGAL_POINTER_VALUE
        hex
        default 0 if X86_32
@@ -1703,10 +1700,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 	depends on MEMORY_HOTPLUG
 
-config HAVE_ARCH_EARLY_PFN_TO_NID
-	def_bool X86_64
-	depends on NUMA
-
 config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA
@@ -1848,7 +1841,7 @@ config APM_ALLOW_INTS
 
 endif # APM
 
-source "arch/x86/kernel/cpu/cpufreq/Kconfig"
+source "drivers/cpufreq/Kconfig"
 
 source "drivers/cpuidle/Kconfig"
 
@@ -2076,7 +2069,7 @@ config OLPC
 	depends on !X86_PAE
 	select GPIOLIB
 	select OF
-	select OF_PROMTREE if PROC_DEVICETREE
+	select OF_PROMTREE
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index d161e939df6..6a7cfdf8ff6 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,6 +1,4 @@
 # Put here option for CPU selection and depending optimization
-if !X86_ELAN
-
 choice
 	prompt "Processor family"
 	default M686 if X86_32
@@ -203,6 +201,14 @@ config MWINCHIP3D
 	  stores for this CPU, which can increase performance of some
 	  operations.
 
+config MELAN
+	bool "AMD Elan"
+	depends on X86_32
+	---help---
+	  Select this for an AMD Elan processor.
+
+	  Do not use this option for K6/Athlon/Opteron processors!
+
 config MGEODEGX1
 	bool "GeodeGX1"
 	depends on X86_32
@@ -292,8 +298,6 @@ config X86_GENERIC
 	  This is really intended for distributors who need more
 	  generic optimizations.
 
-endif
-
 #
 # Define implied options from the CPU selection here
 config X86_INTERNODE_CACHE_SHIFT
@@ -312,7 +316,7 @@ config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
 	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
-	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
+	default "4" if MELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
 config X86_XADD
@@ -358,7 +362,7 @@ config X86_POPAD_OK
 
 config X86_ALIGNMENT_16
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
 
 config X86_INTEL_USERCOPY
 	def_bool y
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index f2ee1abb1df..86cee7b749e 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -37,7 +37,7 @@ cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=
 	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
 
 # AMD Elan support
-cflags-$(CONFIG_X86_ELAN)	+= -march=i486
+cflags-$(CONFIG_MELAN)		+= -march=i486
 
 # Geode GX1 support
 cflags-$(CONFIG_MGEODEGX1)	+= -march=pentium-mmx
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 12e0e7dd869..416d865eae3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -183,8 +183,6 @@ static inline void disable_acpi(void) { }
 
 #define ARCH_HAS_POWER_INIT	1
 
-struct bootnode;
-
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
 extern int x86_acpi_numa_init(void);
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index a63a68be1cc..94d420b360d 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -15,4 +15,13 @@
 	.endm
 #endif
 
+.macro altinstruction_entry orig alt feature orig_len alt_len
+	.align 8
+	.quad \orig
+	.quad \alt
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
 #endif  /*  __ASSEMBLY__  */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 13009d1af99..bf535f947e8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -4,7 +4,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
-#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -191,12 +190,4 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-#define IDEAL_NOP_SIZE_5 5
-extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
-extern void arch_init_ideal_nop5(void);
-#else
-static inline void arch_init_ideal_nop5(void) {}
-#endif
-
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index 916bc8111a0..55d95eb789b 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -19,13 +19,12 @@
 #ifndef _ASM_X86_AMD_IOMMU_PROTO_H
 #define _ASM_X86_AMD_IOMMU_PROTO_H
 
-struct amd_iommu;
+#include <asm/amd_iommu_types.h>
 
 extern int amd_iommu_init_dma_ops(void);
 extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
 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);
 extern void amd_iommu_apply_erratum_63(u16 devid);
 extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
@@ -44,4 +43,12 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev)
 	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
 }
 
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+		return false;
+
+	return !!(iommu->features & f);
+}
+
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index e3509fc303b..4c998299541 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -68,12 +68,25 @@
 #define MMIO_CONTROL_OFFSET     0x0018
 #define MMIO_EXCL_BASE_OFFSET   0x0020
 #define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_EXT_FEATURES	0x0030
 #define MMIO_CMD_HEAD_OFFSET	0x2000
 #define MMIO_CMD_TAIL_OFFSET	0x2008
 #define MMIO_EVT_HEAD_OFFSET	0x2010
 #define MMIO_EVT_TAIL_OFFSET	0x2018
 #define MMIO_STATUS_OFFSET	0x2020
 
+
+/* Extended Feature Bits */
+#define FEATURE_PREFETCH	(1ULL<<0)
+#define FEATURE_PPR		(1ULL<<1)
+#define FEATURE_X2APIC		(1ULL<<2)
+#define FEATURE_NX		(1ULL<<3)
+#define FEATURE_GT		(1ULL<<4)
+#define FEATURE_IA		(1ULL<<6)
+#define FEATURE_GA		(1ULL<<7)
+#define FEATURE_HE		(1ULL<<8)
+#define FEATURE_PC		(1ULL<<9)
+
 /* MMIO status bits */
 #define MMIO_STATUS_COM_WAIT_INT_MASK	0x04
 
@@ -113,7 +126,9 @@
 /* command specific defines */
 #define CMD_COMPL_WAIT          0x01
 #define CMD_INV_DEV_ENTRY       0x02
-#define CMD_INV_IOMMU_PAGES     0x03
+#define CMD_INV_IOMMU_PAGES	0x03
+#define CMD_INV_IOTLB_PAGES	0x04
+#define CMD_INV_ALL		0x08
 
 #define CMD_COMPL_WAIT_STORE_MASK	0x01
 #define CMD_COMPL_WAIT_INT_MASK		0x02
@@ -215,6 +230,8 @@
 #define IOMMU_PTE_IR (1ULL << 61)
 #define IOMMU_PTE_IW (1ULL << 62)
 
+#define DTE_FLAG_IOTLB	0x01
+
 #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
 #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
 #define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
@@ -227,6 +244,7 @@
 /* IOMMU capabilities */
 #define IOMMU_CAP_IOTLB   24
 #define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR     27
 
 #define MAX_DOMAIN_ID 65536
 
@@ -249,6 +267,8 @@ extern bool amd_iommu_dump;
 
 /* global flag if IOMMUs cache non-present entries */
 extern bool amd_iommu_np_cache;
+/* Only true if all IOMMUs support device IOTLBs */
+extern bool amd_iommu_iotlb_sup;
 
 /*
  * Make iterating over all IOMMUs easier
@@ -371,6 +391,9 @@ struct amd_iommu {
 	/* flags read from acpi table */
 	u8 acpi_flags;
 
+	/* Extended features */
+	u64 features;
+
 	/*
 	 * Capability pointer. There could be more than one IOMMU per PCI
 	 * device function if there are more than one AMD IOMMU capability
@@ -409,9 +432,6 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
-	/* becomes true if a command buffer reset is running */
-	bool reset_in_progress;
-
 	/* default dma_ops domain for that IOMMU */
 	struct dma_ops_domain *default_dom;
 
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 331682231bb..67f87f25761 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -11,7 +11,6 @@ struct amd_nb_bus_dev_range {
 
 extern const struct pci_device_id amd_nb_misc_ids[];
 extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
-struct bootnode;
 
 extern bool early_is_amd_nb(u32 value);
 extern int amd_cache_northbridges(void);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 2b7d573be54..a0c46f06121 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -363,7 +363,12 @@ struct apic {
 	 */
 	int (*x86_32_early_logical_apicid)(int cpu);
 
-	/* determine CPU -> NUMA node mapping */
+	/*
+	 * Optional method called from setup_local_APIC() after logical
+	 * apicid is guaranteed to be known to initialize apicid -> node
+	 * mapping if NUMA initialization hasn't done so already.  Don't
+	 * add new users.
+	 */
 	int (*x86_32_numa_cpu_node)(int cpu);
 #endif
 };
@@ -537,8 +542,6 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 	return cpuid_apic >> index_msb;
 }
 
-extern int default_x86_32_numa_cpu_node(int cpu);
-
 #endif
 
 static inline unsigned int
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index 3c7521063d3..aa6a3170ab5 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -4,16 +4,40 @@
 #include <asm/io.h>
 
 /*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E.
+ * Returns physical address of EBDA.  Returns 0 if there is no EBDA.
  */
 static inline unsigned int get_bios_ebda(void)
 {
+	/*
+	 * There is a real-mode segmented pointer pointing to the
+	 * 4K EBDA area at 0x40E.
+	 */
 	unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
 	address <<= 4;
 	return address;	/* 0 means none */
 }
 
+/*
+ * Return the sanitized length of the EBDA in bytes, if it exists.
+ */
+static inline unsigned int get_bios_ebda_length(void)
+{
+	unsigned int address;
+	unsigned int length;
+
+	address = get_bios_ebda();
+	if (!address)
+		return 0;
+
+	/* EBDA length is byte 0 of the EBDA (stored in KiB) */
+	length = *(unsigned char *)phys_to_virt(address);
+	length <<= 10;
+
+	/* Trim the length if it extends beyond 640KiB */
+	length = min_t(unsigned int, (640 * 1024) - address, length);
+	return length;
+}
+
 void reserve_ebda_region(void);
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 91f3e087cf2..5dc6acc98db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -195,6 +195,8 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -207,8 +209,7 @@ extern const char * const x86_power_flags[32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define cpu_has(c, bit)							\
-	(__builtin_constant_p(bit) &&					\
+#define REQUIRED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
 	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
 	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
@@ -218,10 +219,16 @@ extern const char * const x86_power_flags[32];
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
 	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
 	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )	\
-	  ? 1 :								\
+	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit)							\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
 
+#define this_cpu_has(bit)						\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
+	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 057099e5fab..0bdb0c54d9a 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -69,22 +69,18 @@
 
 #define MAX_DMA_CHANNELS	8
 
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
-
-#else
-
 /* 16MB ISA DMA zone */
 #define MAX_DMA_PFN   ((16 * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
 #define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
 
+#ifdef CONFIG_X86_32
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
+#else
 /* Compat define for old dma zone */
 #define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
 #endif
 
 /* 8237 DMA controllers */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8e4a16508d4..7093e4a6a0b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,6 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c2278be..268c783ab1c 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -38,11 +38,10 @@ extern void mcount(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
-	 * call mcount is "e8 <4 byte offset>"
-	 * The addr points to the 4 byte offset and the caller of this
-	 * function wants the pointer to e8. Simply subtract one.
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
 	 */
-	return addr - 1;
+	return addr;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
index fc1f579fb96..65aaa91d585 100644
--- a/arch/x86/include/asm/i8253.h
+++ b/arch/x86/include/asm/i8253.h
@@ -6,6 +6,8 @@
 #define PIT_CH0			0x40
 #define PIT_CH2			0x42
 
+#define PIT_LATCH	LATCH
+
 extern raw_spinlock_t i8253_lock;
 
 extern struct clock_event_device *global_clock_event;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 574dbc22893..a32b18ce6ea 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -5,20 +5,25 @@
 
 #include <linux/types.h>
 #include <asm/nops.h>
+#include <asm/asm.h>
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
-
-# define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:"					\
-			JUMP_LABEL_INITIAL_NOP			\
-			".pushsection __jump_table,  \"aw\" \n\t"\
-			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
-			".popsection \n\t"			\
-			: :  "i" (key) :  : label);		\
-	} while (0)
+#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:"
+		JUMP_LABEL_INITIAL_NOP
+		".pushsection __jump_table,  \"aw\" \n\t"
+		_ASM_ALIGN "\n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+		".popsection \n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index eb16e94ae04..021979a6e23 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -142,8 +142,6 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
-extern void (*x86_mce_decode_callback)(struct mce *m);
-
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 91df7c51806..5e83a416eca 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -13,31 +13,11 @@ extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)	(node_data[nid])
 
 #include <asm/numaq.h>
-/* summit or generic arch */
-#include <asm/srat.h>
-
-extern int get_memcfg_numa_flat(void);
-/*
- * This allows any one NUMA architecture to be compiled
- * for, and still fall back to the flat function if it
- * fails.
- */
-static inline void get_memcfg_numa(void)
-{
-
-	if (get_memcfg_numaq())
-		return;
-	if (get_memcfg_from_srat())
-		return;
-	get_memcfg_numa_flat();
-}
 
 extern void resume_map_numa_kva(pgd_t *pgd);
 
 #else /* !CONFIG_NUMA */
 
-#define get_memcfg_numa get_memcfg_numa_flat
-
 static inline void resume_map_numa_kva(pgd_t *pgd) {}
 
 #endif /* CONFIG_NUMA */
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index 288b96f815a..b3f88d7867c 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -4,36 +4,13 @@
 #ifndef _ASM_X86_MMZONE_64_H
 #define _ASM_X86_MMZONE_64_H
 
-
 #ifdef CONFIG_NUMA
 
 #include <linux/mmdebug.h>
-
 #include <asm/smp.h>
 
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
-	int shift;
-	unsigned int mapsize;
-	s16 *map;
-	s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
 extern struct pglist_data *node_data[];
 
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
-	unsigned nid;
-	VIRTUAL_BUG_ON(!memnodemap);
-	nid = memnodemap[addr >> memnode_shift];
-	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
-	return nid;
-}
-
 #define NODE_DATA(nid)		(node_data[nid])
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 67763c5d8b4..9eae7752ae9 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -35,7 +35,7 @@
 #define MODULE_PROC_FAMILY "K7 "
 #elif defined CONFIG_MK8
 #define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_X86_ELAN
+#elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
 #define MODULE_PROC_FAMILY "CRUSOE "
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index af788496020..405b4032a60 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -1,7 +1,13 @@
 #ifndef _ASM_X86_NOPS_H
 #define _ASM_X86_NOPS_H
 
-/* Define nops for use with alternative() */
+/*
+ * Define nops for use with alternative() and for tracing.
+ *
+ * *_NOP5_ATOMIC must be a single instruction.
+ */
+
+#define NOP_DS_PREFIX 0x3e
 
 /* generic versions from gas
    1: nop
@@ -13,14 +19,15 @@
    6: leal 0x00000000(%esi),%esi
    7: leal 0x00000000(,%esi,1),%esi
 */
-#define GENERIC_NOP1 ".byte 0x90\n"
-#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
-#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
-#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
-#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
-#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
+#define GENERIC_NOP1 0x90
+#define GENERIC_NOP2 0x89,0xf6
+#define GENERIC_NOP3 0x8d,0x76,0x00
+#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
+#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
+#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
+#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
+#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
 
 /* Opteron 64bit nops
    1: nop
@@ -29,13 +36,14 @@
    4: osp osp osp nop
 */
 #define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2	".byte 0x66,0x90\n"
-#define K8_NOP3	".byte 0x66,0x66,0x90\n"
-#define K8_NOP4	".byte 0x66,0x66,0x66,0x90\n"
-#define K8_NOP5	K8_NOP3 K8_NOP2
-#define K8_NOP6	K8_NOP3 K8_NOP3
-#define K8_NOP7	K8_NOP4 K8_NOP3
-#define K8_NOP8	K8_NOP4 K8_NOP4
+#define K8_NOP2	0x66,K8_NOP1
+#define K8_NOP3	0x66,K8_NOP2
+#define K8_NOP4	0x66,K8_NOP3
+#define K8_NOP5	K8_NOP3,K8_NOP2
+#define K8_NOP6	K8_NOP3,K8_NOP3
+#define K8_NOP7	K8_NOP4,K8_NOP3
+#define K8_NOP8	K8_NOP4,K8_NOP4
+#define K8_NOP5_ATOMIC 0x66,K8_NOP4
 
 /* K7 nops
    uses eax dependencies (arbitrary choice)
@@ -47,13 +55,14 @@
    7: leal 0x00000000(,%eax,1),%eax
 */
 #define K7_NOP1	GENERIC_NOP1
-#define K7_NOP2	".byte 0x8b,0xc0\n"
-#define K7_NOP3	".byte 0x8d,0x04,0x20\n"
-#define K7_NOP4	".byte 0x8d,0x44,0x20,0x00\n"
-#define K7_NOP5	K7_NOP4 ASM_NOP1
-#define K7_NOP6	".byte 0x8d,0x80,0,0,0,0\n"
-#define K7_NOP7	".byte 0x8D,0x04,0x05,0,0,0,0\n"
-#define K7_NOP8	K7_NOP7 ASM_NOP1
+#define K7_NOP2	0x8b,0xc0
+#define K7_NOP3	0x8d,0x04,0x20
+#define K7_NOP4	0x8d,0x44,0x20,0x00
+#define K7_NOP5	K7_NOP4,K7_NOP1
+#define K7_NOP6	0x8d,0x80,0,0,0,0
+#define K7_NOP7	0x8D,0x04,0x05,0,0,0,0
+#define K7_NOP8	K7_NOP7,K7_NOP1
+#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
 
 /* P6 nops
    uses eax dependencies (Intel-recommended choice)
@@ -69,52 +78,65 @@
 	There is kernel code that depends on this.
 */
 #define P6_NOP1	GENERIC_NOP1
-#define P6_NOP2	".byte 0x66,0x90\n"
-#define P6_NOP3	".byte 0x0f,0x1f,0x00\n"
-#define P6_NOP4	".byte 0x0f,0x1f,0x40,0\n"
-#define P6_NOP5	".byte 0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP6	".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP7	".byte 0x0f,0x1f,0x80,0,0,0,0\n"
-#define P6_NOP8	".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+#define P6_NOP2	0x66,0x90
+#define P6_NOP3	0x0f,0x1f,0x00
+#define P6_NOP4	0x0f,0x1f,0x40,0
+#define P6_NOP5	0x0f,0x1f,0x44,0x00,0
+#define P6_NOP6	0x66,0x0f,0x1f,0x44,0x00,0
+#define P6_NOP7	0x0f,0x1f,0x80,0,0,0,0
+#define P6_NOP8	0x0f,0x1f,0x84,0x00,0,0,0,0
+#define P6_NOP5_ATOMIC P6_NOP5
+
+#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
 
 #if defined(CONFIG_MK7)
-#define ASM_NOP1 K7_NOP1
-#define ASM_NOP2 K7_NOP2
-#define ASM_NOP3 K7_NOP3
-#define ASM_NOP4 K7_NOP4
-#define ASM_NOP5 K7_NOP5
-#define ASM_NOP6 K7_NOP6
-#define ASM_NOP7 K7_NOP7
-#define ASM_NOP8 K7_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
 #elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 P6_NOP1
-#define ASM_NOP2 P6_NOP2
-#define ASM_NOP3 P6_NOP3
-#define ASM_NOP4 P6_NOP4
-#define ASM_NOP5 P6_NOP5
-#define ASM_NOP6 P6_NOP6
-#define ASM_NOP7 P6_NOP7
-#define ASM_NOP8 P6_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
 #elif defined(CONFIG_X86_64)
-#define ASM_NOP1 K8_NOP1
-#define ASM_NOP2 K8_NOP2
-#define ASM_NOP3 K8_NOP3
-#define ASM_NOP4 K8_NOP4
-#define ASM_NOP5 K8_NOP5
-#define ASM_NOP6 K8_NOP6
-#define ASM_NOP7 K8_NOP7
-#define ASM_NOP8 K8_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
 #else
-#define ASM_NOP1 GENERIC_NOP1
-#define ASM_NOP2 GENERIC_NOP2
-#define ASM_NOP3 GENERIC_NOP3
-#define ASM_NOP4 GENERIC_NOP4
-#define ASM_NOP5 GENERIC_NOP5
-#define ASM_NOP6 GENERIC_NOP6
-#define ASM_NOP7 GENERIC_NOP7
-#define ASM_NOP8 GENERIC_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
 #endif
 
 #define ASM_NOP_MAX 8
+#define NOP_ATOMIC5 (ASM_NOP_MAX+1)	/* Entry for the 5-byte atomic NOP */
+
+#ifndef __ASSEMBLY__
+extern const unsigned char * const *ideal_nops;
+extern void arch_init_ideal_nops(void);
+#endif
 
 #endif /* _ASM_X86_NOPS_H */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index a50fc9f493b..bfacd2ccf65 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,12 +1,24 @@
 #ifndef _ASM_X86_NUMA_H
 #define _ASM_X86_NUMA_H
 
+#include <linux/nodemask.h>
+
 #include <asm/topology.h>
 #include <asm/apicdef.h>
 
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
+#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
+
+/*
+ * 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 int numa_off;
 
 /*
  * __apicid_to_node[] stores the raw mapping between physical apicid and
@@ -17,15 +29,27 @@
  * numa_cpu_node().
  */
 extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern void __init numa_set_distance(int from, int to, int distance);
 
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
 	__apicid_to_node[apicid] = node;
 }
+
+extern int __cpuinit numa_cpu_node(int cpu);
+
 #else	/* CONFIG_NUMA */
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
 }
+
+static inline int numa_cpu_node(int cpu)
+{
+	return NUMA_NO_NODE;
+}
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_X86_32
@@ -37,14 +61,12 @@ static inline void set_apicid_to_node(int apicid, s16 node)
 #ifdef CONFIG_NUMA
 extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
-extern void __init numa_init_array(void);
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
 #else	/* CONFIG_NUMA */
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
-static inline void numa_init_array(void)		{ }
 static inline void init_cpu_to_node(void)		{ }
 static inline void numa_add_cpu(int cpu)		{ }
 static inline void numa_remove_cpu(int cpu)		{ }
@@ -54,4 +76,10 @@ static inline void numa_remove_cpu(int cpu)		{ }
 void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #endif
 
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
+#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
+void numa_emu_cmdline(char *);
+#endif /* CONFIG_NUMA_EMU */
+
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index c6beed1ef10..e7d6b825474 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -1,16 +1,6 @@
 #ifndef _ASM_X86_NUMA_32_H
 #define _ASM_X86_NUMA_32_H
 
-extern int numa_off;
-
-extern int pxm_to_nid(int pxm);
-
-#ifdef CONFIG_NUMA
-extern int __cpuinit numa_cpu_node(int cpu);
-#else	/* CONFIG_NUMA */
-static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
-#endif	/* CONFIG_NUMA */
-
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
 #else
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 344eb1790b4..0c05f7ae46e 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -1,42 +1,6 @@
 #ifndef _ASM_X86_NUMA_64_H
 #define _ASM_X86_NUMA_64_H
 
-#include <linux/nodemask.h>
-
-struct bootnode {
-	u64 start;
-	u64 end;
-};
-
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
-
-extern int numa_off;
-
 extern unsigned long numa_free_all_bootmem(void);
-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 nodemask_t numa_nodes_parsed __initdata;
-
-extern int __cpuinit numa_cpu_node(int cpu);
-extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
-extern void __init numa_set_distance(int from, int to, int distance);
-
-#ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
-#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
-void numa_emu_cmdline(char *);
-#endif /* CONFIG_NUMA_EMU */
-#else
-static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
-#endif
 
 #endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 37c516545ec..c3b3c322fd8 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -29,7 +29,7 @@
 #ifdef CONFIG_X86_NUMAQ
 
 extern int found_numaq;
-extern int get_memcfg_numaq(void);
+extern int numaq_numa_init(void);
 extern int pci_numaq_init(void);
 
 extern void *xquad_portio;
@@ -166,11 +166,6 @@ struct sys_cfg_data {
 
 void numaq_tsc_disable(void);
 
-#else
-static inline int get_memcfg_numaq(void)
-{
-	return 0;
-}
 #endif /* CONFIG_X86_NUMAQ */
 #endif /* _ASM_X86_NUMAQ_H */
 
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index c5d3a5abbb9..24487712e0b 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -26,15 +26,12 @@ extern void setup_olpc_ofw_pgd(void);
 /* check if OFW was detected during boot */
 extern bool olpc_ofw_present(void);
 
+extern void olpc_dt_build_devicetree(void);
+
 #else /* !CONFIG_OLPC */
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
-#endif /* !CONFIG_OLPC */
-
-#ifdef CONFIG_OF_PROMTREE
-extern void olpc_dt_build_devicetree(void);
-#else
 static inline void olpc_dt_build_devicetree(void) { }
-#endif
+#endif /* !CONFIG_OLPC */
 
 #endif /* _ASM_X86_OLPC_OFW_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d475b4398d8..53278b0dfdf 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -517,7 +517,7 @@ do {									\
 	typeof(o2) __o2 = o2;						\
 	typeof(o2) __n2 = n2;						\
 	typeof(o2) __dummy;						\
-	alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4,	\
+	alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4,	\
 		       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",	\
 		       X86_FEATURE_CX16,				\
 		       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),		\
@@ -542,6 +542,33 @@ do {									\
 	old__;								\
 })
 
+static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+                        const unsigned long __percpu *addr)
+{
+	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+	return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+}
+
+static inline int x86_this_cpu_variable_test_bit(int nr,
+                        const unsigned long __percpu *addr)
+{
+	int oldbit;
+
+	asm volatile("bt "__percpu_arg(2)",%1\n\t"
+			"sbb %0,%0"
+			: "=r" (oldbit)
+			: "m" (*(unsigned long *)addr), "Ir" (nr));
+
+	return oldbit;
+}
+
+#define x86_this_cpu_test_bit(nr, addr)			\
+	(__builtin_constant_p((nr))			\
+	 ? x86_this_cpu_constant_test_bit((nr), (addr))	\
+	 : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
diff --git a/arch/x86/include/asm/probe_roms.h b/arch/x86/include/asm/probe_roms.h
new file mode 100644
index 00000000000..4950a0b1d09
--- /dev/null
+++ b/arch/x86/include/asm/probe_roms.h
@@ -0,0 +1,8 @@
+#ifndef _PROBE_ROMS_H_
+#define _PROBE_ROMS_H_
+struct pci_dev;
+
+extern void __iomem *pci_map_biosrom(struct pci_dev *pdev);
+extern void pci_unmap_biosrom(void __iomem *rom);
+extern size_t pci_biosrom_size(struct pci_dev *pdev);
+#endif
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index a898a2b6e10..59ab4dffa37 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -60,6 +60,7 @@
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
+#define X86_CR4_SMEP	0x00100000 /* enable SMEP support */
 
 /*
  * x86-64 Task Priority Register, CR8
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index db8aa19a08a..9756551ec76 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -88,7 +88,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard.text) __used			\
+	static void __section(.discard.text) __used notrace		\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \
@@ -104,10 +104,10 @@ void *extend_brk(size_t size, size_t align);
 	type *name;					\
 	RESERVE_BRK(name, sizeof(type) * entries)
 
+extern void probe_roms(void);
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
-extern void probe_roms(void);
 
 #else
 void __init x86_64_start_kernel(char *real_mode);
diff --git a/arch/x86/include/asm/srat.h b/arch/x86/include/asm/srat.h
deleted file mode 100644
index b508d639d1a..00000000000
--- a/arch/x86/include/asm/srat.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * 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 as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-
-#ifndef _ASM_X86_SRAT_H
-#define _ASM_X86_SRAT_H
-
-#ifdef CONFIG_ACPI_NUMA
-extern int get_memcfg_from_srat(void);
-#else
-static inline int get_memcfg_from_srat(void)
-{
-	return 0;
-}
-#endif
-
-#endif /* _ASM_X86_SRAT_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index d7e89c83645..70bbe39043a 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -37,9 +37,6 @@ print_context_stack_bp(struct thread_info *tinfo,
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
-	void (*warning)(void *data, char *msg);
-	/* msg must contain %s for the symbol */
-	void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
 	void (*address)(void *data, unsigned long address, int reliable);
 	/* On negative return stop dumping */
 	int (*stack)(void *data, char *name);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 12569e691ce..c2ff2a1d845 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -303,24 +303,81 @@ static inline void native_wbinvd(void)
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define read_cr0()	(native_read_cr0())
-#define write_cr0(x)	(native_write_cr0(x))
-#define read_cr2()	(native_read_cr2())
-#define write_cr2(x)	(native_write_cr2(x))
-#define read_cr3()	(native_read_cr3())
-#define write_cr3(x)	(native_write_cr3(x))
-#define read_cr4()	(native_read_cr4())
-#define read_cr4_safe()	(native_read_cr4_safe())
-#define write_cr4(x)	(native_write_cr4(x))
-#define wbinvd()	(native_wbinvd())
+
+static inline unsigned long read_cr0(void)
+{
+	return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+	native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+	return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+	native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+	return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+	native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+	return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+	return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+	native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+	native_wbinvd();
+}
+
 #ifdef CONFIG_X86_64
-#define read_cr8()	(native_read_cr8())
-#define write_cr8(x)	(native_write_cr8(x))
-#define load_gs_index   native_load_gs_index
+
+static inline unsigned long read_cr8(void)
+{
+	return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+	native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+	native_load_gs_index(selector);
+}
+
 #endif
 
 /* Clear the 'TS' bit */
-#define clts()		(native_clts())
+static inline void clts(void)
+{
+	native_clts();
+}
 
 #endif/* CONFIG_PARAVIRT */
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 910a7084f7f..c00692476e9 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -93,19 +93,11 @@ extern void setup_node_to_cpumask_map(void);
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
 #ifdef CONFIG_X86_32
-extern unsigned long node_start_pfn[];
-extern unsigned long node_end_pfn[];
-extern unsigned long node_remap_size[];
-#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
-
 # define SD_CACHE_NICE_TRIES	1
 # define SD_IDLE_IDX		1
-
 #else
-
 # define SD_CACHE_NICE_TRIES	2
 # define SD_IDLE_IDX		2
-
 #endif
 
 /* sched_domains SD_NODE_INIT for NUMA machines */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index abd3e0ea762..99f0ad753f3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -42,7 +42,7 @@
  * Returns 0 if the range is valid, nonzero otherwise.
  *
  * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
  *
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c61934fbf22..64a619d47d3 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -47,8 +47,9 @@ extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 					     unsigned long pfn_e);
 
-extern int m2p_add_override(unsigned long mfn, struct page *page);
-extern int m2p_remove_override(struct page *page);
+extern int m2p_add_override(unsigned long mfn, struct page *page,
+			    bool clear_pte);
+extern int m2p_remove_override(struct page *page, bool clear_pte);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index aa862098916..4fbda9a3f33 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -15,10 +15,26 @@ static inline int pci_xen_hvm_init(void)
 #endif
 #if defined(CONFIG_XEN_DOM0)
 void __init xen_setup_pirqs(void);
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
 #else
 static inline void __init xen_setup_pirqs(void)
 {
 }
+static inline int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+	return -1;
+}
+static inline int xen_register_device_domain_owner(struct pci_dev *dev,
+						   uint16_t domain)
+{
+	return -1;
+}
+static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+	return -1;
+}
 #endif
 
 #if defined(CONFIG_PCI_MSI)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7338ef2218b..250806472a7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -36,7 +36,7 @@ obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
-obj-$(CONFIG_X86_32)	+= probe_roms_32.o
+obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
@@ -117,7 +117,7 @@ obj-$(CONFIG_OF)			+= devicetree.o
 ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_AUDIT)		+= audit_64.o
 
-	obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
+	obj-$(CONFIG_GART_IOMMU)	+= amd_gart_64.o aperture_64.o
 	obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
 	obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o amd_iommu.o
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index ff93bc1b09c..18a857ba7a2 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -112,11 +112,6 @@ static int __init acpi_sleep_setup(char *str)
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
 			acpi_no_s4_hw_signature();
-		if (strncmp(str, "s4_nonvs", 8) == 0) {
-			pr_warning("ACPI: acpi_sleep=s4_nonvs is deprecated, "
-					"please use acpi_sleep=nonvs instead");
-			acpi_nvs_nosave();
-		}
 #endif
 		if (strncmp(str, "nonvs", 5) == 0)
 			acpi_nvs_nosave();
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4a234677e21..a81f2d52f86 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -67,17 +67,30 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
 #define DPRINTK(fmt, args...) if (debug_alternative) \
 	printk(KERN_DEBUG fmt, args)
 
+/*
+ * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
+ * that correspond to that nop. Getting from one nop to the next, we
+ * add to the array the offset that is equal to the sum of all sizes of
+ * nops preceding the one we are after.
+ *
+ * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
+ * nice symmetry of sizes of the previous nops.
+ */
 #if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-/* Use inline assembly to define this because the nops are defined
-   as inline assembly strings in the include files and we cannot
-   get them easily into strings. */
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nintelnops: "
-	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
-	GENERIC_NOP7 GENERIC_NOP8
-    "\t.previous");
-extern const unsigned char intelnops[];
-static const unsigned char *const __initconst_or_module
-intel_nops[ASM_NOP_MAX+1] = {
+static const unsigned char intelnops[] =
+{
+	GENERIC_NOP1,
+	GENERIC_NOP2,
+	GENERIC_NOP3,
+	GENERIC_NOP4,
+	GENERIC_NOP5,
+	GENERIC_NOP6,
+	GENERIC_NOP7,
+	GENERIC_NOP8,
+	GENERIC_NOP5_ATOMIC
+};
+static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	intelnops,
 	intelnops + 1,
@@ -87,17 +100,25 @@ intel_nops[ASM_NOP_MAX+1] = {
 	intelnops + 1 + 2 + 3 + 4 + 5,
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #ifdef K8_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk8nops: "
-	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-	K8_NOP7 K8_NOP8
-    "\t.previous");
-extern const unsigned char k8nops[];
-static const unsigned char *const __initconst_or_module
-k8_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k8nops[] =
+{
+	K8_NOP1,
+	K8_NOP2,
+	K8_NOP3,
+	K8_NOP4,
+	K8_NOP5,
+	K8_NOP6,
+	K8_NOP7,
+	K8_NOP8,
+	K8_NOP5_ATOMIC
+};
+static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	k8nops,
 	k8nops + 1,
@@ -107,17 +128,25 @@ k8_nops[ASM_NOP_MAX+1] = {
 	k8nops + 1 + 2 + 3 + 4 + 5,
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk7nops: "
-	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-	K7_NOP7 K7_NOP8
-    "\t.previous");
-extern const unsigned char k7nops[];
-static const unsigned char *const __initconst_or_module
-k7_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k7nops[] =
+{
+	K7_NOP1,
+	K7_NOP2,
+	K7_NOP3,
+	K7_NOP4,
+	K7_NOP5,
+	K7_NOP6,
+	K7_NOP7,
+	K7_NOP8,
+	K7_NOP5_ATOMIC
+};
+static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	k7nops,
 	k7nops + 1,
@@ -127,17 +156,25 @@ k7_nops[ASM_NOP_MAX+1] = {
 	k7nops + 1 + 2 + 3 + 4 + 5,
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #ifdef P6_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\np6nops: "
-	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
-	P6_NOP7 P6_NOP8
-    "\t.previous");
-extern const unsigned char p6nops[];
-static const unsigned char *const __initconst_or_module
-p6_nops[ASM_NOP_MAX+1] = {
+static const unsigned char  __initconst_or_module p6nops[] =
+{
+	P6_NOP1,
+	P6_NOP2,
+	P6_NOP3,
+	P6_NOP4,
+	P6_NOP5,
+	P6_NOP6,
+	P6_NOP7,
+	P6_NOP8,
+	P6_NOP5_ATOMIC
+};
+static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	p6nops,
 	p6nops + 1,
@@ -147,47 +184,65 @@ p6_nops[ASM_NOP_MAX+1] = {
 	p6nops + 1 + 2 + 3 + 4 + 5,
 	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
 	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
+/* Initialize these to a safe default */
 #ifdef CONFIG_X86_64
+const unsigned char * const *ideal_nops = p6_nops;
+#else
+const unsigned char * const *ideal_nops = intel_nops;
+#endif
 
-extern char __vsyscall_0;
-static const unsigned char *const *__init_or_module find_nop_table(void)
+void __init arch_init_ideal_nops(void)
 {
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_has(X86_FEATURE_NOPL))
-		return p6_nops;
-	else
-		return k8_nops;
-}
-
-#else /* CONFIG_X86_64 */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		/*
+		 * Due to a decoder implementation quirk, some
+		 * specific Intel CPUs actually perform better with
+		 * the "k8_nops" than with the SDM-recommended NOPs.
+		 */
+		if (boot_cpu_data.x86 == 6 &&
+		    boot_cpu_data.x86_model >= 0x0f &&
+		    boot_cpu_data.x86_model != 0x1c &&
+		    boot_cpu_data.x86_model != 0x26 &&
+		    boot_cpu_data.x86_model != 0x27 &&
+		    boot_cpu_data.x86_model < 0x30) {
+			ideal_nops = k8_nops;
+		} else if (boot_cpu_has(X86_FEATURE_NOPL)) {
+			   ideal_nops = p6_nops;
+		} else {
+#ifdef CONFIG_X86_64
+			ideal_nops = k8_nops;
+#else
+			ideal_nops = intel_nops;
+#endif
+		}
 
-static const unsigned char *const *__init_or_module find_nop_table(void)
-{
-	if (boot_cpu_has(X86_FEATURE_K8))
-		return k8_nops;
-	else if (boot_cpu_has(X86_FEATURE_K7))
-		return k7_nops;
-	else if (boot_cpu_has(X86_FEATURE_NOPL))
-		return p6_nops;
-	else
-		return intel_nops;
+	default:
+#ifdef CONFIG_X86_64
+		ideal_nops = k8_nops;
+#else
+		if (boot_cpu_has(X86_FEATURE_K8))
+			ideal_nops = k8_nops;
+		else if (boot_cpu_has(X86_FEATURE_K7))
+			ideal_nops = k7_nops;
+		else
+			ideal_nops = intel_nops;
+#endif
+	}
 }
 
-#endif /* CONFIG_X86_64 */
-
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void __init_or_module add_nops(void *insns, unsigned int len)
 {
-	const unsigned char *const *noptable = find_nop_table();
-
 	while (len > 0) {
 		unsigned int noplen = len;
 		if (noplen > ASM_NOP_MAX)
 			noplen = ASM_NOP_MAX;
-		memcpy(insns, noptable[noplen], noplen);
+		memcpy(insns, ideal_nops[noplen], noplen);
 		insns += noplen;
 		len -= noplen;
 	}
@@ -195,6 +250,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
+extern char __vsyscall_0;
 void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
@@ -210,6 +266,15 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	u8 insnbuf[MAX_PATCH_LEN];
 
 	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+	/*
+	 * The scan order should be from start to end. A later scanned
+	 * alternative code can overwrite a previous scanned alternative code.
+	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
+	 * patch code.
+	 *
+	 * So be careful if you want to change the scan order to any other
+	 * order.
+	 */
 	for (a = start; a < end; a++) {
 		u8 *instr = a->instr;
 		BUG_ON(a->replacementlen > a->instrlen);
@@ -678,29 +743,3 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 	wrote_text = 0;
 	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 }
-
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-
-#ifdef CONFIG_X86_64
-unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
-#else
-unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
-#endif
-
-void __init arch_init_ideal_nop5(void)
-{
-	/*
-	 * There is no good nop for all x86 archs.  This selection
-	 * algorithm should be unified with the one in find_nop_table(),
-	 * but this should be good enough for now.
-	 *
-	 * For cases other than the ones below, use the safe (as in
-	 * always functional) defaults above.
-	 */
-#ifdef CONFIG_X86_64
-	/* Don't use these on 32 bits due to broken virtualizers */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		memcpy(ideal_nop5, p6_nops[5], 5);
-#endif
-}
-#endif
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b117efd24f7..b117efd24f7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 57ca7778722..873e7e1ead7 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/pci-ats.h>
 #include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
@@ -25,6 +26,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/iommu-helper.h>
 #include <linux/iommu.h>
+#include <linux/delay.h>
 #include <asm/proto.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
@@ -34,7 +36,7 @@
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
-#define EXIT_LOOP_COUNT 10000000
+#define LOOP_TIMEOUT	100000
 
 static DEFINE_RWLOCK(amd_iommu_devtable_lock);
 
@@ -57,7 +59,6 @@ struct iommu_cmd {
 	u32 data[4];
 };
 
-static void reset_iommu_command_buffer(struct amd_iommu *iommu);
 static void update_domain(struct protection_domain *domain);
 
 /****************************************************************************
@@ -322,8 +323,6 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 		break;
 	case EVENT_TYPE_ILL_CMD:
 		printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
-		iommu->reset_in_progress = true;
-		reset_iommu_command_buffer(iommu);
 		dump_command(address);
 		break;
 	case EVENT_TYPE_CMD_HARD_ERR:
@@ -367,7 +366,7 @@ static void iommu_poll_events(struct amd_iommu *iommu)
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-irqreturn_t amd_iommu_int_handler(int irq, void *data)
+irqreturn_t amd_iommu_int_thread(int irq, void *data)
 {
 	struct amd_iommu *iommu;
 
@@ -377,192 +376,300 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+irqreturn_t amd_iommu_int_handler(int irq, void *data)
+{
+	return IRQ_WAKE_THREAD;
+}
+
 /****************************************************************************
  *
  * IOMMU command queuing functions
  *
  ****************************************************************************/
 
-/*
- * Writes the command to the IOMMUs command buffer and informs the
- * hardware about the new command. Must be called with iommu->lock held.
- */
-static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
+static int wait_on_sem(volatile u64 *sem)
+{
+	int i = 0;
+
+	while (*sem == 0 && i < LOOP_TIMEOUT) {
+		udelay(1);
+		i += 1;
+	}
+
+	if (i == LOOP_TIMEOUT) {
+		pr_alert("AMD-Vi: Completion-Wait loop timed out\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void copy_cmd_to_buffer(struct amd_iommu *iommu,
+			       struct iommu_cmd *cmd,
+			       u32 tail)
 {
-	u32 tail, head;
 	u8 *target;
 
-	WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
-	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 	target = iommu->cmd_buf + tail;
-	memcpy_toio(target, cmd, sizeof(*cmd));
-	tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
-	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
-	if (tail == head)
-		return -ENOMEM;
+	tail   = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
+
+	/* Copy command to buffer */
+	memcpy(target, cmd, sizeof(*cmd));
+
+	/* Tell the IOMMU about it */
 	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+}
 
-	return 0;
+static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
+{
+	WARN_ON(address & 0x7ULL);
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[0] = lower_32_bits(__pa(address)) | CMD_COMPL_WAIT_STORE_MASK;
+	cmd->data[1] = upper_32_bits(__pa(address));
+	cmd->data[2] = 1;
+	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
+}
+
+static void build_inv_dte(struct iommu_cmd *cmd, u16 devid)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[0] = devid;
+	CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY);
+}
+
+static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
+				  size_t size, u16 domid, int pde)
+{
+	u64 pages;
+	int s;
+
+	pages = iommu_num_pages(address, size, PAGE_SIZE);
+	s     = 0;
+
+	if (pages > 1) {
+		/*
+		 * If we have to flush more than one page, flush all
+		 * TLB entries for this domain
+		 */
+		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+		s = 1;
+	}
+
+	address &= PAGE_MASK;
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[1] |= domid;
+	cmd->data[2]  = lower_32_bits(address);
+	cmd->data[3]  = upper_32_bits(address);
+	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
+	if (s) /* size bit - we flush more than one 4kb page */
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+	if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+}
+
+static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
+				  u64 address, size_t size)
+{
+	u64 pages;
+	int s;
+
+	pages = iommu_num_pages(address, size, PAGE_SIZE);
+	s     = 0;
+
+	if (pages > 1) {
+		/*
+		 * If we have to flush more than one page, flush all
+		 * TLB entries for this domain
+		 */
+		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+		s = 1;
+	}
+
+	address &= PAGE_MASK;
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[0]  = devid;
+	cmd->data[0] |= (qdep & 0xff) << 24;
+	cmd->data[1]  = devid;
+	cmd->data[2]  = lower_32_bits(address);
+	cmd->data[3]  = upper_32_bits(address);
+	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+	if (s)
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+}
+
+static void build_inv_all(struct iommu_cmd *cmd)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	CMD_SET_TYPE(cmd, CMD_INV_ALL);
 }
 
 /*
- * General queuing function for commands. Takes iommu->lock and calls
- * __iommu_queue_command().
+ * Writes the command to the IOMMUs command buffer and informs the
+ * hardware about the new command.
  */
 static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 {
+	u32 left, tail, head, next_tail;
 	unsigned long flags;
-	int ret;
 
+	WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
+
+again:
 	spin_lock_irqsave(&iommu->lock, flags);
-	ret = __iommu_queue_command(iommu, cmd);
-	if (!ret)
-		iommu->need_sync = true;
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
-	return ret;
-}
+	head      = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	tail      = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	next_tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
+	left      = (head - next_tail) % iommu->cmd_buf_size;
 
-/*
- * This function waits until an IOMMU has completed a completion
- * wait command
- */
-static void __iommu_wait_for_completion(struct amd_iommu *iommu)
-{
-	int ready = 0;
-	unsigned status = 0;
-	unsigned long i = 0;
+	if (left <= 2) {
+		struct iommu_cmd sync_cmd;
+		volatile u64 sem = 0;
+		int ret;
 
-	INC_STATS_COUNTER(compl_wait);
+		build_completion_wait(&sync_cmd, (u64)&sem);
+		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
 
-	while (!ready && (i < EXIT_LOOP_COUNT)) {
-		++i;
-		/* wait for the bit to become one */
-		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
-		ready = status & MMIO_STATUS_COM_WAIT_INT_MASK;
+		spin_unlock_irqrestore(&iommu->lock, flags);
+
+		if ((ret = wait_on_sem(&sem)) != 0)
+			return ret;
+
+		goto again;
 	}
 
-	/* set bit back to zero */
-	status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
-	writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
+	copy_cmd_to_buffer(iommu, cmd, tail);
+
+	/* We need to sync now to make sure all commands are processed */
+	iommu->need_sync = true;
+
+	spin_unlock_irqrestore(&iommu->lock, flags);
 
-	if (unlikely(i == EXIT_LOOP_COUNT))
-		iommu->reset_in_progress = true;
+	return 0;
 }
 
 /*
  * This function queues a completion wait command into the command
  * buffer of an IOMMU
  */
-static int __iommu_completion_wait(struct amd_iommu *iommu)
+static int iommu_completion_wait(struct amd_iommu *iommu)
 {
 	struct iommu_cmd cmd;
+	volatile u64 sem = 0;
+	int ret;
 
-	 memset(&cmd, 0, sizeof(cmd));
-	 cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
-	 CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
+	if (!iommu->need_sync)
+		return 0;
 
-	 return __iommu_queue_command(iommu, &cmd);
+	build_completion_wait(&cmd, (u64)&sem);
+
+	ret = iommu_queue_command(iommu, &cmd);
+	if (ret)
+		return ret;
+
+	return wait_on_sem(&sem);
 }
 
-/*
- * This function is called whenever we need to ensure that the IOMMU has
- * completed execution of all commands we sent. It sends a
- * COMPLETION_WAIT command and waits for it to finish. The IOMMU informs
- * us about that by writing a value to a physical address we pass with
- * the command.
- */
-static int iommu_completion_wait(struct amd_iommu *iommu)
+static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
 {
-	int ret = 0;
-	unsigned long flags;
+	struct iommu_cmd cmd;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	build_inv_dte(&cmd, devid);
 
-	if (!iommu->need_sync)
-		goto out;
+	return iommu_queue_command(iommu, &cmd);
+}
 
-	ret = __iommu_completion_wait(iommu);
+static void iommu_flush_dte_all(struct amd_iommu *iommu)
+{
+	u32 devid;
 
-	iommu->need_sync = false;
+	for (devid = 0; devid <= 0xffff; ++devid)
+		iommu_flush_dte(iommu, devid);
 
-	if (ret)
-		goto out;
-
-	__iommu_wait_for_completion(iommu);
+	iommu_completion_wait(iommu);
+}
 
-out:
-	spin_unlock_irqrestore(&iommu->lock, flags);
+/*
+ * This function uses heavy locking and may disable irqs for some time. But
+ * this is no issue because it is only called during resume.
+ */
+static void iommu_flush_tlb_all(struct amd_iommu *iommu)
+{
+	u32 dom_id;
 
-	if (iommu->reset_in_progress)
-		reset_iommu_command_buffer(iommu);
+	for (dom_id = 0; dom_id <= 0xffff; ++dom_id) {
+		struct iommu_cmd cmd;
+		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+				      dom_id, 1);
+		iommu_queue_command(iommu, &cmd);
+	}
 
-	return 0;
+	iommu_completion_wait(iommu);
 }
 
-static void iommu_flush_complete(struct protection_domain *domain)
+static void iommu_flush_all(struct amd_iommu *iommu)
 {
-	int i;
+	struct iommu_cmd cmd;
 
-	for (i = 0; i < amd_iommus_present; ++i) {
-		if (!domain->dev_iommu[i])
-			continue;
+	build_inv_all(&cmd);
 
-		/*
-		 * Devices of this domain are behind this IOMMU
-		 * We need to wait for completion of all commands.
-		 */
-		iommu_completion_wait(amd_iommus[i]);
+	iommu_queue_command(iommu, &cmd);
+	iommu_completion_wait(iommu);
+}
+
+void iommu_flush_all_caches(struct amd_iommu *iommu)
+{
+	if (iommu_feature(iommu, FEATURE_IA)) {
+		iommu_flush_all(iommu);
+	} else {
+		iommu_flush_dte_all(iommu);
+		iommu_flush_tlb_all(iommu);
 	}
 }
 
 /*
- * Command send function for invalidating a device table entry
+ * Command send function for flushing on-device TLB
  */
-static int iommu_flush_device(struct device *dev)
+static int device_flush_iotlb(struct device *dev, u64 address, size_t size)
 {
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
 	u16 devid;
+	int qdep;
 
+	qdep  = pci_ats_queue_depth(pdev);
 	devid = get_device_id(dev);
 	iommu = amd_iommu_rlookup_table[devid];
 
-	/* Build command */
-	memset(&cmd, 0, sizeof(cmd));
-	CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY);
-	cmd.data[0] = devid;
+	build_inv_iotlb_pages(&cmd, devid, qdep, address, size);
 
 	return iommu_queue_command(iommu, &cmd);
 }
 
-static void __iommu_build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-					  u16 domid, int pde, int s)
-{
-	memset(cmd, 0, sizeof(*cmd));
-	address &= PAGE_MASK;
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	cmd->data[1] |= domid;
-	cmd->data[2] = lower_32_bits(address);
-	cmd->data[3] = upper_32_bits(address);
-	if (s) /* size bit - we flush more than one 4kb page */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-	if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-}
-
 /*
- * Generic command send function for invalidaing TLB entries
+ * Command send function for invalidating a device table entry
  */
-static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
-		u64 address, u16 domid, int pde, int s)
+static int device_flush_dte(struct device *dev)
 {
-	struct iommu_cmd cmd;
+	struct amd_iommu *iommu;
+	struct pci_dev *pdev;
+	u16 devid;
 	int ret;
 
-	__iommu_build_inv_iommu_pages(&cmd, address, domid, pde, s);
+	pdev  = to_pci_dev(dev);
+	devid = get_device_id(dev);
+	iommu = amd_iommu_rlookup_table[devid];
 
-	ret = iommu_queue_command(iommu, &cmd);
+	ret = iommu_flush_dte(iommu, devid);
+	if (ret)
+		return ret;
+
+	if (pci_ats_enabled(pdev))
+		ret = device_flush_iotlb(dev, 0, ~0UL);
 
 	return ret;
 }
@@ -572,23 +679,14 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
  * It invalidates a single PTE if the range to flush is within a single
  * page. Otherwise it flushes the whole TLB of the IOMMU.
  */
-static void __iommu_flush_pages(struct protection_domain *domain,
-				u64 address, size_t size, int pde)
+static void __domain_flush_pages(struct protection_domain *domain,
+				 u64 address, size_t size, int pde)
 {
-	int s = 0, i;
-	unsigned long pages = iommu_num_pages(address, size, PAGE_SIZE);
-
-	address &= PAGE_MASK;
-
-	if (pages > 1) {
-		/*
-		 * If we have to flush more than one page, flush all
-		 * TLB entries for this domain
-		 */
-		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
-		s = 1;
-	}
+	struct iommu_dev_data *dev_data;
+	struct iommu_cmd cmd;
+	int ret = 0, i;
 
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
 
 	for (i = 0; i < amd_iommus_present; ++i) {
 		if (!domain->dev_iommu[i])
@@ -598,101 +696,70 @@ static void __iommu_flush_pages(struct protection_domain *domain,
 		 * Devices of this domain are behind this IOMMU
 		 * We need a TLB flush
 		 */
-		iommu_queue_inv_iommu_pages(amd_iommus[i], address,
-					    domain->id, pde, s);
+		ret |= iommu_queue_command(amd_iommus[i], &cmd);
+	}
+
+	list_for_each_entry(dev_data, &domain->dev_list, list) {
+		struct pci_dev *pdev = to_pci_dev(dev_data->dev);
+
+		if (!pci_ats_enabled(pdev))
+			continue;
+
+		ret |= device_flush_iotlb(dev_data->dev, address, size);
 	}
 
-	return;
+	WARN_ON(ret);
 }
 
-static void iommu_flush_pages(struct protection_domain *domain,
-			     u64 address, size_t size)
+static void domain_flush_pages(struct protection_domain *domain,
+			       u64 address, size_t size)
 {
-	__iommu_flush_pages(domain, address, size, 0);
+	__domain_flush_pages(domain, address, size, 0);
 }
 
 /* Flush the whole IO/TLB for a given protection domain */
-static void iommu_flush_tlb(struct protection_domain *domain)
+static void domain_flush_tlb(struct protection_domain *domain)
 {
-	__iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
+	__domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
-static void iommu_flush_tlb_pde(struct protection_domain *domain)
+static void domain_flush_tlb_pde(struct protection_domain *domain)
 {
-	__iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
-}
-
-
-/*
- * This function flushes the DTEs for all devices in domain
- */
-static void iommu_flush_domain_devices(struct protection_domain *domain)
-{
-	struct iommu_dev_data *dev_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(&domain->lock, flags);
-
-	list_for_each_entry(dev_data, &domain->dev_list, list)
-		iommu_flush_device(dev_data->dev);
-
-	spin_unlock_irqrestore(&domain->lock, flags);
+	__domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
 }
 
-static void iommu_flush_all_domain_devices(void)
+static void domain_flush_complete(struct protection_domain *domain)
 {
-	struct protection_domain *domain;
-	unsigned long flags;
+	int i;
 
-	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
+	for (i = 0; i < amd_iommus_present; ++i) {
+		if (!domain->dev_iommu[i])
+			continue;
 
-	list_for_each_entry(domain, &amd_iommu_pd_list, list) {
-		iommu_flush_domain_devices(domain);
-		iommu_flush_complete(domain);
+		/*
+		 * Devices of this domain are behind this IOMMU
+		 * We need to wait for completion of all commands.
+		 */
+		iommu_completion_wait(amd_iommus[i]);
 	}
-
-	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
 }
 
-void amd_iommu_flush_all_devices(void)
-{
-	iommu_flush_all_domain_devices();
-}
 
 /*
- * This function uses heavy locking and may disable irqs for some time. But
- * this is no issue because it is only called during resume.
+ * This function flushes the DTEs for all devices in domain
  */
-void amd_iommu_flush_all_domains(void)
+static void domain_flush_devices(struct protection_domain *domain)
 {
-	struct protection_domain *domain;
+	struct iommu_dev_data *dev_data;
 	unsigned long flags;
 
-	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
-
-	list_for_each_entry(domain, &amd_iommu_pd_list, list) {
-		spin_lock(&domain->lock);
-		iommu_flush_tlb_pde(domain);
-		iommu_flush_complete(domain);
-		spin_unlock(&domain->lock);
-	}
-
-	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
-}
-
-static void reset_iommu_command_buffer(struct amd_iommu *iommu)
-{
-	pr_err("AMD-Vi: Resetting IOMMU command buffer\n");
-
-	if (iommu->reset_in_progress)
-		panic("AMD-Vi: ILLEGAL_COMMAND_ERROR while resetting command buffer\n");
+	spin_lock_irqsave(&domain->lock, flags);
 
-	amd_iommu_reset_cmd_buffer(iommu);
-	amd_iommu_flush_all_devices();
-	amd_iommu_flush_all_domains();
+	list_for_each_entry(dev_data, &domain->dev_list, list)
+		device_flush_dte(dev_data->dev);
 
-	iommu->reset_in_progress = false;
+	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
 /****************************************************************************
@@ -1410,17 +1477,22 @@ static bool dma_ops_domain(struct protection_domain *domain)
 	return domain->flags & PD_DMA_OPS_MASK;
 }
 
-static void set_dte_entry(u16 devid, struct protection_domain *domain)
+static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 {
 	u64 pte_root = virt_to_phys(domain->pt_root);
+	u32 flags = 0;
 
 	pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
 	pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
 
-	amd_iommu_dev_table[devid].data[2] = domain->id;
-	amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
-	amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
+	if (ats)
+		flags |= DTE_FLAG_IOTLB;
+
+	amd_iommu_dev_table[devid].data[3] |= flags;
+	amd_iommu_dev_table[devid].data[2]  = domain->id;
+	amd_iommu_dev_table[devid].data[1]  = upper_32_bits(pte_root);
+	amd_iommu_dev_table[devid].data[0]  = lower_32_bits(pte_root);
 }
 
 static void clear_dte_entry(u16 devid)
@@ -1437,34 +1509,42 @@ static void do_attach(struct device *dev, struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
 	struct amd_iommu *iommu;
+	struct pci_dev *pdev;
+	bool ats = false;
 	u16 devid;
 
 	devid    = get_device_id(dev);
 	iommu    = amd_iommu_rlookup_table[devid];
 	dev_data = get_dev_data(dev);
+	pdev     = to_pci_dev(dev);
+
+	if (amd_iommu_iotlb_sup)
+		ats = pci_ats_enabled(pdev);
 
 	/* Update data structures */
 	dev_data->domain = domain;
 	list_add(&dev_data->list, &domain->dev_list);
-	set_dte_entry(devid, domain);
+	set_dte_entry(devid, domain, ats);
 
 	/* Do reference counting */
 	domain->dev_iommu[iommu->index] += 1;
 	domain->dev_cnt                 += 1;
 
 	/* Flush the DTE entry */
-	iommu_flush_device(dev);
+	device_flush_dte(dev);
 }
 
 static void do_detach(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
 	struct amd_iommu *iommu;
+	struct pci_dev *pdev;
 	u16 devid;
 
 	devid    = get_device_id(dev);
 	iommu    = amd_iommu_rlookup_table[devid];
 	dev_data = get_dev_data(dev);
+	pdev     = to_pci_dev(dev);
 
 	/* decrease reference counters */
 	dev_data->domain->dev_iommu[iommu->index] -= 1;
@@ -1476,7 +1556,7 @@ static void do_detach(struct device *dev)
 	clear_dte_entry(devid);
 
 	/* Flush the DTE entry */
-	iommu_flush_device(dev);
+	device_flush_dte(dev);
 }
 
 /*
@@ -1539,9 +1619,13 @@ out_unlock:
 static int attach_device(struct device *dev,
 			 struct protection_domain *domain)
 {
+	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long flags;
 	int ret;
 
+	if (amd_iommu_iotlb_sup)
+		pci_enable_ats(pdev, PAGE_SHIFT);
+
 	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	ret = __attach_device(dev, domain);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -1551,7 +1635,7 @@ static int attach_device(struct device *dev,
 	 * left the caches in the IOMMU dirty. So we have to flush
 	 * here to evict all dirty stuff.
 	 */
-	iommu_flush_tlb_pde(domain);
+	domain_flush_tlb_pde(domain);
 
 	return ret;
 }
@@ -1598,12 +1682,16 @@ static void __detach_device(struct device *dev)
  */
 static void detach_device(struct device *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long flags;
 
 	/* lock device table */
 	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
 	__detach_device(dev);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	if (amd_iommu_iotlb_sup && pci_ats_enabled(pdev))
+		pci_disable_ats(pdev);
 }
 
 /*
@@ -1692,7 +1780,7 @@ static int device_change_notifier(struct notifier_block *nb,
 		goto out;
 	}
 
-	iommu_flush_device(dev);
+	device_flush_dte(dev);
 	iommu_completion_wait(iommu);
 
 out:
@@ -1753,8 +1841,9 @@ static void update_device_table(struct protection_domain *domain)
 	struct iommu_dev_data *dev_data;
 
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
+		struct pci_dev *pdev = to_pci_dev(dev_data->dev);
 		u16 devid = get_device_id(dev_data->dev);
-		set_dte_entry(devid, domain);
+		set_dte_entry(devid, domain, pci_ats_enabled(pdev));
 	}
 }
 
@@ -1764,8 +1853,9 @@ static void update_domain(struct protection_domain *domain)
 		return;
 
 	update_device_table(domain);
-	iommu_flush_domain_devices(domain);
-	iommu_flush_tlb_pde(domain);
+
+	domain_flush_devices(domain);
+	domain_flush_tlb_pde(domain);
 
 	domain->updated = false;
 }
@@ -1924,10 +2014,10 @@ retry:
 	ADD_STATS_COUNTER(alloced_io_mem, size);
 
 	if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) {
-		iommu_flush_tlb(&dma_dom->domain);
+		domain_flush_tlb(&dma_dom->domain);
 		dma_dom->need_flush = false;
 	} else if (unlikely(amd_iommu_np_cache))
-		iommu_flush_pages(&dma_dom->domain, address, size);
+		domain_flush_pages(&dma_dom->domain, address, size);
 
 out:
 	return address;
@@ -1976,7 +2066,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	dma_ops_free_addresses(dma_dom, dma_addr, pages);
 
 	if (amd_iommu_unmap_flush || dma_dom->need_flush) {
-		iommu_flush_pages(&dma_dom->domain, flush_addr, size);
+		domain_flush_pages(&dma_dom->domain, flush_addr, size);
 		dma_dom->need_flush = false;
 	}
 }
@@ -2012,7 +2102,7 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
 	if (addr == DMA_ERROR_CODE)
 		goto out;
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -2039,7 +2129,7 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 
 	__unmap_single(domain->priv, dma_addr, size, dir);
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -2104,7 +2194,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 			goto unmap;
 	}
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -2150,7 +2240,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
 		s->dma_address = s->dma_length = 0;
 	}
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -2200,7 +2290,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 		goto out_free;
 	}
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
@@ -2232,7 +2322,7 @@ static void free_coherent(struct device *dev, size_t size,
 
 	__unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
 
-	iommu_flush_complete(domain);
+	domain_flush_complete(domain);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
@@ -2476,7 +2566,7 @@ static void amd_iommu_detach_device(struct iommu_domain *dom,
 	if (!iommu)
 		return;
 
-	iommu_flush_device(dev);
+	device_flush_dte(dev);
 	iommu_completion_wait(iommu);
 }
 
@@ -2542,7 +2632,7 @@ static int amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 	unmap_size = iommu_unmap_page(domain, iova, page_size);
 	mutex_unlock(&domain->api_lock);
 
-	iommu_flush_tlb_pde(domain);
+	domain_flush_tlb_pde(domain);
 
 	return get_order(unmap_size);
 }
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 246d727b65b..9179c21120a 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -137,6 +137,7 @@ int amd_iommus_present;
 
 /* IOMMUs have a non-present cache? */
 bool amd_iommu_np_cache __read_mostly;
+bool amd_iommu_iotlb_sup __read_mostly = true;
 
 /*
  * The ACPI table parsing functions set this variable on an error
@@ -180,6 +181,12 @@ static u32 dev_table_size;	/* size of the device table */
 static u32 alias_table_size;	/* size of the alias table */
 static u32 rlookup_table_size;	/* size if the rlookup table */
 
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -293,9 +300,23 @@ static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 /* Function to enable the hardware */
 static void iommu_enable(struct amd_iommu *iommu)
 {
-	printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx\n",
+	static const char * const feat_str[] = {
+		"PreF", "PPR", "X2APIC", "NX", "GT", "[5]",
+		"IA", "GA", "HE", "PC", NULL
+	};
+	int i;
+
+	printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx",
 	       dev_name(&iommu->dev->dev), iommu->cap_ptr);
 
+	if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
+		printk(KERN_CONT " extended features: ");
+		for (i = 0; feat_str[i]; ++i)
+			if (iommu_feature(iommu, (1ULL << i)))
+				printk(KERN_CONT " %s", feat_str[i]);
+	}
+	printk(KERN_CONT "\n");
+
 	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
 }
 
@@ -651,7 +672,7 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
 static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 {
 	int cap_ptr = iommu->cap_ptr;
-	u32 range, misc;
+	u32 range, misc, low, high;
 	int i, j;
 
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
@@ -667,6 +688,15 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 					MMIO_GET_LD(range));
 	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
 
+	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+		amd_iommu_iotlb_sup = false;
+
+	/* read extended feature bits */
+	low  = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
+	high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
+
+	iommu->features = ((u64)high << 32) | low;
+
 	if (!is_rd890_iommu(iommu->dev))
 		return;
 
@@ -1004,10 +1034,11 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 	if (pci_enable_msi(iommu->dev))
 		return 1;
 
-	r = request_irq(iommu->dev->irq, amd_iommu_int_handler,
-			IRQF_SAMPLE_RANDOM,
-			"AMD-Vi",
-			NULL);
+	r = request_threaded_irq(iommu->dev->irq,
+				 amd_iommu_int_handler,
+				 amd_iommu_int_thread,
+				 0, "AMD-Vi",
+				 iommu->dev);
 
 	if (r) {
 		pci_disable_msi(iommu->dev);
@@ -1244,6 +1275,7 @@ static void enable_iommus(void)
 		iommu_set_exclusion_range(iommu);
 		iommu_init_msi(iommu);
 		iommu_enable(iommu);
+		iommu_flush_all_caches(iommu);
 	}
 }
 
@@ -1274,8 +1306,8 @@ static void amd_iommu_resume(void)
 	 * we have to flush after the IOMMUs are enabled because a
 	 * disabled IOMMU will never execute the commands we send
 	 */
-	amd_iommu_flush_all_devices();
-	amd_iommu_flush_all_domains();
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
 }
 
 static int amd_iommu_suspend(void)
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index cd1ffed4ee2..289e92862fd 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -177,7 +177,6 @@ static struct clocksource clocksource_apbt = {
 	.rating		= APBT_CLOCKSOURCE_RATING,
 	.read		= apbt_read_clocksource,
 	.mask		= APBT_MASK,
-	.shift		= APBT_SHIFT,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	.resume		= apbt_restart_clocksource,
 };
@@ -543,14 +542,7 @@ static int apbt_clocksource_register(void)
 	if (t1 == apbt_read_clocksource(&clocksource_apbt))
 		panic("APBT counter not counting. APBT disabled\n");
 
-	/*
-	 * initialize and register APBT clocksource
-	 * convert that to ns/clock cycle
-	 * mult = (ns/c) * 2^APBT_SHIFT
-	 */
-	clocksource_apbt.mult = div_sc(MSEC_PER_SEC,
-				       (unsigned long) apbt_freq, APBT_SHIFT);
-	clocksource_register(&clocksource_apbt);
+	clocksource_register_khz(&clocksource_apbt, (u32)apbt_freq*1000);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 73fb469908c..3d2661ca654 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,22 @@
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
+/*
+ * Using 512M as goal, in case kexec will load kernel_big
+ * that will do the on-position decompress, and could overlap with
+ * with the gart aperture that is used.
+ * Sequence:
+ * kernel_small
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kernel_small (gart area become e820_reserved)
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+ * So don't use 512M below as gart iommu, leave the space for kernel
+ * code for safe.
+ */
+#define GART_MIN_ADDR	(512ULL << 20)
+#define GART_MAX_ADDR	(1ULL   << 32)
+
 int gart_iommu_aperture;
 int gart_iommu_aperture_disabled __initdata;
 int gart_iommu_aperture_allowed __initdata;
@@ -70,21 +86,9 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	/*
-	 * using 512M as goal, in case kexec will load kernel_big
-	 * that will do the on position decompress, and  could overlap with
-	 * that position with gart that is used.
-	 * sequende:
-	 * kernel_small
-	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
-	 * ==> kernel_small(gart area become e820_reserved)
-	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
-	 * ==> kerne_big (uncompressed size will be big than 64M or 128M)
-	 * so don't use 512M below as gart iommu, leave the space for kernel
-	 * code for safe
-	 */
-	addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
-	if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
+	addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
+				      aper_size, aper_size);
+	if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%lx,%uK)\n",
 				addr, aper_size>>10);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index fabf01eff77..f92a8e5d1e2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -505,7 +505,7 @@ static void __cpuinit setup_APIC_timer(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-	if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) {
+	if (this_cpu_has(X86_FEATURE_ARAT)) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
 		/* Make LAPIC timer preferrable over percpu HPET */
 		lapic_clockevent.rating = 150;
@@ -1237,6 +1237,17 @@ void __cpuinit setup_local_APIC(void)
 	/* always use the value from LDR */
 	early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
 		logical_smp_processor_id();
+
+	/*
+	 * Some NUMA implementations (NUMAQ) don't initialize apicid to
+	 * node mapping during NUMA init.  Now that logical apicid is
+	 * guaranteed to be known, give it another chance.  This is already
+	 * a bit too late - percpu allocation has already happened without
+	 * proper NUMA affinity.
+	 */
+	if (apic->x86_32_numa_cpu_node)
+		set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu),
+				   apic->x86_32_numa_cpu_node(cpu));
 #endif
 
 	/*
@@ -1812,30 +1823,41 @@ void smp_spurious_interrupt(struct pt_regs *regs)
  */
 void smp_error_interrupt(struct pt_regs *regs)
 {
-	u32 v, v1;
+	u32 v0, v1;
+	u32 i = 0;
+	static const char * const error_interrupt_reason[] = {
+		"Send CS error",		/* APIC Error Bit 0 */
+		"Receive CS error",		/* APIC Error Bit 1 */
+		"Send accept error",		/* APIC Error Bit 2 */
+		"Receive accept error",		/* APIC Error Bit 3 */
+		"Redirectable IPI",		/* APIC Error Bit 4 */
+		"Send illegal vector",		/* APIC Error Bit 5 */
+		"Received illegal vector",	/* APIC Error Bit 6 */
+		"Illegal register address",	/* APIC Error Bit 7 */
+	};
 
 	exit_idle();
 	irq_enter();
 	/* First tickle the hardware, only then report what went on. -- REW */
-	v = apic_read(APIC_ESR);
+	v0 = apic_read(APIC_ESR);
 	apic_write(APIC_ESR, 0);
 	v1 = apic_read(APIC_ESR);
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
 
-	/*
-	 * Here is what the APIC error bits mean:
-	 * 0: Send CS error
-	 * 1: Receive CS error
-	 * 2: Send accept error
-	 * 3: Receive accept error
-	 * 4: Reserved
-	 * 5: Send illegal vector
-	 * 6: Received illegal vector
-	 * 7: Illegal register address
-	 */
-	pr_debug("APIC error on CPU%d: %02x(%02x)\n",
-		smp_processor_id(), v , v1);
+	apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)",
+		    smp_processor_id(), v0 , v1);
+
+	v1 = v1 & 0xff;
+	while (v1) {
+		if (v1 & 0x1)
+			apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
+		i++;
+		v1 >>= 1;
+	};
+
+	apic_printk(APIC_DEBUG, KERN_CONT "\n");
+
 	irq_exit();
 }
 
@@ -2003,21 +2025,6 @@ void default_init_apic_ldr(void)
 	apic_write(APIC_LDR, val);
 }
 
-#ifdef CONFIG_X86_32
-int default_x86_32_numa_cpu_node(int cpu)
-{
-#ifdef CONFIG_NUMA
-	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-
-	if (apicid != BAD_APICID)
-		return __apicid_to_node[apicid];
-	return NUMA_NO_NODE;
-#else
-	return 0;
-#endif
-}
-#endif
-
 /*
  * Power management
  */
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index f1baa2dc087..775b82bc655 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -119,14 +119,6 @@ static void noop_apic_write(u32 reg, u32 v)
 	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
 }
 
-#ifdef CONFIG_X86_32
-static int noop_x86_32_numa_cpu_node(int cpu)
-{
-	/* we're always on node 0 */
-	return 0;
-}
-#endif
-
 struct apic apic_noop = {
 	.name				= "noop",
 	.probe				= noop_probe,
@@ -195,6 +187,5 @@ struct apic apic_noop = {
 
 #ifdef CONFIG_X86_32
 	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
-	.x86_32_numa_cpu_node		= noop_x86_32_numa_cpu_node,
 #endif
 };
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 541a2e43165..d84ac5a584b 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -253,5 +253,4 @@ struct apic apic_bigsmp = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 
 	.x86_32_early_logical_apicid	= bigsmp_early_logical_apicid,
-	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 3e9de4854c5..70533de5bd2 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -510,11 +510,6 @@ static void es7000_setup_apic_routing(void)
 		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
-static int es7000_numa_cpu_node(int cpu)
-{
-	return 0;
-}
-
 static int es7000_cpu_present_to_apicid(int mps_cpu)
 {
 	if (!mps_cpu)
@@ -688,7 +683,6 @@ struct apic __refdata apic_es7000_cluster = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 
 	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
-	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
 
 struct apic __refdata apic_es7000 = {
@@ -752,5 +746,4 @@ struct apic __refdata apic_es7000 = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 
 	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
-	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 6273eee5134..30f13319e24 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -48,8 +48,6 @@
 #include <asm/e820.h>
 #include <asm/ipi.h>
 
-#define	MB_TO_PAGES(addr)		((addr) << (20 - PAGE_SHIFT))
-
 int found_numaq;
 
 /*
@@ -79,31 +77,20 @@ int					quad_local_to_mp_bus_id[NR_CPUS/4][4];
 static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
 {
 	struct eachquadmem *eq = scd->eq + node;
+	u64 start = (u64)(eq->hi_shrd_mem_start - eq->priv_mem_size) << 20;
+	u64 end = (u64)(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size) << 20;
+	int ret;
 
-	node_set_online(node);
-
-	/* Convert to pages */
-	node_start_pfn[node] =
-		 MB_TO_PAGES(eq->hi_shrd_mem_start - eq->priv_mem_size);
-
-	node_end_pfn[node] =
-		 MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
-
-	memblock_x86_register_active_regions(node, node_start_pfn[node],
-						node_end_pfn[node]);
-
-	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
-
-	node_remap_size[node] = node_memmap_size_bytes(node,
-					node_start_pfn[node],
-					node_end_pfn[node]);
+	node_set(node, numa_nodes_parsed);
+	ret = numa_add_memblk(node, start, end);
+	BUG_ON(ret < 0);
 }
 
 /*
  * Function: smp_dump_qct()
  *
  * Description: gets memory layout from the quad config table.  This
- * function also updates node_online_map with the nodes (quads) present.
+ * function also updates numa_nodes_parsed with the nodes (quads) present.
  */
 static void __init smp_dump_qct(void)
 {
@@ -112,7 +99,6 @@ static void __init smp_dump_qct(void)
 
 	scd = (void *)__va(SYS_CFG_DATA_PRIV_ADDR);
 
-	nodes_clear(node_online_map);
 	for_each_node(node) {
 		if (scd->quads_present31_0 & (1 << node))
 			numaq_register_node(node, scd);
@@ -282,14 +268,14 @@ static __init void early_check_numaq(void)
 	}
 }
 
-int __init get_memcfg_numaq(void)
+int __init numaq_numa_init(void)
 {
 	early_check_numaq();
 	if (!found_numaq)
-		return 0;
+		return -ENOENT;
 	smp_dump_qct();
 
-	return 1;
+	return 0;
 }
 
 #define NUMAQ_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index fc84c7b6110..6541e471fd9 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -172,7 +172,6 @@ struct apic apic_default = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 
 	.x86_32_early_logical_apicid	= default_x86_32_early_logical_apicid,
-	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
 
 extern struct apic apic_numaq;
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index e4b8059b414..35bcd7d995a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -551,5 +551,4 @@ struct apic apic_summit = {
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
 
 	.x86_32_early_logical_apicid	= summit_early_logical_apicid,
-	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index adee12e0da1..3bfa0223596 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1238,7 +1238,6 @@ static int suspend(int vetoable)
 	dpm_suspend_noirq(PMSG_SUSPEND);
 
 	local_irq_disable();
-	sysdev_suspend(PMSG_SUSPEND);
 	syscore_suspend();
 
 	local_irq_enable();
@@ -1258,7 +1257,6 @@ static int suspend(int vetoable)
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
 
 	syscore_resume();
-	sysdev_resume();
 	local_irq_enable();
 
 	dpm_resume_noirq(PMSG_RESUME);
@@ -1282,7 +1280,6 @@ static void standby(void)
 	dpm_suspend_noirq(PMSG_SUSPEND);
 
 	local_irq_disable();
-	sysdev_suspend(PMSG_SUSPEND);
 	syscore_suspend();
 	local_irq_enable();
 
@@ -1292,7 +1289,6 @@ static void standby(void)
 
 	local_irq_disable();
 	syscore_resume();
-	sysdev_resume();
 	local_irq_enable();
 
 	dpm_resume_noirq(PMSG_RESUME);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 3f0ebe429a0..6042981d030 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,7 +30,6 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
-obj-$(CONFIG_CPU_FREQ)			+= cpufreq/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e2ced0074a4..cbc70a27430 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -254,6 +254,25 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 }
 #endif
 
+static int disable_smep __initdata;
+static __init int setup_disable_smep(char *arg)
+{
+	disable_smep = 1;
+	return 1;
+}
+__setup("nosmep", setup_disable_smep);
+
+static __init void setup_smep(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_SMEP)) {
+		if (unlikely(disable_smep)) {
+			setup_clear_cpu_cap(X86_FEATURE_SMEP);
+			clear_in_cr4(X86_CR4_SMEP);
+		} else
+			set_in_cr4(X86_CR4_SMEP);
+	}
+}
+
 /*
  * Some CPU features depend on higher CPUID levels, which may not always
  * be available due to CPUID level capping or broken virtualization
@@ -565,8 +584,7 @@ void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
-		if (eax > 0)
-			c->x86_capability[9] = ebx;
+		c->x86_capability[9] = ebx;
 	}
 
 	/* AMD-defined flags: level 0x80000001 */
@@ -668,6 +686,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	c->cpu_index = 0;
 #endif
 	filter_cpuid_features(c, false);
+
+	setup_smep(c);
 }
 
 void __init early_cpu_init(void)
@@ -753,6 +773,8 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 #endif
 	}
 
+	setup_smep(c);
+
 	get_model_name(c); /* Default name */
 
 	detect_nopl(c);
diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile
deleted file mode 100644
index bd54bf67e6f..00000000000
--- a/arch/x86/kernel/cpu/cpufreq/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-# Link order matters. K8 is preferred to ACPI because of firmware bugs in early
-# K8 systems. ACPI is preferred to all other hardware-specific drivers.
-# speedstep-* is preferred over p4-clockmod.
-
-obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o mperf.o
-obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
-obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
-obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
-obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
-obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
-obj-$(CONFIG_X86_E_POWERSAVER)		+= e_powersaver.o
-obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
-obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
-obj-$(CONFIG_X86_LONGRUN)		+= longrun.o  
-obj-$(CONFIG_X86_GX_SUSPMOD)		+= gx-suspmod.o
-obj-$(CONFIG_X86_SPEEDSTEP_ICH)		+= speedstep-ich.o
-obj-$(CONFIG_X86_SPEEDSTEP_LIB)		+= speedstep-lib.o
-obj-$(CONFIG_X86_SPEEDSTEP_SMI)		+= speedstep-smi.o
-obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO)	+= speedstep-centrino.o
-obj-$(CONFIG_X86_P4_CLOCKMOD)		+= p4-clockmod.o
-obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index df86bc8c859..1edf5ba4fb2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,10 +29,10 @@
 
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
+	u64 misc_enable;
+
 	/* Unmask CPUID levels if masked: */
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
@@ -118,8 +118,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	 * (model 2) with the same problem.
 	 */
 	if (c->x86 == 15) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
@@ -130,6 +128,19 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		}
 	}
 #endif
+
+	/*
+	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
+	 * clear the fast string and enhanced fast string CPU capabilities.
+	 */
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+			printk(KERN_INFO "Disabled fast string operations\n");
+			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
+			setup_clear_cpu_cap(X86_FEATURE_ERMS);
+		}
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -400,12 +411,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 		switch (c->x86_model) {
 		case 5:
-			if (c->x86_mask == 0) {
-				if (l2 == 0)
-					p = "Celeron (Covington)";
-				else if (l2 == 256)
-					p = "Mobile Pentium II (Dixon)";
-			}
+			if (l2 == 0)
+				p = "Celeron (Covington)";
+			else if (l2 == 256)
+				p = "Mobile Pentium II (Dixon)";
 			break;
 
 		case 6:
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 1ce1af2899d..c105c533ed9 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -327,7 +327,6 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 	l3->subcaches[2] = sc2 = !(val & BIT(8))  + !(val & BIT(9));
 	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
 
-	l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
@@ -454,27 +453,16 @@ int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot,
 {
 	int ret = 0;
 
-#define SUBCACHE_MASK	(3UL << 20)
-#define SUBCACHE_INDEX	0xfff
-
-	/*
-	 * check whether this slot is already used or
-	 * the index is already disabled
-	 */
+	/*  check if @slot is already used or the index is already disabled */
 	ret = amd_get_l3_disable_slot(l3, slot);
 	if (ret >= 0)
 		return -EINVAL;
 
-	/*
-	 * check whether the other slot has disabled the
-	 * same index already
-	 */
-	if (index == amd_get_l3_disable_slot(l3, !slot))
+	if (index > l3->indices)
 		return -EINVAL;
 
-	/* do not allow writes outside of allowed bits */
-	if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
-	    ((index & SUBCACHE_INDEX) > l3->indices))
+	/* check whether the other slot has disabled the same index already */
+	if (index == amd_get_l3_disable_slot(l3, !slot))
 		return -EINVAL;
 
 	amd_l3_disable_index(l3, cpu, slot, index);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3385ea26f68..ff1ae9b6464 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -105,20 +105,6 @@ static int			cpu_missing;
 ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
 EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
 
-static int default_decode_mce(struct notifier_block *nb, unsigned long val,
-			       void *data)
-{
-	pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
-	pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
-
-	return NOTIFY_STOP;
-}
-
-static struct notifier_block mce_dec_nb = {
-	.notifier_call = default_decode_mce,
-	.priority      = -1,
-};
-
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -212,6 +198,8 @@ void mce_log(struct mce *mce)
 
 static void print_mce(struct mce *m)
 {
+	int ret = 0;
+
 	pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
 	       m->extcpu, m->mcgstatus, m->bank, m->status);
 
@@ -239,7 +227,11 @@ static void print_mce(struct mce *m)
 	 * Print out human-readable details about the MCE error,
 	 * (if the CPU has an implementation for that)
 	 */
-	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+	if (ret == NOTIFY_STOP)
+		return;
+
+	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -590,7 +582,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
 			mce_log(&m);
 			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
-			add_taint(TAINT_MACHINE_CHECK);
 		}
 
 		/*
@@ -1722,8 +1713,6 @@ __setup("mce", mcheck_enable);
 
 int __init mcheck_init(void)
 {
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
-
 	mcheck_intel_therm_init();
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 0f034460260..27c625178bf 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -187,8 +187,6 @@ static int therm_throt_process(bool new_event, int event, int level)
 				this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package",
 				state->count);
-
-		add_taint(TAINT_MACHINE_CHECK);
 		return 1;
 	}
 	if (old_event) {
@@ -355,7 +353,6 @@ static void notify_thresholds(__u64 msr_val)
 static void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
-	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
@@ -367,19 +364,19 @@ static void intel_thermal_interrupt(void)
 				CORE_LEVEL) != 0)
 		mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
 
-	if (cpu_has(c, X86_FEATURE_PLN))
+	if (this_cpu_has(X86_FEATURE_PLN))
 		if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
 					CORE_LEVEL) != 0)
 			mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
 
-	if (cpu_has(c, X86_FEATURE_PTS)) {
+	if (this_cpu_has(X86_FEATURE_PTS)) {
 		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
 		if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
 					THERMAL_THROTTLING_EVENT,
 					PACKAGE_LEVEL) != 0)
 			mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
-		if (cpu_has(c, X86_FEATURE_PLN))
+		if (this_cpu_has(X86_FEATURE_PLN))
 			if (therm_throt_process(msr_val &
 					PACKAGE_THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
@@ -393,7 +390,6 @@ static void unexpected_thermal_interrupt(void)
 {
 	printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
 			smp_processor_id());
-	add_taint(TAINT_MACHINE_CHECK);
 }
 
 static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e638689279d..3a0338b4b17 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,6 +31,7 @@
 #include <asm/nmi.h>
 #include <asm/compat.h>
 #include <asm/smp.h>
+#include <asm/alternative.h>
 
 #if 0
 #undef wrmsrl
@@ -363,12 +364,18 @@ again:
 	return new_raw_count;
 }
 
-/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */
 static inline int x86_pmu_addr_offset(int index)
 {
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
-		return index << 1;
-	return index;
+	int offset;
+
+	/* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */
+	alternative_io(ASM_NOP2,
+		       "shll $1, %%eax",
+		       X86_FEATURE_PERFCTR_CORE,
+		       "=a" (offset),
+		       "a"  (index));
+
+	return offset;
 }
 
 static inline unsigned int x86_pmu_config_addr(int index)
@@ -1766,17 +1773,6 @@ static struct pmu pmu = {
  * callchain support
  */
 
-static void
-backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	/* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
-	/* Ignore warnings */
-}
-
 static int backtrace_stack(void *data, char *name)
 {
 	return 0;
@@ -1790,8 +1786,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops backtrace_ops = {
-	.warning		= backtrace_warning,
-	.warning_symbol		= backtrace_warning_symbol,
 	.stack			= backtrace_stack,
 	.address		= backtrace_address,
 	.walk_stack		= print_context_stack_bp,
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index cf4e369cea6..fe29c1d2219 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -96,12 +96,14 @@ static __initconst const u64 amd_hw_cache_event_ids
  */
 static const u64 amd_perfmon_event_map[] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+  [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
+  [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x0080,
+  [PERF_COUNT_HW_CACHE_MISSES]			= 0x0081,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
+  [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
+  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
+  [PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
 };
 
 static u64 amd_pmu_event_map(int hw_event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 447a28de6f0..41178c826c4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -36,7 +36,7 @@ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
   [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
 };
 
-static struct event_constraint intel_core_event_constraints[] =
+static struct event_constraint intel_core_event_constraints[] __read_mostly =
 {
 	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
 	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -47,7 +47,7 @@ static struct event_constraint intel_core_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_core2_event_constraints[] =
+static struct event_constraint intel_core2_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -70,7 +70,7 @@ static struct event_constraint intel_core2_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_nehalem_event_constraints[] =
+static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -86,19 +86,19 @@ static struct event_constraint intel_nehalem_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
-static struct extra_reg intel_nehalem_extra_regs[] =
+static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
 	EVENT_EXTRA_END
 };
 
-static struct event_constraint intel_nehalem_percore_constraints[] =
+static struct event_constraint intel_nehalem_percore_constraints[] __read_mostly =
 {
 	INTEL_EVENT_CONSTRAINT(0xb7, 0),
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_westmere_event_constraints[] =
+static struct event_constraint intel_westmere_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -110,7 +110,7 @@ static struct event_constraint intel_westmere_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_snb_event_constraints[] =
+static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -123,21 +123,21 @@ static struct event_constraint intel_snb_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
-static struct extra_reg intel_westmere_extra_regs[] =
+static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
 	EVENT_EXTRA_END
 };
 
-static struct event_constraint intel_westmere_percore_constraints[] =
+static struct event_constraint intel_westmere_percore_constraints[] __read_mostly =
 {
 	INTEL_EVENT_CONSTRAINT(0xb7, 0),
 	INTEL_EVENT_CONSTRAINT(0xbb, 0),
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_gen_event_constraints[] =
+static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -1440,6 +1440,11 @@ static __init int intel_pmu_init(void)
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
+		/* UOPS_ISSUED.STALLED_CYCLES */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+
 		if (ebx & 0x40) {
 			/*
 			 * Erratum AAJ80 detected, we work it around by using
@@ -1480,6 +1485,12 @@ static __init int intel_pmu_init(void)
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_westmere_extra_regs;
+
+		/* UOPS_ISSUED.STALLED_CYCLES */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+
 		pr_cont("Westmere events, ");
 		break;
 
@@ -1491,6 +1502,12 @@ static __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_events;
+
+		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
+
 		pr_cont("SandyBridge events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index e93fcd55fae..ead584fb6a7 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -468,7 +468,7 @@ static struct p4_event_bind p4_event_bind_map[] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
 		.escr_emask	=
-		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
+			P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_X87_ASSIST] = {
@@ -912,8 +912,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1197,7 +1196,7 @@ static __init int p4_pmu_init(void)
 {
 	unsigned int low, high;
 
-	/* If we get stripped -- indexig fails */
+	/* If we get stripped -- indexing fails */
 	BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
 
 	rdmsr(MSR_IA32_MISC_ENABLE, low, high);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index e2a3f0606da..1aae78f775f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -135,20 +135,6 @@ print_context_stack_bp(struct thread_info *tinfo,
 }
 EXPORT_SYMBOL_GPL(print_context_stack_bp);
 
-
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	printk(data);
-	print_symbol(msg, symbol);
-	printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
-	printk("%s%s\n", (char *)data, msg);
-}
-
 static int print_trace_stack(void *data, char *name)
 {
 	printk("%s <%s> ", (char *)data, name);
@@ -166,8 +152,6 @@ static void print_trace_address(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops print_trace_ops = {
-	.warning		= print_trace_warning,
-	.warning_symbol		= print_trace_warning_symbol,
 	.stack			= print_trace_stack,
 	.address		= print_trace_address,
 	.walk_stack		= print_context_stack,
@@ -279,7 +263,6 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 	printk("DEBUG_PAGEALLOC");
 #endif
 	printk("\n");
-	sysfs_printk_last_file();
 	if (notify_die(DIE_OOPS, str, regs, err,
 			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
 		return 1;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index a93742a5746..0ba15a6cc57 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -260,9 +260,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	return mod_code_status;
 }
 
-static unsigned char *ftrace_nop_replace(void)
+static const unsigned char *ftrace_nop_replace(void)
 {
-	return ideal_nop5;
+	return ideal_nops[NOP_ATOMIC5];
 }
 
 static int
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index d6d6bb36193..3bb08509a7a 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -23,7 +23,6 @@
 static void __init i386_default_early_setup(void)
 {
 	/* Initialize 32bit specific setup functions */
-	x86_init.resources.probe_roms = probe_roms;
 	x86_init.resources.reserve_resources = i386_reserve_resources;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index bfe8f729e08..6781765b3a0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -217,7 +217,7 @@ static void hpet_reserve_platform_timers(unsigned int id) { }
 /*
  * Common hpet info
  */
-static unsigned long hpet_period;
+static unsigned long hpet_freq;
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt);
@@ -232,7 +232,6 @@ static struct clock_event_device hpet_clockevent = {
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_mode	= hpet_legacy_set_mode,
 	.set_next_event = hpet_legacy_next_event,
-	.shift		= 32,
 	.irq		= 0,
 	.rating		= 50,
 };
@@ -290,28 +289,12 @@ static void hpet_legacy_clockevent_register(void)
 	hpet_enable_legacy_int();
 
 	/*
-	 * The mult factor is defined as (include/linux/clockchips.h)
-	 *  mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h)
-	 * hpet_period is in units of femtoseconds (per cycle), so
-	 *  mult/2^shift = cyc/ns = 10^6/hpet_period
-	 *  mult = (10^6 * 2^shift)/hpet_period
-	 *  mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period
-	 */
-	hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC,
-				      hpet_period, hpet_clockevent.shift);
-	/* Calculate the min / max delta */
-	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
-							   &hpet_clockevent);
-	/* Setup minimum reprogramming delta. */
-	hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
-							   &hpet_clockevent);
-
-	/*
 	 * Start hpet with the boot cpu mask and make it
 	 * global after the IO_APIC has been initialized.
 	 */
 	hpet_clockevent.cpumask = cpumask_of(smp_processor_id());
-	clockevents_register_device(&hpet_clockevent);
+	clockevents_config_and_register(&hpet_clockevent, hpet_freq,
+					HPET_MIN_PROG_DELTA, 0x7FFFFFFF);
 	global_clock_event = &hpet_clockevent;
 	printk(KERN_DEBUG "hpet clockevent registered\n");
 }
@@ -549,7 +532,6 @@ static int hpet_setup_irq(struct hpet_dev *dev)
 static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 {
 	struct clock_event_device *evt = &hdev->evt;
-	uint64_t hpet_freq;
 
 	WARN_ON(cpu != smp_processor_id());
 	if (!(hdev->flags & HPET_DEV_VALID))
@@ -571,24 +553,10 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 
 	evt->set_mode = hpet_msi_set_mode;
 	evt->set_next_event = hpet_msi_next_event;
-	evt->shift = 32;
-
-	/*
-	 * The period is a femto seconds value. We need to calculate the
-	 * scaled math multiplication factor for nanosecond to hpet tick
-	 * conversion.
-	 */
-	hpet_freq = FSEC_PER_SEC;
-	do_div(hpet_freq, hpet_period);
-	evt->mult = div_sc((unsigned long) hpet_freq,
-				      NSEC_PER_SEC, evt->shift);
-	/* Calculate the max delta */
-	evt->max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, evt);
-	/* 5 usec minimum reprogramming delta. */
-	evt->min_delta_ns = 5000;
-
 	evt->cpumask = cpumask_of(hdev->cpu);
-	clockevents_register_device(evt);
+
+	clockevents_config_and_register(evt, hpet_freq, HPET_MIN_PROG_DELTA,
+					0x7FFFFFFF);
 }
 
 #ifdef CONFIG_HPET
@@ -792,7 +760,6 @@ static struct clocksource clocksource_hpet = {
 static int hpet_clocksource_register(void)
 {
 	u64 start, now;
-	u64 hpet_freq;
 	cycle_t t1;
 
 	/* Start the counter */
@@ -819,24 +786,7 @@ static int hpet_clocksource_register(void)
 		return -ENODEV;
 	}
 
-	/*
-	 * The definition of mult is (include/linux/clocksource.h)
-	 * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc
-	 * so we first need to convert hpet_period to ns/cyc units:
-	 *  mult/2^shift = ns/cyc = hpet_period/10^6
-	 *  mult = (hpet_period * 2^shift)/10^6
-	 *  mult = (hpet_period << shift)/FSEC_PER_NSEC
-	 */
-
-	/* Need to convert hpet_period (fsec/cyc) to cyc/sec:
-	 *
-	 * cyc/sec = FSEC_PER_SEC/hpet_period(fsec/cyc)
-	 * cyc/sec = (FSEC_PER_NSEC * NSEC_PER_SEC)/hpet_period
-	 */
-	hpet_freq = FSEC_PER_SEC;
-	do_div(hpet_freq, hpet_period);
 	clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
-
 	return 0;
 }
 
@@ -845,7 +795,9 @@ static int hpet_clocksource_register(void)
  */
 int __init hpet_enable(void)
 {
+	unsigned long hpet_period;
 	unsigned int id;
+	u64 freq;
 	int i;
 
 	if (!is_hpet_capable())
@@ -884,6 +836,14 @@ int __init hpet_enable(void)
 		goto out_nohpet;
 
 	/*
+	 * The period is a femto seconds value. Convert it to a
+	 * frequency.
+	 */
+	freq = FSEC_PER_SEC;
+	do_div(freq, hpet_period);
+	hpet_freq = freq;
+
+	/*
 	 * Read the HPET ID register to retrieve the IRQ routing
 	 * information and the number of channels
 	 */
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 2dfd3159744..fb66dc9e36c 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -93,7 +93,6 @@ static struct clock_event_device pit_ce = {
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_mode	= init_pit_timer,
 	.set_next_event = pit_next_event,
-	.shift		= 32,
 	.irq		= 0,
 };
 
@@ -108,90 +107,12 @@ void __init setup_pit_timer(void)
 	 * IO_APIC has been initialized.
 	 */
 	pit_ce.cpumask = cpumask_of(smp_processor_id());
-	pit_ce.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, pit_ce.shift);
-	pit_ce.max_delta_ns = clockevent_delta2ns(0x7FFF, &pit_ce);
-	pit_ce.min_delta_ns = clockevent_delta2ns(0xF, &pit_ce);
 
-	clockevents_register_device(&pit_ce);
+	clockevents_config_and_register(&pit_ce, CLOCK_TICK_RATE, 0xF, 0x7FFF);
 	global_clock_event = &pit_ce;
 }
 
 #ifndef CONFIG_X86_64
-/*
- * Since the PIT overflows every tick, its not very useful
- * to just read by itself. So use jiffies to emulate a free
- * running counter:
- */
-static cycle_t pit_read(struct clocksource *cs)
-{
-	static int old_count;
-	static u32 old_jifs;
-	unsigned long flags;
-	int count;
-	u32 jifs;
-
-	raw_spin_lock_irqsave(&i8253_lock, flags);
-	/*
-	 * Although our caller may have the read side of xtime_lock,
-	 * this is now a seqlock, and we are cheating in this routine
-	 * by having side effects on state that we cannot undo if
-	 * there is a collision on the seqlock and our caller has to
-	 * retry.  (Namely, old_jifs and old_count.)  So we must treat
-	 * jiffies as volatile despite the lock.  We read jiffies
-	 * before latching the timer count to guarantee that although
-	 * the jiffies value might be older than the count (that is,
-	 * the counter may underflow between the last point where
-	 * jiffies was incremented and the point where we latch the
-	 * count), it cannot be newer.
-	 */
-	jifs = jiffies;
-	outb_pit(0x00, PIT_MODE);	/* latch the count ASAP */
-	count = inb_pit(PIT_CH0);	/* read the latched count */
-	count |= inb_pit(PIT_CH0) << 8;
-
-	/* VIA686a test code... reset the latch if count > max + 1 */
-	if (count > LATCH) {
-		outb_pit(0x34, PIT_MODE);
-		outb_pit(LATCH & 0xff, PIT_CH0);
-		outb_pit(LATCH >> 8, PIT_CH0);
-		count = LATCH - 1;
-	}
-
-	/*
-	 * It's possible for count to appear to go the wrong way for a
-	 * couple of reasons:
-	 *
-	 *  1. The timer counter underflows, but we haven't handled the
-	 *     resulting interrupt and incremented jiffies yet.
-	 *  2. Hardware problem with the timer, not giving us continuous time,
-	 *     the counter does small "jumps" upwards on some Pentium systems,
-	 *     (see c't 95/10 page 335 for Neptun bug.)
-	 *
-	 * Previous attempts to handle these cases intelligently were
-	 * buggy, so we just do the simple thing now.
-	 */
-	if (count > old_count && jifs == old_jifs)
-		count = old_count;
-
-	old_count = count;
-	old_jifs = jifs;
-
-	raw_spin_unlock_irqrestore(&i8253_lock, flags);
-
-	count = (LATCH - 1) - count;
-
-	return (cycle_t)(jifs * LATCH) + count;
-}
-
-static struct clocksource pit_cs = {
-	.name		= "pit",
-	.rating		= 110,
-	.read		= pit_read,
-	.mask		= CLOCKSOURCE_MASK(32),
-	.mult		= 0,
-	.shift		= 20,
-};
-
 static int __init init_pit_clocksource(void)
 {
 	 /*
@@ -205,10 +126,7 @@ static int __init init_pit_clocksource(void)
 	    pit_ce.mode != CLOCK_EVT_MODE_PERIODIC)
 		return 0;
 
-	pit_cs.mult = clocksource_hz2mult(CLOCK_TICK_RATE, pit_cs.shift);
-
-	return clocksource_register(&pit_cs);
+	return clocksource_i8253_init();
 }
 arch_initcall(init_pit_clocksource);
-
 #endif /* !CONFIG_X86_64 */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 1cb0b9fc78d..6c0802eb2f7 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -249,7 +249,7 @@ void fixup_irqs(void)
 
 		data = irq_desc_get_irq_data(desc);
 		affinity = data->affinity;
-		if (!irq_has_action(irq) ||
+		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
 		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
 			continue;
@@ -276,7 +276,8 @@ void fixup_irqs(void)
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+		if (!irqd_can_move_in_process_context(data) &&
+		    !irqd_irq_disabled(data) && chip->irq_unmask)
 			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 961b6b30ba9..3fee346ef54 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -34,7 +34,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		code.offset = entry->target -
 				(entry->code + JUMP_LABEL_NOP_SIZE);
 	} else
-		memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+		memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
 	get_online_cpus();
 	mutex_lock(&text_mutex);
 	text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
@@ -44,7 +44,8 @@ void arch_jump_label_transform(struct jump_entry *entry,
 
 void arch_jump_label_text_poke_early(jump_label_t addr)
 {
-	text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+	text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5],
+			JUMP_LABEL_NOP_SIZE);
 }
 
 #endif
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index f98d3eafe07..6389a6bca11 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -26,8 +26,6 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 
-#define KVM_SCALE 22
-
 static int kvmclock = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
@@ -120,8 +118,6 @@ static struct clocksource kvm_clock = {
 	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
-	.mult = 1 << KVM_SCALE,
-	.shift = KVM_SCALE,
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -203,7 +199,7 @@ void __init kvmclock_init(void)
 	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
 	kvm_get_preset_lpj();
-	clocksource_register(&kvm_clock);
+	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index ab23f1ad4bf..52f256f2cc8 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -24,6 +24,7 @@
 #include <linux/bug.h>
 #include <linux/mm.h>
 #include <linux/gfp.h>
+#include <linux/jump_label.h>
 
 #include <asm/system.h>
 #include <asm/page.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5a532ce646b..6f9bfffb272 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -715,17 +715,15 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
 	}
 }
 
-static int
+static int __init
 check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
 {
-	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 ret;
+	return 0;
 }
 #else /* CONFIG_X86_IO_APIC */
 static
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 55d745ec118..35ccf75696e 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -50,20 +50,14 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 				struct iommu_table_entry *finish)
 {
 	struct iommu_table_entry *p, *q, *x;
-	char sym_p[KSYM_SYMBOL_LEN];
-	char sym_q[KSYM_SYMBOL_LEN];
 
 	/* Simple cyclic dependency checker. */
 	for (p = start; p < finish; p++) {
 		q = find_dependents_of(start, finish, p);
 		x = find_dependents_of(start, finish, q);
 		if (p == x) {
-			sprint_symbol(sym_p, (unsigned long)p->detect);
-			sprint_symbol(sym_q, (unsigned long)q->detect);
-
-			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
-					" on %s and vice-versa. BREAKING IT.\n",
-					sym_p, sym_q);
+			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
+			       p->detect, q->detect);
 			/* Heavy handed way..*/
 			x->depend = 0;
 		}
@@ -72,12 +66,8 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 	for (p = start; p < finish; p++) {
 		q = find_dependents_of(p, finish, p);
 		if (q && q > p) {
-			sprint_symbol(sym_p, (unsigned long)p->detect);
-			sprint_symbol(sym_q, (unsigned long)q->detect);
-
-			printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
-					"should be called before %s!\n",
-					sym_p, sym_q);
+			printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
+			       p->detect, q->detect);
 		}
 	}
 }
diff --git a/arch/x86/kernel/probe_roms_32.c b/arch/x86/kernel/probe_roms.c
index 071e7fea42e..ba0a4cce53b 100644
--- a/arch/x86/kernel/probe_roms_32.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -73,6 +73,107 @@ static struct resource video_rom_resource = {
 	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
 };
 
+/* does this oprom support the given pci device, or any of the devices
+ * that the driver supports?
+ */
+static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short device)
+{
+	struct pci_driver *drv = pdev->driver;
+	const struct pci_device_id *id;
+
+	if (pdev->vendor == vendor && pdev->device == device)
+		return true;
+
+	for (id = drv ? drv->id_table : NULL; id && id->vendor; id++)
+		if (id->vendor == vendor && id->device == device)
+			break;
+
+	return id && id->vendor;
+}
+
+static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
+		       const unsigned char *rom_list)
+{
+	unsigned short device;
+
+	do {
+		if (probe_kernel_address(rom_list, device) != 0)
+			device = 0;
+
+		if (device && match_id(pdev, vendor, device))
+			break;
+
+		rom_list += 2;
+	} while (device);
+
+	return !!device;
+}
+
+static struct resource *find_oprom(struct pci_dev *pdev)
+{
+	struct resource *oprom = NULL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
+		struct resource *res = &adapter_rom_resources[i];
+		unsigned short offset, vendor, device, list, rev;
+		const unsigned char *rom;
+
+		if (res->end == 0)
+			break;
+
+		rom = isa_bus_to_virt(res->start);
+		if (probe_kernel_address(rom + 0x18, offset) != 0)
+			continue;
+
+		if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+			continue;
+
+		if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+			continue;
+
+		if (match_id(pdev, vendor, device)) {
+			oprom = res;
+			break;
+		}
+
+		if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
+		    probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+		    rev >= 3 && list &&
+		    probe_list(pdev, vendor, rom + offset + list)) {
+			oprom = res;
+			break;
+		}
+	}
+
+	return oprom;
+}
+
+void *pci_map_biosrom(struct pci_dev *pdev)
+{
+	struct resource *oprom = find_oprom(pdev);
+
+	if (!oprom)
+		return NULL;
+
+	return ioremap(oprom->start, resource_size(oprom));
+}
+EXPORT_SYMBOL(pci_map_biosrom);
+
+void pci_unmap_biosrom(void __iomem *image)
+{
+	iounmap(image);
+}
+EXPORT_SYMBOL(pci_unmap_biosrom);
+
+size_t pci_biosrom_size(struct pci_dev *pdev)
+{
+	struct resource *oprom = find_oprom(pdev);
+
+	return oprom ? resource_size(oprom) : 0;
+}
+EXPORT_SYMBOL(pci_biosrom_size);
+
 #define ROMSIGNATURE 0xaa55
 
 static int __init romsignature(const unsigned char *rom)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d46cbe46b7a..88a90a977f8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -449,7 +449,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
 	if (!need_resched()) {
-		if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -465,7 +465,7 @@ static void mwait_idle(void)
 	if (!need_resched()) {
 		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
 		trace_cpu_idle(1, smp_processor_id());
-		if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 08c44b08bf5..0c016f72769 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(pm_power_off);
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-enum reboot_type reboot_type = BOOT_KBD;
+enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
@@ -478,9 +478,24 @@ void __attribute__((weak)) mach_reboot_fixups(void)
 {
 }
 
+/*
+ * Windows compatible x86 hardware expects the following on reboot:
+ *
+ * 1) If the FADT has the ACPI reboot register flag set, try it
+ * 2) If still alive, write to the keyboard controller
+ * 3) If still alive, write to the ACPI reboot register again
+ * 4) If still alive, write to the keyboard controller again
+ *
+ * If the machine is still alive at this stage, it gives up. We default to
+ * following the same pattern, except that if we're still alive after (4) we'll
+ * try to force a triple fault and then cycle between hitting the keyboard
+ * controller and doing that
+ */
 static void native_machine_emergency_restart(void)
 {
 	int i;
+	int attempt = 0;
+	int orig_reboot_type = reboot_type;
 
 	if (reboot_emergency)
 		emergency_vmx_disable_all();
@@ -502,6 +517,13 @@ static void native_machine_emergency_restart(void)
 				outb(0xfe, 0x64); /* pulse reset low */
 				udelay(50);
 			}
+			if (attempt == 0 && orig_reboot_type == BOOT_ACPI) {
+				attempt = 1;
+				reboot_type = BOOT_ACPI;
+			} else {
+				reboot_type = BOOT_TRIPLE;
+			}
+			break;
 
 		case BOOT_TRIPLE:
 			load_idt(&no_idt);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4be9b398470..c3050af9306 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -691,8 +691,6 @@ early_param("reservelow", parse_reservelow);
 
 void __init setup_arch(char **cmdline_p)
 {
-	unsigned long flags;
-
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -1041,9 +1039,7 @@ void __init setup_arch(char **cmdline_p)
 
 	mcheck_init();
 
-	local_irq_save(flags);
-	arch_init_ideal_nop5();
-	local_irq_restore(flags);
+	arch_init_ideal_nops();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 513deac7228..013e7eba83b 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait)
 }
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2871d3c71b..a3c430bdfb6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1332,9 +1332,9 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-	if (!(cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)))
+	if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
 		return;
-	if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH))
+	if (!this_cpu_has(X86_FEATURE_CLFLSH))
 		return;
 	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
 		return;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6515733a289..55d9bc03f69 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -9,15 +9,6 @@
 #include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
-static void save_stack_warning(void *data, char *msg)
-{
-}
-
-static void
-save_stack_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-}
-
 static int save_stack_stack(void *data, char *name)
 {
 	return 0;
@@ -53,16 +44,12 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops save_stack_ops = {
-	.warning	= save_stack_warning,
-	.warning_symbol	= save_stack_warning_symbol,
 	.stack		= save_stack_stack,
 	.address	= save_stack_address,
 	.walk_stack	= print_context_stack,
 };
 
 static const struct stacktrace_ops save_stack_ops_nosched = {
-	.warning	= save_stack_warning,
-	.warning_symbol	= save_stack_warning_symbol,
 	.stack		= save_stack_stack,
 	.address	= save_stack_address_nosched,
 	.walk_stack	= print_context_stack,
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 75ef4b18e9b..6f164bd5e14 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -35,7 +35,7 @@ void iommu_shutdown_noop(void) { }
 struct x86_init_ops x86_init __initdata = {
 
 	.resources = {
-		.probe_roms		= x86_init_noop,
+		.probe_roms		= probe_roms,
 		.reserve_resources	= reserve_standard_io_resources,
 		.memory_setup		= default_machine_specific_memory_setup,
 	},
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 1cd608973ce..e191c096ab9 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -7,7 +7,7 @@
  * kernel and insert a module (lg.ko) which allows us to run other Linux
  * kernels the same way we'd run processes.  We call the first kernel the Host,
  * and the others the Guests.  The program which sets up and configures Guests
- * (such as the example in Documentation/lguest/lguest.c) is called the
+ * (such as the example in Documentation/virtual/lguest/lguest.c) is called the
  * Launcher.
  *
  * Secondly, we only run specially modified Guests, not normal kernels: setting
@@ -913,8 +913,6 @@ static struct clocksource lguest_clock = {
 	.rating		= 200,
 	.read		= lguest_clock_read,
 	.mask		= CLOCKSOURCE_MASK(64),
-	.mult		= 1 << 22,
-	.shift		= 22,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -997,7 +995,7 @@ static void lguest_time_init(void)
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
 	irq_set_handler(0, lguest_time_irq);
 
-	clocksource_register(&lguest_clock);
+	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);
 
 	/* We can't set cpumask in the initializer: damn C limitations!  Set it
 	 * here and register our timer device. */
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index aa4326bfb24..f2145cfa12a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,6 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
 
 /*
  * Zero a page. 	
@@ -14,6 +15,15 @@ ENTRY(clear_page_c)
 	CFI_ENDPROC
 ENDPROC(clear_page_c)
 
+ENTRY(clear_page_c_e)
+	CFI_STARTPROC
+	movl $4096,%ecx
+	xorl %eax,%eax
+	rep stosb
+	ret
+	CFI_ENDPROC
+ENDPROC(clear_page_c_e)
+
 ENTRY(clear_page)
 	CFI_STARTPROC
 	xorl   %eax,%eax
@@ -38,21 +48,26 @@ ENTRY(clear_page)
 .Lclear_page_end:
 ENDPROC(clear_page)
 
-	/* Some CPUs run faster using the string instructions.
-	   It is also a lot simpler. Use this when possible */
+	/*
+	 * Some CPUs support enhanced REP MOVSB/STOSB instructions.
+	 * It is recommended to use this when possible.
+	 * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
+	 * Otherwise, use original function.
+	 *
+	 */
 
 #include <asm/cpufeature.h>
 
 	.section .altinstr_replacement,"ax"
 1:	.byte 0xeb					/* jmp <disp8> */
 	.byte (clear_page_c - clear_page) - (2f - 1b)	/* offset */
-2:
+2:	.byte 0xeb					/* jmp <disp8> */
+	.byte (clear_page_c_e - clear_page) - (3f - 2b)	/* offset */
+3:
 	.previous
 	.section .altinstructions,"a"
-	.align 8
-	.quad clear_page
-	.quad 1b
-	.word X86_FEATURE_REP_GOOD
-	.byte .Lclear_page_end - clear_page
-	.byte 2b - 1b
+	altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
+			     .Lclear_page_end-clear_page, 2b-1b
+	altinstruction_entry clear_page,2b,X86_FEATURE_ERMS,   \
+			     .Lclear_page_end-clear_page,3b-2b
 	.previous
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 99e48261519..024840266ba 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -15,23 +15,30 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
-	.macro ALTERNATIVE_JUMP feature,orig,alt
+/*
+ * By placing feature2 after feature1 in altinstructions section, we logically
+ * implement:
+ * If CPU has feature2, jmp to alt2 is used
+ * else if CPU has feature1, jmp to alt1 is used
+ * else jmp to orig is used.
+ */
+	.macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2
 0:
 	.byte 0xe9	/* 32bit jump */
 	.long \orig-1f	/* by default jump to orig */
 1:
 	.section .altinstr_replacement,"ax"
 2:	.byte 0xe9			/* near jump with 32bit immediate */
-	.long \alt-1b /* offset */   /* or alternatively to alt */
+	.long \alt1-1b /* offset */   /* or alternatively to alt1 */
+3:	.byte 0xe9			/* near jump with 32bit immediate */
+	.long \alt2-1b /* offset */   /* or alternatively to alt2 */
 	.previous
+
 	.section .altinstructions,"a"
-	.align 8
-	.quad  0b
-	.quad  2b
-	.word  \feature			/* when feature is set */
-	.byte  5
-	.byte  5
+	altinstruction_entry 0b,2b,\feature1,5,5
+	altinstruction_entry 0b,3b,\feature2,5,5
 	.previous
 	.endm
 
@@ -72,8 +79,10 @@ ENTRY(_copy_to_user)
 	addq %rdx,%rcx
 	jc bad_to_user
 	cmpq TI_addr_limit(%rax),%rcx
-	jae bad_to_user
-	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+	ja bad_to_user
+	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS,	\
+		copy_user_generic_unrolled,copy_user_generic_string,	\
+		copy_user_enhanced_fast_string
 	CFI_ENDPROC
 ENDPROC(_copy_to_user)
 
@@ -85,8 +94,10 @@ ENTRY(_copy_from_user)
 	addq %rdx,%rcx
 	jc bad_from_user
 	cmpq TI_addr_limit(%rax),%rcx
-	jae bad_from_user
-	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+	ja bad_from_user
+	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS,	\
+		copy_user_generic_unrolled,copy_user_generic_string,	\
+		copy_user_enhanced_fast_string
 	CFI_ENDPROC
 ENDPROC(_copy_from_user)
 
@@ -255,3 +266,37 @@ ENTRY(copy_user_generic_string)
 	.previous
 	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
+
+/*
+ * Some CPUs are adding enhanced REP MOVSB/STOSB instructions.
+ * It's recommended to use enhanced REP MOVSB/STOSB if it's enabled.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ENTRY(copy_user_enhanced_fast_string)
+	CFI_STARTPROC
+	andl %edx,%edx
+	jz 2f
+	movl %edx,%ecx
+1:	rep
+	movsb
+2:	xorl %eax,%eax
+	ret
+
+	.section .fixup,"ax"
+12:	movl %ecx,%edx		/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	.section __ex_table,"a"
+	.align 8
+	.quad 1b,12b
+	.previous
+	CFI_ENDPROC
+ENDPROC(copy_user_enhanced_fast_string)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 75ef61e35e3..efbf2a0ecde 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
 
 /*
  * memcpy - Copy a memory block.
@@ -37,6 +38,23 @@
 .Lmemcpy_e:
 	.previous
 
+/*
+ * memcpy_c_e() - enhanced fast string memcpy. This is faster and simpler than
+ * memcpy_c. Use memcpy_c_e when possible.
+ *
+ * This gets patched over the unrolled variant (below) via the
+ * alternative instructions framework:
+ */
+	.section .altinstr_replacement, "ax", @progbits
+.Lmemcpy_c_e:
+	movq %rdi, %rax
+
+	movl %edx, %ecx
+	rep movsb
+	ret
+.Lmemcpy_e_e:
+	.previous
+
 ENTRY(__memcpy)
 ENTRY(memcpy)
 	CFI_STARTPROC
@@ -49,7 +67,7 @@ ENTRY(memcpy)
 	jb .Lhandle_tail
 
 	/*
-	 * We check whether memory false dependece could occur,
+	 * We check whether memory false dependence could occur,
 	 * then jump to corresponding copy mode.
 	 */
 	cmp  %dil, %sil
@@ -171,21 +189,22 @@ ENDPROC(memcpy)
 ENDPROC(__memcpy)
 
 	/*
-	 * Some CPUs run faster using the string copy instructions.
-	 * It is also a lot simpler. Use this when possible:
-	 */
-
-	.section .altinstructions, "a"
-	.align 8
-	.quad memcpy
-	.quad .Lmemcpy_c
-	.word X86_FEATURE_REP_GOOD
-
-	/*
+	 * Some CPUs are adding enhanced REP MOVSB/STOSB feature
+	 * If the feature is supported, memcpy_c_e() is the first choice.
+	 * If enhanced rep movsb copy is not available, use fast string copy
+	 * memcpy_c() when possible. This is faster and code is simpler than
+	 * original memcpy().
+	 * Otherwise, original memcpy() is used.
+	 * In .altinstructions section, ERMS feature is placed after REG_GOOD
+         * feature to implement the right patch order.
+	 *
 	 * Replace only beginning, memcpy is used to apply alternatives,
 	 * so it is silly to overwrite itself with nops - reboot is the
 	 * only outcome...
 	 */
-	.byte .Lmemcpy_e - .Lmemcpy_c
-	.byte .Lmemcpy_e - .Lmemcpy_c
+	.section .altinstructions, "a"
+	altinstruction_entry memcpy,.Lmemcpy_c,X86_FEATURE_REP_GOOD,\
+			     .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c
+	altinstruction_entry memcpy,.Lmemcpy_c_e,X86_FEATURE_ERMS, \
+			     .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e
 	.previous
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0ecb8433e5a..d0ec9c2936d 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
 #define _STRING_C
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
 
 #undef memmove
 
@@ -24,6 +25,7 @@
  */
 ENTRY(memmove)
 	CFI_STARTPROC
+
 	/* Handle more 32bytes in loop */
 	mov %rdi, %rax
 	cmp $0x20, %rdx
@@ -31,8 +33,13 @@ ENTRY(memmove)
 
 	/* Decide forward/backward copy mode */
 	cmp %rdi, %rsi
-	jb	2f
+	jge .Lmemmove_begin_forward
+	mov %rsi, %r8
+	add %rdx, %r8
+	cmp %rdi, %r8
+	jg 2f
 
+.Lmemmove_begin_forward:
 	/*
 	 * movsq instruction have many startup latency
 	 * so we handle small size by general register.
@@ -78,6 +85,8 @@ ENTRY(memmove)
 	rep movsq
 	movq %r11, (%r10)
 	jmp 13f
+.Lmemmove_end_forward:
+
 	/*
 	 * Handle data backward by movsq.
 	 */
@@ -194,4 +203,22 @@ ENTRY(memmove)
 13:
 	retq
 	CFI_ENDPROC
+
+	.section .altinstr_replacement,"ax"
+.Lmemmove_begin_forward_efs:
+	/* Forward moving data. */
+	movq %rdx, %rcx
+	rep movsb
+	retq
+.Lmemmove_end_forward_efs:
+	.previous
+
+	.section .altinstructions,"a"
+	.align 8
+	.quad .Lmemmove_begin_forward
+	.quad .Lmemmove_begin_forward_efs
+	.word X86_FEATURE_ERMS
+	.byte .Lmemmove_end_forward-.Lmemmove_begin_forward
+	.byte .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
+	.previous
 ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 09d34426965..79bd454b78a 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -2,9 +2,13 @@
 
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 /*
- * ISO C memset - set a memory block to a byte value.
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the orignal function as well.
  *	
  * rdi   destination
  * rsi   value (char) 
@@ -31,6 +35,28 @@
 .Lmemset_e:
 	.previous
 
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+	.section .altinstr_replacement, "ax", @progbits
+.Lmemset_c_e:
+	movq %rdi,%r9
+	movb %sil,%al
+	movl %edx,%ecx
+	rep stosb
+	movq %r9,%rax
+	ret
+.Lmemset_e_e:
+	.previous
+
 ENTRY(memset)
 ENTRY(__memset)
 	CFI_STARTPROC
@@ -112,16 +138,20 @@ ENTRY(__memset)
 ENDPROC(memset)
 ENDPROC(__memset)
 
-	/* Some CPUs run faster using the string instructions.
-	   It is also a lot simpler. Use this when possible */
-
-#include <asm/cpufeature.h>
-
+	/* Some CPUs support enhanced REP MOVSB/STOSB feature.
+	 * It is recommended to use this when possible.
+	 *
+	 * If enhanced REP MOVSB/STOSB feature is not available, use fast string
+	 * instructions.
+	 *
+	 * Otherwise, use original memset function.
+	 *
+	 * In .altinstructions section, ERMS feature is placed after REG_GOOD
+         * feature to implement the right patch order.
+	 */
 	.section .altinstructions,"a"
-	.align 8
-	.quad memset
-	.quad .Lmemset_c
-	.word X86_FEATURE_REP_GOOD
-	.byte .Lfinal - memset
-	.byte .Lmemset_e - .Lmemset_c
+	altinstruction_entry memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
+			     .Lfinal-memset,.Lmemset_e-.Lmemset_c
+	altinstruction_entry memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
+			     .Lfinal-memset,.Lmemset_e_e-.Lmemset_c_e
 	.previous
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 3e608edf995..3d11327c9ab 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -23,8 +23,8 @@ mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
-obj-$(CONFIG_AMD_NUMA)		+= amdtopology_64.o
-obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
+obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
+obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology.c
index 0919c26820d..5247d01329c 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/io.h>
 #include <linux/pci_ids.h>
@@ -69,10 +70,10 @@ static __init void early_get_boot_cpu_id(void)
 
 int __init amd_numa_init(void)
 {
-	unsigned long start = PFN_PHYS(0);
-	unsigned long end = PFN_PHYS(max_pfn);
+	u64 start = PFN_PHYS(0);
+	u64 end = PFN_PHYS(max_pfn);
 	unsigned numnodes;
-	unsigned long prevbase;
+	u64 prevbase;
 	int i, j, nb;
 	u32 nodeid, reg;
 	unsigned int bits, cores, apicid_base;
@@ -95,7 +96,7 @@ int __init amd_numa_init(void)
 
 	prevbase = 0;
 	for (i = 0; i < 8; i++) {
-		unsigned long base, limit;
+		u64 base, limit;
 
 		base = read_pci_config(0, nb, 1, 0x40 + i*8);
 		limit = read_pci_config(0, nb, 1, 0x44 + i*8);
@@ -107,18 +108,18 @@ int __init amd_numa_init(void)
 			continue;
 		}
 		if (nodeid >= numnodes) {
-			pr_info("Ignoring excess node %d (%lx:%lx)\n", nodeid,
+			pr_info("Ignoring excess node %d (%Lx:%Lx)\n", nodeid,
 				base, limit);
 			continue;
 		}
 
 		if (!limit) {
-			pr_info("Skipping node entry %d (base %lx)\n",
+			pr_info("Skipping node entry %d (base %Lx)\n",
 				i, base);
 			continue;
 		}
 		if ((base >> 8) & 3 || (limit >> 8) & 3) {
-			pr_err("Node %d using interleaving mode %lx/%lx\n",
+			pr_err("Node %d using interleaving mode %Lx/%Lx\n",
 			       nodeid, (base >> 8) & 3, (limit >> 8) & 3);
 			return -EINVAL;
 		}
@@ -150,19 +151,19 @@ int __init amd_numa_init(void)
 			continue;
 		}
 		if (limit < base) {
-			pr_err("Node %d bogus settings %lx-%lx.\n",
+			pr_err("Node %d bogus settings %Lx-%Lx.\n",
 			       nodeid, base, limit);
 			continue;
 		}
 
 		/* Could sort here, but pun for now. Should not happen anyroads. */
 		if (prevbase > base) {
-			pr_err("Node map not sorted %lx,%lx\n",
+			pr_err("Node map not sorted %Lx,%Lx\n",
 			       prevbase, base);
 			return -EINVAL;
 		}
 
-		pr_info("Node %d MemBase %016lx Limit %016lx\n",
+		pr_info("Node %d MemBase %016Lx Limit %016Lx\n",
 			nodeid, base, limit);
 
 		prevbase = base;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 80088f99419..29f7c6d9817 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -678,8 +678,10 @@ static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] =
 		virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+#endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM
 	max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
@@ -716,6 +718,7 @@ void __init paging_init(void)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 	olpc_dt_build_devicetree();
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	zone_sizes_init();
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 79423358728..d865c4aeec5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -616,7 +616,9 @@ void __init paging_init(void)
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+#endif
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
@@ -679,14 +681,6 @@ int arch_add_memory(int nid, u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
-#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
-int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0369843511d..be1ef574ce9 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -91,13 +91,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		return (__force void __iomem *)phys_to_virt(phys_addr);
 
 	/*
-	 * Check if the request spans more than any BAR in the iomem resource
-	 * tree.
-	 */
-	WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
-		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
-
-	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
 	last_pfn = last_addr >> PAGE_SHIFT;
@@ -170,6 +163,13 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	ret_addr = (void __iomem *) (vaddr + offset);
 	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
 
+	/*
+	 * Check if the request spans more than any BAR in the iomem resource
+	 * tree.
+	 */
+	WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size),
+		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
+
 	return ret_addr;
 err_free_area:
 	free_vm_area(area);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 745258dfc4d..f5510d889a2 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,11 +1,39 @@
 /* Common code for 32 and 64-bit NUMA */
-#include <linux/topology.h>
-#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/init.h>
 #include <linux/bootmem.h>
-#include <asm/numa.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/topology.h>
+
+#include <asm/e820.h>
+#include <asm/proto.h>
+#include <asm/dma.h>
 #include <asm/acpi.h>
+#include <asm/amd_nb.h>
+
+#include "numa_internal.h"
 
 int __initdata numa_off;
+nodemask_t numa_nodes_parsed __initdata;
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+
+static struct numa_meminfo numa_meminfo
+#ifndef CONFIG_MEMORY_HOTPLUG
+__initdata
+#endif
+;
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
 
 static __init int numa_setup(char *opt)
 {
@@ -32,6 +60,15 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
+int __cpuinit numa_cpu_node(int cpu)
+{
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
+}
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
@@ -95,6 +132,407 @@ void __init setup_node_to_cpumask_map(void)
 	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
+static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
+				     struct numa_meminfo *mi)
+{
+	/* ignore zero length blks */
+	if (start == end)
+		return 0;
+
+	/* whine about and ignore invalid blks */
+	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
+		pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
+			   nid, start, end);
+		return 0;
+	}
+
+	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: too many memblk ranges\n");
+		return -EINVAL;
+	}
+
+	mi->blk[mi->nr_blks].start = start;
+	mi->blk[mi->nr_blks].end = end;
+	mi->blk[mi->nr_blks].nid = nid;
+	mi->nr_blks++;
+	return 0;
+}
+
+/**
+ * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
+ * @idx: Index of memblk to remove
+ * @mi: numa_meminfo to remove memblk from
+ *
+ * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
+ * decrementing @mi->nr_blks.
+ */
+void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
+{
+	mi->nr_blks--;
+	memmove(&mi->blk[idx], &mi->blk[idx + 1],
+		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
+}
+
+/**
+ * numa_add_memblk - Add one numa_memblk to numa_meminfo
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @end: End address of the new memblk
+ *
+ * Add a new memblk to the default numa_meminfo.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
+}
+
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start, u64 end)
+{
+	const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
+	const u64 nd_high = PFN_PHYS(max_pfn_mapped);
+	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
+	bool remapped = false;
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	/*
+	 * Don't confuse VM with a node that doesn't have the
+	 * minimum amount of memory:
+	 */
+	if (end && (end - start) < NODE_MIN_SIZE)
+		return;
+
+	/* initialize remap allocator before aligning to ZONE_ALIGN */
+	init_alloc_remap(nid, start, end);
+
+	start = roundup(start, ZONE_ALIGN);
+
+	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
+	       nid, start, end);
+
+	/*
+	 * Allocate node data.  Try remap allocator first, node-local
+	 * memory and then any node.  Never allocate in DMA zone.
+	 */
+	nd = alloc_remap(nid, nd_size);
+	if (nd) {
+		nd_pa = __pa(nd);
+		remapped = true;
+	} else {
+		nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
+						nd_size, SMP_CACHE_BYTES);
+		if (nd_pa == MEMBLOCK_ERROR)
+			nd_pa = memblock_find_in_range(nd_low, nd_high,
+						nd_size, SMP_CACHE_BYTES);
+		if (nd_pa == MEMBLOCK_ERROR) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
+		memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
+		nd = __va(nd_pa);
+	}
+
+	/* report and initialize */
+	printk(KERN_INFO "  NODE_DATA [%016Lx - %016Lx]%s\n",
+	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (!remapped && tnid != nid)
+		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nid, tnid);
+
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
+	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
+
+	node_set_online(nid);
+}
+
+/**
+ * numa_cleanup_meminfo - Cleanup a numa_meminfo
+ * @mi: numa_meminfo to clean up
+ *
+ * Sanitize @mi by merging and removing unncessary memblks.  Also check for
+ * conflicts and clear unused memblks.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
+{
+	const u64 low = 0;
+	const u64 high = PFN_PHYS(max_pfn);
+	int i, j, k;
+
+	/* first, trim all entries */
+	for (i = 0; i < mi->nr_blks; i++) {
+		struct numa_memblk *bi = &mi->blk[i];
+
+		/* make sure all blocks are inside the limits */
+		bi->start = max(bi->start, low);
+		bi->end = min(bi->end, high);
+
+		/* and there's no empty block */
+		if (bi->start >= bi->end)
+			numa_remove_memblk_from(i--, mi);
+	}
+
+	/* merge neighboring / overlapping entries */
+	for (i = 0; i < mi->nr_blks; i++) {
+		struct numa_memblk *bi = &mi->blk[i];
+
+		for (j = i + 1; j < mi->nr_blks; j++) {
+			struct numa_memblk *bj = &mi->blk[j];
+			u64 start, end;
+
+			/*
+			 * See whether there are overlapping blocks.  Whine
+			 * about but allow overlaps of the same nid.  They
+			 * will be merged below.
+			 */
+			if (bi->end > bj->start && bi->start < bj->end) {
+				if (bi->nid != bj->nid) {
+					pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
+					       bi->nid, bi->start, bi->end,
+					       bj->nid, bj->start, bj->end);
+					return -EINVAL;
+				}
+				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
+					   bi->nid, bi->start, bi->end,
+					   bj->start, bj->end);
+			}
+
+			/*
+			 * Join together blocks on the same node, holes
+			 * between which don't overlap with memory on other
+			 * nodes.
+			 */
+			if (bi->nid != bj->nid)
+				continue;
+			start = min(bi->start, bj->start);
+			end = max(bi->end, bj->end);
+			for (k = 0; k < mi->nr_blks; k++) {
+				struct numa_memblk *bk = &mi->blk[k];
+
+				if (bi->nid == bk->nid)
+					continue;
+				if (start < bk->end && end > bk->start)
+					break;
+			}
+			if (k < mi->nr_blks)
+				continue;
+			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
+			       bi->nid, bi->start, bi->end, bj->start, bj->end,
+			       start, end);
+			bi->start = start;
+			bi->end = end;
+			numa_remove_memblk_from(j--, mi);
+		}
+	}
+
+	/* clear unused ones */
+	for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
+		mi->blk[i].start = mi->blk[i].end = 0;
+		mi->blk[i].nid = NUMA_NO_NODE;
+	}
+
+	return 0;
+}
+
+/*
+ * Set nodes, which have memory in @mi, in *@nodemask.
+ */
+static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
+					      const struct numa_meminfo *mi)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
+		if (mi->blk[i].start != mi->blk[i].end &&
+		    mi->blk[i].nid != NUMA_NO_NODE)
+			node_set(mi->blk[i].nid, *nodemask);
+}
+
+/**
+ * numa_reset_distance - Reset NUMA distance table
+ *
+ * The current table is freed.  The next numa_set_distance() call will
+ * create a new one.
+ */
+void __init numa_reset_distance(void)
+{
+	size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
+
+	/* numa_distance could be 1LU marking allocation failure, test cnt */
+	if (numa_distance_cnt)
+		memblock_x86_free_range(__pa(numa_distance),
+					__pa(numa_distance) + size);
+	numa_distance_cnt = 0;
+	numa_distance = NULL;	/* enable table creation */
+}
+
+static int __init numa_alloc_distance(void)
+{
+	nodemask_t nodes_parsed;
+	size_t size;
+	int i, j, cnt = 0;
+	u64 phys;
+
+	/* size the new table and allocate it */
+	nodes_parsed = numa_nodes_parsed;
+	numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
+
+	for_each_node_mask(i, nodes_parsed)
+		cnt = i;
+	cnt++;
+	size = cnt * cnt * sizeof(numa_distance[0]);
+
+	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+				      size, PAGE_SIZE);
+	if (phys == MEMBLOCK_ERROR) {
+		pr_warning("NUMA: Warning: can't allocate distance table!\n");
+		/* don't retry until explicitly reset */
+		numa_distance = (void *)1LU;
+		return -ENOMEM;
+	}
+	memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
+
+	numa_distance = __va(phys);
+	numa_distance_cnt = cnt;
+
+	/* fill with the default distances */
+	for (i = 0; i < cnt; i++)
+		for (j = 0; j < cnt; j++)
+			numa_distance[i * cnt + j] = i == j ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
+
+	return 0;
+}
+
+/**
+ * numa_set_distance - Set NUMA distance from one NUMA to another
+ * @from: the 'from' node to set distance
+ * @to: the 'to'  node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.  If distance table
+ * doesn't exist, one which is large enough to accommodate all the currently
+ * known nodes will be created.
+ *
+ * If such table cannot be allocated, a warning is printed and further
+ * calls are ignored until the distance table is reset with
+ * numa_reset_distance().
+ *
+ * If @from or @to is higher than the highest known node at the time of
+ * table creation or @distance doesn't make sense, the call is ignored.
+ * This is to allow simplification of specific NUMA config implementations.
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+	if (!numa_distance && numa_alloc_distance() < 0)
+		return;
+
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
+		printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
+			    from, to, distance);
+		return;
+	}
+
+	if ((u8)distance != distance ||
+	    (from == to && distance != LOCAL_DISTANCE)) {
+		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+			     from, to, distance);
+		return;
+	}
+
+	numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+int __node_distance(int from, int to)
+{
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+	return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+/*
+ * Sanity check to catch more bad NUMA configurations (they are amazingly
+ * common).  Make sure the nodes cover all memory.
+ */
+static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
+{
+	u64 numaram, e820ram;
+	int i;
+
+	numaram = 0;
+	for (i = 0; i < mi->nr_blks; i++) {
+		u64 s = mi->blk[i].start >> PAGE_SHIFT;
+		u64 e = mi->blk[i].end >> PAGE_SHIFT;
+		numaram += e - s;
+		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
+		if ((s64)numaram < 0)
+			numaram = 0;
+	}
+
+	e820ram = max_pfn - (memblock_x86_hole_size(0,
+					PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
+	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+	if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
+		printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
+		       (numaram << PAGE_SHIFT) >> 20,
+		       (e820ram << PAGE_SHIFT) >> 20);
+		return false;
+	}
+	return true;
+}
+
+static int __init numa_register_memblks(struct numa_meminfo *mi)
+{
+	int i, nid;
+
+	/* Account for nodes with cpus and no memory */
+	node_possible_map = numa_nodes_parsed;
+	numa_nodemask_from_meminfo(&node_possible_map, mi);
+	if (WARN_ON(nodes_empty(node_possible_map)))
+		return -EINVAL;
+
+	for (i = 0; i < mi->nr_blks; i++)
+		memblock_x86_register_active_regions(mi->blk[i].nid,
+					mi->blk[i].start >> PAGE_SHIFT,
+					mi->blk[i].end >> PAGE_SHIFT);
+
+	/* for out of order entries */
+	sort_node_map();
+	if (!numa_meminfo_cover_memory(mi))
+		return -EINVAL;
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, node_possible_map) {
+		u64 start = PFN_PHYS(max_pfn);
+		u64 end = 0;
+
+		for (i = 0; i < mi->nr_blks; i++) {
+			if (nid != mi->blk[i].nid)
+				continue;
+			start = min(mi->blk[i].start, start);
+			end = max(mi->blk[i].end, end);
+		}
+
+		if (start < end)
+			setup_node_data(nid, start, end);
+	}
+
+	return 0;
+}
+
 /*
  * There are unfortunately some poorly designed mainboards around that
  * only connect memory to a single CPU. This breaks the 1:1 cpu->node
@@ -102,7 +540,7 @@ void __init setup_node_to_cpumask_map(void)
  * as the number of CPUs is not known yet. We round robin the existing
  * nodes.
  */
-void __init numa_init_array(void)
+static void __init numa_init_array(void)
 {
 	int rr, i;
 
@@ -117,6 +555,95 @@ void __init numa_init_array(void)
 	}
 }
 
+static int __init numa_init(int (*init_func)(void))
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, NUMA_NO_NODE);
+
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
+	remove_all_active_ranges();
+	numa_reset_distance();
+
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+	ret = numa_cleanup_meminfo(&numa_meminfo);
+	if (ret < 0)
+		return ret;
+
+	numa_emulation(&numa_meminfo, numa_distance_cnt);
+
+	ret = numa_register_memblks(&numa_meminfo);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < nr_cpu_ids; i++) {
+		int nid = early_cpu_to_node(i);
+
+		if (nid == NUMA_NO_NODE)
+			continue;
+		if (!node_online(nid))
+			numa_clear_node(i);
+	}
+	numa_init_array();
+	return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node and add memory blocks that cover all
+ * allowed memory.  This function must not fail.
+ */
+static int __init dummy_numa_init(void)
+{
+	printk(KERN_INFO "%s\n",
+	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
+	printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
+	       0LLU, PFN_PHYS(max_pfn));
+
+	node_set(0, numa_nodes_parsed);
+	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
+
+	return 0;
+}
+
+/**
+ * x86_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encomapssing whole memory and
+ * never fails.
+ */
+void __init x86_numa_init(void)
+{
+	if (!numa_off) {
+#ifdef CONFIG_X86_NUMAQ
+		if (!numa_init(numaq_numa_init))
+			return;
+#endif
+#ifdef CONFIG_ACPI_NUMA
+		if (!numa_init(x86_acpi_numa_init))
+			return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+		if (!numa_init(amd_numa_init))
+			return;
+#endif
+	}
+
+	numa_init(dummy_numa_init);
+}
+
 static __init int find_near_online_node(int node)
 {
 	int n, val;
@@ -282,3 +809,18 @@ const struct cpumask *cpumask_of_node(int node)
 EXPORT_SYMBOL(cpumask_of_node);
 
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 start)
+{
+	struct numa_meminfo *mi = &numa_meminfo;
+	int nid = mi->blk[0].nid;
+	int i;
+
+	for (i = 0; i < mi->nr_blks; i++)
+		if (mi->blk[i].start <= start && mi->blk[i].end > start)
+			nid = mi->blk[i].nid;
+	return nid;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index bde3906420d..849a975d3fa 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -22,39 +22,11 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/mm.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/highmem.h>
-#include <linux/initrd.h>
-#include <linux/nodemask.h>
 #include <linux/module.h>
-#include <linux/kexec.h>
-#include <linux/pfn.h>
-#include <linux/swap.h>
-#include <linux/acpi.h>
-
-#include <asm/e820.h>
-#include <asm/setup.h>
-#include <asm/mmzone.h>
-#include <asm/bios_ebda.h>
-#include <asm/proto.h>
-
-struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
-EXPORT_SYMBOL(node_data);
-
-/*
- * numa interface - we expect the numa architecture specific code to have
- *                  populated the following initialisation.
- *
- * 1) node_online_map  - the map of all nodes configured (online) in the system
- * 2) node_start_pfn   - the starting page frame number for a node
- * 3) node_end_pfn     - the ending page fram number for a node
- */
-unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly;
-unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;
 
+#include "numa_internal.h"
 
 #ifdef CONFIG_DISCONTIGMEM
 /*
@@ -99,108 +71,46 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
 }
 #endif
 
-extern unsigned long find_max_low_pfn(void);
 extern unsigned long highend_pfn, highstart_pfn;
 
 #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
 
-unsigned long node_remap_size[MAX_NUMNODES];
 static void *node_remap_start_vaddr[MAX_NUMNODES];
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-static unsigned long kva_start_pfn;
-static unsigned long kva_pages;
-
-int __cpuinit numa_cpu_node(int cpu)
-{
-	return apic->x86_32_numa_cpu_node(cpu);
-}
-
-/*
- * FLAT - support for basic PC memory model with discontig enabled, essentially
- *        a single node with all available processors in it with a flat
- *        memory map.
- */
-int __init get_memcfg_numa_flat(void)
-{
-	printk(KERN_DEBUG "NUMA - single node, flat memory mode\n");
-
-	node_start_pfn[0] = 0;
-	node_end_pfn[0] = max_pfn;
-	memblock_x86_register_active_regions(0, 0, max_pfn);
-	memory_present(0, 0, max_pfn);
-	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
-
-        /* Indicate there is one node available. */
-	nodes_clear(node_online_map);
-	node_set_online(0);
-	return 1;
-}
-
-/*
- * Find the highest page frame number we have available for the node
- */
-static void __init propagate_e820_map_node(int nid)
-{
-	if (node_end_pfn[nid] > max_pfn)
-		node_end_pfn[nid] = max_pfn;
-	/*
-	 * if a user has given mem=XXXX, then we need to make sure 
-	 * that the node _starts_ before that, too, not just ends
-	 */
-	if (node_start_pfn[nid] > max_pfn)
-		node_start_pfn[nid] = max_pfn;
-	BUG_ON(node_start_pfn[nid] > node_end_pfn[nid]);
-}
-
-/* 
- * Allocate memory for the pg_data_t for this node via a crude pre-bootmem
- * method.  For node zero take this from the bottom of memory, for
- * subsequent nodes place them at node_remap_start_vaddr which contains
- * node local data in physically node local memory.  See setup_memory()
- * for details.
- */
-static void __init allocate_pgdat(int nid)
-{
-	char buf[16];
-
-	if (node_has_online_mem(nid) && node_remap_start_vaddr[nid])
-		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
-	else {
-		unsigned long pgdat_phys;
-		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
-				 max_pfn_mapped<<PAGE_SHIFT,
-				 sizeof(pg_data_t),
-				 PAGE_SIZE);
-		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
-		memset(buf, 0, sizeof(buf));
-		sprintf(buf, "NODE_DATA %d",  nid);
-		memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
-	}
-	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
-		nid, (unsigned long)NODE_DATA(nid));
-}
-
 /*
- * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel
- * virtual address space (KVA) is reserved and portions of nodes are mapped
- * using it. This is to allow node-local memory to be allocated for
- * structures that would normally require ZONE_NORMAL. The memory is
- * allocated with alloc_remap() and callers should be prepared to allocate
- * from the bootmem allocator instead.
+ * Remap memory allocator
  */
 static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 static void *node_remap_end_vaddr[MAX_NUMNODES];
 static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-static unsigned long node_remap_offset[MAX_NUMNODES];
 
+/**
+ * alloc_remap - Allocate remapped memory
+ * @nid: NUMA node to allocate memory from
+ * @size: The size of allocation
+ *
+ * Allocate @size bytes from the remap area of NUMA node @nid.  The
+ * size of the remap area is predetermined by init_alloc_remap() and
+ * only the callers considered there should call this function.  For
+ * more info, please read the comment on top of init_alloc_remap().
+ *
+ * The caller must be ready to handle allocation failure from this
+ * function and fall back to regular memory allocator in such cases.
+ *
+ * CONTEXT:
+ * Single CPU early boot context.
+ *
+ * RETURNS:
+ * Pointer to the allocated memory on success, %NULL on failure.
+ */
 void *alloc_remap(int nid, unsigned long size)
 {
 	void *allocation = node_remap_alloc_vaddr[nid];
 
 	size = ALIGN(size, L1_CACHE_BYTES);
 
-	if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
+	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
 		return NULL;
 
 	node_remap_alloc_vaddr[nid] += size;
@@ -209,26 +119,6 @@ void *alloc_remap(int nid, unsigned long size)
 	return allocation;
 }
 
-static void __init remap_numa_kva(void)
-{
-	void *vaddr;
-	unsigned long pfn;
-	int node;
-
-	for_each_online_node(node) {
-		printk(KERN_DEBUG "remap_numa_kva: node %d\n", node);
-		for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
-			vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
-			printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n",
-				(unsigned long)vaddr,
-				node_remap_start_pfn[node] + pfn);
-			set_pmd_pfn((ulong) vaddr, 
-				node_remap_start_pfn[node] + pfn, 
-				PAGE_KERNEL_LARGE);
-		}
-	}
-}
-
 #ifdef CONFIG_HIBERNATION
 /**
  * resume_map_numa_kva - add KVA mapping to the temporary page tables created
@@ -240,15 +130,16 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 	int node;
 
 	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, size, pfn;
+		unsigned long start_va, start_pfn, nr_pages, pfn;
 
 		start_va = (unsigned long)node_remap_start_vaddr[node];
 		start_pfn = node_remap_start_pfn[node];
-		size = node_remap_size[node];
+		nr_pages = (node_remap_end_vaddr[node] -
+			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
 
 		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
 
-		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
 			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
 			pgd_t *pgd = pgd_base + pgd_index(vaddr);
 			pud_t *pud = pud_offset(pgd, vaddr);
@@ -264,132 +155,89 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 }
 #endif
 
-static __init unsigned long calculate_numa_remap_pages(void)
+/**
+ * init_alloc_remap - Initialize remap allocator for a NUMA node
+ * @nid: NUMA node to initizlie remap allocator for
+ *
+ * NUMA nodes may end up without any lowmem.  As allocating pgdat and
+ * memmap on a different node with lowmem is inefficient, a special
+ * remap allocator is implemented which can be used by alloc_remap().
+ *
+ * For each node, the amount of memory which will be necessary for
+ * pgdat and memmap is calculated and two memory areas of the size are
+ * allocated - one in the node and the other in lowmem; then, the area
+ * in the node is remapped to the lowmem area.
+ *
+ * As pgdat and memmap must be allocated in lowmem anyway, this
+ * doesn't waste lowmem address space; however, the actual lowmem
+ * which gets remapped over is wasted.  The amount shouldn't be
+ * problematic on machines this feature will be used.
+ *
+ * Initialization failure isn't fatal.  alloc_remap() is used
+ * opportunistically and the callers will fall back to other memory
+ * allocation mechanisms on failure.
+ */
+void __init init_alloc_remap(int nid, u64 start, u64 end)
 {
-	int nid;
-	unsigned long size, reserve_pages = 0;
-
-	for_each_online_node(nid) {
-		u64 node_kva_target;
-		u64 node_kva_final;
-
-		/*
-		 * The acpi/srat node info can show hot-add memroy zones
-		 * where memory could be added but not currently present.
-		 */
-		printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-			nid, node_start_pfn[nid], node_end_pfn[nid]);
-		if (node_start_pfn[nid] > max_pfn)
-			continue;
-		if (!node_end_pfn[nid])
-			continue;
-		if (node_end_pfn[nid] > max_pfn)
-			node_end_pfn[nid] = max_pfn;
-
-		/* ensure the remap includes space for the pgdat. */
-		size = node_remap_size[nid] + sizeof(pg_data_t);
-
-		/* convert size to large (pmd size) pages, rounding up */
-		size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES;
-		/* now the roundup is correct, convert to PAGE_SIZE pages */
-		size = size * PTRS_PER_PTE;
-
-		node_kva_target = round_down(node_end_pfn[nid] - size,
-						 PTRS_PER_PTE);
-		node_kva_target <<= PAGE_SHIFT;
-		do {
-			node_kva_final = memblock_find_in_range(node_kva_target,
-					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
-						((u64)size)<<PAGE_SHIFT,
-						LARGE_PAGE_BYTES);
-			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == MEMBLOCK_ERROR &&
-			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
-
-		if (node_kva_final == MEMBLOCK_ERROR)
-			panic("Can not get kva ram\n");
-
-		node_remap_size[nid] = size;
-		node_remap_offset[nid] = reserve_pages;
-		reserve_pages += size;
-		printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of"
-				  " node %d at %llx\n",
-				size, nid, node_kva_final>>PAGE_SHIFT);
-
-		/*
-		 *  prevent kva address below max_low_pfn want it on system
-		 *  with less memory later.
-		 *  layout will be: KVA address , KVA RAM
-		 *
-		 *  we are supposed to only record the one less then max_low_pfn
-		 *  but we could have some hole in high memory, and it will only
-		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
-		 *  to use it as free.
-		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
-		 */
-		memblock_x86_reserve_range(node_kva_final,
-			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
-			      "KVA RAM");
-
-		node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT;
-	}
-	printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",
-			reserve_pages);
-	return reserve_pages;
-}
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long end_pfn = end >> PAGE_SHIFT;
+	unsigned long size, pfn;
+	u64 node_pa, remap_pa;
+	void *remap_va;
 
-static void init_remap_allocator(int nid)
-{
-	node_remap_start_vaddr[nid] = pfn_to_kaddr(
-			kva_start_pfn + node_remap_offset[nid]);
-	node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +
-		(node_remap_size[nid] * PAGE_SIZE);
-	node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] +
-		ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-
-	printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid,
-		(ulong) node_remap_start_vaddr[nid],
-		(ulong) node_remap_end_vaddr[nid]);
+	/*
+	 * The acpi/srat node info can show hot-add memroy zones where
+	 * memory could be added but not currently present.
+	 */
+	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
+	       nid, start_pfn, end_pfn);
+
+	/* calculate the necessary space aligned to large page size */
+	size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
+	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
+	size = ALIGN(size, LARGE_PAGE_BYTES);
+
+	/* allocate node memory and the lowmem remap area */
+	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
+	if (node_pa == MEMBLOCK_ERROR) {
+		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
+			   size, nid);
+		return;
+	}
+	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
+
+	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
+					  max_low_pfn << PAGE_SHIFT,
+					  size, LARGE_PAGE_BYTES);
+	if (remap_pa == MEMBLOCK_ERROR) {
+		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
+			   size, nid);
+		memblock_x86_free_range(node_pa, node_pa + size);
+		return;
+	}
+	memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
+	remap_va = phys_to_virt(remap_pa);
+
+	/* perform actual remap */
+	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
+		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
+			    (node_pa >> PAGE_SHIFT) + pfn,
+			    PAGE_KERNEL_LARGE);
+
+	/* initialize remap allocator parameters */
+	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
+	node_remap_start_vaddr[nid] = remap_va;
+	node_remap_end_vaddr[nid] = remap_va + size;
+	node_remap_alloc_vaddr[nid] = remap_va;
+
+	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
+	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
 }
 
 void __init initmem_init(void)
 {
-	int nid;
-	long kva_target_pfn;
-
-	/*
-	 * When mapping a NUMA machine we allocate the node_mem_map arrays
-	 * from node local memory.  They are then mapped directly into KVA
-	 * between zone normal and vmalloc space.  Calculate the size of
-	 * this space and use it to adjust the boundary between ZONE_NORMAL
-	 * and ZONE_HIGHMEM.
-	 */
-
-	get_memcfg_numa();
-	numa_init_array();
-
-	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
+	x86_numa_init();
 
-	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
-	do {
-		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
-					max_low_pfn<<PAGE_SHIFT,
-					kva_pages<<PAGE_SHIFT,
-					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
-		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
-
-	if (kva_start_pfn == MEMBLOCK_ERROR)
-		panic("Can not get kva space\n");
-
-	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
-		kva_start_pfn, max_low_pfn);
-	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
-
-	/* avoid clash with initrd */
-	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
-		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
-		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
@@ -409,51 +257,9 @@ void __init initmem_init(void)
 
 	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(max_low_pfn));
-	for_each_online_node(nid) {
-		init_remap_allocator(nid);
-
-		allocate_pgdat(nid);
-	}
-	remap_numa_kva();
 
 	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(highstart_pfn));
-	for_each_online_node(nid)
-		propagate_e820_map_node(nid);
-
-	for_each_online_node(nid) {
-		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
-		NODE_DATA(nid)->node_id = nid;
-	}
 
 	setup_bootmem_allocator();
 }
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int paddr_to_nid(u64 addr)
-{
-	int nid;
-	unsigned long pfn = PFN_DOWN(addr);
-
-	for_each_node(nid)
-		if (node_start_pfn[nid] <= pfn &&
-		    pfn < node_end_pfn[nid])
-			return nid;
-
-	return -1;
-}
-
-/*
- * This function is used to ask node id BEFORE memmap and mem_section's
- * initialization (pfn_to_nid() can't be used yet).
- * If _PXM is not defined on ACPI's DSDT, node id must be found by this.
- */
-int memory_add_physaddr_to_nid(u64 addr)
-{
-	int nid = paddr_to_nid(addr);
-	return (nid >= 0) ? nid : 0;
-}
-
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 85b52fc0308..dd27f401f0a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -2,646 +2,13 @@
  * Generic VM initialization for x86-64 NUMA setups.
  * Copyright 2002,2003 Andi Kleen, SuSE Labs.
  */
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/init.h>
 #include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/ctype.h>
-#include <linux/module.h>
-#include <linux/nodemask.h>
-#include <linux/sched.h>
-#include <linux/acpi.h>
-
-#include <asm/e820.h>
-#include <asm/proto.h>
-#include <asm/dma.h>
-#include <asm/acpi.h>
-#include <asm/amd_nb.h>
 
 #include "numa_internal.h"
 
-struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
-EXPORT_SYMBOL(node_data);
-
-nodemask_t numa_nodes_parsed __initdata;
-
-struct memnode memnode;
-
-static unsigned long __initdata nodemap_addr;
-static unsigned long __initdata nodemap_size;
-
-static struct numa_meminfo numa_meminfo __initdata;
-
-static int numa_distance_cnt;
-static u8 *numa_distance;
-
-/*
- * Given a shift value, try to populate memnodemap[]
- * Returns :
- * 1 if OK
- * 0 if memnodmap[] too small (of shift too small)
- * -1 if node overlap or lost ram (shift too big)
- */
-static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift)
-{
-	unsigned long addr, end;
-	int i, res = -1;
-
-	memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
-	for (i = 0; i < mi->nr_blks; i++) {
-		addr = mi->blk[i].start;
-		end = mi->blk[i].end;
-		if (addr >= end)
-			continue;
-		if ((end >> shift) >= memnodemapsize)
-			return 0;
-		do {
-			if (memnodemap[addr >> shift] != NUMA_NO_NODE)
-				return -1;
-			memnodemap[addr >> shift] = mi->blk[i].nid;
-			addr += (1UL << shift);
-		} while (addr < end);
-		res = 1;
-	}
-	return res;
-}
-
-static int __init allocate_cachealigned_memnodemap(void)
-{
-	unsigned long addr;
-
-	memnodemap = memnode.embedded_map;
-	if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
-		return 0;
-
-	addr = 0x8000;
-	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = memblock_find_in_range(addr, get_max_mapped(),
-				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == MEMBLOCK_ERROR) {
-		printk(KERN_ERR
-		       "NUMA: Unable to allocate Memory to Node hash map\n");
-		nodemap_addr = nodemap_size = 0;
-		return -1;
-	}
-	memnodemap = phys_to_virt(nodemap_addr);
-	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
-
-	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
-	       nodemap_addr, nodemap_addr + nodemap_size);
-	return 0;
-}
-
-/*
- * The LSB of all start and end addresses in the node map is the value of the
- * maximum possible shift.
- */
-static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi)
-{
-	int i, nodes_used = 0;
-	unsigned long start, end;
-	unsigned long bitfield = 0, memtop = 0;
-
-	for (i = 0; i < mi->nr_blks; i++) {
-		start = mi->blk[i].start;
-		end = mi->blk[i].end;
-		if (start >= end)
-			continue;
-		bitfield |= start;
-		nodes_used++;
-		if (end > memtop)
-			memtop = end;
-	}
-	if (nodes_used <= 1)
-		i = 63;
-	else
-		i = find_first_bit(&bitfield, sizeof(unsigned long)*8);
-	memnodemapsize = (memtop >> i)+1;
-	return i;
-}
-
-static int __init compute_hash_shift(const struct numa_meminfo *mi)
-{
-	int shift;
-
-	shift = extract_lsb_from_nodes(mi);
-	if (allocate_cachealigned_memnodemap())
-		return -1;
-	printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
-		shift);
-
-	if (populate_memnodemap(mi, shift) != 1) {
-		printk(KERN_INFO "Your memory is not aligned you need to "
-		       "rebuild your kernel with a bigger NODEMAPSIZE "
-		       "shift=%d\n", shift);
-		return -1;
-	}
-	return shift;
-}
-
-int __meminit  __early_pfn_to_nid(unsigned long pfn)
-{
-	return phys_to_nid(pfn << PAGE_SHIFT);
-}
-
-static void * __init early_node_mem(int nodeid, unsigned long start,
-				    unsigned long end, unsigned long size,
-				    unsigned long align)
-{
-	unsigned long mem;
-
-	/*
-	 * put it on high as possible
-	 * something will go with NODE_DATA
-	 */
-	if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
-		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
-	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
-		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
-	if (mem != MEMBLOCK_ERROR)
-		return __va(mem);
-
-	/* extend the search scope */
-	end = max_pfn_mapped << PAGE_SHIFT;
-	start = MAX_DMA_PFN << PAGE_SHIFT;
-	mem = memblock_find_in_range(start, end, size, align);
-	if (mem != MEMBLOCK_ERROR)
-		return __va(mem);
-
-	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
-		       size, nodeid);
-
-	return NULL;
-}
-
-static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
-				     struct numa_meminfo *mi)
-{
-	/* ignore zero length blks */
-	if (start == end)
-		return 0;
-
-	/* whine about and ignore invalid blks */
-	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
-		pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
-			   nid, start, end);
-		return 0;
-	}
-
-	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
-		pr_err("NUMA: too many memblk ranges\n");
-		return -EINVAL;
-	}
-
-	mi->blk[mi->nr_blks].start = start;
-	mi->blk[mi->nr_blks].end = end;
-	mi->blk[mi->nr_blks].nid = nid;
-	mi->nr_blks++;
-	return 0;
-}
-
-/**
- * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
- * @idx: Index of memblk to remove
- * @mi: numa_meminfo to remove memblk from
- *
- * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
- * decrementing @mi->nr_blks.
- */
-void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
-{
-	mi->nr_blks--;
-	memmove(&mi->blk[idx], &mi->blk[idx + 1],
-		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
-}
-
-/**
- * numa_add_memblk - Add one numa_memblk to numa_meminfo
- * @nid: NUMA node ID of the new memblk
- * @start: Start address of the new memblk
- * @end: End address of the new memblk
- *
- * Add a new memblk to the default numa_meminfo.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init numa_add_memblk(int nid, u64 start, u64 end)
-{
-	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
-}
-
-/* Initialize bootmem allocator for a node */
-void __init
-setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
-{
-	unsigned long start_pfn, last_pfn, nodedata_phys;
-	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 "Initmem setup node %d %016lx-%016lx\n", nodeid,
-	       start, end);
-
-	start_pfn = start >> PAGE_SHIFT;
-	last_pfn = end >> PAGE_SHIFT;
-
-	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size,
-					   SMP_CACHE_BYTES);
-	if (node_data[nodeid] == NULL)
-		return;
-	nodedata_phys = __pa(node_data[nodeid]);
-	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
-	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
-		nodedata_phys + pgdat_size - 1);
-	nid = phys_to_nid(nodedata_phys);
-	if (nid != nodeid)
-		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
-
-	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-	NODE_DATA(nodeid)->node_id = nodeid;
-	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
-	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
-
-	node_set_online(nodeid);
-}
-
-/**
- * numa_cleanup_meminfo - Cleanup a numa_meminfo
- * @mi: numa_meminfo to clean up
- *
- * Sanitize @mi by merging and removing unncessary memblks.  Also check for
- * conflicts and clear unused memblks.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
-{
-	const u64 low = 0;
-	const u64 high = (u64)max_pfn << PAGE_SHIFT;
-	int i, j, k;
-
-	for (i = 0; i < mi->nr_blks; i++) {
-		struct numa_memblk *bi = &mi->blk[i];
-
-		/* make sure all blocks are inside the limits */
-		bi->start = max(bi->start, low);
-		bi->end = min(bi->end, high);
-
-		/* and there's no empty block */
-		if (bi->start >= bi->end) {
-			numa_remove_memblk_from(i--, mi);
-			continue;
-		}
-
-		for (j = i + 1; j < mi->nr_blks; j++) {
-			struct numa_memblk *bj = &mi->blk[j];
-			unsigned long start, end;
-
-			/*
-			 * See whether there are overlapping blocks.  Whine
-			 * about but allow overlaps of the same nid.  They
-			 * will be merged below.
-			 */
-			if (bi->end > bj->start && bi->start < bj->end) {
-				if (bi->nid != bj->nid) {
-					pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
-					       bi->nid, bi->start, bi->end,
-					       bj->nid, bj->start, bj->end);
-					return -EINVAL;
-				}
-				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
-					   bi->nid, bi->start, bi->end,
-					   bj->start, bj->end);
-			}
-
-			/*
-			 * Join together blocks on the same node, holes
-			 * between which don't overlap with memory on other
-			 * nodes.
-			 */
-			if (bi->nid != bj->nid)
-				continue;
-			start = max(min(bi->start, bj->start), low);
-			end = min(max(bi->end, bj->end), high);
-			for (k = 0; k < mi->nr_blks; k++) {
-				struct numa_memblk *bk = &mi->blk[k];
-
-				if (bi->nid == bk->nid)
-					continue;
-				if (start < bk->end && end > bk->start)
-					break;
-			}
-			if (k < mi->nr_blks)
-				continue;
-			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
-			       bi->nid, bi->start, bi->end, bj->start, bj->end,
-			       start, end);
-			bi->start = start;
-			bi->end = end;
-			numa_remove_memblk_from(j--, mi);
-		}
-	}
-
-	for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
-		mi->blk[i].start = mi->blk[i].end = 0;
-		mi->blk[i].nid = NUMA_NO_NODE;
-	}
-
-	return 0;
-}
-
-/*
- * Set nodes, which have memory in @mi, in *@nodemask.
- */
-static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
-					      const struct numa_meminfo *mi)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
-		if (mi->blk[i].start != mi->blk[i].end &&
-		    mi->blk[i].nid != NUMA_NO_NODE)
-			node_set(mi->blk[i].nid, *nodemask);
-}
-
-/**
- * numa_reset_distance - Reset NUMA distance table
- *
- * The current table is freed.  The next numa_set_distance() call will
- * create a new one.
- */
-void __init numa_reset_distance(void)
-{
-	size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
-
-	/* numa_distance could be 1LU marking allocation failure, test cnt */
-	if (numa_distance_cnt)
-		memblock_x86_free_range(__pa(numa_distance),
-					__pa(numa_distance) + size);
-	numa_distance_cnt = 0;
-	numa_distance = NULL;	/* enable table creation */
-}
-
-static int __init numa_alloc_distance(void)
-{
-	nodemask_t nodes_parsed;
-	size_t size;
-	int i, j, cnt = 0;
-	u64 phys;
-
-	/* size the new table and allocate it */
-	nodes_parsed = numa_nodes_parsed;
-	numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
-
-	for_each_node_mask(i, nodes_parsed)
-		cnt = i;
-	cnt++;
-	size = cnt * cnt * sizeof(numa_distance[0]);
-
-	phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT,
-				      size, PAGE_SIZE);
-	if (phys == MEMBLOCK_ERROR) {
-		pr_warning("NUMA: Warning: can't allocate distance table!\n");
-		/* don't retry until explicitly reset */
-		numa_distance = (void *)1LU;
-		return -ENOMEM;
-	}
-	memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
-
-	numa_distance = __va(phys);
-	numa_distance_cnt = cnt;
-
-	/* fill with the default distances */
-	for (i = 0; i < cnt; i++)
-		for (j = 0; j < cnt; j++)
-			numa_distance[i * cnt + j] = i == j ?
-				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
-
-	return 0;
-}
-
-/**
- * numa_set_distance - Set NUMA distance from one NUMA to another
- * @from: the 'from' node to set distance
- * @to: the 'to'  node to set distance
- * @distance: NUMA distance
- *
- * Set the distance from node @from to @to to @distance.  If distance table
- * doesn't exist, one which is large enough to accommodate all the currently
- * known nodes will be created.
- *
- * If such table cannot be allocated, a warning is printed and further
- * calls are ignored until the distance table is reset with
- * numa_reset_distance().
- *
- * If @from or @to is higher than the highest known node at the time of
- * table creation or @distance doesn't make sense, the call is ignored.
- * This is to allow simplification of specific NUMA config implementations.
- */
-void __init numa_set_distance(int from, int to, int distance)
-{
-	if (!numa_distance && numa_alloc_distance() < 0)
-		return;
-
-	if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
-		printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
-			    from, to, distance);
-		return;
-	}
-
-	if ((u8)distance != distance ||
-	    (from == to && distance != LOCAL_DISTANCE)) {
-		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
-			     from, to, distance);
-		return;
-	}
-
-	numa_distance[from * numa_distance_cnt + to] = distance;
-}
-
-int __node_distance(int from, int to)
-{
-	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
-		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
-	return numa_distance[from * numa_distance_cnt + to];
-}
-EXPORT_SYMBOL(__node_distance);
-
-/*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common).  Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
-	unsigned long numaram, e820ram;
-	int i;
-
-	numaram = 0;
-	for (i = 0; i < mi->nr_blks; i++) {
-		unsigned long s = mi->blk[i].start >> PAGE_SHIFT;
-		unsigned long e = mi->blk[i].end >> PAGE_SHIFT;
-		numaram += e - s;
-		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
-		if ((long)numaram < 0)
-			numaram = 0;
-	}
-
-	e820ram = max_pfn - (memblock_x86_hole_size(0,
-					max_pfn << PAGE_SHIFT) >> PAGE_SHIFT);
-	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
-	if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
-		printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n",
-		       (numaram << PAGE_SHIFT) >> 20,
-		       (e820ram << PAGE_SHIFT) >> 20);
-		return false;
-	}
-	return true;
-}
-
-static int __init numa_register_memblks(struct numa_meminfo *mi)
-{
-	int i, nid;
-
-	/* Account for nodes with cpus and no memory */
-	node_possible_map = numa_nodes_parsed;
-	numa_nodemask_from_meminfo(&node_possible_map, mi);
-	if (WARN_ON(nodes_empty(node_possible_map)))
-		return -EINVAL;
-
-	memnode_shift = compute_hash_shift(mi);
-	if (memnode_shift < 0) {
-		printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < mi->nr_blks; i++)
-		memblock_x86_register_active_regions(mi->blk[i].nid,
-					mi->blk[i].start >> PAGE_SHIFT,
-					mi->blk[i].end >> PAGE_SHIFT);
-
-	/* for out of order entries */
-	sort_node_map();
-	if (!numa_meminfo_cover_memory(mi))
-		return -EINVAL;
-
-	/* Finally register nodes. */
-	for_each_node_mask(nid, node_possible_map) {
-		u64 start = (u64)max_pfn << PAGE_SHIFT;
-		u64 end = 0;
-
-		for (i = 0; i < mi->nr_blks; i++) {
-			if (nid != mi->blk[i].nid)
-				continue;
-			start = min(mi->blk[i].start, start);
-			end = max(mi->blk[i].end, end);
-		}
-
-		if (start < end)
-			setup_node_bootmem(nid, start, end);
-	}
-
-	return 0;
-}
-
-/**
- * dummy_numma_init - Fallback dummy NUMA init
- *
- * Used if there's no underlying NUMA architecture, NUMA initialization
- * fails, or NUMA is disabled on the command line.
- *
- * Must online at least one node and add memory blocks that cover all
- * allowed memory.  This function must not fail.
- */
-static int __init dummy_numa_init(void)
-{
-	printk(KERN_INFO "%s\n",
-	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
-	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
-	       0LU, max_pfn << PAGE_SHIFT);
-
-	node_set(0, numa_nodes_parsed);
-	numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT);
-
-	return 0;
-}
-
-static int __init numa_init(int (*init_func)(void))
-{
-	int i;
-	int ret;
-
-	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		set_apicid_to_node(i, NUMA_NO_NODE);
-
-	nodes_clear(numa_nodes_parsed);
-	nodes_clear(node_possible_map);
-	nodes_clear(node_online_map);
-	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-	remove_all_active_ranges();
-	numa_reset_distance();
-
-	ret = init_func();
-	if (ret < 0)
-		return ret;
-	ret = numa_cleanup_meminfo(&numa_meminfo);
-	if (ret < 0)
-		return ret;
-
-	numa_emulation(&numa_meminfo, numa_distance_cnt);
-
-	ret = numa_register_memblks(&numa_meminfo);
-	if (ret < 0)
-		return ret;
-
-	for (i = 0; i < nr_cpu_ids; i++) {
-		int nid = early_cpu_to_node(i);
-
-		if (nid == NUMA_NO_NODE)
-			continue;
-		if (!node_online(nid))
-			numa_clear_node(i);
-	}
-	numa_init_array();
-	return 0;
-}
-
 void __init initmem_init(void)
 {
-	int ret;
-
-	if (!numa_off) {
-#ifdef CONFIG_ACPI_NUMA
-		ret = numa_init(x86_acpi_numa_init);
-		if (!ret)
-			return;
-#endif
-#ifdef CONFIG_AMD_NUMA
-		ret = numa_init(amd_numa_init);
-		if (!ret)
-			return;
-#endif
-	}
-
-	numa_init(dummy_numa_init);
+	x86_numa_init();
 }
 
 unsigned long __init numa_free_all_bootmem(void)
@@ -656,12 +23,3 @@ unsigned long __init numa_free_all_bootmem(void)
 
 	return pages;
 }
-
-int __cpuinit numa_cpu_node(int cpu)
-{
-	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-
-	if (apicid != BAD_APICID)
-		return __apicid_to_node[apicid];
-	return NUMA_NO_NODE;
-}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index de84cc14037..d0ed086b624 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 #include <linux/topology.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 #include <asm/dma.h>
 
 #include "numa_internal.h"
@@ -84,7 +85,13 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
+	/*
+	 * Calculate target node size.  x86_32 freaks on __udivdi3() so do
+	 * the division in ulong number of pages and convert back.
+	 */
+	size = max_addr - addr - memblock_x86_hole_size(addr, max_addr);
+	size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
+
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -226,7 +233,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 	 */
 	while (nodes_weight(physnode_mask)) {
 		for_each_node_mask(i, physnode_mask) {
-			u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
 			u64 start, limit, end;
 			int phys_blk;
 
@@ -298,7 +305,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 {
 	static struct numa_meminfo ei __initdata;
 	static struct numa_meminfo pi __initdata;
-	const u64 max_addr = max_pfn << PAGE_SHIFT;
+	const u64 max_addr = PFN_PHYS(max_pfn);
 	u8 *phys_dist = NULL;
 	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
 	int max_emu_nid, dfl_phys_nid;
@@ -342,8 +349,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	if (numa_dist_cnt) {
 		u64 phys;
 
-		phys = memblock_find_in_range(0,
-					      (u64)max_pfn_mapped << PAGE_SHIFT,
+		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
 		if (phys == MEMBLOCK_ERROR) {
 			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index ef2d97377d7..7178c3afe05 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -19,6 +19,14 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
 int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
 void __init numa_reset_distance(void);
 
+void __init x86_numa_init(void);
+
+#ifdef CONFIG_X86_64
+static inline void init_alloc_remap(int nid, u64 start, u64 end)	{ }
+#else
+void __init init_alloc_remap(int nid, u64 start, u64 end);
+#endif
+
 #ifdef CONFIG_NUMA_EMU
 void __init numa_emulation(struct numa_meminfo *numa_meminfo,
 			   int numa_dist_cnt);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat.c
index 8e9d3394f6d..81dbfdeb080 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat.c
@@ -26,8 +26,6 @@
 
 int acpi_numa __initdata;
 
-static struct bootnode nodes_add[MAX_NUMNODES];
-
 static __init int setup_node(int pxm)
 {
 	return acpi_map_pxm_to_node(pxm);
@@ -37,7 +35,6 @@ static __init void bad_srat(void)
 {
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
-	memset(nodes_add, 0, sizeof(nodes_add));
 }
 
 static __init inline int srat_disabled(void)
@@ -131,73 +128,17 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	       pxm, apic_id, node);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 static inline int save_add_info(void) {return 1;}
 #else
 static inline int save_add_info(void) {return 0;}
 #endif
-/*
- * Update nodes_add[]
- * This code supports one contiguous hot add area per node
- */
-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 changed = 0;
-	struct bootnode *nd = &nodes_add[node];
-
-	/* I had some trouble with strange memory hotadd regions breaking
-	   the boot. Be very strict here and reject anything unexpected.
-	   If you want working memory hotadd write correct SRATs.
-
-	   The node size check is a basic sanity check to guard against
-	   mistakes */
-	if ((signed long)(end - start) < NODE_MIN_SIZE) {
-		printk(KERN_ERR "SRAT: Hotplug area too small\n");
-		return;
-	}
-
-	/* This check might be a bit too strict, but I'm keeping it for now. */
-	if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) {
-		printk(KERN_ERR
-			"SRAT: Hotplug area %lu -> %lu has existing memory\n",
-			s_pfn, e_pfn);
-		return;
-	}
-
-	/* Looks good */
-
-	if (nd->start == nd->end) {
-		nd->start = start;
-		nd->end = end;
-		changed = 1;
-	} else {
-		if (nd->start == end) {
-			nd->start = start;
-			changed = 1;
-		}
-		if (nd->end == start) {
-			nd->end = end;
-			changed = 1;
-		}
-		if (!changed)
-			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
-	}
-
-	if (changed) {
-		node_set(node, numa_nodes_parsed);
-		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 */
 void __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
-	unsigned long start, end;
+	u64 start, end;
 	int node, pxm;
 
 	if (srat_disabled())
@@ -226,11 +167,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		return;
 	}
 
-	printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm,
+	printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
 	       start, end);
-
-	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)
-		update_nodes_add(node, start, end);
 }
 
 void __init acpi_numa_arch_fixup(void) {}
@@ -244,17 +182,3 @@ int __init x86_acpi_numa_init(void)
 		return ret;
 	return srat_disabled() ? -EINVAL : 0;
 }
-
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY)
-int memory_add_physaddr_to_nid(u64 start)
-{
-	int i, ret = 0;
-
-	for_each_node(i)
-		if (nodes_add[i].start <= start && nodes_add[i].end > start)
-			ret = i;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
deleted file mode 100644
index 364f36bdfad..00000000000
--- a/arch/x86/mm/srat_32.c
+++ /dev/null
@@ -1,288 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit 
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * 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 as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-#include <linux/mm.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/mmzone.h>
-#include <linux/acpi.h>
-#include <linux/nodemask.h>
-#include <asm/srat.h>
-#include <asm/topology.h>
-#include <asm/smp.h>
-#include <asm/e820.h>
-
-/*
- * proximity macros and definitions
- */
-#define NODE_ARRAY_INDEX(x)	((x) / 8)	/* 8 bits/char */
-#define NODE_ARRAY_OFFSET(x)	((x) % 8)	/* 8 bits/char */
-#define BMAP_SET(bmap, bit)	((bmap)[NODE_ARRAY_INDEX(bit)] |= 1 << NODE_ARRAY_OFFSET(bit))
-#define BMAP_TEST(bmap, bit)	((bmap)[NODE_ARRAY_INDEX(bit)] & (1 << NODE_ARRAY_OFFSET(bit)))
-/* bitmap length; _PXM is at most 255 */
-#define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8) 
-static u8 __initdata pxm_bitmap[PXM_BITMAP_LEN];	/* bitmap of proximity domains */
-
-#define MAX_CHUNKS_PER_NODE	3
-#define MAXCHUNKS		(MAX_CHUNKS_PER_NODE * MAX_NUMNODES)
-struct node_memory_chunk_s {
-	unsigned long	start_pfn;
-	unsigned long	end_pfn;
-	u8	pxm;		// proximity domain of node
-	u8	nid;		// which cnode contains this chunk?
-	u8	bank;		// which mem bank on this node
-};
-static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS];
-
-static int __initdata num_memory_chunks; /* total number of memory chunks */
-static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC];
-
-int acpi_numa __initdata;
-
-static __init void bad_srat(void)
-{
-        printk(KERN_ERR "SRAT: SRAT not used.\n");
-        acpi_numa = -1;
-	num_memory_chunks = 0;
-}
-
-static __init inline int srat_disabled(void)
-{
-	return numa_off || acpi_numa < 0;
-}
-
-/* Identify CPU proximity domains */
-void __init
-acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity)
-{
-	if (srat_disabled())
-		return;
-	if (cpu_affinity->header.length !=
-	     sizeof(struct acpi_srat_cpu_affinity)) {
-		bad_srat();
-		return;
-	}
-
-	if ((cpu_affinity->flags & ACPI_SRAT_CPU_ENABLED) == 0)
-		return;		/* empty entry */
-
-	/* mark this node as "seen" in node bitmap */
-	BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo);
-
-	/* don't need to check apic_id here, because it is always 8 bits */
-	apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo;
-
-	printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n",
-		cpu_affinity->apic_id, cpu_affinity->proximity_domain_lo);
-}
-
-/*
- * Identify memory proximity domains and hot-remove capabilities.
- * Fill node memory chunk list structure.
- */
-void __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *memory_affinity)
-{
-	unsigned long long paddr, size;
-	unsigned long start_pfn, end_pfn;
-	u8 pxm;
-	struct node_memory_chunk_s *p, *q, *pend;
-
-	if (srat_disabled())
-		return;
-	if (memory_affinity->header.length !=
-	     sizeof(struct acpi_srat_mem_affinity)) {
-		bad_srat();
-		return;
-	}
-
-	if ((memory_affinity->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-		return;		/* empty entry */
-
-	pxm = memory_affinity->proximity_domain & 0xff;
-
-	/* mark this node as "seen" in node bitmap */
-	BMAP_SET(pxm_bitmap, pxm);
-
-	/* calculate info for memory chunk structure */
-	paddr = memory_affinity->base_address;
-	size = memory_affinity->length;
-
-	start_pfn = paddr >> PAGE_SHIFT;
-	end_pfn = (paddr + size) >> PAGE_SHIFT;
-
-
-	if (num_memory_chunks >= MAXCHUNKS) {
-		printk(KERN_WARNING "Too many mem chunks in SRAT."
-			" Ignoring %lld MBytes at %llx\n",
-			size/(1024*1024), paddr);
-		return;
-	}
-
-	/* Insertion sort based on base address */
-	pend = &node_memory_chunk[num_memory_chunks];
-	for (p = &node_memory_chunk[0]; p < pend; p++) {
-		if (start_pfn < p->start_pfn)
-			break;
-	}
-	if (p < pend) {
-		for (q = pend; q >= p; q--)
-			*(q + 1) = *q;
-	}
-	p->start_pfn = start_pfn;
-	p->end_pfn = end_pfn;
-	p->pxm = pxm;
-
-	num_memory_chunks++;
-
-	printk(KERN_DEBUG "Memory range %08lx to %08lx"
-			  " in proximity domain %02x %s\n",
-		start_pfn, end_pfn,
-		pxm,
-		((memory_affinity->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
-		 "enabled and removable" : "enabled" ) );
-}
-
-/* Callback for SLIT parsing */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
-}
-
-void acpi_numa_arch_fixup(void)
-{
-}
-/*
- * The SRAT table always lists ascending addresses, so can always
- * assume that the first "start" address that you see is the real
- * start of the node, and that the current "end" address is after
- * the previous one.
- */
-static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
-{
-	/*
-	 * Only add present memory as told by the e820.
-	 * There is no guarantee from the SRAT that the memory it
-	 * enumerates is present at boot time because it represents
-	 * *possible* memory hotplug areas the same as normal RAM.
-	 */
-	if (memory_chunk->start_pfn >= max_pfn) {
-		printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
-			memory_chunk->start_pfn, memory_chunk->end_pfn);
-		return -1;
-	}
-	if (memory_chunk->nid != nid)
-		return -1;
-
-	if (!node_has_online_mem(nid))
-		node_start_pfn[nid] = memory_chunk->start_pfn;
-
-	if (node_start_pfn[nid] > memory_chunk->start_pfn)
-		node_start_pfn[nid] = memory_chunk->start_pfn;
-
-	if (node_end_pfn[nid] < memory_chunk->end_pfn)
-		node_end_pfn[nid] = memory_chunk->end_pfn;
-
-	return 0;
-}
-
-int __init get_memcfg_from_srat(void)
-{
-	int i, j, nid;
-
-	if (srat_disabled())
-		goto out_fail;
-
-	if (acpi_numa_init() < 0)
-		goto out_fail;
-
-	if (num_memory_chunks == 0) {
-		printk(KERN_DEBUG
-			 "could not find any ACPI SRAT memory areas.\n");
-		goto out_fail;
-	}
-
-	/* Calculate total number of nodes in system from PXM bitmap and create
-	 * a set of sequential node IDs starting at zero.  (ACPI doesn't seem
-	 * to specify the range of _PXM values.)
-	 */
-	/*
-	 * MCD - we no longer HAVE to number nodes sequentially.  PXM domain
-	 * numbers could go as high as 256, and MAX_NUMNODES for i386 is typically
-	 * 32, so we will continue numbering them in this manner until MAX_NUMNODES
-	 * approaches MAX_PXM_DOMAINS for i386.
-	 */
-	nodes_clear(node_online_map);
-	for (i = 0; i < MAX_PXM_DOMAINS; i++) {
-		if (BMAP_TEST(pxm_bitmap, i)) {
-			int nid = acpi_map_pxm_to_node(i);
-			node_set_online(nid);
-		}
-	}
-	BUG_ON(num_online_nodes() == 0);
-
-	/* set cnode id in memory chunk structure */
-	for (i = 0; i < num_memory_chunks; i++)
-		node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm);
-
-	printk(KERN_DEBUG "pxm bitmap: ");
-	for (i = 0; i < sizeof(pxm_bitmap); i++) {
-		printk(KERN_CONT "%02x ", pxm_bitmap[i]);
-	}
-	printk(KERN_CONT "\n");
-	printk(KERN_DEBUG "Number of logical nodes in system = %d\n",
-			 num_online_nodes());
-	printk(KERN_DEBUG "Number of memory chunks in system = %d\n",
-			 num_memory_chunks);
-
-	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
-
-	for (j = 0; j < num_memory_chunks; j++){
-		struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
-		printk(KERN_DEBUG
-			"chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
-		       j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
-		if (node_read_chunk(chunk->nid, chunk))
-			continue;
-
-		memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
-					     min(chunk->end_pfn, max_pfn));
-	}
-	/* for out of order entries in SRAT */
-	sort_node_map();
-
-	for_each_online_node(nid) {
-		unsigned long start = node_start_pfn[nid];
-		unsigned long end = min(node_end_pfn[nid], max_pfn);
-
-		memory_present(nid, start, end);
-		node_remap_size[nid] = node_memmap_size_bytes(nid, start, end);
-	}
-	return 1;
-out_fail:
-	printk(KERN_DEBUG "failed to get NUMA memory information from SRAT"
-			" table\n");
-	return 0;
-}
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 2d49d4e19a3..a5b64ab4cd6 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -16,17 +16,6 @@
 #include <asm/stacktrace.h>
 #include <linux/compat.h>
 
-static void backtrace_warning_symbol(void *data, char *msg,
-				     unsigned long symbol)
-{
-	/* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
-	/* Ignore warnings */
-}
-
 static int backtrace_stack(void *data, char *name)
 {
 	/* Yes, we want all stacks */
@@ -42,8 +31,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 }
 
 static struct stacktrace_ops backtrace_ops = {
-	.warning	= backtrace_warning,
-	.warning_symbol	= backtrace_warning_symbol,
 	.stack		= backtrace_stack,
 	.address	= backtrace_address,
 	.walk_stack	= print_context_stack,
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e37b407a0ee..8214724ce54 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -108,7 +108,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		}
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
 					       (type == PCI_CAP_ID_MSIX) ?
-					       "msi-x" : "msi");
+					       "msi-x" : "msi",
+					       DOMID_SELF);
 		if (irq < 0)
 			goto error;
 		dev_dbg(&dev->dev,
@@ -148,7 +149,8 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
 					       (type == PCI_CAP_ID_MSIX) ?
 					       "pcifront-msi-x" :
-					       "pcifront-msi");
+					       "pcifront-msi",
+						DOMID_SELF);
 		if (irq < 0)
 			goto free;
 		i++;
@@ -190,9 +192,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 		struct physdev_map_pirq map_irq;
+		domid_t domid;
+
+		domid = ret = xen_find_device_domain_owner(dev);
+		/* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED,
+		 * hence check ret value for < 0. */
+		if (ret < 0)
+			domid = DOMID_SELF;
 
 		memset(&map_irq, 0, sizeof(map_irq));
-		map_irq.domid = DOMID_SELF;
+		map_irq.domid = domid;
 		map_irq.type = MAP_PIRQ_TYPE_MSI;
 		map_irq.index = -1;
 		map_irq.pirq = -1;
@@ -215,14 +224,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 		ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
 		if (ret) {
-			dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+			dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n",
+				 ret, domid);
 			goto out;
 		}
 
 		ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
 					       map_irq.pirq, map_irq.index,
 					       (type == PCI_CAP_ID_MSIX) ?
-					       "msi-x" : "msi");
+					       "msi-x" : "msi",
+						domid);
 		if (ret < 0)
 			goto out;
 	}
@@ -461,3 +472,78 @@ void __init xen_setup_pirqs(void)
 	}
 }
 #endif
+
+#ifdef CONFIG_XEN_DOM0
+struct xen_device_domain_owner {
+	domid_t domain;
+	struct pci_dev *dev;
+	struct list_head list;
+};
+
+static DEFINE_SPINLOCK(dev_domain_list_spinlock);
+static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
+
+static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
+{
+	struct xen_device_domain_owner *owner;
+
+	list_for_each_entry(owner, &dev_domain_list, list) {
+		if (owner->dev == dev)
+			return owner;
+	}
+	return NULL;
+}
+
+int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+	struct xen_device_domain_owner *owner;
+	int domain = -ENODEV;
+
+	spin_lock(&dev_domain_list_spinlock);
+	owner = find_device(dev);
+	if (owner)
+		domain = owner->domain;
+	spin_unlock(&dev_domain_list_spinlock);
+	return domain;
+}
+EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
+
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
+{
+	struct xen_device_domain_owner *owner;
+
+	owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
+	if (!owner)
+		return -ENODEV;
+
+	spin_lock(&dev_domain_list_spinlock);
+	if (find_device(dev)) {
+		spin_unlock(&dev_domain_list_spinlock);
+		kfree(owner);
+		return -EEXIST;
+	}
+	owner->domain = domain;
+	owner->dev = dev;
+	list_add_tail(&owner->list, &dev_domain_list);
+	spin_unlock(&dev_domain_list_spinlock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
+
+int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+	struct xen_device_domain_owner *owner;
+
+	spin_lock(&dev_domain_list_spinlock);
+	owner = find_device(dev);
+	if (!owner) {
+		spin_unlock(&dev_domain_list_spinlock);
+		return -ENODEV;
+	}
+	list_del(&owner->list);
+	spin_unlock(&dev_domain_list_spinlock);
+	kfree(owner);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
+#endif
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0fe27d7c625..b30aa26a8df 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -145,17 +145,6 @@ static void virt_efi_reset_system(int reset_type,
 		       data_size, data);
 }
 
-static efi_status_t virt_efi_set_virtual_address_map(
-	unsigned long memory_map_size,
-	unsigned long descriptor_size,
-	u32 descriptor_version,
-	efi_memory_desc_t *virtual_map)
-{
-	return efi_call_virt4(set_virtual_address_map,
-			      memory_map_size, descriptor_size,
-			      descriptor_version, virtual_map);
-}
-
 static efi_status_t __init phys_efi_set_virtual_address_map(
 	unsigned long memory_map_size,
 	unsigned long descriptor_size,
@@ -468,11 +457,25 @@ void __init efi_init(void)
 #endif
 }
 
+void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
+{
+	u64 addr, npages;
+
+	addr = md->virt_addr;
+	npages = md->num_pages;
+
+	memrange_efi_to_native(&addr, &npages);
+
+	if (executable)
+		set_memory_x(addr, npages);
+	else
+		set_memory_nx(addr, npages);
+}
+
 static void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
 	void *p;
-	u64 addr, npages;
 
 	/* Make EFI runtime service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -481,10 +484,7 @@ static void __init runtime_code_page_mkexec(void)
 		if (md->type != EFI_RUNTIME_SERVICES_CODE)
 			continue;
 
-		addr = md->virt_addr;
-		npages = md->num_pages;
-		memrange_efi_to_native(&addr, &npages);
-		set_memory_x(addr, npages);
+		efi_set_executable(md, true);
 	}
 }
 
@@ -498,13 +498,42 @@ static void __init runtime_code_page_mkexec(void)
  */
 void __init efi_enter_virtual_mode(void)
 {
-	efi_memory_desc_t *md;
+	efi_memory_desc_t *md, *prev_md = NULL;
 	efi_status_t status;
 	unsigned long size;
 	u64 end, systab, addr, npages, end_pfn;
-	void *p, *va;
+	void *p, *va, *new_memmap = NULL;
+	int count = 0;
 
 	efi.systab = NULL;
+
+	/* Merge contiguous regions of the same type and attribute */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		u64 prev_size;
+		md = p;
+
+		if (!prev_md) {
+			prev_md = md;
+			continue;
+		}
+
+		if (prev_md->type != md->type ||
+		    prev_md->attribute != md->attribute) {
+			prev_md = md;
+			continue;
+		}
+
+		prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
+			prev_md->num_pages += md->num_pages;
+			md->type = EFI_RESERVED_TYPE;
+			md->attribute = 0;
+			continue;
+		}
+		prev_md = md;
+	}
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -541,15 +570,21 @@ void __init efi_enter_virtual_mode(void)
 			systab += md->virt_addr - md->phys_addr;
 			efi.systab = (efi_system_table_t *) (unsigned long) systab;
 		}
+		new_memmap = krealloc(new_memmap,
+				      (count + 1) * memmap.desc_size,
+				      GFP_KERNEL);
+		memcpy(new_memmap + (count * memmap.desc_size), md,
+		       memmap.desc_size);
+		count++;
 	}
 
 	BUG_ON(!efi.systab);
 
 	status = phys_efi_set_virtual_address_map(
-		memmap.desc_size * memmap.nr_map,
+		memmap.desc_size * count,
 		memmap.desc_size,
 		memmap.desc_version,
-		memmap.phys_map);
+		(efi_memory_desc_t *)__pa(new_memmap));
 
 	if (status != EFI_SUCCESS) {
 		printk(KERN_ALERT "Unable to switch EFI into virtual mode "
@@ -572,11 +607,12 @@ void __init efi_enter_virtual_mode(void)
 	efi.set_variable = virt_efi_set_variable;
 	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
 	efi.reset_system = virt_efi_reset_system;
-	efi.set_virtual_address_map = virt_efi_set_virtual_address_map;
+	efi.set_virtual_address_map = NULL;
 	if (__supported_pte_mask & _PAGE_NX)
 		runtime_code_page_mkexec();
 	early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 	memmap.map = NULL;
+	kfree(new_memmap);
 }
 
 /*
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac0621a7ac3..2649426a790 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -41,22 +41,7 @@
 static pgd_t save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
-static void __init early_mapping_set_exec(unsigned long start,
-					  unsigned long end,
-					  int executable)
-{
-	unsigned long num_pages;
-
-	start &= PMD_MASK;
-	end = (end + PMD_SIZE - 1) & PMD_MASK;
-	num_pages = (end - start) >> PAGE_SHIFT;
-	if (executable)
-		set_memory_x((unsigned long)__va(start), num_pages);
-	else
-		set_memory_nx((unsigned long)__va(start), num_pages);
-}
-
-static void __init early_runtime_code_mapping_set_exec(int executable)
+static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
 	void *p;
@@ -67,11 +52,8 @@ static void __init early_runtime_code_mapping_set_exec(int executable)
 	/* Make EFI runtime service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (md->type == EFI_RUNTIME_SERVICES_CODE) {
-			unsigned long end;
-			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
-			early_mapping_set_exec(md->phys_addr, end, executable);
-		}
+		if (md->type == EFI_RUNTIME_SERVICES_CODE)
+			efi_set_executable(md, executable);
 	}
 }
 
@@ -79,7 +61,7 @@ void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
 
-	early_runtime_code_mapping_set_exec(1);
+	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
 	vaddress = (unsigned long)__va(0x0UL);
 	save_pgd = *pgd_offset_k(0x0UL);
@@ -95,7 +77,7 @@ void __init efi_call_phys_epilog(void)
 	set_pgd(pgd_offset_k(0x0UL), save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
-	early_runtime_code_mapping_set_exec(0);
+	early_code_mapping_set_exec(0);
 }
 
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
@@ -107,8 +89,10 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 		return ioremap(phys_addr, size);
 
 	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
-	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
-		return NULL;
+	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+		unsigned long top = last_map_pfn << PAGE_SHIFT;
+		efi_ioremap(top, size - (top - phys_addr), type);
+	}
 
 	return (void __iomem *)__va(phys_addr);
 }
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 275dbc19e2c..7000e74b308 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -194,7 +194,7 @@ static unsigned long __init mrst_calibrate_tsc(void)
 	return 0;
 }
 
-void __init mrst_time_init(void)
+static void __init mrst_time_init(void)
 {
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
 	switch (mrst_timer_options) {
@@ -216,7 +216,7 @@ void __init mrst_time_init(void)
 	apbt_time_init();
 }
 
-void __cpuinit mrst_arch_setup(void)
+static void __cpuinit mrst_arch_setup(void)
 {
 	if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
 		__mrst_cpu_chip = MRST_CPU_CHIP_PENWELL;
diff --git a/arch/x86/platform/olpc/Makefile b/arch/x86/platform/olpc/Makefile
index c2a8cab65e5..81c5e2165c2 100644
--- a/arch/x86/platform/olpc/Makefile
+++ b/arch/x86/platform/olpc/Makefile
@@ -1,4 +1,2 @@
-obj-$(CONFIG_OLPC)		+= olpc.o
+obj-$(CONFIG_OLPC)		+= olpc.o olpc_ofw.o olpc_dt.o
 obj-$(CONFIG_OLPC_XO1)		+= olpc-xo1.o
-obj-$(CONFIG_OLPC)		+= olpc_ofw.o
-obj-$(CONFIG_OF_PROMTREE)	+= olpc_dt.o
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index edaf3fe8dc5..0060fd59ea0 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -18,6 +18,7 @@
 #include <linux/io.h>
 #include <linux/string.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
 
 #include <asm/geode.h>
 #include <asm/setup.h>
@@ -187,41 +188,43 @@ err:
 }
 EXPORT_SYMBOL_GPL(olpc_ec_cmd);
 
-static bool __init check_ofw_architecture(void)
+static bool __init check_ofw_architecture(struct device_node *root)
 {
-	size_t propsize;
-	char olpc_arch[5];
-	const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 };
-	void *res[] = { &propsize };
+	const char *olpc_arch;
+	int propsize;
 
-	if (olpc_ofw("getprop", args, res)) {
-		printk(KERN_ERR "ofw: getprop call failed!\n");
-		return false;
-	}
+	olpc_arch = of_get_property(root, "architecture", &propsize);
 	return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0;
 }
 
-static u32 __init get_board_revision(void)
+static u32 __init get_board_revision(struct device_node *root)
 {
-	size_t propsize;
-	__be32 rev;
-	const void *args[] = { NULL, "board-revision-int", &rev, (void *)4 };
-	void *res[] = { &propsize };
-
-	if (olpc_ofw("getprop", args, res) || propsize != 4) {
-		printk(KERN_ERR "ofw: getprop call failed!\n");
-		return cpu_to_be32(0);
-	}
-	return be32_to_cpu(rev);
+	int propsize;
+	const __be32 *rev;
+
+	rev = of_get_property(root, "board-revision-int", &propsize);
+	if (propsize != 4)
+		return 0;
+
+	return be32_to_cpu(*rev);
 }
 
 static bool __init platform_detect(void)
 {
-	if (!check_ofw_architecture())
+	struct device_node *root = of_find_node_by_path("/");
+	bool success;
+
+	if (!root)
 		return false;
-	olpc_platform_info.flags |= OLPC_F_PRESENT;
-	olpc_platform_info.boardrev = get_board_revision();
-	return true;
+
+	success = check_ofw_architecture(root);
+	if (success) {
+		olpc_platform_info.boardrev = get_board_revision(root);
+		olpc_platform_info.flags |= OLPC_F_PRESENT;
+	}
+
+	of_node_put(root);
+	return success;
 }
 
 static int __init add_xo1_platform_devices(void)
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index 044bda5b317..d39f63d017d 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -19,7 +19,9 @@
 #include <linux/kernel.h>
 #include <linux/bootmem.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/of_pdt.h>
+#include <asm/olpc.h>
 #include <asm/olpc_ofw.h>
 
 static phandle __init olpc_dt_getsibling(phandle node)
@@ -180,3 +182,20 @@ void __init olpc_dt_build_devicetree(void)
 	pr_info("PROM DT: Built device tree with %u bytes of memory.\n",
 			prom_early_allocated);
 }
+
+/* A list of DT node/bus matches that we want to expose as platform devices */
+static struct of_device_id __initdata of_ids[] = {
+	{ .compatible = "olpc,xo1-battery" },
+	{ .compatible = "olpc,xo1-dcon" },
+	{ .compatible = "olpc,xo1-rtc" },
+	{},
+};
+
+static int __init olpc_create_platform_devices(void)
+{
+	if (machine_is_olpc())
+		return of_platform_bus_probe(NULL, of_ids, NULL);
+	else
+		return 0;
+}
+device_initcall(olpc_create_platform_devices);
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 9daf5d1af9f..0eb90184515 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -40,7 +40,6 @@ static struct clocksource clocksource_uv = {
 	.rating		= 400,
 	.read		= uv_read_rtc,
 	.mask		= (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK,
-	.shift		= 10,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -372,14 +371,11 @@ static __init int uv_rtc_setup_clock(void)
 	if (!is_uv_system())
 		return -ENODEV;
 
-	clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
-				clocksource_uv.shift);
-
 	/* If single blade, prefer tsc */
 	if (uv_num_possible_blades() == 1)
 		clocksource_uv.rating = 250;
 
-	rc = clocksource_register(&clocksource_uv);
+	rc = clocksource_register_hz(&clocksource_uv, sn_rtc_cycles_per_second);
 	if (rc)
 		printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc);
 	else
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e3c6a06cf72..dd7b88f2ec7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -235,7 +235,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 	*dx &= maskedx;
 }
 
-static __init void xen_init_cpuid_mask(void)
+static void __init xen_init_cpuid_mask(void)
 {
 	unsigned int ax, bx, cx, dx;
 	unsigned int xsave_mask;
@@ -400,7 +400,7 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
 /*
  * load_gdt for early boot, when the gdt is only mapped once
  */
-static __init void xen_load_gdt_boot(const struct desc_ptr *dtr)
+static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
 {
 	unsigned long va = dtr->address;
 	unsigned int size = dtr->size + 1;
@@ -662,7 +662,7 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
  * Version of write_gdt_entry for use at early boot-time needed to
  * update an entry as simply as possible.
  */
-static __init void xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
+static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 					    const void *desc, int type)
 {
 	switch (type) {
@@ -933,18 +933,18 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 	return ret;
 }
 
-static const struct pv_info xen_info __initdata = {
+static const struct pv_info xen_info __initconst = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
 	.name = "Xen",
 };
 
-static const struct pv_init_ops xen_init_ops __initdata = {
+static const struct pv_init_ops xen_init_ops __initconst = {
 	.patch = xen_patch,
 };
 
-static const struct pv_cpu_ops xen_cpu_ops __initdata = {
+static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.cpuid = xen_cpuid,
 
 	.set_debugreg = xen_set_debugreg,
@@ -1004,7 +1004,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.end_context_switch = xen_end_context_switch,
 };
 
-static const struct pv_apic_ops xen_apic_ops __initdata = {
+static const struct pv_apic_ops xen_apic_ops __initconst = {
 #ifdef CONFIG_X86_LOCAL_APIC
 	.startup_ipi_hook = paravirt_nop,
 #endif
@@ -1055,7 +1055,7 @@ int xen_panic_handler_init(void)
 	return 0;
 }
 
-static const struct machine_ops __initdata xen_machine_ops = {
+static const struct machine_ops xen_machine_ops __initconst = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,
 	.power_off = xen_machine_halt,
@@ -1332,7 +1332,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
+static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
@@ -1381,7 +1381,7 @@ bool xen_hvm_need_lapic(void)
 }
 EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
-const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
 	.name			= "Xen HVM",
 	.detect			= xen_hvm_platform,
 	.init_platform		= xen_hvm_guest_init,
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 6a6fe893964..8bbb465b6f0 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -113,7 +113,7 @@ static void xen_halt(void)
 		xen_safe_halt();
 }
 
-static const struct pv_irq_ops xen_irq_ops __initdata = {
+static const struct pv_irq_ops xen_irq_ops __initconst = {
 	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
 	.restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
 	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0684f3c74d5..02d75246037 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1054,7 +1054,7 @@ void xen_mm_pin_all(void)
  * that's before we have page structures to store the bits.  So do all
  * the book-keeping now.
  */
-static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
+static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 				  enum pt_level level)
 {
 	SetPagePinned(page);
@@ -1187,7 +1187,7 @@ static void drop_other_mm_ref(void *info)
 
 	active_mm = percpu_read(cpu_tlbstate.active_mm);
 
-	if (active_mm == mm)
+	if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
 		leave_mm(smp_processor_id());
 
 	/* If this cpu still has a stale cr3 reference, then make sure
@@ -1271,7 +1271,7 @@ void xen_exit_mmap(struct mm_struct *mm)
 	spin_unlock(&mm->page_table_lock);
 }
 
-static __init void xen_pagetable_setup_start(pgd_t *base)
+static void __init xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
@@ -1291,7 +1291,7 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
 
 static void xen_post_allocator_init(void);
 
-static __init void xen_pagetable_setup_done(pgd_t *base)
+static void __init xen_pagetable_setup_done(pgd_t *base)
 {
 	xen_setup_shared_info();
 	xen_post_allocator_init();
@@ -1488,7 +1488,7 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 }
 
 #ifdef CONFIG_X86_32
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 {
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
@@ -1498,7 +1498,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 	return pte;
 }
 #else /* CONFIG_X86_64 */
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -1519,7 +1519,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
-static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
 	pte = mask_rw_pte(ptep, pte);
 
@@ -1537,7 +1537,7 @@ static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
@@ -1547,7 +1547,7 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 }
 
 /* Used for pmd and pud */
-static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
@@ -1557,13 +1557,13 @@ static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
 
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
-static __init void xen_release_pte_init(unsigned long pfn)
+static void __init xen_release_pte_init(unsigned long pfn)
 {
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
-static __init void xen_release_pmd_init(unsigned long pfn)
+static void __init xen_release_pmd_init(unsigned long pfn)
 {
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
@@ -1689,7 +1689,7 @@ static void set_page_prot(void *addr, pgprot_t prot)
 		BUG();
 }
 
-static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
 	unsigned pmdidx, pteidx;
 	unsigned ident_pte;
@@ -1772,7 +1772,7 @@ static void convert_pfn_mfn(void *v)
  * of the physical mapping once some sort of allocator has been set
  * up.
  */
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pud_t *l3;
@@ -1843,7 +1843,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
 static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
 
-static __init void xen_write_cr3_init(unsigned long cr3)
+static void __init xen_write_cr3_init(unsigned long cr3)
 {
 	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
 
@@ -1880,7 +1880,7 @@ static __init void xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
@@ -1986,7 +1986,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
-__init void xen_ident_map_ISA(void)
+void __init xen_ident_map_ISA(void)
 {
 	unsigned long pa;
 
@@ -2009,7 +2009,7 @@ __init void xen_ident_map_ISA(void)
 	xen_flush_tlb();
 }
 
-static __init void xen_post_allocator_init(void)
+static void __init xen_post_allocator_init(void)
 {
 #ifdef CONFIG_XEN_DEBUG
 	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
@@ -2046,7 +2046,7 @@ static void xen_leave_lazy_mmu(void)
 	preempt_enable();
 }
 
-static const struct pv_mmu_ops xen_mmu_ops __initdata = {
+static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.read_cr2 = xen_read_cr2,
 	.write_cr2 = xen_write_cr2,
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 141eb0de8b0..58efeb9d544 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -522,11 +522,20 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
 	/* Boundary cross-over for the edges: */
 	if (idx) {
 		unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		unsigned long *mid_mfn_p;
 
 		p2m_init(p2m);
 
 		p2m_top[topidx][mididx] = p2m;
 
+		/* For save/restore we need to MFN of the P2M saved */
+		
+		mid_mfn_p = p2m_top_mfn_p[topidx];
+		WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+			"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+			topidx, mididx);
+		mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
 	}
 	return idx != 0;
 }
@@ -549,12 +558,29 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
 	{
 		unsigned topidx = p2m_top_index(pfn);
-		if (p2m_top[topidx] == p2m_mid_missing) {
-			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		unsigned long *mid_mfn_p;
+		unsigned long **mid;
+
+		mid = p2m_top[topidx];
+		mid_mfn_p = p2m_top_mfn_p[topidx];
+		if (mid == p2m_mid_missing) {
+			mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
 			p2m_mid_init(mid);
 
 			p2m_top[topidx] = mid;
+
+			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
+		}
+		/* And the save/restore P2M tables.. */
+		if (mid_mfn_p == p2m_mid_missing_mfn) {
+			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+			p2m_mid_mfn_init(mid_mfn_p);
+
+			p2m_top_mfn_p[topidx] = mid_mfn_p;
+			p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+			/* Note: we don't set mid_mfn_p[midix] here,
+		 	 * look in __early_alloc_p2m */
 		}
 	}
 
@@ -650,7 +676,7 @@ static unsigned long mfn_hash(unsigned long mfn)
 }
 
 /* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page)
+int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 {
 	unsigned long flags;
 	unsigned long pfn;
@@ -662,7 +688,6 @@ int m2p_add_override(unsigned long mfn, struct page *page)
 	if (!PageHighMem(page)) {
 		address = (unsigned long)__va(pfn << PAGE_SHIFT);
 		ptep = lookup_address(address, &level);
-
 		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
@@ -674,18 +699,17 @@ int m2p_add_override(unsigned long mfn, struct page *page)
 	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
 		return -ENOMEM;
 
-	if (!PageHighMem(page))
+	if (clear_pte && !PageHighMem(page))
 		/* Just zap old mapping for now */
 		pte_clear(&init_mm, address, ptep);
-
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
 
 	return 0;
 }
-
-int m2p_remove_override(struct page *page)
+EXPORT_SYMBOL_GPL(m2p_add_override);
+int m2p_remove_override(struct page *page, bool clear_pte)
 {
 	unsigned long flags;
 	unsigned long mfn;
@@ -713,7 +737,7 @@ int m2p_remove_override(struct page *page)
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
 	set_phys_to_machine(pfn, page->index);
 
-	if (!PageHighMem(page))
+	if (clear_pte && !PageHighMem(page))
 		set_pte_at(&init_mm, address, ptep,
 				pfn_pte(pfn, PAGE_KERNEL));
 		/* No tlb flush necessary because the caller already
@@ -721,6 +745,7 @@ int m2p_remove_override(struct page *page)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(m2p_remove_override);
 
 struct page *m2p_find_override(unsigned long mfn)
 {
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 90bac0aac3a..be1a464f6d6 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -50,7 +50,7 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
  */
 #define EXTRA_MEM_RATIO		(10)
 
-static __init void xen_add_extra_mem(unsigned long pages)
+static void __init xen_add_extra_mem(unsigned long pages)
 {
 	unsigned long pfn;
 
@@ -166,7 +166,7 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
 		if (last > end)
 			continue;
 
-		if (entry->type == E820_RAM) {
+		if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) {
 			if (start > start_pci)
 				identity += set_phys_range_identity(
 						PFN_UP(start_pci), PFN_DOWN(start));
@@ -227,7 +227,11 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
+#ifdef CONFIG_X86_32
+	xen_extra_mem_start = mem_end;
+#else
 	xen_extra_mem_start = max((1ULL << 32), mem_end);
+#endif
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;
 
@@ -336,7 +340,7 @@ static void __init fiddle_vdso(void)
 #endif
 }
 
-static __cpuinit int register_callback(unsigned type, const void *func)
+static int __cpuinit register_callback(unsigned type, const void *func)
 {
 	struct callback_register callback = {
 		.type = type,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 30612441ed9..41038c01de4 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -46,18 +46,17 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }
 
-static __cpuinit void cpu_bringup(void)
+static void __cpuinit cpu_bringup(void)
 {
 	int cpu = smp_processor_id();
 
@@ -85,7 +84,7 @@ static __cpuinit void cpu_bringup(void)
 	wmb();			/* make sure everything is out */
 }
 
-static __cpuinit void cpu_bringup_and_idle(void)
+static void __cpuinit cpu_bringup_and_idle(void)
 {
 	cpu_bringup();
 	cpu_idle();
@@ -242,7 +241,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static __cpuinit int
+static int __cpuinit
 cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 {
 	struct vcpu_guest_context *ctxt;
@@ -486,7 +485,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static const struct smp_ops xen_smp_ops __initdata = {
+static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_smp_prepare_cpus,
 	.smp_cpus_done = xen_smp_cpus_done,
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 2e2d370a47b..5158c505bef 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -26,8 +26,6 @@
 
 #include "xen-ops.h"
 
-#define XEN_SHIFT 22
-
 /* Xen may fire a timer up to this many ns early */
 #define TIMER_SLOP	100000
 #define NS_PER_TICK	(1000000000LL / HZ)
@@ -211,8 +209,6 @@ static struct clocksource xen_clocksource __read_mostly = {
 	.rating = 400,
 	.read = xen_clocksource_get_cycles,
 	.mask = ~0,
-	.mult = 1<<XEN_SHIFT,		/* time directly in nanoseconds */
-	.shift = XEN_SHIFT,
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -439,16 +435,16 @@ void xen_timer_resume(void)
 	}
 }
 
-static const struct pv_time_ops xen_time_ops __initdata = {
+static const struct pv_time_ops xen_time_ops __initconst = {
 	.sched_clock = xen_clocksource_read,
 };
 
-static __init void xen_time_init(void)
+static void __init xen_time_init(void)
 {
 	int cpu = smp_processor_id();
 	struct timespec tp;
 
-	clocksource_register(&xen_clocksource);
+	clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
 		/* Successfully turned off 100Hz tick, so we have the
@@ -468,7 +464,7 @@ static __init void xen_time_init(void)
 	xen_setup_cpu_clockevents();
 }
 
-__init void xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
 {
 	pv_time_ops = xen_time_ops;
 
@@ -490,7 +486,7 @@ static void xen_hvm_setup_cpu_clockevents(void)
 	xen_setup_cpu_clockevents();
 }
 
-__init void xen_hvm_init_time_ops(void)
+void __init xen_hvm_init_time_ops(void)
 {
 	/* vector callback is needed otherwise we cannot receive interrupts
 	 * on cpu > 0 and at this point we don't know how many cpus are
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3112f55638c..97dfdc8757b 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -74,7 +74,7 @@ static inline void xen_hvm_smp_init(void) {}
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 void __init xen_init_spinlocks(void);
-__cpuinit void xen_init_lock_cpu(int cpu);
+void __cpuinit xen_init_lock_cpu(int cpu);
 void xen_uninit_lock_cpu(int cpu);
 #else
 static inline void xen_init_spinlocks(void)
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 177c7d15693..557a469c7aa 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -119,4 +119,7 @@ source "drivers/platform/Kconfig"
 source "drivers/clk/Kconfig"
 
 source "drivers/hwspinlock/Kconfig"
+
+source "drivers/clocksource/Kconfig"
+
 endmenu
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 3a73a93596e..85b32376dad 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -49,10 +49,6 @@ ACPI_MODULE_NAME("processor_perflib");
 
 static DEFINE_MUTEX(performance_mutex);
 
-/* Use cpufreq debug layer for _PPC changes. */
-#define cpufreq_printk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \
-						"cpufreq-core", msg)
-
 /*
  * _PPC support is implemented as a CPUfreq policy notifier:
  * This means each time a CPUfreq driver registered also with
@@ -145,7 +141,7 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 		return -ENODEV;
 	}
 
-	cpufreq_printk("CPU %d: _PPC is %d - frequency %s limited\n", pr->id,
+	pr_debug("CPU %d: _PPC is %d - frequency %s limited\n", pr->id,
 		       (int)ppc, ppc ? "" : "not");
 
 	pr->performance_platform_limit = (int)ppc;
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index ad350173956..605a2954ef1 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -710,20 +710,14 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr)
 }
 
 #ifdef CONFIG_X86
-static int acpi_throttling_rdmsr(struct acpi_processor *pr,
-					u64 *value)
+static int acpi_throttling_rdmsr(u64 *value)
 {
-	struct cpuinfo_x86 *c;
 	u64 msr_high, msr_low;
-	unsigned int cpu;
 	u64 msr = 0;
 	int ret = -1;
 
-	cpu = pr->id;
-	c = &cpu_data(cpu);
-
-	if ((c->x86_vendor != X86_VENDOR_INTEL) ||
-		!cpu_has(c, X86_FEATURE_ACPI)) {
+	if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) ||
+		!this_cpu_has(X86_FEATURE_ACPI)) {
 		printk(KERN_ERR PREFIX
 			"HARDWARE addr space,NOT supported yet\n");
 	} else {
@@ -738,18 +732,13 @@ static int acpi_throttling_rdmsr(struct acpi_processor *pr,
 	return ret;
 }
 
-static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
+static int acpi_throttling_wrmsr(u64 value)
 {
-	struct cpuinfo_x86 *c;
-	unsigned int cpu;
 	int ret = -1;
 	u64 msr;
 
-	cpu = pr->id;
-	c = &cpu_data(cpu);
-
-	if ((c->x86_vendor != X86_VENDOR_INTEL) ||
-		!cpu_has(c, X86_FEATURE_ACPI)) {
+	if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) ||
+		!this_cpu_has(X86_FEATURE_ACPI)) {
 		printk(KERN_ERR PREFIX
 			"HARDWARE addr space,NOT supported yet\n");
 	} else {
@@ -761,15 +750,14 @@ static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
 	return ret;
 }
 #else
-static int acpi_throttling_rdmsr(struct acpi_processor *pr,
-				u64 *value)
+static int acpi_throttling_rdmsr(u64 *value)
 {
 	printk(KERN_ERR PREFIX
 		"HARDWARE addr space,NOT supported yet\n");
 	return -1;
 }
 
-static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
+static int acpi_throttling_wrmsr(u64 value)
 {
 	printk(KERN_ERR PREFIX
 		"HARDWARE addr space,NOT supported yet\n");
@@ -801,7 +789,7 @@ static int acpi_read_throttling_status(struct acpi_processor *pr,
 		ret = 0;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
-		ret = acpi_throttling_rdmsr(pr, value);
+		ret = acpi_throttling_rdmsr(value);
 		break;
 	default:
 		printk(KERN_ERR PREFIX "Unknown addr space %d\n",
@@ -834,7 +822,7 @@ static int acpi_write_throttling_state(struct acpi_processor *pr,
 		ret = 0;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
-		ret = acpi_throttling_wrmsr(pr, value);
+		ret = acpi_throttling_wrmsr(value);
 		break;
 	default:
 		printk(KERN_ERR PREFIX "Unknown addr space %d\n",
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index e9e5238f310..d57e8d0fb82 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -168,11 +168,4 @@ config SYS_HYPERVISOR
 	bool
 	default n
 
-config ARCH_NO_SYSDEV_OPS
-	bool
-	---help---
-	  To be selected by architectures that don't use sysdev class or
-	  sysdev driver power management (suspend/resume) and shutdown
-	  operations.
-
 endmenu
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 19f49e41ce5..a34dca0ad04 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -111,8 +111,6 @@ static inline int driver_match_device(struct device_driver *drv,
 	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
 }
 
-extern void sysdev_shutdown(void);
-
 extern char *make_class_name(const char *name, struct kobject *kobj);
 
 extern int devres_release_all(struct device *dev);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 81b78ede37c..bc8729d603a 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -400,7 +400,7 @@ static void device_remove_groups(struct device *dev,
 static int device_add_attrs(struct device *dev)
 {
 	struct class *class = dev->class;
-	struct device_type *type = dev->type;
+	const struct device_type *type = dev->type;
 	int error;
 
 	if (class) {
@@ -440,7 +440,7 @@ static int device_add_attrs(struct device *dev)
 static void device_remove_attrs(struct device *dev)
 {
 	struct class *class = dev->class;
-	struct device_type *type = dev->type;
+	const struct device_type *type = dev->type;
 
 	device_remove_groups(dev, dev->groups);
 
@@ -1314,8 +1314,7 @@ EXPORT_SYMBOL_GPL(put_device);
 EXPORT_SYMBOL_GPL(device_create_file);
 EXPORT_SYMBOL_GPL(device_remove_file);
 
-struct root_device
-{
+struct root_device {
 	struct device dev;
 	struct module *owner;
 };
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index da57ee9d63f..6658da743c3 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -245,6 +245,10 @@ int device_attach(struct device *dev)
 
 	device_lock(dev);
 	if (dev->driver) {
+		if (klist_node_attached(&dev->p->knode_driver)) {
+			ret = 1;
+			goto out_unlock;
+		}
 		ret = device_bind_driver(dev);
 		if (ret == 0)
 			ret = 1;
@@ -257,6 +261,7 @@ int device_attach(struct device *dev)
 		ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
 		pm_runtime_put_sync(dev);
 	}
+out_unlock:
 	device_unlock(dev);
 	return ret;
 }
@@ -316,8 +321,7 @@ static void __device_release_driver(struct device *dev)
 
 	drv = dev->driver;
 	if (drv) {
-		pm_runtime_get_noresume(dev);
-		pm_runtime_barrier(dev);
+		pm_runtime_get_sync(dev);
 
 		driver_sysfs_remove(dev);
 
@@ -326,6 +330,8 @@ static void __device_release_driver(struct device *dev)
 						     BUS_NOTIFY_UNBIND_DRIVER,
 						     dev);
 
+		pm_runtime_put_sync(dev);
+
 		if (dev->bus && dev->bus->remove)
 			dev->bus->remove(dev);
 		else if (drv->remove)
@@ -338,7 +344,6 @@ static void __device_release_driver(struct device *dev)
 						     BUS_NOTIFY_UNBOUND_DRIVER,
 						     dev);
 
-		pm_runtime_put_sync(dev);
 	}
 }
 
@@ -408,17 +413,16 @@ void *dev_get_drvdata(const struct device *dev)
 }
 EXPORT_SYMBOL(dev_get_drvdata);
 
-void dev_set_drvdata(struct device *dev, void *data)
+int dev_set_drvdata(struct device *dev, void *data)
 {
 	int error;
 
-	if (!dev)
-		return;
 	if (!dev->p) {
 		error = device_private_init(dev);
 		if (error)
-			return;
+			return error;
 	}
 	dev->p->driver_data = data;
+	return 0;
 }
 EXPORT_SYMBOL(dev_set_drvdata);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8c798ef7f13..bbb03e6f725 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -521,6 +521,11 @@ static int _request_firmware(const struct firmware **firmware_p,
 	if (!firmware_p)
 		return -EINVAL;
 
+	if (WARN_ON(usermodehelper_is_disabled())) {
+		dev_err(device, "firmware: %s will not be loaded\n", name);
+		return -EBUSY;
+	}
+
 	*firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL);
 	if (!firmware) {
 		dev_err(device, "%s: kmalloc(struct firmware) failed\n",
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 3da6a43b775..0a134a424a3 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -48,7 +48,8 @@ static const char *memory_uevent_name(struct kset *kset, struct kobject *kobj)
 	return MEMORY_CLASS_NAME;
 }
 
-static int memory_uevent(struct kset *kset, struct kobject *obj, struct kobj_uevent_env *env)
+static int memory_uevent(struct kset *kset, struct kobject *obj,
+			struct kobj_uevent_env *env)
 {
 	int retval = 0;
 
@@ -228,10 +229,11 @@ int memory_isolate_notify(unsigned long val, void *v)
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_section_action(unsigned long phys_index, unsigned long action)
+memory_block_action(unsigned long phys_index, unsigned long action)
 {
 	int i;
 	unsigned long start_pfn, start_paddr;
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	struct page *first_page;
 	int ret;
 
@@ -243,7 +245,7 @@ memory_section_action(unsigned long phys_index, unsigned long action)
 	 * that way.
 	 */
 	if (action == MEM_ONLINE) {
-		for (i = 0; i < PAGES_PER_SECTION; i++) {
+		for (i = 0; i < nr_pages; i++) {
 			if (PageReserved(first_page+i))
 				continue;
 
@@ -257,12 +259,12 @@ memory_section_action(unsigned long phys_index, unsigned long action)
 	switch (action) {
 		case MEM_ONLINE:
 			start_pfn = page_to_pfn(first_page);
-			ret = online_pages(start_pfn, PAGES_PER_SECTION);
+			ret = online_pages(start_pfn, nr_pages);
 			break;
 		case MEM_OFFLINE:
 			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
 			ret = remove_memory(start_paddr,
-					    PAGES_PER_SECTION << PAGE_SHIFT);
+					    nr_pages << PAGE_SHIFT);
 			break;
 		default:
 			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
@@ -276,7 +278,7 @@ memory_section_action(unsigned long phys_index, unsigned long action)
 static int memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
-	int i, ret = 0;
+	int ret = 0;
 
 	mutex_lock(&mem->state_mutex);
 
@@ -288,20 +290,11 @@ static int memory_block_change_state(struct memory_block *mem,
 	if (to_state == MEM_OFFLINE)
 		mem->state = MEM_GOING_OFFLINE;
 
-	for (i = 0; i < sections_per_block; i++) {
-		ret = memory_section_action(mem->start_section_nr + i,
-					    to_state);
-		if (ret)
-			break;
-	}
-
-	if (ret) {
-		for (i = 0; i < sections_per_block; i++)
-			memory_section_action(mem->start_section_nr + i,
-					      from_state_req);
+	ret = memory_block_action(mem->start_section_nr, to_state);
 
+	if (ret)
 		mem->state = from_state_req;
-	} else
+	else
 		mem->state = to_state;
 
 out:
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 9e0e4fc24c4..1c291af637b 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -192,18 +192,18 @@ EXPORT_SYMBOL_GPL(platform_device_alloc);
 int platform_device_add_resources(struct platform_device *pdev,
 				  const struct resource *res, unsigned int num)
 {
-	struct resource *r;
+	struct resource *r = NULL;
 
-	if (!res)
-		return 0;
-
-	r = kmemdup(res, sizeof(struct resource) * num, GFP_KERNEL);
-	if (r) {
-		pdev->resource = r;
-		pdev->num_resources = num;
-		return 0;
+	if (res) {
+		r = kmemdup(res, sizeof(struct resource) * num, GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
 	}
-	return -ENOMEM;
+
+	kfree(pdev->resource);
+	pdev->resource = r;
+	pdev->num_resources = num;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(platform_device_add_resources);
 
@@ -220,17 +220,17 @@ EXPORT_SYMBOL_GPL(platform_device_add_resources);
 int platform_device_add_data(struct platform_device *pdev, const void *data,
 			     size_t size)
 {
-	void *d;
+	void *d = NULL;
 
-	if (!data)
-		return 0;
-
-	d = kmemdup(data, size, GFP_KERNEL);
-	if (d) {
-		pdev->dev.platform_data = d;
-		return 0;
+	if (data) {
+		d = kmemdup(data, size, GFP_KERNEL);
+		if (!d)
+			return -ENOMEM;
 	}
-	return -ENOMEM;
+
+	kfree(pdev->dev.platform_data);
+	pdev->dev.platform_data = d;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(platform_device_add_data);
 
@@ -667,7 +667,7 @@ static int platform_legacy_resume(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_prepare(struct device *dev)
+int platform_pm_prepare(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -678,7 +678,7 @@ static int platform_pm_prepare(struct device *dev)
 	return ret;
 }
 
-static void platform_pm_complete(struct device *dev)
+void platform_pm_complete(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 
@@ -686,16 +686,11 @@ static void platform_pm_complete(struct device *dev)
 		drv->pm->complete(dev);
 }
 
-#else /* !CONFIG_PM_SLEEP */
-
-#define platform_pm_prepare		NULL
-#define platform_pm_complete		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
 
-int __weak platform_pm_suspend(struct device *dev)
+int platform_pm_suspend(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -713,7 +708,7 @@ int __weak platform_pm_suspend(struct device *dev)
 	return ret;
 }
 
-int __weak platform_pm_suspend_noirq(struct device *dev)
+int platform_pm_suspend_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -729,7 +724,7 @@ int __weak platform_pm_suspend_noirq(struct device *dev)
 	return ret;
 }
 
-int __weak platform_pm_resume(struct device *dev)
+int platform_pm_resume(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -747,7 +742,7 @@ int __weak platform_pm_resume(struct device *dev)
 	return ret;
 }
 
-int __weak platform_pm_resume_noirq(struct device *dev)
+int platform_pm_resume_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -763,18 +758,11 @@ int __weak platform_pm_resume_noirq(struct device *dev)
 	return ret;
 }
 
-#else /* !CONFIG_SUSPEND */
-
-#define platform_pm_suspend		NULL
-#define platform_pm_resume		NULL
-#define platform_pm_suspend_noirq	NULL
-#define platform_pm_resume_noirq	NULL
-
-#endif /* !CONFIG_SUSPEND */
+#endif /* CONFIG_SUSPEND */
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 
-static int platform_pm_freeze(struct device *dev)
+int platform_pm_freeze(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -792,7 +780,7 @@ static int platform_pm_freeze(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_freeze_noirq(struct device *dev)
+int platform_pm_freeze_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -808,7 +796,7 @@ static int platform_pm_freeze_noirq(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_thaw(struct device *dev)
+int platform_pm_thaw(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -826,7 +814,7 @@ static int platform_pm_thaw(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_thaw_noirq(struct device *dev)
+int platform_pm_thaw_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -842,7 +830,7 @@ static int platform_pm_thaw_noirq(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_poweroff(struct device *dev)
+int platform_pm_poweroff(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -860,7 +848,7 @@ static int platform_pm_poweroff(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_poweroff_noirq(struct device *dev)
+int platform_pm_poweroff_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -876,7 +864,7 @@ static int platform_pm_poweroff_noirq(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_restore(struct device *dev)
+int platform_pm_restore(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -894,7 +882,7 @@ static int platform_pm_restore(struct device *dev)
 	return ret;
 }
 
-static int platform_pm_restore_noirq(struct device *dev)
+int platform_pm_restore_noirq(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
@@ -910,62 +898,13 @@ static int platform_pm_restore_noirq(struct device *dev)
 	return ret;
 }
 
-#else /* !CONFIG_HIBERNATE_CALLBACKS */
-
-#define platform_pm_freeze		NULL
-#define platform_pm_thaw		NULL
-#define platform_pm_poweroff		NULL
-#define platform_pm_restore		NULL
-#define platform_pm_freeze_noirq	NULL
-#define platform_pm_thaw_noirq		NULL
-#define platform_pm_poweroff_noirq	NULL
-#define platform_pm_restore_noirq	NULL
-
-#endif /* !CONFIG_HIBERNATE_CALLBACKS */
-
-#ifdef CONFIG_PM_RUNTIME
-
-int __weak platform_pm_runtime_suspend(struct device *dev)
-{
-	return pm_generic_runtime_suspend(dev);
-};
-
-int __weak platform_pm_runtime_resume(struct device *dev)
-{
-	return pm_generic_runtime_resume(dev);
-};
-
-int __weak platform_pm_runtime_idle(struct device *dev)
-{
-	return pm_generic_runtime_idle(dev);
-};
-
-#else /* !CONFIG_PM_RUNTIME */
-
-#define platform_pm_runtime_suspend NULL
-#define platform_pm_runtime_resume NULL
-#define platform_pm_runtime_idle NULL
-
-#endif /* !CONFIG_PM_RUNTIME */
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
 
 static const struct dev_pm_ops platform_dev_pm_ops = {
-	.prepare = platform_pm_prepare,
-	.complete = platform_pm_complete,
-	.suspend = platform_pm_suspend,
-	.resume = platform_pm_resume,
-	.freeze = platform_pm_freeze,
-	.thaw = platform_pm_thaw,
-	.poweroff = platform_pm_poweroff,
-	.restore = platform_pm_restore,
-	.suspend_noirq = platform_pm_suspend_noirq,
-	.resume_noirq = platform_pm_resume_noirq,
-	.freeze_noirq = platform_pm_freeze_noirq,
-	.thaw_noirq = platform_pm_thaw_noirq,
-	.poweroff_noirq = platform_pm_poweroff_noirq,
-	.restore_noirq = platform_pm_restore_noirq,
-	.runtime_suspend = platform_pm_runtime_suspend,
-	.runtime_resume = platform_pm_runtime_resume,
-	.runtime_idle = platform_pm_runtime_idle,
+	.runtime_suspend = pm_generic_runtime_suspend,
+	.runtime_resume = pm_generic_runtime_resume,
+	.runtime_idle = pm_generic_runtime_idle,
+	USE_PLATFORM_PM_SLEEP_OPS
 };
 
 struct bus_type platform_bus_type = {
@@ -977,41 +916,6 @@ struct bus_type platform_bus_type = {
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);
 
-/**
- * platform_bus_get_pm_ops() - return pointer to busses dev_pm_ops
- *
- * This function can be used by platform code to get the current
- * set of dev_pm_ops functions used by the platform_bus_type.
- */
-const struct dev_pm_ops * __init platform_bus_get_pm_ops(void)
-{
-	return platform_bus_type.pm;
-}
-
-/**
- * platform_bus_set_pm_ops() - update dev_pm_ops for the platform_bus_type
- *
- * @pm: pointer to new dev_pm_ops struct to be used for platform_bus_type
- *
- * Platform code can override the dev_pm_ops methods of
- * platform_bus_type by using this function.  It is expected that
- * platform code will first do a platform_bus_get_pm_ops(), then
- * kmemdup it, then customize selected methods and pass a pointer to
- * the new struct dev_pm_ops to this function.
- *
- * Since platform-specific code is customizing methods for *all*
- * devices (not just platform-specific devices) it is expected that
- * any custom overrides of these functions will keep existing behavior
- * and simply extend it.  For example, any customization of the
- * runtime PM methods should continue to call the pm_generic_*
- * functions as the default ones do in addition to the
- * platform-specific behavior.
- */
-void __init platform_bus_set_pm_ops(const struct dev_pm_ops *pm)
-{
-	platform_bus_type.pm = pm;
-}
-
 int __init platform_bus_init(void)
 {
 	int error;
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index 118c1b92a51..3647e114d0e 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -3,6 +3,6 @@ obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_OPP)	+= opp.o
+obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
 
-ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
-ccflags-$(CONFIG_PM_VERBOSE)   += -DDEBUG
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
\ No newline at end of file
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
new file mode 100644
index 00000000000..c0dd09df7be
--- /dev/null
+++ b/drivers/base/power/clock_ops.c
@@ -0,0 +1,431 @@
+/*
+ * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks
+ *
+ * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_PM_RUNTIME
+
+struct pm_runtime_clk_data {
+	struct list_head clock_list;
+	struct mutex lock;
+};
+
+enum pce_status {
+	PCE_STATUS_NONE = 0,
+	PCE_STATUS_ACQUIRED,
+	PCE_STATUS_ENABLED,
+	PCE_STATUS_ERROR,
+};
+
+struct pm_clock_entry {
+	struct list_head node;
+	char *con_id;
+	struct clk *clk;
+	enum pce_status status;
+};
+
+static struct pm_runtime_clk_data *__to_prd(struct device *dev)
+{
+	return dev ? dev->power.subsys_data : NULL;
+}
+
+/**
+ * pm_runtime_clk_add - Start using a device clock for runtime PM.
+ * @dev: Device whose clock is going to be used for runtime PM.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the runtime PM of @dev.
+ */
+int pm_runtime_clk_add(struct device *dev, const char *con_id)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!prd)
+		return -EINVAL;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		dev_err(dev, "Not enough memory for clock entry.\n");
+		return -ENOMEM;
+	}
+
+	if (con_id) {
+		ce->con_id = kstrdup(con_id, GFP_KERNEL);
+		if (!ce->con_id) {
+			dev_err(dev,
+				"Not enough memory for clock connection ID.\n");
+			kfree(ce);
+			return -ENOMEM;
+		}
+	}
+
+	mutex_lock(&prd->lock);
+	list_add_tail(&ce->node, &prd->clock_list);
+	mutex_unlock(&prd->lock);
+	return 0;
+}
+
+/**
+ * __pm_runtime_clk_remove - Destroy runtime PM clock entry.
+ * @ce: Runtime PM clock entry to destroy.
+ *
+ * This routine must be called under the mutex protecting the runtime PM list
+ * of clocks corresponding the the @ce's device.
+ */
+static void __pm_runtime_clk_remove(struct pm_clock_entry *ce)
+{
+	if (!ce)
+		return;
+
+	list_del(&ce->node);
+
+	if (ce->status < PCE_STATUS_ERROR) {
+		if (ce->status == PCE_STATUS_ENABLED)
+			clk_disable(ce->clk);
+
+		if (ce->status >= PCE_STATUS_ACQUIRED)
+			clk_put(ce->clk);
+	}
+
+	if (ce->con_id)
+		kfree(ce->con_id);
+
+	kfree(ce);
+}
+
+/**
+ * pm_runtime_clk_remove - Stop using a device clock for runtime PM.
+ * @dev: Device whose clock should not be used for runtime PM any more.
+ * @con_id: Connection ID of the clock.
+ *
+ * Remove the clock represented by @con_id from the list of clocks used for
+ * the runtime PM of @dev.
+ */
+void pm_runtime_clk_remove(struct device *dev, const char *con_id)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!prd)
+		return;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry(ce, &prd->clock_list, node) {
+		if (!con_id && !ce->con_id) {
+			__pm_runtime_clk_remove(ce);
+			break;
+		} else if (!con_id || !ce->con_id) {
+			continue;
+		} else if (!strcmp(con_id, ce->con_id)) {
+			__pm_runtime_clk_remove(ce);
+			break;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+}
+
+/**
+ * pm_runtime_clk_init - Initialize a device's list of runtime PM clocks.
+ * @dev: Device to initialize the list of runtime PM clocks for.
+ *
+ * Allocate a struct pm_runtime_clk_data object, initialize its lock member and
+ * make the @dev's power.subsys_data field point to it.
+ */
+int pm_runtime_clk_init(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd;
+
+	prd = kzalloc(sizeof(*prd), GFP_KERNEL);
+	if (!prd) {
+		dev_err(dev, "Not enough memory fo runtime PM data.\n");
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&prd->clock_list);
+	mutex_init(&prd->lock);
+	dev->power.subsys_data = prd;
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_destroy - Destroy a device's list of runtime PM clocks.
+ * @dev: Device to destroy the list of runtime PM clocks for.
+ *
+ * Clear the @dev's power.subsys_data field, remove the list of clock entries
+ * from the struct pm_runtime_clk_data object pointed to by it before and free
+ * that object.
+ */
+void pm_runtime_clk_destroy(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce, *c;
+
+	if (!prd)
+		return;
+
+	dev->power.subsys_data = NULL;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry_safe_reverse(ce, c, &prd->clock_list, node)
+		__pm_runtime_clk_remove(ce);
+
+	mutex_unlock(&prd->lock);
+
+	kfree(prd);
+}
+
+/**
+ * pm_runtime_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @con_id: Connection ID of the clock.
+ */
+static void pm_runtime_clk_acquire(struct device *dev,
+				    struct pm_clock_entry *ce)
+{
+	ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+/**
+ * pm_runtime_clk_suspend - Disable clocks in a device's runtime PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_runtime_clk_suspend(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!prd)
+		return 0;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry_reverse(ce, &prd->clock_list, node) {
+		if (ce->status == PCE_STATUS_NONE)
+			pm_runtime_clk_acquire(dev, ce);
+
+		if (ce->status < PCE_STATUS_ERROR) {
+			clk_disable(ce->clk);
+			ce->status = PCE_STATUS_ACQUIRED;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_resume - Enable clocks in a device's runtime PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_runtime_clk_resume(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!prd)
+		return 0;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry(ce, &prd->clock_list, node) {
+		if (ce->status == PCE_STATUS_NONE)
+			pm_runtime_clk_acquire(dev, ce);
+
+		if (ce->status < PCE_STATUS_ERROR) {
+			clk_enable(ce->clk);
+			ce->status = PCE_STATUS_ENABLED;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the pwr_domain member of that object is copied to the device's
+ * pwr_domain field and its con_ids member is used to populate the device's list
+ * of runtime PM clocks, depending on @action.
+ *
+ * If the device's pwr_domain field is already populated with a value different
+ * from the one stored in the struct pm_clk_notifier_block object, the function
+ * does nothing.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char *con_id;
+	int error;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (dev->pwr_domain)
+			break;
+
+		error = pm_runtime_clk_init(dev);
+		if (error)
+			break;
+
+		dev->pwr_domain = clknb->pwr_domain;
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
+				pm_runtime_clk_add(dev, con_id);
+		} else {
+			pm_runtime_clk_add(dev, NULL);
+		}
+
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->pwr_domain != clknb->pwr_domain)
+			break;
+
+		dev->pwr_domain = NULL;
+		pm_runtime_clk_destroy(dev);
+		break;
+	}
+
+	return 0;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+/**
+ * enable_clock - Enable a device clock.
+ * @dev: Device whose clock is to be enabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void enable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_enable(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced on.\n");
+	}
+}
+
+/**
+ * disable_clock - Disable a device clock.
+ * @dev: Device whose clock is to be disabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void disable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_disable(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced off.\n");
+	}
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the con_ids member of that object is used to enable or disable
+ * the device's clocks, depending on @action.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char *con_id;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
+				enable_clock(dev, con_id);
+		} else {
+			enable_clock(dev, NULL);
+		}
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids[0]; *con_id; con_id++)
+				disable_clock(dev, con_id);
+		} else {
+			disable_clock(dev, NULL);
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+/**
+ * pm_runtime_clk_add_notifier - Add bus type notifier for runtime PM clocks.
+ * @bus: Bus type to add the notifier to.
+ * @clknb: Notifier to be added to the given bus type.
+ *
+ * The nb member of @clknb is not expected to be initialized and its
+ * notifier_call member will be replaced with pm_runtime_clk_notify().  However,
+ * the remaining members of @clknb should be populated prior to calling this
+ * routine.
+ */
+void pm_runtime_clk_add_notifier(struct bus_type *bus,
+				 struct pm_clk_notifier_block *clknb)
+{
+	if (!bus || !clknb)
+		return;
+
+	clknb->nb.notifier_call = pm_runtime_clk_notify;
+	bus_register_notifier(bus, &clknb->nb);
+}
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
index 42f97f92562..cb3bb368681 100644
--- a/drivers/base/power/generic_ops.c
+++ b/drivers/base/power/generic_ops.c
@@ -74,6 +74,23 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_resume);
 
 #ifdef CONFIG_PM_SLEEP
 /**
+ * pm_generic_prepare - Generic routine preparing a device for power transition.
+ * @dev: Device to prepare.
+ *
+ * Prepare a device for a system-wide power transition.
+ */
+int pm_generic_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (drv && drv->pm && drv->pm->prepare)
+		ret = drv->pm->prepare(dev);
+
+	return ret;
+}
+
+/**
  * __pm_generic_call - Generic suspend/freeze/poweroff/thaw subsystem callback.
  * @dev: Device to handle.
  * @event: PM transition of the system under way.
@@ -213,16 +230,38 @@ int pm_generic_restore(struct device *dev)
 	return __pm_generic_resume(dev, PM_EVENT_RESTORE);
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore);
+
+/**
+ * pm_generic_complete - Generic routine competing a device power transition.
+ * @dev: Device to handle.
+ *
+ * Complete a device power transition during a system-wide power transition.
+ */
+void pm_generic_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+
+	/*
+	 * Let runtime PM try to suspend devices that haven't been in use before
+	 * going into the system-wide sleep state we're resuming from.
+	 */
+	pm_runtime_idle(dev);
+}
 #endif /* CONFIG_PM_SLEEP */
 
 struct dev_pm_ops generic_subsys_pm_ops = {
 #ifdef CONFIG_PM_SLEEP
+	.prepare = pm_generic_prepare,
 	.suspend = pm_generic_suspend,
 	.resume = pm_generic_resume,
 	.freeze = pm_generic_freeze,
 	.thaw = pm_generic_thaw,
 	.poweroff = pm_generic_poweroff,
 	.restore = pm_generic_restore,
+	.complete = pm_generic_complete,
 #endif
 #ifdef CONFIG_PM_RUNTIME
 	.runtime_suspend = pm_generic_runtime_suspend,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index abe3ab709e8..aa632020774 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -426,10 +426,8 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 
 	if (dev->pwr_domain) {
 		pm_dev_dbg(dev, state, "EARLY power domain ");
-		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
-	}
-
-	if (dev->type && dev->type->pm) {
+		error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "EARLY type ");
 		error = pm_noirq_op(dev, dev->type->pm, state);
 	} else if (dev->class && dev->class->pm) {
@@ -517,7 +515,8 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	if (dev->pwr_domain) {
 		pm_dev_dbg(dev, state, "power domain ");
-		pm_op(dev, &dev->pwr_domain->ops, state);
+		error = pm_op(dev, &dev->pwr_domain->ops, state);
+		goto End;
 	}
 
 	if (dev->type && dev->type->pm) {
@@ -580,11 +579,13 @@ static bool is_async(struct device *dev)
  * Execute the appropriate "resume" callback for all devices whose status
  * indicates that they are suspended.
  */
-static void dpm_resume(pm_message_t state)
+void dpm_resume(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
 
+	might_sleep();
+
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
@@ -629,12 +630,11 @@ static void device_complete(struct device *dev, pm_message_t state)
 {
 	device_lock(dev);
 
-	if (dev->pwr_domain && dev->pwr_domain->ops.complete) {
+	if (dev->pwr_domain) {
 		pm_dev_dbg(dev, state, "completing power domain ");
-		dev->pwr_domain->ops.complete(dev);
-	}
-
-	if (dev->type && dev->type->pm) {
+		if (dev->pwr_domain->ops.complete)
+			dev->pwr_domain->ops.complete(dev);
+	} else if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "completing type ");
 		if (dev->type->pm->complete)
 			dev->type->pm->complete(dev);
@@ -658,10 +658,12 @@ static void device_complete(struct device *dev, pm_message_t state)
  * Execute the ->complete() callbacks for all devices whose PM status is not
  * DPM_ON (this allows new devices to be registered).
  */
-static void dpm_complete(pm_message_t state)
+void dpm_complete(pm_message_t state)
 {
 	struct list_head list;
 
+	might_sleep();
+
 	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
 	while (!list_empty(&dpm_prepared_list)) {
@@ -690,7 +692,6 @@ static void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
-	might_sleep();
 	dpm_resume(state);
 	dpm_complete(state);
 }
@@ -732,7 +733,12 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
 	int error;
 
-	if (dev->type && dev->type->pm) {
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "LATE power domain ");
+		error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+		if (error)
+			return error;
+	} else if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "LATE type ");
 		error = pm_noirq_op(dev, dev->type->pm, state);
 		if (error)
@@ -749,11 +755,6 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 			return error;
 	}
 
-	if (dev->pwr_domain) {
-		pm_dev_dbg(dev, state, "LATE power domain ");
-		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
-	}
-
 	return 0;
 }
 
@@ -841,21 +842,27 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		goto End;
 	}
 
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		error = pm_op(dev, &dev->pwr_domain->ops, state);
+		goto End;
+	}
+
 	if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "type ");
 		error = pm_op(dev, dev->type->pm, state);
-		goto Domain;
+		goto End;
 	}
 
 	if (dev->class) {
 		if (dev->class->pm) {
 			pm_dev_dbg(dev, state, "class ");
 			error = pm_op(dev, dev->class->pm, state);
-			goto Domain;
+			goto End;
 		} else if (dev->class->suspend) {
 			pm_dev_dbg(dev, state, "legacy class ");
 			error = legacy_suspend(dev, state, dev->class->suspend);
-			goto Domain;
+			goto End;
 		}
 	}
 
@@ -869,12 +876,6 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		}
 	}
 
- Domain:
-	if (!error && dev->pwr_domain) {
-		pm_dev_dbg(dev, state, "power domain ");
-		pm_op(dev, &dev->pwr_domain->ops, state);
-	}
-
  End:
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
@@ -914,11 +915,13 @@ static int device_suspend(struct device *dev)
  * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices.
  * @state: PM transition of the system being carried out.
  */
-static int dpm_suspend(pm_message_t state)
+int dpm_suspend(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	might_sleep();
+
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
@@ -965,7 +968,14 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
 	device_lock(dev);
 
-	if (dev->type && dev->type->pm) {
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "preparing power domain ");
+		if (dev->pwr_domain->ops.prepare)
+			error = dev->pwr_domain->ops.prepare(dev);
+		suspend_report_result(dev->pwr_domain->ops.prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->type && dev->type->pm) {
 		pm_dev_dbg(dev, state, "preparing type ");
 		if (dev->type->pm->prepare)
 			error = dev->type->pm->prepare(dev);
@@ -984,13 +994,6 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		if (dev->bus->pm->prepare)
 			error = dev->bus->pm->prepare(dev);
 		suspend_report_result(dev->bus->pm->prepare, error);
-		if (error)
-			goto End;
-	}
-
-	if (dev->pwr_domain && dev->pwr_domain->ops.prepare) {
-		pm_dev_dbg(dev, state, "preparing power domain ");
-		dev->pwr_domain->ops.prepare(dev);
 	}
 
  End:
@@ -1005,10 +1008,12 @@ static int device_prepare(struct device *dev, pm_message_t state)
  *
  * Execute the ->prepare() callback(s) for all devices.
  */
-static int dpm_prepare(pm_message_t state)
+int dpm_prepare(pm_message_t state)
 {
 	int error = 0;
 
+	might_sleep();
+
 	mutex_lock(&dpm_list_mtx);
 	while (!list_empty(&dpm_list)) {
 		struct device *dev = to_device(dpm_list.next);
@@ -1057,7 +1062,6 @@ int dpm_suspend_start(pm_message_t state)
 {
 	int error;
 
-	might_sleep();
 	error = dpm_prepare(state);
 	if (!error)
 		error = dpm_suspend(state);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 3172c60d23a..0d4587b15c5 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -168,7 +168,6 @@ static int rpm_check_suspend_allowed(struct device *dev)
 static int rpm_idle(struct device *dev, int rpmflags)
 {
 	int (*callback)(struct device *);
-	int (*domain_callback)(struct device *);
 	int retval;
 
 	retval = rpm_check_suspend_allowed(dev);
@@ -214,7 +213,9 @@ static int rpm_idle(struct device *dev, int rpmflags)
 
 	dev->power.idle_notification = true;
 
-	if (dev->type && dev->type->pm)
+	if (dev->pwr_domain)
+		callback = dev->pwr_domain->ops.runtime_idle;
+	else if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_idle;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_idle;
@@ -223,19 +224,10 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
-	if (dev->pwr_domain)
-		domain_callback = dev->pwr_domain->ops.runtime_idle;
-	else
-		domain_callback = NULL;
-
-	if (callback || domain_callback) {
+	if (callback) {
 		spin_unlock_irq(&dev->power.lock);
 
-		if (domain_callback)
-			retval = domain_callback(dev);
-
-		if (!retval && callback)
-			callback(dev);
+		callback(dev);
 
 		spin_lock_irq(&dev->power.lock);
 	}
@@ -382,7 +374,9 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
-	if (dev->type && dev->type->pm)
+	if (dev->pwr_domain)
+		callback = dev->pwr_domain->ops.runtime_suspend;
+	else if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_suspend;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_suspend;
@@ -400,8 +394,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		else
 			pm_runtime_cancel_pending(dev);
 	} else {
-		if (dev->pwr_domain)
-			rpm_callback(dev->pwr_domain->ops.runtime_suspend, dev);
  no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
@@ -582,9 +574,8 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	__update_runtime_status(dev, RPM_RESUMING);
 
 	if (dev->pwr_domain)
-		rpm_callback(dev->pwr_domain->ops.runtime_resume, dev);
-
-	if (dev->type && dev->type->pm)
+		callback = dev->pwr_domain->ops.runtime_resume;
+	else if (dev->type && dev->type->pm)
 		callback = dev->type->pm->runtime_resume;
 	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->runtime_resume;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index fff49bee781..a9f5b897961 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -212,8 +212,9 @@ static ssize_t autosuspend_delay_ms_store(struct device *dev,
 static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
 		autosuspend_delay_ms_store);
 
-#endif
+#endif /* CONFIG_PM_RUNTIME */
 
+#ifdef CONFIG_PM_SLEEP
 static ssize_t
 wake_show(struct device * dev, struct device_attribute *attr, char * buf)
 {
@@ -248,7 +249,6 @@ wake_store(struct device * dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
 
-#ifdef CONFIG_PM_SLEEP
 static ssize_t wakeup_count_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index abbbd33e8d8..84f7c7d5a09 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -110,7 +110,6 @@ void wakeup_source_add(struct wakeup_source *ws)
 	spin_lock_irq(&events_lock);
 	list_add_rcu(&ws->entry, &wakeup_sources);
 	spin_unlock_irq(&events_lock);
-	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(wakeup_source_add);
 
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index acde9b5ee13..9dff77bfe1e 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -328,203 +328,8 @@ void sysdev_unregister(struct sys_device *sysdev)
 	kobject_put(&sysdev->kobj);
 }
 
-
-#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
-/**
- *	sysdev_shutdown - Shut down all system devices.
- *
- *	Loop over each class of system devices, and the devices in each
- *	of those classes. For each device, we call the shutdown method for
- *	each driver registered for the device - the auxiliaries,
- *	and the class driver.
- *
- *	Note: The list is iterated in reverse order, so that we shut down
- *	child devices before we shut down their parents. The list ordering
- *	is guaranteed by virtue of the fact that child devices are registered
- *	after their parents.
- */
-void sysdev_shutdown(void)
-{
-	struct sysdev_class *cls;
-
-	pr_debug("Shutting Down System Devices\n");
-
-	mutex_lock(&sysdev_drivers_lock);
-	list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) {
-		struct sys_device *sysdev;
-
-		pr_debug("Shutting down type '%s':\n",
-			 kobject_name(&cls->kset.kobj));
-
-		list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) {
-			struct sysdev_driver *drv;
-			pr_debug(" %s\n", kobject_name(&sysdev->kobj));
-
-			/* Call auxiliary drivers first */
-			list_for_each_entry(drv, &cls->drivers, entry) {
-				if (drv->shutdown)
-					drv->shutdown(sysdev);
-			}
-
-			/* Now call the generic one */
-			if (cls->shutdown)
-				cls->shutdown(sysdev);
-		}
-	}
-	mutex_unlock(&sysdev_drivers_lock);
-}
-
-static void __sysdev_resume(struct sys_device *dev)
-{
-	struct sysdev_class *cls = dev->cls;
-	struct sysdev_driver *drv;
-
-	/* First, call the class-specific one */
-	if (cls->resume)
-		cls->resume(dev);
-	WARN_ONCE(!irqs_disabled(),
-		"Interrupts enabled after %pF\n", cls->resume);
-
-	/* Call auxiliary drivers next. */
-	list_for_each_entry(drv, &cls->drivers, entry) {
-		if (drv->resume)
-			drv->resume(dev);
-		WARN_ONCE(!irqs_disabled(),
-			"Interrupts enabled after %pF\n", drv->resume);
-	}
-}
-
-/**
- *	sysdev_suspend - Suspend all system devices.
- *	@state:		Power state to enter.
- *
- *	We perform an almost identical operation as sysdev_shutdown()
- *	above, though calling ->suspend() instead. Interrupts are disabled
- *	when this called. Devices are responsible for both saving state and
- *	quiescing or powering down the device.
- *
- *	This is only called by the device PM core, so we let them handle
- *	all synchronization.
- */
-int sysdev_suspend(pm_message_t state)
-{
-	struct sysdev_class *cls;
-	struct sys_device *sysdev, *err_dev;
-	struct sysdev_driver *drv, *err_drv;
-	int ret;
-
-	pr_debug("Checking wake-up interrupts\n");
-
-	/* Return error code if there are any wake-up interrupts pending */
-	ret = check_wakeup_irqs();
-	if (ret)
-		return ret;
-
-	WARN_ONCE(!irqs_disabled(),
-		"Interrupts enabled while suspending system devices\n");
-
-	pr_debug("Suspending System Devices\n");
-
-	list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) {
-		pr_debug("Suspending type '%s':\n",
-			 kobject_name(&cls->kset.kobj));
-
-		list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) {
-			pr_debug(" %s\n", kobject_name(&sysdev->kobj));
-
-			/* Call auxiliary drivers first */
-			list_for_each_entry(drv, &cls->drivers, entry) {
-				if (drv->suspend) {
-					ret = drv->suspend(sysdev, state);
-					if (ret)
-						goto aux_driver;
-				}
-				WARN_ONCE(!irqs_disabled(),
-					"Interrupts enabled after %pF\n",
-					drv->suspend);
-			}
-
-			/* Now call the generic one */
-			if (cls->suspend) {
-				ret = cls->suspend(sysdev, state);
-				if (ret)
-					goto cls_driver;
-				WARN_ONCE(!irqs_disabled(),
-					"Interrupts enabled after %pF\n",
-					cls->suspend);
-			}
-		}
-	}
-	return 0;
-	/* resume current sysdev */
-cls_driver:
-	drv = NULL;
-	printk(KERN_ERR "Class suspend failed for %s: %d\n",
-		kobject_name(&sysdev->kobj), ret);
-
-aux_driver:
-	if (drv)
-		printk(KERN_ERR "Class driver suspend failed for %s: %d\n",
-				kobject_name(&sysdev->kobj), ret);
-	list_for_each_entry(err_drv, &cls->drivers, entry) {
-		if (err_drv == drv)
-			break;
-		if (err_drv->resume)
-			err_drv->resume(sysdev);
-	}
-
-	/* resume other sysdevs in current class */
-	list_for_each_entry(err_dev, &cls->kset.list, kobj.entry) {
-		if (err_dev == sysdev)
-			break;
-		pr_debug(" %s\n", kobject_name(&err_dev->kobj));
-		__sysdev_resume(err_dev);
-	}
-
-	/* resume other classes */
-	list_for_each_entry_continue(cls, &system_kset->list, kset.kobj.entry) {
-		list_for_each_entry(err_dev, &cls->kset.list, kobj.entry) {
-			pr_debug(" %s\n", kobject_name(&err_dev->kobj));
-			__sysdev_resume(err_dev);
-		}
-	}
-	return ret;
-}
-EXPORT_SYMBOL_GPL(sysdev_suspend);
-
-/**
- *	sysdev_resume - Bring system devices back to life.
- *
- *	Similar to sysdev_suspend(), but we iterate the list forwards
- *	to guarantee that parent devices are resumed before their children.
- *
- *	Note: Interrupts are disabled when called.
- */
-int sysdev_resume(void)
-{
-	struct sysdev_class *cls;
-
-	WARN_ONCE(!irqs_disabled(),
-		"Interrupts enabled while resuming system devices\n");
-
-	pr_debug("Resuming System Devices\n");
-
-	list_for_each_entry(cls, &system_kset->list, kset.kobj.entry) {
-		struct sys_device *sysdev;
-
-		pr_debug("Resuming type '%s':\n",
-			 kobject_name(&cls->kset.kobj));
-
-		list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) {
-			pr_debug(" %s\n", kobject_name(&sysdev->kobj));
-
-			__sysdev_resume(sysdev);
-		}
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(sysdev_resume);
-#endif /* CONFIG_ARCH_NO_SYSDEV_OPS */
+EXPORT_SYMBOL_GPL(sysdev_register);
+EXPORT_SYMBOL_GPL(sysdev_unregister);
 
 int __init system_bus_init(void)
 {
@@ -534,9 +339,6 @@ int __init system_bus_init(void)
 	return 0;
 }
 
-EXPORT_SYMBOL_GPL(sysdev_register);
-EXPORT_SYMBOL_GPL(sysdev_unregister);
-
 #define to_ext_attr(x) container_of(x, struct sysdev_ext_attribute, attr)
 
 ssize_t sysdev_store_ulong(struct sys_device *sysdev,
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index ad59b4e0a9b..49502bc5360 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -523,7 +523,7 @@ config RAW_DRIVER
           with the O_DIRECT flag.
 
 config MAX_RAW_DEVS
-	int "Maximum number of RAW devices to support (1-8192)"
+	int "Maximum number of RAW devices to support (1-65536)"
 	depends on RAW_DRIVER
 	default "256"
 	help
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 7066e801b9d..051474c65b7 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -84,8 +84,6 @@ static struct clocksource clocksource_hpet = {
 	.rating		= 250,
 	.read		= read_hpet,
 	.mask		= CLOCKSOURCE_MASK(64),
-	.mult		= 0,		/* to be calculated */
-	.shift		= 10,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 static struct clocksource *hpet_clocksource;
@@ -934,9 +932,7 @@ int hpet_alloc(struct hpet_data *hdp)
 	if (!hpet_clocksource) {
 		hpet_mctr = (void __iomem *)&hpetp->hp_hpet->hpet_mc;
 		CLKSRC_FSYS_MMIO_SET(clocksource_hpet.fsys_mmio, hpet_mctr);
-		clocksource_hpet.mult = clocksource_hz2mult(hpetp->hp_tick_freq,
-						clocksource_hpet.shift);
-		clocksource_register(&clocksource_hpet);
+		clocksource_register_hz(&clocksource_hpet, hpetp->hp_tick_freq);
 		hpetp->hp_clocksource = &clocksource_hpet;
 		hpet_clocksource = &clocksource_hpet;
 	}
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 436a9901799..8fc04b4f311 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -806,29 +806,41 @@ static const struct file_operations oldmem_fops = {
 };
 #endif
 
-static ssize_t kmsg_write(struct file *file, const char __user *buf,
-			  size_t count, loff_t *ppos)
+static ssize_t kmsg_writev(struct kiocb *iocb, const struct iovec *iv,
+			   unsigned long count, loff_t pos)
 {
-	char *tmp;
-	ssize_t ret;
+	char *line, *p;
+	int i;
+	ssize_t ret = -EFAULT;
+	size_t len = iov_length(iv, count);
 
-	tmp = kmalloc(count + 1, GFP_KERNEL);
-	if (tmp == NULL)
+	line = kmalloc(len + 1, GFP_KERNEL);
+	if (line == NULL)
 		return -ENOMEM;
-	ret = -EFAULT;
-	if (!copy_from_user(tmp, buf, count)) {
-		tmp[count] = 0;
-		ret = printk("%s", tmp);
-		if (ret > count)
-			/* printk can add a prefix */
-			ret = count;
+
+	/*
+	 * copy all vectors into a single string, to ensure we do
+	 * not interleave our log line with other printk calls
+	 */
+	p = line;
+	for (i = 0; i < count; i++) {
+		if (copy_from_user(p, iv[i].iov_base, iv[i].iov_len))
+			goto out;
+		p += iv[i].iov_len;
 	}
-	kfree(tmp);
+	p[0] = '\0';
+
+	ret = printk("%s", line);
+	/* printk can add a prefix */
+	if (ret > len)
+		ret = len;
+out:
+	kfree(line);
 	return ret;
 }
 
 static const struct file_operations kmsg_fops = {
-	.write = kmsg_write,
+	.aio_write = kmsg_writev,
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index b4b9d5a4788..b33e8ea314e 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -21,6 +21,7 @@
 #include <linux/mutex.h>
 #include <linux/gfp.h>
 #include <linux/compat.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 
@@ -30,10 +31,15 @@ struct raw_device_data {
 };
 
 static struct class *raw_class;
-static struct raw_device_data raw_devices[MAX_RAW_MINORS];
+static struct raw_device_data *raw_devices;
 static DEFINE_MUTEX(raw_mutex);
 static const struct file_operations raw_ctl_fops; /* forward declaration */
 
+static int max_raw_minors = MAX_RAW_MINORS;
+
+module_param(max_raw_minors, int, 0);
+MODULE_PARM_DESC(max_raw_minors, "Maximum number of raw devices (1-65536)");
+
 /*
  * Open/close code for raw IO.
  *
@@ -125,7 +131,7 @@ static int bind_set(int number, u64 major, u64 minor)
 	struct raw_device_data *rawdev;
 	int err = 0;
 
-	if (number <= 0 || number >= MAX_RAW_MINORS)
+	if (number <= 0 || number >= max_raw_minors)
 		return -EINVAL;
 
 	if (MAJOR(dev) != major || MINOR(dev) != minor)
@@ -312,14 +318,27 @@ static int __init raw_init(void)
 	dev_t dev = MKDEV(RAW_MAJOR, 0);
 	int ret;
 
-	ret = register_chrdev_region(dev, MAX_RAW_MINORS, "raw");
+	if (max_raw_minors < 1 || max_raw_minors > 65536) {
+		printk(KERN_WARNING "raw: invalid max_raw_minors (must be"
+			" between 1 and 65536), using %d\n", MAX_RAW_MINORS);
+		max_raw_minors = MAX_RAW_MINORS;
+	}
+
+	raw_devices = vmalloc(sizeof(struct raw_device_data) * max_raw_minors);
+	if (!raw_devices) {
+		printk(KERN_ERR "Not enough memory for raw device structures\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+	memset(raw_devices, 0, sizeof(struct raw_device_data) * max_raw_minors);
+
+	ret = register_chrdev_region(dev, max_raw_minors, "raw");
 	if (ret)
 		goto error;
 
 	cdev_init(&raw_cdev, &raw_fops);
-	ret = cdev_add(&raw_cdev, dev, MAX_RAW_MINORS);
+	ret = cdev_add(&raw_cdev, dev, max_raw_minors);
 	if (ret) {
-		kobject_put(&raw_cdev.kobj);
 		goto error_region;
 	}
 
@@ -336,8 +355,9 @@ static int __init raw_init(void)
 	return 0;
 
 error_region:
-	unregister_chrdev_region(dev, MAX_RAW_MINORS);
+	unregister_chrdev_region(dev, max_raw_minors);
 error:
+	vfree(raw_devices);
 	return ret;
 }
 
@@ -346,7 +366,7 @@ static void __exit raw_exit(void)
 	device_destroy(raw_class, MKDEV(RAW_MAJOR, 0));
 	class_destroy(raw_class);
 	cdev_del(&raw_cdev);
-	unregister_chrdev_region(MKDEV(RAW_MAJOR, 0), MAX_RAW_MINORS);
+	unregister_chrdev_region(MKDEV(RAW_MAJOR, 0), max_raw_minors);
 }
 
 module_init(raw_init);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
new file mode 100644
index 00000000000..110aeeb52f9
--- /dev/null
+++ b/drivers/clocksource/Kconfig
@@ -0,0 +1,2 @@
+config CLKSRC_I8253
+	bool
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index be61ece6330..cfb6383b543 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC)	+= cs5535-clockevt.o
 obj-$(CONFIG_SH_TIMER_CMT)	+= sh_cmt.o
 obj-$(CONFIG_SH_TIMER_MTU2)	+= sh_mtu2.o
 obj-$(CONFIG_SH_TIMER_TMU)	+= sh_tmu.o
+obj-$(CONFIG_CLKSRC_I8253)	+= i8253.o
diff --git a/drivers/clocksource/cyclone.c b/drivers/clocksource/cyclone.c
index 64e528e8bfa..72f811f73e9 100644
--- a/drivers/clocksource/cyclone.c
+++ b/drivers/clocksource/cyclone.c
@@ -29,8 +29,6 @@ static struct clocksource clocksource_cyclone = {
 	.rating		= 250,
 	.read		= read_cyclone,
 	.mask		= CYCLONE_TIMER_MASK,
-	.mult		= 10,
-	.shift		= 0,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -108,12 +106,8 @@ static int __init init_cyclone_clocksource(void)
 	}
 	cyclone_ptr = cyclone_timer;
 
-	/* sort out mult/shift values: */
-	clocksource_cyclone.shift = 22;
-	clocksource_cyclone.mult = clocksource_hz2mult(CYCLONE_TIMER_FREQ,
-						clocksource_cyclone.shift);
-
-	return clocksource_register(&clocksource_cyclone);
+	return clocksource_register_hz(&clocksource_cyclone,
+					CYCLONE_TIMER_FREQ);
 }
 
 arch_initcall(init_cyclone_clocksource);
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
new file mode 100644
index 00000000000..225c1761b37
--- /dev/null
+++ b/drivers/clocksource/i8253.c
@@ -0,0 +1,88 @@
+/*
+ * i8253 PIT clocksource
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/timex.h>
+
+#include <asm/i8253.h>
+
+/*
+ * Since the PIT overflows every tick, its not very useful
+ * to just read by itself. So use jiffies to emulate a free
+ * running counter:
+ */
+static cycle_t i8253_read(struct clocksource *cs)
+{
+	static int old_count;
+	static u32 old_jifs;
+	unsigned long flags;
+	int count;
+	u32 jifs;
+
+	raw_spin_lock_irqsave(&i8253_lock, flags);
+	/*
+	 * Although our caller may have the read side of xtime_lock,
+	 * this is now a seqlock, and we are cheating in this routine
+	 * by having side effects on state that we cannot undo if
+	 * there is a collision on the seqlock and our caller has to
+	 * retry.  (Namely, old_jifs and old_count.)  So we must treat
+	 * jiffies as volatile despite the lock.  We read jiffies
+	 * before latching the timer count to guarantee that although
+	 * the jiffies value might be older than the count (that is,
+	 * the counter may underflow between the last point where
+	 * jiffies was incremented and the point where we latch the
+	 * count), it cannot be newer.
+	 */
+	jifs = jiffies;
+	outb_pit(0x00, PIT_MODE);	/* latch the count ASAP */
+	count = inb_pit(PIT_CH0);	/* read the latched count */
+	count |= inb_pit(PIT_CH0) << 8;
+
+	/* VIA686a test code... reset the latch if count > max + 1 */
+	if (count > LATCH) {
+		outb_pit(0x34, PIT_MODE);
+		outb_pit(PIT_LATCH & 0xff, PIT_CH0);
+		outb_pit(PIT_LATCH >> 8, PIT_CH0);
+		count = PIT_LATCH - 1;
+	}
+
+	/*
+	 * It's possible for count to appear to go the wrong way for a
+	 * couple of reasons:
+	 *
+	 *  1. The timer counter underflows, but we haven't handled the
+	 *     resulting interrupt and incremented jiffies yet.
+	 *  2. Hardware problem with the timer, not giving us continuous time,
+	 *     the counter does small "jumps" upwards on some Pentium systems,
+	 *     (see c't 95/10 page 335 for Neptun bug.)
+	 *
+	 * Previous attempts to handle these cases intelligently were
+	 * buggy, so we just do the simple thing now.
+	 */
+	if (count > old_count && jifs == old_jifs)
+		count = old_count;
+
+	old_count = count;
+	old_jifs = jifs;
+
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
+
+	count = (PIT_LATCH - 1) - count;
+
+	return (cycle_t)(jifs * PIT_LATCH) + count;
+}
+
+static struct clocksource i8253_cs = {
+	.name		= "pit",
+	.rating		= 110,
+	.read		= i8253_read,
+	.mask		= CLOCKSOURCE_MASK(32),
+};
+
+int __init clocksource_i8253_init(void)
+{
+	return clocksource_register_hz(&i8253_cs, PIT_TICK_RATE);
+}
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index ca8ee8093d6..9fb84853d8e 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -1,3 +1,5 @@
+menu "CPU Frequency scaling"
+
 config CPU_FREQ
 	bool "CPU Frequency scaling"
 	help
@@ -18,19 +20,6 @@ if CPU_FREQ
 config CPU_FREQ_TABLE
 	tristate
 
-config CPU_FREQ_DEBUG
-	bool "Enable CPUfreq debugging"
-	help
-	  Say Y here to enable CPUfreq subsystem (including drivers)
-	  debugging. You will need to activate it via the kernel
-	  command line by passing
-	     cpufreq.debug=<value>
-
-	  To get <value>, add 
-	       1 to activate CPUfreq core debugging,
-	       2 to activate CPUfreq drivers debugging, and
-	       4 to activate CPUfreq governor debugging
-
 config CPU_FREQ_STAT
 	tristate "CPU frequency translation statistics"
 	select CPU_FREQ_TABLE
@@ -190,4 +179,10 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
-endif	# CPU_FREQ
+menu "x86 CPU frequency scaling drivers"
+depends on X86
+source "drivers/cpufreq/Kconfig.x86"
+endmenu
+
+endif
+endmenu
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/drivers/cpufreq/Kconfig.x86
index 870e6cc6ad2..78ff7ee4895 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig.x86
@@ -1,15 +1,7 @@
 #
-# CPU Frequency scaling
+# x86 CPU Frequency scaling drivers
 #
 
-menu "CPU Frequency scaling"
-
-source "drivers/cpufreq/Kconfig"
-
-if CPU_FREQ
-
-comment "CPUFreq processor drivers"
-
 config X86_PCC_CPUFREQ
 	tristate "Processor Clocking Control interface driver"
 	depends on ACPI && ACPI_PROCESSOR
@@ -43,7 +35,7 @@ config X86_ACPI_CPUFREQ
 config ELAN_CPUFREQ
 	tristate "AMD Elan SC400 and SC410"
 	select CPU_FREQ_TABLE
-	depends on X86_ELAN
+	depends on MELAN
 	---help---
 	  This adds the CPUFreq driver for AMD Elan SC400 and SC410
 	  processors.
@@ -59,7 +51,7 @@ config ELAN_CPUFREQ
 config SC520_CPUFREQ
 	tristate "AMD Elan SC520"
 	select CPU_FREQ_TABLE
-	depends on X86_ELAN
+	depends on MELAN
 	---help---
 	  This adds the CPUFreq driver for AMD Elan SC520 processor.
 
@@ -261,6 +253,3 @@ config X86_SPEEDSTEP_RELAXED_CAP_CHECK
 	  option lets the probing code bypass some of those checks if the
 	  parameter "relaxed_check=1" is passed to the module.
 
-endif	# CPU_FREQ
-
-endmenu
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 71fc3b4173f..c7f1a6f16b6 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -13,3 +13,29 @@ obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o
 
+##################################################################################d
+# x86 drivers.
+# Link order matters. K8 is preferred to ACPI because of firmware bugs in early
+# K8 systems. ACPI is preferred to all other hardware-specific drivers.
+# speedstep-* is preferred over p4-clockmod.
+
+obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o mperf.o
+obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
+obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
+obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
+obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
+obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
+obj-$(CONFIG_X86_E_POWERSAVER)		+= e_powersaver.o
+obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
+obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
+obj-$(CONFIG_X86_LONGRUN)		+= longrun.o
+obj-$(CONFIG_X86_GX_SUSPMOD)		+= gx-suspmod.o
+obj-$(CONFIG_X86_SPEEDSTEP_ICH)		+= speedstep-ich.o
+obj-$(CONFIG_X86_SPEEDSTEP_LIB)		+= speedstep-lib.o
+obj-$(CONFIG_X86_SPEEDSTEP_SMI)		+= speedstep-smi.o
+obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO)	+= speedstep-centrino.o
+obj-$(CONFIG_X86_P4_CLOCKMOD)		+= p4-clockmod.o
+obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
+
+##################################################################################d
+
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index a2baafb2fe6..4e04e127438 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -47,9 +47,6 @@
 #include <asm/cpufeature.h>
 #include "mperf.h"
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"acpi-cpufreq", msg)
-
 MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
 MODULE_LICENSE("GPL");
@@ -233,7 +230,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 	cmd.mask = mask;
 	drv_read(&cmd);
 
-	dprintk("get_cur_val = %u\n", cmd.val);
+	pr_debug("get_cur_val = %u\n", cmd.val);
 
 	return cmd.val;
 }
@@ -244,7 +241,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	unsigned int freq;
 	unsigned int cached_freq;
 
-	dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
+	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
 
 	if (unlikely(data == NULL ||
 		     data->acpi_data == NULL || data->freq_table == NULL)) {
@@ -261,7 +258,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 		data->resume = 1;
 	}
 
-	dprintk("cur freq = %u\n", freq);
+	pr_debug("cur freq = %u\n", freq);
 
 	return freq;
 }
@@ -293,7 +290,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	unsigned int i;
 	int result = 0;
 
-	dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
+	pr_debug("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
 
 	if (unlikely(data == NULL ||
 	     data->acpi_data == NULL || data->freq_table == NULL)) {
@@ -313,11 +310,11 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	next_perf_state = data->freq_table[next_state].index;
 	if (perf->state == next_perf_state) {
 		if (unlikely(data->resume)) {
-			dprintk("Called after resume, resetting to P%d\n",
+			pr_debug("Called after resume, resetting to P%d\n",
 				next_perf_state);
 			data->resume = 0;
 		} else {
-			dprintk("Already at target state (P%d)\n",
+			pr_debug("Already at target state (P%d)\n",
 				next_perf_state);
 			goto out;
 		}
@@ -357,7 +354,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 
 	if (acpi_pstate_strict) {
 		if (!check_freqs(cmd.mask, freqs.new, data)) {
-			dprintk("acpi_cpufreq_target failed (%d)\n",
+			pr_debug("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
 			result = -EAGAIN;
 			goto out;
@@ -378,7 +375,7 @@ static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
-	dprintk("acpi_cpufreq_verify\n");
+	pr_debug("acpi_cpufreq_verify\n");
 
 	return cpufreq_frequency_table_verify(policy, data->freq_table);
 }
@@ -433,11 +430,11 @@ static void free_acpi_perf_data(void)
 static int __init acpi_cpufreq_early_init(void)
 {
 	unsigned int i;
-	dprintk("acpi_cpufreq_early_init\n");
+	pr_debug("acpi_cpufreq_early_init\n");
 
 	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
 	if (!acpi_perf_data) {
-		dprintk("Memory allocation error for acpi_perf_data.\n");
+		pr_debug("Memory allocation error for acpi_perf_data.\n");
 		return -ENOMEM;
 	}
 	for_each_possible_cpu(i) {
@@ -519,7 +516,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	static int blacklisted;
 #endif
 
-	dprintk("acpi_cpufreq_cpu_init\n");
+	pr_debug("acpi_cpufreq_cpu_init\n");
 
 #ifdef CONFIG_SMP
 	if (blacklisted)
@@ -566,7 +563,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	/* capability check */
 	if (perf->state_count <= 1) {
-		dprintk("No P-States\n");
+		pr_debug("No P-States\n");
 		result = -ENODEV;
 		goto err_unreg;
 	}
@@ -578,11 +575,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
-		dprintk("SYSTEM IO addr space\n");
+		pr_debug("SYSTEM IO addr space\n");
 		data->cpu_feature = SYSTEM_IO_CAPABLE;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
-		dprintk("HARDWARE addr space\n");
+		pr_debug("HARDWARE addr space\n");
 		if (!check_est_cpu(cpu)) {
 			result = -ENODEV;
 			goto err_unreg;
@@ -590,7 +587,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
 		break;
 	default:
-		dprintk("Unknown addr space %d\n",
+		pr_debug("Unknown addr space %d\n",
 			(u32) (perf->control_register.space_id));
 		result = -ENODEV;
 		goto err_unreg;
@@ -661,9 +658,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (cpu_has(c, X86_FEATURE_APERFMPERF))
 		acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
 
-	dprintk("CPU%u - ACPI performance management activated.\n", cpu);
+	pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
 	for (i = 0; i < perf->state_count; i++)
-		dprintk("     %cP%d: %d MHz, %d mW, %d uS\n",
+		pr_debug("     %cP%d: %d MHz, %d mW, %d uS\n",
 			(i == perf->state ? '*' : ' '), i,
 			(u32) perf->states[i].core_frequency,
 			(u32) perf->states[i].power,
@@ -694,7 +691,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
-	dprintk("acpi_cpufreq_cpu_exit\n");
+	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
 		cpufreq_frequency_table_put_attr(policy->cpu);
@@ -712,7 +709,7 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
-	dprintk("acpi_cpufreq_resume\n");
+	pr_debug("acpi_cpufreq_resume\n");
 
 	data->resume = 1;
 
@@ -743,7 +740,7 @@ static int __init acpi_cpufreq_init(void)
 	if (acpi_disabled)
 		return 0;
 
-	dprintk("acpi_cpufreq_init\n");
+	pr_debug("acpi_cpufreq_init\n");
 
 	ret = acpi_cpufreq_early_init();
 	if (ret)
@@ -758,7 +755,7 @@ static int __init acpi_cpufreq_init(void)
 
 static void __exit acpi_cpufreq_exit(void)
 {
-	dprintk("acpi_cpufreq_exit\n");
+	pr_debug("acpi_cpufreq_exit\n");
 
 	cpufreq_unregister_driver(&acpi_cpufreq_driver);
 
diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index 141abebc451..7bac808804f 100644
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -57,8 +57,6 @@ MODULE_PARM_DESC(min_fsb,
 		"Minimum FSB to use, if not defined: current FSB - 50");
 
 #define PFX "cpufreq-nforce2: "
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"cpufreq-nforce2", msg)
 
 /**
  * nforce2_calc_fsb - calculate FSB
@@ -270,7 +268,7 @@ static int nforce2_target(struct cpufreq_policy *policy,
 	if (freqs.old == freqs.new)
 		return 0;
 
-	dprintk("Old CPU frequency %d kHz, new %d kHz\n",
+	pr_debug("Old CPU frequency %d kHz, new %d kHz\n",
 	       freqs.old, freqs.new);
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
@@ -282,7 +280,7 @@ static int nforce2_target(struct cpufreq_policy *policy,
 		printk(KERN_ERR PFX "Changing FSB to %d failed\n",
 			target_fsb);
 	else
-		dprintk("Changed FSB successfully to %d\n",
+		pr_debug("Changed FSB successfully to %d\n",
 			target_fsb);
 
 	/* Enable IRQs */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2dafc5c38ae..0a5bea9e358 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -32,9 +32,6 @@
 
 #include <trace/events/power.h>
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \
-						"cpufreq-core", msg)
-
 /**
  * The "cpufreq driver" - the arch- or hardware-dependent low
  * level driver of CPUFreq support, and its spinlock. This lock
@@ -181,93 +178,6 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
 
 /*********************************************************************
- *                     UNIFIED DEBUG HELPERS                         *
- *********************************************************************/
-#ifdef CONFIG_CPU_FREQ_DEBUG
-
-/* what part(s) of the CPUfreq subsystem are debugged? */
-static unsigned int debug;
-
-/* is the debug output ratelimit'ed using printk_ratelimit? User can
- * set or modify this value.
- */
-static unsigned int debug_ratelimit = 1;
-
-/* is the printk_ratelimit'ing enabled? It's enabled after a successful
- * loading of a cpufreq driver, temporarily disabled when a new policy
- * is set, and disabled upon cpufreq driver removal
- */
-static unsigned int disable_ratelimit = 1;
-static DEFINE_SPINLOCK(disable_ratelimit_lock);
-
-static void cpufreq_debug_enable_ratelimit(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&disable_ratelimit_lock, flags);
-	if (disable_ratelimit)
-		disable_ratelimit--;
-	spin_unlock_irqrestore(&disable_ratelimit_lock, flags);
-}
-
-static void cpufreq_debug_disable_ratelimit(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&disable_ratelimit_lock, flags);
-	disable_ratelimit++;
-	spin_unlock_irqrestore(&disable_ratelimit_lock, flags);
-}
-
-void cpufreq_debug_printk(unsigned int type, const char *prefix,
-			const char *fmt, ...)
-{
-	char s[256];
-	va_list args;
-	unsigned int len;
-	unsigned long flags;
-
-	WARN_ON(!prefix);
-	if (type & debug) {
-		spin_lock_irqsave(&disable_ratelimit_lock, flags);
-		if (!disable_ratelimit && debug_ratelimit
-					&& !printk_ratelimit()) {
-			spin_unlock_irqrestore(&disable_ratelimit_lock, flags);
-			return;
-		}
-		spin_unlock_irqrestore(&disable_ratelimit_lock, flags);
-
-		len = snprintf(s, 256, KERN_DEBUG "%s: ", prefix);
-
-		va_start(args, fmt);
-		len += vsnprintf(&s[len], (256 - len), fmt, args);
-		va_end(args);
-
-		printk(s);
-
-		WARN_ON(len < 5);
-	}
-}
-EXPORT_SYMBOL(cpufreq_debug_printk);
-
-
-module_param(debug, uint, 0644);
-MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core,"
-			" 2 to debug drivers, and 4 to debug governors.");
-
-module_param(debug_ratelimit, uint, 0644);
-MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging:"
-					" set to 0 to disable ratelimiting.");
-
-#else /* !CONFIG_CPU_FREQ_DEBUG */
-
-static inline void cpufreq_debug_enable_ratelimit(void) { return; }
-static inline void cpufreq_debug_disable_ratelimit(void) { return; }
-
-#endif /* CONFIG_CPU_FREQ_DEBUG */
-
-
-/*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
 
@@ -291,7 +201,7 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 	if (!l_p_j_ref_freq) {
 		l_p_j_ref = loops_per_jiffy;
 		l_p_j_ref_freq = ci->old;
-		dprintk("saving %lu as reference value for loops_per_jiffy; "
+		pr_debug("saving %lu as reference value for loops_per_jiffy; "
 			"freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq);
 	}
 	if ((val == CPUFREQ_PRECHANGE  && ci->old < ci->new) ||
@@ -299,7 +209,7 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
 		loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
 								ci->new);
-		dprintk("scaling loops_per_jiffy to %lu "
+		pr_debug("scaling loops_per_jiffy to %lu "
 			"for frequency %u kHz\n", loops_per_jiffy, ci->new);
 	}
 }
@@ -326,7 +236,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 	BUG_ON(irqs_disabled());
 
 	freqs->flags = cpufreq_driver->flags;
-	dprintk("notification %u of frequency transition to %u kHz\n",
+	pr_debug("notification %u of frequency transition to %u kHz\n",
 		state, freqs->new);
 
 	policy = per_cpu(cpufreq_cpu_data, freqs->cpu);
@@ -340,7 +250,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
 			if ((policy) && (policy->cpu == freqs->cpu) &&
 			    (policy->cur) && (policy->cur != freqs->old)) {
-				dprintk("Warning: CPU frequency is"
+				pr_debug("Warning: CPU frequency is"
 					" %u, cpufreq assumed %u kHz.\n",
 					freqs->old, policy->cur);
 				freqs->old = policy->cur;
@@ -353,7 +263,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 
 	case CPUFREQ_POSTCHANGE:
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
-		dprintk("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
+		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
 			(unsigned long)freqs->cpu);
 		trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu);
 		trace_cpu_frequency(freqs->new, freqs->cpu);
@@ -411,21 +321,14 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 		t = __find_governor(str_governor);
 
 		if (t == NULL) {
-			char *name = kasprintf(GFP_KERNEL, "cpufreq_%s",
-								str_governor);
-
-			if (name) {
-				int ret;
+			int ret;
 
-				mutex_unlock(&cpufreq_governor_mutex);
-				ret = request_module("%s", name);
-				mutex_lock(&cpufreq_governor_mutex);
+			mutex_unlock(&cpufreq_governor_mutex);
+			ret = request_module("cpufreq_%s", str_governor);
+			mutex_lock(&cpufreq_governor_mutex);
 
-				if (ret == 0)
-					t = __find_governor(str_governor);
-			}
-
-			kfree(name);
+			if (ret == 0)
+				t = __find_governor(str_governor);
 		}
 
 		if (t != NULL) {
@@ -753,7 +656,7 @@ no_policy:
 static void cpufreq_sysfs_release(struct kobject *kobj)
 {
 	struct cpufreq_policy *policy = to_policy(kobj);
-	dprintk("last reference is dropped\n");
+	pr_debug("last reference is dropped\n");
 	complete(&policy->kobj_unregister);
 }
 
@@ -788,7 +691,7 @@ static int cpufreq_add_dev_policy(unsigned int cpu,
 	gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
 	if (gov) {
 		policy->governor = gov;
-		dprintk("Restoring governor %s for cpu %d\n",
+		pr_debug("Restoring governor %s for cpu %d\n",
 		       policy->governor->name, cpu);
 	}
 #endif
@@ -824,7 +727,7 @@ static int cpufreq_add_dev_policy(unsigned int cpu,
 			per_cpu(cpufreq_cpu_data, cpu) = managed_policy;
 			spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-			dprintk("CPU already managed, adding link\n");
+			pr_debug("CPU already managed, adding link\n");
 			ret = sysfs_create_link(&sys_dev->kobj,
 						&managed_policy->kobj,
 						"cpufreq");
@@ -865,7 +768,7 @@ static int cpufreq_add_dev_symlink(unsigned int cpu,
 		if (!cpu_online(j))
 			continue;
 
-		dprintk("CPU %u already managed, adding link\n", j);
+		pr_debug("CPU %u already managed, adding link\n", j);
 		managed_policy = cpufreq_cpu_get(cpu);
 		cpu_sys_dev = get_cpu_sysdev(j);
 		ret = sysfs_create_link(&cpu_sys_dev->kobj, &policy->kobj,
@@ -941,7 +844,7 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 	policy->user_policy.governor = policy->governor;
 
 	if (ret) {
-		dprintk("setting policy failed\n");
+		pr_debug("setting policy failed\n");
 		if (cpufreq_driver->exit)
 			cpufreq_driver->exit(policy);
 	}
@@ -977,8 +880,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 	if (cpu_is_offline(cpu))
 		return 0;
 
-	cpufreq_debug_disable_ratelimit();
-	dprintk("adding CPU %u\n", cpu);
+	pr_debug("adding CPU %u\n", cpu);
 
 #ifdef CONFIG_SMP
 	/* check whether a different CPU already registered this
@@ -986,7 +888,6 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 	policy = cpufreq_cpu_get(cpu);
 	if (unlikely(policy)) {
 		cpufreq_cpu_put(policy);
-		cpufreq_debug_enable_ratelimit();
 		return 0;
 	}
 #endif
@@ -1037,7 +938,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 	 */
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
-		dprintk("initialization failed\n");
+		pr_debug("initialization failed\n");
 		goto err_unlock_policy;
 	}
 	policy->user_policy.min = policy->min;
@@ -1063,8 +964,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	module_put(cpufreq_driver->owner);
-	dprintk("initialization complete\n");
-	cpufreq_debug_enable_ratelimit();
+	pr_debug("initialization complete\n");
 
 	return 0;
 
@@ -1088,7 +988,6 @@ err_free_policy:
 nomem_out:
 	module_put(cpufreq_driver->owner);
 module_out:
-	cpufreq_debug_enable_ratelimit();
 	return ret;
 }
 
@@ -1112,15 +1011,13 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
 	unsigned int j;
 #endif
 
-	cpufreq_debug_disable_ratelimit();
-	dprintk("unregistering CPU %u\n", cpu);
+	pr_debug("unregistering CPU %u\n", cpu);
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	data = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!data) {
 		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		cpufreq_debug_enable_ratelimit();
 		unlock_policy_rwsem_write(cpu);
 		return -EINVAL;
 	}
@@ -1132,12 +1029,11 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
 	 * only need to unlink, put and exit
 	 */
 	if (unlikely(cpu != data->cpu)) {
-		dprintk("removing link\n");
+		pr_debug("removing link\n");
 		cpumask_clear_cpu(cpu, data->cpus);
 		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 		kobj = &sys_dev->kobj;
 		cpufreq_cpu_put(data);
-		cpufreq_debug_enable_ratelimit();
 		unlock_policy_rwsem_write(cpu);
 		sysfs_remove_link(kobj, "cpufreq");
 		return 0;
@@ -1170,7 +1066,7 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
 		for_each_cpu(j, data->cpus) {
 			if (j == cpu)
 				continue;
-			dprintk("removing link for cpu %u\n", j);
+			pr_debug("removing link for cpu %u\n", j);
 #ifdef CONFIG_HOTPLUG_CPU
 			strncpy(per_cpu(cpufreq_cpu_governor, j),
 				data->governor->name, CPUFREQ_NAME_LEN);
@@ -1199,21 +1095,35 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev)
 	 * not referenced anymore by anybody before we proceed with
 	 * unloading.
 	 */
-	dprintk("waiting for dropping of refcount\n");
+	pr_debug("waiting for dropping of refcount\n");
 	wait_for_completion(cmp);
-	dprintk("wait complete\n");
+	pr_debug("wait complete\n");
 
 	lock_policy_rwsem_write(cpu);
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(data);
 	unlock_policy_rwsem_write(cpu);
 
+#ifdef CONFIG_HOTPLUG_CPU
+	/* when the CPU which is the parent of the kobj is hotplugged
+	 * offline, check for siblings, and create cpufreq sysfs interface
+	 * and symlinks
+	 */
+	if (unlikely(cpumask_weight(data->cpus) > 1)) {
+		/* first sibling now owns the new sysfs dir */
+		cpumask_clear_cpu(cpu, data->cpus);
+		cpufreq_add_dev(get_cpu_sysdev(cpumask_first(data->cpus)));
+
+		/* finally remove our own symlink */
+		lock_policy_rwsem_write(cpu);
+		__cpufreq_remove_dev(sys_dev);
+	}
+#endif
+
 	free_cpumask_var(data->related_cpus);
 	free_cpumask_var(data->cpus);
 	kfree(data);
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 
-	cpufreq_debug_enable_ratelimit();
 	return 0;
 }
 
@@ -1239,7 +1149,7 @@ static void handle_update(struct work_struct *work)
 	struct cpufreq_policy *policy =
 		container_of(work, struct cpufreq_policy, update);
 	unsigned int cpu = policy->cpu;
-	dprintk("handle_update for cpu %u called\n", cpu);
+	pr_debug("handle_update for cpu %u called\n", cpu);
 	cpufreq_update_policy(cpu);
 }
 
@@ -1257,7 +1167,7 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,
 {
 	struct cpufreq_freqs freqs;
 
-	dprintk("Warning: CPU frequency out of sync: cpufreq and timing "
+	pr_debug("Warning: CPU frequency out of sync: cpufreq and timing "
 	       "core thinks of %u, is %u kHz.\n", old_freq, new_freq);
 
 	freqs.cpu = cpu;
@@ -1360,7 +1270,7 @@ static int cpufreq_bp_suspend(void)
 	int cpu = smp_processor_id();
 	struct cpufreq_policy *cpu_policy;
 
-	dprintk("suspending cpu %u\n", cpu);
+	pr_debug("suspending cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
 	cpu_policy = cpufreq_cpu_get(cpu);
@@ -1398,7 +1308,7 @@ static void cpufreq_bp_resume(void)
 	int cpu = smp_processor_id();
 	struct cpufreq_policy *cpu_policy;
 
-	dprintk("resuming cpu %u\n", cpu);
+	pr_debug("resuming cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
 	cpu_policy = cpufreq_cpu_get(cpu);
@@ -1510,7 +1420,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 {
 	int retval = -EINVAL;
 
-	dprintk("target for CPU %u: %u kHz, relation %u\n", policy->cpu,
+	pr_debug("target for CPU %u: %u kHz, relation %u\n", policy->cpu,
 		target_freq, relation);
 	if (cpu_online(policy->cpu) && cpufreq_driver->target)
 		retval = cpufreq_driver->target(policy, target_freq, relation);
@@ -1596,7 +1506,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	if (!try_module_get(policy->governor->owner))
 		return -EINVAL;
 
-	dprintk("__cpufreq_governor for CPU %u, event %u\n",
+	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
 						policy->cpu, event);
 	ret = policy->governor->governor(policy, event);
 
@@ -1697,8 +1607,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 {
 	int ret = 0;
 
-	cpufreq_debug_disable_ratelimit();
-	dprintk("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu,
+	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu,
 		policy->min, policy->max);
 
 	memcpy(&policy->cpuinfo, &data->cpuinfo,
@@ -1735,19 +1644,19 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 	data->min = policy->min;
 	data->max = policy->max;
 
-	dprintk("new min and max freqs are %u - %u kHz\n",
+	pr_debug("new min and max freqs are %u - %u kHz\n",
 					data->min, data->max);
 
 	if (cpufreq_driver->setpolicy) {
 		data->policy = policy->policy;
-		dprintk("setting range\n");
+		pr_debug("setting range\n");
 		ret = cpufreq_driver->setpolicy(policy);
 	} else {
 		if (policy->governor != data->governor) {
 			/* save old, working values */
 			struct cpufreq_governor *old_gov = data->governor;
 
-			dprintk("governor switch\n");
+			pr_debug("governor switch\n");
 
 			/* end old governor */
 			if (data->governor)
@@ -1757,7 +1666,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 			data->governor = policy->governor;
 			if (__cpufreq_governor(data, CPUFREQ_GOV_START)) {
 				/* new governor failed, so re-start old one */
-				dprintk("starting governor %s failed\n",
+				pr_debug("starting governor %s failed\n",
 							data->governor->name);
 				if (old_gov) {
 					data->governor = old_gov;
@@ -1769,12 +1678,11 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 			}
 			/* might be a policy change, too, so fall through */
 		}
-		dprintk("governor: change or update limits\n");
+		pr_debug("governor: change or update limits\n");
 		__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
 	}
 
 error_out:
-	cpufreq_debug_enable_ratelimit();
 	return ret;
 }
 
@@ -1801,7 +1709,7 @@ int cpufreq_update_policy(unsigned int cpu)
 		goto fail;
 	}
 
-	dprintk("updating policy for CPU %u\n", cpu);
+	pr_debug("updating policy for CPU %u\n", cpu);
 	memcpy(&policy, data, sizeof(struct cpufreq_policy));
 	policy.min = data->user_policy.min;
 	policy.max = data->user_policy.max;
@@ -1813,7 +1721,7 @@ int cpufreq_update_policy(unsigned int cpu)
 	if (cpufreq_driver->get) {
 		policy.cur = cpufreq_driver->get(cpu);
 		if (!data->cur) {
-			dprintk("Driver did not initialize current freq");
+			pr_debug("Driver did not initialize current freq");
 			data->cur = policy.cur;
 		} else {
 			if (data->cur != policy.cur)
@@ -1889,7 +1797,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	    ((!driver_data->setpolicy) && (!driver_data->target)))
 		return -EINVAL;
 
-	dprintk("trying to register driver %s\n", driver_data->name);
+	pr_debug("trying to register driver %s\n", driver_data->name);
 
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
@@ -1920,15 +1828,14 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 
 		/* if all ->init() calls failed, unregister */
 		if (ret) {
-			dprintk("no CPU initialized for driver %s\n",
+			pr_debug("no CPU initialized for driver %s\n",
 							driver_data->name);
 			goto err_sysdev_unreg;
 		}
 	}
 
 	register_hotcpu_notifier(&cpufreq_cpu_notifier);
-	dprintk("driver %s up and running\n", driver_data->name);
-	cpufreq_debug_enable_ratelimit();
+	pr_debug("driver %s up and running\n", driver_data->name);
 
 	return 0;
 err_sysdev_unreg:
@@ -1955,14 +1862,10 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 {
 	unsigned long flags;
 
-	cpufreq_debug_disable_ratelimit();
-
-	if (!cpufreq_driver || (driver != cpufreq_driver)) {
-		cpufreq_debug_enable_ratelimit();
+	if (!cpufreq_driver || (driver != cpufreq_driver))
 		return -EINVAL;
-	}
 
-	dprintk("unregistering driver %s\n", driver->name);
+	pr_debug("unregistering driver %s\n", driver->name);
 
 	sysdev_driver_unregister(&cpu_sysdev_class, &cpufreq_sysdev_driver);
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index 7e2e515087f..f13a8a9af6a 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -15,9 +15,6 @@
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg)
-
 
 static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 					unsigned int event)
@@ -25,7 +22,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 	switch (event) {
 	case CPUFREQ_GOV_START:
 	case CPUFREQ_GOV_LIMITS:
-		dprintk("setting to %u kHz because of event %u\n",
+		pr_debug("setting to %u kHz because of event %u\n",
 						policy->max, event);
 		__cpufreq_driver_target(policy, policy->max,
 						CPUFREQ_RELATION_H);
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index e6db5faf3eb..4c2eb512f2b 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -15,16 +15,13 @@
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg)
-
 static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 					unsigned int event)
 {
 	switch (event) {
 	case CPUFREQ_GOV_START:
 	case CPUFREQ_GOV_LIMITS:
-		dprintk("setting to %u kHz because of event %u\n",
+		pr_debug("setting to %u kHz because of event %u\n",
 							policy->min, event);
 		__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_L);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 00d73fc8e4e..b60a4c26368 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -165,17 +165,27 @@ static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
 	return -1;
 }
 
+/* should be called late in the CPU removal sequence so that the stats
+ * memory is still available in case someone tries to use it.
+ */
 static void cpufreq_stats_free_table(unsigned int cpu)
 {
 	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, cpu);
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	if (policy && policy->cpu == cpu)
-		sysfs_remove_group(&policy->kobj, &stats_attr_group);
 	if (stat) {
 		kfree(stat->time_in_state);
 		kfree(stat);
 	}
 	per_cpu(cpufreq_stats_table, cpu) = NULL;
+}
+
+/* must be called early in the CPU removal sequence (before
+ * cpufreq_remove_dev) so that policy is still valid.
+ */
+static void cpufreq_stats_free_sysfs(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	if (policy && policy->cpu == cpu)
+		sysfs_remove_group(&policy->kobj, &stats_attr_group);
 	if (policy)
 		cpufreq_cpu_put(policy);
 }
@@ -316,6 +326,9 @@ static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
 	case CPU_ONLINE_FROZEN:
 		cpufreq_update_policy(cpu);
 		break;
+	case CPU_DOWN_PREPARE:
+		cpufreq_stats_free_sysfs(cpu);
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		cpufreq_stats_free_table(cpu);
@@ -324,9 +337,10 @@ static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block cpufreq_stat_cpu_notifier __refdata =
-{
+/* priority=1 so this will get called before cpufreq_remove_dev */
+static struct notifier_block cpufreq_stat_cpu_notifier __refdata = {
 	.notifier_call = cpufreq_stat_cpu_callback,
+	.priority = 1,
 };
 
 static struct notifier_block notifier_policy_block = {
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 66d2d1d6c80..f231015904c 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -37,9 +37,6 @@ static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 static DEFINE_MUTEX(userspace_mutex);
 static int cpus_using_userspace_governor;
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "userspace", msg)
-
 /* keep track of frequency transitions */
 static int
 userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
@@ -50,7 +47,7 @@ userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	if (!per_cpu(cpu_is_managed, freq->cpu))
 		return 0;
 
-	dprintk("saving cpu_cur_freq of cpu %u to be %u kHz\n",
+	pr_debug("saving cpu_cur_freq of cpu %u to be %u kHz\n",
 			freq->cpu, freq->new);
 	per_cpu(cpu_cur_freq, freq->cpu) = freq->new;
 
@@ -73,7 +70,7 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 {
 	int ret = -EINVAL;
 
-	dprintk("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
+	pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
 	mutex_lock(&userspace_mutex);
 	if (!per_cpu(cpu_is_managed, policy->cpu))
@@ -134,7 +131,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 		per_cpu(cpu_max_freq, cpu) = policy->max;
 		per_cpu(cpu_cur_freq, cpu) = policy->cur;
 		per_cpu(cpu_set_freq, cpu) = policy->cur;
-		dprintk("managing cpu %u started "
+		pr_debug("managing cpu %u started "
 			"(%u - %u kHz, currently %u kHz)\n",
 				cpu,
 				per_cpu(cpu_min_freq, cpu),
@@ -156,12 +153,12 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 		per_cpu(cpu_min_freq, cpu) = 0;
 		per_cpu(cpu_max_freq, cpu) = 0;
 		per_cpu(cpu_set_freq, cpu) = 0;
-		dprintk("managing cpu %u stopped\n", cpu);
+		pr_debug("managing cpu %u stopped\n", cpu);
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_LIMITS:
 		mutex_lock(&userspace_mutex);
-		dprintk("limit event for cpu %u: %u - %u kHz, "
+		pr_debug("limit event for cpu %u: %u - %u kHz, "
 			"currently %u kHz, last set to %u kHz\n",
 			cpu, policy->min, policy->max,
 			per_cpu(cpu_cur_freq, cpu),
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 35a257dd4bb..35a257dd4bb 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index c587db472a7..c587db472a7 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 05432216e22..90431cb9280 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -14,9 +14,6 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg)
-
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
@@ -31,11 +28,11 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
 		unsigned int freq = table[i].frequency;
 		if (freq == CPUFREQ_ENTRY_INVALID) {
-			dprintk("table entry %u is invalid, skipping\n", i);
+			pr_debug("table entry %u is invalid, skipping\n", i);
 
 			continue;
 		}
-		dprintk("table entry %u: %u kHz, %u index\n",
+		pr_debug("table entry %u: %u kHz, %u index\n",
 					i, freq, table[i].index);
 		if (freq < min_freq)
 			min_freq = freq;
@@ -61,7 +58,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 	unsigned int i;
 	unsigned int count = 0;
 
-	dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n",
+	pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n",
 					policy->min, policy->max, policy->cpu);
 
 	if (!cpu_online(policy->cpu))
@@ -86,7 +83,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
 				     policy->cpuinfo.max_freq);
 
-	dprintk("verification lead to (%u - %u kHz) for cpu %u\n",
+	pr_debug("verification lead to (%u - %u kHz) for cpu %u\n",
 				policy->min, policy->max, policy->cpu);
 
 	return 0;
@@ -110,7 +107,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	};
 	unsigned int i;
 
-	dprintk("request for target %u kHz (relation: %u) for cpu %u\n",
+	pr_debug("request for target %u kHz (relation: %u) for cpu %u\n",
 					target_freq, relation, policy->cpu);
 
 	switch (relation) {
@@ -167,7 +164,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	} else
 		*index = optimal.index;
 
-	dprintk("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
+	pr_debug("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
 		table[*index].index);
 
 	return 0;
@@ -216,14 +213,14 @@ EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
 void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu)
 {
-	dprintk("setting show_table for cpu %u to %p\n", cpu, table);
+	pr_debug("setting show_table for cpu %u to %p\n", cpu, table);
 	per_cpu(cpufreq_show_table, cpu) = table;
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_attr);
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu)
 {
-	dprintk("clearing show_table for cpu %u\n", cpu);
+	pr_debug("clearing show_table for cpu %u\n", cpu);
 	per_cpu(cpufreq_show_table, cpu) = NULL;
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c
index 32974cf8423..ffe1f2c92ed 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/drivers/cpufreq/gx-suspmod.c
@@ -142,9 +142,6 @@ module_param(max_duration, int, 0444);
 #define POLICY_MIN_DIV 20
 
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"gx-suspmod", msg)
-
 /**
  * we can detect a core multipiler from dir0_lsb
  * from GX1 datasheet p.56,
@@ -191,7 +188,7 @@ static __init struct pci_dev *gx_detect_chipset(void)
 	/* check if CPU is a MediaGX or a Geode. */
 	if ((boot_cpu_data.x86_vendor != X86_VENDOR_NSC) &&
 	    (boot_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) {
-		dprintk("error: no MediaGX/Geode processor found!\n");
+		pr_debug("error: no MediaGX/Geode processor found!\n");
 		return NULL;
 	}
 
@@ -201,7 +198,7 @@ static __init struct pci_dev *gx_detect_chipset(void)
 			return gx_pci;
 	}
 
-	dprintk("error: no supported chipset found!\n");
+	pr_debug("error: no supported chipset found!\n");
 	return NULL;
 }
 
@@ -305,14 +302,14 @@ static void gx_set_cpuspeed(unsigned int khz)
 			break;
 		default:
 			local_irq_restore(flags);
-			dprintk("fatal: try to set unknown chipset.\n");
+			pr_debug("fatal: try to set unknown chipset.\n");
 			return;
 		}
 	} else {
 		suscfg = gx_params->pci_suscfg & ~(SUSMOD);
 		gx_params->off_duration = 0;
 		gx_params->on_duration = 0;
-		dprintk("suspend modulation disabled: cpu runs 100%% speed.\n");
+		pr_debug("suspend modulation disabled: cpu runs 100%% speed.\n");
 	}
 
 	gx_write_byte(PCI_MODOFF, gx_params->off_duration);
@@ -327,9 +324,9 @@ static void gx_set_cpuspeed(unsigned int khz)
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
-	dprintk("suspend modulation w/ duration of ON:%d us, OFF:%d us\n",
+	pr_debug("suspend modulation w/ duration of ON:%d us, OFF:%d us\n",
 		gx_params->on_duration * 32, gx_params->off_duration * 32);
-	dprintk("suspend modulation w/ clock speed: %d kHz.\n", freqs.new);
+	pr_debug("suspend modulation w/ clock speed: %d kHz.\n", freqs.new);
 }
 
 /****************************************************************
@@ -428,8 +425,8 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy)
 	stock_freq = maxfreq;
 	curfreq = gx_get_cpuspeed(0);
 
-	dprintk("cpu max frequency is %d.\n", maxfreq);
-	dprintk("cpu current frequency is %dkHz.\n", curfreq);
+	pr_debug("cpu max frequency is %d.\n", maxfreq);
+	pr_debug("cpu current frequency is %dkHz.\n", curfreq);
 
 	/* setup basic struct for cpufreq API */
 	policy->cpu = 0;
@@ -475,7 +472,7 @@ static int __init cpufreq_gx_init(void)
 	if (max_duration > 0xff)
 		max_duration = 0xff;
 
-	dprintk("geode suspend modulation available.\n");
+	pr_debug("geode suspend modulation available.\n");
 
 	params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL);
 	if (params == NULL)
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index cf48cdd6907..f47d26e2a13 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -77,9 +77,6 @@ static int scale_voltage;
 static int disable_acpi_c3;
 static int revid_errata;
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"longhaul", msg)
-
 
 /* Clock ratios multiplied by 10 */
 static int mults[32];
@@ -87,7 +84,6 @@ static int eblcr[32];
 static int longhaul_version;
 static struct cpufreq_frequency_table *longhaul_table;
 
-#ifdef CONFIG_CPU_FREQ_DEBUG
 static char speedbuffer[8];
 
 static char *print_speed(int speed)
@@ -106,7 +102,6 @@ static char *print_speed(int speed)
 
 	return speedbuffer;
 }
-#endif
 
 
 static unsigned int calc_speed(int mult)
@@ -275,7 +270,7 @@ static void longhaul_setstate(unsigned int table_index)
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
-	dprintk("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
+	pr_debug("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
 			fsb, mult/10, mult%10, print_speed(speed/1000));
 retry_loop:
 	preempt_disable();
@@ -460,12 +455,12 @@ static int __cpuinit longhaul_get_ranges(void)
 		break;
 	}
 
-	dprintk("MinMult:%d.%dx MaxMult:%d.%dx\n",
+	pr_debug("MinMult:%d.%dx MaxMult:%d.%dx\n",
 		 minmult/10, minmult%10, maxmult/10, maxmult%10);
 
 	highest_speed = calc_speed(maxmult);
 	lowest_speed = calc_speed(minmult);
-	dprintk("FSB:%dMHz  Lowest speed: %s   Highest speed:%s\n", fsb,
+	pr_debug("FSB:%dMHz  Lowest speed: %s   Highest speed:%s\n", fsb,
 		 print_speed(lowest_speed/1000),
 		 print_speed(highest_speed/1000));
 
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.h b/drivers/cpufreq/longhaul.h
index cbf48fbca88..cbf48fbca88 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.h
+++ b/drivers/cpufreq/longhaul.h
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/drivers/cpufreq/longrun.c
index d9f51367666..34ea359b370 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/drivers/cpufreq/longrun.c
@@ -15,9 +15,6 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"longrun", msg)
-
 static struct cpufreq_driver	longrun_driver;
 
 /**
@@ -40,14 +37,14 @@ static void __cpuinit longrun_get_policy(struct cpufreq_policy *policy)
 	u32 msr_lo, msr_hi;
 
 	rdmsr(MSR_TMTA_LONGRUN_FLAGS, msr_lo, msr_hi);
-	dprintk("longrun flags are %x - %x\n", msr_lo, msr_hi);
+	pr_debug("longrun flags are %x - %x\n", msr_lo, msr_hi);
 	if (msr_lo & 0x01)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
 	rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
-	dprintk("longrun ctrl is %x - %x\n", msr_lo, msr_hi);
+	pr_debug("longrun ctrl is %x - %x\n", msr_lo, msr_hi);
 	msr_lo &= 0x0000007F;
 	msr_hi &= 0x0000007F;
 
@@ -150,7 +147,7 @@ static unsigned int longrun_get(unsigned int cpu)
 		return 0;
 
 	cpuid(0x80860007, &eax, &ebx, &ecx, &edx);
-	dprintk("cpuid eax is %u\n", eax);
+	pr_debug("cpuid eax is %u\n", eax);
 
 	return eax * 1000;
 }
@@ -196,7 +193,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
 		rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi);
 		*high_freq = msr_lo * 1000; /* to kHz */
 
-		dprintk("longrun table interface told %u - %u kHz\n",
+		pr_debug("longrun table interface told %u - %u kHz\n",
 				*low_freq, *high_freq);
 
 		if (*low_freq > *high_freq)
@@ -207,7 +204,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
 	/* set the upper border to the value determined during TSC init */
 	*high_freq = (cpu_khz / 1000);
 	*high_freq = *high_freq * 1000;
-	dprintk("high frequency is %u kHz\n", *high_freq);
+	pr_debug("high frequency is %u kHz\n", *high_freq);
 
 	/* get current borders */
 	rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi);
@@ -233,7 +230,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
 		/* restore values */
 		wrmsr(MSR_TMTA_LONGRUN_CTRL, save_lo, save_hi);
 	}
-	dprintk("percentage is %u %%, freq is %u MHz\n", ecx, eax);
+	pr_debug("percentage is %u %%, freq is %u MHz\n", ecx, eax);
 
 	/* performance_pctg = (current_freq - low_freq)/(high_freq - low_freq)
 	 * eqals
@@ -249,7 +246,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
 	edx = ((eax - ebx) * 100) / (100 - ecx);
 	*low_freq = edx * 1000; /* back to kHz */
 
-	dprintk("low frequency is %u kHz\n", *low_freq);
+	pr_debug("low frequency is %u kHz\n", *low_freq);
 
 	if (*low_freq > *high_freq)
 		*low_freq = *high_freq;
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.c b/drivers/cpufreq/mperf.c
index 911e193018a..911e193018a 100644
--- a/arch/x86/kernel/cpu/cpufreq/mperf.c
+++ b/drivers/cpufreq/mperf.c
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.h b/drivers/cpufreq/mperf.h
index 5dbf2950dc2..5dbf2950dc2 100644
--- a/arch/x86/kernel/cpu/cpufreq/mperf.h
+++ b/drivers/cpufreq/mperf.h
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 52c93648e49..6be3e0760c2 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -35,8 +35,6 @@
 #include "speedstep-lib.h"
 
 #define PFX	"p4-clockmod: "
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"p4-clockmod", msg)
 
 /*
  * Duty Cycle (3bits), note DC_DISABLE is not specified in
@@ -66,7 +64,7 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate)
 	rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h);
 
 	if (l & 0x01)
-		dprintk("CPU#%d currently thermal throttled\n", cpu);
+		pr_debug("CPU#%d currently thermal throttled\n", cpu);
 
 	if (has_N44_O17_errata[cpu] &&
 	    (newstate == DC_25PT || newstate == DC_DFLT))
@@ -74,10 +72,10 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate)
 
 	rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h);
 	if (newstate == DC_DISABLE) {
-		dprintk("CPU#%d disabling modulation\n", cpu);
+		pr_debug("CPU#%d disabling modulation\n", cpu);
 		wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l & ~(1<<4), h);
 	} else {
-		dprintk("CPU#%d setting duty cycle to %d%%\n",
+		pr_debug("CPU#%d setting duty cycle to %d%%\n",
 			cpu, ((125 * newstate) / 10));
 		/* bits 63 - 5	: reserved
 		 * bit  4	: enable/disable
@@ -217,7 +215,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	case 0x0f11:
 	case 0x0f12:
 		has_N44_O17_errata[policy->cpu] = 1;
-		dprintk("has errata -- disabling low frequencies\n");
+		pr_debug("has errata -- disabling low frequencies\n");
 	}
 
 	if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D &&
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 755a31e0f5b..7b0603eb012 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -39,7 +39,7 @@
 
 #include <acpi/processor.h>
 
-#define PCC_VERSION 	"1.00.00"
+#define PCC_VERSION	"1.10.00"
 #define POLL_LOOPS 	300
 
 #define CMD_COMPLETE 	0x1
@@ -48,9 +48,6 @@
 
 #define BUF_SZ		4
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER,	\
-					     "pcc-cpufreq", msg)
-
 struct pcc_register_resource {
 	u8 descriptor;
 	u16 length;
@@ -102,7 +99,7 @@ static struct acpi_generic_address doorbell;
 static u64 doorbell_preserve;
 static u64 doorbell_write;
 
-static u8 OSC_UUID[16] = {0x63, 0x9B, 0x2C, 0x9F, 0x70, 0x91, 0x49, 0x1f,
+static u8 OSC_UUID[16] = {0x9F, 0x2C, 0x9B, 0x63, 0x91, 0x70, 0x1f, 0x49,
 			  0xBB, 0x4F, 0xA5, 0x98, 0x2F, 0xA1, 0xB5, 0x46};
 
 struct pcc_cpu {
@@ -152,7 +149,7 @@ static unsigned int pcc_get_freq(unsigned int cpu)
 
 	spin_lock(&pcc_lock);
 
-	dprintk("get: get_freq for CPU %d\n", cpu);
+	pr_debug("get: get_freq for CPU %d\n", cpu);
 	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
 
 	input_buffer = 0x1;
@@ -170,7 +167,7 @@ static unsigned int pcc_get_freq(unsigned int cpu)
 
 	status = ioread16(&pcch_hdr->status);
 	if (status != CMD_COMPLETE) {
-		dprintk("get: FAILED: for CPU %d, status is %d\n",
+		pr_debug("get: FAILED: for CPU %d, status is %d\n",
 			cpu, status);
 		goto cmd_incomplete;
 	}
@@ -178,14 +175,14 @@ static unsigned int pcc_get_freq(unsigned int cpu)
 	curr_freq = (((ioread32(&pcch_hdr->nominal) * (output_buffer & 0xff))
 			/ 100) * 1000);
 
-	dprintk("get: SUCCESS: (virtual) output_offset for cpu %d is "
-		"0x%x, contains a value of: 0x%x. Speed is: %d MHz\n",
+	pr_debug("get: SUCCESS: (virtual) output_offset for cpu %d is "
+		"0x%p, contains a value of: 0x%x. Speed is: %d MHz\n",
 		cpu, (pcch_virt_addr + pcc_cpu_data->output_offset),
 		output_buffer, curr_freq);
 
 	freq_limit = (output_buffer >> 8) & 0xff;
 	if (freq_limit != 0xff) {
-		dprintk("get: frequency for cpu %d is being temporarily"
+		pr_debug("get: frequency for cpu %d is being temporarily"
 			" capped at %d\n", cpu, curr_freq);
 	}
 
@@ -212,8 +209,8 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy,
 	cpu = policy->cpu;
 	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
 
-	dprintk("target: CPU %d should go to target freq: %d "
-		"(virtual) input_offset is 0x%x\n",
+	pr_debug("target: CPU %d should go to target freq: %d "
+		"(virtual) input_offset is 0x%p\n",
 		cpu, target_freq,
 		(pcch_virt_addr + pcc_cpu_data->input_offset));
 
@@ -234,14 +231,14 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy,
 
 	status = ioread16(&pcch_hdr->status);
 	if (status != CMD_COMPLETE) {
-		dprintk("target: FAILED for cpu %d, with status: 0x%x\n",
+		pr_debug("target: FAILED for cpu %d, with status: 0x%x\n",
 			cpu, status);
 		goto cmd_incomplete;
 	}
 	iowrite16(0, &pcch_hdr->status);
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-	dprintk("target: was SUCCESSFUL for cpu %d\n", cpu);
+	pr_debug("target: was SUCCESSFUL for cpu %d\n", cpu);
 	spin_unlock(&pcc_lock);
 
 	return 0;
@@ -293,7 +290,7 @@ static int pcc_get_offset(int cpu)
 	memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
 	memset_io((pcch_virt_addr + pcc_cpu_data->output_offset), 0, BUF_SZ);
 
-	dprintk("pcc_get_offset: for CPU %d: pcc_cpu_data "
+	pr_debug("pcc_get_offset: for CPU %d: pcc_cpu_data "
 		"input_offset: 0x%x, pcc_cpu_data output_offset: 0x%x\n",
 		cpu, pcc_cpu_data->input_offset, pcc_cpu_data->output_offset);
 out_free:
@@ -410,7 +407,7 @@ static int __init pcc_cpufreq_probe(void)
 	if (ACPI_SUCCESS(status)) {
 		ret = pcc_cpufreq_do_osc(&osc_handle);
 		if (ret)
-			dprintk("probe: _OSC evaluation did not succeed\n");
+			pr_debug("probe: _OSC evaluation did not succeed\n");
 		/* Firmware's use of _OSC is optional */
 		ret = 0;
 	}
@@ -433,7 +430,7 @@ static int __init pcc_cpufreq_probe(void)
 
 	mem_resource = (struct pcc_memory_resource *)member->buffer.pointer;
 
-	dprintk("probe: mem_resource descriptor: 0x%x,"
+	pr_debug("probe: mem_resource descriptor: 0x%x,"
 		" length: %d, space_id: %d, resource_usage: %d,"
 		" type_specific: %d, granularity: 0x%llx,"
 		" minimum: 0x%llx, maximum: 0x%llx,"
@@ -453,13 +450,13 @@ static int __init pcc_cpufreq_probe(void)
 	pcch_virt_addr = ioremap_nocache(mem_resource->minimum,
 					mem_resource->address_length);
 	if (pcch_virt_addr == NULL) {
-		dprintk("probe: could not map shared mem region\n");
+		pr_debug("probe: could not map shared mem region\n");
 		goto out_free;
 	}
 	pcch_hdr = pcch_virt_addr;
 
-	dprintk("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr);
-	dprintk("probe: PCCH header is at physical address: 0x%llx,"
+	pr_debug("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr);
+	pr_debug("probe: PCCH header is at physical address: 0x%llx,"
 		" signature: 0x%x, length: %d bytes, major: %d, minor: %d,"
 		" supported features: 0x%x, command field: 0x%x,"
 		" status field: 0x%x, nominal latency: %d us\n",
@@ -469,7 +466,7 @@ static int __init pcc_cpufreq_probe(void)
 		ioread16(&pcch_hdr->command), ioread16(&pcch_hdr->status),
 		ioread32(&pcch_hdr->latency));
 
-	dprintk("probe: min time between commands: %d us,"
+	pr_debug("probe: min time between commands: %d us,"
 		" max time between commands: %d us,"
 		" nominal CPU frequency: %d MHz,"
 		" minimum CPU frequency: %d MHz,"
@@ -494,7 +491,7 @@ static int __init pcc_cpufreq_probe(void)
 	doorbell.access_width = 64;
 	doorbell.address = reg_resource->address;
 
-	dprintk("probe: doorbell: space_id is %d, bit_width is %d, "
+	pr_debug("probe: doorbell: space_id is %d, bit_width is %d, "
 		"bit_offset is %d, access_width is %d, address is 0x%llx\n",
 		doorbell.space_id, doorbell.bit_width, doorbell.bit_offset,
 		doorbell.access_width, reg_resource->address);
@@ -515,7 +512,7 @@ static int __init pcc_cpufreq_probe(void)
 
 	doorbell_write = member->integer.value;
 
-	dprintk("probe: doorbell_preserve: 0x%llx,"
+	pr_debug("probe: doorbell_preserve: 0x%llx,"
 		" doorbell_write: 0x%llx\n",
 		doorbell_preserve, doorbell_write);
 
@@ -550,7 +547,7 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	result = pcc_get_offset(cpu);
 	if (result) {
-		dprintk("init: PCCP evaluation failed\n");
+		pr_debug("init: PCCP evaluation failed\n");
 		goto out;
 	}
 
@@ -561,12 +558,12 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cur = pcc_get_freq(cpu);
 
 	if (!policy->cur) {
-		dprintk("init: Unable to get current CPU frequency\n");
+		pr_debug("init: Unable to get current CPU frequency\n");
 		result = -EINVAL;
 		goto out;
 	}
 
-	dprintk("init: policy->max is %d, policy->min is %d\n",
+	pr_debug("init: policy->max is %d, policy->min is %d\n",
 		policy->max, policy->min);
 out:
 	return result;
@@ -597,7 +594,7 @@ static int __init pcc_cpufreq_init(void)
 
 	ret = pcc_cpufreq_probe();
 	if (ret) {
-		dprintk("pcc_cpufreq_init: PCCH evaluation failed\n");
+		pr_debug("pcc_cpufreq_init: PCCH evaluation failed\n");
 		return ret;
 	}
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index b3379d6a5c5..b3379d6a5c5 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 4a45fd6e41b..d71d9f37235 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -68,7 +68,6 @@ union powernow_acpi_control_t {
 };
 #endif
 
-#ifdef CONFIG_CPU_FREQ_DEBUG
 /* divide by 1000 to get VCore voltage in V. */
 static const int mobile_vid_table[32] = {
     2000, 1950, 1900, 1850, 1800, 1750, 1700, 1650,
@@ -76,7 +75,6 @@ static const int mobile_vid_table[32] = {
     1275, 1250, 1225, 1200, 1175, 1150, 1125, 1100,
     1075, 1050, 1025, 1000, 975, 950, 925, 0,
 };
-#endif
 
 /* divide by 10 to get FID. */
 static const int fid_codes[32] = {
@@ -103,9 +101,6 @@ static unsigned int fsb;
 static unsigned int latency;
 static char have_a0;
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"powernow-k7", msg)
-
 static int check_fsb(unsigned int fsbspeed)
 {
 	int delta;
@@ -209,7 +204,7 @@ static int get_ranges(unsigned char *pst)
 		vid = *pst++;
 		powernow_table[j].index |= (vid << 8); /* upper 8 bits */
 
-		dprintk("   FID: 0x%x (%d.%dx [%dMHz])  "
+		pr_debug("   FID: 0x%x (%d.%dx [%dMHz])  "
 			 "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10,
 			 fid_codes[fid] % 10, speed/1000, vid,
 			 mobile_vid_table[vid]/1000,
@@ -367,7 +362,7 @@ static int powernow_acpi_init(void)
 		unsigned int speed, speed_mhz;
 
 		pc.val = (unsigned long) state->control;
-		dprintk("acpi:  P%d: %d MHz %d mW %d uS control %08x SGTC %d\n",
+		pr_debug("acpi:  P%d: %d MHz %d mW %d uS control %08x SGTC %d\n",
 			 i,
 			 (u32) state->core_frequency,
 			 (u32) state->power,
@@ -401,7 +396,7 @@ static int powernow_acpi_init(void)
 				invalidate_entry(i);
 		}
 
-		dprintk("   FID: 0x%x (%d.%dx [%dMHz])  "
+		pr_debug("   FID: 0x%x (%d.%dx [%dMHz])  "
 			 "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10,
 			 fid_codes[fid] % 10, speed_mhz, vid,
 			 mobile_vid_table[vid]/1000,
@@ -409,7 +404,7 @@ static int powernow_acpi_init(void)
 
 		if (state->core_frequency != speed_mhz) {
 			state->core_frequency = speed_mhz;
-			dprintk("   Corrected ACPI frequency to %d\n",
+			pr_debug("   Corrected ACPI frequency to %d\n",
 				speed_mhz);
 		}
 
@@ -453,8 +448,8 @@ static int powernow_acpi_init(void)
 
 static void print_pst_entry(struct pst_s *pst, unsigned int j)
 {
-	dprintk("PST:%d (@%p)\n", j, pst);
-	dprintk(" cpuid: 0x%x  fsb: %d  maxFID: 0x%x  startvid: 0x%x\n",
+	pr_debug("PST:%d (@%p)\n", j, pst);
+	pr_debug(" cpuid: 0x%x  fsb: %d  maxFID: 0x%x  startvid: 0x%x\n",
 		pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid);
 }
 
@@ -474,20 +469,20 @@ static int powernow_decode_bios(int maxfid, int startvid)
 		p = phys_to_virt(i);
 
 		if (memcmp(p, "AMDK7PNOW!",  10) == 0) {
-			dprintk("Found PSB header at %p\n", p);
+			pr_debug("Found PSB header at %p\n", p);
 			psb = (struct psb_s *) p;
-			dprintk("Table version: 0x%x\n", psb->tableversion);
+			pr_debug("Table version: 0x%x\n", psb->tableversion);
 			if (psb->tableversion != 0x12) {
 				printk(KERN_INFO PFX "Sorry, only v1.2 tables"
 						" supported right now\n");
 				return -ENODEV;
 			}
 
-			dprintk("Flags: 0x%x\n", psb->flags);
+			pr_debug("Flags: 0x%x\n", psb->flags);
 			if ((psb->flags & 1) == 0)
-				dprintk("Mobile voltage regulator\n");
+				pr_debug("Mobile voltage regulator\n");
 			else
-				dprintk("Desktop voltage regulator\n");
+				pr_debug("Desktop voltage regulator\n");
 
 			latency = psb->settlingtime;
 			if (latency < 100) {
@@ -497,9 +492,9 @@ static int powernow_decode_bios(int maxfid, int startvid)
 						"Correcting.\n", latency);
 				latency = 100;
 			}
-			dprintk("Settling Time: %d microseconds.\n",
+			pr_debug("Settling Time: %d microseconds.\n",
 					psb->settlingtime);
-			dprintk("Has %d PST tables. (Only dumping ones "
+			pr_debug("Has %d PST tables. (Only dumping ones "
 					"relevant to this CPU).\n",
 					psb->numpst);
 
@@ -650,7 +645,7 @@ static int __cpuinit powernow_cpu_init(struct cpufreq_policy *policy)
 		printk(KERN_WARNING PFX "can not determine bus frequency\n");
 		return -EINVAL;
 	}
-	dprintk("FSB: %3dMHz\n", fsb/1000);
+	pr_debug("FSB: %3dMHz\n", fsb/1000);
 
 	if (dmi_check_system(powernow_dmi_table) || acpi_force) {
 		printk(KERN_INFO PFX "PSB/PST known to be broken.  "
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.h b/drivers/cpufreq/powernow-k7.h
index 35fb4eaf6e1..35fb4eaf6e1 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.h
+++ b/drivers/cpufreq/powernow-k7.h
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 2368e38327b..83479b6fb9a 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -139,7 +139,7 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
 	}
 	do {
 		if (i++ > 10000) {
-			dprintk("detected change pending stuck\n");
+			pr_debug("detected change pending stuck\n");
 			return 1;
 		}
 		rdmsr(MSR_FIDVID_STATUS, lo, hi);
@@ -176,7 +176,7 @@ static void fidvid_msr_init(void)
 	fid = lo & MSR_S_LO_CURRENT_FID;
 	lo = fid | (vid << MSR_C_LO_VID_SHIFT);
 	hi = MSR_C_HI_STP_GNT_BENIGN;
-	dprintk("cpu%d, init lo 0x%x, hi 0x%x\n", smp_processor_id(), lo, hi);
+	pr_debug("cpu%d, init lo 0x%x, hi 0x%x\n", smp_processor_id(), lo, hi);
 	wrmsr(MSR_FIDVID_CTL, lo, hi);
 }
 
@@ -196,7 +196,7 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid)
 	lo |= (data->currvid << MSR_C_LO_VID_SHIFT);
 	lo |= MSR_C_LO_INIT_FID_VID;
 
-	dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n",
+	pr_debug("writing fid 0x%x, lo 0x%x, hi 0x%x\n",
 		fid, lo, data->plllock * PLL_LOCK_CONVERSION);
 
 	do {
@@ -244,7 +244,7 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid)
 	lo |= (vid << MSR_C_LO_VID_SHIFT);
 	lo |= MSR_C_LO_INIT_FID_VID;
 
-	dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n",
+	pr_debug("writing vid 0x%x, lo 0x%x, hi 0x%x\n",
 		vid, lo, STOP_GRANT_5NS);
 
 	do {
@@ -325,7 +325,7 @@ static int transition_fid_vid(struct powernow_k8_data *data,
 		return 1;
 	}
 
-	dprintk("transitioned (cpu%d): new fid 0x%x, vid 0x%x\n",
+	pr_debug("transitioned (cpu%d): new fid 0x%x, vid 0x%x\n",
 		smp_processor_id(), data->currfid, data->currvid);
 
 	return 0;
@@ -339,7 +339,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
 	u32 savefid = data->currfid;
 	u32 maxvid, lo, rvomult = 1;
 
-	dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, "
+	pr_debug("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, "
 		"reqvid 0x%x, rvo 0x%x\n",
 		smp_processor_id(),
 		data->currfid, data->currvid, reqvid, data->rvo);
@@ -349,12 +349,12 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
 	rvosteps *= rvomult;
 	rdmsr(MSR_FIDVID_STATUS, lo, maxvid);
 	maxvid = 0x1f & (maxvid >> 16);
-	dprintk("ph1 maxvid=0x%x\n", maxvid);
+	pr_debug("ph1 maxvid=0x%x\n", maxvid);
 	if (reqvid < maxvid) /* lower numbers are higher voltages */
 		reqvid = maxvid;
 
 	while (data->currvid > reqvid) {
-		dprintk("ph1: curr 0x%x, req vid 0x%x\n",
+		pr_debug("ph1: curr 0x%x, req vid 0x%x\n",
 			data->currvid, reqvid);
 		if (decrease_vid_code_by_step(data, reqvid, data->vidmvs))
 			return 1;
@@ -365,7 +365,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
 		if (data->currvid == maxvid) {
 			rvosteps = 0;
 		} else {
-			dprintk("ph1: changing vid for rvo, req 0x%x\n",
+			pr_debug("ph1: changing vid for rvo, req 0x%x\n",
 				data->currvid - 1);
 			if (decrease_vid_code_by_step(data, data->currvid-1, 1))
 				return 1;
@@ -382,7 +382,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
 		return 1;
 	}
 
-	dprintk("ph1 complete, currfid 0x%x, currvid 0x%x\n",
+	pr_debug("ph1 complete, currfid 0x%x, currvid 0x%x\n",
 		data->currfid, data->currvid);
 
 	return 0;
@@ -400,7 +400,7 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
 		return 0;
 	}
 
-	dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, "
+	pr_debug("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, "
 		"reqfid 0x%x\n",
 		smp_processor_id(),
 		data->currfid, data->currvid, reqfid);
@@ -457,7 +457,7 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
 		return 1;
 	}
 
-	dprintk("ph2 complete, currfid 0x%x, currvid 0x%x\n",
+	pr_debug("ph2 complete, currfid 0x%x, currvid 0x%x\n",
 		data->currfid, data->currvid);
 
 	return 0;
@@ -470,7 +470,7 @@ static int core_voltage_post_transition(struct powernow_k8_data *data,
 	u32 savefid = data->currfid;
 	u32 savereqvid = reqvid;
 
-	dprintk("ph3 (cpu%d): starting, currfid 0x%x, currvid 0x%x\n",
+	pr_debug("ph3 (cpu%d): starting, currfid 0x%x, currvid 0x%x\n",
 		smp_processor_id(),
 		data->currfid, data->currvid);
 
@@ -498,17 +498,17 @@ static int core_voltage_post_transition(struct powernow_k8_data *data,
 		return 1;
 
 	if (savereqvid != data->currvid) {
-		dprintk("ph3 failed, currvid 0x%x\n", data->currvid);
+		pr_debug("ph3 failed, currvid 0x%x\n", data->currvid);
 		return 1;
 	}
 
 	if (savefid != data->currfid) {
-		dprintk("ph3 failed, currfid changed 0x%x\n",
+		pr_debug("ph3 failed, currfid changed 0x%x\n",
 			data->currfid);
 		return 1;
 	}
 
-	dprintk("ph3 complete, currfid 0x%x, currvid 0x%x\n",
+	pr_debug("ph3 complete, currfid 0x%x, currvid 0x%x\n",
 		data->currfid, data->currvid);
 
 	return 0;
@@ -707,7 +707,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 		return -EIO;
 	}
 
-	dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
+	pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
 	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
@@ -717,7 +717,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 		    (pst[j].vid == data->currvid))
 			return 0;
 
-	dprintk("currfid/vid do not match PST, ignoring\n");
+	pr_debug("currfid/vid do not match PST, ignoring\n");
 	return 0;
 }
 
@@ -739,36 +739,36 @@ static int find_psb_table(struct powernow_k8_data *data)
 		if (memcmp(psb, PSB_ID_STRING, PSB_ID_STRING_LEN) != 0)
 			continue;
 
-		dprintk("found PSB header at 0x%p\n", psb);
+		pr_debug("found PSB header at 0x%p\n", psb);
 
-		dprintk("table vers: 0x%x\n", psb->tableversion);
+		pr_debug("table vers: 0x%x\n", psb->tableversion);
 		if (psb->tableversion != PSB_VERSION_1_4) {
 			printk(KERN_ERR FW_BUG PFX "PSB table is not v1.4\n");
 			return -ENODEV;
 		}
 
-		dprintk("flags: 0x%x\n", psb->flags1);
+		pr_debug("flags: 0x%x\n", psb->flags1);
 		if (psb->flags1) {
 			printk(KERN_ERR FW_BUG PFX "unknown flags\n");
 			return -ENODEV;
 		}
 
 		data->vstable = psb->vstable;
-		dprintk("voltage stabilization time: %d(*20us)\n",
+		pr_debug("voltage stabilization time: %d(*20us)\n",
 				data->vstable);
 
-		dprintk("flags2: 0x%x\n", psb->flags2);
+		pr_debug("flags2: 0x%x\n", psb->flags2);
 		data->rvo = psb->flags2 & 3;
 		data->irt = ((psb->flags2) >> 2) & 3;
 		mvs = ((psb->flags2) >> 4) & 3;
 		data->vidmvs = 1 << mvs;
 		data->batps = ((psb->flags2) >> 6) & 3;
 
-		dprintk("ramp voltage offset: %d\n", data->rvo);
-		dprintk("isochronous relief time: %d\n", data->irt);
-		dprintk("maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs);
+		pr_debug("ramp voltage offset: %d\n", data->rvo);
+		pr_debug("isochronous relief time: %d\n", data->irt);
+		pr_debug("maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs);
 
-		dprintk("numpst: 0x%x\n", psb->num_tables);
+		pr_debug("numpst: 0x%x\n", psb->num_tables);
 		cpst = psb->num_tables;
 		if ((psb->cpuid == 0x00000fc0) ||
 		    (psb->cpuid == 0x00000fe0)) {
@@ -783,13 +783,13 @@ static int find_psb_table(struct powernow_k8_data *data)
 		}
 
 		data->plllock = psb->plllocktime;
-		dprintk("plllocktime: 0x%x (units 1us)\n", psb->plllocktime);
-		dprintk("maxfid: 0x%x\n", psb->maxfid);
-		dprintk("maxvid: 0x%x\n", psb->maxvid);
+		pr_debug("plllocktime: 0x%x (units 1us)\n", psb->plllocktime);
+		pr_debug("maxfid: 0x%x\n", psb->maxfid);
+		pr_debug("maxvid: 0x%x\n", psb->maxvid);
 		maxvid = psb->maxvid;
 
 		data->numps = psb->numps;
-		dprintk("numpstates: 0x%x\n", data->numps);
+		pr_debug("numpstates: 0x%x\n", data->numps);
 		return fill_powernow_table(data,
 				(struct pst_s *)(psb+1), maxvid);
 	}
@@ -834,13 +834,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	u64 control, status;
 
 	if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
-		dprintk("register performance failed: bad ACPI data\n");
+		pr_debug("register performance failed: bad ACPI data\n");
 		return -EIO;
 	}
 
 	/* verify the data contained in the ACPI structures */
 	if (data->acpi_data.state_count <= 1) {
-		dprintk("No ACPI P-States\n");
+		pr_debug("No ACPI P-States\n");
 		goto err_out;
 	}
 
@@ -849,7 +849,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
 	    (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
-		dprintk("Invalid control/status registers (%x - %x)\n",
+		pr_debug("Invalid control/status registers (%llx - %llx)\n",
 			control, status);
 		goto err_out;
 	}
@@ -858,7 +858,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
 		* (data->acpi_data.state_count + 1)), GFP_KERNEL);
 	if (!powernow_table) {
-		dprintk("powernow_table memory alloc failure\n");
+		pr_debug("powernow_table memory alloc failure\n");
 		goto err_out;
 	}
 
@@ -928,7 +928,7 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		}
 		rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
 		if (!(hi & HW_PSTATE_VALID_MASK)) {
-			dprintk("invalid pstate %d, ignoring\n", index);
+			pr_debug("invalid pstate %d, ignoring\n", index);
 			invalidate_entry(powernow_table, i);
 			continue;
 		}
@@ -968,7 +968,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 			vid = (control >> VID_SHIFT) & VID_MASK;
 		}
 
-		dprintk("   %d : fid 0x%x, vid 0x%x\n", i, fid, vid);
+		pr_debug("   %d : fid 0x%x, vid 0x%x\n", i, fid, vid);
 
 		index = fid | (vid<<8);
 		powernow_table[i].index = index;
@@ -978,7 +978,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 
 		/* verify frequency is OK */
 		if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) {
-			dprintk("invalid freq %u kHz, ignoring\n", freq);
+			pr_debug("invalid freq %u kHz, ignoring\n", freq);
 			invalidate_entry(powernow_table, i);
 			continue;
 		}
@@ -986,7 +986,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 		/* verify voltage is OK -
 		 * BIOSs are using "off" to indicate invalid */
 		if (vid == VID_OFF) {
-			dprintk("invalid vid %u, ignoring\n", vid);
+			pr_debug("invalid vid %u, ignoring\n", vid);
 			invalidate_entry(powernow_table, i);
 			continue;
 		}
@@ -1047,7 +1047,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	int res, i;
 	struct cpufreq_freqs freqs;
 
-	dprintk("cpu %d transition to index %u\n", smp_processor_id(), index);
+	pr_debug("cpu %d transition to index %u\n", smp_processor_id(), index);
 
 	/* fid/vid correctness check for k8 */
 	/* fid are the lower 8 bits of the index we stored into
@@ -1057,18 +1057,18 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	fid = data->powernow_table[index].index & 0xFF;
 	vid = (data->powernow_table[index].index & 0xFF00) >> 8;
 
-	dprintk("table matched fid 0x%x, giving vid 0x%x\n", fid, vid);
+	pr_debug("table matched fid 0x%x, giving vid 0x%x\n", fid, vid);
 
 	if (query_current_values_with_pending_wait(data))
 		return 1;
 
 	if ((data->currvid == vid) && (data->currfid == fid)) {
-		dprintk("target matches current values (fid 0x%x, vid 0x%x)\n",
+		pr_debug("target matches current values (fid 0x%x, vid 0x%x)\n",
 			fid, vid);
 		return 0;
 	}
 
-	dprintk("cpu %d, changing to fid 0x%x, vid 0x%x\n",
+	pr_debug("cpu %d, changing to fid 0x%x, vid 0x%x\n",
 		smp_processor_id(), fid, vid);
 	freqs.old = find_khz_freq_from_fid(data->currfid);
 	freqs.new = find_khz_freq_from_fid(fid);
@@ -1096,7 +1096,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data,
 	int res, i;
 	struct cpufreq_freqs freqs;
 
-	dprintk("cpu %d transition to index %u\n", smp_processor_id(), index);
+	pr_debug("cpu %d transition to index %u\n", smp_processor_id(), index);
 
 	/* get MSR index for hardware pstate transition */
 	pstate = index & HW_PSTATE_MASK;
@@ -1156,14 +1156,14 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 		goto err_out;
 	}
 
-	dprintk("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n",
+	pr_debug("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n",
 		pol->cpu, targfreq, pol->min, pol->max, relation);
 
 	if (query_current_values_with_pending_wait(data))
 		goto err_out;
 
 	if (cpu_family != CPU_HW_PSTATE) {
-		dprintk("targ: curr fid 0x%x, vid 0x%x\n",
+		pr_debug("targ: curr fid 0x%x, vid 0x%x\n",
 		data->currfid, data->currvid);
 
 		if ((checkvid != data->currvid) ||
@@ -1319,7 +1319,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 				data->currpstate);
 	else
 		pol->cur = find_khz_freq_from_fid(data->currfid);
-	dprintk("policy current frequency %d kHz\n", pol->cur);
+	pr_debug("policy current frequency %d kHz\n", pol->cur);
 
 	/* min/max the cpu is capable of */
 	if (cpufreq_frequency_table_cpuinfo(pol, data->powernow_table)) {
@@ -1337,10 +1337,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu);
 
 	if (cpu_family == CPU_HW_PSTATE)
-		dprintk("cpu_init done, current pstate 0x%x\n",
+		pr_debug("cpu_init done, current pstate 0x%x\n",
 				data->currpstate);
 	else
-		dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n",
+		pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
 			data->currfid, data->currvid);
 
 	per_cpu(powernow_data, pol->cpu) = data;
@@ -1586,7 +1586,7 @@ static int __cpuinit powernowk8_init(void)
 /* driver entry point for term */
 static void __exit powernowk8_exit(void)
 {
-	dprintk("exit\n");
+	pr_debug("exit\n");
 
 	if (boot_cpu_has(X86_FEATURE_CPB)) {
 		msrs_free(msrs);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/drivers/cpufreq/powernow-k8.h
index df3529b1c02..3744d26cdc2 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/drivers/cpufreq/powernow-k8.h
@@ -211,8 +211,6 @@ struct pst_s {
 	u8 vid;
 };
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k8", msg)
-
 static int core_voltage_pre_transition(struct powernow_k8_data *data,
 	u32 reqvid, u32 regfid);
 static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid);
diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 435a996a613..1e205e6b172 100644
--- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -29,8 +29,6 @@
 
 static __u8 __iomem *cpuctl;
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"sc520_freq", msg)
 #define PFX "sc520_freq: "
 
 static struct cpufreq_frequency_table sc520_freq_table[] = {
@@ -66,7 +64,7 @@ static void sc520_freq_set_cpu_state(unsigned int state)
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
-	dprintk("attempting to set frequency to %i kHz\n",
+	pr_debug("attempting to set frequency to %i kHz\n",
 			sc520_freq_table[state].frequency);
 
 	local_irq_disable();
@@ -161,7 +159,7 @@ static int __init sc520_freq_init(void)
 	/* Test if we have the right hardware */
 	if (c->x86_vendor != X86_VENDOR_AMD ||
 	    c->x86 != 4 || c->x86_model != 9) {
-		dprintk("no Elan SC520 processor found!\n");
+		pr_debug("no Elan SC520 processor found!\n");
 		return -ENODEV;
 	}
 	cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 9b1ff37de46..6ea3455def2 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -29,9 +29,6 @@
 #define PFX		"speedstep-centrino: "
 #define MAINTAINER	"cpufreq@vger.kernel.org"
 
-#define dprintk(msg...) \
-	cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg)
-
 #define INTEL_MSR_RANGE	(0xffff)
 
 struct cpu_id
@@ -244,7 +241,7 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy)
 
 	if (model->cpu_id == NULL) {
 		/* No match at all */
-		dprintk("no support for CPU model \"%s\": "
+		pr_debug("no support for CPU model \"%s\": "
 		       "send /proc/cpuinfo to " MAINTAINER "\n",
 		       cpu->x86_model_id);
 		return -ENOENT;
@@ -252,15 +249,15 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy)
 
 	if (model->op_points == NULL) {
 		/* Matched a non-match */
-		dprintk("no table support for CPU model \"%s\"\n",
+		pr_debug("no table support for CPU model \"%s\"\n",
 		       cpu->x86_model_id);
-		dprintk("try using the acpi-cpufreq driver\n");
+		pr_debug("try using the acpi-cpufreq driver\n");
 		return -ENOENT;
 	}
 
 	per_cpu(centrino_model, policy->cpu) = model;
 
-	dprintk("found \"%s\": max frequency: %dkHz\n",
+	pr_debug("found \"%s\": max frequency: %dkHz\n",
 	       model->model_name, model->max_freq);
 
 	return 0;
@@ -369,7 +366,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy)
 		per_cpu(centrino_cpu, policy->cpu) = &cpu_ids[i];
 
 	if (!per_cpu(centrino_cpu, policy->cpu)) {
-		dprintk("found unsupported CPU with "
+		pr_debug("found unsupported CPU with "
 		"Enhanced SpeedStep: send /proc/cpuinfo to "
 		MAINTAINER "\n");
 		return -ENODEV;
@@ -385,7 +382,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy)
 
 	if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
 		l |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
-		dprintk("trying to enable Enhanced SpeedStep (%x)\n", l);
+		pr_debug("trying to enable Enhanced SpeedStep (%x)\n", l);
 		wrmsr(MSR_IA32_MISC_ENABLE, l, h);
 
 		/* check to see if it stuck */
@@ -402,7 +399,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy)
 						/* 10uS transition latency */
 	policy->cur = freq;
 
-	dprintk("centrino_cpu_init: cur=%dkHz\n", policy->cur);
+	pr_debug("centrino_cpu_init: cur=%dkHz\n", policy->cur);
 
 	ret = cpufreq_frequency_table_cpuinfo(policy,
 		per_cpu(centrino_model, policy->cpu)->op_points);
@@ -498,7 +495,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 			good_cpu = j;
 
 		if (good_cpu >= nr_cpu_ids) {
-			dprintk("couldn't limit to CPUs in this domain\n");
+			pr_debug("couldn't limit to CPUs in this domain\n");
 			retval = -EAGAIN;
 			if (first_cpu) {
 				/* We haven't started the transition yet. */
@@ -512,7 +509,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 		if (first_cpu) {
 			rdmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, &oldmsr, &h);
 			if (msr == (oldmsr & 0xffff)) {
-				dprintk("no change needed - msr was and needs "
+				pr_debug("no change needed - msr was and needs "
 					"to be %x\n", oldmsr);
 				retval = 0;
 				goto out;
@@ -521,7 +518,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 			freqs.old = extract_clock(oldmsr, cpu, 0);
 			freqs.new = extract_clock(msr, cpu, 0);
 
-			dprintk("target=%dkHz old=%d new=%d msr=%04x\n",
+			pr_debug("target=%dkHz old=%d new=%d msr=%04x\n",
 				target_freq, freqs.old, freqs.new, msr);
 
 			for_each_cpu(k, policy->cpus) {
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 561758e9518..a748ce782fe 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -53,10 +53,6 @@ static struct cpufreq_frequency_table speedstep_freqs[] = {
 };
 
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"speedstep-ich", msg)
-
-
 /**
  * speedstep_find_register - read the PMBASE address
  *
@@ -80,7 +76,7 @@ static int speedstep_find_register(void)
 		return -ENODEV;
 	}
 
-	dprintk("pmbase is 0x%x\n", pmbase);
+	pr_debug("pmbase is 0x%x\n", pmbase);
 	return 0;
 }
 
@@ -106,13 +102,13 @@ static void speedstep_set_state(unsigned int state)
 	/* read state */
 	value = inb(pmbase + 0x50);
 
-	dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
+	pr_debug("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
 
 	/* write new state */
 	value &= 0xFE;
 	value |= state;
 
-	dprintk("writing 0x%x to pmbase 0x%x + 0x50\n", value, pmbase);
+	pr_debug("writing 0x%x to pmbase 0x%x + 0x50\n", value, pmbase);
 
 	/* Disable bus master arbitration */
 	pm2_blk = inb(pmbase + 0x20);
@@ -132,10 +128,10 @@ static void speedstep_set_state(unsigned int state)
 	/* Enable IRQs */
 	local_irq_restore(flags);
 
-	dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
+	pr_debug("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value);
 
 	if (state == (value & 0x1))
-		dprintk("change to %u MHz succeeded\n",
+		pr_debug("change to %u MHz succeeded\n",
 			speedstep_get_frequency(speedstep_processor) / 1000);
 	else
 		printk(KERN_ERR "cpufreq: change failed - I/O error\n");
@@ -165,7 +161,7 @@ static int speedstep_activate(void)
 	pci_read_config_word(speedstep_chipset_dev, 0x00A0, &value);
 	if (!(value & 0x08)) {
 		value |= 0x08;
-		dprintk("activating SpeedStep (TM) registers\n");
+		pr_debug("activating SpeedStep (TM) registers\n");
 		pci_write_config_word(speedstep_chipset_dev, 0x00A0, value);
 	}
 
@@ -218,7 +214,7 @@ static unsigned int speedstep_detect_chipset(void)
 			return 2; /* 2-M */
 
 		if (hostbridge->revision < 5) {
-			dprintk("hostbridge does not support speedstep\n");
+			pr_debug("hostbridge does not support speedstep\n");
 			speedstep_chipset_dev = NULL;
 			pci_dev_put(hostbridge);
 			return 0;
@@ -246,7 +242,7 @@ static unsigned int speedstep_get(unsigned int cpu)
 	if (smp_call_function_single(cpu, get_freq_data, &speed, 1) != 0)
 		BUG();
 
-	dprintk("detected %u kHz as current frequency\n", speed);
+	pr_debug("detected %u kHz as current frequency\n", speed);
 	return speed;
 }
 
@@ -276,7 +272,7 @@ static int speedstep_target(struct cpufreq_policy *policy,
 	freqs.new = speedstep_freqs[newstate].frequency;
 	freqs.cpu = policy->cpu;
 
-	dprintk("transiting from %u to %u kHz\n", freqs.old, freqs.new);
+	pr_debug("transiting from %u to %u kHz\n", freqs.old, freqs.new);
 
 	/* no transition necessary */
 	if (freqs.old == freqs.new)
@@ -351,7 +347,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 	if (!speed)
 		return -EIO;
 
-	dprintk("currently at %s speed setting - %i MHz\n",
+	pr_debug("currently at %s speed setting - %i MHz\n",
 		(speed == speedstep_freqs[SPEEDSTEP_LOW].frequency)
 		? "low" : "high",
 		(speed / 1000));
@@ -405,14 +401,14 @@ static int __init speedstep_init(void)
 	/* detect processor */
 	speedstep_processor = speedstep_detect_processor();
 	if (!speedstep_processor) {
-		dprintk("Intel(R) SpeedStep(TM) capable processor "
+		pr_debug("Intel(R) SpeedStep(TM) capable processor "
 				"not found\n");
 		return -ENODEV;
 	}
 
 	/* detect chipset */
 	if (!speedstep_detect_chipset()) {
-		dprintk("Intel(R) SpeedStep(TM) for this chipset not "
+		pr_debug("Intel(R) SpeedStep(TM) for this chipset not "
 				"(yet) available.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index a94ec6be69f..8af2d2fd9d5 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -18,9 +18,6 @@
 #include <asm/tsc.h>
 #include "speedstep-lib.h"
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"speedstep-lib", msg)
-
 #define PFX "speedstep-lib: "
 
 #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK
@@ -75,7 +72,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor)
 
 	/* read MSR 0x2a - we only need the low 32 bits */
 	rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
-	dprintk("P3 - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
+	pr_debug("P3 - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
 	msr_tmp = msr_lo;
 
 	/* decode the FSB */
@@ -89,7 +86,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor)
 
 	/* decode the multiplier */
 	if (processor == SPEEDSTEP_CPU_PIII_C_EARLY) {
-		dprintk("workaround for early PIIIs\n");
+		pr_debug("workaround for early PIIIs\n");
 		msr_lo &= 0x03c00000;
 	} else
 		msr_lo &= 0x0bc00000;
@@ -100,7 +97,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor)
 		j++;
 	}
 
-	dprintk("speed is %u\n",
+	pr_debug("speed is %u\n",
 		(msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100));
 
 	return msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100;
@@ -112,7 +109,7 @@ static unsigned int pentiumM_get_frequency(void)
 	u32 msr_lo, msr_tmp;
 
 	rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
-	dprintk("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
+	pr_debug("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp);
 
 	/* see table B-2 of 24547212.pdf */
 	if (msr_lo & 0x00040000) {
@@ -122,7 +119,7 @@ static unsigned int pentiumM_get_frequency(void)
 	}
 
 	msr_tmp = (msr_lo >> 22) & 0x1f;
-	dprintk("bits 22-26 are 0x%x, speed is %u\n",
+	pr_debug("bits 22-26 are 0x%x, speed is %u\n",
 			msr_tmp, (msr_tmp * 100 * 1000));
 
 	return msr_tmp * 100 * 1000;
@@ -160,11 +157,11 @@ static unsigned int pentium_core_get_frequency(void)
 	}
 
 	rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
-	dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n",
+	pr_debug("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n",
 			msr_lo, msr_tmp);
 
 	msr_tmp = (msr_lo >> 22) & 0x1f;
-	dprintk("bits 22-26 are 0x%x, speed is %u\n",
+	pr_debug("bits 22-26 are 0x%x, speed is %u\n",
 			msr_tmp, (msr_tmp * fsb));
 
 	ret = (msr_tmp * fsb);
@@ -190,7 +187,7 @@ static unsigned int pentium4_get_frequency(void)
 
 	rdmsr(0x2c, msr_lo, msr_hi);
 
-	dprintk("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi);
+	pr_debug("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi);
 
 	/* decode the FSB: see IA-32 Intel (C) Architecture Software
 	 * Developer's Manual, Volume 3: System Prgramming Guide,
@@ -217,7 +214,7 @@ static unsigned int pentium4_get_frequency(void)
 	/* Multiplier. */
 	mult = msr_lo >> 24;
 
-	dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n",
+	pr_debug("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n",
 			fsb, mult, (fsb * mult));
 
 	ret = (fsb * mult);
@@ -257,7 +254,7 @@ unsigned int speedstep_detect_processor(void)
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	u32 ebx, msr_lo, msr_hi;
 
-	dprintk("x86: %x, model: %x\n", c->x86, c->x86_model);
+	pr_debug("x86: %x, model: %x\n", c->x86, c->x86_model);
 
 	if ((c->x86_vendor != X86_VENDOR_INTEL) ||
 	    ((c->x86 != 6) && (c->x86 != 0xF)))
@@ -272,7 +269,7 @@ unsigned int speedstep_detect_processor(void)
 		ebx = cpuid_ebx(0x00000001);
 		ebx &= 0x000000FF;
 
-		dprintk("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask);
+		pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask);
 
 		switch (c->x86_mask) {
 		case 4:
@@ -327,7 +324,7 @@ unsigned int speedstep_detect_processor(void)
 		/* cpuid_ebx(1) is 0x04 for desktop PIII,
 		 * 0x06 for mobile PIII-M */
 		ebx = cpuid_ebx(0x00000001);
-		dprintk("ebx is %x\n", ebx);
+		pr_debug("ebx is %x\n", ebx);
 
 		ebx &= 0x000000FF;
 
@@ -344,7 +341,7 @@ unsigned int speedstep_detect_processor(void)
 		/* all mobile PIII Coppermines have FSB 100 MHz
 		 * ==> sort out a few desktop PIIIs. */
 		rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_hi);
-		dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n",
+		pr_debug("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n",
 				msr_lo, msr_hi);
 		msr_lo &= 0x00c0000;
 		if (msr_lo != 0x0080000)
@@ -357,12 +354,12 @@ unsigned int speedstep_detect_processor(void)
 		 * bit 56 or 57 is set
 		 */
 		rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi);
-		dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n",
+		pr_debug("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n",
 				msr_lo, msr_hi);
 		if ((msr_hi & (1<<18)) &&
 		    (relaxed_check ? 1 : (msr_hi & (3<<24)))) {
 			if (c->x86_mask == 0x01) {
-				dprintk("early PIII version\n");
+				pr_debug("early PIII version\n");
 				return SPEEDSTEP_CPU_PIII_C_EARLY;
 			} else
 				return SPEEDSTEP_CPU_PIII_C;
@@ -393,14 +390,14 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 	if ((!processor) || (!low_speed) || (!high_speed) || (!set_state))
 		return -EINVAL;
 
-	dprintk("trying to determine both speeds\n");
+	pr_debug("trying to determine both speeds\n");
 
 	/* get current speed */
 	prev_speed = speedstep_get_frequency(processor);
 	if (!prev_speed)
 		return -EIO;
 
-	dprintk("previous speed is %u\n", prev_speed);
+	pr_debug("previous speed is %u\n", prev_speed);
 
 	local_irq_save(flags);
 
@@ -412,7 +409,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 		goto out;
 	}
 
-	dprintk("low speed is %u\n", *low_speed);
+	pr_debug("low speed is %u\n", *low_speed);
 
 	/* start latency measurement */
 	if (transition_latency)
@@ -431,7 +428,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 		goto out;
 	}
 
-	dprintk("high speed is %u\n", *high_speed);
+	pr_debug("high speed is %u\n", *high_speed);
 
 	if (*low_speed == *high_speed) {
 		ret = -ENODEV;
@@ -445,7 +442,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 	if (transition_latency) {
 		*transition_latency = (tv2.tv_sec - tv1.tv_sec) * USEC_PER_SEC +
 			tv2.tv_usec - tv1.tv_usec;
-		dprintk("transition latency is %u uSec\n", *transition_latency);
+		pr_debug("transition latency is %u uSec\n", *transition_latency);
 
 		/* convert uSec to nSec and add 20% for safety reasons */
 		*transition_latency *= 1200;
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h b/drivers/cpufreq/speedstep-lib.h
index 70d9cea1219..70d9cea1219 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h
+++ b/drivers/cpufreq/speedstep-lib.h
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index 91bc25b67bc..c76ead3490b 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -55,9 +55,6 @@ static struct cpufreq_frequency_table speedstep_freqs[] = {
  * of DMA activity going on? */
 #define SMI_TRIES 5
 
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
-		"speedstep-smi", msg)
-
 /**
  * speedstep_smi_ownership
  */
@@ -70,7 +67,7 @@ static int speedstep_smi_ownership(void)
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
 	magic = virt_to_phys(magic_data);
 
-	dprintk("trying to obtain ownership with command %x at port %x\n",
+	pr_debug("trying to obtain ownership with command %x at port %x\n",
 			command, smi_port);
 
 	__asm__ __volatile__(
@@ -85,7 +82,7 @@ static int speedstep_smi_ownership(void)
 		: "memory"
 	);
 
-	dprintk("result is %x\n", result);
+	pr_debug("result is %x\n", result);
 
 	return result;
 }
@@ -106,13 +103,13 @@ static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high)
 	u32 function = GET_SPEEDSTEP_FREQS;
 
 	if (!(ist_info.event & 0xFFFF)) {
-		dprintk("bug #1422 -- can't read freqs from BIOS\n");
+		pr_debug("bug #1422 -- can't read freqs from BIOS\n");
 		return -ENODEV;
 	}
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
 
-	dprintk("trying to determine frequencies with command %x at port %x\n",
+	pr_debug("trying to determine frequencies with command %x at port %x\n",
 			command, smi_port);
 
 	__asm__ __volatile__(
@@ -129,7 +126,7 @@ static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high)
 		  "d" (smi_port), "S" (0), "D" (0)
 	);
 
-	dprintk("result %x, low_freq %u, high_freq %u\n",
+	pr_debug("result %x, low_freq %u, high_freq %u\n",
 			result, low_mhz, high_mhz);
 
 	/* abort if results are obviously incorrect... */
@@ -154,7 +151,7 @@ static int speedstep_get_state(void)
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
 
-	dprintk("trying to determine current setting with command %x "
+	pr_debug("trying to determine current setting with command %x "
 		"at port %x\n", command, smi_port);
 
 	__asm__ __volatile__(
@@ -168,7 +165,7 @@ static int speedstep_get_state(void)
 		  "d" (smi_port), "S" (0), "D" (0)
 	);
 
-	dprintk("state is %x, result is %x\n", state, result);
+	pr_debug("state is %x, result is %x\n", state, result);
 
 	return state & 1;
 }
@@ -194,13 +191,13 @@ static void speedstep_set_state(unsigned int state)
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
 
-	dprintk("trying to set frequency to state %u "
+	pr_debug("trying to set frequency to state %u "
 		"with command %x at port %x\n",
 		state, command, smi_port);
 
 	do {
 		if (retry) {
-			dprintk("retry %u, previous result %u, waiting...\n",
+			pr_debug("retry %u, previous result %u, waiting...\n",
 					retry, result);
 			mdelay(retry * 50);
 		}
@@ -221,7 +218,7 @@ static void speedstep_set_state(unsigned int state)
 	local_irq_restore(flags);
 
 	if (new_state == state)
-		dprintk("change to %u MHz succeeded after %u tries "
+		pr_debug("change to %u MHz succeeded after %u tries "
 			"with result %u\n",
 			(speedstep_freqs[new_state].frequency / 1000),
 			retry, result);
@@ -292,7 +289,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	result = speedstep_smi_ownership();
 	if (result) {
-		dprintk("fails in acquiring ownership of a SMI interface.\n");
+		pr_debug("fails in acquiring ownership of a SMI interface.\n");
 		return -EINVAL;
 	}
 
@@ -304,7 +301,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 	if (result) {
 		/* fall back to speedstep_lib.c dection mechanism:
 		 * try both states out */
-		dprintk("could not detect low and high frequencies "
+		pr_debug("could not detect low and high frequencies "
 				"by SMI call.\n");
 		result = speedstep_get_freqs(speedstep_processor,
 				low, high,
@@ -312,18 +309,18 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 				&speedstep_set_state);
 
 		if (result) {
-			dprintk("could not detect two different speeds"
+			pr_debug("could not detect two different speeds"
 					" -- aborting.\n");
 			return result;
 		} else
-			dprintk("workaround worked.\n");
+			pr_debug("workaround worked.\n");
 	}
 
 	/* get current speed setting */
 	state = speedstep_get_state();
 	speed = speedstep_freqs[state].frequency;
 
-	dprintk("currently at %s speed setting - %i MHz\n",
+	pr_debug("currently at %s speed setting - %i MHz\n",
 		(speed == speedstep_freqs[SPEEDSTEP_LOW].frequency)
 		? "low" : "high",
 		(speed / 1000));
@@ -360,7 +357,7 @@ static int speedstep_resume(struct cpufreq_policy *policy)
 	int result = speedstep_smi_ownership();
 
 	if (result)
-		dprintk("fails in re-acquiring ownership of a SMI interface.\n");
+		pr_debug("fails in re-acquiring ownership of a SMI interface.\n");
 
 	return result;
 }
@@ -403,12 +400,12 @@ static int __init speedstep_init(void)
 	}
 
 	if (!speedstep_processor) {
-		dprintk("No supported Intel CPU detected.\n");
+		pr_debug("No supported Intel CPU detected.\n");
 		return -ENODEV;
 	}
 
-	dprintk("signature:0x%.8lx, command:0x%.8lx, "
-		"event:0x%.8lx, perf_level:0x%.8lx.\n",
+	pr_debug("signature:0x%.8ulx, command:0x%.8ulx, "
+		"event:0x%.8ulx, perf_level:0x%.8ulx.\n",
 		ist_info.signature, ist_info.command,
 		ist_info.event, ist_info.perf_level);
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index b3a25a55ba2..efba163595d 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -157,4 +157,6 @@ config SIGMA
 	  If unsure, say N here.  Drivers that need these helpers will select
 	  this option automatically.
 
+source "drivers/firmware/google/Kconfig"
+
 endmenu
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 00bb0b80a79..47338c97912 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_SIGMA)		+= sigma.o
+
+obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
diff --git a/drivers/firmware/edd.c b/drivers/firmware/edd.c
index 96c25d93eed..f1b7f659d3c 100644
--- a/drivers/firmware/edd.c
+++ b/drivers/firmware/edd.c
@@ -531,8 +531,8 @@ static int
 edd_has_edd30(struct edd_device *edev)
 {
 	struct edd_info *info;
-	int i, nonzero_path = 0;
-	char c;
+	int i;
+	u8 csum = 0;
 
 	if (!edev)
 		return 0;
@@ -544,16 +544,16 @@ edd_has_edd30(struct edd_device *edev)
 		return 0;
 	}
 
-	for (i = 30; i <= 73; i++) {
-		c = *(((uint8_t *) info) + i + 4);
-		if (c) {
-			nonzero_path++;
-			break;
-		}
-	}
-	if (!nonzero_path) {
+
+	/* We support only T13 spec */
+	if (info->params.device_path_info_length != 44)
+		return 0;
+
+	for (i = 30; i < info->params.device_path_info_length + 30; i++)
+		csum += *(((u8 *)&info->params) + i);
+
+	if (csum)
 		return 0;
-	}
 
 	return 1;
 }
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index ff0c373e3bb..a2d2f1f0d4f 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -677,8 +677,8 @@ create_efivars_bin_attributes(struct efivars *efivars)
 
 	return 0;
 out_free:
-	kfree(efivars->new_var);
-	efivars->new_var = NULL;
+	kfree(efivars->del_var);
+	efivars->del_var = NULL;
 	kfree(efivars->new_var);
 	efivars->new_var = NULL;
 	return error;
@@ -803,6 +803,8 @@ efivars_init(void)
 	ops.set_variable = efi.set_variable;
 	ops.get_next_variable = efi.get_next_variable;
 	error = register_efivars(&__efivars, &ops, efi_kobj);
+	if (error)
+		goto err_put;
 
 	/* Don't forget the systab entry */
 	error = sysfs_create_group(efi_kobj, &efi_subsys_attr_group);
@@ -810,18 +812,25 @@ efivars_init(void)
 		printk(KERN_ERR
 		       "efivars: Sysfs attribute export failed with error %d.\n",
 		       error);
-		unregister_efivars(&__efivars);
-		kobject_put(efi_kobj);
+		goto err_unregister;
 	}
 
+	return 0;
+
+err_unregister:
+	unregister_efivars(&__efivars);
+err_put:
+	kobject_put(efi_kobj);
 	return error;
 }
 
 static void __exit
 efivars_exit(void)
 {
-	unregister_efivars(&__efivars);
-	kobject_put(efi_kobj);
+	if (efi_enabled) {
+		unregister_efivars(&__efivars);
+		kobject_put(efi_kobj);
+	}
 }
 
 module_init(efivars_init);
diff --git a/drivers/firmware/google/Kconfig b/drivers/firmware/google/Kconfig
new file mode 100644
index 00000000000..87096b6ca5c
--- /dev/null
+++ b/drivers/firmware/google/Kconfig
@@ -0,0 +1,31 @@
+config GOOGLE_FIRMWARE
+	bool "Google Firmware Drivers"
+	depends on X86
+	default n
+	help
+	  These firmware drivers are used by Google's servers.  They are
+	  only useful if you are working directly on one of their
+	  proprietary servers.  If in doubt, say "N".
+
+menu "Google Firmware Drivers"
+	depends on GOOGLE_FIRMWARE
+
+config GOOGLE_SMI
+	tristate "SMI interface for Google platforms"
+	depends on ACPI && DMI
+	select EFI_VARS
+	help
+	  Say Y here if you want to enable SMI callbacks for Google
+	  platforms.  This provides an interface for writing to and
+	  clearing the EFI event log and reading and writing NVRAM
+	  variables.
+
+config GOOGLE_MEMCONSOLE
+	tristate "Firmware Memory Console"
+	depends on DMI
+	help
+	  This option enables the kernel to search for a firmware log in
+	  the EBDA on Google servers.  If found, this log is exported to
+	  userland in the file /sys/firmware/log.
+
+endmenu
diff --git a/drivers/firmware/google/Makefile b/drivers/firmware/google/Makefile
new file mode 100644
index 00000000000..54a294e3cb6
--- /dev/null
+++ b/drivers/firmware/google/Makefile
@@ -0,0 +1,3 @@
+
+obj-$(CONFIG_GOOGLE_SMI)		+= gsmi.o
+obj-$(CONFIG_GOOGLE_MEMCONSOLE)		+= memconsole.o
diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c
new file mode 100644
index 00000000000..fa7f0b3e81d
--- /dev/null
+++ b/drivers/firmware/google/gsmi.c
@@ -0,0 +1,940 @@
+/*
+ * Copyright 2010 Google Inc. All Rights Reserved.
+ * Author: dlaurie@google.com (Duncan Laurie)
+ *
+ * Re-worked to expose sysfs APIs by mikew@google.com (Mike Waychison)
+ *
+ * EFI SMI interface for Google platforms
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/ioctl.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+#include <linux/dmi.h>
+#include <linux/kdebug.h>
+#include <linux/reboot.h>
+#include <linux/efi.h>
+
+#define GSMI_SHUTDOWN_CLEAN	0	/* Clean Shutdown */
+/* TODO(mikew@google.com): Tie in HARDLOCKUP_DETECTOR with NMIWDT */
+#define GSMI_SHUTDOWN_NMIWDT	1	/* NMI Watchdog */
+#define GSMI_SHUTDOWN_PANIC	2	/* Panic */
+#define GSMI_SHUTDOWN_OOPS	3	/* Oops */
+#define GSMI_SHUTDOWN_DIE	4	/* Die -- No longer meaningful */
+#define GSMI_SHUTDOWN_MCE	5	/* Machine Check */
+#define GSMI_SHUTDOWN_SOFTWDT	6	/* Software Watchdog */
+#define GSMI_SHUTDOWN_MBE	7	/* Uncorrected ECC */
+#define GSMI_SHUTDOWN_TRIPLE	8	/* Triple Fault */
+
+#define DRIVER_VERSION		"1.0"
+#define GSMI_GUID_SIZE		16
+#define GSMI_BUF_SIZE		1024
+#define GSMI_BUF_ALIGN		sizeof(u64)
+#define GSMI_CALLBACK		0xef
+
+/* SMI return codes */
+#define GSMI_SUCCESS		0x00
+#define GSMI_UNSUPPORTED2	0x03
+#define GSMI_LOG_FULL		0x0b
+#define GSMI_VAR_NOT_FOUND	0x0e
+#define GSMI_HANDSHAKE_SPIN	0x7d
+#define GSMI_HANDSHAKE_CF	0x7e
+#define GSMI_HANDSHAKE_NONE	0x7f
+#define GSMI_INVALID_PARAMETER	0x82
+#define GSMI_UNSUPPORTED	0x83
+#define GSMI_BUFFER_TOO_SMALL	0x85
+#define GSMI_NOT_READY		0x86
+#define GSMI_DEVICE_ERROR	0x87
+#define GSMI_NOT_FOUND		0x8e
+
+#define QUIRKY_BOARD_HASH 0x78a30a50
+
+/* Internally used commands passed to the firmware */
+#define GSMI_CMD_GET_NVRAM_VAR		0x01
+#define GSMI_CMD_GET_NEXT_VAR		0x02
+#define GSMI_CMD_SET_NVRAM_VAR		0x03
+#define GSMI_CMD_SET_EVENT_LOG		0x08
+#define GSMI_CMD_CLEAR_EVENT_LOG	0x09
+#define GSMI_CMD_CLEAR_CONFIG		0x20
+#define GSMI_CMD_HANDSHAKE_TYPE		0xC1
+
+/* Magic entry type for kernel events */
+#define GSMI_LOG_ENTRY_TYPE_KERNEL     0xDEAD
+
+/* SMI buffers must be in 32bit physical address space */
+struct gsmi_buf {
+	u8 *start;			/* start of buffer */
+	size_t length;			/* length of buffer */
+	dma_addr_t handle;		/* dma allocation handle */
+	u32 address;			/* physical address of buffer */
+};
+
+struct gsmi_device {
+	struct platform_device *pdev;	/* platform device */
+	struct gsmi_buf *name_buf;	/* variable name buffer */
+	struct gsmi_buf *data_buf;	/* generic data buffer */
+	struct gsmi_buf *param_buf;	/* parameter buffer */
+	spinlock_t lock;		/* serialize access to SMIs */
+	u16 smi_cmd;			/* SMI command port */
+	int handshake_type;		/* firmware handler interlock type */
+	struct dma_pool *dma_pool;	/* DMA buffer pool */
+} gsmi_dev;
+
+/* Packed structures for communicating with the firmware */
+struct gsmi_nvram_var_param {
+	efi_guid_t	guid;
+	u32		name_ptr;
+	u32		attributes;
+	u32		data_len;
+	u32		data_ptr;
+} __packed;
+
+struct gsmi_get_next_var_param {
+	u8	guid[GSMI_GUID_SIZE];
+	u32	name_ptr;
+	u32	name_len;
+} __packed;
+
+struct gsmi_set_eventlog_param {
+	u32	data_ptr;
+	u32	data_len;
+	u32	type;
+} __packed;
+
+/* Event log formats */
+struct gsmi_log_entry_type_1 {
+	u16	type;
+	u32	instance;
+} __packed;
+
+
+/*
+ * Some platforms don't have explicit SMI handshake
+ * and need to wait for SMI to complete.
+ */
+#define GSMI_DEFAULT_SPINCOUNT	0x10000
+static unsigned int spincount = GSMI_DEFAULT_SPINCOUNT;
+module_param(spincount, uint, 0600);
+MODULE_PARM_DESC(spincount,
+	"The number of loop iterations to use when using the spin handshake.");
+
+static struct gsmi_buf *gsmi_buf_alloc(void)
+{
+	struct gsmi_buf *smibuf;
+
+	smibuf = kzalloc(sizeof(*smibuf), GFP_KERNEL);
+	if (!smibuf) {
+		printk(KERN_ERR "gsmi: out of memory\n");
+		return NULL;
+	}
+
+	/* allocate buffer in 32bit address space */
+	smibuf->start = dma_pool_alloc(gsmi_dev.dma_pool, GFP_KERNEL,
+				       &smibuf->handle);
+	if (!smibuf->start) {
+		printk(KERN_ERR "gsmi: failed to allocate name buffer\n");
+		kfree(smibuf);
+		return NULL;
+	}
+
+	/* fill in the buffer handle */
+	smibuf->length = GSMI_BUF_SIZE;
+	smibuf->address = (u32)virt_to_phys(smibuf->start);
+
+	return smibuf;
+}
+
+static void gsmi_buf_free(struct gsmi_buf *smibuf)
+{
+	if (smibuf) {
+		if (smibuf->start)
+			dma_pool_free(gsmi_dev.dma_pool, smibuf->start,
+				      smibuf->handle);
+		kfree(smibuf);
+	}
+}
+
+/*
+ * Make a call to gsmi func(sub).  GSMI error codes are translated to
+ * in-kernel errnos (0 on success, -ERRNO on error).
+ */
+static int gsmi_exec(u8 func, u8 sub)
+{
+	u16 cmd = (sub << 8) | func;
+	u16 result = 0;
+	int rc = 0;
+
+	/*
+	 * AH  : Subfunction number
+	 * AL  : Function number
+	 * EBX : Parameter block address
+	 * DX  : SMI command port
+	 *
+	 * Three protocols here. See also the comment in gsmi_init().
+	 */
+	if (gsmi_dev.handshake_type == GSMI_HANDSHAKE_CF) {
+		/*
+		 * If handshake_type == HANDSHAKE_CF then set CF on the
+		 * way in and wait for the handler to clear it; this avoids
+		 * corrupting register state on those chipsets which have
+		 * a delay between writing the SMI trigger register and
+		 * entering SMM.
+		 */
+		asm volatile (
+			"stc\n"
+			"outb %%al, %%dx\n"
+		"1:      jc 1b\n"
+			: "=a" (result)
+			: "0" (cmd),
+			  "d" (gsmi_dev.smi_cmd),
+			  "b" (gsmi_dev.param_buf->address)
+			: "memory", "cc"
+		);
+	} else if (gsmi_dev.handshake_type == GSMI_HANDSHAKE_SPIN) {
+		/*
+		 * If handshake_type == HANDSHAKE_SPIN we spin a
+		 * hundred-ish usecs to ensure the SMI has triggered.
+		 */
+		asm volatile (
+			"outb %%al, %%dx\n"
+		"1:      loop 1b\n"
+			: "=a" (result)
+			: "0" (cmd),
+			  "d" (gsmi_dev.smi_cmd),
+			  "b" (gsmi_dev.param_buf->address),
+			  "c" (spincount)
+			: "memory", "cc"
+		);
+	} else {
+		/*
+		 * If handshake_type == HANDSHAKE_NONE we do nothing;
+		 * either we don't need to or it's legacy firmware that
+		 * doesn't understand the CF protocol.
+		 */
+		asm volatile (
+			"outb %%al, %%dx\n\t"
+			: "=a" (result)
+			: "0" (cmd),
+			  "d" (gsmi_dev.smi_cmd),
+			  "b" (gsmi_dev.param_buf->address)
+			: "memory", "cc"
+		);
+	}
+
+	/* check return code from SMI handler */
+	switch (result) {
+	case GSMI_SUCCESS:
+		break;
+	case GSMI_VAR_NOT_FOUND:
+		/* not really an error, but let the caller know */
+		rc = 1;
+		break;
+	case GSMI_INVALID_PARAMETER:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Invalid parameter\n", cmd);
+		rc = -EINVAL;
+		break;
+	case GSMI_BUFFER_TOO_SMALL:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Buffer too small\n", cmd);
+		rc = -ENOMEM;
+		break;
+	case GSMI_UNSUPPORTED:
+	case GSMI_UNSUPPORTED2:
+		if (sub != GSMI_CMD_HANDSHAKE_TYPE)
+			printk(KERN_ERR "gsmi: exec 0x%04x: Not supported\n",
+			       cmd);
+		rc = -ENOSYS;
+		break;
+	case GSMI_NOT_READY:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Not ready\n", cmd);
+		rc = -EBUSY;
+		break;
+	case GSMI_DEVICE_ERROR:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Device error\n", cmd);
+		rc = -EFAULT;
+		break;
+	case GSMI_NOT_FOUND:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Data not found\n", cmd);
+		rc = -ENOENT;
+		break;
+	case GSMI_LOG_FULL:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Log full\n", cmd);
+		rc = -ENOSPC;
+		break;
+	case GSMI_HANDSHAKE_CF:
+	case GSMI_HANDSHAKE_SPIN:
+	case GSMI_HANDSHAKE_NONE:
+		rc = result;
+		break;
+	default:
+		printk(KERN_ERR "gsmi: exec 0x%04x: Unknown error 0x%04x\n",
+		       cmd, result);
+		rc = -ENXIO;
+	}
+
+	return rc;
+}
+
+/* Return the number of unicode characters in data */
+static size_t
+utf16_strlen(efi_char16_t *data, unsigned long maxlength)
+{
+	unsigned long length = 0;
+
+	while (*data++ != 0 && length < maxlength)
+		length++;
+	return length;
+}
+
+static efi_status_t gsmi_get_variable(efi_char16_t *name,
+				      efi_guid_t *vendor, u32 *attr,
+				      unsigned long *data_size,
+				      void *data)
+{
+	struct gsmi_nvram_var_param param = {
+		.name_ptr = gsmi_dev.name_buf->address,
+		.data_ptr = gsmi_dev.data_buf->address,
+		.data_len = (u32)*data_size,
+	};
+	efi_status_t ret = EFI_SUCCESS;
+	unsigned long flags;
+	size_t name_len = utf16_strlen(name, GSMI_BUF_SIZE / 2);
+	int rc;
+
+	if (name_len >= GSMI_BUF_SIZE / 2)
+		return EFI_BAD_BUFFER_SIZE;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* Vendor guid */
+	memcpy(&param.guid, vendor, sizeof(param.guid));
+
+	/* variable name, already in UTF-16 */
+	memset(gsmi_dev.name_buf->start, 0, gsmi_dev.name_buf->length);
+	memcpy(gsmi_dev.name_buf->start, name, name_len * 2);
+
+	/* data pointer */
+	memset(gsmi_dev.data_buf->start, 0, gsmi_dev.data_buf->length);
+
+	/* parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_GET_NVRAM_VAR);
+	if (rc < 0) {
+		printk(KERN_ERR "gsmi: Get Variable failed\n");
+		ret = EFI_LOAD_ERROR;
+	} else if (rc == 1) {
+		/* variable was not found */
+		ret = EFI_NOT_FOUND;
+	} else {
+		/* Get the arguments back */
+		memcpy(&param, gsmi_dev.param_buf->start, sizeof(param));
+
+		/* The size reported is the min of all of our buffers */
+		*data_size = min(*data_size, gsmi_dev.data_buf->length);
+		*data_size = min_t(unsigned long, *data_size, param.data_len);
+
+		/* Copy data back to return buffer. */
+		memcpy(data, gsmi_dev.data_buf->start, *data_size);
+
+		/* All variables are have the following attributes */
+		*attr = EFI_VARIABLE_NON_VOLATILE |
+			EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			EFI_VARIABLE_RUNTIME_ACCESS;
+	}
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	return ret;
+}
+
+static efi_status_t gsmi_get_next_variable(unsigned long *name_size,
+					   efi_char16_t *name,
+					   efi_guid_t *vendor)
+{
+	struct gsmi_get_next_var_param param = {
+		.name_ptr = gsmi_dev.name_buf->address,
+		.name_len = gsmi_dev.name_buf->length,
+	};
+	efi_status_t ret = EFI_SUCCESS;
+	int rc;
+	unsigned long flags;
+
+	/* For the moment, only support buffers that exactly match in size */
+	if (*name_size != GSMI_BUF_SIZE)
+		return EFI_BAD_BUFFER_SIZE;
+
+	/* Let's make sure the thing is at least null-terminated */
+	if (utf16_strlen(name, GSMI_BUF_SIZE / 2) == GSMI_BUF_SIZE / 2)
+		return EFI_INVALID_PARAMETER;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* guid */
+	memcpy(&param.guid, vendor, sizeof(param.guid));
+
+	/* variable name, already in UTF-16 */
+	memcpy(gsmi_dev.name_buf->start, name, *name_size);
+
+	/* parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_GET_NEXT_VAR);
+	if (rc < 0) {
+		printk(KERN_ERR "gsmi: Get Next Variable Name failed\n");
+		ret = EFI_LOAD_ERROR;
+	} else if (rc == 1) {
+		/* variable not found -- end of list */
+		ret = EFI_NOT_FOUND;
+	} else {
+		/* copy variable data back to return buffer */
+		memcpy(&param, gsmi_dev.param_buf->start, sizeof(param));
+
+		/* Copy the name back */
+		memcpy(name, gsmi_dev.name_buf->start, GSMI_BUF_SIZE);
+		*name_size = utf16_strlen(name, GSMI_BUF_SIZE / 2) * 2;
+
+		/* copy guid to return buffer */
+		memcpy(vendor, &param.guid, sizeof(param.guid));
+		ret = EFI_SUCCESS;
+	}
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	return ret;
+}
+
+static efi_status_t gsmi_set_variable(efi_char16_t *name,
+				      efi_guid_t *vendor,
+				      unsigned long attr,
+				      unsigned long data_size,
+				      void *data)
+{
+	struct gsmi_nvram_var_param param = {
+		.name_ptr = gsmi_dev.name_buf->address,
+		.data_ptr = gsmi_dev.data_buf->address,
+		.data_len = (u32)data_size,
+		.attributes = EFI_VARIABLE_NON_VOLATILE |
+			      EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			      EFI_VARIABLE_RUNTIME_ACCESS,
+	};
+	size_t name_len = utf16_strlen(name, GSMI_BUF_SIZE / 2);
+	efi_status_t ret = EFI_SUCCESS;
+	int rc;
+	unsigned long flags;
+
+	if (name_len >= GSMI_BUF_SIZE / 2)
+		return EFI_BAD_BUFFER_SIZE;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* guid */
+	memcpy(&param.guid, vendor, sizeof(param.guid));
+
+	/* variable name, already in UTF-16 */
+	memset(gsmi_dev.name_buf->start, 0, gsmi_dev.name_buf->length);
+	memcpy(gsmi_dev.name_buf->start, name, name_len * 2);
+
+	/* data pointer */
+	memset(gsmi_dev.data_buf->start, 0, gsmi_dev.data_buf->length);
+	memcpy(gsmi_dev.data_buf->start, data, data_size);
+
+	/* parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_SET_NVRAM_VAR);
+	if (rc < 0) {
+		printk(KERN_ERR "gsmi: Set Variable failed\n");
+		ret = EFI_INVALID_PARAMETER;
+	}
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	return ret;
+}
+
+static const struct efivar_operations efivar_ops = {
+	.get_variable = gsmi_get_variable,
+	.set_variable = gsmi_set_variable,
+	.get_next_variable = gsmi_get_next_variable,
+};
+
+static ssize_t eventlog_write(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr,
+			       char *buf, loff_t pos, size_t count)
+{
+	struct gsmi_set_eventlog_param param = {
+		.data_ptr = gsmi_dev.data_buf->address,
+	};
+	int rc = 0;
+	unsigned long flags;
+
+	/* Pull the type out */
+	if (count < sizeof(u32))
+		return -EINVAL;
+	param.type = *(u32 *)buf;
+	count -= sizeof(u32);
+	buf += sizeof(u32);
+
+	/* The remaining buffer is the data payload */
+	if (count > gsmi_dev.data_buf->length)
+		return -EINVAL;
+	param.data_len = count - sizeof(u32);
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* data pointer */
+	memset(gsmi_dev.data_buf->start, 0, gsmi_dev.data_buf->length);
+	memcpy(gsmi_dev.data_buf->start, buf, param.data_len);
+
+	/* parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_SET_EVENT_LOG);
+	if (rc < 0)
+		printk(KERN_ERR "gsmi: Set Event Log failed\n");
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	return rc;
+
+}
+
+static struct bin_attribute eventlog_bin_attr = {
+	.attr = {.name = "append_to_eventlog", .mode = 0200},
+	.write = eventlog_write,
+};
+
+static ssize_t gsmi_clear_eventlog_store(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 const char *buf, size_t count)
+{
+	int rc;
+	unsigned long flags;
+	unsigned long val;
+	struct {
+		u32 percentage;
+		u32 data_type;
+	} param;
+
+	rc = strict_strtoul(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	/*
+	 * Value entered is a percentage, 0 through 100, anything else
+	 * is invalid.
+	 */
+	if (val > 100)
+		return -EINVAL;
+
+	/* data_type here selects the smbios event log. */
+	param.percentage = val;
+	param.data_type = 0;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_CLEAR_EVENT_LOG);
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	if (rc)
+		return rc;
+	return count;
+}
+
+static struct kobj_attribute gsmi_clear_eventlog_attr = {
+	.attr = {.name = "clear_eventlog", .mode = 0200},
+	.store = gsmi_clear_eventlog_store,
+};
+
+static ssize_t gsmi_clear_config_store(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       const char *buf, size_t count)
+{
+	int rc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	/* clear parameter buffer */
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_CLEAR_CONFIG);
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	if (rc)
+		return rc;
+	return count;
+}
+
+static struct kobj_attribute gsmi_clear_config_attr = {
+	.attr = {.name = "clear_config", .mode = 0200},
+	.store = gsmi_clear_config_store,
+};
+
+static const struct attribute *gsmi_attrs[] = {
+	&gsmi_clear_config_attr.attr,
+	&gsmi_clear_eventlog_attr.attr,
+	NULL,
+};
+
+static int gsmi_shutdown_reason(int reason)
+{
+	struct gsmi_log_entry_type_1 entry = {
+		.type     = GSMI_LOG_ENTRY_TYPE_KERNEL,
+		.instance = reason,
+	};
+	struct gsmi_set_eventlog_param param = {
+		.data_len = sizeof(entry),
+		.type     = 1,
+	};
+	static int saved_reason;
+	int rc = 0;
+	unsigned long flags;
+
+	/* avoid duplicate entries in the log */
+	if (saved_reason & (1 << reason))
+		return 0;
+
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+
+	saved_reason |= (1 << reason);
+
+	/* data pointer */
+	memset(gsmi_dev.data_buf->start, 0, gsmi_dev.data_buf->length);
+	memcpy(gsmi_dev.data_buf->start, &entry, sizeof(entry));
+
+	/* parameter buffer */
+	param.data_ptr = gsmi_dev.data_buf->address;
+	memset(gsmi_dev.param_buf->start, 0, gsmi_dev.param_buf->length);
+	memcpy(gsmi_dev.param_buf->start, &param, sizeof(param));
+
+	rc = gsmi_exec(GSMI_CALLBACK, GSMI_CMD_SET_EVENT_LOG);
+
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	if (rc < 0)
+		printk(KERN_ERR "gsmi: Log Shutdown Reason failed\n");
+	else
+		printk(KERN_EMERG "gsmi: Log Shutdown Reason 0x%02x\n",
+		       reason);
+
+	return rc;
+}
+
+static int gsmi_reboot_callback(struct notifier_block *nb,
+				unsigned long reason, void *arg)
+{
+	gsmi_shutdown_reason(GSMI_SHUTDOWN_CLEAN);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block gsmi_reboot_notifier = {
+	.notifier_call = gsmi_reboot_callback
+};
+
+static int gsmi_die_callback(struct notifier_block *nb,
+			     unsigned long reason, void *arg)
+{
+	if (reason == DIE_OOPS)
+		gsmi_shutdown_reason(GSMI_SHUTDOWN_OOPS);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block gsmi_die_notifier = {
+	.notifier_call = gsmi_die_callback
+};
+
+static int gsmi_panic_callback(struct notifier_block *nb,
+			       unsigned long reason, void *arg)
+{
+	gsmi_shutdown_reason(GSMI_SHUTDOWN_PANIC);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block gsmi_panic_notifier = {
+	.notifier_call = gsmi_panic_callback,
+};
+
+/*
+ * This hash function was blatantly copied from include/linux/hash.h.
+ * It is used by this driver to obfuscate a board name that requires a
+ * quirk within this driver.
+ *
+ * Please do not remove this copy of the function as any changes to the
+ * global utility hash_64() function would break this driver's ability
+ * to identify a board and provide the appropriate quirk -- mikew@google.com
+ */
+static u64 __init local_hash_64(u64 val, unsigned bits)
+{
+	u64 hash = val;
+
+	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
+	u64 n = hash;
+	n <<= 18;
+	hash -= n;
+	n <<= 33;
+	hash -= n;
+	n <<= 3;
+	hash += n;
+	n <<= 3;
+	hash -= n;
+	n <<= 4;
+	hash += n;
+	n <<= 2;
+	hash += n;
+
+	/* High bits are more random, so use them. */
+	return hash >> (64 - bits);
+}
+
+static u32 __init hash_oem_table_id(char s[8])
+{
+	u64 input;
+	memcpy(&input, s, 8);
+	return local_hash_64(input, 32);
+}
+
+static struct dmi_system_id gsmi_dmi_table[] __initdata = {
+	{
+		.ident = "Google Board",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Google, Inc."),
+		},
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(dmi, gsmi_dmi_table);
+
+static __init int gsmi_system_valid(void)
+{
+	u32 hash;
+
+	if (!dmi_check_system(gsmi_dmi_table))
+		return -ENODEV;
+
+	/*
+	 * Only newer firmware supports the gsmi interface.  All older
+	 * firmware that didn't support this interface used to plug the
+	 * table name in the first four bytes of the oem_table_id field.
+	 * Newer firmware doesn't do that though, so use that as the
+	 * discriminant factor.  We have to do this in order to
+	 * whitewash our board names out of the public driver.
+	 */
+	if (!strncmp(acpi_gbl_FADT.header.oem_table_id, "FACP", 4)) {
+		printk(KERN_INFO "gsmi: Board is too old\n");
+		return -ENODEV;
+	}
+
+	/* Disable on board with 1.0 BIOS due to Google bug 2602657 */
+	hash = hash_oem_table_id(acpi_gbl_FADT.header.oem_table_id);
+	if (hash == QUIRKY_BOARD_HASH) {
+		const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION);
+		if (strncmp(bios_ver, "1.0", 3) == 0) {
+			pr_info("gsmi: disabled on this board's BIOS %s\n",
+				bios_ver);
+			return -ENODEV;
+		}
+	}
+
+	/* check for valid SMI command port in ACPI FADT */
+	if (acpi_gbl_FADT.smi_command == 0) {
+		pr_info("gsmi: missing smi_command\n");
+		return -ENODEV;
+	}
+
+	/* Found */
+	return 0;
+}
+
+static struct kobject *gsmi_kobj;
+static struct efivars efivars;
+
+static __init int gsmi_init(void)
+{
+	unsigned long flags;
+	int ret;
+
+	ret = gsmi_system_valid();
+	if (ret)
+		return ret;
+
+	gsmi_dev.smi_cmd = acpi_gbl_FADT.smi_command;
+
+	/* register device */
+	gsmi_dev.pdev = platform_device_register_simple("gsmi", -1, NULL, 0);
+	if (IS_ERR(gsmi_dev.pdev)) {
+		printk(KERN_ERR "gsmi: unable to register platform device\n");
+		return PTR_ERR(gsmi_dev.pdev);
+	}
+
+	/* SMI access needs to be serialized */
+	spin_lock_init(&gsmi_dev.lock);
+
+	/* SMI callbacks require 32bit addresses */
+	gsmi_dev.pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	gsmi_dev.pdev->dev.dma_mask =
+		&gsmi_dev.pdev->dev.coherent_dma_mask;
+	ret = -ENOMEM;
+	gsmi_dev.dma_pool = dma_pool_create("gsmi", &gsmi_dev.pdev->dev,
+					     GSMI_BUF_SIZE, GSMI_BUF_ALIGN, 0);
+	if (!gsmi_dev.dma_pool)
+		goto out_err;
+
+	/*
+	 * pre-allocate buffers because sometimes we are called when
+	 * this is not feasible: oops, panic, die, mce, etc
+	 */
+	gsmi_dev.name_buf = gsmi_buf_alloc();
+	if (!gsmi_dev.name_buf) {
+		printk(KERN_ERR "gsmi: failed to allocate name buffer\n");
+		goto out_err;
+	}
+
+	gsmi_dev.data_buf = gsmi_buf_alloc();
+	if (!gsmi_dev.data_buf) {
+		printk(KERN_ERR "gsmi: failed to allocate data buffer\n");
+		goto out_err;
+	}
+
+	gsmi_dev.param_buf = gsmi_buf_alloc();
+	if (!gsmi_dev.param_buf) {
+		printk(KERN_ERR "gsmi: failed to allocate param buffer\n");
+		goto out_err;
+	}
+
+	/*
+	 * Determine type of handshake used to serialize the SMI
+	 * entry. See also gsmi_exec().
+	 *
+	 * There's a "behavior" present on some chipsets where writing the
+	 * SMI trigger register in the southbridge doesn't result in an
+	 * immediate SMI. Rather, the processor can execute "a few" more
+	 * instructions before the SMI takes effect. To ensure synchronous
+	 * behavior, implement a handshake between the kernel driver and the
+	 * firmware handler to spin until released. This ioctl determines
+	 * the type of handshake.
+	 *
+	 * NONE: The firmware handler does not implement any
+	 * handshake. Either it doesn't need to, or it's legacy firmware
+	 * that doesn't know it needs to and never will.
+	 *
+	 * CF: The firmware handler will clear the CF in the saved
+	 * state before returning. The driver may set the CF and test for
+	 * it to clear before proceeding.
+	 *
+	 * SPIN: The firmware handler does not implement any handshake
+	 * but the driver should spin for a hundred or so microseconds
+	 * to ensure the SMI has triggered.
+	 *
+	 * Finally, the handler will return -ENOSYS if
+	 * GSMI_CMD_HANDSHAKE_TYPE is unimplemented, which implies
+	 * HANDSHAKE_NONE.
+	 */
+	spin_lock_irqsave(&gsmi_dev.lock, flags);
+	gsmi_dev.handshake_type = GSMI_HANDSHAKE_SPIN;
+	gsmi_dev.handshake_type =
+	    gsmi_exec(GSMI_CALLBACK, GSMI_CMD_HANDSHAKE_TYPE);
+	if (gsmi_dev.handshake_type == -ENOSYS)
+		gsmi_dev.handshake_type = GSMI_HANDSHAKE_NONE;
+	spin_unlock_irqrestore(&gsmi_dev.lock, flags);
+
+	/* Remove and clean up gsmi if the handshake could not complete. */
+	if (gsmi_dev.handshake_type == -ENXIO) {
+		printk(KERN_INFO "gsmi version " DRIVER_VERSION
+		       " failed to load\n");
+		ret = -ENODEV;
+		goto out_err;
+	}
+
+	printk(KERN_INFO "gsmi version " DRIVER_VERSION " loaded\n");
+
+	/* Register in the firmware directory */
+	ret = -ENOMEM;
+	gsmi_kobj = kobject_create_and_add("gsmi", firmware_kobj);
+	if (!gsmi_kobj) {
+		printk(KERN_INFO "gsmi: Failed to create firmware kobj\n");
+		goto out_err;
+	}
+
+	/* Setup eventlog access */
+	ret = sysfs_create_bin_file(gsmi_kobj, &eventlog_bin_attr);
+	if (ret) {
+		printk(KERN_INFO "gsmi: Failed to setup eventlog");
+		goto out_err;
+	}
+
+	/* Other attributes */
+	ret = sysfs_create_files(gsmi_kobj, gsmi_attrs);
+	if (ret) {
+		printk(KERN_INFO "gsmi: Failed to add attrs");
+		goto out_err;
+	}
+
+	if (register_efivars(&efivars, &efivar_ops, gsmi_kobj)) {
+		printk(KERN_INFO "gsmi: Failed to register efivars\n");
+		goto out_err;
+	}
+
+	register_reboot_notifier(&gsmi_reboot_notifier);
+	register_die_notifier(&gsmi_die_notifier);
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &gsmi_panic_notifier);
+
+	return 0;
+
+ out_err:
+	kobject_put(gsmi_kobj);
+	gsmi_buf_free(gsmi_dev.param_buf);
+	gsmi_buf_free(gsmi_dev.data_buf);
+	gsmi_buf_free(gsmi_dev.name_buf);
+	if (gsmi_dev.dma_pool)
+		dma_pool_destroy(gsmi_dev.dma_pool);
+	platform_device_unregister(gsmi_dev.pdev);
+	pr_info("gsmi: failed to load: %d\n", ret);
+	return ret;
+}
+
+static void __exit gsmi_exit(void)
+{
+	unregister_reboot_notifier(&gsmi_reboot_notifier);
+	unregister_die_notifier(&gsmi_die_notifier);
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &gsmi_panic_notifier);
+	unregister_efivars(&efivars);
+
+	kobject_put(gsmi_kobj);
+	gsmi_buf_free(gsmi_dev.param_buf);
+	gsmi_buf_free(gsmi_dev.data_buf);
+	gsmi_buf_free(gsmi_dev.name_buf);
+	dma_pool_destroy(gsmi_dev.dma_pool);
+	platform_device_unregister(gsmi_dev.pdev);
+}
+
+module_init(gsmi_init);
+module_exit(gsmi_exit);
+
+MODULE_AUTHOR("Google, Inc.");
+MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/memconsole.c b/drivers/firmware/google/memconsole.c
new file mode 100644
index 00000000000..2a90ba61361
--- /dev/null
+++ b/drivers/firmware/google/memconsole.c
@@ -0,0 +1,166 @@
+/*
+ * memconsole.c
+ *
+ * Infrastructure for importing the BIOS memory based console
+ * into the kernel log ringbuffer.
+ *
+ * Copyright 2010 Google Inc. All rights reserved.
+ */
+
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/dmi.h>
+#include <asm/bios_ebda.h>
+
+#define BIOS_MEMCONSOLE_V1_MAGIC	0xDEADBABE
+#define BIOS_MEMCONSOLE_V2_MAGIC	(('M')|('C'<<8)|('O'<<16)|('N'<<24))
+
+struct biosmemcon_ebda {
+	u32 signature;
+	union {
+		struct {
+			u8  enabled;
+			u32 buffer_addr;
+			u16 start;
+			u16 end;
+			u16 num_chars;
+			u8  wrapped;
+		} __packed v1;
+		struct {
+			u32 buffer_addr;
+			/* Misdocumented as number of pages! */
+			u16 num_bytes;
+			u16 start;
+			u16 end;
+		} __packed v2;
+	};
+} __packed;
+
+static char *memconsole_baseaddr;
+static size_t memconsole_length;
+
+static ssize_t memconsole_read(struct file *filp, struct kobject *kobp,
+			       struct bin_attribute *bin_attr, char *buf,
+			       loff_t pos, size_t count)
+{
+	return memory_read_from_buffer(buf, count, &pos, memconsole_baseaddr,
+				       memconsole_length);
+}
+
+static struct bin_attribute memconsole_bin_attr = {
+	.attr = {.name = "log", .mode = 0444},
+	.read = memconsole_read,
+};
+
+
+static void found_v1_header(struct biosmemcon_ebda *hdr)
+{
+	printk(KERN_INFO "BIOS console v1 EBDA structure found at %p\n", hdr);
+	printk(KERN_INFO "BIOS console buffer at 0x%.8x, "
+	       "start = %d, end = %d, num = %d\n",
+	       hdr->v1.buffer_addr, hdr->v1.start,
+	       hdr->v1.end, hdr->v1.num_chars);
+
+	memconsole_length = hdr->v1.num_chars;
+	memconsole_baseaddr = phys_to_virt(hdr->v1.buffer_addr);
+}
+
+static void found_v2_header(struct biosmemcon_ebda *hdr)
+{
+	printk(KERN_INFO "BIOS console v2 EBDA structure found at %p\n", hdr);
+	printk(KERN_INFO "BIOS console buffer at 0x%.8x, "
+	       "start = %d, end = %d, num_bytes = %d\n",
+	       hdr->v2.buffer_addr, hdr->v2.start,
+	       hdr->v2.end, hdr->v2.num_bytes);
+
+	memconsole_length = hdr->v2.end - hdr->v2.start;
+	memconsole_baseaddr = phys_to_virt(hdr->v2.buffer_addr
+					   + hdr->v2.start);
+}
+
+/*
+ * Search through the EBDA for the BIOS Memory Console, and
+ * set the global variables to point to it.  Return true if found.
+ */
+static bool found_memconsole(void)
+{
+	unsigned int address;
+	size_t length, cur;
+
+	address = get_bios_ebda();
+	if (!address) {
+		printk(KERN_INFO "BIOS EBDA non-existent.\n");
+		return false;
+	}
+
+	/* EBDA length is byte 0 of EBDA (in KB) */
+	length = *(u8 *)phys_to_virt(address);
+	length <<= 10; /* convert to bytes */
+
+	/*
+	 * Search through EBDA for BIOS memory console structure
+	 * note: signature is not necessarily dword-aligned
+	 */
+	for (cur = 0; cur < length; cur++) {
+		struct biosmemcon_ebda *hdr = phys_to_virt(address + cur);
+
+		/* memconsole v1 */
+		if (hdr->signature == BIOS_MEMCONSOLE_V1_MAGIC) {
+			found_v1_header(hdr);
+			return true;
+		}
+
+		/* memconsole v2 */
+		if (hdr->signature == BIOS_MEMCONSOLE_V2_MAGIC) {
+			found_v2_header(hdr);
+			return true;
+		}
+	}
+
+	printk(KERN_INFO "BIOS console EBDA structure not found!\n");
+	return false;
+}
+
+static struct dmi_system_id memconsole_dmi_table[] __initdata = {
+	{
+		.ident = "Google Board",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Google, Inc."),
+		},
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(dmi, memconsole_dmi_table);
+
+static int __init memconsole_init(void)
+{
+	int ret;
+
+	if (!dmi_check_system(memconsole_dmi_table))
+		return -ENODEV;
+
+	if (!found_memconsole())
+		return -ENODEV;
+
+	memconsole_bin_attr.size = memconsole_length;
+
+	ret = sysfs_create_bin_file(firmware_kobj, &memconsole_bin_attr);
+
+	return ret;
+}
+
+static void __exit memconsole_exit(void)
+{
+	sysfs_remove_bin_file(firmware_kobj, &memconsole_bin_attr);
+}
+
+module_init(memconsole_init);
+module_exit(memconsole_exit);
+
+MODULE_AUTHOR("Google, Inc.");
+MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c
index 2192456dfd6..f032e446fc1 100644
--- a/drivers/firmware/iscsi_ibft_find.c
+++ b/drivers/firmware/iscsi_ibft_find.c
@@ -42,7 +42,20 @@
 struct acpi_table_ibft *ibft_addr;
 EXPORT_SYMBOL_GPL(ibft_addr);
 
-#define IBFT_SIGN "iBFT"
+static const struct {
+	char *sign;
+} ibft_signs[] = {
+#ifdef CONFIG_ACPI
+	/*
+	 * One spec says "IBFT", the other says "iBFT". We have to check
+	 * for both.
+	 */
+	{ ACPI_SIG_IBFT },
+#endif
+	{ "iBFT" },
+	{ "BIFT" },	/* Broadcom iSCSI Offload */
+};
+
 #define IBFT_SIGN_LEN 4
 #define IBFT_START 0x80000 /* 512kB */
 #define IBFT_END 0x100000 /* 1MB */
@@ -62,6 +75,7 @@ static int __init find_ibft_in_mem(void)
 	unsigned long pos;
 	unsigned int len = 0;
 	void *virt;
+	int i;
 
 	for (pos = IBFT_START; pos < IBFT_END; pos += 16) {
 		/* The table can't be inside the VGA BIOS reserved space,
@@ -69,18 +83,23 @@ static int __init find_ibft_in_mem(void)
 		if (pos == VGA_MEM)
 			pos += VGA_SIZE;
 		virt = isa_bus_to_virt(pos);
-		if (memcmp(virt, IBFT_SIGN, IBFT_SIGN_LEN) == 0) {
-			unsigned long *addr =
-			    (unsigned long *)isa_bus_to_virt(pos + 4);
-			len = *addr;
-			/* if the length of the table extends past 1M,
-			 * the table cannot be valid. */
-			if (pos + len <= (IBFT_END-1)) {
-				ibft_addr = (struct acpi_table_ibft *)virt;
-				break;
+
+		for (i = 0; i < ARRAY_SIZE(ibft_signs); i++) {
+			if (memcmp(virt, ibft_signs[i].sign, IBFT_SIGN_LEN) ==
+			    0) {
+				unsigned long *addr =
+				    (unsigned long *)isa_bus_to_virt(pos + 4);
+				len = *addr;
+				/* if the length of the table extends past 1M,
+				 * the table cannot be valid. */
+				if (pos + len <= (IBFT_END-1)) {
+					ibft_addr = (struct acpi_table_ibft *)virt;
+					goto done;
+				}
 			}
 		}
 	}
+done:
 	return len;
 }
 /*
@@ -89,18 +108,12 @@ static int __init find_ibft_in_mem(void)
  */
 unsigned long __init find_ibft_region(unsigned long *sizep)
 {
-
+	int i;
 	ibft_addr = NULL;
 
 #ifdef CONFIG_ACPI
-	/*
-	 * One spec says "IBFT", the other says "iBFT". We have to check
-	 * for both.
-	 */
-	if (!ibft_addr)
-		acpi_table_parse(ACPI_SIG_IBFT, acpi_find_ibft);
-	if (!ibft_addr)
-		acpi_table_parse(IBFT_SIGN, acpi_find_ibft);
+	for (i = 0; i < ARRAY_SIZE(ibft_signs) && !ibft_addr; i++)
+		acpi_table_parse(ibft_signs[i].sign, acpi_find_ibft);
 #endif /* CONFIG_ACPI */
 
 	/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 5ed9d25d021..99dde874fbb 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -148,6 +148,7 @@ struct rdma_id_private {
 	u32			qp_num;
 	u8			srq;
 	u8			tos;
+	u8			reuseaddr;
 };
 
 struct cma_multicast {
@@ -712,6 +713,21 @@ static inline int cma_any_addr(struct sockaddr *addr)
 	return cma_zero_addr(addr) || cma_loopback_addr(addr);
 }
 
+static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst)
+{
+	if (src->sa_family != dst->sa_family)
+		return -1;
+
+	switch (src->sa_family) {
+	case AF_INET:
+		return ((struct sockaddr_in *) src)->sin_addr.s_addr !=
+		       ((struct sockaddr_in *) dst)->sin_addr.s_addr;
+	default:
+		return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr,
+				     &((struct sockaddr_in6 *) dst)->sin6_addr);
+	}
+}
+
 static inline __be16 cma_port(struct sockaddr *addr)
 {
 	if (addr->sa_family == AF_INET)
@@ -1564,50 +1580,6 @@ static void cma_listen_on_all(struct rdma_id_private *id_priv)
 	mutex_unlock(&lock);
 }
 
-int rdma_listen(struct rdma_cm_id *id, int backlog)
-{
-	struct rdma_id_private *id_priv;
-	int ret;
-
-	id_priv = container_of(id, struct rdma_id_private, id);
-	if (id_priv->state == CMA_IDLE) {
-		((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET;
-		ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr);
-		if (ret)
-			return ret;
-	}
-
-	if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN))
-		return -EINVAL;
-
-	id_priv->backlog = backlog;
-	if (id->device) {
-		switch (rdma_node_get_transport(id->device->node_type)) {
-		case RDMA_TRANSPORT_IB:
-			ret = cma_ib_listen(id_priv);
-			if (ret)
-				goto err;
-			break;
-		case RDMA_TRANSPORT_IWARP:
-			ret = cma_iw_listen(id_priv, backlog);
-			if (ret)
-				goto err;
-			break;
-		default:
-			ret = -ENOSYS;
-			goto err;
-		}
-	} else
-		cma_listen_on_all(id_priv);
-
-	return 0;
-err:
-	id_priv->backlog = 0;
-	cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND);
-	return ret;
-}
-EXPORT_SYMBOL(rdma_listen);
-
 void rdma_set_service_type(struct rdma_cm_id *id, int tos)
 {
 	struct rdma_id_private *id_priv;
@@ -2090,6 +2062,25 @@ err:
 }
 EXPORT_SYMBOL(rdma_resolve_addr);
 
+int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse)
+{
+	struct rdma_id_private *id_priv;
+	unsigned long flags;
+	int ret;
+
+	id_priv = container_of(id, struct rdma_id_private, id);
+	spin_lock_irqsave(&id_priv->lock, flags);
+	if (id_priv->state == CMA_IDLE) {
+		id_priv->reuseaddr = reuse;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+	spin_unlock_irqrestore(&id_priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_set_reuseaddr);
+
 static void cma_bind_port(struct rdma_bind_list *bind_list,
 			  struct rdma_id_private *id_priv)
 {
@@ -2165,41 +2156,71 @@ retry:
 	return -EADDRNOTAVAIL;
 }
 
-static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
+/*
+ * Check that the requested port is available.  This is called when trying to
+ * bind to a specific port, or when trying to listen on a bound port.  In
+ * the latter case, the provided id_priv may already be on the bind_list, but
+ * we still need to check that it's okay to start listening.
+ */
+static int cma_check_port(struct rdma_bind_list *bind_list,
+			  struct rdma_id_private *id_priv, uint8_t reuseaddr)
 {
 	struct rdma_id_private *cur_id;
-	struct sockaddr_in *sin, *cur_sin;
-	struct rdma_bind_list *bind_list;
+	struct sockaddr *addr, *cur_addr;
 	struct hlist_node *node;
+
+	addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
+	if (cma_any_addr(addr) && !reuseaddr)
+		return -EADDRNOTAVAIL;
+
+	hlist_for_each_entry(cur_id, node, &bind_list->owners, node) {
+		if (id_priv == cur_id)
+			continue;
+
+		if ((cur_id->state == CMA_LISTEN) ||
+		    !reuseaddr || !cur_id->reuseaddr) {
+			cur_addr = (struct sockaddr *) &cur_id->id.route.addr.src_addr;
+			if (cma_any_addr(cur_addr))
+				return -EADDRNOTAVAIL;
+
+			if (!cma_addr_cmp(addr, cur_addr))
+				return -EADDRINUSE;
+		}
+	}
+	return 0;
+}
+
+static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
+{
+	struct rdma_bind_list *bind_list;
 	unsigned short snum;
+	int ret;
 
-	sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
-	snum = ntohs(sin->sin_port);
+	snum = ntohs(cma_port((struct sockaddr *) &id_priv->id.route.addr.src_addr));
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
 	bind_list = idr_find(ps, snum);
-	if (!bind_list)
-		return cma_alloc_port(ps, id_priv, snum);
-
-	/*
-	 * We don't support binding to any address if anyone is bound to
-	 * a specific address on the same port.
-	 */
-	if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr))
-		return -EADDRNOTAVAIL;
-
-	hlist_for_each_entry(cur_id, node, &bind_list->owners, node) {
-		if (cma_any_addr((struct sockaddr *) &cur_id->id.route.addr.src_addr))
-			return -EADDRNOTAVAIL;
-
-		cur_sin = (struct sockaddr_in *) &cur_id->id.route.addr.src_addr;
-		if (sin->sin_addr.s_addr == cur_sin->sin_addr.s_addr)
-			return -EADDRINUSE;
+	if (!bind_list) {
+		ret = cma_alloc_port(ps, id_priv, snum);
+	} else {
+		ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr);
+		if (!ret)
+			cma_bind_port(bind_list, id_priv);
 	}
+	return ret;
+}
 
-	cma_bind_port(bind_list, id_priv);
-	return 0;
+static int cma_bind_listen(struct rdma_id_private *id_priv)
+{
+	struct rdma_bind_list *bind_list = id_priv->bind_list;
+	int ret = 0;
+
+	mutex_lock(&lock);
+	if (bind_list->owners.first->next)
+		ret = cma_check_port(bind_list, id_priv, 0);
+	mutex_unlock(&lock);
+	return ret;
 }
 
 static int cma_get_port(struct rdma_id_private *id_priv)
@@ -2253,6 +2274,56 @@ static int cma_check_linklocal(struct rdma_dev_addr *dev_addr,
 	return 0;
 }
 
+int rdma_listen(struct rdma_cm_id *id, int backlog)
+{
+	struct rdma_id_private *id_priv;
+	int ret;
+
+	id_priv = container_of(id, struct rdma_id_private, id);
+	if (id_priv->state == CMA_IDLE) {
+		((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET;
+		ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr);
+		if (ret)
+			return ret;
+	}
+
+	if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN))
+		return -EINVAL;
+
+	if (id_priv->reuseaddr) {
+		ret = cma_bind_listen(id_priv);
+		if (ret)
+			goto err;
+	}
+
+	id_priv->backlog = backlog;
+	if (id->device) {
+		switch (rdma_node_get_transport(id->device->node_type)) {
+		case RDMA_TRANSPORT_IB:
+			ret = cma_ib_listen(id_priv);
+			if (ret)
+				goto err;
+			break;
+		case RDMA_TRANSPORT_IWARP:
+			ret = cma_iw_listen(id_priv, backlog);
+			if (ret)
+				goto err;
+			break;
+		default:
+			ret = -ENOSYS;
+			goto err;
+		}
+	} else
+		cma_listen_on_all(id_priv);
+
+	return 0;
+err:
+	id_priv->backlog = 0;
+	cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_listen);
+
 int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 {
 	struct rdma_id_private *id_priv;
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 2a1e9ae134b..a9c042345c6 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -725,7 +725,7 @@ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv,
 	 */
 	clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
 	BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_SENT);
-	if (iw_event->status == IW_CM_EVENT_STATUS_ACCEPTED) {
+	if (iw_event->status == 0) {
 		cm_id_priv->id.local_addr = iw_event->local_addr;
 		cm_id_priv->id.remote_addr = iw_event->remote_addr;
 		cm_id_priv->state = IW_CM_STATE_ESTABLISHED;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index ec1e9da1488..b3fa798525b 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -883,6 +883,13 @@ static int ucma_set_option_id(struct ucma_context *ctx, int optname,
 		}
 		rdma_set_service_type(ctx->cm_id, *((u8 *) optval));
 		break;
+	case RDMA_OPTION_ID_REUSEADDR:
+		if (optlen != sizeof(int)) {
+			ret = -EINVAL;
+			break;
+		}
+		ret = rdma_set_reuseaddr(ctx->cm_id, *((int *) optval) ? 1 : 0);
+		break;
 	default:
 		ret = -ENOSYS;
 	}
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 9d8dcfab2b3..d7ee70fc917 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1198,9 +1198,7 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	}
 	PDBG("%s ep %p status %d error %d\n", __func__, ep,
 	     rpl->status, status2errno(rpl->status));
-	ep->com.wr_wait.ret = status2errno(rpl->status);
-	ep->com.wr_wait.done = 1;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 
 	return 0;
 }
@@ -1234,9 +1232,7 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_listen_ep *ep = lookup_stid(t, stid);
 
 	PDBG("%s ep %p\n", __func__, ep);
-	ep->com.wr_wait.ret = status2errno(rpl->status);
-	ep->com.wr_wait.done = 1;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 	return 0;
 }
 
@@ -1466,7 +1462,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_qp_attributes attrs;
 	int disconnect = 1;
 	int release = 0;
-	int closing = 0;
+	int abort = 0;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(hdr);
 
@@ -1492,23 +1488,22 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		 * in rdma connection migration (see c4iw_accept_cr()).
 		 */
 		__state_set(&ep->com, CLOSING);
-		ep->com.wr_wait.done = 1;
-		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.wr_wait.wait);
+		c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 		break;
 	case MPA_REP_SENT:
 		__state_set(&ep->com, CLOSING);
-		ep->com.wr_wait.done = 1;
-		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.wr_wait.wait);
+		c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 		break;
 	case FPDU_MODE:
 		start_ep_timer(ep);
 		__state_set(&ep->com, CLOSING);
-		closing = 1;
+		attrs.next_state = C4IW_QP_STATE_CLOSING;
+		abort = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
+				       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 		peer_close_upcall(ep);
+		disconnect = 1;
 		break;
 	case ABORTING:
 		disconnect = 0;
@@ -1536,11 +1531,6 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		BUG_ON(1);
 	}
 	mutex_unlock(&ep->com.mutex);
-	if (closing) {
-		attrs.next_state = C4IW_QP_STATE_CLOSING;
-		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
-			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
-	}
 	if (disconnect)
 		c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
 	if (release)
@@ -1581,9 +1571,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 	/*
 	 * Wake up any threads in rdma_init() or rdma_fini().
 	 */
-	ep->com.wr_wait.done = 1;
-	ep->com.wr_wait.ret = -ECONNRESET;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 
 	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
@@ -1710,14 +1698,14 @@ static int terminate(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = lookup_tid(t, tid);
 	BUG_ON(!ep);
 
-	if (ep->com.qp) {
+	if (ep && ep->com.qp) {
 		printk(KERN_WARNING MOD "TERM received tid %u qpid %u\n", tid,
 		       ep->com.qp->wq.sq.qid);
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
 		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
 			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 	} else
-		printk(KERN_WARNING MOD "TERM received tid %u no qp\n", tid);
+		printk(KERN_WARNING MOD "TERM received tid %u no ep/qp\n", tid);
 
 	return 0;
 }
@@ -2296,14 +2284,8 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 		ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
 		wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
 		PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
-		if (wr_waitp) {
-			if (ret)
-				wr_waitp->ret = -ret;
-			else
-				wr_waitp->ret = 0;
-			wr_waitp->done = 1;
-			wake_up(&wr_waitp->wait);
-		}
+		if (wr_waitp)
+			c4iw_wake_up(wr_waitp, ret ? -ret : 0);
 		kfree_skb(skb);
 		break;
 	case 2:
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index e29172c2afc..40a13cc633a 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -44,7 +44,7 @@ MODULE_DESCRIPTION("Chelsio T4 RDMA Driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(DRV_VERSION);
 
-static LIST_HEAD(dev_list);
+static LIST_HEAD(uld_ctx_list);
 static DEFINE_MUTEX(dev_mutex);
 
 static struct dentry *c4iw_debugfs_root;
@@ -370,18 +370,23 @@ static void c4iw_rdev_close(struct c4iw_rdev *rdev)
 	c4iw_destroy_resource(&rdev->resource);
 }
 
-static void c4iw_remove(struct c4iw_dev *dev)
+struct uld_ctx {
+	struct list_head entry;
+	struct cxgb4_lld_info lldi;
+	struct c4iw_dev *dev;
+};
+
+static void c4iw_remove(struct uld_ctx *ctx)
 {
-	PDBG("%s c4iw_dev %p\n", __func__,  dev);
-	list_del(&dev->entry);
-	if (dev->registered)
-		c4iw_unregister_device(dev);
-	c4iw_rdev_close(&dev->rdev);
-	idr_destroy(&dev->cqidr);
-	idr_destroy(&dev->qpidr);
-	idr_destroy(&dev->mmidr);
-	iounmap(dev->rdev.oc_mw_kva);
-	ib_dealloc_device(&dev->ibdev);
+	PDBG("%s c4iw_dev %p\n", __func__,  ctx->dev);
+	c4iw_unregister_device(ctx->dev);
+	c4iw_rdev_close(&ctx->dev->rdev);
+	idr_destroy(&ctx->dev->cqidr);
+	idr_destroy(&ctx->dev->qpidr);
+	idr_destroy(&ctx->dev->mmidr);
+	iounmap(ctx->dev->rdev.oc_mw_kva);
+	ib_dealloc_device(&ctx->dev->ibdev);
+	ctx->dev = NULL;
 }
 
 static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
@@ -392,7 +397,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 	devp = (struct c4iw_dev *)ib_alloc_device(sizeof(*devp));
 	if (!devp) {
 		printk(KERN_ERR MOD "Cannot allocate ib device\n");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	devp->rdev.lldi = *infop;
 
@@ -402,27 +407,23 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 	devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
 					       devp->rdev.lldi.vr->ocq.size);
 
-	printk(KERN_INFO MOD "ocq memory: "
+	PDBG(KERN_INFO MOD "ocq memory: "
 	       "hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
 	       devp->rdev.lldi.vr->ocq.start, devp->rdev.lldi.vr->ocq.size,
 	       devp->rdev.oc_mw_pa, devp->rdev.oc_mw_kva);
 
-	mutex_lock(&dev_mutex);
-
 	ret = c4iw_rdev_open(&devp->rdev);
 	if (ret) {
 		mutex_unlock(&dev_mutex);
 		printk(KERN_ERR MOD "Unable to open CXIO rdev err %d\n", ret);
 		ib_dealloc_device(&devp->ibdev);
-		return NULL;
+		return ERR_PTR(ret);
 	}
 
 	idr_init(&devp->cqidr);
 	idr_init(&devp->qpidr);
 	idr_init(&devp->mmidr);
 	spin_lock_init(&devp->lock);
-	list_add_tail(&devp->entry, &dev_list);
-	mutex_unlock(&dev_mutex);
 
 	if (c4iw_debugfs_root) {
 		devp->debugfs_root = debugfs_create_dir(
@@ -435,7 +436,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 
 static void *c4iw_uld_add(const struct cxgb4_lld_info *infop)
 {
-	struct c4iw_dev *dev;
+	struct uld_ctx *ctx;
 	static int vers_printed;
 	int i;
 
@@ -443,25 +444,33 @@ static void *c4iw_uld_add(const struct cxgb4_lld_info *infop)
 		printk(KERN_INFO MOD "Chelsio T4 RDMA Driver - version %s\n",
 		       DRV_VERSION);
 
-	dev = c4iw_alloc(infop);
-	if (!dev)
+	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
+	if (!ctx) {
+		ctx = ERR_PTR(-ENOMEM);
 		goto out;
+	}
+	ctx->lldi = *infop;
 
 	PDBG("%s found device %s nchan %u nrxq %u ntxq %u nports %u\n",
-	     __func__, pci_name(dev->rdev.lldi.pdev),
-	     dev->rdev.lldi.nchan, dev->rdev.lldi.nrxq,
-	     dev->rdev.lldi.ntxq, dev->rdev.lldi.nports);
+	     __func__, pci_name(ctx->lldi.pdev),
+	     ctx->lldi.nchan, ctx->lldi.nrxq,
+	     ctx->lldi.ntxq, ctx->lldi.nports);
+
+	mutex_lock(&dev_mutex);
+	list_add_tail(&ctx->entry, &uld_ctx_list);
+	mutex_unlock(&dev_mutex);
 
-	for (i = 0; i < dev->rdev.lldi.nrxq; i++)
-		PDBG("rxqid[%u] %u\n", i, dev->rdev.lldi.rxq_ids[i]);
+	for (i = 0; i < ctx->lldi.nrxq; i++)
+		PDBG("rxqid[%u] %u\n", i, ctx->lldi.rxq_ids[i]);
 out:
-	return dev;
+	return ctx;
 }
 
 static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 			const struct pkt_gl *gl)
 {
-	struct c4iw_dev *dev = handle;
+	struct uld_ctx *ctx = handle;
+	struct c4iw_dev *dev = ctx->dev;
 	struct sk_buff *skb;
 	const struct cpl_act_establish *rpl;
 	unsigned int opcode;
@@ -503,47 +512,49 @@ nomem:
 
 static int c4iw_uld_state_change(void *handle, enum cxgb4_state new_state)
 {
-	struct c4iw_dev *dev = handle;
+	struct uld_ctx *ctx = handle;
 
 	PDBG("%s new_state %u\n", __func__, new_state);
 	switch (new_state) {
 	case CXGB4_STATE_UP:
-		printk(KERN_INFO MOD "%s: Up\n", pci_name(dev->rdev.lldi.pdev));
-		if (!dev->registered) {
-			int ret;
-			ret = c4iw_register_device(dev);
-			if (ret)
+		printk(KERN_INFO MOD "%s: Up\n", pci_name(ctx->lldi.pdev));
+		if (!ctx->dev) {
+			int ret = 0;
+
+			ctx->dev = c4iw_alloc(&ctx->lldi);
+			if (!IS_ERR(ctx->dev))
+				ret = c4iw_register_device(ctx->dev);
+			if (IS_ERR(ctx->dev) || ret)
 				printk(KERN_ERR MOD
 				       "%s: RDMA registration failed: %d\n",
-				       pci_name(dev->rdev.lldi.pdev), ret);
+				       pci_name(ctx->lldi.pdev), ret);
 		}
 		break;
 	case CXGB4_STATE_DOWN:
 		printk(KERN_INFO MOD "%s: Down\n",
-		       pci_name(dev->rdev.lldi.pdev));
-		if (dev->registered)
-			c4iw_unregister_device(dev);
+		       pci_name(ctx->lldi.pdev));
+		if (ctx->dev)
+			c4iw_remove(ctx);
 		break;
 	case CXGB4_STATE_START_RECOVERY:
 		printk(KERN_INFO MOD "%s: Fatal Error\n",
-		       pci_name(dev->rdev.lldi.pdev));
-		dev->rdev.flags |= T4_FATAL_ERROR;
-		if (dev->registered) {
+		       pci_name(ctx->lldi.pdev));
+		if (ctx->dev) {
 			struct ib_event event;
 
+			ctx->dev->rdev.flags |= T4_FATAL_ERROR;
 			memset(&event, 0, sizeof event);
 			event.event  = IB_EVENT_DEVICE_FATAL;
-			event.device = &dev->ibdev;
+			event.device = &ctx->dev->ibdev;
 			ib_dispatch_event(&event);
-			c4iw_unregister_device(dev);
+			c4iw_remove(ctx);
 		}
 		break;
 	case CXGB4_STATE_DETACH:
 		printk(KERN_INFO MOD "%s: Detach\n",
-		       pci_name(dev->rdev.lldi.pdev));
-		mutex_lock(&dev_mutex);
-		c4iw_remove(dev);
-		mutex_unlock(&dev_mutex);
+		       pci_name(ctx->lldi.pdev));
+		if (ctx->dev)
+			c4iw_remove(ctx);
 		break;
 	}
 	return 0;
@@ -576,11 +587,13 @@ static int __init c4iw_init_module(void)
 
 static void __exit c4iw_exit_module(void)
 {
-	struct c4iw_dev *dev, *tmp;
+	struct uld_ctx *ctx, *tmp;
 
 	mutex_lock(&dev_mutex);
-	list_for_each_entry_safe(dev, tmp, &dev_list, entry) {
-		c4iw_remove(dev);
+	list_for_each_entry_safe(ctx, tmp, &uld_ctx_list, entry) {
+		if (ctx->dev)
+			c4iw_remove(ctx);
+		kfree(ctx);
 	}
 	mutex_unlock(&dev_mutex);
 	cxgb4_unregister_uld(CXGB4_ULD_RDMA);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 9f6166f5926..35d2a5dd9bb 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -131,42 +131,58 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev)
 
 #define C4IW_WR_TO (10*HZ)
 
+enum {
+	REPLY_READY = 0,
+};
+
 struct c4iw_wr_wait {
 	wait_queue_head_t wait;
-	int done;
+	unsigned long status;
 	int ret;
 };
 
 static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
 {
 	wr_waitp->ret = 0;
-	wr_waitp->done = 0;
+	wr_waitp->status = 0;
 	init_waitqueue_head(&wr_waitp->wait);
 }
 
+static inline void c4iw_wake_up(struct c4iw_wr_wait *wr_waitp, int ret)
+{
+	wr_waitp->ret = ret;
+	set_bit(REPLY_READY, &wr_waitp->status);
+	wake_up(&wr_waitp->wait);
+}
+
 static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
 				 struct c4iw_wr_wait *wr_waitp,
 				 u32 hwtid, u32 qpid,
 				 const char *func)
 {
 	unsigned to = C4IW_WR_TO;
-	do {
+	int ret;
 
-		wait_event_timeout(wr_waitp->wait, wr_waitp->done, to);
-		if (!wr_waitp->done) {
+	do {
+		ret = wait_event_timeout(wr_waitp->wait,
+			test_and_clear_bit(REPLY_READY, &wr_waitp->status), to);
+		if (!ret) {
 			printk(KERN_ERR MOD "%s - Device %s not responding - "
 			       "tid %u qpid %u\n", func,
 			       pci_name(rdev->lldi.pdev), hwtid, qpid);
+			if (c4iw_fatal_error(rdev)) {
+				wr_waitp->ret = -EIO;
+				break;
+			}
 			to = to << 2;
 		}
-	} while (!wr_waitp->done);
+	} while (!ret);
 	if (wr_waitp->ret)
-		printk(KERN_WARNING MOD "%s: FW reply %d tid %u qpid %u\n",
-		       pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);
+		PDBG("%s: FW reply %d tid %u qpid %u\n",
+		     pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);
 	return wr_waitp->ret;
 }
 
-
 struct c4iw_dev {
 	struct ib_device ibdev;
 	struct c4iw_rdev rdev;
@@ -175,9 +191,7 @@ struct c4iw_dev {
 	struct idr qpidr;
 	struct idr mmidr;
 	spinlock_t lock;
-	struct list_head entry;
 	struct dentry *debugfs_root;
-	u8 registered;
 };
 
 static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index f66dd8bf512..5b9e4220ca0 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -516,7 +516,6 @@ int c4iw_register_device(struct c4iw_dev *dev)
 		if (ret)
 			goto bail2;
 	}
-	dev->registered = 1;
 	return 0;
 bail2:
 	ib_unregister_device(&dev->ibdev);
@@ -535,6 +534,5 @@ void c4iw_unregister_device(struct c4iw_dev *dev)
 				   c4iw_class_attributes[i]);
 	ib_unregister_device(&dev->ibdev);
 	kfree(dev->ibdev.iwcm);
-	dev->registered = 0;
 	return;
 }
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 70a5a3c646d..3b773b05a89 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -214,7 +214,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		V_FW_RI_RES_WR_HOSTFCMODE(0) |	/* no host cidx updates */
 		V_FW_RI_RES_WR_CPRIO(0) |	/* don't keep in chip cache */
 		V_FW_RI_RES_WR_PCIECHN(0) |	/* set by uP at ri_init time */
-		t4_sq_onchip(&wq->sq) ? F_FW_RI_RES_WR_ONCHIP : 0 |
+		(t4_sq_onchip(&wq->sq) ? F_FW_RI_RES_WR_ONCHIP : 0) |
 		V_FW_RI_RES_WR_IQID(scq->cqid));
 	res->u.sqrq.dcaen_to_eqsize = cpu_to_be32(
 		V_FW_RI_RES_WR_DCAEN(0) |
@@ -1210,7 +1210,6 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			if (ret) {
 				if (internal)
 					c4iw_get_ep(&qhp->ep->com);
-				disconnect = abort = 1;
 				goto err;
 			}
 			break;
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index 58c0e417bc3..be24ac72611 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -398,7 +398,6 @@ static int __devinit ipath_init_one(struct pci_dev *pdev,
 	struct ipath_devdata *dd;
 	unsigned long long addr;
 	u32 bar0 = 0, bar1 = 0;
-	u8 rev;
 
 	dd = ipath_alloc_devdata(pdev);
 	if (IS_ERR(dd)) {
@@ -540,13 +539,7 @@ static int __devinit ipath_init_one(struct pci_dev *pdev,
 		goto bail_regions;
 	}
 
-	ret = pci_read_config_byte(pdev, PCI_REVISION_ID, &rev);
-	if (ret) {
-		ipath_dev_err(dd, "Failed to read PCI revision ID unit "
-			      "%u: err %d\n", dd->ipath_unit, -ret);
-		goto bail_regions;	/* shouldn't ever happen */
-	}
-	dd->ipath_pcirev = rev;
+	dd->ipath_pcirev = pdev->revision;
 
 #if defined(__powerpc__)
 	/* There isn't a generic way to specify writethrough mappings */
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 33c7eedaba6..e74cdf9ef47 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -2563,7 +2563,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp)
 	u16 last_ae;
 	u8 original_hw_tcp_state;
 	u8 original_ibqp_state;
-	enum iw_cm_event_status disconn_status = IW_CM_EVENT_STATUS_OK;
+	int disconn_status = 0;
 	int issue_disconn = 0;
 	int issue_close = 0;
 	int issue_flush = 0;
@@ -2605,7 +2605,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp)
 			(last_ae == NES_AEQE_AEID_LLP_CONNECTION_RESET))) {
 		issue_disconn = 1;
 		if (last_ae == NES_AEQE_AEID_LLP_CONNECTION_RESET)
-			disconn_status = IW_CM_EVENT_STATUS_RESET;
+			disconn_status = -ECONNRESET;
 	}
 
 	if (((original_hw_tcp_state == NES_AEQE_TCP_STATE_CLOSED) ||
@@ -2666,7 +2666,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp)
 			cm_id->provider_data = nesqp;
 			/* Send up the close complete event */
 			cm_event.event = IW_CM_EVENT_CLOSE;
-			cm_event.status = IW_CM_EVENT_STATUS_OK;
+			cm_event.status = 0;
 			cm_event.provider_data = cm_id->provider_data;
 			cm_event.local_addr = cm_id->local_addr;
 			cm_event.remote_addr = cm_id->remote_addr;
@@ -2966,7 +2966,7 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	nes_add_ref(&nesqp->ibqp);
 
 	cm_event.event = IW_CM_EVENT_ESTABLISHED;
-	cm_event.status = IW_CM_EVENT_STATUS_ACCEPTED;
+	cm_event.status = 0;
 	cm_event.provider_data = (void *)nesqp;
 	cm_event.local_addr = cm_id->local_addr;
 	cm_event.remote_addr = cm_id->remote_addr;
@@ -3377,7 +3377,7 @@ static void cm_event_connected(struct nes_cm_event *event)
 
 	/* notify OF layer we successfully created the requested connection */
 	cm_event.event = IW_CM_EVENT_CONNECT_REPLY;
-	cm_event.status = IW_CM_EVENT_STATUS_ACCEPTED;
+	cm_event.status = 0;
 	cm_event.provider_data = cm_id->provider_data;
 	cm_event.local_addr.sin_family = AF_INET;
 	cm_event.local_addr.sin_port = cm_id->local_addr.sin_port;
@@ -3484,7 +3484,7 @@ static void cm_event_reset(struct nes_cm_event *event)
 	nesqp->cm_id = NULL;
 	/* cm_id->provider_data = NULL; */
 	cm_event.event = IW_CM_EVENT_DISCONNECT;
-	cm_event.status = IW_CM_EVENT_STATUS_RESET;
+	cm_event.status = -ECONNRESET;
 	cm_event.provider_data = cm_id->provider_data;
 	cm_event.local_addr = cm_id->local_addr;
 	cm_event.remote_addr = cm_id->remote_addr;
@@ -3495,7 +3495,7 @@ static void cm_event_reset(struct nes_cm_event *event)
 	ret = cm_id->event_handler(cm_id, &cm_event);
 	atomic_inc(&cm_closes);
 	cm_event.event = IW_CM_EVENT_CLOSE;
-	cm_event.status = IW_CM_EVENT_STATUS_OK;
+	cm_event.status = 0;
 	cm_event.provider_data = cm_id->provider_data;
 	cm_event.local_addr = cm_id->local_addr;
 	cm_event.remote_addr = cm_id->remote_addr;
@@ -3534,7 +3534,7 @@ static void cm_event_mpa_req(struct nes_cm_event *event)
 			cm_node, cm_id, jiffies);
 
 	cm_event.event = IW_CM_EVENT_CONNECT_REQUEST;
-	cm_event.status = IW_CM_EVENT_STATUS_OK;
+	cm_event.status = 0;
 	cm_event.provider_data = (void *)cm_node;
 
 	cm_event.local_addr.sin_family = AF_INET;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 26d8018c0a7..95ca93ceeda 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1484,7 +1484,7 @@ static int nes_destroy_qp(struct ib_qp *ibqp)
 			(nesqp->ibqp_state == IB_QPS_RTR)) && (nesqp->cm_id)) {
 		cm_id = nesqp->cm_id;
 		cm_event.event = IW_CM_EVENT_CONNECT_REPLY;
-		cm_event.status = IW_CM_EVENT_STATUS_TIMEOUT;
+		cm_event.status = -ETIMEDOUT;
 		cm_event.local_addr = cm_id->local_addr;
 		cm_event.remote_addr = cm_id->remote_addr;
 		cm_event.private_data = NULL;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 6bab3eaea70..9f53e68a096 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -7534,7 +7534,8 @@ static int serdes_7322_init_new(struct qib_pportdata *ppd)
 	ibsd_wr_allchans(ppd, 4, (1 << 10), BMASK(10, 10));
 	tstart = get_jiffies_64();
 	while (chan_done &&
-	       !time_after64(tstart, tstart + msecs_to_jiffies(500))) {
+	       !time_after64(get_jiffies_64(),
+			tstart + msecs_to_jiffies(500))) {
 		msleep(20);
 		for (chan = 0; chan < SERDES_CHANS; ++chan) {
 			rxcaldone = ahb_mod(ppd->dd, IBSD(ppd->hw_pidx),
diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c
index 48b6674cbc4..891cc2ff5f0 100644
--- a/drivers/infiniband/hw/qib/qib_pcie.c
+++ b/drivers/infiniband/hw/qib/qib_pcie.c
@@ -526,11 +526,8 @@ static int qib_tune_pcie_coalesce(struct qib_devdata *dd)
 	 */
 	devid = parent->device;
 	if (devid >= 0x25e2 && devid <= 0x25fa) {
-		u8 rev;
-
 		/* 5000 P/V/X/Z */
-		pci_read_config_byte(parent, PCI_REVISION_ID, &rev);
-		if (rev <= 0xb2)
+		if (parent->revision <= 0xb2)
 			bits = 1U << 10;
 		else
 			bits = 7U << 10;
diff --git a/drivers/input/keyboard/atakbd.c b/drivers/input/keyboard/atakbd.c
index 1839194ea98..10bcd4ae540 100644
--- a/drivers/input/keyboard/atakbd.c
+++ b/drivers/input/keyboard/atakbd.c
@@ -223,8 +223,9 @@ static int __init atakbd_init(void)
 		return -ENODEV;
 
 	// need to init core driver if not already done so
-	if (atari_keyb_init())
-		return -ENODEV;
+	error = atari_keyb_init();
+	if (error)
+		return error;
 
 	atakbd_dev = input_allocate_device();
 	if (!atakbd_dev)
diff --git a/drivers/input/mouse/atarimouse.c b/drivers/input/mouse/atarimouse.c
index adf45b3040e..5c4a692bf73 100644
--- a/drivers/input/mouse/atarimouse.c
+++ b/drivers/input/mouse/atarimouse.c
@@ -77,15 +77,15 @@ static void atamouse_interrupt(char *buf)
 #endif
 
 	/* only relative events get here */
-	dx =  buf[1];
-	dy = -buf[2];
+	dx = buf[1];
+	dy = buf[2];
 
 	input_report_rel(atamouse_dev, REL_X, dx);
 	input_report_rel(atamouse_dev, REL_Y, dy);
 
-	input_report_key(atamouse_dev, BTN_LEFT,   buttons & 0x1);
+	input_report_key(atamouse_dev, BTN_LEFT,   buttons & 0x4);
 	input_report_key(atamouse_dev, BTN_MIDDLE, buttons & 0x2);
-	input_report_key(atamouse_dev, BTN_RIGHT,  buttons & 0x4);
+	input_report_key(atamouse_dev, BTN_RIGHT,  buttons & 0x1);
 
 	input_sync(atamouse_dev);
 
@@ -108,7 +108,7 @@ static int atamouse_open(struct input_dev *dev)
 static void atamouse_close(struct input_dev *dev)
 {
 	ikbd_mouse_disable();
-	atari_mouse_interrupt_hook = NULL;
+	atari_input_mouse_interrupt_hook = NULL;
 }
 
 static int __init atamouse_init(void)
@@ -118,8 +118,9 @@ static int __init atamouse_init(void)
 	if (!MACH_IS_ATARI || !ATARIHW_PRESENT(ST_MFP))
 		return -ENODEV;
 
-	if (!atari_keyb_init())
-		return -ENODEV;
+	error = atari_keyb_init();
+	if (error)
+		return error;
 
 	atamouse_dev = input_allocate_device();
 	if (!atamouse_dev)
diff --git a/drivers/lguest/Kconfig b/drivers/lguest/Kconfig
index 0aaa0597a62..34ae49dc557 100644
--- a/drivers/lguest/Kconfig
+++ b/drivers/lguest/Kconfig
@@ -5,8 +5,10 @@ config LGUEST
 	---help---
 	  This is a very simple module which allows you to run
 	  multiple instances of the same Linux kernel, using the
-	  "lguest" command found in the Documentation/lguest directory.
+	  "lguest" command found in the Documentation/virtual/lguest
+	  directory.
+
 	  Note that "lguest" is pronounced to rhyme with "fell quest",
-	  not "rustyvisor".  See Documentation/lguest/lguest.txt.
+	  not "rustyvisor". See Documentation/virtual/lguest/lguest.txt.
 
 	  If unsure, say N.  If curious, say M.  If masochistic, say Y.
diff --git a/drivers/lguest/Makefile b/drivers/lguest/Makefile
index 7d463c26124..8ac947c7e7c 100644
--- a/drivers/lguest/Makefile
+++ b/drivers/lguest/Makefile
@@ -18,7 +18,7 @@ Mastery: PREFIX=M
 Beer:
 	@for f in Preparation Guest Drivers Launcher Host Switcher Mastery; do echo "{==- $$f -==}"; make -s $$f; done; echo "{==-==}"
 Preparation Preparation! Guest Drivers Launcher Host Switcher Mastery:
-	@sh ../../Documentation/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'`
+	@sh ../../Documentation/virtual/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'`
 Puppy:
 	@clear
 	@printf "      __  \n (___()'\`;\n /,    /\`\n \\\\\\\"--\\\\\\   \n"
diff --git a/drivers/misc/ti-st/Kconfig b/drivers/misc/ti-st/Kconfig
index 2c8c3f39710..abb5de1afce 100644
--- a/drivers/misc/ti-st/Kconfig
+++ b/drivers/misc/ti-st/Kconfig
@@ -5,7 +5,7 @@
 menu "Texas Instruments shared transport line discipline"
 config TI_ST
 	tristate "Shared transport core driver"
-	depends on RFKILL
+	depends on NET && GPIOLIB
 	select FW_LOADER
 	help
 	  This enables the shared transport core driver for TI
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 486117f72c9..f91f82eabda 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -43,13 +43,15 @@ static void add_channel_to_table(struct st_data_s *st_gdata,
 	pr_info("%s: id %d\n", __func__, new_proto->chnl_id);
 	/* list now has the channel id as index itself */
 	st_gdata->list[new_proto->chnl_id] = new_proto;
+	st_gdata->is_registered[new_proto->chnl_id] = true;
 }
 
 static void remove_channel_from_table(struct st_data_s *st_gdata,
 		struct st_proto_s *proto)
 {
 	pr_info("%s: id %d\n", __func__, proto->chnl_id);
-	st_gdata->list[proto->chnl_id] = NULL;
+/*	st_gdata->list[proto->chnl_id] = NULL; */
+	st_gdata->is_registered[proto->chnl_id] = false;
 }
 
 /*
@@ -104,7 +106,7 @@ void st_send_frame(unsigned char chnl_id, struct st_data_s *st_gdata)
 
 	if (unlikely
 	    (st_gdata == NULL || st_gdata->rx_skb == NULL
-	     || st_gdata->list[chnl_id] == NULL)) {
+	     || st_gdata->is_registered[chnl_id] == false)) {
 		pr_err("chnl_id %d not registered, no data to send?",
 			   chnl_id);
 		kfree_skb(st_gdata->rx_skb);
@@ -141,14 +143,15 @@ void st_reg_complete(struct st_data_s *st_gdata, char err)
 	unsigned char i = 0;
 	pr_info(" %s ", __func__);
 	for (i = 0; i < ST_MAX_CHANNELS; i++) {
-		if (likely(st_gdata != NULL && st_gdata->list[i] != NULL &&
-			   st_gdata->list[i]->reg_complete_cb != NULL)) {
+		if (likely(st_gdata != NULL &&
+			st_gdata->is_registered[i] == true &&
+				st_gdata->list[i]->reg_complete_cb != NULL)) {
 			st_gdata->list[i]->reg_complete_cb
 				(st_gdata->list[i]->priv_data, err);
 			pr_info("protocol %d's cb sent %d\n", i, err);
 			if (err) { /* cleanup registered protocol */
 				st_gdata->protos_registered--;
-				st_gdata->list[i] = NULL;
+				st_gdata->is_registered[i] = false;
 			}
 		}
 	}
@@ -475,9 +478,9 @@ void kim_st_list_protocols(struct st_data_s *st_gdata, void *buf)
 {
 	seq_printf(buf, "[%d]\nBT=%c\nFM=%c\nGPS=%c\n",
 			st_gdata->protos_registered,
-			st_gdata->list[0x04] != NULL ? 'R' : 'U',
-			st_gdata->list[0x08] != NULL ? 'R' : 'U',
-			st_gdata->list[0x09] != NULL ? 'R' : 'U');
+			st_gdata->is_registered[0x04] == true ? 'R' : 'U',
+			st_gdata->is_registered[0x08] == true ? 'R' : 'U',
+			st_gdata->is_registered[0x09] == true ? 'R' : 'U');
 }
 
 /********************************************************************/
@@ -504,7 +507,7 @@ long st_register(struct st_proto_s *new_proto)
 		return -EPROTONOSUPPORT;
 	}
 
-	if (st_gdata->list[new_proto->chnl_id] != NULL) {
+	if (st_gdata->is_registered[new_proto->chnl_id] == true) {
 		pr_err("chnl_id %d already registered", new_proto->chnl_id);
 		return -EALREADY;
 	}
@@ -563,7 +566,7 @@ long st_register(struct st_proto_s *new_proto)
 		/* check for already registered once more,
 		 * since the above check is old
 		 */
-		if (st_gdata->list[new_proto->chnl_id] != NULL) {
+		if (st_gdata->is_registered[new_proto->chnl_id] == true) {
 			pr_err(" proto %d already registered ",
 				   new_proto->chnl_id);
 			return -EALREADY;
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index b4488c8f6b2..5da93ee6f6b 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -30,6 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
+#include <linux/sysfs.h>
 #include <linux/tty.h>
 
 #include <linux/skbuff.h>
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 44b1f46458c..5069111c81c 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -260,6 +260,13 @@ config MTD_BCM963XX
 	  Support for parsing CFE image tag and creating MTD partitions on
 	  Broadcom BCM63xx boards.
 
+config MTD_LANTIQ
+	tristate "Lantiq SoC NOR support"
+	depends on LANTIQ
+	select MTD_PARTITIONS
+	help
+	  Support for NOR flash attached to the Lantiq SoC's External Bus Unit.
+
 config MTD_DILNETPC
 	tristate "CFI Flash device mapped on DIL/Net PC"
 	depends on X86 && MTD_PARTITIONS && MTD_CFI_INTELEXT && BROKEN
diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile
index 08533bd5cba..6adf4c9b905 100644
--- a/drivers/mtd/maps/Makefile
+++ b/drivers/mtd/maps/Makefile
@@ -60,3 +60,4 @@ obj-$(CONFIG_MTD_VMU)		+= vmu-flash.o
 obj-$(CONFIG_MTD_GPIO_ADDR)	+= gpio-addr-flash.o
 obj-$(CONFIG_MTD_BCM963XX)	+= bcm963xx-flash.o
 obj-$(CONFIG_MTD_LATCH_ADDR)	+= latch-addr-flash.o
+obj-$(CONFIG_MTD_LANTIQ)	+= lantiq-flash.o
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
new file mode 100644
index 00000000000..a90cabd7b84
--- /dev/null
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -0,0 +1,251 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2004 Liu Peng Infineon IFAP DC COM CPE
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/map.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/cfi.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/physmap.h>
+
+#include <lantiq_soc.h>
+#include <lantiq_platform.h>
+
+/*
+ * The NOR flash is connected to the same external bus unit (EBU) as PCI.
+ * To make PCI work we need to enable the endianness swapping for the address
+ * written to the EBU. This endianness swapping works for PCI correctly but
+ * fails for attached NOR devices. To workaround this we need to use a complex
+ * map. The workaround involves swapping all addresses whilst probing the chip.
+ * Once probing is complete we stop swapping the addresses but swizzle the
+ * unlock addresses to ensure that access to the NOR device works correctly.
+ */
+
+enum {
+	LTQ_NOR_PROBING,
+	LTQ_NOR_NORMAL
+};
+
+struct ltq_mtd {
+	struct resource *res;
+	struct mtd_info *mtd;
+	struct map_info *map;
+};
+
+static char ltq_map_name[] = "ltq_nor";
+
+static map_word
+ltq_read16(struct map_info *map, unsigned long adr)
+{
+	unsigned long flags;
+	map_word temp;
+
+	if (map->map_priv_1 == LTQ_NOR_PROBING)
+		adr ^= 2;
+	spin_lock_irqsave(&ebu_lock, flags);
+	temp.x[0] = *(u16 *)(map->virt + adr);
+	spin_unlock_irqrestore(&ebu_lock, flags);
+	return temp;
+}
+
+static void
+ltq_write16(struct map_info *map, map_word d, unsigned long adr)
+{
+	unsigned long flags;
+
+	if (map->map_priv_1 == LTQ_NOR_PROBING)
+		adr ^= 2;
+	spin_lock_irqsave(&ebu_lock, flags);
+	*(u16 *)(map->virt + adr) = d.x[0];
+	spin_unlock_irqrestore(&ebu_lock, flags);
+}
+
+/*
+ * The following 2 functions copy data between iomem and a cached memory
+ * section. As memcpy() makes use of pre-fetching we cannot use it here.
+ * The normal alternative of using memcpy_{to,from}io also makes use of
+ * memcpy() on MIPS so it is not applicable either. We are therefore stuck
+ * with having to use our own loop.
+ */
+static void
+ltq_copy_from(struct map_info *map, void *to,
+	unsigned long from, ssize_t len)
+{
+	unsigned char *f = (unsigned char *)map->virt + from;
+	unsigned char *t = (unsigned char *)to;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ebu_lock, flags);
+	while (len--)
+		*t++ = *f++;
+	spin_unlock_irqrestore(&ebu_lock, flags);
+}
+
+static void
+ltq_copy_to(struct map_info *map, unsigned long to,
+	const void *from, ssize_t len)
+{
+	unsigned char *f = (unsigned char *)from;
+	unsigned char *t = (unsigned char *)map->virt + to;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ebu_lock, flags);
+	while (len--)
+		*t++ = *f++;
+	spin_unlock_irqrestore(&ebu_lock, flags);
+}
+
+static const char const *part_probe_types[] = { "cmdlinepart", NULL };
+
+static int __init
+ltq_mtd_probe(struct platform_device *pdev)
+{
+	struct physmap_flash_data *ltq_mtd_data = dev_get_platdata(&pdev->dev);
+	struct ltq_mtd *ltq_mtd;
+	struct mtd_partition *parts;
+	struct resource *res;
+	int nr_parts = 0;
+	struct cfi_private *cfi;
+	int err;
+
+	ltq_mtd = kzalloc(sizeof(struct ltq_mtd), GFP_KERNEL);
+	platform_set_drvdata(pdev, ltq_mtd);
+
+	ltq_mtd->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!ltq_mtd->res) {
+		dev_err(&pdev->dev, "failed to get memory resource");
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	res = devm_request_mem_region(&pdev->dev, ltq_mtd->res->start,
+		resource_size(ltq_mtd->res), dev_name(&pdev->dev));
+	if (!ltq_mtd->res) {
+		dev_err(&pdev->dev, "failed to request mem resource");
+		err = -EBUSY;
+		goto err_out;
+	}
+
+	ltq_mtd->map = kzalloc(sizeof(struct map_info), GFP_KERNEL);
+	ltq_mtd->map->phys = res->start;
+	ltq_mtd->map->size = resource_size(res);
+	ltq_mtd->map->virt = devm_ioremap_nocache(&pdev->dev,
+				ltq_mtd->map->phys, ltq_mtd->map->size);
+	if (!ltq_mtd->map->virt) {
+		dev_err(&pdev->dev, "failed to ioremap!\n");
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	ltq_mtd->map->name = ltq_map_name;
+	ltq_mtd->map->bankwidth = 2;
+	ltq_mtd->map->read = ltq_read16;
+	ltq_mtd->map->write = ltq_write16;
+	ltq_mtd->map->copy_from = ltq_copy_from;
+	ltq_mtd->map->copy_to = ltq_copy_to;
+
+	ltq_mtd->map->map_priv_1 = LTQ_NOR_PROBING;
+	ltq_mtd->mtd = do_map_probe("cfi_probe", ltq_mtd->map);
+	ltq_mtd->map->map_priv_1 = LTQ_NOR_NORMAL;
+
+	if (!ltq_mtd->mtd) {
+		dev_err(&pdev->dev, "probing failed\n");
+		err = -ENXIO;
+		goto err_unmap;
+	}
+
+	ltq_mtd->mtd->owner = THIS_MODULE;
+
+	cfi = ltq_mtd->map->fldrv_priv;
+	cfi->addr_unlock1 ^= 1;
+	cfi->addr_unlock2 ^= 1;
+
+	nr_parts = parse_mtd_partitions(ltq_mtd->mtd,
+				part_probe_types, &parts, 0);
+	if (nr_parts > 0) {
+		dev_info(&pdev->dev,
+			"using %d partitions from cmdline", nr_parts);
+	} else {
+		nr_parts = ltq_mtd_data->nr_parts;
+		parts = ltq_mtd_data->parts;
+	}
+
+	err = add_mtd_partitions(ltq_mtd->mtd, parts, nr_parts);
+	if (err) {
+		dev_err(&pdev->dev, "failed to add partitions\n");
+		goto err_destroy;
+	}
+
+	return 0;
+
+err_destroy:
+	map_destroy(ltq_mtd->mtd);
+err_unmap:
+	iounmap(ltq_mtd->map->virt);
+err_free:
+	kfree(ltq_mtd->map);
+err_out:
+	kfree(ltq_mtd);
+	return err;
+}
+
+static int __devexit
+ltq_mtd_remove(struct platform_device *pdev)
+{
+	struct ltq_mtd *ltq_mtd = platform_get_drvdata(pdev);
+
+	if (ltq_mtd) {
+		if (ltq_mtd->mtd) {
+			del_mtd_partitions(ltq_mtd->mtd);
+			map_destroy(ltq_mtd->mtd);
+		}
+		if (ltq_mtd->map->virt)
+			iounmap(ltq_mtd->map->virt);
+		kfree(ltq_mtd->map);
+		kfree(ltq_mtd);
+	}
+	return 0;
+}
+
+static struct platform_driver ltq_mtd_driver = {
+	.remove = __devexit_p(ltq_mtd_remove),
+	.driver = {
+		.name = "ltq_nor",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init
+init_ltq_mtd(void)
+{
+	int ret = platform_driver_probe(&ltq_mtd_driver, ltq_mtd_probe);
+
+	if (ret)
+		pr_err("ltq_nor: error registering platform driver");
+	return ret;
+}
+
+static void __exit
+exit_ltq_mtd(void)
+{
+	platform_driver_unregister(&ltq_mtd_driver);
+}
+
+module_init(init_ltq_mtd);
+module_exit(exit_ltq_mtd);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_DESCRIPTION("Lantiq SoC NOR");
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index 3ffe05db492..5d513b54a7d 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -470,7 +471,7 @@ static int __init au1xxx_nand_init(void)
 
 #ifdef CONFIG_MIPS_PB1550
 	/* set gpio206 high */
-	au_writel(au_readl(GPIO2_DIR) & ~(1 << 6), GPIO2_DIR);
+	gpio_direction_input(206);
 
 	boot_swapboot = (au_readl(MEM_STSTAT) & (0x7 << 1)) | ((bcsr_read(BCSR_STATUS) >> 6) & 0x1);
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 6c884ef1b06..19f04a34783 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2017,6 +2017,13 @@ config FTMAC100
 	  from Faraday. It is used on Faraday A320, Andes AG101 and some
 	  other ARM/NDS32 SoC's.
 
+config LANTIQ_ETOP
+	tristate "Lantiq SoC ETOP driver"
+	depends on SOC_TYPE_XWAY
+	help
+	  Support for the MII0 inside the Lantiq SoC
+
+
 source "drivers/net/fs_enet/Kconfig"
 
 source "drivers/net/octeon/Kconfig"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index e5a7375685a..209fbb70619 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -259,6 +259,7 @@ obj-$(CONFIG_MLX4_CORE) += mlx4/
 obj-$(CONFIG_ENC28J60) += enc28j60.o
 obj-$(CONFIG_ETHOC) += ethoc.o
 obj-$(CONFIG_GRETH) += greth.o
+obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o
 
 obj-$(CONFIG_XTENSA_XT2000_SONIC) += xtsonic.o
 
diff --git a/drivers/net/atarilance.c b/drivers/net/atarilance.c
index ce0091eb06f..1264d781b55 100644
--- a/drivers/net/atarilance.c
+++ b/drivers/net/atarilance.c
@@ -554,7 +554,7 @@ static unsigned long __init lance_probe1( struct net_device *dev,
 		memaddr == (unsigned short *)0xffe00000) {
 		/* PAMs card and Riebl on ST use level 5 autovector */
 		if (request_irq(IRQ_AUTO_5, lance_interrupt, IRQ_TYPE_PRIO,
-		            "PAM/Riebl-ST Ethernet", dev)) {
+		            "PAM,Riebl-ST Ethernet", dev)) {
 			printk( "Lance: request for irq %d failed\n", IRQ_AUTO_5 );
 			return 0;
 		}
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 6f8adc7f5d7..e145f2c455c 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -5100,11 +5100,6 @@ err_set_interrupt:
 	return err;
 }
 
-static void ring_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct ixgbe_ring, rcu));
-}
-
 /**
  * ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings
  * @adapter: board private structure to clear interrupt scheme on
@@ -5126,7 +5121,7 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
 		/* ixgbe_get_stats64() might access this ring, we must wait
 		 * a grace period before freeing it.
 		 */
-		call_rcu(&ring->rcu, ring_free_rcu);
+		kfree_rcu(ring, rcu);
 		adapter->rx_ring[i] = NULL;
 	}
 
diff --git a/drivers/net/lantiq_etop.c b/drivers/net/lantiq_etop.c
new file mode 100644
index 00000000000..45f252b7da3
--- /dev/null
+++ b/drivers/net/lantiq_etop.c
@@ -0,0 +1,805 @@
+/*
+ *   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., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
+ *
+ *   Copyright (C) 2011 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/uaccess.h>
+#include <linux/in.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/phy.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/skbuff.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
+#include <linux/ethtool.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+
+#include <asm/checksum.h>
+
+#include <lantiq_soc.h>
+#include <xway_dma.h>
+#include <lantiq_platform.h>
+
+#define LTQ_ETOP_MDIO		0x11804
+#define MDIO_REQUEST		0x80000000
+#define MDIO_READ		0x40000000
+#define MDIO_ADDR_MASK		0x1f
+#define MDIO_ADDR_OFFSET	0x15
+#define MDIO_REG_MASK		0x1f
+#define MDIO_REG_OFFSET		0x10
+#define MDIO_VAL_MASK		0xffff
+
+#define PPE32_CGEN		0x800
+#define LQ_PPE32_ENET_MAC_CFG	0x1840
+
+#define LTQ_ETOP_ENETS0		0x11850
+#define LTQ_ETOP_MAC_DA0	0x1186C
+#define LTQ_ETOP_MAC_DA1	0x11870
+#define LTQ_ETOP_CFG		0x16020
+#define LTQ_ETOP_IGPLEN		0x16080
+
+#define MAX_DMA_CHAN		0x8
+#define MAX_DMA_CRC_LEN		0x4
+#define MAX_DMA_DATA_LEN	0x600
+
+#define ETOP_FTCU		BIT(28)
+#define ETOP_MII_MASK		0xf
+#define ETOP_MII_NORMAL		0xd
+#define ETOP_MII_REVERSE	0xe
+#define ETOP_PLEN_UNDER		0x40
+#define ETOP_CGEN		0x800
+
+/* use 2 static channels for TX/RX */
+#define LTQ_ETOP_TX_CHANNEL	1
+#define LTQ_ETOP_RX_CHANNEL	6
+#define IS_TX(x)		(x == LTQ_ETOP_TX_CHANNEL)
+#define IS_RX(x)		(x == LTQ_ETOP_RX_CHANNEL)
+
+#define ltq_etop_r32(x)		ltq_r32(ltq_etop_membase + (x))
+#define ltq_etop_w32(x, y)	ltq_w32(x, ltq_etop_membase + (y))
+#define ltq_etop_w32_mask(x, y, z)	\
+		ltq_w32_mask(x, y, ltq_etop_membase + (z))
+
+#define DRV_VERSION	"1.0"
+
+static void __iomem *ltq_etop_membase;
+
+struct ltq_etop_chan {
+	int idx;
+	int tx_free;
+	struct net_device *netdev;
+	struct napi_struct napi;
+	struct ltq_dma_channel dma;
+	struct sk_buff *skb[LTQ_DESC_NUM];
+};
+
+struct ltq_etop_priv {
+	struct net_device *netdev;
+	struct ltq_eth_data *pldata;
+	struct resource *res;
+
+	struct mii_bus *mii_bus;
+	struct phy_device *phydev;
+
+	struct ltq_etop_chan ch[MAX_DMA_CHAN];
+	int tx_free[MAX_DMA_CHAN >> 1];
+
+	spinlock_t lock;
+};
+
+static int
+ltq_etop_alloc_skb(struct ltq_etop_chan *ch)
+{
+	ch->skb[ch->dma.desc] = dev_alloc_skb(MAX_DMA_DATA_LEN);
+	if (!ch->skb[ch->dma.desc])
+		return -ENOMEM;
+	ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(NULL,
+		ch->skb[ch->dma.desc]->data, MAX_DMA_DATA_LEN,
+		DMA_FROM_DEVICE);
+	ch->dma.desc_base[ch->dma.desc].addr =
+		CPHYSADDR(ch->skb[ch->dma.desc]->data);
+	ch->dma.desc_base[ch->dma.desc].ctl =
+		LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) |
+		MAX_DMA_DATA_LEN;
+	skb_reserve(ch->skb[ch->dma.desc], NET_IP_ALIGN);
+	return 0;
+}
+
+static void
+ltq_etop_hw_receive(struct ltq_etop_chan *ch)
+{
+	struct ltq_etop_priv *priv = netdev_priv(ch->netdev);
+	struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc];
+	struct sk_buff *skb = ch->skb[ch->dma.desc];
+	int len = (desc->ctl & LTQ_DMA_SIZE_MASK) - MAX_DMA_CRC_LEN;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (ltq_etop_alloc_skb(ch)) {
+		netdev_err(ch->netdev,
+			"failed to allocate new rx buffer, stopping DMA\n");
+		ltq_dma_close(&ch->dma);
+	}
+	ch->dma.desc++;
+	ch->dma.desc %= LTQ_DESC_NUM;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	skb_put(skb, len);
+	skb->dev = ch->netdev;
+	skb->protocol = eth_type_trans(skb, ch->netdev);
+	netif_receive_skb(skb);
+}
+
+static int
+ltq_etop_poll_rx(struct napi_struct *napi, int budget)
+{
+	struct ltq_etop_chan *ch = container_of(napi,
+				struct ltq_etop_chan, napi);
+	int rx = 0;
+	int complete = 0;
+
+	while ((rx < budget) && !complete) {
+		struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc];
+
+		if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) {
+			ltq_etop_hw_receive(ch);
+			rx++;
+		} else {
+			complete = 1;
+		}
+	}
+	if (complete || !rx) {
+		napi_complete(&ch->napi);
+		ltq_dma_ack_irq(&ch->dma);
+	}
+	return rx;
+}
+
+static int
+ltq_etop_poll_tx(struct napi_struct *napi, int budget)
+{
+	struct ltq_etop_chan *ch =
+		container_of(napi, struct ltq_etop_chan, napi);
+	struct ltq_etop_priv *priv = netdev_priv(ch->netdev);
+	struct netdev_queue *txq =
+		netdev_get_tx_queue(ch->netdev, ch->idx >> 1);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	while ((ch->dma.desc_base[ch->tx_free].ctl &
+			(LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) {
+		dev_kfree_skb_any(ch->skb[ch->tx_free]);
+		ch->skb[ch->tx_free] = NULL;
+		memset(&ch->dma.desc_base[ch->tx_free], 0,
+			sizeof(struct ltq_dma_desc));
+		ch->tx_free++;
+		ch->tx_free %= LTQ_DESC_NUM;
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (netif_tx_queue_stopped(txq))
+		netif_tx_start_queue(txq);
+	napi_complete(&ch->napi);
+	ltq_dma_ack_irq(&ch->dma);
+	return 1;
+}
+
+static irqreturn_t
+ltq_etop_dma_irq(int irq, void *_priv)
+{
+	struct ltq_etop_priv *priv = _priv;
+	int ch = irq - LTQ_DMA_CH0_INT;
+
+	napi_schedule(&priv->ch[ch].napi);
+	return IRQ_HANDLED;
+}
+
+static void
+ltq_etop_free_channel(struct net_device *dev, struct ltq_etop_chan *ch)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	ltq_dma_free(&ch->dma);
+	if (ch->dma.irq)
+		free_irq(ch->dma.irq, priv);
+	if (IS_RX(ch->idx)) {
+		int desc;
+		for (desc = 0; desc < LTQ_DESC_NUM; desc++)
+			dev_kfree_skb_any(ch->skb[ch->dma.desc]);
+	}
+}
+
+static void
+ltq_etop_hw_exit(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	int i;
+
+	ltq_pmu_disable(PMU_PPE);
+	for (i = 0; i < MAX_DMA_CHAN; i++)
+		if (IS_TX(i) || IS_RX(i))
+			ltq_etop_free_channel(dev, &priv->ch[i]);
+}
+
+static int
+ltq_etop_hw_init(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	int i;
+
+	ltq_pmu_enable(PMU_PPE);
+
+	switch (priv->pldata->mii_mode) {
+	case PHY_INTERFACE_MODE_RMII:
+		ltq_etop_w32_mask(ETOP_MII_MASK,
+			ETOP_MII_REVERSE, LTQ_ETOP_CFG);
+		break;
+
+	case PHY_INTERFACE_MODE_MII:
+		ltq_etop_w32_mask(ETOP_MII_MASK,
+			ETOP_MII_NORMAL, LTQ_ETOP_CFG);
+		break;
+
+	default:
+		netdev_err(dev, "unknown mii mode %d\n",
+			priv->pldata->mii_mode);
+		return -ENOTSUPP;
+	}
+
+	/* enable crc generation */
+	ltq_etop_w32(PPE32_CGEN, LQ_PPE32_ENET_MAC_CFG);
+
+	ltq_dma_init_port(DMA_PORT_ETOP);
+
+	for (i = 0; i < MAX_DMA_CHAN; i++) {
+		int irq = LTQ_DMA_CH0_INT + i;
+		struct ltq_etop_chan *ch = &priv->ch[i];
+
+		ch->idx = ch->dma.nr = i;
+
+		if (IS_TX(i)) {
+			ltq_dma_alloc_tx(&ch->dma);
+			request_irq(irq, ltq_etop_dma_irq, IRQF_DISABLED,
+				"etop_tx", priv);
+		} else if (IS_RX(i)) {
+			ltq_dma_alloc_rx(&ch->dma);
+			for (ch->dma.desc = 0; ch->dma.desc < LTQ_DESC_NUM;
+					ch->dma.desc++)
+				if (ltq_etop_alloc_skb(ch))
+					return -ENOMEM;
+			ch->dma.desc = 0;
+			request_irq(irq, ltq_etop_dma_irq, IRQF_DISABLED,
+				"etop_rx", priv);
+		}
+		ch->dma.irq = irq;
+	}
+	return 0;
+}
+
+static void
+ltq_etop_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+	strcpy(info->driver, "Lantiq ETOP");
+	strcpy(info->bus_info, "internal");
+	strcpy(info->version, DRV_VERSION);
+}
+
+static int
+ltq_etop_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int
+ltq_etop_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static int
+ltq_etop_nway_reset(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	return phy_start_aneg(priv->phydev);
+}
+
+static const struct ethtool_ops ltq_etop_ethtool_ops = {
+	.get_drvinfo = ltq_etop_get_drvinfo,
+	.get_settings = ltq_etop_get_settings,
+	.set_settings = ltq_etop_set_settings,
+	.nway_reset = ltq_etop_nway_reset,
+};
+
+static int
+ltq_etop_mdio_wr(struct mii_bus *bus, int phy_addr, int phy_reg, u16 phy_data)
+{
+	u32 val = MDIO_REQUEST |
+		((phy_addr & MDIO_ADDR_MASK) << MDIO_ADDR_OFFSET) |
+		((phy_reg & MDIO_REG_MASK) << MDIO_REG_OFFSET) |
+		phy_data;
+
+	while (ltq_etop_r32(LTQ_ETOP_MDIO) & MDIO_REQUEST)
+		;
+	ltq_etop_w32(val, LTQ_ETOP_MDIO);
+	return 0;
+}
+
+static int
+ltq_etop_mdio_rd(struct mii_bus *bus, int phy_addr, int phy_reg)
+{
+	u32 val = MDIO_REQUEST | MDIO_READ |
+		((phy_addr & MDIO_ADDR_MASK) << MDIO_ADDR_OFFSET) |
+		((phy_reg & MDIO_REG_MASK) << MDIO_REG_OFFSET);
+
+	while (ltq_etop_r32(LTQ_ETOP_MDIO) & MDIO_REQUEST)
+		;
+	ltq_etop_w32(val, LTQ_ETOP_MDIO);
+	while (ltq_etop_r32(LTQ_ETOP_MDIO) & MDIO_REQUEST)
+		;
+	val = ltq_etop_r32(LTQ_ETOP_MDIO) & MDIO_VAL_MASK;
+	return val;
+}
+
+static void
+ltq_etop_mdio_link(struct net_device *dev)
+{
+	/* nothing to do  */
+}
+
+static int
+ltq_etop_mdio_probe(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = NULL;
+	int phy_addr;
+
+	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) {
+		if (priv->mii_bus->phy_map[phy_addr]) {
+			phydev = priv->mii_bus->phy_map[phy_addr];
+			break;
+		}
+	}
+
+	if (!phydev) {
+		netdev_err(dev, "no PHY found\n");
+		return -ENODEV;
+	}
+
+	phydev = phy_connect(dev, dev_name(&phydev->dev), &ltq_etop_mdio_link,
+			0, priv->pldata->mii_mode);
+
+	if (IS_ERR(phydev)) {
+		netdev_err(dev, "Could not attach to PHY\n");
+		return PTR_ERR(phydev);
+	}
+
+	phydev->supported &= (SUPPORTED_10baseT_Half
+			      | SUPPORTED_10baseT_Full
+			      | SUPPORTED_100baseT_Half
+			      | SUPPORTED_100baseT_Full
+			      | SUPPORTED_Autoneg
+			      | SUPPORTED_MII
+			      | SUPPORTED_TP);
+
+	phydev->advertising = phydev->supported;
+	priv->phydev = phydev;
+	pr_info("%s: attached PHY [%s] (phy_addr=%s, irq=%d)\n",
+	       dev->name, phydev->drv->name,
+	       dev_name(&phydev->dev), phydev->irq);
+
+	return 0;
+}
+
+static int
+ltq_etop_mdio_init(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	int i;
+	int err;
+
+	priv->mii_bus = mdiobus_alloc();
+	if (!priv->mii_bus) {
+		netdev_err(dev, "failed to allocate mii bus\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	priv->mii_bus->priv = dev;
+	priv->mii_bus->read = ltq_etop_mdio_rd;
+	priv->mii_bus->write = ltq_etop_mdio_wr;
+	priv->mii_bus->name = "ltq_mii";
+	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%x", 0);
+	priv->mii_bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
+	if (!priv->mii_bus->irq) {
+		err = -ENOMEM;
+		goto err_out_free_mdiobus;
+	}
+
+	for (i = 0; i < PHY_MAX_ADDR; ++i)
+		priv->mii_bus->irq[i] = PHY_POLL;
+
+	if (mdiobus_register(priv->mii_bus)) {
+		err = -ENXIO;
+		goto err_out_free_mdio_irq;
+	}
+
+	if (ltq_etop_mdio_probe(dev)) {
+		err = -ENXIO;
+		goto err_out_unregister_bus;
+	}
+	return 0;
+
+err_out_unregister_bus:
+	mdiobus_unregister(priv->mii_bus);
+err_out_free_mdio_irq:
+	kfree(priv->mii_bus->irq);
+err_out_free_mdiobus:
+	mdiobus_free(priv->mii_bus);
+err_out:
+	return err;
+}
+
+static void
+ltq_etop_mdio_cleanup(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	phy_disconnect(priv->phydev);
+	mdiobus_unregister(priv->mii_bus);
+	kfree(priv->mii_bus->irq);
+	mdiobus_free(priv->mii_bus);
+}
+
+static int
+ltq_etop_open(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < MAX_DMA_CHAN; i++) {
+		struct ltq_etop_chan *ch = &priv->ch[i];
+
+		if (!IS_TX(i) && (!IS_RX(i)))
+			continue;
+		ltq_dma_open(&ch->dma);
+		napi_enable(&ch->napi);
+	}
+	phy_start(priv->phydev);
+	netif_tx_start_all_queues(dev);
+	return 0;
+}
+
+static int
+ltq_etop_stop(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	int i;
+
+	netif_tx_stop_all_queues(dev);
+	phy_stop(priv->phydev);
+	for (i = 0; i < MAX_DMA_CHAN; i++) {
+		struct ltq_etop_chan *ch = &priv->ch[i];
+
+		if (!IS_RX(i) && !IS_TX(i))
+			continue;
+		napi_disable(&ch->napi);
+		ltq_dma_close(&ch->dma);
+	}
+	return 0;
+}
+
+static int
+ltq_etop_tx(struct sk_buff *skb, struct net_device *dev)
+{
+	int queue = skb_get_queue_mapping(skb);
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue);
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	struct ltq_etop_chan *ch = &priv->ch[(queue << 1) | 1];
+	struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc];
+	int len;
+	unsigned long flags;
+	u32 byte_offset;
+
+	len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len;
+
+	if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) {
+		dev_kfree_skb_any(skb);
+		netdev_err(dev, "tx ring full\n");
+		netif_tx_stop_queue(txq);
+		return NETDEV_TX_BUSY;
+	}
+
+	/* dma needs to start on a 16 byte aligned address */
+	byte_offset = CPHYSADDR(skb->data) % 16;
+	ch->skb[ch->dma.desc] = skb;
+
+	dev->trans_start = jiffies;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	desc->addr = ((unsigned int) dma_map_single(NULL, skb->data, len,
+						DMA_TO_DEVICE)) - byte_offset;
+	wmb();
+	desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP |
+		LTQ_DMA_TX_OFFSET(byte_offset) | (len & LTQ_DMA_SIZE_MASK);
+	ch->dma.desc++;
+	ch->dma.desc %= LTQ_DESC_NUM;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (ch->dma.desc_base[ch->dma.desc].ctl & LTQ_DMA_OWN)
+		netif_tx_stop_queue(txq);
+
+	return NETDEV_TX_OK;
+}
+
+static int
+ltq_etop_change_mtu(struct net_device *dev, int new_mtu)
+{
+	int ret = eth_change_mtu(dev, new_mtu);
+
+	if (!ret) {
+		struct ltq_etop_priv *priv = netdev_priv(dev);
+		unsigned long flags;
+
+		spin_lock_irqsave(&priv->lock, flags);
+		ltq_etop_w32((ETOP_PLEN_UNDER << 16) | new_mtu,
+			LTQ_ETOP_IGPLEN);
+		spin_unlock_irqrestore(&priv->lock, flags);
+	}
+	return ret;
+}
+
+static int
+ltq_etop_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+
+	/* TODO: mii-toll reports "No MII transceiver present!." ?!*/
+	return phy_mii_ioctl(priv->phydev, rq, cmd);
+}
+
+static int
+ltq_etop_set_mac_address(struct net_device *dev, void *p)
+{
+	int ret = eth_mac_addr(dev, p);
+
+	if (!ret) {
+		struct ltq_etop_priv *priv = netdev_priv(dev);
+		unsigned long flags;
+
+		/* store the mac for the unicast filter */
+		spin_lock_irqsave(&priv->lock, flags);
+		ltq_etop_w32(*((u32 *)dev->dev_addr), LTQ_ETOP_MAC_DA0);
+		ltq_etop_w32(*((u16 *)&dev->dev_addr[4]) << 16,
+			LTQ_ETOP_MAC_DA1);
+		spin_unlock_irqrestore(&priv->lock, flags);
+	}
+	return ret;
+}
+
+static void
+ltq_etop_set_multicast_list(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	unsigned long flags;
+
+	/* ensure that the unicast filter is not enabled in promiscious mode */
+	spin_lock_irqsave(&priv->lock, flags);
+	if ((dev->flags & IFF_PROMISC) || (dev->flags & IFF_ALLMULTI))
+		ltq_etop_w32_mask(ETOP_FTCU, 0, LTQ_ETOP_ENETS0);
+	else
+		ltq_etop_w32_mask(0, ETOP_FTCU, LTQ_ETOP_ENETS0);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static u16
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	/* we are currently only using the first queue */
+	return 0;
+}
+
+static int
+ltq_etop_init(struct net_device *dev)
+{
+	struct ltq_etop_priv *priv = netdev_priv(dev);
+	struct sockaddr mac;
+	int err;
+
+	ether_setup(dev);
+	dev->watchdog_timeo = 10 * HZ;
+	err = ltq_etop_hw_init(dev);
+	if (err)
+		goto err_hw;
+	ltq_etop_change_mtu(dev, 1500);
+
+	memcpy(&mac, &priv->pldata->mac, sizeof(struct sockaddr));
+	if (!is_valid_ether_addr(mac.sa_data)) {
+		pr_warn("etop: invalid MAC, using random\n");
+		random_ether_addr(mac.sa_data);
+	}
+
+	err = ltq_etop_set_mac_address(dev, &mac);
+	if (err)
+		goto err_netdev;
+	ltq_etop_set_multicast_list(dev);
+	err = ltq_etop_mdio_init(dev);
+	if (err)
+		goto err_netdev;
+	return 0;
+
+err_netdev:
+	unregister_netdev(dev);
+	free_netdev(dev);
+err_hw:
+	ltq_etop_hw_exit(dev);
+	return err;
+}
+
+static void
+ltq_etop_tx_timeout(struct net_device *dev)
+{
+	int err;
+
+	ltq_etop_hw_exit(dev);
+	err = ltq_etop_hw_init(dev);
+	if (err)
+		goto err_hw;
+	dev->trans_start = jiffies;
+	netif_wake_queue(dev);
+	return;
+
+err_hw:
+	ltq_etop_hw_exit(dev);
+	netdev_err(dev, "failed to restart etop after TX timeout\n");
+}
+
+static const struct net_device_ops ltq_eth_netdev_ops = {
+	.ndo_open = ltq_etop_open,
+	.ndo_stop = ltq_etop_stop,
+	.ndo_start_xmit = ltq_etop_tx,
+	.ndo_change_mtu = ltq_etop_change_mtu,
+	.ndo_do_ioctl = ltq_etop_ioctl,
+	.ndo_set_mac_address = ltq_etop_set_mac_address,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_set_multicast_list = ltq_etop_set_multicast_list,
+	.ndo_select_queue = ltq_etop_select_queue,
+	.ndo_init = ltq_etop_init,
+	.ndo_tx_timeout = ltq_etop_tx_timeout,
+};
+
+static int __init
+ltq_etop_probe(struct platform_device *pdev)
+{
+	struct net_device *dev;
+	struct ltq_etop_priv *priv;
+	struct resource *res;
+	int err;
+	int i;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "failed to get etop resource\n");
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		resource_size(res), dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev, "failed to request etop resource\n");
+		err = -EBUSY;
+		goto err_out;
+	}
+
+	ltq_etop_membase = devm_ioremap_nocache(&pdev->dev,
+		res->start, resource_size(res));
+	if (!ltq_etop_membase) {
+		dev_err(&pdev->dev, "failed to remap etop engine %d\n",
+			pdev->id);
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	dev = alloc_etherdev_mq(sizeof(struct ltq_etop_priv), 4);
+	strcpy(dev->name, "eth%d");
+	dev->netdev_ops = &ltq_eth_netdev_ops;
+	dev->ethtool_ops = &ltq_etop_ethtool_ops;
+	priv = netdev_priv(dev);
+	priv->res = res;
+	priv->pldata = dev_get_platdata(&pdev->dev);
+	priv->netdev = dev;
+	spin_lock_init(&priv->lock);
+
+	for (i = 0; i < MAX_DMA_CHAN; i++) {
+		if (IS_TX(i))
+			netif_napi_add(dev, &priv->ch[i].napi,
+				ltq_etop_poll_tx, 8);
+		else if (IS_RX(i))
+			netif_napi_add(dev, &priv->ch[i].napi,
+				ltq_etop_poll_rx, 32);
+		priv->ch[i].netdev = dev;
+	}
+
+	err = register_netdev(dev);
+	if (err)
+		goto err_free;
+
+	platform_set_drvdata(pdev, dev);
+	return 0;
+
+err_free:
+	kfree(dev);
+err_out:
+	return err;
+}
+
+static int __devexit
+ltq_etop_remove(struct platform_device *pdev)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+
+	if (dev) {
+		netif_tx_stop_all_queues(dev);
+		ltq_etop_hw_exit(dev);
+		ltq_etop_mdio_cleanup(dev);
+		unregister_netdev(dev);
+	}
+	return 0;
+}
+
+static struct platform_driver ltq_mii_driver = {
+	.remove = __devexit_p(ltq_etop_remove),
+	.driver = {
+		.name = "ltq_etop",
+		.owner = THIS_MODULE,
+	},
+};
+
+int __init
+init_ltq_etop(void)
+{
+	int ret = platform_driver_probe(&ltq_mii_driver, ltq_etop_probe);
+
+	if (ret)
+		pr_err("ltq_etop: Error registering platfom driver!");
+	return ret;
+}
+
+static void __exit
+exit_ltq_etop(void)
+{
+	platform_driver_unregister(&ltq_mii_driver);
+}
+
+module_init(init_ltq_etop);
+module_exit(exit_ltq_etop);
+
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_DESCRIPTION("Lantiq SoC ETOP");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 78e34e9e4f0..d8e4e69ad0b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -603,21 +603,13 @@ static int macvlan_port_create(struct net_device *dev)
 	return err;
 }
 
-static void macvlan_port_rcu_free(struct rcu_head *head)
-{
-	struct macvlan_port *port;
-
-	port = container_of(head, struct macvlan_port, rcu);
-	kfree(port);
-}
-
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get(dev);
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
-	call_rcu(&port->rcu, macvlan_port_rcu_free);
+	kfree_rcu(port, rcu);
 }
 
 static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index d552d2c7784..6af6b628175 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -39,6 +39,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
+#include <linux/pci-ats.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 #include "pci.h"
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 553d8ee55c1..42fae477651 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -13,6 +13,7 @@
 #include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/delay.h>
+#include <linux/pci-ats.h>
 #include "pci.h"
 
 #define VIRTFN_ID_LEN	16
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a6ec200fe5e..4020025f854 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -250,15 +250,6 @@ struct pci_sriov {
 	u8 __iomem *mstate;	/* VF Migration State Array */
 };
 
-/* Address Translation Service */
-struct pci_ats {
-	int pos;	/* capability position */
-	int stu;	/* Smallest Translation Unit */
-	int qdep;	/* Invalidate Queue Depth */
-	int ref_cnt;	/* Physical Function reference count */
-	unsigned int is_enabled:1;	/* Enable bit is set */
-};
-
 #ifdef CONFIG_PCI_IOV
 extern int pci_iov_init(struct pci_dev *dev);
 extern void pci_iov_release(struct pci_dev *dev);
@@ -269,19 +260,6 @@ extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev,
 extern void pci_restore_iov_state(struct pci_dev *dev);
 extern int pci_iov_bus_range(struct pci_bus *bus);
 
-extern int pci_enable_ats(struct pci_dev *dev, int ps);
-extern void pci_disable_ats(struct pci_dev *dev);
-extern int pci_ats_queue_depth(struct pci_dev *dev);
-/**
- * pci_ats_enabled - query the ATS status
- * @dev: the PCI device
- *
- * Returns 1 if ATS capability is enabled, or 0 if not.
- */
-static inline int pci_ats_enabled(struct pci_dev *dev)
-{
-	return dev->ats && dev->ats->is_enabled;
-}
 #else
 static inline int pci_iov_init(struct pci_dev *dev)
 {
@@ -304,21 +282,6 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
 	return 0;
 }
 
-static inline int pci_enable_ats(struct pci_dev *dev, int ps)
-{
-	return -ENODEV;
-}
-static inline void pci_disable_ats(struct pci_dev *dev)
-{
-}
-static inline int pci_ats_queue_depth(struct pci_dev *dev)
-{
-	return -ENODEV;
-}
-static inline int pci_ats_enabled(struct pci_dev *dev)
-{
-	return 0;
-}
 #endif /* CONFIG_PCI_IOV */
 
 static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index e1878877399..42891726ea7 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -3,10 +3,10 @@
 #
 
 config RTC_LIB
-	tristate
+	bool
 
 menuconfig RTC_CLASS
-	tristate "Real Time Clock"
+	bool "Real Time Clock"
 	default n
 	depends on !S390
 	select RTC_LIB
@@ -15,9 +15,6 @@ menuconfig RTC_CLASS
  	  be allowed to plug one or more RTCs to your system. You will
 	  probably want to enable one or more of the interfaces below.
 
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-core.
-
 if RTC_CLASS
 
 config RTC_HCTOSYS
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 39013867cbd..4194e59e14c 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -41,26 +41,21 @@ static void rtc_device_release(struct device *dev)
  * system's wall clock; restore it on resume().
  */
 
-static struct timespec	delta;
 static time_t		oldtime;
+static struct timespec	oldts;
 
 static int rtc_suspend(struct device *dev, pm_message_t mesg)
 {
 	struct rtc_device	*rtc = to_rtc_device(dev);
 	struct rtc_time		tm;
-	struct timespec		ts = current_kernel_time();
 
 	if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0)
 		return 0;
 
 	rtc_read_time(rtc, &tm);
+	ktime_get_ts(&oldts);
 	rtc_tm_to_time(&tm, &oldtime);
 
-	/* RTC precision is 1 second; adjust delta for avg 1/2 sec err */
-	set_normalized_timespec(&delta,
-				ts.tv_sec - oldtime,
-				ts.tv_nsec - (NSEC_PER_SEC >> 1));
-
 	return 0;
 }
 
@@ -70,10 +65,12 @@ static int rtc_resume(struct device *dev)
 	struct rtc_time		tm;
 	time_t			newtime;
 	struct timespec		time;
+	struct timespec		newts;
 
 	if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0)
 		return 0;
 
+	ktime_get_ts(&newts);
 	rtc_read_time(rtc, &tm);
 	if (rtc_valid_tm(&tm) != 0) {
 		pr_debug("%s:  bogus resume time\n", dev_name(&rtc->dev));
@@ -85,15 +82,13 @@ static int rtc_resume(struct device *dev)
 			pr_debug("%s:  time travel!\n", dev_name(&rtc->dev));
 		return 0;
 	}
+	/* calculate the RTC time delta */
+	set_normalized_timespec(&time, newtime - oldtime, 0);
 
-	/* restore wall clock using delta against this RTC;
-	 * adjust again for avg 1/2 second RTC sampling error
-	 */
-	set_normalized_timespec(&time,
-				newtime + delta.tv_sec,
-				(NSEC_PER_SEC >> 1) + delta.tv_nsec);
-	do_settimeofday(&time);
+	/* subtract kernel time between rtc_suspend to rtc_resume */
+	time = timespec_sub(time, timespec_sub(newts, oldts));
 
+	timekeeping_inject_sleeptime(&time);
 	return 0;
 }
 
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 6f34963b3c6..7ad48585c5e 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -662,7 +662,6 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 static int ssb_pci_sprom_get(struct ssb_bus *bus,
 			     struct ssb_sprom *sprom)
 {
-	const struct ssb_sprom *fallback;
 	int err;
 	u16 *buf;
 
@@ -707,10 +706,17 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 		if (err) {
 			/* All CRC attempts failed.
 			 * Maybe there is no SPROM on the device?
-			 * If we have a fallback, use that. */
-			fallback = ssb_get_fallback_sprom();
-			if (fallback) {
-				memcpy(sprom, fallback, sizeof(*sprom));
+			 * Now we ask the arch code if there is some sprom
+			 * available for this device in some other storage */
+			err = ssb_fill_sprom_with_fallback(bus, sprom);
+			if (err) {
+				ssb_printk(KERN_WARNING PFX "WARNING: Using"
+					   " fallback SPROM failed (err %d)\n",
+					   err);
+			} else {
+				ssb_dprintk(KERN_DEBUG PFX "Using SPROM"
+					    " revision %d provided by"
+					    " platform.\n", sprom->revision);
 				err = 0;
 				goto out_free;
 			}
diff --git a/drivers/ssb/sprom.c b/drivers/ssb/sprom.c
index 5f34d7a3e3a..45ff0e3a382 100644
--- a/drivers/ssb/sprom.c
+++ b/drivers/ssb/sprom.c
@@ -17,7 +17,7 @@
 #include <linux/slab.h>
 
 
-static const struct ssb_sprom *fallback_sprom;
+static int(*get_fallback_sprom)(struct ssb_bus *dev, struct ssb_sprom *out);
 
 
 static int sprom2hex(const u16 *sprom, char *buf, size_t buf_len,
@@ -145,36 +145,43 @@ out:
 }
 
 /**
- * ssb_arch_set_fallback_sprom - Set a fallback SPROM for use if no SPROM is found.
+ * ssb_arch_register_fallback_sprom - Registers a method providing a
+ * fallback SPROM if no SPROM is found.
  *
- * @sprom: The SPROM data structure to register.
+ * @sprom_callback: The callback function.
  *
- * With this function the architecture implementation may register a fallback
- * SPROM data structure. The fallback is only used for PCI based SSB devices,
- * where no valid SPROM can be found in the shadow registers.
+ * With this function the architecture implementation may register a
+ * callback handler which fills the SPROM data structure. The fallback is
+ * only used for PCI based SSB devices, where no valid SPROM can be found
+ * in the shadow registers.
  *
- * This function is useful for weird architectures that have a half-assed SSB device
- * hardwired to their PCI bus.
+ * This function is useful for weird architectures that have a half-assed
+ * SSB device hardwired to their PCI bus.
  *
- * Note that it does only work with PCI attached SSB devices. PCMCIA devices currently
- * don't use this fallback.
- * Architectures must provide the SPROM for native SSB devices anyway,
- * so the fallback also isn't used for native devices.
+ * Note that it does only work with PCI attached SSB devices. PCMCIA
+ * devices currently don't use this fallback.
+ * Architectures must provide the SPROM for native SSB devices anyway, so
+ * the fallback also isn't used for native devices.
  *
- * This function is available for architecture code, only. So it is not exported.
+ * This function is available for architecture code, only. So it is not
+ * exported.
  */
-int ssb_arch_set_fallback_sprom(const struct ssb_sprom *sprom)
+int ssb_arch_register_fallback_sprom(int (*sprom_callback)(struct ssb_bus *bus,
+				     struct ssb_sprom *out))
 {
-	if (fallback_sprom)
+	if (get_fallback_sprom)
 		return -EEXIST;
-	fallback_sprom = sprom;
+	get_fallback_sprom = sprom_callback;
 
 	return 0;
 }
 
-const struct ssb_sprom *ssb_get_fallback_sprom(void)
+int ssb_fill_sprom_with_fallback(struct ssb_bus *bus, struct ssb_sprom *out)
 {
-	return fallback_sprom;
+	if (!get_fallback_sprom)
+		return -ENOENT;
+
+	return get_fallback_sprom(bus, out);
 }
 
 /* http://bcm-v4.sipsolutions.net/802.11/IsSpromAvailable */
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 0331139a726..77653014db0 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -171,7 +171,8 @@ ssize_t ssb_attr_sprom_store(struct ssb_bus *bus,
 			     const char *buf, size_t count,
 			     int (*sprom_check_crc)(const u16 *sprom, size_t size),
 			     int (*sprom_write)(struct ssb_bus *bus, const u16 *sprom));
-extern const struct ssb_sprom *ssb_get_fallback_sprom(void);
+extern int ssb_fill_sprom_with_fallback(struct ssb_bus *bus,
+					struct ssb_sprom *out);
 
 
 /* core.c */
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 80484af781e..b1f0f83b870 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1391,6 +1391,14 @@ config SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE
 	help
 	  Support for Console on the NWP serial ports.
 
+config SERIAL_LANTIQ
+	bool "Lantiq serial driver"
+	depends on LANTIQ
+	select SERIAL_CORE
+	select SERIAL_CORE_CONSOLE
+	help
+	  Support for console and UART on Lantiq SoCs.
+
 config SERIAL_QE
 	tristate "Freescale QUICC Engine serial port support"
 	depends on QUICC_ENGINE
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index fee0690ef8e..35276043d9d 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -94,3 +94,4 @@ obj-$(CONFIG_SERIAL_IFX6X60)  	+= ifx6x60.o
 obj-$(CONFIG_SERIAL_PCH_UART)	+= pch_uart.o
 obj-$(CONFIG_SERIAL_MSM_SMD)	+= msm_smd_tty.o
 obj-$(CONFIG_SERIAL_MXS_AUART) += mxs-auart.o
+obj-$(CONFIG_SERIAL_LANTIQ)	+= lantiq.o
diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c
new file mode 100644
index 00000000000..58cf279ed87
--- /dev/null
+++ b/drivers/tty/serial/lantiq.c
@@ -0,0 +1,756 @@
+/*
+ *  Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o.
+ *
+ * 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Copyright (C) 2004 Infineon IFAP DC COM CPE
+ * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2007 John Crispin <blogic@openwrt.org>
+ * Copyright (C) 2010 Thomas Langer, <thomas.langer@lantiq.com>
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/sysrq.h>
+#include <linux/device.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/serial_core.h>
+#include <linux/serial.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+
+#include <lantiq_soc.h>
+
+#define PORT_LTQ_ASC		111
+#define MAXPORTS		2
+#define UART_DUMMY_UER_RX	1
+#define DRVNAME			"ltq_asc"
+#ifdef __BIG_ENDIAN
+#define LTQ_ASC_TBUF		(0x0020 + 3)
+#define LTQ_ASC_RBUF		(0x0024 + 3)
+#else
+#define LTQ_ASC_TBUF		0x0020
+#define LTQ_ASC_RBUF		0x0024
+#endif
+#define LTQ_ASC_FSTAT		0x0048
+#define LTQ_ASC_WHBSTATE	0x0018
+#define LTQ_ASC_STATE		0x0014
+#define LTQ_ASC_IRNCR		0x00F8
+#define LTQ_ASC_CLC		0x0000
+#define LTQ_ASC_ID		0x0008
+#define LTQ_ASC_PISEL		0x0004
+#define LTQ_ASC_TXFCON		0x0044
+#define LTQ_ASC_RXFCON		0x0040
+#define LTQ_ASC_CON		0x0010
+#define LTQ_ASC_BG		0x0050
+#define LTQ_ASC_IRNREN		0x00F4
+
+#define ASC_IRNREN_TX		0x1
+#define ASC_IRNREN_RX		0x2
+#define ASC_IRNREN_ERR		0x4
+#define ASC_IRNREN_TX_BUF	0x8
+#define ASC_IRNCR_TIR		0x1
+#define ASC_IRNCR_RIR		0x2
+#define ASC_IRNCR_EIR		0x4
+
+#define ASCOPT_CSIZE		0x3
+#define TXFIFO_FL		1
+#define RXFIFO_FL		1
+#define ASCCLC_DISS		0x2
+#define ASCCLC_RMCMASK		0x0000FF00
+#define ASCCLC_RMCOFFSET	8
+#define ASCCON_M_8ASYNC		0x0
+#define ASCCON_M_7ASYNC		0x2
+#define ASCCON_ODD		0x00000020
+#define ASCCON_STP		0x00000080
+#define ASCCON_BRS		0x00000100
+#define ASCCON_FDE		0x00000200
+#define ASCCON_R		0x00008000
+#define ASCCON_FEN		0x00020000
+#define ASCCON_ROEN		0x00080000
+#define ASCCON_TOEN		0x00100000
+#define ASCSTATE_PE		0x00010000
+#define ASCSTATE_FE		0x00020000
+#define ASCSTATE_ROE		0x00080000
+#define ASCSTATE_ANY		(ASCSTATE_ROE|ASCSTATE_PE|ASCSTATE_FE)
+#define ASCWHBSTATE_CLRREN	0x00000001
+#define ASCWHBSTATE_SETREN	0x00000002
+#define ASCWHBSTATE_CLRPE	0x00000004
+#define ASCWHBSTATE_CLRFE	0x00000008
+#define ASCWHBSTATE_CLRROE	0x00000020
+#define ASCTXFCON_TXFEN		0x0001
+#define ASCTXFCON_TXFFLU	0x0002
+#define ASCTXFCON_TXFITLMASK	0x3F00
+#define ASCTXFCON_TXFITLOFF	8
+#define ASCRXFCON_RXFEN		0x0001
+#define ASCRXFCON_RXFFLU	0x0002
+#define ASCRXFCON_RXFITLMASK	0x3F00
+#define ASCRXFCON_RXFITLOFF	8
+#define ASCFSTAT_RXFFLMASK	0x003F
+#define ASCFSTAT_TXFFLMASK	0x3F00
+#define ASCFSTAT_TXFREEMASK	0x3F000000
+#define ASCFSTAT_TXFREEOFF	24
+
+static void lqasc_tx_chars(struct uart_port *port);
+static struct ltq_uart_port *lqasc_port[MAXPORTS];
+static struct uart_driver lqasc_reg;
+static DEFINE_SPINLOCK(ltq_asc_lock);
+
+struct ltq_uart_port {
+	struct uart_port	port;
+	struct clk		*clk;
+	unsigned int		tx_irq;
+	unsigned int		rx_irq;
+	unsigned int		err_irq;
+};
+
+static inline struct
+ltq_uart_port *to_ltq_uart_port(struct uart_port *port)
+{
+	return container_of(port, struct ltq_uart_port, port);
+}
+
+static void
+lqasc_stop_tx(struct uart_port *port)
+{
+	return;
+}
+
+static void
+lqasc_start_tx(struct uart_port *port)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+	lqasc_tx_chars(port);
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+	return;
+}
+
+static void
+lqasc_stop_rx(struct uart_port *port)
+{
+	ltq_w32(ASCWHBSTATE_CLRREN, port->membase + LTQ_ASC_WHBSTATE);
+}
+
+static void
+lqasc_enable_ms(struct uart_port *port)
+{
+}
+
+static int
+lqasc_rx_chars(struct uart_port *port)
+{
+	struct tty_struct *tty = tty_port_tty_get(&port->state->port);
+	unsigned int ch = 0, rsr = 0, fifocnt;
+
+	if (!tty) {
+		dev_dbg(port->dev, "%s:tty is busy now", __func__);
+		return -EBUSY;
+	}
+	fifocnt =
+		ltq_r32(port->membase + LTQ_ASC_FSTAT) & ASCFSTAT_RXFFLMASK;
+	while (fifocnt--) {
+		u8 flag = TTY_NORMAL;
+		ch = ltq_r8(port->membase + LTQ_ASC_RBUF);
+		rsr = (ltq_r32(port->membase + LTQ_ASC_STATE)
+			& ASCSTATE_ANY) | UART_DUMMY_UER_RX;
+		tty_flip_buffer_push(tty);
+		port->icount.rx++;
+
+		/*
+		 * Note that the error handling code is
+		 * out of the main execution path
+		 */
+		if (rsr & ASCSTATE_ANY) {
+			if (rsr & ASCSTATE_PE) {
+				port->icount.parity++;
+				ltq_w32_mask(0, ASCWHBSTATE_CLRPE,
+					port->membase + LTQ_ASC_WHBSTATE);
+			} else if (rsr & ASCSTATE_FE) {
+				port->icount.frame++;
+				ltq_w32_mask(0, ASCWHBSTATE_CLRFE,
+					port->membase + LTQ_ASC_WHBSTATE);
+			}
+			if (rsr & ASCSTATE_ROE) {
+				port->icount.overrun++;
+				ltq_w32_mask(0, ASCWHBSTATE_CLRROE,
+					port->membase + LTQ_ASC_WHBSTATE);
+			}
+
+			rsr &= port->read_status_mask;
+
+			if (rsr & ASCSTATE_PE)
+				flag = TTY_PARITY;
+			else if (rsr & ASCSTATE_FE)
+				flag = TTY_FRAME;
+		}
+
+		if ((rsr & port->ignore_status_mask) == 0)
+			tty_insert_flip_char(tty, ch, flag);
+
+		if (rsr & ASCSTATE_ROE)
+			/*
+			 * Overrun is special, since it's reported
+			 * immediately, and doesn't affect the current
+			 * character
+			 */
+			tty_insert_flip_char(tty, 0, TTY_OVERRUN);
+	}
+	if (ch != 0)
+		tty_flip_buffer_push(tty);
+	tty_kref_put(tty);
+	return 0;
+}
+
+static void
+lqasc_tx_chars(struct uart_port *port)
+{
+	struct circ_buf *xmit = &port->state->xmit;
+	if (uart_tx_stopped(port)) {
+		lqasc_stop_tx(port);
+		return;
+	}
+
+	while (((ltq_r32(port->membase + LTQ_ASC_FSTAT) &
+		ASCFSTAT_TXFREEMASK) >> ASCFSTAT_TXFREEOFF) != 0) {
+		if (port->x_char) {
+			ltq_w8(port->x_char, port->membase + LTQ_ASC_TBUF);
+			port->icount.tx++;
+			port->x_char = 0;
+			continue;
+		}
+
+		if (uart_circ_empty(xmit))
+			break;
+
+		ltq_w8(port->state->xmit.buf[port->state->xmit.tail],
+			port->membase + LTQ_ASC_TBUF);
+		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+		port->icount.tx++;
+	}
+
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(port);
+}
+
+static irqreturn_t
+lqasc_tx_int(int irq, void *_port)
+{
+	unsigned long flags;
+	struct uart_port *port = (struct uart_port *)_port;
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+	ltq_w32(ASC_IRNCR_TIR, port->membase + LTQ_ASC_IRNCR);
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+	lqasc_start_tx(port);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t
+lqasc_err_int(int irq, void *_port)
+{
+	unsigned long flags;
+	struct uart_port *port = (struct uart_port *)_port;
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+	/* clear any pending interrupts */
+	ltq_w32_mask(0, ASCWHBSTATE_CLRPE | ASCWHBSTATE_CLRFE |
+		ASCWHBSTATE_CLRROE, port->membase + LTQ_ASC_WHBSTATE);
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t
+lqasc_rx_int(int irq, void *_port)
+{
+	unsigned long flags;
+	struct uart_port *port = (struct uart_port *)_port;
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+	ltq_w32(ASC_IRNCR_RIR, port->membase + LTQ_ASC_IRNCR);
+	lqasc_rx_chars(port);
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+	return IRQ_HANDLED;
+}
+
+static unsigned int
+lqasc_tx_empty(struct uart_port *port)
+{
+	int status;
+	status = ltq_r32(port->membase + LTQ_ASC_FSTAT) & ASCFSTAT_TXFFLMASK;
+	return status ? 0 : TIOCSER_TEMT;
+}
+
+static unsigned int
+lqasc_get_mctrl(struct uart_port *port)
+{
+	return TIOCM_CTS | TIOCM_CAR | TIOCM_DSR;
+}
+
+static void
+lqasc_set_mctrl(struct uart_port *port, u_int mctrl)
+{
+}
+
+static void
+lqasc_break_ctl(struct uart_port *port, int break_state)
+{
+}
+
+static int
+lqasc_startup(struct uart_port *port)
+{
+	struct ltq_uart_port *ltq_port = to_ltq_uart_port(port);
+	int retval;
+
+	port->uartclk = clk_get_rate(ltq_port->clk);
+
+	ltq_w32_mask(ASCCLC_DISS | ASCCLC_RMCMASK, (1 << ASCCLC_RMCOFFSET),
+		port->membase + LTQ_ASC_CLC);
+
+	ltq_w32(0, port->membase + LTQ_ASC_PISEL);
+	ltq_w32(
+		((TXFIFO_FL << ASCTXFCON_TXFITLOFF) & ASCTXFCON_TXFITLMASK) |
+		ASCTXFCON_TXFEN | ASCTXFCON_TXFFLU,
+		port->membase + LTQ_ASC_TXFCON);
+	ltq_w32(
+		((RXFIFO_FL << ASCRXFCON_RXFITLOFF) & ASCRXFCON_RXFITLMASK)
+		| ASCRXFCON_RXFEN | ASCRXFCON_RXFFLU,
+		port->membase + LTQ_ASC_RXFCON);
+	/* make sure other settings are written to hardware before
+	 * setting enable bits
+	 */
+	wmb();
+	ltq_w32_mask(0, ASCCON_M_8ASYNC | ASCCON_FEN | ASCCON_TOEN |
+		ASCCON_ROEN, port->membase + LTQ_ASC_CON);
+
+	retval = request_irq(ltq_port->tx_irq, lqasc_tx_int,
+		IRQF_DISABLED, "asc_tx", port);
+	if (retval) {
+		pr_err("failed to request lqasc_tx_int\n");
+		return retval;
+	}
+
+	retval = request_irq(ltq_port->rx_irq, lqasc_rx_int,
+		IRQF_DISABLED, "asc_rx", port);
+	if (retval) {
+		pr_err("failed to request lqasc_rx_int\n");
+		goto err1;
+	}
+
+	retval = request_irq(ltq_port->err_irq, lqasc_err_int,
+		IRQF_DISABLED, "asc_err", port);
+	if (retval) {
+		pr_err("failed to request lqasc_err_int\n");
+		goto err2;
+	}
+
+	ltq_w32(ASC_IRNREN_RX | ASC_IRNREN_ERR | ASC_IRNREN_TX,
+		port->membase + LTQ_ASC_IRNREN);
+	return 0;
+
+err2:
+	free_irq(ltq_port->rx_irq, port);
+err1:
+	free_irq(ltq_port->tx_irq, port);
+	return retval;
+}
+
+static void
+lqasc_shutdown(struct uart_port *port)
+{
+	struct ltq_uart_port *ltq_port = to_ltq_uart_port(port);
+	free_irq(ltq_port->tx_irq, port);
+	free_irq(ltq_port->rx_irq, port);
+	free_irq(ltq_port->err_irq, port);
+
+	ltq_w32(0, port->membase + LTQ_ASC_CON);
+	ltq_w32_mask(ASCRXFCON_RXFEN, ASCRXFCON_RXFFLU,
+		port->membase + LTQ_ASC_RXFCON);
+	ltq_w32_mask(ASCTXFCON_TXFEN, ASCTXFCON_TXFFLU,
+		port->membase + LTQ_ASC_TXFCON);
+}
+
+static void
+lqasc_set_termios(struct uart_port *port,
+	struct ktermios *new, struct ktermios *old)
+{
+	unsigned int cflag;
+	unsigned int iflag;
+	unsigned int divisor;
+	unsigned int baud;
+	unsigned int con = 0;
+	unsigned long flags;
+
+	cflag = new->c_cflag;
+	iflag = new->c_iflag;
+
+	switch (cflag & CSIZE) {
+	case CS7:
+		con = ASCCON_M_7ASYNC;
+		break;
+
+	case CS5:
+	case CS6:
+	default:
+		new->c_cflag &= ~ CSIZE;
+		new->c_cflag |= CS8;
+		con = ASCCON_M_8ASYNC;
+		break;
+	}
+
+	cflag &= ~CMSPAR; /* Mark/Space parity is not supported */
+
+	if (cflag & CSTOPB)
+		con |= ASCCON_STP;
+
+	if (cflag & PARENB) {
+		if (!(cflag & PARODD))
+			con &= ~ASCCON_ODD;
+		else
+			con |= ASCCON_ODD;
+	}
+
+	port->read_status_mask = ASCSTATE_ROE;
+	if (iflag & INPCK)
+		port->read_status_mask |= ASCSTATE_FE | ASCSTATE_PE;
+
+	port->ignore_status_mask = 0;
+	if (iflag & IGNPAR)
+		port->ignore_status_mask |= ASCSTATE_FE | ASCSTATE_PE;
+
+	if (iflag & IGNBRK) {
+		/*
+		 * If we're ignoring parity and break indicators,
+		 * ignore overruns too (for real raw support).
+		 */
+		if (iflag & IGNPAR)
+			port->ignore_status_mask |= ASCSTATE_ROE;
+	}
+
+	if ((cflag & CREAD) == 0)
+		port->ignore_status_mask |= UART_DUMMY_UER_RX;
+
+	/* set error signals  - framing, parity  and overrun, enable receiver */
+	con |= ASCCON_FEN | ASCCON_TOEN | ASCCON_ROEN;
+
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+
+	/* set up CON */
+	ltq_w32_mask(0, con, port->membase + LTQ_ASC_CON);
+
+	/* Set baud rate - take a divider of 2 into account */
+	baud = uart_get_baud_rate(port, new, old, 0, port->uartclk / 16);
+	divisor = uart_get_divisor(port, baud);
+	divisor = divisor / 2 - 1;
+
+	/* disable the baudrate generator */
+	ltq_w32_mask(ASCCON_R, 0, port->membase + LTQ_ASC_CON);
+
+	/* make sure the fractional divider is off */
+	ltq_w32_mask(ASCCON_FDE, 0, port->membase + LTQ_ASC_CON);
+
+	/* set up to use divisor of 2 */
+	ltq_w32_mask(ASCCON_BRS, 0, port->membase + LTQ_ASC_CON);
+
+	/* now we can write the new baudrate into the register */
+	ltq_w32(divisor, port->membase + LTQ_ASC_BG);
+
+	/* turn the baudrate generator back on */
+	ltq_w32_mask(0, ASCCON_R, port->membase + LTQ_ASC_CON);
+
+	/* enable rx */
+	ltq_w32(ASCWHBSTATE_SETREN, port->membase + LTQ_ASC_WHBSTATE);
+
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+
+	/* Don't rewrite B0 */
+        if (tty_termios_baud_rate(new))
+		tty_termios_encode_baud_rate(new, baud, baud);
+}
+
+static const char*
+lqasc_type(struct uart_port *port)
+{
+	if (port->type == PORT_LTQ_ASC)
+		return DRVNAME;
+	else
+		return NULL;
+}
+
+static void
+lqasc_release_port(struct uart_port *port)
+{
+	if (port->flags & UPF_IOREMAP) {
+		iounmap(port->membase);
+		port->membase = NULL;
+	}
+}
+
+static int
+lqasc_request_port(struct uart_port *port)
+{
+	struct platform_device *pdev = to_platform_device(port->dev);
+	struct resource *res;
+	int size;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "cannot obtain I/O memory region");
+		return -ENODEV;
+	}
+	size = resource_size(res);
+
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		size, dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev, "cannot request I/O memory region");
+		return -EBUSY;
+	}
+
+	if (port->flags & UPF_IOREMAP) {
+		port->membase = devm_ioremap_nocache(&pdev->dev,
+			port->mapbase, size);
+		if (port->membase == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static void
+lqasc_config_port(struct uart_port *port, int flags)
+{
+	if (flags & UART_CONFIG_TYPE) {
+		port->type = PORT_LTQ_ASC;
+		lqasc_request_port(port);
+	}
+}
+
+static int
+lqasc_verify_port(struct uart_port *port,
+	struct serial_struct *ser)
+{
+	int ret = 0;
+	if (ser->type != PORT_UNKNOWN && ser->type != PORT_LTQ_ASC)
+		ret = -EINVAL;
+	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+		ret = -EINVAL;
+	if (ser->baud_base < 9600)
+		ret = -EINVAL;
+	return ret;
+}
+
+static struct uart_ops lqasc_pops = {
+	.tx_empty =	lqasc_tx_empty,
+	.set_mctrl =	lqasc_set_mctrl,
+	.get_mctrl =	lqasc_get_mctrl,
+	.stop_tx =	lqasc_stop_tx,
+	.start_tx =	lqasc_start_tx,
+	.stop_rx =	lqasc_stop_rx,
+	.enable_ms =	lqasc_enable_ms,
+	.break_ctl =	lqasc_break_ctl,
+	.startup =	lqasc_startup,
+	.shutdown =	lqasc_shutdown,
+	.set_termios =	lqasc_set_termios,
+	.type =		lqasc_type,
+	.release_port =	lqasc_release_port,
+	.request_port =	lqasc_request_port,
+	.config_port =	lqasc_config_port,
+	.verify_port =	lqasc_verify_port,
+};
+
+static void
+lqasc_console_putchar(struct uart_port *port, int ch)
+{
+	int fifofree;
+
+	if (!port->membase)
+		return;
+
+	do {
+		fifofree = (ltq_r32(port->membase + LTQ_ASC_FSTAT)
+			& ASCFSTAT_TXFREEMASK) >> ASCFSTAT_TXFREEOFF;
+	} while (fifofree == 0);
+	ltq_w8(ch, port->membase + LTQ_ASC_TBUF);
+}
+
+
+static void
+lqasc_console_write(struct console *co, const char *s, u_int count)
+{
+	struct ltq_uart_port *ltq_port;
+	struct uart_port *port;
+	unsigned long flags;
+
+	if (co->index >= MAXPORTS)
+		return;
+
+	ltq_port = lqasc_port[co->index];
+	if (!ltq_port)
+		return;
+
+	port = &ltq_port->port;
+
+	spin_lock_irqsave(&ltq_asc_lock, flags);
+	uart_console_write(port, s, count, lqasc_console_putchar);
+	spin_unlock_irqrestore(&ltq_asc_lock, flags);
+}
+
+static int __init
+lqasc_console_setup(struct console *co, char *options)
+{
+	struct ltq_uart_port *ltq_port;
+	struct uart_port *port;
+	int baud = 115200;
+	int bits = 8;
+	int parity = 'n';
+	int flow = 'n';
+
+	if (co->index >= MAXPORTS)
+		return -ENODEV;
+
+	ltq_port = lqasc_port[co->index];
+	if (!ltq_port)
+		return -ENODEV;
+
+	port = &ltq_port->port;
+
+	port->uartclk = clk_get_rate(ltq_port->clk);
+
+	if (options)
+		uart_parse_options(options, &baud, &parity, &bits, &flow);
+	return uart_set_options(port, co, baud, parity, bits, flow);
+}
+
+static struct console lqasc_console = {
+	.name =		"ttyLTQ",
+	.write =	lqasc_console_write,
+	.device =	uart_console_device,
+	.setup =	lqasc_console_setup,
+	.flags =	CON_PRINTBUFFER,
+	.index =	-1,
+	.data =		&lqasc_reg,
+};
+
+static int __init
+lqasc_console_init(void)
+{
+	register_console(&lqasc_console);
+	return 0;
+}
+console_initcall(lqasc_console_init);
+
+static struct uart_driver lqasc_reg = {
+	.owner =	THIS_MODULE,
+	.driver_name =	DRVNAME,
+	.dev_name =	"ttyLTQ",
+	.major =	0,
+	.minor =	0,
+	.nr =		MAXPORTS,
+	.cons =		&lqasc_console,
+};
+
+static int __init
+lqasc_probe(struct platform_device *pdev)
+{
+	struct ltq_uart_port *ltq_port;
+	struct uart_port *port;
+	struct resource *mmres, *irqres;
+	int tx_irq, rx_irq, err_irq;
+	struct clk *clk;
+	int ret;
+
+	mmres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	irqres = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!mmres || !irqres)
+		return -ENODEV;
+
+	if (pdev->id >= MAXPORTS)
+		return -EBUSY;
+
+	if (lqasc_port[pdev->id] != NULL)
+		return -EBUSY;
+
+	clk = clk_get(&pdev->dev, "fpi");
+	if (IS_ERR(clk)) {
+		pr_err("failed to get fpi clk\n");
+		return -ENOENT;
+	}
+
+	tx_irq = platform_get_irq_byname(pdev, "tx");
+	rx_irq = platform_get_irq_byname(pdev, "rx");
+	err_irq = platform_get_irq_byname(pdev, "err");
+	if ((tx_irq < 0) | (rx_irq < 0) | (err_irq < 0))
+		return -ENODEV;
+
+	ltq_port = kzalloc(sizeof(struct ltq_uart_port), GFP_KERNEL);
+	if (!ltq_port)
+		return -ENOMEM;
+
+	port = &ltq_port->port;
+
+	port->iotype	= SERIAL_IO_MEM;
+	port->flags	= ASYNC_BOOT_AUTOCONF | UPF_IOREMAP;
+	port->ops	= &lqasc_pops;
+	port->fifosize	= 16;
+	port->type	= PORT_LTQ_ASC,
+	port->line	= pdev->id;
+	port->dev	= &pdev->dev;
+
+	port->irq	= tx_irq; /* unused, just to be backward-compatibe */
+	port->mapbase	= mmres->start;
+
+	ltq_port->clk	= clk;
+
+	ltq_port->tx_irq = tx_irq;
+	ltq_port->rx_irq = rx_irq;
+	ltq_port->err_irq = err_irq;
+
+	lqasc_port[pdev->id] = ltq_port;
+	platform_set_drvdata(pdev, ltq_port);
+
+	ret = uart_add_one_port(&lqasc_reg, port);
+
+	return ret;
+}
+
+static struct platform_driver lqasc_driver = {
+	.driver		= {
+		.name	= DRVNAME,
+		.owner	= THIS_MODULE,
+	},
+};
+
+int __init
+init_lqasc(void)
+{
+	int ret;
+
+	ret = uart_register_driver(&lqasc_reg);
+	if (ret != 0)
+		return ret;
+
+	ret = platform_driver_probe(&lqasc_driver, lqasc_probe);
+	if (ret != 0)
+		uart_unregister_driver(&lqasc_reg);
+
+	return ret;
+}
+
+module_init(init_lqasc);
+
+MODULE_DESCRIPTION("Lantiq serial port driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 51fe1795d5a..d2efe823c20 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -381,7 +381,13 @@ static int uio_get_minor(struct uio_device *idev)
 			retval = -ENOMEM;
 		goto exit;
 	}
-	idev->minor = id & MAX_ID_MASK;
+	if (id < UIO_MAX_DEVICES) {
+		idev->minor = id;
+	} else {
+		dev_err(idev->dev, "too many uio devices\n");
+		retval = -EINVAL;
+		idr_remove(&uio_idr, id);
+	}
 exit:
 	mutex_unlock(&minor_lock);
 	return retval;
@@ -587,14 +593,12 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 
 static int uio_find_mem_index(struct vm_area_struct *vma)
 {
-	int mi;
 	struct uio_device *idev = vma->vm_private_data;
 
-	for (mi = 0; mi < MAX_UIO_MAPS; mi++) {
-		if (idev->info->mem[mi].size == 0)
+	if (vma->vm_pgoff < MAX_UIO_MAPS) {
+		if (idev->info->mem[vma->vm_pgoff].size == 0)
 			return -1;
-		if (vma->vm_pgoff == mi)
-			return mi;
+		return (int)vma->vm_pgoff;
 	}
 	return -1;
 }
diff --git a/drivers/uio/uio_netx.c b/drivers/uio/uio_netx.c
index 5ffdb483b01..a879fd5741f 100644
--- a/drivers/uio/uio_netx.c
+++ b/drivers/uio/uio_netx.c
@@ -18,6 +18,9 @@
 
 #define PCI_VENDOR_ID_HILSCHER		0x15CF
 #define PCI_DEVICE_ID_HILSCHER_NETX	0x0000
+#define PCI_DEVICE_ID_HILSCHER_NETPLC	0x0010
+#define PCI_SUBDEVICE_ID_NETPLC_RAM	0x0000
+#define PCI_SUBDEVICE_ID_NETPLC_FLASH	0x0001
 #define PCI_SUBDEVICE_ID_NXSB_PCA	0x3235
 #define PCI_SUBDEVICE_ID_NXPCA		0x3335
 
@@ -66,6 +69,10 @@ static int __devinit netx_pci_probe(struct pci_dev *dev,
 		bar = 0;
 		info->name = "netx";
 		break;
+	case PCI_DEVICE_ID_HILSCHER_NETPLC:
+		bar = 0;
+		info->name = "netplc";
+		break;
 	default:
 		bar = 2;
 		info->name = "netx_plx";
@@ -134,6 +141,18 @@ static struct pci_device_id netx_pci_ids[] = {
 		.subdevice =	0,
 	},
 	{
+		.vendor =       PCI_VENDOR_ID_HILSCHER,
+		.device =       PCI_DEVICE_ID_HILSCHER_NETPLC,
+		.subvendor =    PCI_VENDOR_ID_HILSCHER,
+		.subdevice =    PCI_SUBDEVICE_ID_NETPLC_RAM,
+	},
+	{
+		.vendor =       PCI_VENDOR_ID_HILSCHER,
+		.device =       PCI_DEVICE_ID_HILSCHER_NETPLC,
+		.subvendor =    PCI_VENDOR_ID_HILSCHER,
+		.subdevice =    PCI_SUBDEVICE_ID_NETPLC_FLASH,
+	},
+	{
 		.vendor =	PCI_VENDOR_ID_PLX,
 		.device =	PCI_DEVICE_ID_PLX_9030,
 		.subvendor =	PCI_VENDOR_ID_PLX,
diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c
index 7174d518b8a..0f424af7f10 100644
--- a/drivers/uio/uio_pdrv_genirq.c
+++ b/drivers/uio/uio_pdrv_genirq.c
@@ -189,6 +189,10 @@ static int uio_pdrv_genirq_remove(struct platform_device *pdev)
 
 	uio_unregister_device(priv->uioinfo);
 	pm_runtime_disable(&pdev->dev);
+
+	priv->uioinfo->handler = NULL;
+	priv->uioinfo->irqcontrol = NULL;
+
 	kfree(priv);
 	return 0;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2ab29124163..7aa4eea930f 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -4,7 +4,7 @@
  * Author: Michael S. Tsirkin <mst@redhat.com>
  *
  * Inspiration, some code, and most witty comments come from
- * Documentation/lguest/lguest.c, by Rusty Russell
+ * Documentation/virtual/lguest/lguest.c, by Rusty Russell
  *
  * This work is licensed under the terms of the GNU GPL, version 2.
  *
diff --git a/drivers/video/atafb.c b/drivers/video/atafb.c
index 5b2b5ef4edb..64e41f5448c 100644
--- a/drivers/video/atafb.c
+++ b/drivers/video/atafb.c
@@ -3117,7 +3117,7 @@ int __init atafb_init(void)
 			atafb_ops.fb_setcolreg = &falcon_setcolreg;
 			error = request_irq(IRQ_AUTO_4, falcon_vbl_switcher,
 					    IRQ_TYPE_PRIO,
-					    "framebuffer/modeswitch",
+					    "framebuffer:modeswitch",
 					    falcon_vbl_switcher);
 			if (error)
 				return error;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 1b0f98bc51b..022f9eb0b7b 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -990,6 +990,12 @@ config BCM63XX_WDT
 	  To compile this driver as a loadable module, choose M here.
 	  The module will be called bcm63xx_wdt.
 
+config LANTIQ_WDT
+	tristate "Lantiq SoC watchdog"
+	depends on LANTIQ
+	help
+	  Hardware driver for the Lantiq SoC Watchdog Timer.
+
 # PARISC Architecture
 
 # POWERPC Architecture
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 3f8608b922a..ed26f7094e4 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -123,6 +123,7 @@ obj-$(CONFIG_AR7_WDT) += ar7_wdt.o
 obj-$(CONFIG_TXX9_WDT) += txx9wdt.o
 obj-$(CONFIG_OCTEON_WDT) += octeon-wdt.o
 octeon-wdt-y := octeon-wdt-main.o octeon-wdt-nmi.o
+obj-$(CONFIG_LANTIQ_WDT) += lantiq_wdt.o
 
 # PARISC Architecture
 
diff --git a/drivers/watchdog/lantiq_wdt.c b/drivers/watchdog/lantiq_wdt.c
new file mode 100644
index 00000000000..7d82adac1cb
--- /dev/null
+++ b/drivers/watchdog/lantiq_wdt.c
@@ -0,0 +1,261 @@
+/*
+ *  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.
+ *
+ *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ *  Based on EP93xx wdt driver
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/watchdog.h>
+#include <linux/platform_device.h>
+#include <linux/uaccess.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+
+#include <lantiq.h>
+
+/* Section 3.4 of the datasheet
+ * The password sequence protects the WDT control register from unintended
+ * write actions, which might cause malfunction of the WDT.
+ *
+ * essentially the following two magic passwords need to be written to allow
+ * IO access to the WDT core
+ */
+#define LTQ_WDT_PW1		0x00BE0000
+#define LTQ_WDT_PW2		0x00DC0000
+
+#define LTQ_WDT_CR		0x0	/* watchdog control register */
+#define LTQ_WDT_SR		0x8	/* watchdog status register */
+
+#define LTQ_WDT_SR_EN		(0x1 << 31)	/* enable bit */
+#define LTQ_WDT_SR_PWD		(0x3 << 26)	/* turn on power */
+#define LTQ_WDT_SR_CLKDIV	(0x3 << 24)	/* turn on clock and set */
+						/* divider to 0x40000 */
+#define LTQ_WDT_DIVIDER		0x40000
+#define LTQ_MAX_TIMEOUT		((1 << 16) - 1)	/* the reload field is 16 bit */
+
+static int nowayout = WATCHDOG_NOWAYOUT;
+
+static void __iomem *ltq_wdt_membase;
+static unsigned long ltq_io_region_clk_rate;
+
+static unsigned long ltq_wdt_bootstatus;
+static unsigned long ltq_wdt_in_use;
+static int ltq_wdt_timeout = 30;
+static int ltq_wdt_ok_to_close;
+
+static void
+ltq_wdt_enable(void)
+{
+	ltq_wdt_timeout = ltq_wdt_timeout *
+			(ltq_io_region_clk_rate / LTQ_WDT_DIVIDER) + 0x1000;
+	if (ltq_wdt_timeout > LTQ_MAX_TIMEOUT)
+		ltq_wdt_timeout = LTQ_MAX_TIMEOUT;
+
+	/* write the first password magic */
+	ltq_w32(LTQ_WDT_PW1, ltq_wdt_membase + LTQ_WDT_CR);
+	/* write the second magic plus the configuration and new timeout */
+	ltq_w32(LTQ_WDT_SR_EN | LTQ_WDT_SR_PWD | LTQ_WDT_SR_CLKDIV |
+		LTQ_WDT_PW2 | ltq_wdt_timeout, ltq_wdt_membase + LTQ_WDT_CR);
+}
+
+static void
+ltq_wdt_disable(void)
+{
+	/* write the first password magic */
+	ltq_w32(LTQ_WDT_PW1, ltq_wdt_membase + LTQ_WDT_CR);
+	/* write the second password magic with no config
+	 * this turns the watchdog off
+	 */
+	ltq_w32(LTQ_WDT_PW2, ltq_wdt_membase + LTQ_WDT_CR);
+}
+
+static ssize_t
+ltq_wdt_write(struct file *file, const char __user *data,
+		size_t len, loff_t *ppos)
+{
+	if (len) {
+		if (!nowayout) {
+			size_t i;
+
+			ltq_wdt_ok_to_close = 0;
+			for (i = 0; i != len; i++) {
+				char c;
+
+				if (get_user(c, data + i))
+					return -EFAULT;
+				if (c == 'V')
+					ltq_wdt_ok_to_close = 1;
+				else
+					ltq_wdt_ok_to_close = 0;
+			}
+		}
+		ltq_wdt_enable();
+	}
+
+	return len;
+}
+
+static struct watchdog_info ident = {
+	.options = WDIOF_MAGICCLOSE | WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING |
+			WDIOF_CARDRESET,
+	.identity = "ltq_wdt",
+};
+
+static long
+ltq_wdt_ioctl(struct file *file,
+		unsigned int cmd, unsigned long arg)
+{
+	int ret = -ENOTTY;
+
+	switch (cmd) {
+	case WDIOC_GETSUPPORT:
+		ret = copy_to_user((struct watchdog_info __user *)arg, &ident,
+				sizeof(ident)) ? -EFAULT : 0;
+		break;
+
+	case WDIOC_GETBOOTSTATUS:
+		ret = put_user(ltq_wdt_bootstatus, (int __user *)arg);
+		break;
+
+	case WDIOC_GETSTATUS:
+		ret = put_user(0, (int __user *)arg);
+		break;
+
+	case WDIOC_SETTIMEOUT:
+		ret = get_user(ltq_wdt_timeout, (int __user *)arg);
+		if (!ret)
+			ltq_wdt_enable();
+		/* intentional drop through */
+	case WDIOC_GETTIMEOUT:
+		ret = put_user(ltq_wdt_timeout, (int __user *)arg);
+		break;
+
+	case WDIOC_KEEPALIVE:
+		ltq_wdt_enable();
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+static int
+ltq_wdt_open(struct inode *inode, struct file *file)
+{
+	if (test_and_set_bit(0, &ltq_wdt_in_use))
+		return -EBUSY;
+	ltq_wdt_in_use = 1;
+	ltq_wdt_enable();
+
+	return nonseekable_open(inode, file);
+}
+
+static int
+ltq_wdt_release(struct inode *inode, struct file *file)
+{
+	if (ltq_wdt_ok_to_close)
+		ltq_wdt_disable();
+	else
+		pr_err("ltq_wdt: watchdog closed without warning\n");
+	ltq_wdt_ok_to_close = 0;
+	clear_bit(0, &ltq_wdt_in_use);
+
+	return 0;
+}
+
+static const struct file_operations ltq_wdt_fops = {
+	.owner		= THIS_MODULE,
+	.write		= ltq_wdt_write,
+	.unlocked_ioctl	= ltq_wdt_ioctl,
+	.open		= ltq_wdt_open,
+	.release	= ltq_wdt_release,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice ltq_wdt_miscdev = {
+	.minor	= WATCHDOG_MINOR,
+	.name	= "watchdog",
+	.fops	= &ltq_wdt_fops,
+};
+
+static int __init
+ltq_wdt_probe(struct platform_device *pdev)
+{
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	struct clk *clk;
+
+	if (!res) {
+		dev_err(&pdev->dev, "cannot obtain I/O memory region");
+		return -ENOENT;
+	}
+	res = devm_request_mem_region(&pdev->dev, res->start,
+		resource_size(res), dev_name(&pdev->dev));
+	if (!res) {
+		dev_err(&pdev->dev, "cannot request I/O memory region");
+		return -EBUSY;
+	}
+	ltq_wdt_membase = devm_ioremap_nocache(&pdev->dev, res->start,
+		resource_size(res));
+	if (!ltq_wdt_membase) {
+		dev_err(&pdev->dev, "cannot remap I/O memory region\n");
+		return -ENOMEM;
+	}
+
+	/* we do not need to enable the clock as it is always running */
+	clk = clk_get(&pdev->dev, "io");
+	WARN_ON(!clk);
+	ltq_io_region_clk_rate = clk_get_rate(clk);
+	clk_put(clk);
+
+	if (ltq_reset_cause() == LTQ_RST_CAUSE_WDTRST)
+		ltq_wdt_bootstatus = WDIOF_CARDRESET;
+
+	return misc_register(&ltq_wdt_miscdev);
+}
+
+static int __devexit
+ltq_wdt_remove(struct platform_device *pdev)
+{
+	misc_deregister(&ltq_wdt_miscdev);
+
+	if (ltq_wdt_membase)
+		iounmap(ltq_wdt_membase);
+
+	return 0;
+}
+
+
+static struct platform_driver ltq_wdt_driver = {
+	.remove = __devexit_p(ltq_wdt_remove),
+	.driver = {
+		.name = "ltq_wdt",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init
+init_ltq_wdt(void)
+{
+	return platform_driver_probe(&ltq_wdt_driver, ltq_wdt_probe);
+}
+
+static void __exit
+exit_ltq_wdt(void)
+{
+	return platform_driver_unregister(&ltq_wdt_driver);
+}
+
+module_init(init_ltq_wdt);
+module_exit(exit_ltq_wdt);
+
+module_param(nowayout, int, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
+
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_DESCRIPTION("Lantiq SoC Watchdog");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
diff --git a/drivers/watchdog/mtx-1_wdt.c b/drivers/watchdog/mtx-1_wdt.c
index 5ec5ac1f787..1479dc4d612 100644
--- a/drivers/watchdog/mtx-1_wdt.c
+++ b/drivers/watchdog/mtx-1_wdt.c
@@ -66,6 +66,7 @@ static struct {
 	int default_ticks;
 	unsigned long inuse;
 	unsigned gpio;
+	int gstate;
 } mtx1_wdt_device;
 
 static void mtx1_wdt_trigger(unsigned long unused)
@@ -75,13 +76,13 @@ static void mtx1_wdt_trigger(unsigned long unused)
 	spin_lock(&mtx1_wdt_device.lock);
 	if (mtx1_wdt_device.running)
 		ticks--;
-	/*
-	 * toggle GPIO2_15
-	 */
-	tmp = au_readl(GPIO2_DIR);
-	tmp = (tmp & ~(1 << mtx1_wdt_device.gpio)) |
-	      ((~tmp) & (1 << mtx1_wdt_device.gpio));
-	au_writel(tmp, GPIO2_DIR);
+
+	/* toggle wdt gpio */
+	mtx1_wdt_device.gstate = ~mtx1_wdt_device.gstate;
+	if (mtx1_wdt_device.gstate)
+		gpio_direction_output(mtx1_wdt_device.gpio, 1);
+	else
+		gpio_direction_input(mtx1_wdt_device.gpio);
 
 	if (mtx1_wdt_device.queue && ticks)
 		mod_timer(&mtx1_wdt_device.timer, jiffies + MTX1_WDT_INTERVAL);
@@ -103,7 +104,8 @@ static void mtx1_wdt_start(void)
 	spin_lock_irqsave(&mtx1_wdt_device.lock, flags);
 	if (!mtx1_wdt_device.queue) {
 		mtx1_wdt_device.queue = 1;
-		gpio_set_value(mtx1_wdt_device.gpio, 1);
+		mtx1_wdt_device.gstate = 1;
+		gpio_direction_output(mtx1_wdt_device.gpio, 1);
 		mod_timer(&mtx1_wdt_device.timer, jiffies + MTX1_WDT_INTERVAL);
 	}
 	mtx1_wdt_device.running++;
@@ -117,7 +119,8 @@ static int mtx1_wdt_stop(void)
 	spin_lock_irqsave(&mtx1_wdt_device.lock, flags);
 	if (mtx1_wdt_device.queue) {
 		mtx1_wdt_device.queue = 0;
-		gpio_set_value(mtx1_wdt_device.gpio, 0);
+		mtx1_wdt_device.gstate = 0;
+		gpio_direction_output(mtx1_wdt_device.gpio, 0);
 	}
 	ticks = mtx1_wdt_device.default_ticks;
 	spin_unlock_irqrestore(&mtx1_wdt_device.lock, flags);
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index f420f1ff7f1..4781f806701 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -4,21 +4,21 @@ obj-y	+= xenbus/
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_features.o			:= $(nostackp)
 
-obj-$(CONFIG_BLOCK)		+= biomerge.o
-obj-$(CONFIG_HOTPLUG_CPU)	+= cpu_hotplug.o
-obj-$(CONFIG_XEN_XENCOMM)	+= xencomm.o
-obj-$(CONFIG_XEN_BALLOON)	+= xen-balloon.o
-obj-$(CONFIG_XEN_DEV_EVTCHN)	+= xen-evtchn.o
-obj-$(CONFIG_XEN_GNTDEV)	+= xen-gntdev.o
+obj-$(CONFIG_BLOCK)			+= biomerge.o
+obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
+obj-$(CONFIG_XEN_XENCOMM)		+= xencomm.o
+obj-$(CONFIG_XEN_BALLOON)		+= xen-balloon.o
+obj-$(CONFIG_XEN_DEV_EVTCHN)		+= xen-evtchn.o
+obj-$(CONFIG_XEN_GNTDEV)		+= xen-gntdev.o
 obj-$(CONFIG_XEN_GRANT_DEV_ALLOC)	+= xen-gntalloc.o
-obj-$(CONFIG_XENFS)		+= xenfs/
+obj-$(CONFIG_XENFS)			+= xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
-obj-$(CONFIG_XEN_PLATFORM_PCI)	+= xen-platform-pci.o
-obj-$(CONFIG_SWIOTLB_XEN)	+= swiotlb-xen.o
-obj-$(CONFIG_XEN_DOM0)		+= pci.o
+obj-$(CONFIG_XEN_PLATFORM_PCI)		+= xen-platform-pci.o
+obj-$(CONFIG_SWIOTLB_XEN)		+= swiotlb-xen.o
+obj-$(CONFIG_XEN_DOM0)			+= pci.o
 
-xen-evtchn-y			:= evtchn.o
+xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o
 
-xen-platform-pci-y		:= platform-pci.o
+xen-platform-pci-y			:= platform-pci.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 043af8ad6b6..f54290baa3d 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -114,7 +114,6 @@ static void __balloon_append(struct page *page)
 	if (PageHighMem(page)) {
 		list_add_tail(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_high++;
-		dec_totalhigh_pages();
 	} else {
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
@@ -124,6 +123,8 @@ static void __balloon_append(struct page *page)
 static void balloon_append(struct page *page)
 {
 	__balloon_append(page);
+	if (PageHighMem(page))
+		dec_totalhigh_pages();
 	totalram_pages--;
 }
 
@@ -193,7 +194,7 @@ static enum bp_state update_schedule(enum bp_state state)
 	return BP_EAGAIN;
 }
 
-static unsigned long current_target(void)
+static long current_credit(void)
 {
 	unsigned long target = balloon_stats.target_pages;
 
@@ -202,7 +203,7 @@ static unsigned long current_target(void)
 		     balloon_stats.balloon_low +
 		     balloon_stats.balloon_high);
 
-	return target;
+	return target - balloon_stats.current_pages;
 }
 
 static enum bp_state increase_reservation(unsigned long nr_pages)
@@ -246,7 +247,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		set_phys_to_machine(pfn, frame_list[i]);
 
 		/* Link back into the page tables if not highmem. */
-		if (!xen_hvm_domain() && pfn < max_low_pfn) {
+		if (xen_pv_domain() && !PageHighMem(page)) {
 			int ret;
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
@@ -293,7 +294,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 		scrub_page(page);
 
-		if (!xen_hvm_domain() && !PageHighMem(page)) {
+		if (xen_pv_domain() && !PageHighMem(page)) {
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
 				__pte_ma(0), 0);
@@ -337,7 +338,7 @@ static void balloon_process(struct work_struct *work)
 	mutex_lock(&balloon_mutex);
 
 	do {
-		credit = current_target() - balloon_stats.current_pages;
+		credit = current_credit();
 
 		if (credit > 0)
 			state = increase_reservation(credit);
@@ -420,7 +421,7 @@ void free_xenballooned_pages(int nr_pages, struct page** pages)
 	}
 
 	/* The balloon may be too large now. Shrink it if needed. */
-	if (current_target() != balloon_stats.current_pages)
+	if (current_credit())
 		schedule_delayed_work(&balloon_worker, 0);
 
 	mutex_unlock(&balloon_mutex);
@@ -429,7 +430,7 @@ EXPORT_SYMBOL(free_xenballooned_pages);
 
 static int __init balloon_init(void)
 {
- 	unsigned long pfn, nr_pages, extra_pfn_end;
+	unsigned long pfn, extra_pfn_end;
 	struct page *page;
 
 	if (!xen_domain())
@@ -437,11 +438,7 @@ static int __init balloon_init(void)
 
 	pr_info("xen/balloon: Initialising balloon driver.\n");
 
- 	if (xen_pv_domain())
- 		nr_pages = xen_start_info->nr_pages;
- 	else
- 		nr_pages = max_pfn;
- 	balloon_stats.current_pages = min(nr_pages, max_pfn);
+	balloon_stats.current_pages = xen_pv_domain() ? min(xen_start_info->nr_pages, max_pfn) : max_pfn;
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
@@ -466,7 +463,7 @@ static int __init balloon_init(void)
 	     pfn < extra_pfn_end;
 	     pfn++) {
 		page = pfn_to_page(pfn);
-		/* totalram_pages doesn't include the boot-time
+		/* totalram_pages and totalhigh_pages do not include the boot-time
 		   balloon extension, so don't subtract from it. */
 		__balloon_append(page);
 	}
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 33167b43ac7..3ff822b4814 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -101,6 +101,7 @@ struct irq_info
 			unsigned short gsi;
 			unsigned char vector;
 			unsigned char flags;
+			uint16_t domid;
 		} pirq;
 	} u;
 };
@@ -118,6 +119,8 @@ static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
 static struct irq_chip xen_dynamic_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
+static void enable_dynirq(struct irq_data *data);
+static void disable_dynirq(struct irq_data *data);
 
 /* Get info for IRQ */
 static struct irq_info *info_for_irq(unsigned irq)
@@ -184,6 +187,7 @@ static void xen_irq_info_pirq_init(unsigned irq,
 				   unsigned short pirq,
 				   unsigned short gsi,
 				   unsigned short vector,
+				   uint16_t domid,
 				   unsigned char flags)
 {
 	struct irq_info *info = info_for_irq(irq);
@@ -193,6 +197,7 @@ static void xen_irq_info_pirq_init(unsigned irq,
 	info->u.pirq.pirq = pirq;
 	info->u.pirq.gsi = gsi;
 	info->u.pirq.vector = vector;
+	info->u.pirq.domid = domid;
 	info->u.pirq.flags = flags;
 }
 
@@ -473,16 +478,6 @@ static void xen_free_irq(unsigned irq)
 	irq_free_desc(irq);
 }
 
-static void pirq_unmask_notify(int irq)
-{
-	struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
-
-	if (unlikely(pirq_needs_eoi(irq))) {
-		int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
-		WARN_ON(rc);
-	}
-}
-
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -506,6 +501,29 @@ static bool probing_irq(int irq)
 	return desc && desc->action == NULL;
 }
 
+static void eoi_pirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+	int rc = 0;
+
+	irq_move_irq(data);
+
+	if (VALID_EVTCHN(evtchn))
+		clear_evtchn(evtchn);
+
+	if (pirq_needs_eoi(data->irq)) {
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+		WARN_ON(rc);
+	}
+}
+
+static void mask_ack_pirq(struct irq_data *data)
+{
+	disable_dynirq(data);
+	eoi_pirq(data);
+}
+
 static unsigned int __startup_pirq(unsigned int irq)
 {
 	struct evtchn_bind_pirq bind_pirq;
@@ -539,7 +557,7 @@ static unsigned int __startup_pirq(unsigned int irq)
 
 out:
 	unmask_evtchn(evtchn);
-	pirq_unmask_notify(irq);
+	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
 }
@@ -579,18 +597,7 @@ static void enable_pirq(struct irq_data *data)
 
 static void disable_pirq(struct irq_data *data)
 {
-}
-
-static void ack_pirq(struct irq_data *data)
-{
-	int evtchn = evtchn_from_irq(data->irq);
-
-	irq_move_irq(data);
-
-	if (VALID_EVTCHN(evtchn)) {
-		mask_evtchn(evtchn);
-		clear_evtchn(evtchn);
-	}
+	disable_dynirq(data);
 }
 
 static int find_irq_by_gsi(unsigned gsi)
@@ -639,9 +646,6 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	if (irq < 0)
 		goto out;
 
-	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
-				      name);
-
 	irq_op.irq = irq;
 	irq_op.vector = 0;
 
@@ -655,9 +659,35 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 		goto out;
 	}
 
-	xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector,
+	xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
 			       shareable ? PIRQ_SHAREABLE : 0);
 
+	pirq_query_unmask(irq);
+	/* We try to use the handler with the appropriate semantic for the
+	 * type of interrupt: if the interrupt doesn't need an eoi
+	 * (pirq_needs_eoi returns false), we treat it like an edge
+	 * triggered interrupt so we use handle_edge_irq.
+	 * As a matter of fact this only happens when the corresponding
+	 * physical interrupt is edge triggered or an msi.
+	 *
+	 * On the other hand if the interrupt needs an eoi (pirq_needs_eoi
+	 * returns true) we treat it like a level triggered interrupt so we
+	 * use handle_fasteoi_irq like the native code does for this kind of
+	 * interrupts.
+	 * Depending on the Xen version, pirq_needs_eoi might return true
+	 * not only for level triggered interrupts but for edge triggered
+	 * interrupts too. In any case Xen always honors the eoi mechanism,
+	 * not injecting any more pirqs of the same kind if the first one
+	 * hasn't received an eoi yet. Therefore using the fasteoi handler
+	 * is the right choice either way.
+	 */
+	if (pirq_needs_eoi(irq))
+		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+				handle_fasteoi_irq, name);
+	else
+		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+				handle_edge_irq, name);
+
 out:
 	spin_unlock(&irq_mapping_update_lock);
 
@@ -680,7 +710,8 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 }
 
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, int vector, const char *name)
+			     int pirq, int vector, const char *name,
+			     domid_t domid)
 {
 	int irq, ret;
 
@@ -690,10 +721,10 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	if (irq == -1)
 		goto out;
 
-	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
-				      name);
+	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
+			name);
 
-	xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, 0);
+	xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
 	ret = irq_set_msi_desc(irq, msidesc);
 	if (ret < 0)
 		goto error_irq;
@@ -722,9 +753,16 @@ int xen_destroy_irq(int irq)
 
 	if (xen_initial_domain()) {
 		unmap_irq.pirq = info->u.pirq.pirq;
-		unmap_irq.domid = DOMID_SELF;
+		unmap_irq.domid = info->u.pirq.domid;
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
-		if (rc) {
+		/* If another domain quits without making the pci_disable_msix
+		 * call, the Xen hypervisor takes care of freeing the PIRQs
+		 * (free_domain_pirqs).
+		 */
+		if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
+			printk(KERN_INFO "domain %d does not have %d anymore\n",
+				info->u.pirq.domid, info->u.pirq.pirq);
+		else if (rc) {
 			printk(KERN_WARNING "unmap irq failed %d\n", rc);
 			goto out;
 		}
@@ -759,6 +797,12 @@ out:
 	return irq;
 }
 
+
+int xen_pirq_from_irq(unsigned irq)
+{
+	return pirq_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 int bind_evtchn_to_irq(unsigned int evtchn)
 {
 	int irq;
@@ -773,7 +817,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 			goto out;
 
 		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
-					      handle_fasteoi_irq, "event");
+					      handle_edge_irq, "event");
 
 		xen_irq_info_evtchn_init(irq, evtchn);
 	}
@@ -1179,9 +1223,6 @@ static void __xen_evtchn_do_upcall(void)
 				port = (word_idx * BITS_PER_LONG) + bit_idx;
 				irq = evtchn_to_irq[port];
 
-				mask_evtchn(port);
-				clear_evtchn(port);
-
 				if (irq != -1) {
 					desc = irq_to_desc(irq);
 					if (desc)
@@ -1337,10 +1378,16 @@ static void ack_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);
 
-	irq_move_masked_irq(data);
+	irq_move_irq(data);
 
 	if (VALID_EVTCHN(evtchn))
-		unmask_evtchn(evtchn);
+		clear_evtchn(evtchn);
+}
+
+static void mask_ack_dynirq(struct irq_data *data)
+{
+	disable_dynirq(data);
+	ack_dynirq(data);
 }
 
 static int retrigger_dynirq(struct irq_data *data)
@@ -1502,6 +1549,18 @@ void xen_poll_irq(int irq)
 	xen_poll_irq_timeout(irq, 0 /* no timeout */);
 }
 
+/* Check whether the IRQ line is shared with other guests. */
+int xen_test_irq_shared(int irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+	struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
+
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+		return 0;
+	return !(irq_status.flags & XENIRQSTAT_shared);
+}
+EXPORT_SYMBOL_GPL(xen_test_irq_shared);
+
 void xen_irq_resume(void)
 {
 	unsigned int cpu, evtchn;
@@ -1535,7 +1594,9 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.irq_mask		= disable_dynirq,
 	.irq_unmask		= enable_dynirq,
 
-	.irq_eoi		= ack_dynirq,
+	.irq_ack		= ack_dynirq,
+	.irq_mask_ack		= mask_ack_dynirq,
+
 	.irq_set_affinity	= set_affinity_irq,
 	.irq_retrigger		= retrigger_dynirq,
 };
@@ -1545,14 +1606,15 @@ static struct irq_chip xen_pirq_chip __read_mostly = {
 
 	.irq_startup		= startup_pirq,
 	.irq_shutdown		= shutdown_pirq,
-
 	.irq_enable		= enable_pirq,
-	.irq_unmask		= enable_pirq,
-
 	.irq_disable		= disable_pirq,
-	.irq_mask		= disable_pirq,
 
-	.irq_ack		= ack_pirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= eoi_pirq,
+	.irq_eoi		= eoi_pirq,
+	.irq_mask_ack		= mask_ack_pirq,
 
 	.irq_set_affinity	= set_affinity_irq,
 
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index a7ffdfe19fc..f6832f46aea 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -427,6 +427,17 @@ static long gntalloc_ioctl(struct file *filp, unsigned int cmd,
 	return 0;
 }
 
+static void gntalloc_vma_open(struct vm_area_struct *vma)
+{
+	struct gntalloc_gref *gref = vma->vm_private_data;
+	if (!gref)
+		return;
+
+	spin_lock(&gref_lock);
+	gref->users++;
+	spin_unlock(&gref_lock);
+}
+
 static void gntalloc_vma_close(struct vm_area_struct *vma)
 {
 	struct gntalloc_gref *gref = vma->vm_private_data;
@@ -441,6 +452,7 @@ static void gntalloc_vma_close(struct vm_area_struct *vma)
 }
 
 static struct vm_operations_struct gntalloc_vmops = {
+	.open = gntalloc_vma_open,
 	.close = gntalloc_vma_close,
 };
 
@@ -471,8 +483,6 @@ static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_private_data = gref;
 
 	vma->vm_flags |= VM_RESERVED;
-	vma->vm_flags |= VM_DONTCOPY;
-	vma->vm_flags |= VM_PFNMAP | VM_PFN_AT_MMAP;
 
 	vma->vm_ops = &gntalloc_vmops;
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index b0f9e8fb005..f914b26cf0c 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -330,17 +330,26 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 /* ------------------------------------------------------------------ */
 
+static void gntdev_vma_open(struct vm_area_struct *vma)
+{
+	struct grant_map *map = vma->vm_private_data;
+
+	pr_debug("gntdev_vma_open %p\n", vma);
+	atomic_inc(&map->users);
+}
+
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
 	struct grant_map *map = vma->vm_private_data;
 
-	pr_debug("close %p\n", vma);
+	pr_debug("gntdev_vma_close %p\n", vma);
 	map->vma = NULL;
 	vma->vm_private_data = NULL;
 	gntdev_put_map(map);
 }
 
 static struct vm_operations_struct gntdev_vmops = {
+	.open = gntdev_vma_open,
 	.close = gntdev_vma_close,
 };
 
@@ -652,7 +661,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
 	vma->vm_ops = &gntdev_vmops;
 
-	vma->vm_flags |= VM_RESERVED|VM_DONTCOPY|VM_DONTEXPAND|VM_PFNMAP;
+	vma->vm_flags |= VM_RESERVED|VM_DONTEXPAND;
+
+	if (use_ptemod)
+		vma->vm_flags |= VM_DONTCOPY|VM_PFNMAP;
 
 	vma->vm_private_data = map;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 3745a318def..fd725cde6ad 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -466,13 +466,30 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		if (map_ops[i].status)
 			continue;
 
-		/* m2p override only supported for GNTMAP_contains_pte mappings */
-		if (!(map_ops[i].flags & GNTMAP_contains_pte))
-			continue;
-		pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
+		if (map_ops[i].flags & GNTMAP_contains_pte) {
+			pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
 				(map_ops[i].host_addr & ~PAGE_MASK));
-		mfn = pte_mfn(*pte);
-		ret = m2p_add_override(mfn, pages[i]);
+			mfn = pte_mfn(*pte);
+		} else {
+			/* If you really wanted to do this:
+			 * mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
+			 *
+			 * The reason we do not implement it is b/c on the
+			 * unmap path (gnttab_unmap_refs) we have no means of
+			 * checking whether the page is !GNTMAP_contains_pte.
+			 *
+			 * That is without some extra data-structure to carry
+			 * the struct page, bool clear_pte, and list_head next
+			 * tuples and deal with allocation/delallocation, etc.
+			 *
+			 * The users of this API set the GNTMAP_contains_pte
+			 * flag so lets just return not supported until it
+			 * becomes neccessary to implement.
+			 */
+			return -EOPNOTSUPP;
+		}
+		ret = m2p_add_override(mfn, pages[i],
+				       map_ops[i].flags & GNTMAP_contains_pte);
 		if (ret)
 			return ret;
 	}
@@ -494,7 +511,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		return ret;
 
 	for (i = 0; i < count; i++) {
-		ret = m2p_remove_override(pages[i]);
+		ret = m2p_remove_override(pages[i], true /* clear the PTE */);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index a2eee574784..0b5366b5be2 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -70,12 +70,7 @@ static int xen_suspend(void *data)
 
 	BUG_ON(!irqs_disabled());
 
-	err = sysdev_suspend(PMSG_FREEZE);
-	if (!err) {
-		err = syscore_suspend();
-		if (err)
-			sysdev_resume();
-	}
+	err = syscore_suspend();
 	if (err) {
 		printk(KERN_ERR "xen_suspend: system core suspend failed: %d\n",
 			err);
@@ -102,7 +97,6 @@ static int xen_suspend(void *data)
 	}
 
 	syscore_resume();
-	sysdev_resume();
 
 	return 0;
 }
diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
index 60f1827a32c..1e0fe01eb67 100644
--- a/drivers/xen/sys-hypervisor.c
+++ b/drivers/xen/sys-hypervisor.c
@@ -215,7 +215,7 @@ static struct attribute_group xen_compilation_group = {
 	.attrs = xen_compile_attrs,
 };
 
-int __init static xen_compilation_init(void)
+static int __init xen_compilation_init(void)
 {
 	return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
 }
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 3313dd19f54..9a37a9b6de3 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -53,11 +53,14 @@ DEFINE_SPINLOCK(configfs_dirent_lock);
 static void configfs_d_iput(struct dentry * dentry,
 			    struct inode * inode)
 {
-	struct configfs_dirent * sd = dentry->d_fsdata;
+	struct configfs_dirent *sd = dentry->d_fsdata;
 
 	if (sd) {
 		BUG_ON(sd->s_dentry != dentry);
+		/* Coordinate with configfs_readdir */
+		spin_lock(&configfs_dirent_lock);
 		sd->s_dentry = NULL;
+		spin_unlock(&configfs_dirent_lock);
 		configfs_put(sd);
 	}
 	iput(inode);
@@ -689,7 +692,8 @@ static int create_default_group(struct config_group *parent_group,
 			sd = child->d_fsdata;
 			sd->s_type |= CONFIGFS_USET_DEFAULT;
 		} else {
-			d_delete(child);
+			BUG_ON(child->d_inode);
+			d_drop(child);
 			dput(child);
 		}
 	}
@@ -1545,7 +1549,7 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
 	struct configfs_dirent * parent_sd = dentry->d_fsdata;
 	struct configfs_dirent *cursor = filp->private_data;
 	struct list_head *p, *q = &cursor->s_sibling;
-	ino_t ino;
+	ino_t ino = 0;
 	int i = filp->f_pos;
 
 	switch (i) {
@@ -1573,6 +1577,7 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
 				struct configfs_dirent *next;
 				const char * name;
 				int len;
+				struct inode *inode = NULL;
 
 				next = list_entry(p, struct configfs_dirent,
 						   s_sibling);
@@ -1581,9 +1586,28 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
 
 				name = configfs_get_name(next);
 				len = strlen(name);
-				if (next->s_dentry)
-					ino = next->s_dentry->d_inode->i_ino;
-				else
+
+				/*
+				 * We'll have a dentry and an inode for
+				 * PINNED items and for open attribute
+				 * files.  We lock here to prevent a race
+				 * with configfs_d_iput() clearing
+				 * s_dentry before calling iput().
+				 *
+				 * Why do we go to the trouble?  If
+				 * someone has an attribute file open,
+				 * the inode number should match until
+				 * they close it.  Beyond that, we don't
+				 * care.
+				 */
+				spin_lock(&configfs_dirent_lock);
+				dentry = next->s_dentry;
+				if (dentry)
+					inode = dentry->d_inode;
+				if (inode)
+					ino = inode->i_ino;
+				spin_unlock(&configfs_dirent_lock);
+				if (!inode)
 					ino = iunique(configfs_sb, 2);
 
 				if (filldir(dirent, name, len, filp->f_pos, ino,
@@ -1683,7 +1707,8 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
 		err = configfs_attach_group(sd->s_element, &group->cg_item,
 					    dentry);
 		if (err) {
-			d_delete(dentry);
+			BUG_ON(dentry->d_inode);
+			d_drop(dentry);
 			dput(dentry);
 		} else {
 			spin_lock(&configfs_dirent_lock);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 89d394d8fe2..90f76575c05 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -428,26 +428,17 @@ static ssize_t write_file_bool(struct file *file, const char __user *user_buf,
 			       size_t count, loff_t *ppos)
 {
 	char buf[32];
-	int buf_size;
+	size_t buf_size;
+	bool bv;
 	u32 *val = file->private_data;
 
 	buf_size = min(count, (sizeof(buf)-1));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
 
-	switch (buf[0]) {
-	case 'y':
-	case 'Y':
-	case '1':
-		*val = 1;
-		break;
-	case 'n':
-	case 'N':
-	case '0':
-		*val = 0;
-		break;
-	}
-	
+	if (strtobool(buf, &bv) == 0)
+		*val = bv;
+
 	return count;
 }
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 643720209a9..9a3e6bbff27 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -539,25 +539,41 @@ static int o2hb_verify_crc(struct o2hb_region *reg,
 
 /* We want to make sure that nobody is heartbeating on top of us --
  * this will help detect an invalid configuration. */
-static int o2hb_check_last_timestamp(struct o2hb_region *reg)
+static void o2hb_check_last_timestamp(struct o2hb_region *reg)
 {
-	int node_num, ret;
 	struct o2hb_disk_slot *slot;
 	struct o2hb_disk_heartbeat_block *hb_block;
+	char *errstr;
 
-	node_num = o2nm_this_node();
-
-	ret = 1;
-	slot = &reg->hr_slots[node_num];
+	slot = &reg->hr_slots[o2nm_this_node()];
 	/* Don't check on our 1st timestamp */
-	if (slot->ds_last_time) {
-		hb_block = slot->ds_raw_block;
+	if (!slot->ds_last_time)
+		return;
 
-		if (le64_to_cpu(hb_block->hb_seq) != slot->ds_last_time)
-			ret = 0;
-	}
+	hb_block = slot->ds_raw_block;
+	if (le64_to_cpu(hb_block->hb_seq) == slot->ds_last_time &&
+	    le64_to_cpu(hb_block->hb_generation) == slot->ds_last_generation &&
+	    hb_block->hb_node == slot->ds_node_num)
+		return;
 
-	return ret;
+#define ERRSTR1		"Another node is heartbeating on device"
+#define ERRSTR2		"Heartbeat generation mismatch on device"
+#define ERRSTR3		"Heartbeat sequence mismatch on device"
+
+	if (hb_block->hb_node != slot->ds_node_num)
+		errstr = ERRSTR1;
+	else if (le64_to_cpu(hb_block->hb_generation) !=
+		 slot->ds_last_generation)
+		errstr = ERRSTR2;
+	else
+		errstr = ERRSTR3;
+
+	mlog(ML_ERROR, "%s (%s): expected(%u:0x%llx, 0x%llx), "
+	     "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_dev_name,
+	     slot->ds_node_num, (unsigned long long)slot->ds_last_generation,
+	     (unsigned long long)slot->ds_last_time, hb_block->hb_node,
+	     (unsigned long long)le64_to_cpu(hb_block->hb_generation),
+	     (unsigned long long)le64_to_cpu(hb_block->hb_seq));
 }
 
 static inline void o2hb_prepare_block(struct o2hb_region *reg,
@@ -983,9 +999,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 	/* With an up to date view of the slots, we can check that no
 	 * other node has been improperly configured to heartbeat in
 	 * our slot. */
-	if (!o2hb_check_last_timestamp(reg))
-		mlog(ML_ERROR, "Device \"%s\": another node is heartbeating "
-		     "in our slot!\n", reg->hr_dev_name);
+	o2hb_check_last_timestamp(reg);
 
 	/* fill in the proper info for our next heartbeat */
 	o2hb_prepare_block(reg, reg->hr_generation);
@@ -999,8 +1013,8 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 	}
 
 	i = -1;
-	while((i = find_next_bit(configured_nodes, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
-
+	while((i = find_next_bit(configured_nodes,
+				 O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
 		change |= o2hb_check_slot(reg, &reg->hr_slots[i]);
 	}
 
@@ -1690,6 +1704,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	struct file *filp = NULL;
 	struct inode *inode = NULL;
 	ssize_t ret = -EINVAL;
+	int live_threshold;
 
 	if (reg->hr_bdev)
 		goto out;
@@ -1766,8 +1781,18 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	 * A node is considered live after it has beat LIVE_THRESHOLD
 	 * times.  We're not steady until we've given them a chance
 	 * _after_ our first read.
+	 * The default threshold is bare minimum so as to limit the delay
+	 * during mounts. For global heartbeat, the threshold doubled for the
+	 * first region.
 	 */
-	atomic_set(&reg->hr_steady_iterations, O2HB_LIVE_THRESHOLD + 1);
+	live_threshold = O2HB_LIVE_THRESHOLD;
+	if (o2hb_global_heartbeat_active()) {
+		spin_lock(&o2hb_live_lock);
+		if (o2hb_pop_count(&o2hb_region_bitmap, O2NM_MAX_REGIONS) == 1)
+			live_threshold <<= 1;
+		spin_unlock(&o2hb_live_lock);
+	}
+	atomic_set(&reg->hr_steady_iterations, live_threshold + 1);
 
 	hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s",
 			      reg->hr_item.ci_name);
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 9fe5b8fd658..8582e3f4f12 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2868,7 +2868,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 		bytes = blocks_wanted << sb->s_blocksize_bits;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
 	struct ocfs2_inode_info *oi = OCFS2_I(dir);
-	struct ocfs2_alloc_context *data_ac;
+	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	struct buffer_head *dirdata_bh = NULL;
 	struct buffer_head *dx_root_bh = NULL;
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 7540a492eab..3b179d6cbde 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1614,7 +1614,8 @@ static int dlm_try_to_join_domain(struct dlm_ctxt *dlm)
 	spin_unlock(&dlm->spinlock);
 
 	/* Support for global heartbeat and node info was added in 1.1 */
-	if (dlm_protocol.pv_major > 1 || dlm_protocol.pv_minor > 0) {
+	if (dlm->dlm_locking_proto.pv_major > 1 ||
+	    dlm->dlm_locking_proto.pv_minor > 0) {
 		status = dlm_send_nodeinfo(dlm, ctxt->yes_resp_map);
 		if (status) {
 			mlog_errno(status);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index fede57ed005..84d166328cf 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2574,6 +2574,9 @@ fail:
 		res->state &= ~DLM_LOCK_RES_MIGRATING;
 		wake = 1;
 		spin_unlock(&res->spinlock);
+		if (dlm_is_host_down(ret))
+			dlm_wait_for_node_death(dlm, target,
+						DLM_NODE_DEATH_WAIT_MAX);
 		goto leave;
 	}
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 41565ae5285..89659d6dc20 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1607,6 +1607,9 @@ static void ocfs2_calc_trunc_pos(struct inode *inode,
 	range = le32_to_cpu(rec->e_cpos) + ocfs2_rec_clusters(el, rec);
 
 	if (le32_to_cpu(rec->e_cpos) >= trunc_start) {
+		/*
+		 * remove an entire extent record.
+		 */
 		*trunc_cpos = le32_to_cpu(rec->e_cpos);
 		/*
 		 * Skip holes if any.
@@ -1617,7 +1620,16 @@ static void ocfs2_calc_trunc_pos(struct inode *inode,
 		*blkno = le64_to_cpu(rec->e_blkno);
 		*trunc_end = le32_to_cpu(rec->e_cpos);
 	} else if (range > trunc_start) {
+		/*
+		 * remove a partial extent record, which means we're
+		 * removing the last extent record.
+		 */
 		*trunc_cpos = trunc_start;
+		/*
+		 * skip hole if any.
+		 */
+		if (range < *trunc_end)
+			*trunc_end = range;
 		*trunc_len = *trunc_end - trunc_start;
 		coff = trunc_start - le32_to_cpu(rec->e_cpos);
 		*blkno = le64_to_cpu(rec->e_blkno) +
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b141a44605c..295d56454e8 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1260,6 +1260,9 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 {
 	struct ocfs2_journal *journal = osb->journal;
 
+	if (ocfs2_is_hard_readonly(osb))
+		return;
+
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index da3fefe91a8..1ad8c93c1b8 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -24,13 +24,6 @@
 
 #include "sysfs.h"
 
-/* used in crash dumps to help with debugging */
-static char last_sysfs_file[PATH_MAX];
-void sysfs_printk_last_file(void)
-{
-	printk(KERN_EMERG "last sysfs file: %s\n", last_sysfs_file);
-}
-
 /*
  * There's one sysfs_buffer for each open file and one
  * sysfs_open_dirent for each sysfs_dirent with one or more open
@@ -337,11 +330,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	struct sysfs_buffer *buffer;
 	const struct sysfs_ops *ops;
 	int error = -EACCES;
-	char *p;
-
-	p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file));
-	if (!IS_ERR(p))
-		memmove(last_sysfs_file, p, strlen(p) + 1);
 
 	/* need attr_sd for attr and ops, its parent for kobj */
 	if (!sysfs_get_active(attr_sd))
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index c8769dc222d..194414f8298 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -101,9 +101,9 @@ int sysfs_create_group(struct kobject *kobj,
 }
 
 /**
- * sysfs_update_group - given a directory kobject, create an attribute group
- * @kobj:	The kobject to create the group on
- * @grp:	The attribute group to create
+ * sysfs_update_group - given a directory kobject, update an attribute group
+ * @kobj:	The kobject to update the group on
+ * @grp:	The attribute group to update
  *
  * This function updates an attribute group.  Unlike
  * sysfs_create_group(), it will explicitly not warn or error if any
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bd297a20ab9..077c00d94f6 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -170,6 +170,10 @@
 	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
+	. = ALIGN(8);                                                   \
+	VMLINUX_SYMBOL(__start___jump_table) = .;                       \
+	*(__jump_table)                                                 \
+	VMLINUX_SYMBOL(__stop___jump_table) = .;                        \
 	. = ALIGN(8);							\
 	VMLINUX_SYMBOL(__start___verbose) = .;                          \
 	*(__verbose)                                                    \
@@ -228,8 +232,6 @@
 									\
 	BUG_TABLE							\
 									\
-	JUMP_TABLE							\
-									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -274,70 +276,70 @@
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___ksymtab) = .;			\
-		*(__ksymtab)						\
+		*(SORT(___ksymtab+*))					\
 		VMLINUX_SYMBOL(__stop___ksymtab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_gpl) = .;		\
-		*(__ksymtab_gpl)					\
+		*(SORT(___ksymtab_gpl+*))				\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__ksymtab_unused  : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_unused) = .;		\
-		*(__ksymtab_unused)					\
+		*(SORT(___ksymtab_unused+*))				\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .;	\
-		*(__ksymtab_unused_gpl)					\
+		*(SORT(___ksymtab_unused_gpl+*))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .;	\
-		*(__ksymtab_gpl_future)					\
+		*(SORT(___ksymtab_gpl_future+*))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___kcrctab) = .;			\
-		*(__kcrctab)						\
+		*(SORT(___kcrctab+*))					\
 		VMLINUX_SYMBOL(__stop___kcrctab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_gpl) = .;		\
-		*(__kcrctab_gpl)					\
+		*(SORT(___kcrctab_gpl+*))				\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__kcrctab_unused  : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_unused) = .;		\
-		*(__kcrctab_unused)					\
+		*(SORT(___kcrctab_unused+*))				\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .;	\
-		*(__kcrctab_unused_gpl)					\
+		*(SORT(___kcrctab_unused_gpl+*))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .;	\
-		*(__kcrctab_gpl_future)					\
+		*(SORT(___kcrctab_gpl_future+*))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .;	\
 	}								\
 									\
@@ -589,14 +591,6 @@
 #define BUG_TABLE
 #endif
 
-#define JUMP_TABLE							\
-	. = ALIGN(8);							\
-	__jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___jump_table) = .;		\
-		*(__jump_table)						\
-		VMLINUX_SYMBOL(__stop___jump_table) = .;		\
-	}
-
 #ifdef CONFIG_PM_TRACE
 #define TRACEDATA							\
 	. = ALIGN(4);							\
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
new file mode 100644
index 00000000000..c5d6095b46f
--- /dev/null
+++ b/include/linux/alarmtimer.h
@@ -0,0 +1,40 @@
+#ifndef _LINUX_ALARMTIMER_H
+#define _LINUX_ALARMTIMER_H
+
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/timerqueue.h>
+#include <linux/rtc.h>
+
+enum alarmtimer_type {
+	ALARM_REALTIME,
+	ALARM_BOOTTIME,
+
+	ALARM_NUMTYPE,
+};
+
+/**
+ * struct alarm - Alarm timer structure
+ * @node:	timerqueue node for adding to the event list this value
+ *		also includes the expiration time.
+ * @period:	Period for recuring alarms
+ * @function:	Function pointer to be executed when the timer fires.
+ * @type:	Alarm type (BOOTTIME/REALTIME)
+ * @enabled:	Flag that represents if the alarm is set to fire or not
+ * @data:	Internal data value.
+ */
+struct alarm {
+	struct timerqueue_node	node;
+	ktime_t			period;
+	void			(*function)(struct alarm *);
+	enum alarmtimer_type	type;
+	bool			enabled;
+	void			*data;
+};
+
+void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
+		void (*function)(struct alarm *));
+void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period);
+void alarm_cancel(struct alarm *alarm);
+
+#endif
diff --git a/include/linux/bsearch.h b/include/linux/bsearch.h
new file mode 100644
index 00000000000..90b1aa86722
--- /dev/null
+++ b/include/linux/bsearch.h
@@ -0,0 +1,9 @@
+#ifndef _LINUX_BSEARCH_H
+#define _LINUX_BSEARCH_H
+
+#include <linux/types.h>
+
+void *bsearch(const void *key, const void *base, size_t num, size_t size,
+	      int (*cmp)(const void *key, const void *elt));
+
+#endif /* _LINUX_BSEARCH_H */
diff --git a/include/linux/capability.h b/include/linux/capability.h
index d4675af963f..4554db0cde8 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -355,7 +355,12 @@ struct cpu_vfs_cap_data {
 
 #define CAP_SYSLOG           34
 
-#define CAP_LAST_CAP         CAP_SYSLOG
+/* Allow triggering something that will wake the system */
+
+#define CAP_WAKE_ALARM            35
+
+
+#define CAP_LAST_CAP         CAP_WAKE_ALARM
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index fc53492b6ad..d6733e27af3 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -56,46 +56,52 @@ enum clock_event_nofitiers {
 
 /**
  * struct clock_event_device - clock event device descriptor
- * @name:		ptr to clock event name
- * @features:		features
+ * @event_handler:	Assigned by the framework to be called by the low
+ *			level handler of the event source
+ * @set_next_event:	set next event function
+ * @next_event:		local storage for the next event in oneshot mode
  * @max_delta_ns:	maximum delta value in ns
  * @min_delta_ns:	minimum delta value in ns
  * @mult:		nanosecond to cycles multiplier
  * @shift:		nanoseconds to cycles divisor (power of two)
+ * @mode:		operating mode assigned by the management code
+ * @features:		features
+ * @retries:		number of forced programming retries
+ * @set_mode:		set mode function
+ * @broadcast:		function to broadcast events
+ * @min_delta_ticks:	minimum delta value in ticks stored for reconfiguration
+ * @max_delta_ticks:	maximum delta value in ticks stored for reconfiguration
+ * @name:		ptr to clock event name
  * @rating:		variable to rate clock event devices
  * @irq:		IRQ number (only for non CPU local devices)
  * @cpumask:		cpumask to indicate for which CPUs this device works
- * @set_next_event:	set next event function
- * @set_mode:		set mode function
- * @event_handler:	Assigned by the framework to be called by the low
- *			level handler of the event source
- * @broadcast:		function to broadcast events
  * @list:		list head for the management code
- * @mode:		operating mode assigned by the management code
- * @next_event:		local storage for the next event in oneshot mode
- * @retries:		number of forced programming retries
  */
 struct clock_event_device {
-	const char		*name;
-	unsigned int		features;
+	void			(*event_handler)(struct clock_event_device *);
+	int			(*set_next_event)(unsigned long evt,
+						  struct clock_event_device *);
+	ktime_t			next_event;
 	u64			max_delta_ns;
 	u64			min_delta_ns;
 	u32			mult;
 	u32			shift;
+	enum clock_event_mode	mode;
+	unsigned int		features;
+	unsigned long		retries;
+
+	void			(*broadcast)(const struct cpumask *mask);
+	void			(*set_mode)(enum clock_event_mode mode,
+					    struct clock_event_device *);
+	unsigned long		min_delta_ticks;
+	unsigned long		max_delta_ticks;
+
+	const char		*name;
 	int			rating;
 	int			irq;
 	const struct cpumask	*cpumask;
-	int			(*set_next_event)(unsigned long evt,
-						  struct clock_event_device *);
-	void			(*set_mode)(enum clock_event_mode mode,
-					    struct clock_event_device *);
-	void			(*event_handler)(struct clock_event_device *);
-	void			(*broadcast)(const struct cpumask *mask);
 	struct list_head	list;
-	enum clock_event_mode	mode;
-	ktime_t			next_event;
-	unsigned long		retries;
-};
+} ____cacheline_aligned;
 
 /*
  * Calculate a multiplication factor for scaled math, which is used to convert
@@ -122,6 +128,12 @@ extern u64 clockevent_delta2ns(unsigned long latch,
 			       struct clock_event_device *evt);
 extern void clockevents_register_device(struct clock_event_device *dev);
 
+extern void clockevents_config_and_register(struct clock_event_device *dev,
+					    u32 freq, unsigned long min_delta,
+					    unsigned long max_delta);
+
+extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq);
+
 extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
 extern void clockevents_set_mode(struct clock_event_device *dev,
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c37b21ad5a3..c918fbd33ee 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -159,42 +159,38 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  */
 struct clocksource {
 	/*
-	 * First part of structure is read mostly
+	 * Hotpath data, fits in a single cache line when the
+	 * clocksource itself is cacheline aligned.
 	 */
-	char *name;
-	struct list_head list;
-	int rating;
 	cycle_t (*read)(struct clocksource *cs);
-	int (*enable)(struct clocksource *cs);
-	void (*disable)(struct clocksource *cs);
+	cycle_t cycle_last;
 	cycle_t mask;
 	u32 mult;
 	u32 shift;
 	u64 max_idle_ns;
-	unsigned long flags;
-	cycle_t (*vread)(void);
-	void (*suspend)(struct clocksource *cs);
-	void (*resume)(struct clocksource *cs);
+
 #ifdef CONFIG_IA64
 	void *fsys_mmio;        /* used by fsyscall asm code */
 #define CLKSRC_FSYS_MMIO_SET(mmio, addr)      ((mmio) = (addr))
 #else
 #define CLKSRC_FSYS_MMIO_SET(mmio, addr)      do { } while (0)
 #endif
-
-	/*
-	 * Second part is written at each timer interrupt
-	 * Keep it in a different cache line to dirty no
-	 * more than one cache line.
-	 */
-	cycle_t cycle_last ____cacheline_aligned_in_smp;
+	const char *name;
+	struct list_head list;
+	int rating;
+	cycle_t (*vread)(void);
+	int (*enable)(struct clocksource *cs);
+	void (*disable)(struct clocksource *cs);
+	unsigned long flags;
+	void (*suspend)(struct clocksource *cs);
+	void (*resume)(struct clocksource *cs);
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
 	struct list_head wd_list;
 	cycle_t wd_last;
 #endif
-};
+} ____cacheline_aligned;
 
 /*
  * Clock source flags bits::
@@ -341,4 +337,6 @@ static inline void update_vsyscall_tz(void)
 
 extern void timekeeping_notify(struct clocksource *clock);
 
+extern int clocksource_i8253_init(void);
+
 #endif /* _LINUX_CLOCKSOURCE_H */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9343dd3de85..11be48e0d16 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2001 Russell King
  *            (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
- *            
+ *
  * 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.
@@ -56,9 +56,9 @@ static inline int cpufreq_unregister_notifier(struct notifier_block *nb,
 #define CPUFREQ_POLICY_POWERSAVE	(1)
 #define CPUFREQ_POLICY_PERFORMANCE	(2)
 
-/* Frequency values here are CPU kHz so that hardware which doesn't run 
- * with some frequencies can complain without having to guess what per 
- * cent / per mille means. 
+/* Frequency values here are CPU kHz so that hardware which doesn't run
+ * with some frequencies can complain without having to guess what per
+ * cent / per mille means.
  * Maximum transition latency is in nanoseconds - if it's unknown,
  * CPUFREQ_ETERNAL shall be used.
  */
@@ -72,13 +72,15 @@ extern struct kobject *cpufreq_global_kobject;
 struct cpufreq_cpuinfo {
 	unsigned int		max_freq;
 	unsigned int		min_freq;
-	unsigned int		transition_latency; /* in 10^(-9) s = nanoseconds */
+
+	/* in 10^(-9) s = nanoseconds */
+	unsigned int		transition_latency;
 };
 
 struct cpufreq_real_policy {
 	unsigned int		min;    /* in kHz */
 	unsigned int		max;    /* in kHz */
-        unsigned int		policy; /* see above */
+	unsigned int		policy; /* see above */
 	struct cpufreq_governor	*governor; /* see below */
 };
 
@@ -94,7 +96,7 @@ struct cpufreq_policy {
 	unsigned int		max;    /* in kHz */
 	unsigned int		cur;    /* in kHz, only needed if cpufreq
 					 * governors are used */
-        unsigned int		policy; /* see above */
+	unsigned int		policy; /* see above */
 	struct cpufreq_governor	*governor; /* see below */
 
 	struct work_struct	update; /* if update_policy() needs to be
@@ -167,11 +169,11 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, u_int mu
 
 struct cpufreq_governor {
 	char	name[CPUFREQ_NAME_LEN];
-	int 	(*governor)	(struct cpufreq_policy *policy,
+	int	(*governor)	(struct cpufreq_policy *policy,
 				 unsigned int event);
 	ssize_t	(*show_setspeed)	(struct cpufreq_policy *policy,
 					 char *buf);
-	int 	(*store_setspeed)	(struct cpufreq_policy *policy,
+	int	(*store_setspeed)	(struct cpufreq_policy *policy,
 					 unsigned int freq);
 	unsigned int max_transition_latency; /* HW must be able to switch to
 			next freq faster than this value in nano secs or we
@@ -180,7 +182,8 @@ struct cpufreq_governor {
 	struct module		*owner;
 };
 
-/* pass a target to the cpufreq driver 
+/*
+ * Pass a target to the cpufreq driver.
  */
 extern int cpufreq_driver_target(struct cpufreq_policy *policy,
 				 unsigned int target_freq,
@@ -237,9 +240,9 @@ struct cpufreq_driver {
 
 /* flags */
 
-#define CPUFREQ_STICKY		0x01	/* the driver isn't removed even if 
+#define CPUFREQ_STICKY		0x01	/* the driver isn't removed even if
 					 * all ->init() calls failed */
-#define CPUFREQ_CONST_LOOPS 	0x02	/* loops_per_jiffy or other kernel
+#define CPUFREQ_CONST_LOOPS	0x02	/* loops_per_jiffy or other kernel
 					 * "constants" aren't affected by
 					 * frequency transitions */
 #define CPUFREQ_PM_NO_WARN	0x04	/* don't warn on suspend/resume speed
@@ -252,7 +255,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state);
 
 
-static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) 
+static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max)
 {
 	if (policy->min < min)
 		policy->min = min;
@@ -386,34 +389,15 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 /* the following 3 funtions are for cpufreq core use only */
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
-void   cpufreq_cpu_put (struct cpufreq_policy *data);
+void   cpufreq_cpu_put(struct cpufreq_policy *data);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 
-void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, 
+void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
 
 
-/*********************************************************************
- *                     UNIFIED DEBUG HELPERS                         *
- *********************************************************************/
-
-#define CPUFREQ_DEBUG_CORE	1
-#define CPUFREQ_DEBUG_DRIVER	2
-#define CPUFREQ_DEBUG_GOVERNOR	4
-
-#ifdef CONFIG_CPU_FREQ_DEBUG
-
-extern void cpufreq_debug_printk(unsigned int type, const char *prefix, 
-				 const char *fmt, ...);
-
-#else
-
-#define cpufreq_debug_printk(msg...) do { } while(0)
-
-#endif /* CONFIG_CPU_FREQ_DEBUG */
-
 #endif /* _LINUX_CPUFREQ_H */
diff --git a/include/linux/device.h b/include/linux/device.h
index d08399db6e2..c66111affca 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -47,6 +47,38 @@ extern int __must_check bus_create_file(struct bus_type *,
 					struct bus_attribute *);
 extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
 
+/**
+ * struct bus_type - The bus type of the device
+ *
+ * @name:	The name of the bus.
+ * @bus_attrs:	Default attributes of the bus.
+ * @dev_attrs:	Default attributes of the devices on the bus.
+ * @drv_attrs:	Default attributes of the device drivers on the bus.
+ * @match:	Called, perhaps multiple times, whenever a new device or driver
+ *		is added for this bus. It should return a nonzero value if the
+ *		given device can be handled by the given driver.
+ * @uevent:	Called when a device is added, removed, or a few other things
+ *		that generate uevents to add the environment variables.
+ * @probe:	Called when a new device or driver add to this bus, and callback
+ *		the specific driver's probe to initial the matched device.
+ * @remove:	Called when a device removed from this bus.
+ * @shutdown:	Called at shut-down time to quiesce the device.
+ * @suspend:	Called when a device on this bus wants to go to sleep mode.
+ * @resume:	Called to bring a device on this bus out of sleep mode.
+ * @pm:		Power management operations of this bus, callback the specific
+ *		device driver's pm-ops.
+ * @p:		The private data of the driver core, only the driver core can
+ *		touch this.
+ *
+ * A bus is a channel between the processor and one or more devices. For the
+ * purposes of the device model, all devices are connected via a bus, even if
+ * it is an internal, virtual, "platform" bus. Buses can plug into each other.
+ * A USB controller is usually a PCI device, for example. The device model
+ * represents the actual connections between buses and the devices they control.
+ * A bus is represented by the bus_type structure. It contains the name, the
+ * default attributes, the bus' methods, PM operations, and the driver core's
+ * private data.
+ */
 struct bus_type {
 	const char		*name;
 	struct bus_attribute	*bus_attrs;
@@ -119,6 +151,37 @@ extern int bus_unregister_notifier(struct bus_type *bus,
 extern struct kset *bus_get_kset(struct bus_type *bus);
 extern struct klist *bus_get_device_klist(struct bus_type *bus);
 
+/**
+ * struct device_driver - The basic device driver structure
+ * @name:	Name of the device driver.
+ * @bus:	The bus which the device of this driver belongs to.
+ * @owner:	The module owner.
+ * @mod_name:	Used for built-in modules.
+ * @suppress_bind_attrs: Disables bind/unbind via sysfs.
+ * @of_match_table: The open firmware table.
+ * @probe:	Called to query the existence of a specific device,
+ *		whether this driver can work with it, and bind the driver
+ *		to a specific device.
+ * @remove:	Called when the device is removed from the system to
+ *		unbind a device from this driver.
+ * @shutdown:	Called at shut-down time to quiesce the device.
+ * @suspend:	Called to put the device to sleep mode. Usually to a
+ *		low power state.
+ * @resume:	Called to bring a device from sleep mode.
+ * @groups:	Default attributes that get created by the driver core
+ *		automatically.
+ * @pm:		Power management operations of the device which matched
+ *		this driver.
+ * @p:		Driver core's private data, no one other than the driver
+ *		core can touch this.
+ *
+ * The device driver-model tracks all of the drivers known to the system.
+ * The main reason for this tracking is to enable the driver core to match
+ * up drivers with new devices. Once drivers are known objects within the
+ * system, however, a number of other things become possible. Device drivers
+ * can export information and configuration variables that are independent
+ * of any specific device.
+ */
 struct device_driver {
 	const char		*name;
 	struct bus_type		*bus;
@@ -185,8 +248,34 @@ struct device *driver_find_device(struct device_driver *drv,
 				  struct device *start, void *data,
 				  int (*match)(struct device *dev, void *data));
 
-/*
- * device classes
+/**
+ * struct class - device classes
+ * @name:	Name of the class.
+ * @owner:	The module owner.
+ * @class_attrs: Default attributes of this class.
+ * @dev_attrs:	Default attributes of the devices belong to the class.
+ * @dev_bin_attrs: Default binary attributes of the devices belong to the class.
+ * @dev_kobj:	The kobject that represents this class and links it into the hierarchy.
+ * @dev_uevent:	Called when a device is added, removed from this class, or a
+ *		few other things that generate uevents to add the environment
+ *		variables.
+ * @devnode:	Callback to provide the devtmpfs.
+ * @class_release: Called to release this class.
+ * @dev_release: Called to release the device.
+ * @suspend:	Used to put the device to sleep mode, usually to a low power
+ *		state.
+ * @resume:	Used to bring the device from the sleep mode.
+ * @ns_type:	Callbacks so sysfs can detemine namespaces.
+ * @namespace:	Namespace of the device belongs to this class.
+ * @pm:		The default device power management operations of this class.
+ * @p:		The private data of the driver core, no one other than the
+ *		driver core can touch this.
+ *
+ * A class is a higher-level view of a device that abstracts out low-level
+ * implementation details. Drivers may see a SCSI disk or an ATA disk, but,
+ * at the class level, they are all simply disks. Classes allow user space
+ * to work with devices based on what they do, rather than how they are
+ * connected or how they work.
  */
 struct class {
 	const char		*name;
@@ -401,6 +490,65 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
+/**
+ * struct device - The basic device structure
+ * @parent:	The device's "parent" device, the device to which it is attached.
+ * 		In most cases, a parent device is some sort of bus or host
+ * 		controller. If parent is NULL, the device, is a top-level device,
+ * 		which is not usually what you want.
+ * @p:		Holds the private data of the driver core portions of the device.
+ * 		See the comment of the struct device_private for detail.
+ * @kobj:	A top-level, abstract class from which other classes are derived.
+ * @init_name:	Initial name of the device.
+ * @type:	The type of device.
+ * 		This identifies the device type and carries type-specific
+ * 		information.
+ * @mutex:	Mutex to synchronize calls to its driver.
+ * @bus:	Type of bus device is on.
+ * @driver:	Which driver has allocated this
+ * @platform_data: Platform data specific to the device.
+ * 		Example: For devices on custom boards, as typical of embedded
+ * 		and SOC based hardware, Linux often uses platform_data to point
+ * 		to board-specific structures describing devices and how they
+ * 		are wired.  That can include what ports are available, chip
+ * 		variants, which GPIO pins act in what additional roles, and so
+ * 		on.  This shrinks the "Board Support Packages" (BSPs) and
+ * 		minimizes board-specific #ifdefs in drivers.
+ * @power:	For device power management.
+ * 		See Documentation/power/devices.txt for details.
+ * @pwr_domain:	Provide callbacks that are executed during system suspend,
+ * 		hibernation, system resume and during runtime PM transitions
+ * 		along with subsystem-level and driver-level callbacks.
+ * @numa_node:	NUMA node this device is close to.
+ * @dma_mask:	Dma mask (if dma'ble device).
+ * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
+ * 		hardware supports 64-bit addresses for consistent allocations
+ * 		such descriptors.
+ * @dma_parms:	A low level driver may set these to teach IOMMU code about
+ * 		segment limitations.
+ * @dma_pools:	Dma pools (if dma'ble device).
+ * @dma_mem:	Internal for coherent mem override.
+ * @archdata:	For arch-specific additions.
+ * @of_node:	Associated device tree node.
+ * @of_match:	Matching of_device_id from driver.
+ * @devt:	For creating the sysfs "dev".
+ * @devres_lock: Spinlock to protect the resource of the device.
+ * @devres_head: The resources list of the device.
+ * @knode_class: The node used to add the device to the class list.
+ * @class:	The class of the device.
+ * @groups:	Optional attribute groups.
+ * @release:	Callback to free the device after all references have
+ * 		gone away. This should be set by the allocator of the
+ * 		device (i.e. the bus driver that discovered the device).
+ *
+ * At the lowest level, every device in a Linux system is represented by an
+ * instance of struct device. The device structure contains the information
+ * that the device model core needs to model the system. Most subsystems,
+ * however, track additional information about the devices they host. As a
+ * result, it is rare for devices to be represented by bare device structures;
+ * instead, that structure, like kobject structures, is usually embedded within
+ * a higher-level representation of the device.
+ */
 struct device {
 	struct device		*parent;
 
@@ -408,7 +556,7 @@ struct device {
 
 	struct kobject kobj;
 	const char		*init_name; /* initial name of the device */
-	struct device_type	*type;
+	const struct device_type *type;
 
 	struct mutex		mutex;	/* mutex to synchronize calls to
 					 * its driver.
@@ -556,7 +704,7 @@ extern int device_move(struct device *dev, struct device *new_parent,
 extern const char *device_get_devnode(struct device *dev,
 				      mode_t *mode, const char **tmp);
 extern void *dev_get_drvdata(const struct device *dev);
-extern void dev_set_drvdata(struct device *dev, void *data);
+extern int dev_set_drvdata(struct device *dev, void *data);
 
 /*
  * Root device objects for grouping under /sys/devices
@@ -610,7 +758,7 @@ extern int (*platform_notify)(struct device *dev);
 extern int (*platform_notify_remove)(struct device *dev);
 
 
-/**
+/*
  * get_device - atomically increment the reference count for the device.
  *
  */
@@ -632,13 +780,6 @@ static inline int devtmpfs_mount(const char *mountpoint) { return 0; }
 /* drivers/base/power/shutdown.c */
 extern void device_shutdown(void);
 
-#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
-/* drivers/base/sys.c */
-extern void sysdev_shutdown(void);
-#else
-static inline void sysdev_shutdown(void) { }
-#endif
-
 /* debugging and troubleshooting/diagnostic helpers. */
 extern const char *dev_driver_string(const struct device *dev);
 
@@ -741,13 +882,17 @@ do {						     \
 #endif
 
 /*
- * dev_WARN() acts like dev_printk(), but with the key difference
+ * dev_WARN*() acts like dev_printk(), but with the key difference
  * of using a WARN/WARN_ON to get the message out, including the
  * file/line information and a backtrace.
  */
 #define dev_WARN(dev, format, arg...) \
 	WARN(1, "Device: %s\n" format, dev_driver_string(dev), ## arg);
 
+#define dev_WARN_ONCE(dev, condition, format, arg...) \
+	WARN_ONCE(condition, "Device %s\n" format, \
+			dev_driver_string(dev), ## arg)
+
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
 	MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor))
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 0c9653f11c1..e747ecd48e1 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -1,8 +1,6 @@
 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
-#include <linux/jump_label.h>
-
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ca29e03c1fa..9d88e1cb5db 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -29,9 +29,22 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
 
+struct ftrace_hash;
+
+enum {
+	FTRACE_OPS_FL_ENABLED		= 1 << 0,
+	FTRACE_OPS_FL_GLOBAL		= 1 << 1,
+	FTRACE_OPS_FL_DYNAMIC		= 1 << 2,
+};
+
 struct ftrace_ops {
-	ftrace_func_t	  func;
-	struct ftrace_ops *next;
+	ftrace_func_t			func;
+	struct ftrace_ops		*next;
+	unsigned long			flags;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	struct ftrace_hash		*notrace_hash;
+	struct ftrace_hash		*filter_hash;
+#endif
 };
 
 extern int function_trace_stop;
@@ -146,14 +159,13 @@ extern void unregister_ftrace_function_probe_all(char *glob);
 extern int ftrace_text_reserved(void *start, void *end);
 
 enum {
-	FTRACE_FL_FREE		= (1 << 0),
-	FTRACE_FL_FAILED	= (1 << 1),
-	FTRACE_FL_FILTER	= (1 << 2),
-	FTRACE_FL_ENABLED	= (1 << 3),
-	FTRACE_FL_NOTRACE	= (1 << 4),
-	FTRACE_FL_CONVERTED	= (1 << 5),
+	FTRACE_FL_ENABLED	= (1 << 30),
+	FTRACE_FL_FREE		= (1 << 31),
 };
 
+#define FTRACE_FL_MASK		(0x3UL << 30)
+#define FTRACE_REF_MAX		((1 << 30) - 1)
+
 struct dyn_ftrace {
 	union {
 		unsigned long		ip; /* address of mcount call-site */
@@ -167,7 +179,12 @@ struct dyn_ftrace {
 };
 
 int ftrace_force_update(void);
-void ftrace_set_filter(unsigned char *buf, int len, int reset);
+void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+		       int len, int reset);
+void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+			int len, int reset);
+void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
+void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 
 int register_ftrace_command(struct ftrace_func_command *cmd);
 int unregister_ftrace_command(struct ftrace_func_command *cmd);
diff --git a/include/linux/init.h b/include/linux/init.h
index 577671c5515..9146f39cddd 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -79,29 +79,29 @@
 #define __exitused  __used
 #endif
 
-#define __exit          __section(.exit.text) __exitused __cold
+#define __exit          __section(.exit.text) __exitused __cold notrace
 
 /* Used for HOTPLUG */
-#define __devinit        __section(.devinit.text) __cold
+#define __devinit        __section(.devinit.text) __cold notrace
 #define __devinitdata    __section(.devinit.data)
 #define __devinitconst   __section(.devinit.rodata)
-#define __devexit        __section(.devexit.text) __exitused __cold
+#define __devexit        __section(.devexit.text) __exitused __cold notrace
 #define __devexitdata    __section(.devexit.data)
 #define __devexitconst   __section(.devexit.rodata)
 
 /* Used for HOTPLUG_CPU */
-#define __cpuinit        __section(.cpuinit.text) __cold
+#define __cpuinit        __section(.cpuinit.text) __cold notrace
 #define __cpuinitdata    __section(.cpuinit.data)
 #define __cpuinitconst   __section(.cpuinit.rodata)
-#define __cpuexit        __section(.cpuexit.text) __exitused __cold
+#define __cpuexit        __section(.cpuexit.text) __exitused __cold notrace
 #define __cpuexitdata    __section(.cpuexit.data)
 #define __cpuexitconst   __section(.cpuexit.rodata)
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold
+#define __meminit        __section(.meminit.text) __cold notrace
 #define __meminitdata    __section(.meminit.data)
 #define __meminitconst   __section(.meminit.rodata)
-#define __memexit        __section(.memexit.text) __exitused __cold
+#define __memexit        __section(.memexit.text) __exitused __cold notrace
 #define __memexitdata    __section(.memexit.data)
 #define __memexitconst   __section(.memexit.rodata)
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index caa151fbebb..689496bb665 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -134,7 +134,6 @@ extern struct cred init_cred;
 	.stack		= &init_thread_info,				\
 	.usage		= ATOMIC_INIT(2),				\
 	.flags		= PF_KTHREAD,					\
-	.lock_depth	= -1,						\
 	.prio		= MAX_PRIO-20,					\
 	.static_prio	= MAX_PRIO-20,					\
 	.normal_prio	= MAX_PRIO-20,					\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index bea0ac75071..6c12989839d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -414,7 +414,6 @@ enum
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
-	RCU_SOFTIRQ,	/* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
 };
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 09a308072f5..8b453844663 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -53,12 +53,13 @@ typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
  * Bits which can be modified via irq_set/clear/modify_status_flags()
  * IRQ_LEVEL			- Interrupt is level type. Will be also
  *				  updated in the code when the above trigger
- *				  bits are modified via set_irq_type()
+ *				  bits are modified via irq_set_irq_type()
  * IRQ_PER_CPU			- Mark an interrupt PER_CPU. Will protect
  *				  it from affinity setting
  * IRQ_NOPROBE			- Interrupt cannot be probed by autoprobing
  * IRQ_NOREQUEST		- Interrupt cannot be requested via
  *				  request_irq()
+ * IRQ_NOTHREAD			- Interrupt cannot be threaded
  * IRQ_NOAUTOEN			- Interrupt is not automatically enabled in
  *				  request/setup_irq()
  * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
@@ -85,6 +86,7 @@ enum {
 	IRQ_NO_BALANCING	= (1 << 13),
 	IRQ_MOVE_PCNTXT		= (1 << 14),
 	IRQ_NESTED_THREAD	= (1 << 15),
+	IRQ_NOTHREAD		= (1 << 16),
 };
 
 #define IRQF_MODIFY_MASK	\
@@ -261,23 +263,6 @@ static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d)
  * struct irq_chip - hardware interrupt chip descriptor
  *
  * @name:		name for /proc/interrupts
- * @startup:		deprecated, replaced by irq_startup
- * @shutdown:		deprecated, replaced by irq_shutdown
- * @enable:		deprecated, replaced by irq_enable
- * @disable:		deprecated, replaced by irq_disable
- * @ack:		deprecated, replaced by irq_ack
- * @mask:		deprecated, replaced by irq_mask
- * @mask_ack:		deprecated, replaced by irq_mask_ack
- * @unmask:		deprecated, replaced by irq_unmask
- * @eoi:		deprecated, replaced by irq_eoi
- * @end:		deprecated, will go away with __do_IRQ()
- * @set_affinity:	deprecated, replaced by irq_set_affinity
- * @retrigger:		deprecated, replaced by irq_retrigger
- * @set_type:		deprecated, replaced by irq_set_type
- * @set_wake:		deprecated, replaced by irq_wake
- * @bus_lock:		deprecated, replaced by irq_bus_lock
- * @bus_sync_unlock:	deprecated, replaced by irq_bus_sync_unlock
- *
  * @irq_startup:	start up the interrupt (defaults to ->enable if NULL)
  * @irq_shutdown:	shut down the interrupt (defaults to ->disable if NULL)
  * @irq_enable:		enable the interrupt (defaults to chip->unmask if NULL)
@@ -295,6 +280,9 @@ static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d)
  * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
  * @irq_cpu_online:	configure an interrupt source for a secondary CPU
  * @irq_cpu_offline:	un-configure an interrupt source for a secondary CPU
+ * @irq_suspend:	function called from core code on suspend once per chip
+ * @irq_resume:		function called from core code on resume once per chip
+ * @irq_pm_shutdown:	function called from core code on shutdown once per chip
  * @irq_print_chip:	optional to print special chip info in show_interrupts
  * @flags:		chip specific flags
  *
@@ -324,6 +312,10 @@ struct irq_chip {
 	void		(*irq_cpu_online)(struct irq_data *data);
 	void		(*irq_cpu_offline)(struct irq_data *data);
 
+	void		(*irq_suspend)(struct irq_data *data);
+	void		(*irq_resume)(struct irq_data *data);
+	void		(*irq_pm_shutdown)(struct irq_data *data);
+
 	void		(*irq_print_chip)(struct irq_data *data, struct seq_file *p);
 
 	unsigned long	flags;
@@ -439,7 +431,7 @@ irq_set_handler(unsigned int irq, irq_flow_handler_t handle)
 /*
  * Set a highlevel chained flow handler for a given IRQ.
  * (a chained handler is automatically enabled and set to
- *  IRQ_NOREQUEST and IRQ_NOPROBE)
+ *  IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD)
  */
 static inline void
 irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
@@ -469,6 +461,16 @@ static inline void irq_set_probe(unsigned int irq)
 	irq_modify_status(irq, IRQ_NOPROBE, 0);
 }
 
+static inline void irq_set_nothread(unsigned int irq)
+{
+	irq_modify_status(irq, 0, IRQ_NOTHREAD);
+}
+
+static inline void irq_set_thread(unsigned int irq)
+{
+	irq_modify_status(irq, IRQ_NOTHREAD, 0);
+}
+
 static inline void irq_set_nested_thread(unsigned int irq, bool nest)
 {
 	if (nest)
@@ -573,6 +575,145 @@ static inline int irq_reserve_irq(unsigned int irq)
 	return irq_reserve_irqs(irq, 1);
 }
 
+#ifndef irq_reg_writel
+# define irq_reg_writel(val, addr)	writel(val, addr)
+#endif
+#ifndef irq_reg_readl
+# define irq_reg_readl(addr)		readl(addr)
+#endif
+
+/**
+ * struct irq_chip_regs - register offsets for struct irq_gci
+ * @enable:	Enable register offset to reg_base
+ * @disable:	Disable register offset to reg_base
+ * @mask:	Mask register offset to reg_base
+ * @ack:	Ack register offset to reg_base
+ * @eoi:	Eoi register offset to reg_base
+ * @type:	Type configuration register offset to reg_base
+ * @polarity:	Polarity configuration register offset to reg_base
+ */
+struct irq_chip_regs {
+	unsigned long		enable;
+	unsigned long		disable;
+	unsigned long		mask;
+	unsigned long		ack;
+	unsigned long		eoi;
+	unsigned long		type;
+	unsigned long		polarity;
+};
+
+/**
+ * struct irq_chip_type - Generic interrupt chip instance for a flow type
+ * @chip:		The real interrupt chip which provides the callbacks
+ * @regs:		Register offsets for this chip
+ * @handler:		Flow handler associated with this chip
+ * @type:		Chip can handle these flow types
+ *
+ * A irq_generic_chip can have several instances of irq_chip_type when
+ * it requires different functions and register offsets for different
+ * flow types.
+ */
+struct irq_chip_type {
+	struct irq_chip		chip;
+	struct irq_chip_regs	regs;
+	irq_flow_handler_t	handler;
+	u32			type;
+};
+
+/**
+ * struct irq_chip_generic - Generic irq chip data structure
+ * @lock:		Lock to protect register and cache data access
+ * @reg_base:		Register base address (virtual)
+ * @irq_base:		Interrupt base nr for this chip
+ * @irq_cnt:		Number of interrupts handled by this chip
+ * @mask_cache:		Cached mask register
+ * @type_cache:		Cached type register
+ * @polarity_cache:	Cached polarity register
+ * @wake_enabled:	Interrupt can wakeup from suspend
+ * @wake_active:	Interrupt is marked as an wakeup from suspend source
+ * @num_ct:		Number of available irq_chip_type instances (usually 1)
+ * @private:		Private data for non generic chip callbacks
+ * @list:		List head for keeping track of instances
+ * @chip_types:		Array of interrupt irq_chip_types
+ *
+ * Note, that irq_chip_generic can have multiple irq_chip_type
+ * implementations which can be associated to a particular irq line of
+ * an irq_chip_generic instance. That allows to share and protect
+ * state in an irq_chip_generic instance when we need to implement
+ * different flow mechanisms (level/edge) for it.
+ */
+struct irq_chip_generic {
+	raw_spinlock_t		lock;
+	void __iomem		*reg_base;
+	unsigned int		irq_base;
+	unsigned int		irq_cnt;
+	u32			mask_cache;
+	u32			type_cache;
+	u32			polarity_cache;
+	u32			wake_enabled;
+	u32			wake_active;
+	unsigned int		num_ct;
+	void			*private;
+	struct list_head	list;
+	struct irq_chip_type	chip_types[0];
+};
+
+/**
+ * enum irq_gc_flags - Initialization flags for generic irq chips
+ * @IRQ_GC_INIT_MASK_CACHE:	Initialize the mask_cache by reading mask reg
+ * @IRQ_GC_INIT_NESTED_LOCK:	Set the lock class of the irqs to nested for
+ *				irq chips which need to call irq_set_wake() on
+ *				the parent irq. Usually GPIO implementations
+ */
+enum irq_gc_flags {
+	IRQ_GC_INIT_MASK_CACHE		= 1 << 0,
+	IRQ_GC_INIT_NESTED_LOCK		= 1 << 1,
+};
+
+/* Generic chip callback functions */
+void irq_gc_noop(struct irq_data *d);
+void irq_gc_mask_disable_reg(struct irq_data *d);
+void irq_gc_mask_set_bit(struct irq_data *d);
+void irq_gc_mask_clr_bit(struct irq_data *d);
+void irq_gc_unmask_enable_reg(struct irq_data *d);
+void irq_gc_ack(struct irq_data *d);
+void irq_gc_mask_disable_reg_and_ack(struct irq_data *d);
+void irq_gc_eoi(struct irq_data *d);
+int irq_gc_set_wake(struct irq_data *d, unsigned int on);
+
+/* Setup functions for irq_chip_generic */
+struct irq_chip_generic *
+irq_alloc_generic_chip(const char *name, int nr_ct, unsigned int irq_base,
+		       void __iomem *reg_base, irq_flow_handler_t handler);
+void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
+			    enum irq_gc_flags flags, unsigned int clr,
+			    unsigned int set);
+int irq_setup_alt_chip(struct irq_data *d, unsigned int type);
+void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk,
+			     unsigned int clr, unsigned int set);
+
+static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d)
+{
+	return container_of(d->chip, struct irq_chip_type, chip);
+}
+
+#define IRQ_MSK(n) (u32)((n) < 32 ? ((1 << (n)) - 1) : UINT_MAX)
+
+#ifdef CONFIG_SMP
+static inline void irq_gc_lock(struct irq_chip_generic *gc)
+{
+	raw_spin_lock(&gc->lock);
+}
+
+static inline void irq_gc_unlock(struct irq_chip_generic *gc)
+{
+	raw_spin_unlock(&gc->lock);
+}
+#else
+static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
+static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
+#endif
+
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #endif /* !CONFIG_S390 */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index a082905b5eb..2d921b35212 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -16,16 +16,18 @@ struct timer_rand_state;
  * @irq_data:		per irq and chip data passed down to chip functions
  * @timer_rand_state:	pointer to timer rand state struct
  * @kstat_irqs:		irq stats per cpu
- * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
+ * @handle_irq:		highlevel irq-events handler
+ * @preflow_handler:	handler called before the flow handler (currently used by sparc)
  * @action:		the irq action chain
  * @status:		status information
  * @core_internal_state__do_not_mess_with_it: core internal status information
  * @depth:		disable-depth, for nested irq_disable() calls
- * @wake_depth:		enable depth, for multiple set_irq_wake() callers
+ * @wake_depth:		enable depth, for multiple irq_set_irq_wake() callers
  * @irq_count:		stats field to detect stalled irqs
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
  * @lock:		locking for SMP
+ * @affinity_hint:	hint to user space for preferred irq affinity
  * @affinity_notify:	context for notification of affinity changes
  * @pending_mask:	pending rebalanced interrupts
  * @threads_oneshot:	bitfield to handle shared oneshot threads
@@ -109,10 +111,7 @@ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *de
 	desc->handle_irq(irq, desc);
 }
 
-static inline void generic_handle_irq(unsigned int irq)
-{
-	generic_handle_irq_desc(irq, irq_to_desc(irq));
-}
+int generic_handle_irq(unsigned int irq);
 
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 7880f18e4b8..83e745f3ead 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -1,20 +1,43 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
+#include <linux/types.h>
+#include <linux/compiler.h>
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
+
+struct jump_label_key {
+	atomic_t enabled;
+	struct jump_entry *entries;
+#ifdef CONFIG_MODULES
+	struct jump_label_mod *next;
+#endif
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
 
 enum jump_label_type {
+	JUMP_LABEL_DISABLE = 0,
 	JUMP_LABEL_ENABLE,
-	JUMP_LABEL_DISABLE
 };
 
 struct module;
 
 #ifdef HAVE_JUMP_LABEL
 
+#ifdef CONFIG_MODULES
+#define JUMP_LABEL_INIT {{ 0 }, NULL, NULL}
+#else
+#define JUMP_LABEL_INIT {{ 0 }, NULL}
+#endif
+
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	return arch_static_branch(key);
+}
+
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
@@ -23,37 +46,37 @@ extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
 				 enum jump_label_type type);
 extern void arch_jump_label_text_poke_early(jump_label_t addr);
-extern void jump_label_update(unsigned long key, enum jump_label_type type);
-extern void jump_label_apply_nops(struct module *mod);
 extern int jump_label_text_reserved(void *start, void *end);
+extern void jump_label_inc(struct jump_label_key *key);
+extern void jump_label_dec(struct jump_label_key *key);
+extern bool jump_label_enabled(struct jump_label_key *key);
+extern void jump_label_apply_nops(struct module *mod);
 
-#define jump_label_enable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+#else
 
-#define jump_label_disable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+#include <asm/atomic.h>
 
-#else
+#define JUMP_LABEL_INIT {ATOMIC_INIT(0)}
 
-#define JUMP_LABEL(key, label)			\
-do {						\
-	if (unlikely(*key))			\
-		goto label;			\
-} while (0)
+struct jump_label_key {
+	atomic_t enabled;
+};
 
-#define jump_label_enable(cond_var)	\
-do {					\
-       *(cond_var) = 1;			\
-} while (0)
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	if (unlikely(atomic_read(&key->enabled)))
+		return true;
+	return false;
+}
 
-#define jump_label_disable(cond_var)	\
-do {					\
-       *(cond_var) = 0;			\
-} while (0)
+static inline void jump_label_inc(struct jump_label_key *key)
+{
+	atomic_inc(&key->enabled);
+}
 
-static inline int jump_label_apply_nops(struct module *mod)
+static inline void jump_label_dec(struct jump_label_key *key)
 {
-	return 0;
+	atomic_dec(&key->enabled);
 }
 
 static inline int jump_label_text_reserved(void *start, void *end)
@@ -64,16 +87,16 @@ static inline int jump_label_text_reserved(void *start, void *end)
 static inline void jump_label_lock(void) {}
 static inline void jump_label_unlock(void) {}
 
-#endif
+static inline bool jump_label_enabled(struct jump_label_key *key)
+{
+	return !!atomic_read(&key->enabled);
+}
 
-#define COND_STMT(key, stmt)					\
-do {								\
-	__label__ jl_enabled;					\
-	JUMP_LABEL(key, jl_enabled);				\
-	if (0) {						\
-jl_enabled:							\
-		stmt;						\
-	}							\
-} while (0)
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+#endif
 
 #endif
diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h
deleted file mode 100644
index e5d012ad92c..00000000000
--- a/include/linux/jump_label_ref.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _LINUX_JUMP_LABEL_REF_H
-#define _LINUX_JUMP_LABEL_REF_H
-
-#include <linux/jump_label.h>
-#include <asm/atomic.h>
-
-#ifdef HAVE_JUMP_LABEL
-
-static inline void jump_label_inc(atomic_t *key)
-{
-	if (atomic_add_return(1, key) == 1)
-		jump_label_enable(key);
-}
-
-static inline void jump_label_dec(atomic_t *key)
-{
-	if (atomic_dec_and_test(key))
-		jump_label_disable(key);
-}
-
-#else /* !HAVE_JUMP_LABEL */
-
-static inline void jump_label_inc(atomic_t *key)
-{
-	atomic_inc(key);
-}
-
-static inline void jump_label_dec(atomic_t *key)
-{
-	atomic_dec(key);
-}
-
-#undef JUMP_LABEL
-#define JUMP_LABEL(key, label)						\
-do {									\
-	if (unlikely(__builtin_choose_expr(				\
-	      __builtin_types_compatible_p(typeof(key), atomic_t *),	\
-	      atomic_read((atomic_t *)(key)), *(key))))			\
-		goto label;						\
-} while (0)
-
-#endif /* HAVE_JUMP_LABEL */
-
-#endif /* _LINUX_JUMP_LABEL_REF_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 00cec4dc0ae..f37ba716ef8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -283,6 +283,7 @@ extern char *get_options(const char *str, int nints, int *ints);
 extern unsigned long long memparse(const char *ptr, char **retptr);
 
 extern int core_kernel_text(unsigned long addr);
+extern int core_kernel_data(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
 extern int func_ptr_is_kernel_text(void *ptr);
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 6efd7a78de6..31023182385 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -113,5 +113,6 @@ extern void usermodehelper_init(void);
 
 extern int usermodehelper_disable(void);
 extern void usermodehelper_enable(void);
+extern bool usermodehelper_is_disabled(void);
 
 #endif /* __LINUX_KMOD_H__ */
diff --git a/include/linux/list.h b/include/linux/list.h
index 3a54266a1e8..cc6d2aa6b41 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/poison.h>
-#include <linux/prefetch.h>
+#include <linux/const.h>
 
 /*
  * Simple doubly linked list implementation.
@@ -367,18 +367,15 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @head:	the head for your list.
  */
 #define list_for_each(pos, head) \
-	for (pos = (head)->next; prefetch(pos->next), pos != (head); \
-        	pos = pos->next)
+	for (pos = (head)->next; pos != (head); pos = pos->next)
 
 /**
  * __list_for_each	-	iterate over a list
  * @pos:	the &struct list_head to use as a loop cursor.
  * @head:	the head for your list.
  *
- * This variant differs from list_for_each() in that it's the
- * simplest possible list iteration code, no prefetching is done.
- * Use this for code that knows the list to be very short (empty
- * or 1 entry) most of the time.
+ * This variant doesn't differ from list_for_each() any more.
+ * We don't do prefetching in either case.
  */
 #define __list_for_each(pos, head) \
 	for (pos = (head)->next; pos != (head); pos = pos->next)
@@ -389,8 +386,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @head:	the head for your list.
  */
 #define list_for_each_prev(pos, head) \
-	for (pos = (head)->prev; prefetch(pos->prev), pos != (head); \
-        	pos = pos->prev)
+	for (pos = (head)->prev; pos != (head); pos = pos->prev)
 
 /**
  * list_for_each_safe - iterate over a list safe against removal of list entry
@@ -410,7 +406,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_prev_safe(pos, n, head) \
 	for (pos = (head)->prev, n = pos->prev; \
-	     prefetch(pos->prev), pos != (head); \
+	     pos != (head); \
 	     pos = n, n = pos->prev)
 
 /**
@@ -421,7 +417,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_entry((head)->next, typeof(*pos), member);	\
-	     prefetch(pos->member.next), &pos->member != (head); 	\
+	     &pos->member != (head); 	\
 	     pos = list_entry(pos->member.next, typeof(*pos), member))
 
 /**
@@ -432,7 +428,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
-	     prefetch(pos->member.prev), &pos->member != (head); 	\
+	     &pos->member != (head); 	\
 	     pos = list_entry(pos->member.prev, typeof(*pos), member))
 
 /**
@@ -457,7 +453,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue(pos, head, member) 		\
 	for (pos = list_entry(pos->member.next, typeof(*pos), member);	\
-	     prefetch(pos->member.next), &pos->member != (head);	\
+	     &pos->member != (head);	\
 	     pos = list_entry(pos->member.next, typeof(*pos), member))
 
 /**
@@ -471,7 +467,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue_reverse(pos, head, member)		\
 	for (pos = list_entry(pos->member.prev, typeof(*pos), member);	\
-	     prefetch(pos->member.prev), &pos->member != (head);	\
+	     &pos->member != (head);	\
 	     pos = list_entry(pos->member.prev, typeof(*pos), member))
 
 /**
@@ -483,7 +479,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from(pos, head, member) 			\
-	for (; prefetch(pos->member.next), &pos->member != (head);	\
+	for (; &pos->member != (head);	\
 	     pos = list_entry(pos->member.next, typeof(*pos), member))
 
 /**
@@ -664,8 +660,7 @@ static inline void hlist_move_list(struct hlist_head *old,
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
-	for (pos = (head)->first; pos && ({ prefetch(pos->next); 1; }); \
-	     pos = pos->next)
+	for (pos = (head)->first; pos ; pos = pos->next)
 
 #define hlist_for_each_safe(pos, n, head) \
 	for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
@@ -680,7 +675,7 @@ static inline void hlist_move_list(struct hlist_head *old,
  */
 #define hlist_for_each_entry(tpos, pos, head, member)			 \
 	for (pos = (head)->first;					 \
-	     pos && ({ prefetch(pos->next); 1;}) &&			 \
+	     pos &&							 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
 	     pos = pos->next)
 
@@ -692,7 +687,7 @@ static inline void hlist_move_list(struct hlist_head *old,
  */
 #define hlist_for_each_entry_continue(tpos, pos, member)		 \
 	for (pos = (pos)->next;						 \
-	     pos && ({ prefetch(pos->next); 1;}) &&			 \
+	     pos &&							 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
 	     pos = pos->next)
 
@@ -703,7 +698,7 @@ static inline void hlist_move_list(struct hlist_head *old,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_from(tpos, pos, member)			 \
-	for (; pos && ({ prefetch(pos->next); 1;}) &&			 \
+	for (; pos &&							 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
 	     pos = pos->next)
 
diff --git a/include/linux/module.h b/include/linux/module.h
index 5de42043dff..d9ca2d5dc6d 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -64,6 +64,9 @@ struct module_version_attribute {
 	const char *version;
 } __attribute__ ((__aligned__(sizeof(void *))));
 
+extern ssize_t __modver_version_show(struct module_attribute *,
+				     struct module *, char *);
+
 struct module_kobject
 {
 	struct kobject kobj;
@@ -172,12 +175,7 @@ extern struct module __this_module;
 #define MODULE_VERSION(_version) MODULE_INFO(version, _version)
 #else
 #define MODULE_VERSION(_version)					\
-	extern ssize_t __modver_version_show(struct module_attribute *,	\
-					     struct module *, char *);	\
-	static struct module_version_attribute __modver_version_attr	\
-	__used								\
-    __attribute__ ((__section__ ("__modver"),aligned(sizeof(void *)))) \
-	= {								\
+	static struct module_version_attribute ___modver_attr = {	\
 		.mattr	= {						\
 			.attr	= {					\
 				.name	= "version",			\
@@ -187,7 +185,10 @@ extern struct module __this_module;
 		},							\
 		.module_name	= KBUILD_MODNAME,			\
 		.version	= _version,				\
-	}
+	};								\
+	static const struct module_version_attribute			\
+	__used __attribute__ ((__section__ ("__modver")))		\
+	* __moduleparam_const __modver_attr = &___modver_attr
 #endif
 
 /* Optional firmware file (or files) needed by the module
@@ -223,7 +224,7 @@ struct module_use {
 	extern void *__crc_##sym __attribute__((weak));		\
 	static const unsigned long __kcrctab_##sym		\
 	__used							\
-	__attribute__((section("__kcrctab" sec), unused))	\
+	__attribute__((section("___kcrctab" sec "+" #sym), unused))	\
 	= (unsigned long) &__crc_##sym;
 #else
 #define __CRC_SYMBOL(sym, sec)
@@ -238,7 +239,7 @@ struct module_use {
 	= MODULE_SYMBOL_PREFIX #sym;                    	\
 	static const struct kernel_symbol __ksymtab_##sym	\
 	__used							\
-	__attribute__((section("__ksymtab" sec), unused))	\
+	__attribute__((section("___ksymtab" sec "+" #sym), unused))	\
 	= { (unsigned long)&sym, __kstrtab_##sym }
 
 #define EXPORT_SYMBOL(sym)					\
@@ -367,34 +368,35 @@ struct module
 	struct module_notes_attrs *notes_attrs;
 #endif
 
+	/* The command line arguments (may be mangled).  People like
+	   keeping pointers to this stuff */
+	char *args;
+
 #ifdef CONFIG_SMP
 	/* Per-cpu data. */
 	void __percpu *percpu;
 	unsigned int percpu_size;
 #endif
 
-	/* The command line arguments (may be mangled).  People like
-	   keeping pointers to this stuff */
-	char *args;
 #ifdef CONFIG_TRACEPOINTS
-	struct tracepoint * const *tracepoints_ptrs;
 	unsigned int num_tracepoints;
+	struct tracepoint * const *tracepoints_ptrs;
 #endif
 #ifdef HAVE_JUMP_LABEL
 	struct jump_entry *jump_entries;
 	unsigned int num_jump_entries;
 #endif
 #ifdef CONFIG_TRACING
-	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
+	const char **trace_bprintk_fmt_start;
 #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;
+	unsigned long *ftrace_callsites;
 #endif
 
 #ifdef CONFIG_MODULE_UNLOAD
@@ -475,8 +477,9 @@ const struct kernel_symbol *find_symbol(const char *name,
 					bool warn);
 
 /* Walk the exported symbol table */
-bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
-			    unsigned int symnum, void *data), void *data);
+bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
+				    struct module *owner,
+				    void *data), void *data);
 
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 07b41951e3f..ddaae98c53f 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -67,9 +67,9 @@ struct kparam_string {
 struct kparam_array
 {
 	unsigned int max;
+	unsigned int elemsize;
 	unsigned int *num;
 	const struct kernel_param_ops *ops;
-	unsigned int elemsize;
 	void *elem;
 };
 
@@ -371,8 +371,9 @@ extern int param_get_invbool(char *buffer, const struct kernel_param *kp);
  */
 #define module_param_array_named(name, array, type, nump, perm)		\
 	static const struct kparam_array __param_arr_##name		\
-	= { ARRAY_SIZE(array), nump, &param_ops_##type,			\
-	    sizeof(array[0]), array };					\
+	= { .max = ARRAY_SIZE(array), .num = nump,                      \
+	    .ops = &param_ops_##type,					\
+	    .elemsize = sizeof(array[0]), .elem = array };		\
 	__module_param_call(MODULE_PARAM_PREFIX, name,			\
 			    &param_array_ops,				\
 			    .arr = &__param_arr_##name,			\
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 94b48bd40dd..c75471db576 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -51,7 +51,7 @@ struct mutex {
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
-	struct thread_info	*owner;
+	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
new file mode 100644
index 00000000000..655824fa4c7
--- /dev/null
+++ b/include/linux/pci-ats.h
@@ -0,0 +1,52 @@
+#ifndef LINUX_PCI_ATS_H
+#define LINUX_PCI_ATS_H
+
+/* Address Translation Service */
+struct pci_ats {
+	int pos;        /* capability position */
+	int stu;        /* Smallest Translation Unit */
+	int qdep;       /* Invalidate Queue Depth */
+	int ref_cnt;    /* Physical Function reference count */
+	unsigned int is_enabled:1;      /* Enable bit is set */
+};
+
+#ifdef CONFIG_PCI_IOV
+
+extern int pci_enable_ats(struct pci_dev *dev, int ps);
+extern void pci_disable_ats(struct pci_dev *dev);
+extern int pci_ats_queue_depth(struct pci_dev *dev);
+/**
+ * pci_ats_enabled - query the ATS status
+ * @dev: the PCI device
+ *
+ * Returns 1 if ATS capability is enabled, or 0 if not.
+ */
+static inline int pci_ats_enabled(struct pci_dev *dev)
+{
+	return dev->ats && dev->ats->is_enabled;
+}
+
+#else /* CONFIG_PCI_IOV */
+
+static inline int pci_enable_ats(struct pci_dev *dev, int ps)
+{
+	return -ENODEV;
+}
+
+static inline void pci_disable_ats(struct pci_dev *dev)
+{
+}
+
+static inline int pci_ats_queue_depth(struct pci_dev *dev)
+{
+	return -ENODEV;
+}
+
+static inline int pci_ats_enabled(struct pci_dev *dev)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PCI_IOV */
+
+#endif /* LINUX_PCI_ATS_H*/
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ee9f1e78280..3412684ce5d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -2,8 +2,8 @@
  * Performance events:
  *
  *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
- *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
- *    Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
  *
  * Data type definitions, declarations, prototypes.
  *
@@ -52,6 +52,8 @@ enum perf_hw_id {
 	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
 	PERF_COUNT_HW_BRANCH_MISSES		= 5,
 	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
 
 	PERF_COUNT_HW_MAX,			/* non-ABI */
 };
@@ -468,9 +470,9 @@ enum perf_callchain_context {
 	PERF_CONTEXT_MAX		= (__u64)-4095,
 };
 
-#define PERF_FLAG_FD_NO_GROUP	(1U << 0)
-#define PERF_FLAG_FD_OUTPUT	(1U << 1)
-#define PERF_FLAG_PID_CGROUP	(1U << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
+#define PERF_FLAG_FD_OUTPUT		(1U << 1)
+#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
 
 #ifdef __KERNEL__
 /*
@@ -484,9 +486,9 @@ enum perf_callchain_context {
 #endif
 
 struct perf_guest_info_callbacks {
-	int (*is_in_guest) (void);
-	int (*is_user_mode) (void);
-	unsigned long (*get_guest_ip) (void);
+	int				(*is_in_guest)(void);
+	int				(*is_user_mode)(void);
+	unsigned long			(*get_guest_ip)(void);
 };
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
@@ -505,7 +507,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/irq_work.h>
-#include <linux/jump_label_ref.h>
+#include <linux/jump_label.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -652,19 +654,19 @@ struct pmu {
 	 * Start the transaction, after this ->add() doesn't need to
 	 * do schedulability tests.
 	 */
-	void (*start_txn)	(struct pmu *pmu); /* optional */
+	void (*start_txn)		(struct pmu *pmu); /* optional */
 	/*
 	 * If ->start_txn() disabled the ->add() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(struct pmu *pmu); /* optional */
+	int  (*commit_txn)		(struct pmu *pmu); /* optional */
 	/*
 	 * Will cancel the transaction, assumes ->del() is called
 	 * for each successful ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(struct pmu *pmu); /* optional */
+	void (*cancel_txn)		(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -712,15 +714,15 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
 					struct pt_regs *regs);
 
 enum perf_group_flag {
-	PERF_GROUP_SOFTWARE = 0x1,
+	PERF_GROUP_SOFTWARE		= 0x1,
 };
 
-#define SWEVENT_HLIST_BITS	8
-#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+#define SWEVENT_HLIST_BITS		8
+#define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
 
 struct swevent_hlist {
-	struct hlist_head	heads[SWEVENT_HLIST_SIZE];
-	struct rcu_head		rcu_head;
+	struct hlist_head		heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head			rcu_head;
 };
 
 #define PERF_ATTACH_CONTEXT	0x01
@@ -733,13 +735,13 @@ struct swevent_hlist {
  * This is a per-cpu dynamically allocated data structure.
  */
 struct perf_cgroup_info {
-	u64 time;
-	u64 timestamp;
+	u64				time;
+	u64				timestamp;
 };
 
 struct perf_cgroup {
-	struct cgroup_subsys_state css;
-	struct perf_cgroup_info *info;	/* timing info, one per cpu */
+	struct				cgroup_subsys_state css;
+	struct				perf_cgroup_info *info;	/* timing info, one per cpu */
 };
 #endif
 
@@ -923,7 +925,7 @@ struct perf_event_context {
 
 /*
  * Number of contexts where an event can trigger:
- * 	task, softirq, hardirq, nmi.
+ *	task, softirq, hardirq, nmi.
  */
 #define PERF_NR_CONTEXTS	4
 
@@ -1001,8 +1003,7 @@ struct perf_sample_data {
 	struct perf_raw_record		*raw;
 };
 
-static inline
-void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
 {
 	data->addr = addr;
 	data->raw  = NULL;
@@ -1034,13 +1035,12 @@ static inline int is_software_event(struct perf_event *event)
 	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
-extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
-static inline void
-perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
+static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
 #endif
 
 /*
@@ -1063,26 +1063,24 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
 	struct pt_regs hot_regs;
 
-	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
-	return;
-
-have_event:
-	if (!regs) {
-		perf_fetch_caller_regs(&hot_regs);
-		regs = &hot_regs;
+	if (static_branch(&perf_swevent_enabled[event_id])) {
+		if (!regs) {
+			perf_fetch_caller_regs(&hot_regs);
+			regs = &hot_regs;
+		}
+		__perf_sw_event(event_id, nr, nmi, regs, addr);
 	}
-	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_sched_events;
+extern struct jump_label_key perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-	COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
+	if (static_branch(&perf_sched_events))
+		__perf_event_task_sched_in(task);
 }
 
-static inline
-void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
@@ -1100,14 +1098,10 @@ extern void perf_event_fork(struct task_struct *tsk);
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 
-extern void perf_callchain_user(struct perf_callchain_entry *entry,
-				struct pt_regs *regs);
-extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
-				  struct pt_regs *regs);
-
+extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
 
-static inline void
-perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
 {
 	if (entry->nr < PERF_MAX_STACK_DEPTH)
 		entry->ip[entry->nr++] = ip;
@@ -1143,9 +1137,9 @@ extern void perf_tp_event(u64 addr, u64 count, void *record,
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
-#define perf_misc_flags(regs)	(user_mode(regs) ? PERF_RECORD_MISC_USER : \
-				 PERF_RECORD_MISC_KERNEL)
-#define perf_instruction_pointer(regs)	instruction_pointer(regs)
+# define perf_misc_flags(regs) \
+		(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
+# define perf_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
 
 extern int perf_output_begin(struct perf_output_handle *handle,
@@ -1180,9 +1174,9 @@ static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
-(struct perf_guest_info_callbacks *callbacks) { return 0; }
+(struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 static inline int perf_unregister_guest_info_callbacks
-(struct perf_guest_info_callbacks *callbacks) { return 0; }
+(struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_comm(struct task_struct *tsk)		{ }
@@ -1195,23 +1189,22 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 static inline void perf_event_task_tick(void)				{ }
 #endif
 
-#define perf_output_put(handle, x) \
-	perf_output_copy((handle), &(x), sizeof(x))
+#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
 
 /*
  * This has to have a higher priority than migration_notifier in sched.c.
  */
-#define perf_cpu_notifier(fn)					\
-do {								\
-	static struct notifier_block fn##_nb __cpuinitdata =	\
-		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
-	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
-		(void *)(unsigned long)smp_processor_id());	\
-	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
-		(void *)(unsigned long)smp_processor_id());	\
-	fn(&fn##_nb, (unsigned long)CPU_ONLINE,			\
-		(void *)(unsigned long)smp_processor_id());	\
-	register_cpu_notifier(&fn##_nb);			\
+#define perf_cpu_notifier(fn)						\
+do {									\
+	static struct notifier_block fn##_nb __cpuinitdata =		\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF };	\
+	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,			\
+		(void *)(unsigned long)smp_processor_id());		\
+	fn(&fn##_nb, (unsigned long)CPU_STARTING,			\
+		(void *)(unsigned long)smp_processor_id());		\
+	fn(&fn##_nb, (unsigned long)CPU_ONLINE,				\
+		(void *)(unsigned long)smp_processor_id());		\
+	register_cpu_notifier(&fn##_nb);				\
 } while (0)
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 744942c95fe..ede1a80e335 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -150,9 +150,6 @@ extern struct platform_device *platform_create_bundle(struct platform_driver *dr
 					struct resource *res, unsigned int n_res,
 					const void *data, size_t size);
 
-extern const struct dev_pm_ops * platform_bus_get_pm_ops(void);
-extern void platform_bus_set_pm_ops(const struct dev_pm_ops *pm);
-
 /* early platform driver interface */
 struct early_platform_driver {
 	const char *class_str;
@@ -205,4 +202,64 @@ static inline char *early_platform_driver_setup_func(void)		\
 }
 #endif /* MODULE */
 
+#ifdef CONFIG_PM_SLEEP
+extern int platform_pm_prepare(struct device *dev);
+extern void platform_pm_complete(struct device *dev);
+#else
+#define platform_pm_prepare	NULL
+#define platform_pm_complete	NULL
+#endif
+
+#ifdef CONFIG_SUSPEND
+extern int platform_pm_suspend(struct device *dev);
+extern int platform_pm_suspend_noirq(struct device *dev);
+extern int platform_pm_resume(struct device *dev);
+extern int platform_pm_resume_noirq(struct device *dev);
+#else
+#define platform_pm_suspend		NULL
+#define platform_pm_resume		NULL
+#define platform_pm_suspend_noirq	NULL
+#define platform_pm_resume_noirq	NULL
+#endif
+
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+extern int platform_pm_freeze(struct device *dev);
+extern int platform_pm_freeze_noirq(struct device *dev);
+extern int platform_pm_thaw(struct device *dev);
+extern int platform_pm_thaw_noirq(struct device *dev);
+extern int platform_pm_poweroff(struct device *dev);
+extern int platform_pm_poweroff_noirq(struct device *dev);
+extern int platform_pm_restore(struct device *dev);
+extern int platform_pm_restore_noirq(struct device *dev);
+#else
+#define platform_pm_freeze		NULL
+#define platform_pm_thaw		NULL
+#define platform_pm_poweroff		NULL
+#define platform_pm_restore		NULL
+#define platform_pm_freeze_noirq	NULL
+#define platform_pm_thaw_noirq		NULL
+#define platform_pm_poweroff_noirq	NULL
+#define platform_pm_restore_noirq	NULL
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+#define USE_PLATFORM_PM_SLEEP_OPS \
+	.prepare = platform_pm_prepare, \
+	.complete = platform_pm_complete, \
+	.suspend = platform_pm_suspend, \
+	.resume = platform_pm_resume, \
+	.freeze = platform_pm_freeze, \
+	.thaw = platform_pm_thaw, \
+	.poweroff = platform_pm_poweroff, \
+	.restore = platform_pm_restore, \
+	.suspend_noirq = platform_pm_suspend_noirq, \
+	.resume_noirq = platform_pm_resume_noirq, \
+	.freeze_noirq = platform_pm_freeze_noirq, \
+	.thaw_noirq = platform_pm_thaw_noirq, \
+	.poweroff_noirq = platform_pm_poweroff_noirq, \
+	.restore_noirq = platform_pm_restore_noirq,
+#else
+#define USE_PLATFORM_PM_SLEEP_OPS
+#endif
+
 #endif /* _PLATFORM_DEVICE_H_ */
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 512e09177e5..3160648ccdd 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -460,6 +460,7 @@ struct dev_pm_info {
 	unsigned long		active_jiffies;
 	unsigned long		suspended_jiffies;
 	unsigned long		accounting_timestamp;
+	void			*subsys_data;  /* Owned by the subsystem. */
 #endif
 };
 
@@ -529,21 +530,17 @@ struct dev_power_domain {
  */
 
 #ifdef CONFIG_PM_SLEEP
-#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
-extern int sysdev_suspend(pm_message_t state);
-extern int sysdev_resume(void);
-#else
-static inline int sysdev_suspend(pm_message_t state) { return 0; }
-static inline int sysdev_resume(void) { return 0; }
-#endif
-
 extern void device_pm_lock(void);
 extern void dpm_resume_noirq(pm_message_t state);
 extern void dpm_resume_end(pm_message_t state);
+extern void dpm_resume(pm_message_t state);
+extern void dpm_complete(pm_message_t state);
 
 extern void device_pm_unlock(void);
 extern int dpm_suspend_noirq(pm_message_t state);
 extern int dpm_suspend_start(pm_message_t state);
+extern int dpm_suspend(pm_message_t state);
+extern int dpm_prepare(pm_message_t state);
 
 extern void __suspend_report_result(const char *function, void *fn, int ret);
 
@@ -553,6 +550,16 @@ extern void __suspend_report_result(const char *function, void *fn, int ret);
 	} while (0)
 
 extern int device_pm_wait_for_dev(struct device *sub, struct device *dev);
+
+extern int pm_generic_prepare(struct device *dev);
+extern int pm_generic_suspend(struct device *dev);
+extern int pm_generic_resume(struct device *dev);
+extern int pm_generic_freeze(struct device *dev);
+extern int pm_generic_thaw(struct device *dev);
+extern int pm_generic_restore(struct device *dev);
+extern int pm_generic_poweroff(struct device *dev);
+extern void pm_generic_complete(struct device *dev);
+
 #else /* !CONFIG_PM_SLEEP */
 
 #define device_pm_lock() do {} while (0)
@@ -569,6 +576,15 @@ static inline int device_pm_wait_for_dev(struct device *a, struct device *b)
 {
 	return 0;
 }
+
+#define pm_generic_prepare	NULL
+#define pm_generic_suspend	NULL
+#define pm_generic_resume	NULL
+#define pm_generic_freeze	NULL
+#define pm_generic_thaw		NULL
+#define pm_generic_restore	NULL
+#define pm_generic_poweroff	NULL
+#define pm_generic_complete	NULL
 #endif /* !CONFIG_PM_SLEEP */
 
 /* How to reorder dpm_list after device_move() */
@@ -579,11 +595,4 @@ enum dpm_order {
 	DPM_ORDER_DEV_LAST,
 };
 
-extern int pm_generic_suspend(struct device *dev);
-extern int pm_generic_resume(struct device *dev);
-extern int pm_generic_freeze(struct device *dev);
-extern int pm_generic_thaw(struct device *dev);
-extern int pm_generic_restore(struct device *dev);
-extern int pm_generic_poweroff(struct device *dev);
-
 #endif /* _LINUX_PM_H */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 8de9aa6e7de..878cf84baeb 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -245,4 +245,46 @@ static inline void pm_runtime_dont_use_autosuspend(struct device *dev)
 	__pm_runtime_use_autosuspend(dev, false);
 }
 
+struct pm_clk_notifier_block {
+	struct notifier_block nb;
+	struct dev_power_domain *pwr_domain;
+	char *con_ids[];
+};
+
+#ifdef CONFIG_PM_RUNTIME_CLK
+extern int pm_runtime_clk_init(struct device *dev);
+extern void pm_runtime_clk_destroy(struct device *dev);
+extern int pm_runtime_clk_add(struct device *dev, const char *con_id);
+extern void pm_runtime_clk_remove(struct device *dev, const char *con_id);
+extern int pm_runtime_clk_suspend(struct device *dev);
+extern int pm_runtime_clk_resume(struct device *dev);
+#else
+static inline int pm_runtime_clk_init(struct device *dev)
+{
+	return -EINVAL;
+}
+static inline void pm_runtime_clk_destroy(struct device *dev)
+{
+}
+static inline int pm_runtime_clk_add(struct device *dev, const char *con_id)
+{
+	return -EINVAL;
+}
+static inline void pm_runtime_clk_remove(struct device *dev, const char *con_id)
+{
+}
+#define pm_runtime_clock_suspend	NULL
+#define pm_runtime_clock_resume		NULL
+#endif
+
+#ifdef CONFIG_HAVE_CLK
+extern void pm_runtime_clk_add_notifier(struct bus_type *bus,
+					struct pm_clk_notifier_block *clknb);
+#else
+static inline void pm_runtime_clk_add_notifier(struct bus_type *bus,
+					struct pm_clk_notifier_block *clknb)
+{
+}
+#endif
+
 #endif
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index d51243ae072..808227d40a6 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/sched.h>
 #include <linux/timex.h>
+#include <linux/alarmtimer.h>
 
 union cpu_time_count {
 	cputime_t cpu;
@@ -80,6 +81,7 @@ struct k_itimer {
 			unsigned long incr;
 			unsigned long expires;
 		} mmtimer;
+		struct alarm alarmtimer;
 	} it;
 };
 
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 7066acb2c53..033b507b33b 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -136,6 +136,14 @@ static inline void rb_set_color(struct rb_node *rb, int color)
 #define RB_EMPTY_NODE(node)	(rb_parent(node) == node)
 #define RB_CLEAR_NODE(node)	(rb_set_parent(node, node))
 
+static inline void rb_init_node(struct rb_node *rb)
+{
+	rb->rb_parent_color = 0;
+	rb->rb_right = NULL;
+	rb->rb_left = NULL;
+	RB_CLEAR_NODE(rb);
+}
+
 extern void rb_insert_color(struct rb_node *, struct rb_root *);
 extern void rb_erase(struct rb_node *, struct rb_root *);
 
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 2dea94fc440..e3beb315517 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -253,7 +253,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  */
 #define list_for_each_entry_rcu(pos, head, member) \
 	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
-		prefetch(pos->member.next), &pos->member != (head); \
+		&pos->member != (head); \
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 
@@ -270,7 +270,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  */
 #define list_for_each_continue_rcu(pos, head) \
 	for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \
-		prefetch((pos)->next), (pos) != (head); \
+		(pos) != (head); \
 		(pos) = rcu_dereference_raw(list_next_rcu(pos)))
 
 /**
@@ -284,7 +284,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  */
 #define list_for_each_entry_continue_rcu(pos, head, member) 		\
 	for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
-	     prefetch(pos->member.next), &pos->member != (head);	\
+	     &pos->member != (head);	\
 	     pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 /**
@@ -427,7 +427,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
 
 #define __hlist_for_each_rcu(pos, head)				\
 	for (pos = rcu_dereference(hlist_first_rcu(head));	\
-	     pos && ({ prefetch(pos->next); 1; });		\
+	     pos;						\
 	     pos = rcu_dereference(hlist_next_rcu(pos)))
 
 /**
@@ -443,7 +443,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  */
 #define hlist_for_each_entry_rcu(tpos, pos, head, member)		\
 	for (pos = rcu_dereference_raw(hlist_first_rcu(head));		\
-		pos && ({ prefetch(pos->next); 1; }) &&			 \
+		pos &&							 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
 		pos = rcu_dereference_raw(hlist_next_rcu(pos)))
 
@@ -460,7 +460,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  */
 #define hlist_for_each_entry_rcu_bh(tpos, pos, head, member)		 \
 	for (pos = rcu_dereference_bh((head)->first);			 \
-		pos && ({ prefetch(pos->next); 1; }) &&			 \
+		pos &&							 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
 		pos = rcu_dereference_bh(pos->next))
 
@@ -472,7 +472,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  */
 #define hlist_for_each_entry_continue_rcu(tpos, pos, member)		\
 	for (pos = rcu_dereference((pos)->next);			\
-	     pos && ({ prefetch(pos->next); 1; }) &&			\
+	     pos &&							\
 	     ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });  \
 	     pos = rcu_dereference(pos->next))
 
@@ -484,7 +484,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  */
 #define hlist_for_each_entry_continue_rcu_bh(tpos, pos, member)		\
 	for (pos = rcu_dereference_bh((pos)->next);			\
-	     pos && ({ prefetch(pos->next); 1; }) &&			\
+	     pos &&							\
 	     ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; });  \
 	     pos = rcu_dereference_bh(pos->next))
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ff422d2b7f9..99f9aa7c280 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -47,6 +47,18 @@
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+extern void rcutorture_record_test_transition(void);
+extern void rcutorture_record_progress(unsigned long vernum);
+#else
+static inline void rcutorture_record_test_transition(void)
+{
+}
+static inline void rcutorture_record_progress(unsigned long vernum)
+{
+}
+#endif
+
 #define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
 #define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
@@ -68,7 +80,6 @@ extern void call_rcu_sched(struct rcu_head *head,
 extern void synchronize_sched(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
-extern int sched_expedited_torture_stats(char *page);
 
 static inline void __rcu_read_lock_bh(void)
 {
@@ -774,6 +785,7 @@ extern struct debug_obj_descr rcuhead_debug_descr;
 
 static inline void debug_rcu_head_queue(struct rcu_head *head)
 {
+	WARN_ON_ONCE((unsigned long)head & 0x3);
 	debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
@@ -797,4 +809,60 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
+{
+	return offset < 4096;
+}
+
+static __always_inline
+void __kfree_rcu(struct rcu_head *head, unsigned long offset)
+{
+	typedef void (*rcu_callback)(struct rcu_head *);
+
+	BUILD_BUG_ON(!__builtin_constant_p(offset));
+
+	/* See the kfree_rcu() header comment. */
+	BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+
+	call_rcu(head, (rcu_callback)offset);
+}
+
+extern void kfree(const void *);
+
+static inline void __rcu_reclaim(struct rcu_head *head)
+{
+	unsigned long offset = (unsigned long)head->func;
+
+	if (__is_kfree_rcu_offset(offset))
+		kfree((void *)head - offset);
+	else
+		head->func(head);
+}
+
+/**
+ * kfree_rcu() - kfree an object after a grace period.
+ * @ptr:	pointer to kfree
+ * @rcu_head:	the name of the struct rcu_head within the type of @ptr.
+ *
+ * Many rcu callbacks functions just call kfree() on the base structure.
+ * These functions are trivial, but their size adds up, and furthermore
+ * when they are used in a kernel module, that module must invoke the
+ * high-latency rcu_barrier() function at module-unload time.
+ *
+ * The kfree_rcu() function handles this issue.  Rather than encoding a
+ * function address in the embedded rcu_head structure, kfree_rcu() instead
+ * encodes the offset of the rcu_head structure within the base structure.
+ * Because the functions are not allowed in the low-order 4096 bytes of
+ * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
+ * If the offset is larger than 4095 bytes, a compile-time error will
+ * be generated in __kfree_rcu().  If this error is triggered, you can
+ * either fall back to use of call_rcu() or rearrange the structure to
+ * position the rcu_head structure into the first 4096 bytes.
+ *
+ * Note that the allowable offset might decrease in the future, for example,
+ * to allow something like kmem_cache_free_rcu().
+ */
+#define kfree_rcu(ptr, rcu_head)					\
+	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
+
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 30ebd7c8d87..52b3e0281fd 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -100,6 +100,14 @@ static inline void rcu_note_context_switch(int cpu)
 }
 
 /*
+ * Take advantage of the fact that there is only one CPU, which
+ * allows us to ignore virtualization-based context switches.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+}
+
+/*
  * Return the number of grace periods.
  */
 static inline long rcu_batches_completed(void)
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 3a933482734..e65d06634dd 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -35,6 +35,16 @@ extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
 extern void rcu_cpu_stall_reset(void);
 
+/*
+ * Note a virtualization-based context switch.  This is simply a
+ * wrapper around rcu_note_context_switch(), which allows TINY_RCU
+ * to save a few bytes.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+	rcu_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 extern void exit_rcu(void);
@@ -58,9 +68,12 @@ static inline void synchronize_rcu_bh_expedited(void)
 
 extern void rcu_barrier(void);
 
+extern unsigned long rcutorture_testseq;
+extern unsigned long rcutorture_vernum;
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
 extern long rcu_batches_completed_sched(void);
+
 extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 781abd13767..12211e1666e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
-extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
+extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
 struct user_namespace;
@@ -731,10 +731,6 @@ struct sched_info {
 	/* timestamps */
 	unsigned long long last_arrival,/* when we last ran on a cpu */
 			   last_queued;	/* when we were last queued to run */
-#ifdef CONFIG_SCHEDSTATS
-	/* BKL stats */
-	unsigned int bkl_count;
-#endif
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
@@ -868,6 +864,7 @@ static inline int sd_power_saving_flags(void)
 
 struct sched_group {
 	struct sched_group *next;	/* Must be a circular list */
+	atomic_t ref;
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
@@ -882,9 +879,6 @@ struct sched_group {
 	 * 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];
 };
@@ -894,17 +888,6 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
 	return to_cpumask(sg->cpumask);
 }
 
-enum sched_domain_level {
-	SD_LV_NONE = 0,
-	SD_LV_SIBLING,
-	SD_LV_MC,
-	SD_LV_BOOK,
-	SD_LV_CPU,
-	SD_LV_NODE,
-	SD_LV_ALLNODES,
-	SD_LV_MAX
-};
-
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -913,6 +896,8 @@ struct sched_domain_attr {
 	.relax_domain_level = -1,			\
 }
 
+extern int sched_domain_level_max;
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -930,7 +915,7 @@ struct sched_domain {
 	unsigned int forkexec_idx;
 	unsigned int smt_gain;
 	int flags;			/* See SD_* */
-	enum sched_domain_level level;
+	int level;
 
 	/* Runtime fields. */
 	unsigned long last_balance;	/* init to jiffies. units in jiffies */
@@ -973,6 +958,10 @@ struct sched_domain {
 #ifdef CONFIG_SCHED_DEBUG
 	char *name;
 #endif
+	union {
+		void *private;		/* used during construction */
+		struct rcu_head rcu;	/* used during destruction */
+	};
 
 	unsigned int span_weight;
 	/*
@@ -981,9 +970,6 @@ struct sched_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];
 };
@@ -1048,8 +1034,12 @@ struct sched_domain;
 #define WF_FORK		0x02		/* child wakeup after fork */
 
 #define ENQUEUE_WAKEUP		1
-#define ENQUEUE_WAKING		2
-#define ENQUEUE_HEAD		4
+#define ENQUEUE_HEAD		2
+#ifdef CONFIG_SMP
+#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
+#else
+#define ENQUEUE_WAKING		0
+#endif
 
 #define DEQUEUE_SLEEP		1
 
@@ -1067,12 +1057,11 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
-			       int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
-	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,
@@ -1197,13 +1186,11 @@ struct task_struct {
 	unsigned int flags;	/* per process flags, defined below */
 	unsigned int ptrace;
 
-	int lock_depth;		/* BKL lock depth */
-
 #ifdef CONFIG_SMP
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-	int oncpu;
-#endif
+	struct task_struct *wake_entry;
+	int on_cpu;
 #endif
+	int on_rq;
 
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;
@@ -1274,6 +1261,7 @@ struct task_struct {
 
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
+	unsigned sched_contributes_to_load:1;
 
 	pid_t pid;
 	pid_t tgid;
@@ -2063,14 +2051,13 @@ extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
-extern void wake_up_new_task(struct task_struct *tsk,
-				unsigned long clone_flags);
+extern void wake_up_new_task(struct task_struct *tsk);
 #ifdef CONFIG_SMP
  extern void kick_process(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p, int clone_flags);
+extern void sched_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
@@ -2195,8 +2182,10 @@ 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
+void scheduler_ipi(void);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void scheduler_ipi(void) { }
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e98cd2e5719..06d69648fc8 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -88,12 +88,12 @@ static __always_inline unsigned read_seqbegin(const seqlock_t *sl)
 	unsigned ret;
 
 repeat:
-	ret = sl->sequence;
-	smp_rmb();
+	ret = ACCESS_ONCE(sl->sequence);
 	if (unlikely(ret & 1)) {
 		cpu_relax();
 		goto repeat;
 	}
+	smp_rmb();
 
 	return ret;
 }
diff --git a/include/linux/signal.h b/include/linux/signal.h
index fcd2b14b193..29a68ac7af8 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -7,6 +7,8 @@
 #ifdef __KERNEL__
 #include <linux/list.h>
 
+struct task_struct;
+
 /* for sysctl */
 extern int print_fatal_signals;
 /*
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index 9659eff52ca..045f72ab5df 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -404,7 +404,9 @@ extern bool ssb_is_sprom_available(struct ssb_bus *bus);
 
 /* Set a fallback SPROM.
  * See kdoc at the function definition for complete documentation. */
-extern int ssb_arch_set_fallback_sprom(const struct ssb_sprom *sprom);
+extern int ssb_arch_register_fallback_sprom(
+		int (*sprom_callback)(struct ssb_bus *bus,
+		struct ssb_sprom *out));
 
 /* Suspend a SSB bus.
  * Call this from the parent bus suspend routine. */
diff --git a/include/linux/string.h b/include/linux/string.h
index a716ee2a8ad..a176db2f2c8 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -123,6 +123,7 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
 extern void argv_free(char **argv);
 
 extern bool sysfs_streq(const char *s1, const char *s2);
+extern int strtobool(const char *s, bool *res);
 
 #ifdef CONFIG_BINARY_PRINTF
 int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args);
diff --git a/include/linux/sysdev.h b/include/linux/sysdev.h
index dfb078db8eb..d35e783a598 100644
--- a/include/linux/sysdev.h
+++ b/include/linux/sysdev.h
@@ -34,12 +34,6 @@ struct sysdev_class {
 	struct list_head	drivers;
 	struct sysdev_class_attribute **attrs;
 	struct kset		kset;
-#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
-	/* Default operations for these types of devices */
-	int	(*shutdown)(struct sys_device *);
-	int	(*suspend)(struct sys_device *, pm_message_t state);
-	int	(*resume)(struct sys_device *);
-#endif
 };
 
 struct sysdev_class_attribute {
@@ -77,11 +71,6 @@ struct sysdev_driver {
 	struct list_head	entry;
 	int	(*add)(struct sys_device *);
 	int	(*remove)(struct sys_device *);
-#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
-	int	(*shutdown)(struct sys_device *);
-	int	(*suspend)(struct sys_device *, pm_message_t state);
-	int	(*resume)(struct sys_device *);
-#endif
 };
 
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 30b881555fa..c3acda60eee 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -176,7 +176,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
 				      const unsigned char *name);
 struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd);
 void sysfs_put(struct sysfs_dirent *sd);
-void sysfs_printk_last_file(void);
 
 /* Called to clear a ns tag when it is no longer valid */
 void sysfs_exit_ns(enum kobj_ns_type type, const void *tag);
@@ -348,10 +347,6 @@ static inline int __must_check sysfs_init(void)
 	return 0;
 }
 
-static inline void sysfs_printk_last_file(void)
-{
-}
-
 #endif /* CONFIG_SYSFS */
 
 #endif /* _SYSFS_H_ */
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 7071ec5d011..b004e557caa 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -140,12 +140,12 @@ extern long st_unregister(struct st_proto_s *);
  */
 struct st_data_s {
 	unsigned long st_state;
-	struct tty_struct *tty;
 	struct sk_buff *tx_skb;
 #define ST_TX_SENDING	1
 #define ST_TX_WAKEUP	2
 	unsigned long tx_state;
 	struct st_proto_s *list[ST_MAX_CHANNELS];
+	bool is_registered[ST_MAX_CHANNELS];
 	unsigned long rx_state;
 	unsigned long rx_count;
 	struct sk_buff *rx_skb;
@@ -155,6 +155,7 @@ struct st_data_s {
 	unsigned char	protos_registered;
 	unsigned long ll_state;
 	void *kim_data;
+	struct tty_struct *tty;
 };
 
 /*
diff --git a/include/linux/time.h b/include/linux/time.h
index 454a2620578..b3061782dec 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -126,6 +126,7 @@ struct timespec __current_kernel_time(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
 void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 				struct timespec *wtom, struct timespec *sleep);
+void timekeeping_inject_sleeptime(struct timespec *delta);
 
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
@@ -294,6 +295,8 @@ struct itimerval {
 #define CLOCK_REALTIME_COARSE		5
 #define CLOCK_MONOTONIC_COARSE		6
 #define CLOCK_BOOTTIME			7
+#define CLOCK_REALTIME_ALARM		8
+#define CLOCK_BOOTTIME_ALARM		9
 
 /*
  * The IDs of various hardware clocks:
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index a520fd70a59..5088727478f 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -39,7 +39,7 @@ struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head)
 
 static inline void timerqueue_init(struct timerqueue_node *node)
 {
-	RB_CLEAR_NODE(&node->node);
+	rb_init_node(&node->node);
 }
 
 static inline void timerqueue_init_head(struct timerqueue_head *head)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 97c84a58efb..d530a4460a0 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -29,7 +29,7 @@ struct tracepoint_func {
 
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
-	int state;			/* State. */
+	struct jump_label_key key;
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
@@ -146,9 +146,7 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
-		return;							\
-do_trace:								\
+		if (static_branch(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
@@ -176,14 +174,14 @@ do_trace:								\
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
  */
-#define DEFINE_TRACE_FN(name, reg, unreg)				\
-	static const char __tpstrtab_##name[]				\
-	__attribute__((section("__tracepoints_strings"))) = #name;	\
-	struct tracepoint __tracepoint_##name				\
-	__attribute__((section("__tracepoints"))) =			\
-		{ __tpstrtab_##name, 0, reg, unreg, NULL };		\
-	static struct tracepoint * const __tracepoint_ptr_##name __used	\
-	__attribute__((section("__tracepoints_ptrs"))) =		\
+#define DEFINE_TRACE_FN(name, reg, unreg)				 \
+	static const char __tpstrtab_##name[]				 \
+	__attribute__((section("__tracepoints_strings"))) = #name;	 \
+	struct tracepoint __tracepoint_##name				 \
+	__attribute__((section("__tracepoints"))) =			 \
+		{ __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\
+	static struct tracepoint * const __tracepoint_ptr_##name __used	 \
+	__attribute__((section("__tracepoints_ptrs"))) =		 \
 		&__tracepoint_##name;
 
 #define DEFINE_TRACE(name)						\
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 505845ddb0b..01e094c6d0a 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -115,7 +115,6 @@
  * sctp/protocol.c
  */
 extern struct sock *sctp_get_ctl_sock(void);
-extern void sctp_local_addr_free(struct rcu_head *head);
 extern int sctp_copy_local_addr_list(struct sctp_bind_addr *,
 				     sctp_scope_t, gfp_t gfp,
 				     int flags);
diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h
index cbb822e8d79..2d0191c90f9 100644
--- a/include/rdma/iw_cm.h
+++ b/include/rdma/iw_cm.h
@@ -46,18 +46,9 @@ enum iw_cm_event_type {
 	IW_CM_EVENT_CLOSE		 /* close complete */
 };
 
-enum iw_cm_event_status {
-	IW_CM_EVENT_STATUS_OK = 0,	 /* request successful */
-	IW_CM_EVENT_STATUS_ACCEPTED = 0, /* connect request accepted */
-	IW_CM_EVENT_STATUS_REJECTED,	 /* connect request rejected */
-	IW_CM_EVENT_STATUS_TIMEOUT,	 /* the operation timed out */
-	IW_CM_EVENT_STATUS_RESET,	 /* reset from remote peer */
-	IW_CM_EVENT_STATUS_EINVAL,	 /* asynchronous failure for bad parm */
-};
-
 struct iw_cm_event {
 	enum iw_cm_event_type event;
-	enum iw_cm_event_status status;
+	int			 status;
 	struct sockaddr_in local_addr;
 	struct sockaddr_in remote_addr;
 	void *private_data;
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 4fae9030464..169f7a53fb0 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -329,4 +329,14 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr);
  */
 void rdma_set_service_type(struct rdma_cm_id *id, int tos);
 
+/**
+ * rdma_set_reuseaddr - Allow the reuse of local addresses when binding
+ *    the rdma_cm_id.
+ * @id: Communication identifier to configure.
+ * @reuse: Value indicating if the bound address is reusable.
+ *
+ * Reuse must be set before an address is bound to the id.
+ */
+int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse);
+
 #endif /* RDMA_CM_H */
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
index 1d165022c02..fc82c1896f7 100644
--- a/include/rdma/rdma_user_cm.h
+++ b/include/rdma/rdma_user_cm.h
@@ -221,8 +221,9 @@ enum {
 
 /* Option details */
 enum {
-	RDMA_OPTION_ID_TOS	= 0,
-	RDMA_OPTION_IB_PATH	= 1
+	RDMA_OPTION_ID_TOS	 = 0,
+	RDMA_OPTION_ID_REUSEADDR = 1,
+	RDMA_OPTION_IB_PATH	 = 1
 };
 
 struct rdma_ucm_set_option {
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 1c09820df58..ae045ca7d35 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -20,8 +20,7 @@ struct softirq_action;
 			 softirq_name(BLOCK_IOPOLL),	\
 			 softirq_name(TASKLET),		\
 			 softirq_name(SCHED),		\
-			 softirq_name(HRTIMER),		\
-			 softirq_name(RCU))
+			 softirq_name(HRTIMER))
 
 /**
  * irq_handler_entry - called immediately before the irq action handler
diff --git a/include/xen/events.h b/include/xen/events.h
index f1b87ad48ac..9af21e19545 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -85,7 +85,8 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
 /* Bind an PSI pirq to an irq. */
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, int vector, const char *name);
+			     int pirq, int vector, const char *name,
+			     domid_t domid);
 #endif
 
 /* De-allocates the above mentioned physical interrupt. */
@@ -94,4 +95,10 @@ int xen_destroy_irq(int irq);
 /* Return irq from pirq */
 int xen_irq_from_pirq(unsigned pirq);
 
+/* Return the pirq allocated to the irq. */
+int xen_pirq_from_irq(unsigned irq);
+
+/* Determine whether to ignore this IRQ if it is passed to a guest. */
+int xen_test_irq_shared(int irq);
+
 #endif	/* _XEN_EVENTS_H */
diff --git a/init/Kconfig b/init/Kconfig
index 7a71e0a9992..4986ecc49e6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -485,7 +485,7 @@ config TREE_RCU_TRACE
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && TINY_PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU
 	default n
 	help
 	  This option boosts the priority of preempted RCU readers that
@@ -827,6 +827,11 @@ config SCHED_AUTOGROUP
 	  desktop applications.  Task group autogeneration is currently based
 	  upon task session.
 
+config SCHED_TTWU_QUEUE
+	bool
+	depends on !SPARC32
+	default y
+
 config MM_OWNER
 	bool
 
diff --git a/init/main.c b/init/main.c
index 4a9479ef454..48df882d51d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -580,8 +580,8 @@ asmlinkage void __init start_kernel(void)
 #endif
 	page_cgroup_init();
 	enable_debug_pagealloc();
-	kmemleak_init();
 	debug_objects_mem_init();
+	kmemleak_init();
 	setup_per_cpu_pageset();
 	numa_policy_init();
 	if (late_time_init)
diff --git a/kernel/Makefile b/kernel/Makefile
index 85cbfb31e73..e9cf19155b4 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -21,7 +21,6 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
-CFLAGS_REMOVE_perf_event.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
@@ -103,8 +102,9 @@ obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
-obj-$(CONFIG_PERF_EVENTS) += perf_event.o
-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+
+obj-$(CONFIG_PERF_EVENTS) += events/
+
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 25c7eb52de1..909a35510af 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -326,12 +326,6 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
 	return &css_set_table[index];
 }
 
-static void free_css_set_rcu(struct rcu_head *obj)
-{
-	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
-	kfree(cg);
-}
-
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
@@ -375,7 +369,7 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 	}
 
 	write_unlock(&css_set_lock);
-	call_rcu(&cg->rcu_head, free_css_set_rcu);
+	kfree_rcu(cg, rcu_head);
 }
 
 /*
@@ -812,13 +806,6 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 	return ret;
 }
 
-static void free_cgroup_rcu(struct rcu_head *obj)
-{
-	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
-
-	kfree(cgrp);
-}
-
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -856,7 +843,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 */
 		BUG_ON(!list_empty(&cgrp->pidlists));
 
-		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
+		kfree_rcu(cgrp, rcu_head);
 	}
 	iput(inode);
 }
@@ -4623,14 +4610,6 @@ bool css_is_ancestor(struct cgroup_subsys_state *child,
 	return ret;
 }
 
-static void __free_css_id_cb(struct rcu_head *head)
-{
-	struct css_id *id;
-
-	id = container_of(head, struct css_id, rcu_head);
-	kfree(id);
-}
-
 void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 {
 	struct css_id *id = css->id;
@@ -4645,7 +4624,7 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, id->id);
 	spin_unlock(&ss->id_lock);
-	call_rcu(&id->rcu_head, __free_css_id_cb);
+	kfree_rcu(id, rcu_head);
 }
 EXPORT_SYMBOL_GPL(free_css_id);
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 33eee16addb..2bb8c2e98ff 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void)
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
 #ifdef CONFIG_SMP
-	if (val < -1 || val >= SD_LV_MAX)
+	if (val < -1 || val >= sched_domain_level_max)
 		return -EINVAL;
 #endif
 
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
new file mode 100644
index 00000000000..1ce23d3d839
--- /dev/null
+++ b/kernel/events/Makefile
@@ -0,0 +1,6 @@
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_core.o = -pg
+endif
+
+obj-y := core.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
diff --git a/kernel/perf_event.c b/kernel/events/core.c
index 8e81a9860a0..c09767f7db3 100644
--- a/kernel/perf_event.c
+++ b/kernel/events/core.c
@@ -2,8 +2,8 @@
  * Performance events core code:
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
- *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
@@ -39,10 +39,10 @@
 #include <asm/irq_regs.h>
 
 struct remote_function_call {
-	struct task_struct *p;
-	int (*func)(void *info);
-	void *info;
-	int ret;
+	struct task_struct	*p;
+	int			(*func)(void *info);
+	void			*info;
+	int			ret;
 };
 
 static void remote_function(void *data)
@@ -76,10 +76,10 @@ static int
 task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
 {
 	struct remote_function_call data = {
-		.p = p,
-		.func = func,
-		.info = info,
-		.ret = -ESRCH, /* No such (running) process */
+		.p	= p,
+		.func	= func,
+		.info	= info,
+		.ret	= -ESRCH, /* No such (running) process */
 	};
 
 	if (task_curr(p))
@@ -100,10 +100,10 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
 static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 {
 	struct remote_function_call data = {
-		.p = NULL,
-		.func = func,
-		.info = info,
-		.ret = -ENXIO, /* No such CPU */
+		.p	= NULL,
+		.func	= func,
+		.info	= info,
+		.ret	= -ENXIO, /* No such CPU */
 	};
 
 	smp_call_function_single(cpu, remote_function, &data, 1);
@@ -125,7 +125,7 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-atomic_t perf_sched_events __read_mostly;
+struct jump_label_key perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -586,14 +586,6 @@ static void get_ctx(struct perf_event_context *ctx)
 	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
-static void free_ctx(struct rcu_head *head)
-{
-	struct perf_event_context *ctx;
-
-	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx);
-}
-
 static void put_ctx(struct perf_event_context *ctx)
 {
 	if (atomic_dec_and_test(&ctx->refcount)) {
@@ -601,7 +593,7 @@ static void put_ctx(struct perf_event_context *ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task)
 			put_task_struct(ctx->task);
-		call_rcu(&ctx->rcu_head, free_ctx);
+		kfree_rcu(ctx, rcu_head);
 	}
 }
 
@@ -5331,14 +5323,6 @@ swevent_hlist_deref(struct swevent_htable *swhash)
 					 lockdep_is_held(&swhash->hlist_mutex));
 }
 
-static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
-{
-	struct swevent_hlist *hlist;
-
-	hlist = container_of(rcu_head, struct swevent_hlist, rcu_head);
-	kfree(hlist);
-}
-
 static void swevent_hlist_release(struct swevent_htable *swhash)
 {
 	struct swevent_hlist *hlist = swevent_hlist_deref(swhash);
@@ -5347,7 +5331,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash)
 		return;
 
 	rcu_assign_pointer(swhash->swevent_hlist, NULL);
-	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
+	kfree_rcu(hlist, rcu_head);
 }
 
 static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
@@ -5429,7 +5413,7 @@ fail:
 	return err;
 }
 
-atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 static void sw_perf_event_destroy(struct perf_event *event)
 {
@@ -7445,11 +7429,11 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 struct cgroup_subsys perf_subsys = {
-	.name = "perf_event",
-	.subsys_id = perf_subsys_id,
-	.create = perf_cgroup_create,
-	.destroy = perf_cgroup_destroy,
-	.exit = perf_cgroup_exit,
-	.attach = perf_cgroup_attach,
+	.name		= "perf_event",
+	.subsys_id	= perf_subsys_id,
+	.create		= perf_cgroup_create,
+	.destroy	= perf_cgroup_destroy,
+	.exit		= perf_cgroup_exit,
+	.attach		= perf_cgroup_attach,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 086adf25a55..086adf25a55 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
diff --git a/kernel/extable.c b/kernel/extable.c
index 7f8f263f852..c2d625fcda7 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -72,6 +72,14 @@ int core_kernel_text(unsigned long addr)
 	return 0;
 }
 
+int core_kernel_data(unsigned long addr)
+{
+	if (addr >= (unsigned long)_sdata &&
+	    addr < (unsigned long)_edata)
+		return 1;
+	return 0;
+}
+
 int __kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
diff --git a/kernel/fork.c b/kernel/fork.c
index e7548dee636..2b44d82b823 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1103,7 +1103,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	posix_cpu_timers_init(p);
 
-	p->lock_depth = -1;		/* -1 = no lock */
 	do_posix_clock_monotonic_gettime(&p->start_time);
 	p->real_start_time = p->start_time;
 	monotonic_to_bootbased(&p->real_start_time);
@@ -1153,7 +1152,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p, clone_flags);
+	sched_fork(p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1464,7 +1463,7 @@ long do_fork(unsigned long clone_flags,
 		 */
 		p->flags &= ~PF_STARTING;
 
-		wake_up_new_task(p, clone_flags);
+		wake_up_new_task(p);
 
 		tracehook_report_clone_complete(trace, regs,
 						clone_flags, nr, p);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 66ecd2ead21..7b01de98bb6 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -17,7 +17,7 @@ static inline void frozen_process(void)
 {
 	if (!unlikely(current->flags & PF_NOFREEZE)) {
 		current->flags |= PF_FROZEN;
-		wmb();
+		smp_wmb();
 	}
 	clear_freeze_flag(current);
 }
@@ -93,7 +93,7 @@ bool freeze_task(struct task_struct *p, bool sig_only)
 	 * the task as frozen and next clears its TIF_FREEZE.
 	 */
 	if (!freezing(p)) {
-		rmb();
+		smp_rmb();
 		if (frozen(p))
 			return false;
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 87fdb3f8db1..dbbbf7d4308 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -81,7 +81,7 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
-static int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 53ead174da2..ea640120ab8 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -33,7 +33,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 /*
  * Zero means infinite timeout - no checking done:
  */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
 
 unsigned long __read_mostly sysctl_hung_task_warnings = 10;
 
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c574f9a12c4..d1d051b38e0 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -48,6 +48,10 @@ config IRQ_PREFLOW_FASTEOI
 config IRQ_EDGE_EOI_HANDLER
        bool
 
+# Generic configurable interrupt chip implementation
+config GENERIC_IRQ_CHIP
+       bool
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 54329cd7b3e..73290056cfb 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,5 +1,6 @@
 
 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
+obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 4af1e2b244c..d5a3009da71 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -310,6 +310,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_simple_irq);
 
 /**
  *	handle_level_irq - Level type irq handler
@@ -573,6 +574,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	if (handle != handle_bad_irq && is_chained) {
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
+		irq_settings_set_nothread(desc);
 		irq_startup(desc);
 	}
 out:
@@ -612,6 +614,7 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 
 	irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(irq_modify_status);
 
 /**
  *	irq_cpu_online - Invoke all irq_cpu_online functions.
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 306cba37e9a..97a8bfadc88 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -27,6 +27,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	P(IRQ_PER_CPU);
 	P(IRQ_NOPROBE);
 	P(IRQ_NOREQUEST);
+	P(IRQ_NOTHREAD);
 	P(IRQ_NOAUTOEN);
 
 	PS(IRQS_AUTODETECT);
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
new file mode 100644
index 00000000000..31a9db71190
--- /dev/null
+++ b/kernel/irq/generic-chip.c
@@ -0,0 +1,354 @@
+/*
+ * Library implementing the most common irq chip callback functions
+ *
+ * Copyright (C) 2011, Thomas Gleixner
+ */
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/syscore_ops.h>
+
+#include "internals.h"
+
+static LIST_HEAD(gc_list);
+static DEFINE_RAW_SPINLOCK(gc_lock);
+
+static inline struct irq_chip_regs *cur_regs(struct irq_data *d)
+{
+	return &container_of(d->chip, struct irq_chip_type, chip)->regs;
+}
+
+/**
+ * irq_gc_noop - NOOP function
+ * @d: irq_data
+ */
+void irq_gc_noop(struct irq_data *d)
+{
+}
+
+/**
+ * irq_gc_mask_disable_reg - Mask chip via disable register
+ * @d: irq_data
+ *
+ * Chip has separate enable/disable registers instead of a single mask
+ * register.
+ */
+void irq_gc_mask_disable_reg(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->disable);
+	gc->mask_cache &= ~mask;
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_mask_set_mask_bit - Mask chip via setting bit in mask register
+ * @d: irq_data
+ *
+ * Chip has a single mask register. Values of this register are cached
+ * and protected by gc->lock
+ */
+void irq_gc_mask_set_bit(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	gc->mask_cache |= mask;
+	irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask);
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_mask_set_mask_bit - Mask chip via clearing bit in mask register
+ * @d: irq_data
+ *
+ * Chip has a single mask register. Values of this register are cached
+ * and protected by gc->lock
+ */
+void irq_gc_mask_clr_bit(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	gc->mask_cache &= ~mask;
+	irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask);
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_unmask_enable_reg - Unmask chip via enable register
+ * @d: irq_data
+ *
+ * Chip has separate enable/disable registers instead of a single mask
+ * register.
+ */
+void irq_gc_unmask_enable_reg(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->enable);
+	gc->mask_cache |= mask;
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_ack - Ack pending interrupt
+ * @d: irq_data
+ */
+void irq_gc_ack(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack);
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt
+ * @d: irq_data
+ */
+void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->mask);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack);
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_eoi - EOI interrupt
+ * @d: irq_data
+ */
+void irq_gc_eoi(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->eoi);
+	irq_gc_unlock(gc);
+}
+
+/**
+ * irq_gc_set_wake - Set/clr wake bit for an interrupt
+ * @d: irq_data
+ *
+ * For chips where the wake from suspend functionality is not
+ * configured in a separate register and the wakeup active state is
+ * just stored in a bitmask.
+ */
+int irq_gc_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << (d->irq - gc->irq_base);
+
+	if (!(mask & gc->wake_enabled))
+		return -EINVAL;
+
+	irq_gc_lock(gc);
+	if (on)
+		gc->wake_active |= mask;
+	else
+		gc->wake_active &= ~mask;
+	irq_gc_unlock(gc);
+	return 0;
+}
+
+/**
+ * irq_alloc_generic_chip - Allocate a generic chip and initialize it
+ * @name:	Name of the irq chip
+ * @num_ct:	Number of irq_chip_type instances associated with this
+ * @irq_base:	Interrupt base nr for this chip
+ * @reg_base:	Register base address (virtual)
+ * @handler:	Default flow handler associated with this chip
+ *
+ * Returns an initialized irq_chip_generic structure. The chip defaults
+ * to the primary (index 0) irq_chip_type and @handler
+ */
+struct irq_chip_generic *
+irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base,
+		       void __iomem *reg_base, irq_flow_handler_t handler)
+{
+	struct irq_chip_generic *gc;
+	unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
+
+	gc = kzalloc(sz, GFP_KERNEL);
+	if (gc) {
+		raw_spin_lock_init(&gc->lock);
+		gc->num_ct = num_ct;
+		gc->irq_base = irq_base;
+		gc->reg_base = reg_base;
+		gc->chip_types->chip.name = name;
+		gc->chip_types->handler = handler;
+	}
+	return gc;
+}
+
+/*
+ * Separate lockdep class for interrupt chip which can nest irq_desc
+ * lock.
+ */
+static struct lock_class_key irq_nested_lock_class;
+
+/**
+ * irq_setup_generic_chip - Setup a range of interrupts with a generic chip
+ * @gc:		Generic irq chip holding all data
+ * @msk:	Bitmask holding the irqs to initialize relative to gc->irq_base
+ * @flags:	Flags for initialization
+ * @clr:	IRQ_* bits to clear
+ * @set:	IRQ_* bits to set
+ *
+ * Set up max. 32 interrupts starting from gc->irq_base. Note, this
+ * initializes all interrupts to the primary irq_chip_type and its
+ * associated handler.
+ */
+void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
+			    enum irq_gc_flags flags, unsigned int clr,
+			    unsigned int set)
+{
+	struct irq_chip_type *ct = gc->chip_types;
+	unsigned int i;
+
+	raw_spin_lock(&gc_lock);
+	list_add_tail(&gc->list, &gc_list);
+	raw_spin_unlock(&gc_lock);
+
+	/* Init mask cache ? */
+	if (flags & IRQ_GC_INIT_MASK_CACHE)
+		gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask);
+
+	for (i = gc->irq_base; msk; msk >>= 1, i++) {
+		if (!msk & 0x01)
+			continue;
+
+		if (flags & IRQ_GC_INIT_NESTED_LOCK)
+			irq_set_lockdep_class(i, &irq_nested_lock_class);
+
+		irq_set_chip_and_handler(i, &ct->chip, ct->handler);
+		irq_set_chip_data(i, gc);
+		irq_modify_status(i, clr, set);
+	}
+	gc->irq_cnt = i - gc->irq_base;
+}
+
+/**
+ * irq_setup_alt_chip - Switch to alternative chip
+ * @d:		irq_data for this interrupt
+ * @type	Flow type to be initialized
+ *
+ * Only to be called from chip->irq_set_type() callbacks.
+ */
+int irq_setup_alt_chip(struct irq_data *d, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = gc->chip_types;
+	unsigned int i;
+
+	for (i = 0; i < gc->num_ct; i++, ct++) {
+		if (ct->type & type) {
+			d->chip = &ct->chip;
+			irq_data_to_desc(d)->handle_irq = ct->handler;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
+/**
+ * irq_remove_generic_chip - Remove a chip
+ * @gc:		Generic irq chip holding all data
+ * @msk:	Bitmask holding the irqs to initialize relative to gc->irq_base
+ * @clr:	IRQ_* bits to clear
+ * @set:	IRQ_* bits to set
+ *
+ * Remove up to 32 interrupts starting from gc->irq_base.
+ */
+void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk,
+			     unsigned int clr, unsigned int set)
+{
+	unsigned int i = gc->irq_base;
+
+	raw_spin_lock(&gc_lock);
+	list_del(&gc->list);
+	raw_spin_unlock(&gc_lock);
+
+	for (; msk; msk >>= 1, i++) {
+		if (!msk & 0x01)
+			continue;
+
+		/* Remove handler first. That will mask the irq line */
+		irq_set_handler(i, NULL);
+		irq_set_chip(i, &no_irq_chip);
+		irq_set_chip_data(i, NULL);
+		irq_modify_status(i, clr, set);
+	}
+}
+
+#ifdef CONFIG_PM
+static int irq_gc_suspend(void)
+{
+	struct irq_chip_generic *gc;
+
+	list_for_each_entry(gc, &gc_list, list) {
+		struct irq_chip_type *ct = gc->chip_types;
+
+		if (ct->chip.irq_suspend)
+			ct->chip.irq_suspend(irq_get_irq_data(gc->irq_base));
+	}
+	return 0;
+}
+
+static void irq_gc_resume(void)
+{
+	struct irq_chip_generic *gc;
+
+	list_for_each_entry(gc, &gc_list, list) {
+		struct irq_chip_type *ct = gc->chip_types;
+
+		if (ct->chip.irq_resume)
+			ct->chip.irq_resume(irq_get_irq_data(gc->irq_base));
+	}
+}
+#else
+#define irq_gc_suspend NULL
+#define irq_gc_resume NULL
+#endif
+
+static void irq_gc_shutdown(void)
+{
+	struct irq_chip_generic *gc;
+
+	list_for_each_entry(gc, &gc_list, list) {
+		struct irq_chip_type *ct = gc->chip_types;
+
+		if (ct->chip.irq_pm_shutdown)
+			ct->chip.irq_pm_shutdown(irq_get_irq_data(gc->irq_base));
+	}
+}
+
+static struct syscore_ops irq_gc_syscore_ops = {
+	.suspend = irq_gc_suspend,
+	.resume = irq_gc_resume,
+	.shutdown = irq_gc_shutdown,
+};
+
+static int __init irq_gc_init_ops(void)
+{
+	register_syscore_ops(&irq_gc_syscore_ops);
+	return 0;
+}
+device_initcall(irq_gc_init_ops);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 2c039c9b938..886e80347b3 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -22,7 +22,7 @@
  */
 static struct lock_class_key irq_desc_lock_class;
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+#if defined(CONFIG_SMP)
 static void __init init_irq_default_affinity(void)
 {
 	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
@@ -290,6 +290,22 @@ static int irq_expand_nr_irqs(unsigned int nr)
 
 #endif /* !CONFIG_SPARSE_IRQ */
 
+/**
+ * generic_handle_irq - Invoke the handler for a particular irq
+ * @irq:	The irq number to handle
+ *
+ */
+int generic_handle_irq(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc)
+		return -EINVAL;
+	generic_handle_irq_desc(irq, desc);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(generic_handle_irq);
+
 /* Dynamic interrupt handling */
 
 /**
@@ -311,6 +327,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
 	bitmap_clear(allocated_irqs, from, cnt);
 	mutex_unlock(&sparse_irq_lock);
 }
+EXPORT_SYMBOL_GPL(irq_free_descs);
 
 /**
  * irq_alloc_descs - allocate and initialize a range of irq descriptors
@@ -351,6 +368,7 @@ err:
 	mutex_unlock(&sparse_irq_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(irq_alloc_descs);
 
 /**
  * irq_reserve_irqs - mark irqs allocated
@@ -430,7 +448,6 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
 }
 
-#ifdef CONFIG_GENERIC_HARDIRQS
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -443,4 +460,3 @@ unsigned int kstat_irqs(unsigned int irq)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
 	return sum;
 }
-#endif /* CONFIG_GENERIC_HARDIRQS */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 07c1611f389..f7ce0021e1c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -900,7 +900,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		new->handler = irq_nested_primary_handler;
 	} else {
-		irq_setup_forced_threading(new);
+		if (irq_settings_can_thread(desc))
+			irq_setup_forced_threading(new);
 	}
 
 	/*
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 0d91730b633..f1667833d44 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -8,6 +8,7 @@ enum {
 	_IRQ_LEVEL		= IRQ_LEVEL,
 	_IRQ_NOPROBE		= IRQ_NOPROBE,
 	_IRQ_NOREQUEST		= IRQ_NOREQUEST,
+	_IRQ_NOTHREAD		= IRQ_NOTHREAD,
 	_IRQ_NOAUTOEN		= IRQ_NOAUTOEN,
 	_IRQ_MOVE_PCNTXT	= IRQ_MOVE_PCNTXT,
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
@@ -20,6 +21,7 @@ enum {
 #define IRQ_LEVEL		GOT_YOU_MORON
 #define IRQ_NOPROBE		GOT_YOU_MORON
 #define IRQ_NOREQUEST		GOT_YOU_MORON
+#define IRQ_NOTHREAD		GOT_YOU_MORON
 #define IRQ_NOAUTOEN		GOT_YOU_MORON
 #define IRQ_NESTED_THREAD	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
@@ -94,6 +96,21 @@ static inline void irq_settings_set_norequest(struct irq_desc *desc)
 	desc->status_use_accessors |= _IRQ_NOREQUEST;
 }
 
+static inline bool irq_settings_can_thread(struct irq_desc *desc)
+{
+	return !(desc->status_use_accessors & _IRQ_NOTHREAD);
+}
+
+static inline void irq_settings_clr_nothread(struct irq_desc *desc)
+{
+	desc->status_use_accessors &= ~_IRQ_NOTHREAD;
+}
+
+static inline void irq_settings_set_nothread(struct irq_desc *desc)
+{
+	desc->status_use_accessors |= _IRQ_NOTHREAD;
+}
+
 static inline bool irq_settings_can_probe(struct irq_desc *desc)
 {
 	return !(desc->status_use_accessors & _IRQ_NOPROBE);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 3b79bd93833..74d1c099fbd 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -2,43 +2,23 @@
  * jump label support
  *
  * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
  *
  */
-#include <linux/jump_label.h>
 #include <linux/memory.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/list.h>
-#include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
 #include <linux/err.h>
+#include <linux/jump_label.h>
 
 #ifdef HAVE_JUMP_LABEL
 
-#define JUMP_LABEL_HASH_BITS 6
-#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS)
-static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE];
-
 /* mutex to protect coming/going of the the jump_label table */
 static DEFINE_MUTEX(jump_label_mutex);
 
-struct jump_label_entry {
-	struct hlist_node hlist;
-	struct jump_entry *table;
-	int nr_entries;
-	/* hang modules off here */
-	struct hlist_head modules;
-	unsigned long key;
-};
-
-struct jump_label_module_entry {
-	struct hlist_node hlist;
-	struct jump_entry *table;
-	int nr_entries;
-	struct module *mod;
-};
-
 void jump_label_lock(void)
 {
 	mutex_lock(&jump_label_mutex);
@@ -49,6 +29,11 @@ void jump_label_unlock(void)
 	mutex_unlock(&jump_label_mutex);
 }
 
+bool jump_label_enabled(struct jump_label_key *key)
+{
+	return !!atomic_read(&key->enabled);
+}
+
 static int jump_label_cmp(const void *a, const void *b)
 {
 	const struct jump_entry *jea = a;
@@ -64,7 +49,7 @@ static int jump_label_cmp(const void *a, const void *b)
 }
 
 static void
-sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop)
+jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
 {
 	unsigned long size;
 
@@ -73,118 +58,25 @@ sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop)
 	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
 }
 
-static struct jump_label_entry *get_jump_label_entry(jump_label_t key)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct jump_label_entry *e;
-	u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0);
-
-	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (key == e->key)
-			return e;
-	}
-	return NULL;
-}
+static void jump_label_update(struct jump_label_key *key, int enable);
 
-static struct jump_label_entry *
-add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table)
+void jump_label_inc(struct jump_label_key *key)
 {
-	struct hlist_head *head;
-	struct jump_label_entry *e;
-	u32 hash;
-
-	e = get_jump_label_entry(key);
-	if (e)
-		return ERR_PTR(-EEXIST);
-
-	e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL);
-	if (!e)
-		return ERR_PTR(-ENOMEM);
-
-	hash = jhash((void *)&key, sizeof(jump_label_t), 0);
-	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
-	e->key = key;
-	e->table = table;
-	e->nr_entries = nr_entries;
-	INIT_HLIST_HEAD(&(e->modules));
-	hlist_add_head(&e->hlist, head);
-	return e;
-}
+	if (atomic_inc_not_zero(&key->enabled))
+		return;
 
-static int
-build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop)
-{
-	struct jump_entry *iter, *iter_begin;
-	struct jump_label_entry *entry;
-	int count;
-
-	sort_jump_label_entries(start, stop);
-	iter = start;
-	while (iter < stop) {
-		entry = get_jump_label_entry(iter->key);
-		if (!entry) {
-			iter_begin = iter;
-			count = 0;
-			while ((iter < stop) &&
-				(iter->key == iter_begin->key)) {
-				iter++;
-				count++;
-			}
-			entry = add_jump_label_entry(iter_begin->key,
-							count, iter_begin);
-			if (IS_ERR(entry))
-				return PTR_ERR(entry);
-		 } else {
-			WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n");
-			return -1;
-		}
-	}
-	return 0;
+	jump_label_lock();
+	if (atomic_add_return(1, &key->enabled) == 1)
+		jump_label_update(key, JUMP_LABEL_ENABLE);
+	jump_label_unlock();
 }
 
-/***
- * jump_label_update - update jump label text
- * @key -  key value associated with a a jump label
- * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE
- *
- * Will enable/disable the jump for jump label @key, depending on the
- * value of @type.
- *
- */
-
-void jump_label_update(unsigned long key, enum jump_label_type type)
+void jump_label_dec(struct jump_label_key *key)
 {
-	struct jump_entry *iter;
-	struct jump_label_entry *entry;
-	struct hlist_node *module_node;
-	struct jump_label_module_entry *e_module;
-	int count;
+	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
+		return;
 
-	jump_label_lock();
-	entry = get_jump_label_entry((jump_label_t)key);
-	if (entry) {
-		count = entry->nr_entries;
-		iter = entry->table;
-		while (count--) {
-			if (kernel_text_address(iter->code))
-				arch_jump_label_transform(iter, type);
-			iter++;
-		}
-		/* eanble/disable jump labels in modules */
-		hlist_for_each_entry(e_module, module_node, &(entry->modules),
-							hlist) {
-			count = e_module->nr_entries;
-			iter = e_module->table;
-			while (count--) {
-				if (iter->key &&
-						kernel_text_address(iter->code))
-					arch_jump_label_transform(iter, type);
-				iter++;
-			}
-		}
-	}
+	jump_label_update(key, JUMP_LABEL_DISABLE);
 	jump_label_unlock();
 }
 
@@ -197,77 +89,33 @@ static int addr_conflict(struct jump_entry *entry, void *start, void *end)
 	return 0;
 }
 
-#ifdef CONFIG_MODULES
-
-static int module_conflict(void *start, void *end)
+static int __jump_label_text_reserved(struct jump_entry *iter_start,
+		struct jump_entry *iter_stop, void *start, void *end)
 {
-	struct hlist_head *head;
-	struct hlist_node *node, *node_next, *module_node, *module_node_next;
-	struct jump_label_entry *e;
-	struct jump_label_module_entry *e_module;
 	struct jump_entry *iter;
-	int i, count;
-	int conflict = 0;
-
-	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
-		head = &jump_label_table[i];
-		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
-			hlist_for_each_entry_safe(e_module, module_node,
-							module_node_next,
-							&(e->modules), hlist) {
-				count = e_module->nr_entries;
-				iter = e_module->table;
-				while (count--) {
-					if (addr_conflict(iter, start, end)) {
-						conflict = 1;
-						goto out;
-					}
-					iter++;
-				}
-			}
-		}
-	}
-out:
-	return conflict;
-}
-
-#endif
-
-/***
- * jump_label_text_reserved - check if addr range is reserved
- * @start: start text addr
- * @end: end text addr
- *
- * checks if the text addr located between @start and @end
- * overlaps with any of the jump label patch addresses. Code
- * that wants to modify kernel text should first verify that
- * it does not overlap with any of the jump label addresses.
- * Caller must hold jump_label_mutex.
- *
- * returns 1 if there is an overlap, 0 otherwise
- */
-int jump_label_text_reserved(void *start, void *end)
-{
-	struct jump_entry *iter;
-	struct jump_entry *iter_start = __start___jump_table;
-	struct jump_entry *iter_stop = __start___jump_table;
-	int conflict = 0;
 
 	iter = iter_start;
 	while (iter < iter_stop) {
-		if (addr_conflict(iter, start, end)) {
-			conflict = 1;
-			goto out;
-		}
+		if (addr_conflict(iter, start, end))
+			return 1;
 		iter++;
 	}
 
-	/* now check modules */
-#ifdef CONFIG_MODULES
-	conflict = module_conflict(start, end);
-#endif
-out:
-	return conflict;
+	return 0;
+}
+
+static void __jump_label_update(struct jump_label_key *key,
+		struct jump_entry *entry, int enable)
+{
+	for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+		/*
+		 * entry->code set to 0 invalidates module init text sections
+		 * kernel_text_address() verifies we are not in core kernel
+		 * init code, see jump_label_invalidate_module_init().
+		 */
+		if (entry->code && kernel_text_address(entry->code))
+			arch_jump_label_transform(entry, enable);
+	}
 }
 
 /*
@@ -277,142 +125,173 @@ void __weak arch_jump_label_text_poke_early(jump_label_t addr)
 {
 }
 
-static __init int init_jump_label(void)
+static __init int jump_label_init(void)
 {
-	int ret;
 	struct jump_entry *iter_start = __start___jump_table;
 	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_label_key *key = NULL;
 	struct jump_entry *iter;
 
 	jump_label_lock();
-	ret = build_jump_label_hashtable(__start___jump_table,
-					 __stop___jump_table);
-	iter = iter_start;
-	while (iter < iter_stop) {
+	jump_label_sort_entries(iter_start, iter_stop);
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
 		arch_jump_label_text_poke_early(iter->code);
-		iter++;
+		if (iter->key == (jump_label_t)(unsigned long)key)
+			continue;
+
+		key = (struct jump_label_key *)(unsigned long)iter->key;
+		atomic_set(&key->enabled, 0);
+		key->entries = iter;
+#ifdef CONFIG_MODULES
+		key->next = NULL;
+#endif
 	}
 	jump_label_unlock();
-	return ret;
+
+	return 0;
 }
-early_initcall(init_jump_label);
+early_initcall(jump_label_init);
 
 #ifdef CONFIG_MODULES
 
-static struct jump_label_module_entry *
-add_jump_label_module_entry(struct jump_label_entry *entry,
-			    struct jump_entry *iter_begin,
-			    int count, struct module *mod)
+struct jump_label_mod {
+	struct jump_label_mod *next;
+	struct jump_entry *entries;
+	struct module *mod;
+};
+
+static int __jump_label_mod_text_reserved(void *start, void *end)
+{
+	struct module *mod;
+
+	mod = __module_text_address((unsigned long)start);
+	if (!mod)
+		return 0;
+
+	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+
+	return __jump_label_text_reserved(mod->jump_entries,
+				mod->jump_entries + mod->num_jump_entries,
+				start, end);
+}
+
+static void __jump_label_mod_update(struct jump_label_key *key, int enable)
+{
+	struct jump_label_mod *mod = key->next;
+
+	while (mod) {
+		__jump_label_update(key, mod->entries, enable);
+		mod = mod->next;
+	}
+}
+
+/***
+ * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
+ * @mod: module to patch
+ *
+ * Allow for run-time selection of the optimal nops. Before the module
+ * loads patch these with arch_get_jump_label_nop(), which is specified by
+ * the arch specific jump label code.
+ */
+void jump_label_apply_nops(struct module *mod)
 {
-	struct jump_label_module_entry *e;
-
-	e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL);
-	if (!e)
-		return ERR_PTR(-ENOMEM);
-	e->mod = mod;
-	e->nr_entries = count;
-	e->table = iter_begin;
-	hlist_add_head(&e->hlist, &entry->modules);
-	return e;
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
+	struct jump_entry *iter;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (iter_start == iter_stop)
+		return;
+
+	for (iter = iter_start; iter < iter_stop; iter++)
+		arch_jump_label_text_poke_early(iter->code);
 }
 
-static int add_jump_label_module(struct module *mod)
+static int jump_label_add_module(struct module *mod)
 {
-	struct jump_entry *iter, *iter_begin;
-	struct jump_label_entry *entry;
-	struct jump_label_module_entry *module_entry;
-	int count;
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
+	struct jump_entry *iter;
+	struct jump_label_key *key = NULL;
+	struct jump_label_mod *jlm;
 
 	/* if the module doesn't have jump label entries, just return */
-	if (!mod->num_jump_entries)
+	if (iter_start == iter_stop)
 		return 0;
 
-	sort_jump_label_entries(mod->jump_entries,
-				mod->jump_entries + mod->num_jump_entries);
-	iter = mod->jump_entries;
-	while (iter < mod->jump_entries + mod->num_jump_entries) {
-		entry = get_jump_label_entry(iter->key);
-		iter_begin = iter;
-		count = 0;
-		while ((iter < mod->jump_entries + mod->num_jump_entries) &&
-			(iter->key == iter_begin->key)) {
-				iter++;
-				count++;
-		}
-		if (!entry) {
-			entry = add_jump_label_entry(iter_begin->key, 0, NULL);
-			if (IS_ERR(entry))
-				return PTR_ERR(entry);
+	jump_label_sort_entries(iter_start, iter_stop);
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		if (iter->key == (jump_label_t)(unsigned long)key)
+			continue;
+
+		key = (struct jump_label_key *)(unsigned long)iter->key;
+
+		if (__module_address(iter->key) == mod) {
+			atomic_set(&key->enabled, 0);
+			key->entries = iter;
+			key->next = NULL;
+			continue;
 		}
-		module_entry = add_jump_label_module_entry(entry, iter_begin,
-							   count, mod);
-		if (IS_ERR(module_entry))
-			return PTR_ERR(module_entry);
+
+		jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL);
+		if (!jlm)
+			return -ENOMEM;
+
+		jlm->mod = mod;
+		jlm->entries = iter;
+		jlm->next = key->next;
+		key->next = jlm;
+
+		if (jump_label_enabled(key))
+			__jump_label_update(key, iter, JUMP_LABEL_ENABLE);
 	}
+
 	return 0;
 }
 
-static void remove_jump_label_module(struct module *mod)
+static void jump_label_del_module(struct module *mod)
 {
-	struct hlist_head *head;
-	struct hlist_node *node, *node_next, *module_node, *module_node_next;
-	struct jump_label_entry *e;
-	struct jump_label_module_entry *e_module;
-	int i;
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
+	struct jump_entry *iter;
+	struct jump_label_key *key = NULL;
+	struct jump_label_mod *jlm, **prev;
 
-	/* if the module doesn't have jump label entries, just return */
-	if (!mod->num_jump_entries)
-		return;
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		if (iter->key == (jump_label_t)(unsigned long)key)
+			continue;
+
+		key = (struct jump_label_key *)(unsigned long)iter->key;
+
+		if (__module_address(iter->key) == mod)
+			continue;
+
+		prev = &key->next;
+		jlm = key->next;
 
-	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
-		head = &jump_label_table[i];
-		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
-			hlist_for_each_entry_safe(e_module, module_node,
-						  module_node_next,
-						  &(e->modules), hlist) {
-				if (e_module->mod == mod) {
-					hlist_del(&e_module->hlist);
-					kfree(e_module);
-				}
-			}
-			if (hlist_empty(&e->modules) && (e->nr_entries == 0)) {
-				hlist_del(&e->hlist);
-				kfree(e);
-			}
+		while (jlm && jlm->mod != mod) {
+			prev = &jlm->next;
+			jlm = jlm->next;
+		}
+
+		if (jlm) {
+			*prev = jlm->next;
+			kfree(jlm);
 		}
 	}
 }
 
-static void remove_jump_label_module_init(struct module *mod)
+static void jump_label_invalidate_module_init(struct module *mod)
 {
-	struct hlist_head *head;
-	struct hlist_node *node, *node_next, *module_node, *module_node_next;
-	struct jump_label_entry *e;
-	struct jump_label_module_entry *e_module;
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
 	struct jump_entry *iter;
-	int i, count;
-
-	/* if the module doesn't have jump label entries, just return */
-	if (!mod->num_jump_entries)
-		return;
 
-	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
-		head = &jump_label_table[i];
-		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
-			hlist_for_each_entry_safe(e_module, module_node,
-						  module_node_next,
-						  &(e->modules), hlist) {
-				if (e_module->mod != mod)
-					continue;
-				count = e_module->nr_entries;
-				iter = e_module->table;
-				while (count--) {
-					if (within_module_init(iter->code, mod))
-						iter->key = 0;
-					iter++;
-				}
-			}
-		}
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		if (within_module_init(iter->code, mod))
+			iter->code = 0;
 	}
 }
 
@@ -426,59 +305,77 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	switch (val) {
 	case MODULE_STATE_COMING:
 		jump_label_lock();
-		ret = add_jump_label_module(mod);
+		ret = jump_label_add_module(mod);
 		if (ret)
-			remove_jump_label_module(mod);
+			jump_label_del_module(mod);
 		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
 		jump_label_lock();
-		remove_jump_label_module(mod);
+		jump_label_del_module(mod);
 		jump_label_unlock();
 		break;
 	case MODULE_STATE_LIVE:
 		jump_label_lock();
-		remove_jump_label_module_init(mod);
+		jump_label_invalidate_module_init(mod);
 		jump_label_unlock();
 		break;
 	}
-	return ret;
-}
 
-/***
- * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
- * @mod: module to patch
- *
- * Allow for run-time selection of the optimal nops. Before the module
- * loads patch these with arch_get_jump_label_nop(), which is specified by
- * the arch specific jump label code.
- */
-void jump_label_apply_nops(struct module *mod)
-{
-	struct jump_entry *iter;
-
-	/* if the module doesn't have jump label entries, just return */
-	if (!mod->num_jump_entries)
-		return;
-
-	iter = mod->jump_entries;
-	while (iter < mod->jump_entries + mod->num_jump_entries) {
-		arch_jump_label_text_poke_early(iter->code);
-		iter++;
-	}
+	return notifier_from_errno(ret);
 }
 
 struct notifier_block jump_label_module_nb = {
 	.notifier_call = jump_label_module_notify,
-	.priority = 0,
+	.priority = 1, /* higher than tracepoints */
 };
 
-static __init int init_jump_label_module(void)
+static __init int jump_label_init_module(void)
 {
 	return register_module_notifier(&jump_label_module_nb);
 }
-early_initcall(init_jump_label_module);
+early_initcall(jump_label_init_module);
 
 #endif /* CONFIG_MODULES */
 
+/***
+ * jump_label_text_reserved - check if addr range is reserved
+ * @start: start text addr
+ * @end: end text addr
+ *
+ * checks if the text addr located between @start and @end
+ * overlaps with any of the jump label patch addresses. Code
+ * that wants to modify kernel text should first verify that
+ * it does not overlap with any of the jump label addresses.
+ * Caller must hold jump_label_mutex.
+ *
+ * returns 1 if there is an overlap, 0 otherwise
+ */
+int jump_label_text_reserved(void *start, void *end)
+{
+	int ret = __jump_label_text_reserved(__start___jump_table,
+			__stop___jump_table, start, end);
+
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_MODULES
+	ret = __jump_label_mod_text_reserved(start, end);
+#endif
+	return ret;
+}
+
+static void jump_label_update(struct jump_label_key *key, int enable)
+{
+	struct jump_entry *entry = key->entries;
+
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, enable);
+
+#ifdef CONFIG_MODULES
+	__jump_label_mod_update(key, enable);
+#endif
+}
+
 #endif
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 87b77de03dd..8d814cbc810 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1531,13 +1531,7 @@ int kernel_kexec(void)
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
-		/* Suspend system devices */
-		error = sysdev_suspend(PMSG_FREEZE);
-		if (!error) {
-			error = syscore_suspend();
-			if (error)
-				sysdev_resume();
-		}
+		error = syscore_suspend();
 		if (error)
 			goto Enable_irqs;
 	} else
@@ -1553,7 +1547,6 @@ int kernel_kexec(void)
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
 		syscore_resume();
-		sysdev_resume();
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9cd0591c96a..5ae0ff38425 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -245,7 +245,6 @@ static void __call_usermodehelper(struct work_struct *work)
 	}
 }
 
-#ifdef CONFIG_PM_SLEEP
 /*
  * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
  * (used for preventing user land processes from being created after the user
@@ -301,6 +300,15 @@ void usermodehelper_enable(void)
 	usermodehelper_disabled = 0;
 }
 
+/**
+ * usermodehelper_is_disabled - check if new helpers are allowed to be started
+ */
+bool usermodehelper_is_disabled(void)
+{
+	return usermodehelper_disabled;
+}
+EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
+
 static void helper_lock(void)
 {
 	atomic_inc(&running_helpers);
@@ -312,12 +320,6 @@ static void helper_unlock(void)
 	if (atomic_dec_and_test(&running_helpers))
 		wake_up(&running_helpers_waitq);
 }
-#else /* CONFIG_PM_SLEEP */
-#define usermodehelper_disabled	0
-
-static inline void helper_lock(void) {}
-static inline void helper_unlock(void) {}
-#endif /* CONFIG_PM_SLEEP */
 
 /**
  * call_usermodehelper_setup - prepare to call a usermode helper
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 0b624e79180..3b053c04dd8 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -16,6 +16,7 @@
 #include <linux/kexec.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/capability.h>
 
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
@@ -131,6 +132,14 @@ KERNEL_ATTR_RO(vmcoreinfo);
 
 #endif /* CONFIG_KEXEC */
 
+/* whether file capabilities are enabled */
+static ssize_t fscaps_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", file_caps_enabled);
+}
+KERNEL_ATTR_RO(fscaps);
+
 /*
  * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
  */
@@ -158,6 +167,7 @@ struct kobject *kernel_kobj;
 EXPORT_SYMBOL_GPL(kernel_kobj);
 
 static struct attribute * kernel_attrs[] = {
+	&fscaps_attr.attr,
 #if defined(CONFIG_HOTPLUG)
 	&uevent_seqnum_attr.attr,
 	&uevent_helper_attr.attr,
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 53a68956f13..63437d065ac 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -490,6 +490,18 @@ void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS])
 	usage[i] = '\0';
 }
 
+static int __print_lock_name(struct lock_class *class)
+{
+	char str[KSYM_NAME_LEN];
+	const char *name;
+
+	name = class->name;
+	if (!name)
+		name = __get_key_name(class->key, str);
+
+	return printk("%s", name);
+}
+
 static void print_lock_name(struct lock_class *class)
 {
 	char str[KSYM_NAME_LEN], usage[LOCK_USAGE_CHARS];
@@ -1053,6 +1065,56 @@ print_circular_bug_entry(struct lock_list *target, int depth)
 	return 0;
 }
 
+static void
+print_circular_lock_scenario(struct held_lock *src,
+			     struct held_lock *tgt,
+			     struct lock_list *prt)
+{
+	struct lock_class *source = hlock_class(src);
+	struct lock_class *target = hlock_class(tgt);
+	struct lock_class *parent = prt->class;
+
+	/*
+	 * A direct locking problem where unsafe_class lock is taken
+	 * directly by safe_class lock, then all we need to show
+	 * is the deadlock scenario, as it is obvious that the
+	 * unsafe lock is taken under the safe lock.
+	 *
+	 * But if there is a chain instead, where the safe lock takes
+	 * an intermediate lock (middle_class) where this lock is
+	 * not the same as the safe lock, then the lock chain is
+	 * used to describe the problem. Otherwise we would need
+	 * to show a different CPU case for each link in the chain
+	 * from the safe_class lock to the unsafe_class lock.
+	 */
+	if (parent != source) {
+		printk("Chain exists of:\n  ");
+		__print_lock_name(source);
+		printk(" --> ");
+		__print_lock_name(parent);
+		printk(" --> ");
+		__print_lock_name(target);
+		printk("\n\n");
+	}
+
+	printk(" Possible unsafe locking scenario:\n\n");
+	printk("       CPU0                    CPU1\n");
+	printk("       ----                    ----\n");
+	printk("  lock(");
+	__print_lock_name(target);
+	printk(");\n");
+	printk("                               lock(");
+	__print_lock_name(parent);
+	printk(");\n");
+	printk("                               lock(");
+	__print_lock_name(target);
+	printk(");\n");
+	printk("  lock(");
+	__print_lock_name(source);
+	printk(");\n");
+	printk("\n *** DEADLOCK ***\n\n");
+}
+
 /*
  * When a circular dependency is detected, print the
  * header first:
@@ -1096,6 +1158,7 @@ static noinline int print_circular_bug(struct lock_list *this,
 {
 	struct task_struct *curr = current;
 	struct lock_list *parent;
+	struct lock_list *first_parent;
 	int depth;
 
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
@@ -1109,6 +1172,7 @@ static noinline int print_circular_bug(struct lock_list *this,
 	print_circular_bug_header(target, depth, check_src, check_tgt);
 
 	parent = get_lock_parent(target);
+	first_parent = parent;
 
 	while (parent) {
 		print_circular_bug_entry(parent, --depth);
@@ -1116,6 +1180,9 @@ static noinline int print_circular_bug(struct lock_list *this,
 	}
 
 	printk("\nother info that might help us debug this:\n\n");
+	print_circular_lock_scenario(check_src, check_tgt,
+				     first_parent);
+
 	lockdep_print_held_locks(curr);
 
 	printk("\nstack backtrace:\n");
@@ -1314,7 +1381,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf,
 		printk("\n");
 
 		if (depth == 0 && (entry != root)) {
-			printk("lockdep:%s bad BFS generated tree\n", __func__);
+			printk("lockdep:%s bad path found in chain graph\n", __func__);
 			break;
 		}
 
@@ -1325,6 +1392,62 @@ print_shortest_lock_dependencies(struct lock_list *leaf,
 	return;
 }
 
+static void
+print_irq_lock_scenario(struct lock_list *safe_entry,
+			struct lock_list *unsafe_entry,
+			struct lock_class *prev_class,
+			struct lock_class *next_class)
+{
+	struct lock_class *safe_class = safe_entry->class;
+	struct lock_class *unsafe_class = unsafe_entry->class;
+	struct lock_class *middle_class = prev_class;
+
+	if (middle_class == safe_class)
+		middle_class = next_class;
+
+	/*
+	 * A direct locking problem where unsafe_class lock is taken
+	 * directly by safe_class lock, then all we need to show
+	 * is the deadlock scenario, as it is obvious that the
+	 * unsafe lock is taken under the safe lock.
+	 *
+	 * But if there is a chain instead, where the safe lock takes
+	 * an intermediate lock (middle_class) where this lock is
+	 * not the same as the safe lock, then the lock chain is
+	 * used to describe the problem. Otherwise we would need
+	 * to show a different CPU case for each link in the chain
+	 * from the safe_class lock to the unsafe_class lock.
+	 */
+	if (middle_class != unsafe_class) {
+		printk("Chain exists of:\n  ");
+		__print_lock_name(safe_class);
+		printk(" --> ");
+		__print_lock_name(middle_class);
+		printk(" --> ");
+		__print_lock_name(unsafe_class);
+		printk("\n\n");
+	}
+
+	printk(" Possible interrupt unsafe locking scenario:\n\n");
+	printk("       CPU0                    CPU1\n");
+	printk("       ----                    ----\n");
+	printk("  lock(");
+	__print_lock_name(unsafe_class);
+	printk(");\n");
+	printk("                               local_irq_disable();\n");
+	printk("                               lock(");
+	__print_lock_name(safe_class);
+	printk(");\n");
+	printk("                               lock(");
+	__print_lock_name(middle_class);
+	printk(");\n");
+	printk("  <Interrupt>\n");
+	printk("    lock(");
+	__print_lock_name(safe_class);
+	printk(");\n");
+	printk("\n *** DEADLOCK ***\n\n");
+}
+
 static int
 print_bad_irq_dependency(struct task_struct *curr,
 			 struct lock_list *prev_root,
@@ -1376,6 +1499,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
 
 	printk("\nother info that might help us debug this:\n\n");
+	print_irq_lock_scenario(backwards_entry, forwards_entry,
+				hlock_class(prev), hlock_class(next));
+
 	lockdep_print_held_locks(curr);
 
 	printk("\nthe dependencies between %s-irq-safe lock", irqclass);
@@ -1539,6 +1665,26 @@ static inline void inc_chains(void)
 
 #endif
 
+static void
+print_deadlock_scenario(struct held_lock *nxt,
+			     struct held_lock *prv)
+{
+	struct lock_class *next = hlock_class(nxt);
+	struct lock_class *prev = hlock_class(prv);
+
+	printk(" Possible unsafe locking scenario:\n\n");
+	printk("       CPU0\n");
+	printk("       ----\n");
+	printk("  lock(");
+	__print_lock_name(prev);
+	printk(");\n");
+	printk("  lock(");
+	__print_lock_name(next);
+	printk(");\n");
+	printk("\n *** DEADLOCK ***\n\n");
+	printk(" May be due to missing lock nesting notation\n\n");
+}
+
 static int
 print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 		   struct held_lock *next)
@@ -1557,6 +1703,7 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 	print_lock(prev);
 
 	printk("\nother info that might help us debug this:\n");
+	print_deadlock_scenario(next, prev);
 	lockdep_print_held_locks(curr);
 
 	printk("\nstack backtrace:\n");
@@ -1826,7 +1973,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	struct list_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
 	struct held_lock *hlock_curr, *hlock_next;
-	int i, j, n, cn;
+	int i, j;
 
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return 0;
@@ -1886,15 +2033,9 @@ cache_hit:
 	}
 	i++;
 	chain->depth = curr->lockdep_depth + 1 - i;
-	cn = nr_chain_hlocks;
-	while (cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS) {
-		n = cmpxchg(&nr_chain_hlocks, cn, cn + chain->depth);
-		if (n == cn)
-			break;
-		cn = n;
-	}
-	if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
-		chain->base = cn;
+	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
+		chain->base = nr_chain_hlocks;
+		nr_chain_hlocks += chain->depth;
 		for (j = 0; j < chain->depth - 1; j++, i++) {
 			int lock_id = curr->held_locks[i].class_idx - 1;
 			chain_hlocks[chain->base + j] = lock_id;
@@ -2011,6 +2152,24 @@ static void check_chain_key(struct task_struct *curr)
 #endif
 }
 
+static void
+print_usage_bug_scenario(struct held_lock *lock)
+{
+	struct lock_class *class = hlock_class(lock);
+
+	printk(" Possible unsafe locking scenario:\n\n");
+	printk("       CPU0\n");
+	printk("       ----\n");
+	printk("  lock(");
+	__print_lock_name(class);
+	printk(");\n");
+	printk("  <Interrupt>\n");
+	printk("    lock(");
+	__print_lock_name(class);
+	printk(");\n");
+	printk("\n *** DEADLOCK ***\n\n");
+}
+
 static int
 print_usage_bug(struct task_struct *curr, struct held_lock *this,
 		enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit)
@@ -2039,6 +2198,8 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	print_irqtrace_events(curr);
 	printk("\nother info that might help us debug this:\n");
+	print_usage_bug_scenario(this);
+
 	lockdep_print_held_locks(curr);
 
 	printk("\nstack backtrace:\n");
@@ -2073,6 +2234,10 @@ print_irq_inversion_bug(struct task_struct *curr,
 			struct held_lock *this, int forwards,
 			const char *irqclass)
 {
+	struct lock_list *entry = other;
+	struct lock_list *middle = NULL;
+	int depth;
+
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
 		return 0;
 
@@ -2091,6 +2256,25 @@ print_irq_inversion_bug(struct task_struct *curr,
 	printk("\n\nand interrupts could create inverse lock ordering between them.\n\n");
 
 	printk("\nother info that might help us debug this:\n");
+
+	/* Find a middle lock (if one exists) */
+	depth = get_lock_depth(other);
+	do {
+		if (depth == 0 && (entry != root)) {
+			printk("lockdep:%s bad path found in chain graph\n", __func__);
+			break;
+		}
+		middle = entry;
+		entry = get_lock_parent(entry);
+		depth--;
+	} while (entry && entry != root && (depth >= 0));
+	if (forwards)
+		print_irq_lock_scenario(root, other,
+			middle ? middle->class : root->class, other->class);
+	else
+		print_irq_lock_scenario(other, root,
+			middle ? middle->class : other->class, root->class);
+
 	lockdep_print_held_locks(curr);
 
 	printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n");
diff --git a/kernel/module.c b/kernel/module.c
index d5938a5c19c..22879725678 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -57,6 +57,7 @@
 #include <linux/kmemleak.h>
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
+#include <linux/bsearch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
@@ -240,23 +241,24 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 				   struct module *owner,
 				   bool (*fn)(const struct symsearch *syms,
 					      struct module *owner,
-					      unsigned int symnum, void *data),
+					      void *data),
 				   void *data)
 {
-	unsigned int i, j;
+	unsigned int j;
 
 	for (j = 0; j < arrsize; j++) {
-		for (i = 0; i < arr[j].stop - arr[j].start; i++)
-			if (fn(&arr[j], owner, i, data))
-				return true;
+		if (fn(&arr[j], owner, data))
+			return true;
 	}
 
 	return false;
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
-			    unsigned int symnum, void *data), void *data)
+bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
+				    struct module *owner,
+				    void *data),
+			 void *data)
 {
 	struct module *mod;
 	static const struct symsearch arr[] = {
@@ -309,7 +311,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(each_symbol);
+EXPORT_SYMBOL_GPL(each_symbol_section);
 
 struct find_symbol_arg {
 	/* Input */
@@ -323,15 +325,12 @@ struct find_symbol_arg {
 	const struct kernel_symbol *sym;
 };
 
-static bool find_symbol_in_section(const struct symsearch *syms,
-				   struct module *owner,
-				   unsigned int symnum, void *data)
+static bool check_symbol(const struct symsearch *syms,
+				 struct module *owner,
+				 unsigned int symnum, void *data)
 {
 	struct find_symbol_arg *fsa = data;
 
-	if (strcmp(syms->start[symnum].name, fsa->name) != 0)
-		return false;
-
 	if (!fsa->gplok) {
 		if (syms->licence == GPL_ONLY)
 			return false;
@@ -365,6 +364,30 @@ static bool find_symbol_in_section(const struct symsearch *syms,
 	return true;
 }
 
+static int cmp_name(const void *va, const void *vb)
+{
+	const char *a;
+	const struct kernel_symbol *b;
+	a = va; b = vb;
+	return strcmp(a, b->name);
+}
+
+static bool find_symbol_in_section(const struct symsearch *syms,
+				   struct module *owner,
+				   void *data)
+{
+	struct find_symbol_arg *fsa = data;
+	struct kernel_symbol *sym;
+
+	sym = bsearch(fsa->name, syms->start, syms->stop - syms->start,
+			sizeof(struct kernel_symbol), cmp_name);
+
+	if (sym != NULL && check_symbol(syms, owner, sym - syms->start, data))
+		return true;
+
+	return false;
+}
+
 /* Find a symbol and return it, along with, (optional) crc and
  * (optional) module which owns it.  Needs preempt disabled or module_mutex. */
 const struct kernel_symbol *find_symbol(const char *name,
@@ -379,7 +402,7 @@ const struct kernel_symbol *find_symbol(const char *name,
 	fsa.gplok = gplok;
 	fsa.warn = warn;
 
-	if (each_symbol(find_symbol_in_section, &fsa)) {
+	if (each_symbol_section(find_symbol_in_section, &fsa)) {
 		if (owner)
 			*owner = fsa.owner;
 		if (crc)
@@ -1607,27 +1630,28 @@ static void set_section_ro_nx(void *base,
 	}
 }
 
-/* Setting memory back to RW+NX before releasing it */
-void unset_section_ro_nx(struct module *mod, void *module_region)
+static void unset_module_core_ro_nx(struct module *mod)
 {
-	unsigned long total_pages;
-
-	if (mod->module_core == module_region) {
-		/* Set core as NX+RW */
-		total_pages = MOD_NUMBER_OF_PAGES(mod->module_core, mod->core_size);
-		set_memory_nx((unsigned long)mod->module_core, total_pages);
-		set_memory_rw((unsigned long)mod->module_core, total_pages);
+	set_page_attributes(mod->module_core + mod->core_text_size,
+		mod->module_core + mod->core_size,
+		set_memory_x);
+	set_page_attributes(mod->module_core,
+		mod->module_core + mod->core_ro_size,
+		set_memory_rw);
+}
 
-	} else if (mod->module_init == module_region) {
-		/* Set init as NX+RW */
-		total_pages = MOD_NUMBER_OF_PAGES(mod->module_init, mod->init_size);
-		set_memory_nx((unsigned long)mod->module_init, total_pages);
-		set_memory_rw((unsigned long)mod->module_init, total_pages);
-	}
+static void unset_module_init_ro_nx(struct module *mod)
+{
+	set_page_attributes(mod->module_init + mod->init_text_size,
+		mod->module_init + mod->init_size,
+		set_memory_x);
+	set_page_attributes(mod->module_init,
+		mod->module_init + mod->init_ro_size,
+		set_memory_rw);
 }
 
 /* Iterate through all modules and set each module's text as RW */
-void set_all_modules_text_rw()
+void set_all_modules_text_rw(void)
 {
 	struct module *mod;
 
@@ -1648,7 +1672,7 @@ void set_all_modules_text_rw()
 }
 
 /* Iterate through all modules and set each module's text as RO */
-void set_all_modules_text_ro()
+void set_all_modules_text_ro(void)
 {
 	struct module *mod;
 
@@ -1669,7 +1693,8 @@ void set_all_modules_text_ro()
 }
 #else
 static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { }
-static inline void unset_section_ro_nx(struct module *mod, void *module_region) { }
+static void unset_module_core_ro_nx(struct module *mod) { }
+static void unset_module_init_ro_nx(struct module *mod) { }
 #endif
 
 /* Free a module, remove from lists, etc. */
@@ -1696,7 +1721,7 @@ static void free_module(struct module *mod)
 	destroy_params(mod->kp, mod->num_kp);
 
 	/* This may be NULL, but that's OK */
-	unset_section_ro_nx(mod, mod->module_init);
+	unset_module_init_ro_nx(mod);
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
 	percpu_modfree(mod);
@@ -1705,7 +1730,7 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
 	/* Finally, free the core (containing the module structure) */
-	unset_section_ro_nx(mod, mod->module_core);
+	unset_module_core_ro_nx(mod);
 	module_free(mod, mod->module_core);
 
 #ifdef CONFIG_MPU
@@ -2030,11 +2055,8 @@ static const struct kernel_symbol *lookup_symbol(const char *name,
 	const struct kernel_symbol *start,
 	const struct kernel_symbol *stop)
 {
-	const struct kernel_symbol *ks = start;
-	for (; ks < stop; ks++)
-		if (strcmp(ks->name, name) == 0)
-			return ks;
-	return NULL;
+	return bsearch(name, start, stop - start,
+			sizeof(struct kernel_symbol), cmp_name);
 }
 
 static int is_exported(const char *name, unsigned long value,
@@ -2931,10 +2953,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	mod->symtab = mod->core_symtab;
 	mod->strtab = mod->core_strtab;
 #endif
-	unset_section_ro_nx(mod, mod->module_init);
+	unset_module_init_ro_nx(mod);
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
+	mod->init_ro_size = 0;
 	mod->init_text_size = 0;
 	mutex_unlock(&module_mutex);
 
diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c
index ec815a960b5..73da83aff41 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/mutex-debug.c
@@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info());
+	DEBUG_LOCKS_WARN_ON(lock->owner != current);
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }
diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h
index 57d527a16f9..0799fd3e4cf 100644
--- a/kernel/mutex-debug.h
+++ b/kernel/mutex-debug.h
@@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current_thread_info();
+	lock->owner = current;
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)
diff --git a/kernel/mutex.c b/kernel/mutex.c
index c4195fa9890..2c938e2337c 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -160,14 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 */
 
 	for (;;) {
-		struct thread_info *owner;
-
-		/*
-		 * If we own the BKL, then don't spin. The owner of
-		 * the mutex might be waiting on us to release the BKL.
-		 */
-		if (unlikely(current->lock_depth >= 0))
-			break;
+		struct task_struct *owner;
 
 		/*
 		 * If there's an owner, wait for it to either
diff --git a/kernel/mutex.h b/kernel/mutex.h
index 67578ca48f9..4115fbf83b1 100644
--- a/kernel/mutex.h
+++ b/kernel/mutex.h
@@ -19,7 +19,7 @@
 #ifdef CONFIG_SMP
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current_thread_info();
+	lock->owner = current;
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)
diff --git a/kernel/params.c b/kernel/params.c
index 7ab388a48a2..ed72e133086 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -297,21 +297,15 @@ EXPORT_SYMBOL(param_ops_charp);
 int param_set_bool(const char *val, const struct kernel_param *kp)
 {
 	bool v;
+	int ret;
 
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
 	/* One of =[yYnN01] */
-	switch (val[0]) {
-	case 'y': case 'Y': case '1':
-		v = true;
-		break;
-	case 'n': case 'N': case '0':
-		v = false;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = strtobool(val, &v);
+	if (ret)
+		return ret;
 
 	if (kp->flags & KPARAM_ISBOOL)
 		*(bool *)kp->arg = v;
@@ -821,15 +815,18 @@ ssize_t __modver_version_show(struct module_attribute *mattr,
 	return sprintf(buf, "%s\n", vattr->version);
 }
 
-extern struct module_version_attribute __start___modver[], __stop___modver[];
+extern const struct module_version_attribute *__start___modver[];
+extern const struct module_version_attribute *__stop___modver[];
 
 static void __init version_sysfs_builtin(void)
 {
-	const struct module_version_attribute *vattr;
+	const struct module_version_attribute **p;
 	struct module_kobject *mk;
 	int err;
 
-	for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
+	for (p = __start___modver; p < __stop___modver; p++) {
+		const struct module_version_attribute *vattr = *p;
+
 		mk = locate_module_kobject(vattr->module_name);
 		if (mk) {
 			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 6de9a8fc341..87f4d24b55b 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -125,12 +125,6 @@ config PM_DEBUG
 	code. This is helpful when debugging and reporting PM bugs, like
 	suspend support.
 
-config PM_VERBOSE
-	bool "Verbose Power Management debugging"
-	depends on PM_DEBUG
-	---help---
-	This option enables verbose messages from the Power Management code.
-
 config PM_ADVANCED_DEBUG
 	bool "Extra PM attributes in sysfs for low-level debugging/testing"
 	depends on PM_DEBUG
@@ -229,3 +223,7 @@ config PM_OPP
 	  representing individual voltage domains and provides SOC
 	  implementations a ready to use framework to manage OPPs.
 	  For more information, read <file:Documentation/power/opp.txt>
+
+config PM_RUNTIME_CLK
+	def_bool y
+	depends on PM_RUNTIME && HAVE_CLK
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 50aae660174..f9bec56d882 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -272,12 +272,7 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_FREEZE);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -302,7 +297,6 @@ static int create_image(int platform_mode)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
@@ -333,20 +327,25 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
+	pm_message_t msg = PMSG_RECOVER;
 	int error;
 
 	error = platform_begin(platform_mode);
 	if (error)
 		goto Close;
 
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
+		goto Complete_devices;
+
 	/* Preallocate image memory before shutting down devices. */
 	error = hibernate_preallocate_memory();
 	if (error)
-		goto Close;
+		goto Complete_devices;
 
 	suspend_console();
 	pm_restrict_gfp_mask();
-	error = dpm_suspend_start(PMSG_FREEZE);
+	error = dpm_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
 
@@ -364,13 +363,17 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		swsusp_free();
 
-	dpm_resume_end(in_suspend ?
-		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE;
+	dpm_resume(msg);
 
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
 	resume_console();
+
+ Complete_devices:
+	dpm_complete(msg);
+
  Close:
 	platform_end(platform_mode);
 	return error;
@@ -409,12 +412,7 @@ static int resume_target_kernel(bool platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_QUIESCE);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (error)
 		goto Enable_irqs;
 
@@ -442,7 +440,6 @@ static int resume_target_kernel(bool platform_mode)
 	touch_softlockup_watchdog();
 
 	syscore_resume();
-	sysdev_resume();
 
  Enable_irqs:
 	local_irq_enable();
@@ -528,7 +525,6 @@ int hibernation_platform_enter(void)
 		goto Platform_finish;
 
 	local_irq_disable();
-	sysdev_suspend(PMSG_HIBERNATE);
 	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
@@ -541,7 +537,6 @@ int hibernation_platform_enter(void)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	local_irq_enable();
 	enable_nonboot_cpus();
 
@@ -982,10 +977,33 @@ static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *att
 
 power_attr(image_size);
 
+static ssize_t reserved_size_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lu\n", reserved_size);
+}
+
+static ssize_t reserved_size_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned long size;
+
+	if (sscanf(buf, "%lu", &size) == 1) {
+		reserved_size = size;
+		return n;
+	}
+
+	return -EINVAL;
+}
+
+power_attr(reserved_size);
+
 static struct attribute * g[] = {
 	&disk_attr.attr,
 	&resume_attr.attr,
 	&image_size_attr.attr,
+	&reserved_size_attr.attr,
 	NULL,
 };
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index de9aef8742f..2981af4ce7c 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -337,6 +337,7 @@ static int __init pm_init(void)
 	if (error)
 		return error;
 	hibernate_image_size_init();
+	hibernate_reserved_size_init();
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 03634be55f6..9a00a0a2628 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -15,6 +15,7 @@ struct swsusp_info {
 
 #ifdef CONFIG_HIBERNATION
 /* kernel/power/snapshot.c */
+extern void __init hibernate_reserved_size_init(void);
 extern void __init hibernate_image_size_init(void);
 
 #ifdef CONFIG_ARCH_HIBERNATION_HEADER
@@ -55,6 +56,7 @@ extern int hibernation_platform_enter(void);
 
 #else /* !CONFIG_HIBERNATION */
 
+static inline void hibernate_reserved_size_init(void) {}
 static inline void hibernate_image_size_init(void) {}
 #endif /* !CONFIG_HIBERNATION */
 
@@ -72,6 +74,8 @@ static struct kobj_attribute _name##_attr = {	\
 
 /* Preferred image size in bytes (default 500 MB) */
 extern unsigned long image_size;
+/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */
+extern unsigned long reserved_size;
 extern int in_suspend;
 extern dev_t swsusp_resume_device;
 extern sector_t swsusp_resume_block;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ca0aacc2487..ace55889f70 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -41,16 +41,28 @@ static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
 
 /*
+ * Number of bytes to reserve for memory allocations made by device drivers
+ * from their ->freeze() and ->freeze_noirq() callbacks so that they don't
+ * cause image creation to fail (tunable via /sys/power/reserved_size).
+ */
+unsigned long reserved_size;
+
+void __init hibernate_reserved_size_init(void)
+{
+	reserved_size = SPARE_PAGES * PAGE_SIZE;
+}
+
+/*
  * Preferred image size in bytes (tunable via /sys/power/image_size).
- * When it is set to N, the image creating code will do its best to
- * ensure the image size will not exceed N bytes, but if that is
- * impossible, it will try to create the smallest image possible.
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
  */
 unsigned long image_size;
 
 void __init hibernate_image_size_init(void)
 {
-	image_size = (totalram_pages / 3) * PAGE_SIZE;
+	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
 }
 
 /* List of PBEs needed for restoring the pages that were allocated before
@@ -1263,11 +1275,13 @@ static unsigned long minimum_image_size(unsigned long saveable)
  * frame in use.  We also need a number of page frames to be free during
  * hibernation for allocations made while saving the image and for device
  * drivers, in case they need to allocate memory from their hibernation
- * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
- * respectively, both of which are rough estimates).  To make this happen, we
- * compute the total number of available page frames and allocate at least
+ * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough
+ * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through
+ * /sys/power/reserved_size, respectively).  To make this happen, we compute the
+ * total number of available page frames and allocate at least
  *
- * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2
+ *  + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE)
  *
  * of them, which corresponds to the maximum size of a hibernation image.
  *
@@ -1322,7 +1336,8 @@ int hibernate_preallocate_memory(void)
 	count -= totalreserve_pages;
 
 	/* Compute the maximum number of saveable pages to leave in memory. */
-	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	max_size = (count - (size + PAGES_FOR_IO)) / 2
+			- 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE);
 	/* Compute the desired number of image pages specified by image_size. */
 	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
 	if (size > max_size)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6275970b218..1c41ba21541 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -163,19 +163,13 @@ static int suspend_enter(suspend_state_t state)
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
-	error = sysdev_suspend(PMSG_SUSPEND);
-	if (!error) {
-		error = syscore_suspend();
-		if (error)
-			sysdev_resume();
-	}
+	error = syscore_suspend();
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
 			events_check_enabled = false;
 		}
 		syscore_resume();
-		sysdev_resume();
 	}
 
 	arch_suspend_enable_irqs();
@@ -226,7 +220,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	suspend_enter(state);
+	error = suspend_enter(state);
 
  Resume_devices:
 	suspend_test_start();
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index f3240e98792..7784bd216b6 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -142,10 +142,17 @@ static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();
@@ -184,10 +191,17 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();
@@ -214,15 +228,17 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
-		 * Note that the machinery to reliably determine whether
-		 * or not we are in an RCU read-side critical section
-		 * exists only in the preemptible RCU implementations
-		 * (TINY_PREEMPT_RCU and TREE_PREEMPT_RCU), which is why
-		 * DEBUG_OBJECTS_RCU_HEAD is disallowed if !PREEMPT.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 0c343b9a46d..421abfd3641 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -40,10 +40,10 @@
 static struct task_struct *rcu_kthread_task;
 static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
 static unsigned long have_rcu_kthread_work;
-static void invoke_rcu_kthread(void);
 
 /* Forward declarations for rcutiny_plugin.h. */
 struct rcu_ctrlblk;
+static void invoke_rcu_kthread(void);
 static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
 static int rcu_kthread(void *arg);
 static void __call_rcu(struct rcu_head *head,
@@ -79,36 +79,45 @@ void rcu_exit_nohz(void)
 #endif /* #ifdef CONFIG_NO_HZ */
 
 /*
- * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
- * Also disable irqs to avoid confusion due to interrupt handlers
+ * Helper function for rcu_sched_qs() and rcu_bh_qs().
+ * Also irqs are disabled to avoid confusion due to interrupt handlers
  * invoking call_rcu().
  */
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	if (rcp->rcucblist != NULL &&
 	    rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
-		local_irq_restore(flags);
 		return 1;
 	}
-	local_irq_restore(flags);
 
 	return 0;
 }
 
 /*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+	have_rcu_kthread_work = 1;
+	wake_up(&rcu_kthread_wq);
+}
+
+/*
  * Record an rcu quiescent state.  And an rcu_bh quiescent state while we
  * are at it, given that any rcu quiescent state is also an rcu_bh
  * quiescent state.  Use "+" instead of "||" to defeat short circuiting.
  */
 void rcu_sched_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
 	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -116,8 +125,12 @@ void rcu_sched_qs(int cpu)
  */
 void rcu_bh_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -167,7 +180,7 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		prefetch(next);
 		debug_rcu_head_unqueue(list);
 		local_bh_disable();
-		list->func(list);
+		__rcu_reclaim(list);
 		local_bh_enable();
 		list = next;
 		RCU_TRACE(cb_count++);
@@ -208,20 +221,6 @@ static int rcu_kthread(void *arg)
 }
 
 /*
- * Wake up rcu_kthread() to process callbacks now eligible for invocation
- * or to boost readers.
- */
-static void invoke_rcu_kthread(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	have_rcu_kthread_work = 1;
-	wake_up(&rcu_kthread_wq);
-	local_irq_restore(flags);
-}
-
-/*
  * Wait for a grace period to elapse.  But it is illegal to invoke
  * synchronize_sched() from within an RCU read-side critical section.
  * Therefore, any legal call to synchronize_sched() is a quiescent
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 3cb8e362e88..f259c676195 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -100,23 +100,28 @@ struct rcu_preempt_ctrlblk {
 	u8 completed;		/* Last grace period completed. */
 				/*  If all three are equal, RCU is idle. */
 #ifdef CONFIG_RCU_BOOST
-	s8 boosted_this_gp;	/* Has boosting already happened? */
 	unsigned long boost_time; /* When to start boosting (jiffies) */
 #endif /* #ifdef CONFIG_RCU_BOOST */
 #ifdef CONFIG_RCU_TRACE
 	unsigned long n_grace_periods;
 #ifdef CONFIG_RCU_BOOST
 	unsigned long n_tasks_boosted;
+				/* Total number of tasks boosted. */
 	unsigned long n_exp_boosts;
+				/* Number of tasks boosted for expedited GP. */
 	unsigned long n_normal_boosts;
-	unsigned long n_normal_balk_blkd_tasks;
-	unsigned long n_normal_balk_gp_tasks;
-	unsigned long n_normal_balk_boost_tasks;
-	unsigned long n_normal_balk_boosted;
-	unsigned long n_normal_balk_notyet;
-	unsigned long n_normal_balk_nos;
-	unsigned long n_exp_balk_blkd_tasks;
-	unsigned long n_exp_balk_nos;
+				/* Number of tasks boosted for normal GP. */
+	unsigned long n_balk_blkd_tasks;
+				/* Refused to boost: no blocked tasks. */
+	unsigned long n_balk_exp_gp_tasks;
+				/* Refused to boost: nothing blocking GP. */
+	unsigned long n_balk_boost_tasks;
+				/* Refused to boost: already boosting. */
+	unsigned long n_balk_notyet;
+				/* Refused to boost: not yet time. */
+	unsigned long n_balk_nos;
+				/* Refused to boost: not sure why, though. */
+				/*  This can happen due to race conditions. */
 #endif /* #ifdef CONFIG_RCU_BOOST */
 #endif /* #ifdef CONFIG_RCU_TRACE */
 };
@@ -201,7 +206,6 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t)
 
 #ifdef CONFIG_RCU_BOOST
 static void rcu_initiate_boost_trace(void);
-static void rcu_initiate_exp_boost_trace(void);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 /*
@@ -219,41 +223,21 @@ static void show_tiny_preempt_stats(struct seq_file *m)
 		   "N."[!rcu_preempt_ctrlblk.gp_tasks],
 		   "E."[!rcu_preempt_ctrlblk.exp_tasks]);
 #ifdef CONFIG_RCU_BOOST
-	seq_printf(m, "             ttb=%c btg=",
-		   "B."[!rcu_preempt_ctrlblk.boost_tasks]);
-	switch (rcu_preempt_ctrlblk.boosted_this_gp) {
-	case -1:
-		seq_puts(m, "exp");
-		break;
-	case 0:
-		seq_puts(m, "no");
-		break;
-	case 1:
-		seq_puts(m, "begun");
-		break;
-	case 2:
-		seq_puts(m, "done");
-		break;
-	default:
-		seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp);
-	}
-	seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
+	seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
+		   "             ",
+		   "B."[!rcu_preempt_ctrlblk.boost_tasks],
 		   rcu_preempt_ctrlblk.n_tasks_boosted,
 		   rcu_preempt_ctrlblk.n_exp_boosts,
 		   rcu_preempt_ctrlblk.n_normal_boosts,
 		   (int)(jiffies & 0xffff),
 		   (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
-	seq_printf(m, "             %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n",
-		   "normal balk",
-		   rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks,
-		   rcu_preempt_ctrlblk.n_normal_balk_gp_tasks,
-		   rcu_preempt_ctrlblk.n_normal_balk_boost_tasks,
-		   rcu_preempt_ctrlblk.n_normal_balk_boosted,
-		   rcu_preempt_ctrlblk.n_normal_balk_notyet,
-		   rcu_preempt_ctrlblk.n_normal_balk_nos);
-	seq_printf(m, "             exp balk: bt=%lu nos=%lu\n",
-		   rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks,
-		   rcu_preempt_ctrlblk.n_exp_balk_nos);
+	seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n",
+		   "             balk",
+		   rcu_preempt_ctrlblk.n_balk_blkd_tasks,
+		   rcu_preempt_ctrlblk.n_balk_exp_gp_tasks,
+		   rcu_preempt_ctrlblk.n_balk_boost_tasks,
+		   rcu_preempt_ctrlblk.n_balk_notyet,
+		   rcu_preempt_ctrlblk.n_balk_nos);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 }
 
@@ -271,25 +255,59 @@ static int rcu_boost(void)
 {
 	unsigned long flags;
 	struct rt_mutex mtx;
-	struct list_head *np;
 	struct task_struct *t;
+	struct list_head *tb;
 
-	if (rcu_preempt_ctrlblk.boost_tasks == NULL)
+	if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
+	    rcu_preempt_ctrlblk.exp_tasks == NULL)
 		return 0;  /* Nothing to boost. */
+
 	raw_local_irq_save(flags);
-	rcu_preempt_ctrlblk.boosted_this_gp++;
-	t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct,
-			 rcu_node_entry);
-	np = rcu_next_node_entry(t);
+
+	/*
+	 * Recheck with irqs disabled: all tasks in need of boosting
+	 * might exit their RCU read-side critical sections on their own
+	 * if we are preempted just before disabling irqs.
+	 */
+	if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
+	    rcu_preempt_ctrlblk.exp_tasks == NULL) {
+		raw_local_irq_restore(flags);
+		return 0;
+	}
+
+	/*
+	 * Preferentially boost tasks blocking expedited grace periods.
+	 * This cannot starve the normal grace periods because a second
+	 * expedited grace period must boost all blocked tasks, including
+	 * those blocking the pre-existing normal grace period.
+	 */
+	if (rcu_preempt_ctrlblk.exp_tasks != NULL) {
+		tb = rcu_preempt_ctrlblk.exp_tasks;
+		RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
+	} else {
+		tb = rcu_preempt_ctrlblk.boost_tasks;
+		RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
+	}
+	RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
+
+	/*
+	 * We boost task t by manufacturing an rt_mutex that appears to
+	 * be held by task t.  We leave a pointer to that rt_mutex where
+	 * task t can find it, and task t will release the mutex when it
+	 * exits its outermost RCU read-side critical section.  Then
+	 * simply acquiring this artificial rt_mutex will boost task
+	 * t's priority.  (Thanks to tglx for suggesting this approach!)
+	 */
+	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
 	t->rcu_boost_mutex = &mtx;
 	t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
 	raw_local_irq_restore(flags);
 	rt_mutex_lock(&mtx);
-	RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
-	rcu_preempt_ctrlblk.boosted_this_gp++;
-	rt_mutex_unlock(&mtx);
-	return rcu_preempt_ctrlblk.boost_tasks != NULL;
+	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
+
+	return rcu_preempt_ctrlblk.boost_tasks != NULL ||
+	       rcu_preempt_ctrlblk.exp_tasks != NULL;
 }
 
 /*
@@ -304,42 +322,25 @@ static int rcu_boost(void)
  */
 static int rcu_initiate_boost(void)
 {
-	if (!rcu_preempt_blocked_readers_cgp()) {
-		RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++);
+	if (!rcu_preempt_blocked_readers_cgp() &&
+	    rcu_preempt_ctrlblk.exp_tasks == NULL) {
+		RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++);
 		return 0;
 	}
-	if (rcu_preempt_ctrlblk.gp_tasks != NULL &&
-	    rcu_preempt_ctrlblk.boost_tasks == NULL &&
-	    rcu_preempt_ctrlblk.boosted_this_gp == 0 &&
-	    ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) {
-		rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks;
+	if (rcu_preempt_ctrlblk.exp_tasks != NULL ||
+	    (rcu_preempt_ctrlblk.gp_tasks != NULL &&
+	     rcu_preempt_ctrlblk.boost_tasks == NULL &&
+	     ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) {
+		if (rcu_preempt_ctrlblk.exp_tasks == NULL)
+			rcu_preempt_ctrlblk.boost_tasks =
+				rcu_preempt_ctrlblk.gp_tasks;
 		invoke_rcu_kthread();
-		RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
 	} else
 		RCU_TRACE(rcu_initiate_boost_trace());
 	return 1;
 }
 
-/*
- * Initiate boosting for an expedited grace period.
- */
-static void rcu_initiate_expedited_boost(void)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) {
-		rcu_preempt_ctrlblk.boost_tasks =
-			rcu_preempt_ctrlblk.blkd_tasks.next;
-		rcu_preempt_ctrlblk.boosted_this_gp = -1;
-		invoke_rcu_kthread();
-		RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
-	} else
-		RCU_TRACE(rcu_initiate_exp_boost_trace());
-	raw_local_irq_restore(flags);
-}
-
-#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000);
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
 
 /*
  * Do priority-boost accounting for the start of a new grace period.
@@ -347,8 +348,6 @@ static void rcu_initiate_expedited_boost(void)
 static void rcu_preempt_boost_start_gp(void)
 {
 	rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
-	if (rcu_preempt_ctrlblk.boosted_this_gp > 0)
-		rcu_preempt_ctrlblk.boosted_this_gp = 0;
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
@@ -372,13 +371,6 @@ static int rcu_initiate_boost(void)
 }
 
 /*
- * If there is no RCU priority boosting, we don't initiate expedited boosting.
- */
-static void rcu_initiate_expedited_boost(void)
-{
-}
-
-/*
  * If there is no RCU priority boosting, nothing to do at grace-period start.
  */
 static void rcu_preempt_boost_start_gp(void)
@@ -418,7 +410,7 @@ static void rcu_preempt_cpu_qs(void)
 	if (!rcu_preempt_gp_in_progress())
 		return;
 	/*
-	 * Check up on boosting.  If there are no readers blocking the
+	 * Check up on boosting.  If there are readers blocking the
 	 * current grace period, leave.
 	 */
 	if (rcu_initiate_boost())
@@ -578,7 +570,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		empty = !rcu_preempt_blocked_readers_cgp();
 		empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
 		np = rcu_next_node_entry(t);
-		list_del(&t->rcu_node_entry);
+		list_del_init(&t->rcu_node_entry);
 		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
 			rcu_preempt_ctrlblk.gp_tasks = np;
 		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
@@ -587,7 +579,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
 			rcu_preempt_ctrlblk.boost_tasks = np;
 #endif /* #ifdef CONFIG_RCU_BOOST */
-		INIT_LIST_HEAD(&t->rcu_node_entry);
 
 		/*
 		 * If this was the last task on the current list, and if
@@ -812,13 +803,16 @@ void synchronize_rcu_expedited(void)
 	rpcp->exp_tasks = rpcp->blkd_tasks.next;
 	if (rpcp->exp_tasks == &rpcp->blkd_tasks)
 		rpcp->exp_tasks = NULL;
-	local_irq_restore(flags);
 
 	/* Wait for tail of ->blkd_tasks list to drain. */
-	if (rcu_preempted_readers_exp())
-		rcu_initiate_expedited_boost();
+	if (!rcu_preempted_readers_exp())
+		local_irq_restore(flags);
+	else {
+		rcu_initiate_boost();
+		local_irq_restore(flags);
 		wait_event(sync_rcu_preempt_exp_wq,
 			   !rcu_preempted_readers_exp());
+	}
 
 	/* Clean up and exit. */
 	barrier(); /* ensure expedited GP seen before counter increment. */
@@ -931,24 +925,17 @@ void __init rcu_scheduler_starting(void)
 
 static void rcu_initiate_boost_trace(void)
 {
-	if (rcu_preempt_ctrlblk.gp_tasks == NULL)
-		rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++;
+	if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
+		rcu_preempt_ctrlblk.n_balk_blkd_tasks++;
+	else if (rcu_preempt_ctrlblk.gp_tasks == NULL &&
+		 rcu_preempt_ctrlblk.exp_tasks == NULL)
+		rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++;
 	else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
-		rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++;
-	else if (rcu_preempt_ctrlblk.boosted_this_gp != 0)
-		rcu_preempt_ctrlblk.n_normal_balk_boosted++;
+		rcu_preempt_ctrlblk.n_balk_boost_tasks++;
 	else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
-		rcu_preempt_ctrlblk.n_normal_balk_notyet++;
-	else
-		rcu_preempt_ctrlblk.n_normal_balk_nos++;
-}
-
-static void rcu_initiate_exp_boost_trace(void)
-{
-	if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
-		rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++;
+		rcu_preempt_ctrlblk.n_balk_notyet++;
 	else
-		rcu_preempt_ctrlblk.n_exp_balk_nos++;
+		rcu_preempt_ctrlblk.n_balk_nos++;
 }
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index c224da41890..2e138db0338 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -131,7 +131,7 @@ struct rcu_torture {
 
 static LIST_HEAD(rcu_torture_freelist);
 static struct rcu_torture __rcu *rcu_torture_current;
-static long rcu_torture_current_version;
+static unsigned long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
 static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
@@ -146,8 +146,6 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
-static long n_rcu_torture_boost_allocerror;
-static long n_rcu_torture_boost_afferror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static long n_rcu_torture_timers;
@@ -163,11 +161,11 @@ static int stutter_pause_test;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
-#ifdef CONFIG_RCU_BOOST
+#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
-#else /* #ifdef CONFIG_RCU_BOOST */
+#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 #define rcu_can_boost() 0
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
+#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
@@ -751,6 +749,7 @@ static int rcu_torture_boost(void *arg)
 		n_rcu_torture_boost_rterror++;
 	}
 
+	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
 		/* Wait for the next test interval. */
@@ -810,6 +809,7 @@ checkwait:	rcu_stutter_wait("rcu_torture_boost");
 
 	/* Clean up and exit. */
 	VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
+	destroy_rcu_head_on_stack(&rbi.rcu);
 	rcutorture_shutdown_absorb("rcu_torture_boost");
 	while (!kthread_should_stop() || rbi.inflight)
 		schedule_timeout_uninterruptible(1);
@@ -886,7 +886,7 @@ rcu_torture_writer(void *arg)
 			old_rp->rtort_pipe_count++;
 			cur_ops->deferred_free(old_rp);
 		}
-		rcu_torture_current_version++;
+		rcutorture_record_progress(++rcu_torture_current_version);
 		oldbatch = cur_ops->completed();
 		rcu_stutter_wait("rcu_torture_writer");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
@@ -1066,8 +1066,8 @@ rcu_torture_printk(char *page)
 	}
 	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
 	cnt += sprintf(&page[cnt],
-		       "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
-		       "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld "
+		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
+		       "rtmbe: %d rtbke: %ld rtbre: %ld "
 		       "rtbf: %ld rtb: %ld nt: %ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
@@ -1078,16 +1078,12 @@ rcu_torture_printk(char *page)
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
 		       n_rcu_torture_boost_rterror,
-		       n_rcu_torture_boost_allocerror,
-		       n_rcu_torture_boost_afferror,
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
-	    n_rcu_torture_boost_allocerror != 0 ||
-	    n_rcu_torture_boost_afferror != 0 ||
 	    n_rcu_torture_boost_failure != 0)
 		cnt += sprintf(&page[cnt], " !!!");
 	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
@@ -1331,6 +1327,7 @@ rcu_torture_cleanup(void)
 	int i;
 
 	mutex_lock(&fullstop_mutex);
+	rcutorture_record_test_transition();
 	if (fullstop == FULLSTOP_SHUTDOWN) {
 		printk(KERN_WARNING /* but going down anyway, so... */
 		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
@@ -1486,8 +1483,6 @@ rcu_torture_init(void)
 	atomic_set(&n_rcu_torture_error, 0);
 	n_rcu_torture_boost_ktrerror = 0;
 	n_rcu_torture_boost_rterror = 0;
-	n_rcu_torture_boost_allocerror = 0;
-	n_rcu_torture_boost_afferror = 0;
 	n_rcu_torture_boost_failure = 0;
 	n_rcu_torture_boosts = 0;
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -1624,6 +1619,7 @@ rcu_torture_init(void)
 		}
 	}
 	register_reboot_notifier(&rcutorture_shutdown_nb);
+	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index dd4aea806f8..e486f7c3ffb 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -47,6 +47,8 @@
 #include <linux/mutex.h>
 #include <linux/time.h>
 #include <linux/kernel_stat.h>
+#include <linux/wait.h>
+#include <linux/kthread.h>
 
 #include "rcutree.h"
 
@@ -79,10 +81,41 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
+static struct rcu_state *rcu_state;
+
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
 /*
+ * Control variables for per-CPU and per-rcu_node kthreads.  These
+ * handle all flavors of RCU.
+ */
+static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
+static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
+DEFINE_PER_CPU(char, rcu_cpu_has_work);
+static char rcu_kthreads_spawnable;
+
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
+static void invoke_rcu_cpu_kthread(void);
+
+#define RCU_KTHREAD_PRIO 1	/* RT priority for per-CPU kthreads. */
+
+/*
+ * Track the rcutorture test sequence number and the update version
+ * number within a given test.  The rcutorture_testseq is incremented
+ * on every rcutorture module load and unload, so has an odd value
+ * when a test is running.  The rcutorture_vernum is set to zero
+ * when rcutorture starts and is incremented on each rcutorture update.
+ * These variables enable correlating rcutorture output with the
+ * RCU tracing information.
+ */
+unsigned long rcutorture_testseq;
+unsigned long rcutorture_vernum;
+
+/*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
  * structure's ->lock, but of course results can be subject to change.
@@ -124,6 +157,7 @@ void rcu_note_context_switch(int cpu)
 	rcu_sched_qs(cpu);
 	rcu_preempt_note_context_switch(cpu);
 }
+EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
@@ -140,10 +174,8 @@ module_param(blimit, int, 0);
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-int rcu_cpu_stall_suppress __read_mostly = RCU_CPU_STALL_SUPPRESS_INIT;
+int rcu_cpu_stall_suppress __read_mostly;
 module_param(rcu_cpu_stall_suppress, int, 0644);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
 static int rcu_pending(int cpu);
@@ -176,6 +208,31 @@ void rcu_bh_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
 /*
+ * Record the number of times rcutorture tests have been initiated and
+ * terminated.  This information allows the debugfs tracing stats to be
+ * correlated to the rcutorture messages, even when the rcutorture module
+ * is being repeatedly loaded and unloaded.  In other words, we cannot
+ * store this state in rcutorture itself.
+ */
+void rcutorture_record_test_transition(void)
+{
+	rcutorture_testseq++;
+	rcutorture_vernum = 0;
+}
+EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
+
+/*
+ * Record the number of writer passes through the current rcutorture test.
+ * This is also used to correlate debugfs tracing stats with the rcutorture
+ * messages.
+ */
+void rcutorture_record_progress(unsigned long vernum)
+{
+	rcutorture_vernum++;
+}
+EXPORT_SYMBOL_GPL(rcutorture_record_progress);
+
+/*
  * Force a quiescent state for RCU-sched.
  */
 void rcu_sched_force_quiescent_state(void)
@@ -234,8 +291,8 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 		return 1;
 	}
 
-	/* If preemptable RCU, no point in sending reschedule IPI. */
-	if (rdp->preemptable)
+	/* If preemptible RCU, no point in sending reschedule IPI. */
+	if (rdp->preemptible)
 		return 0;
 
 	/* The CPU is online, so send it a reschedule IPI. */
@@ -450,8 +507,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 int rcu_cpu_stall_suppress __read_mostly;
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -537,21 +592,24 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	long delta;
+	unsigned long j;
+	unsigned long js;
 	struct rcu_node *rnp;
 
 	if (rcu_cpu_stall_suppress)
 		return;
-	delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
+	j = ACCESS_ONCE(jiffies);
+	js = ACCESS_ONCE(rsp->jiffies_stall);
 	rnp = rdp->mynode;
-	if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && delta >= 0) {
+	if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
-	} else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) {
+	} else if (rcu_gp_in_progress(rsp) &&
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
 
-		/* They had two time units to dump stack, so complain. */
+		/* They had a few time units to dump stack, so complain. */
 		print_other_cpu_stall(rsp);
 	}
 }
@@ -587,26 +645,6 @@ static void __init check_cpu_stall_init(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
 }
 
-#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-static void record_gp_stall_check_time(struct rcu_state *rsp)
-{
-}
-
-static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-}
-
-void rcu_cpu_stall_reset(void)
-{
-}
-
-static void __init check_cpu_stall_init(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
  * Update CPU-local rcu_data state to record the newly noticed grace period.
  * This is used both when we started the grace period and when we notice
@@ -809,6 +847,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		rnp->completed = rsp->completed;
 		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
 		rcu_start_gp_per_cpu(rsp, rnp, rdp);
+		rcu_preempt_boost_start_gp(rnp);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
@@ -844,6 +883,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		rnp->completed = rsp->completed;
 		if (rnp == rdp->mynode)
 			rcu_start_gp_per_cpu(rsp, rnp, rdp);
+		rcu_preempt_boost_start_gp(rnp);
 		raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
@@ -864,7 +904,12 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
+	unsigned long gp_duration;
+
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+	gp_duration = jiffies - rsp->gp_start;
+	if (gp_duration > rsp->gp_max)
+		rsp->gp_max = gp_duration;
 	rsp->completed = rsp->gpnum;
 	rsp->signaled = RCU_GP_IDLE;
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
@@ -894,7 +939,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			return;
 		}
 		rnp->qsmask &= ~mask;
-		if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
+		if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
 
 			/* Other bits still set at this level, so done. */
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1037,6 +1082,8 @@ static void rcu_send_cbs_to_online(struct rcu_state *rsp)
 /*
  * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
  * and move all callbacks from the outgoing CPU to the current one.
+ * There can only be one CPU hotplug operation at a time, so no other
+ * CPU can be attempting to update rcu_cpu_kthread_task.
  */
 static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 {
@@ -1045,6 +1092,14 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	int need_report = 0;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp;
+	struct task_struct *t;
+
+	/* Stop the CPU's kthread. */
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t != NULL) {
+		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
+		kthread_stop(t);
+	}
 
 	/* Exclude any attempts to start a new grace period. */
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -1082,6 +1137,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (need_report & RCU_OFL_TASKS_EXP_GP)
 		rcu_report_exp_rnp(rsp, rnp);
+	rcu_node_kthread_setaffinity(rnp, -1);
 }
 
 /*
@@ -1143,7 +1199,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 		next = list->next;
 		prefetch(next);
 		debug_rcu_head_unqueue(list);
-		list->func(list);
+		__rcu_reclaim(list);
 		list = next;
 		if (++count >= rdp->blimit)
 			break;
@@ -1179,7 +1235,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Re-raise the RCU softirq if there are callbacks remaining. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
-		raise_softirq(RCU_SOFTIRQ);
+		invoke_rcu_cpu_kthread();
 }
 
 /*
@@ -1225,7 +1281,7 @@ void rcu_check_callbacks(int cpu, int user)
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
-		raise_softirq(RCU_SOFTIRQ);
+		invoke_rcu_cpu_kthread();
 }
 
 #ifdef CONFIG_SMP
@@ -1233,6 +1289,8 @@ void rcu_check_callbacks(int cpu, int user)
 /*
  * Scan the leaf rcu_node structures, processing dyntick state for any that
  * have not yet encountered a quiescent state, using the function specified.
+ * Also initiate boosting for any threads blocked on the root rcu_node.
+ *
  * The caller must have suppressed start of new grace periods.
  */
 static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
@@ -1251,7 +1309,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
 			return;
 		}
 		if (rnp->qsmask == 0) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			rcu_initiate_boost(rnp, flags); /* releases rnp->lock */
 			continue;
 		}
 		cpu = rnp->grplo;
@@ -1269,6 +1327,11 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
 		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
+	rnp = rcu_get_root(rsp);
+	if (rnp->qsmask == 0) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
+	}
 }
 
 /*
@@ -1389,7 +1452,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 /*
  * Do softirq processing for the current CPU.
  */
-static void rcu_process_callbacks(struct softirq_action *unused)
+static void rcu_process_callbacks(void)
 {
 	/*
 	 * Memory references from any prior RCU read-side critical sections
@@ -1414,6 +1477,347 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 	rcu_needs_cpu_flush();
 }
 
+/*
+ * Wake up the current CPU's kthread.  This replaces raise_softirq()
+ * in earlier versions of RCU.  Note that because we are running on
+ * the current CPU with interrupts disabled, the rcu_cpu_kthread_task
+ * cannot disappear out from under us.
+ */
+static void invoke_rcu_cpu_kthread(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__this_cpu_write(rcu_cpu_has_work, 1);
+	if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
+		local_irq_restore(flags);
+		return;
+	}
+	wake_up(&__get_cpu_var(rcu_cpu_wq));
+	local_irq_restore(flags);
+}
+
+/*
+ * Wake up the specified per-rcu_node-structure kthread.
+ * Because the per-rcu_node kthreads are immortal, we don't need
+ * to do anything to keep them alive.
+ */
+static void invoke_rcu_node_kthread(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+
+	t = rnp->node_kthread_task;
+	if (t != NULL)
+		wake_up_process(t);
+}
+
+/*
+ * Set the specified CPU's kthread to run RT or not, as specified by
+ * the to_rt argument.  The CPU-hotplug locks are held, so the task
+ * is not going away.
+ */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+	int policy;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t == NULL)
+		return;
+	if (to_rt) {
+		policy = SCHED_FIFO;
+		sp.sched_priority = RCU_KTHREAD_PRIO;
+	} else {
+		policy = SCHED_NORMAL;
+		sp.sched_priority = 0;
+	}
+	sched_setscheduler_nocheck(t, policy, &sp);
+}
+
+/*
+ * Timer handler to initiate the waking up of per-CPU kthreads that
+ * have yielded the CPU due to excess numbers of RCU callbacks.
+ * We wake up the per-rcu_node kthread, which in turn will wake up
+ * the booster kthread.
+ */
+static void rcu_cpu_kthread_timer(unsigned long arg)
+{
+	unsigned long flags;
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
+	struct rcu_node *rnp = rdp->mynode;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	rnp->wakemask |= rdp->grpmask;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	invoke_rcu_node_kthread(rnp);
+}
+
+/*
+ * Drop to non-real-time priority and yield, but only after posting a
+ * timer that will cause us to regain our real-time priority if we
+ * remain preempted.  Either way, we restore our real-time priority
+ * before returning.
+ */
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+{
+	struct sched_param sp;
+	struct timer_list yield_timer;
+
+	setup_timer_on_stack(&yield_timer, f, arg);
+	mod_timer(&yield_timer, jiffies + 2);
+	sp.sched_priority = 0;
+	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
+	set_user_nice(current, 19);
+	schedule();
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+	del_timer(&yield_timer);
+}
+
+/*
+ * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
+ * This can happen while the corresponding CPU is either coming online
+ * or going offline.  We cannot wait until the CPU is fully online
+ * before starting the kthread, because the various notifier functions
+ * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
+ * the corresponding CPU is online.
+ *
+ * Return 1 if the kthread needs to stop, 0 otherwise.
+ *
+ * Caller must disable bh.  This function can momentarily enable it.
+ */
+static int rcu_cpu_kthread_should_stop(int cpu)
+{
+	while (cpu_is_offline(cpu) ||
+	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
+	       smp_processor_id() != cpu) {
+		if (kthread_should_stop())
+			return 1;
+		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
+		local_bh_enable();
+		schedule_timeout_uninterruptible(1);
+		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
+			set_cpus_allowed_ptr(current, cpumask_of(cpu));
+		local_bh_disable();
+	}
+	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+	return 0;
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
+ * earlier RCU softirq.
+ */
+static int rcu_cpu_kthread(void *arg)
+{
+	int cpu = (int)(long)arg;
+	unsigned long flags;
+	int spincnt = 0;
+	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
+	wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
+	char work;
+	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+
+	for (;;) {
+		*statusp = RCU_KTHREAD_WAITING;
+		wait_event_interruptible(*wqp,
+					 *workp != 0 || kthread_should_stop());
+		local_bh_disable();
+		if (rcu_cpu_kthread_should_stop(cpu)) {
+			local_bh_enable();
+			break;
+		}
+		*statusp = RCU_KTHREAD_RUNNING;
+		per_cpu(rcu_cpu_kthread_loops, cpu)++;
+		local_irq_save(flags);
+		work = *workp;
+		*workp = 0;
+		local_irq_restore(flags);
+		if (work)
+			rcu_process_callbacks();
+		local_bh_enable();
+		if (*workp != 0)
+			spincnt++;
+		else
+			spincnt = 0;
+		if (spincnt > 10) {
+			*statusp = RCU_KTHREAD_YIELDING;
+			rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
+			spincnt = 0;
+		}
+	}
+	*statusp = RCU_KTHREAD_STOPPED;
+	return 0;
+}
+
+/*
+ * Spawn a per-CPU kthread, setting up affinity and priority.
+ * Because the CPU hotplug lock is held, no other CPU will be attempting
+ * to manipulate rcu_cpu_kthread_task.  There might be another CPU
+ * attempting to access it during boot, but the locking in kthread_bind()
+ * will enforce sufficient ordering.
+ */
+static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
+{
+	struct sched_param sp;
+	struct task_struct *t;
+
+	if (!rcu_kthreads_spawnable ||
+	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
+		return 0;
+	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+	kthread_bind(t, cpu);
+	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
+	per_cpu(rcu_cpu_kthread_task, cpu) = t;
+	wake_up_process(t);
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	return 0;
+}
+
+/*
+ * Per-rcu_node kthread, which is in charge of waking up the per-CPU
+ * kthreads when needed.  We ignore requests to wake up kthreads
+ * for offline CPUs, which is OK because force_quiescent_state()
+ * takes care of this case.
+ */
+static int rcu_node_kthread(void *arg)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp = (struct rcu_node *)arg;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	for (;;) {
+		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
+		wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
+		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		mask = rnp->wakemask;
+		rnp->wakemask = 0;
+		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
+			if ((mask & 0x1) == 0)
+				continue;
+			preempt_disable();
+			t = per_cpu(rcu_cpu_kthread_task, cpu);
+			if (!cpu_online(cpu) || t == NULL) {
+				preempt_enable();
+				continue;
+			}
+			per_cpu(rcu_cpu_has_work, cpu) = 1;
+			sp.sched_priority = RCU_KTHREAD_PRIO;
+			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+			preempt_enable();
+		}
+	}
+	/* NOTREACHED */
+	rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
+	return 0;
+}
+
+/*
+ * Set the per-rcu_node kthread's affinity to cover all CPUs that are
+ * served by the rcu_node in question.  The CPU hotplug lock is still
+ * held, so the value of rnp->qsmaskinit will be stable.
+ *
+ * We don't include outgoingcpu in the affinity set, use -1 if there is
+ * no outgoing CPU.  If there are no CPUs left in the affinity set,
+ * this function allows the kthread to execute on any CPU.
+ */
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+{
+	cpumask_var_t cm;
+	int cpu;
+	unsigned long mask = rnp->qsmaskinit;
+
+	if (rnp->node_kthread_task == NULL)
+		return;
+	if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+		return;
+	cpumask_clear(cm);
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
+		if ((mask & 0x1) && cpu != outgoingcpu)
+			cpumask_set_cpu(cpu, cm);
+	if (cpumask_weight(cm) == 0) {
+		cpumask_setall(cm);
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
+			cpumask_clear_cpu(cpu, cm);
+		WARN_ON_ONCE(cpumask_weight(cm) == 0);
+	}
+	set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
+	rcu_boost_kthread_setaffinity(rnp, cm);
+	free_cpumask_var(cm);
+}
+
+/*
+ * Spawn a per-rcu_node kthread, setting priority and affinity.
+ * Called during boot before online/offline can happen, or, if
+ * during runtime, with the main CPU-hotplug locks held.  So only
+ * one of these can be executing at a time.
+ */
+static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
+						struct rcu_node *rnp)
+{
+	unsigned long flags;
+	int rnp_index = rnp - &rsp->node[0];
+	struct sched_param sp;
+	struct task_struct *t;
+
+	if (!rcu_kthreads_spawnable ||
+	    rnp->qsmaskinit == 0)
+		return 0;
+	if (rnp->node_kthread_task == NULL) {
+		t = kthread_create(rcu_node_kthread, (void *)rnp,
+				   "rcun%d", rnp_index);
+		if (IS_ERR(t))
+			return PTR_ERR(t);
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		rnp->node_kthread_task = t;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		wake_up_process(t);
+		sp.sched_priority = 99;
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	}
+	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
+}
+
+/*
+ * Spawn all kthreads -- called as soon as the scheduler is running.
+ */
+static int __init rcu_spawn_kthreads(void)
+{
+	int cpu;
+	struct rcu_node *rnp;
+
+	rcu_kthreads_spawnable = 1;
+	for_each_possible_cpu(cpu) {
+		init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
+		per_cpu(rcu_cpu_has_work, cpu) = 0;
+		if (cpu_online(cpu))
+			(void)rcu_spawn_one_cpu_kthread(cpu);
+	}
+	rnp = rcu_get_root(rcu_state);
+	init_waitqueue_head(&rnp->node_wq);
+	rcu_init_boost_waitqueue(rnp);
+	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	if (NUM_RCU_NODES > 1)
+		rcu_for_each_leaf_node(rcu_state, rnp) {
+			init_waitqueue_head(&rnp->node_wq);
+			rcu_init_boost_waitqueue(rnp);
+			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+		}
+	return 0;
+}
+early_initcall(rcu_spawn_kthreads);
+
 static void
 __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	   struct rcu_state *rsp)
@@ -1439,6 +1843,13 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	/* Add the callback to our list. */
 	*rdp->nxttail[RCU_NEXT_TAIL] = head;
 	rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
+	rdp->qlen++;
+
+	/* If interrupts were disabled, don't dive into RCU core. */
+	if (irqs_disabled_flags(flags)) {
+		local_irq_restore(flags);
+		return;
+	}
 
 	/*
 	 * Force the grace period if too many callbacks or too long waiting.
@@ -1447,7 +1858,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	 * invoking force_quiescent_state() if the newly enqueued callback
 	 * is the only one waiting for a grace period to complete.
 	 */
-	if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
+	if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
 
 		/* Are we ignoring a completed grace period? */
 		rcu_process_gp_end(rsp, rdp);
@@ -1583,7 +1994,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		 * or RCU-bh, force a local reschedule.
 		 */
 		rdp->n_rp_qs_pending++;
-		if (!rdp->preemptable &&
+		if (!rdp->preemptible &&
 		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
 				 jiffies))
 			set_need_resched();
@@ -1760,7 +2171,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
  * that this CPU cannot possibly have any RCU callbacks in flight yet.
  */
 static void __cpuinit
-rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -1772,7 +2183,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
-	rdp->preemptable = preemptable;
+	rdp->preemptible = preemptible;
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -1813,6 +2224,19 @@ static void __cpuinit rcu_online_cpu(int cpu)
 	rcu_preempt_init_percpu_data(cpu);
 }
 
+static void __cpuinit rcu_online_kthreads(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+
+	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
+	if (rcu_kthreads_spawnable) {
+		(void)rcu_spawn_one_cpu_kthread(cpu);
+		if (rnp->node_kthread_task == NULL)
+			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	}
+}
+
 /*
  * Handle CPU online/offline notification events.
  */
@@ -1820,11 +2244,23 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		rcu_online_cpu(cpu);
+		rcu_online_kthreads(cpu);
+		break;
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+		rcu_node_kthread_setaffinity(rnp, -1);
+		rcu_cpu_kthread_setrt(cpu, 1);
+		break;
+	case CPU_DOWN_PREPARE:
+		rcu_node_kthread_setaffinity(rnp, cpu);
+		rcu_cpu_kthread_setrt(cpu, 0);
 		break;
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
@@ -1943,10 +2379,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 					      j / rsp->levelspread[i - 1];
 			}
 			rnp->level = i;
-			INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[2]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
+			INIT_LIST_HEAD(&rnp->blkd_tasks);
 		}
 	}
 
@@ -1968,7 +2401,6 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
-	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index e8f057e44e3..257664815d5 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -91,6 +91,14 @@ struct rcu_dynticks {
 				/*  remains even for nmi from irq handler. */
 };
 
+/* RCU's kthread states for tracing. */
+#define RCU_KTHREAD_STOPPED  0
+#define RCU_KTHREAD_RUNNING  1
+#define RCU_KTHREAD_WAITING  2
+#define RCU_KTHREAD_OFFCPU   3
+#define RCU_KTHREAD_YIELDING 4
+#define RCU_KTHREAD_MAX      4
+
 /*
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
@@ -109,10 +117,11 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
-	unsigned long expmask;	/* Groups that have ->blocked_tasks[] */
+	unsigned long expmask;	/* Groups that have ->blkd_tasks */
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
+	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -122,11 +131,68 @@ struct rcu_node {
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	struct rcu_node *parent;
-	struct list_head blocked_tasks[4];
-				/* Tasks blocked in RCU read-side critsect. */
-				/*  Grace period number (->gpnum) x blocked */
-				/*  by tasks on the (x & 0x1) element of the */
-				/*  blocked_tasks[] array. */
+	struct list_head blkd_tasks;
+				/* Tasks blocked in RCU read-side critical */
+				/*  section.  Tasks are placed at the head */
+				/*  of this list and age towards the tail. */
+	struct list_head *gp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current grace period, or NULL if there */
+				/*  is no such task. */
+	struct list_head *exp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current expedited grace period, or NULL */
+				/*  if there is no such task.  If there */
+				/*  is no current expedited grace period, */
+				/*  then there can cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+	struct list_head *boost_tasks;
+				/* Pointer to first task that needs to be */
+				/*  priority boosted, or NULL if no priority */
+				/*  boosting is needed for this rcu_node */
+				/*  structure.  If there are no tasks */
+				/*  queued on this rcu_node structure that */
+				/*  are blocking the current grace period, */
+				/*  there can be no such task. */
+	unsigned long boost_time;
+				/* When to start boosting (jiffies). */
+	struct task_struct *boost_kthread_task;
+				/* kthread that takes care of priority */
+				/*  boosting for this rcu_node structure. */
+	wait_queue_head_t boost_wq;
+				/* Wait queue on which to park the boost */
+				/*  kthread. */
+	unsigned int boost_kthread_status;
+				/* State of boost_kthread_task for tracing. */
+	unsigned long n_tasks_boosted;
+				/* Total number of tasks boosted. */
+	unsigned long n_exp_boosts;
+				/* Number of tasks boosted for expedited GP. */
+	unsigned long n_normal_boosts;
+				/* Number of tasks boosted for normal GP. */
+	unsigned long n_balk_blkd_tasks;
+				/* Refused to boost: no blocked tasks. */
+	unsigned long n_balk_exp_gp_tasks;
+				/* Refused to boost: nothing blocking GP. */
+	unsigned long n_balk_boost_tasks;
+				/* Refused to boost: already boosting. */
+	unsigned long n_balk_notblocked;
+				/* Refused to boost: RCU RS CS still running. */
+	unsigned long n_balk_notyet;
+				/* Refused to boost: not yet time. */
+	unsigned long n_balk_nos;
+				/* Refused to boost: not sure why, though. */
+				/*  This can happen due to race conditions. */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+	struct task_struct *node_kthread_task;
+				/* kthread that takes care of this rcu_node */
+				/*  structure, for example, awakening the */
+				/*  per-CPU kthreads as needed. */
+	wait_queue_head_t node_wq;
+				/* Wait queue on which to park the per-node */
+				/*  kthread. */
+	unsigned int node_kthread_status;
+				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -175,7 +241,7 @@ struct rcu_data {
 	bool		passed_quiesc;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		preemptable;	/* Preemptable RCU? */
+	bool		preemptible;	/* Preemptible RCU? */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 
@@ -254,7 +320,6 @@ struct rcu_data {
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA	       (5 * HZ)
@@ -272,13 +337,6 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
-#define RCU_CPU_STALL_SUPPRESS_INIT 0
-#else
-#define RCU_CPU_STALL_SUPPRESS_INIT 1
-#endif
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -325,12 +383,12 @@ struct rcu_state {
 						/*  due to lock unavailable. */
 	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
 						/*  due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	unsigned long gp_max;			/* Maximum GP duration in */
+						/*  jiffies. */
 	char *name;				/* Name of structure. */
 };
 
@@ -361,16 +419,14 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(int cpu);
-static int rcu_preempted_readers(struct rcu_node *rnp);
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_stall_reset(void);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
@@ -390,5 +446,13 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
+static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+					  cpumask_var_t cm);
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+						 struct rcu_node *rnp,
+						 int rnp_index);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index a3638710dc6..3f6559a5f5c 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1,7 +1,7 @@
 /*
  * Read-Copy Update mechanism for mutual exclusion (tree-based version)
  * Internal non-public definitions that provide either classic
- * or preemptable semantics.
+ * or preemptible semantics.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -54,10 +54,6 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
 	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
 #endif
-#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO
-	       "\tRCU-based detection of stalled CPUs is disabled.\n");
-#endif
 #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
 	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
 #endif
@@ -70,6 +66,7 @@ static void __init rcu_bootup_announce_oddness(void)
 
 struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+static struct rcu_state *rcu_state = &rcu_preempt_state;
 
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 
@@ -78,7 +75,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
  */
 static void __init rcu_bootup_announce(void)
 {
-	printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n");
 	rcu_bootup_announce_oddness();
 }
 
@@ -111,7 +108,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
- * Record a preemptable-RCU quiescent state for the specified CPU.  Note
+ * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
@@ -134,12 +131,12 @@ static void rcu_preempt_qs(int cpu)
  * We have entered the scheduler, and the current task might soon be
  * context-switched away from.  If this task is in an RCU read-side
  * critical section, we will no longer be able to rely on the CPU to
- * record that fact, so we enqueue the task on the appropriate entry
- * of the blocked_tasks[] array.  The task will dequeue itself when
- * it exits the outermost enclosing RCU read-side critical section.
- * Therefore, the current grace period cannot be permitted to complete
- * until the blocked_tasks[] entry indexed by the low-order bit of
- * rnp->gpnum empties.
+ * record that fact, so we enqueue the task on the blkd_tasks list.
+ * The task will dequeue itself when it exits the outermost enclosing
+ * RCU read-side critical section.  Therefore, the current grace period
+ * cannot be permitted to complete until the blkd_tasks list entries
+ * predating the current grace period drain, in other words, until
+ * rnp->gp_tasks becomes NULL.
  *
  * Caller must disable preemption.
  */
@@ -147,7 +144,6 @@ static void rcu_preempt_note_context_switch(int cpu)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
-	int phase;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
@@ -169,15 +165,30 @@ static void rcu_preempt_note_context_switch(int cpu)
 		 * (i.e., this CPU has not yet passed through a quiescent
 		 * state for the current grace period), then as long
 		 * as that task remains queued, the current grace period
-		 * cannot end.
+		 * cannot end.  Note that there is some uncertainty as
+		 * to exactly when the current grace period started.
+		 * We take a conservative approach, which can result
+		 * in unnecessarily waiting on tasks that started very
+		 * slightly after the current grace period began.  C'est
+		 * la vie!!!
 		 *
 		 * But first, note that the current CPU must still be
 		 * on line!
 		 */
 		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
-		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
-		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
+		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
+			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
+			rnp->gp_tasks = &t->rcu_node_entry;
+#ifdef CONFIG_RCU_BOOST
+			if (rnp->boost_tasks != NULL)
+				rnp->boost_tasks = rnp->gp_tasks;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+		} else {
+			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
+			if (rnp->qsmask & rdp->grpmask)
+				rnp->gp_tasks = &t->rcu_node_entry;
+		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
@@ -196,7 +207,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 }
 
 /*
- * Tree-preemptable RCU implementation for rcu_read_lock().
+ * Tree-preemptible RCU implementation for rcu_read_lock().
  * Just increment ->rcu_read_lock_nesting, shared state will be updated
  * if we block.
  */
@@ -212,12 +223,9 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock);
  * for the specified rcu_node structure.  If the caller needs a reliable
  * answer, it must hold the rcu_node's ->lock.
  */
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
-	int phase = rnp->gpnum & 0x1;
-
-	return !list_empty(&rnp->blocked_tasks[phase]) ||
-	       !list_empty(&rnp->blocked_tasks[phase + 2]);
+	return rnp->gp_tasks != NULL;
 }
 
 /*
@@ -233,7 +241,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	unsigned long mask;
 	struct rcu_node *rnp_p;
 
-	if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
+	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;  /* Still need more quiescent states! */
 	}
@@ -257,6 +265,21 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 }
 
 /*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t,
+					     struct rcu_node *rnp)
+{
+	struct list_head *np;
+
+	np = t->rcu_node_entry.next;
+	if (np == &rnp->blkd_tasks)
+		np = NULL;
+	return np;
+}
+
+/*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
@@ -266,6 +289,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	int empty;
 	int empty_exp;
 	unsigned long flags;
+	struct list_head *np;
 	struct rcu_node *rnp;
 	int special;
 
@@ -306,10 +330,19 @@ static void rcu_read_unlock_special(struct task_struct *t)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
-		empty = !rcu_preempted_readers(rnp);
+		empty = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
+		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
+		if (&t->rcu_node_entry == rnp->gp_tasks)
+			rnp->gp_tasks = np;
+		if (&t->rcu_node_entry == rnp->exp_tasks)
+			rnp->exp_tasks = np;
+#ifdef CONFIG_RCU_BOOST
+		if (&t->rcu_node_entry == rnp->boost_tasks)
+			rnp->boost_tasks = np;
+#endif /* #ifdef CONFIG_RCU_BOOST */
 		t->rcu_blocked_node = NULL;
 
 		/*
@@ -322,6 +355,15 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		else
 			rcu_report_unblock_qs_rnp(rnp, flags);
 
+#ifdef CONFIG_RCU_BOOST
+		/* Unboost if we were boosted. */
+		if (special & RCU_READ_UNLOCK_BOOSTED) {
+			t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
+			rt_mutex_unlock(t->rcu_boost_mutex);
+			t->rcu_boost_mutex = NULL;
+		}
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 		/*
 		 * If this was the last task on the expedited lists,
 		 * then we need to report up the rcu_node hierarchy.
@@ -334,7 +376,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 }
 
 /*
- * Tree-preemptable RCU implementation for rcu_read_unlock().
+ * Tree-preemptible RCU implementation for rcu_read_unlock().
  * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
  * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
  * invoke rcu_read_unlock_special() to clean up after a context switch
@@ -356,8 +398,6 @@ void __rcu_read_unlock(void)
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 #ifdef CONFIG_RCU_CPU_STALL_VERBOSE
 
 /*
@@ -367,18 +407,16 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 {
 	unsigned long flags;
-	struct list_head *lp;
-	int phase;
 	struct task_struct *t;
 
-	if (rcu_preempted_readers(rnp)) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		phase = rnp->gpnum & 0x1;
-		lp = &rnp->blocked_tasks[phase];
-		list_for_each_entry(t, lp, rcu_node_entry)
-			sched_show_task(t);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	}
+	if (!rcu_preempt_blocked_readers_cgp(rnp))
+		return;
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	t = list_entry(rnp->gp_tasks,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+		sched_show_task(t);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -408,16 +446,14 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
-	struct list_head *lp;
-	int phase;
 	struct task_struct *t;
 
-	if (rcu_preempted_readers(rnp)) {
-		phase = rnp->gpnum & 0x1;
-		lp = &rnp->blocked_tasks[phase];
-		list_for_each_entry(t, lp, rcu_node_entry)
-			printk(" P%d", t->pid);
-	}
+	if (!rcu_preempt_blocked_readers_cgp(rnp))
+		return;
+	t = list_entry(rnp->gp_tasks,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+		printk(" P%d", t->pid);
 }
 
 /*
@@ -430,18 +466,21 @@ static void rcu_preempt_stall_reset(void)
 	rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
  * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
  * must be held by the caller.
+ *
+ * Also, if there are blocked tasks on the list, they automatically
+ * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 {
-	WARN_ON_ONCE(rcu_preempted_readers(rnp));
+	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+	if (!list_empty(&rnp->blkd_tasks))
+		rnp->gp_tasks = rnp->blkd_tasks.next;
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
@@ -465,50 +504,68 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 				     struct rcu_node *rnp,
 				     struct rcu_data *rdp)
 {
-	int i;
 	struct list_head *lp;
 	struct list_head *lp_root;
 	int retval = 0;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
-	struct task_struct *tp;
+	struct task_struct *t;
 
 	if (rnp == rnp_root) {
 		WARN_ONCE(1, "Last CPU thought to be offlined?");
 		return 0;  /* Shouldn't happen: at least one CPU online. */
 	}
-	WARN_ON_ONCE(rnp != rdp->mynode &&
-		     (!list_empty(&rnp->blocked_tasks[0]) ||
-		      !list_empty(&rnp->blocked_tasks[1]) ||
-		      !list_empty(&rnp->blocked_tasks[2]) ||
-		      !list_empty(&rnp->blocked_tasks[3])));
+
+	/* If we are on an internal node, complain bitterly. */
+	WARN_ON_ONCE(rnp != rdp->mynode);
 
 	/*
-	 * Move tasks up to root rcu_node.  Rely on the fact that the
-	 * root rcu_node can be at most one ahead of the rest of the
-	 * rcu_nodes in terms of gp_num value.  This fact allows us to
-	 * move the blocked_tasks[] array directly, element by element.
+	 * Move tasks up to root rcu_node.  Don't try to get fancy for
+	 * this corner-case operation -- just put this node's tasks
+	 * at the head of the root node's list, and update the root node's
+	 * ->gp_tasks and ->exp_tasks pointers to those of this node's,
+	 * if non-NULL.  This might result in waiting for more tasks than
+	 * absolutely necessary, but this is a good performance/complexity
+	 * tradeoff.
 	 */
-	if (rcu_preempted_readers(rnp))
+	if (rcu_preempt_blocked_readers_cgp(rnp))
 		retval |= RCU_OFL_TASKS_NORM_GP;
 	if (rcu_preempted_readers_exp(rnp))
 		retval |= RCU_OFL_TASKS_EXP_GP;
-	for (i = 0; i < 4; i++) {
-		lp = &rnp->blocked_tasks[i];
-		lp_root = &rnp_root->blocked_tasks[i];
-		while (!list_empty(lp)) {
-			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
-			raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
-			list_del(&tp->rcu_node_entry);
-			tp->rcu_blocked_node = rnp_root;
-			list_add(&tp->rcu_node_entry, lp_root);
-			raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */
-		}
+	lp = &rnp->blkd_tasks;
+	lp_root = &rnp_root->blkd_tasks;
+	while (!list_empty(lp)) {
+		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
+		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		list_del(&t->rcu_node_entry);
+		t->rcu_blocked_node = rnp_root;
+		list_add(&t->rcu_node_entry, lp_root);
+		if (&t->rcu_node_entry == rnp->gp_tasks)
+			rnp_root->gp_tasks = rnp->gp_tasks;
+		if (&t->rcu_node_entry == rnp->exp_tasks)
+			rnp_root->exp_tasks = rnp->exp_tasks;
+#ifdef CONFIG_RCU_BOOST
+		if (&t->rcu_node_entry == rnp->boost_tasks)
+			rnp_root->boost_tasks = rnp->boost_tasks;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+		raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
 	}
+
+#ifdef CONFIG_RCU_BOOST
+	/* In case root is being boosted and leaf is not. */
+	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	if (rnp_root->boost_tasks != NULL &&
+	    rnp_root->boost_tasks != rnp_root->gp_tasks)
+		rnp_root->boost_tasks = rnp_root->gp_tasks;
+	raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+	rnp->gp_tasks = NULL;
+	rnp->exp_tasks = NULL;
 	return retval;
 }
 
 /*
- * Do CPU-offline processing for preemptable RCU.
+ * Do CPU-offline processing for preemptible RCU.
  */
 static void rcu_preempt_offline_cpu(int cpu)
 {
@@ -537,7 +594,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 }
 
 /*
- * Process callbacks for preemptable RCU.
+ * Process callbacks for preemptible RCU.
  */
 static void rcu_preempt_process_callbacks(void)
 {
@@ -546,7 +603,7 @@ static void rcu_preempt_process_callbacks(void)
 }
 
 /*
- * Queue a preemptable-RCU callback for invocation after a grace period.
+ * Queue a preemptible-RCU callback for invocation after a grace period.
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
@@ -594,8 +651,7 @@ static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
  */
 static int rcu_preempted_readers_exp(struct rcu_node *rnp)
 {
-	return !list_empty(&rnp->blocked_tasks[2]) ||
-	       !list_empty(&rnp->blocked_tasks[3]);
+	return rnp->exp_tasks != NULL;
 }
 
 /*
@@ -655,13 +711,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 static void
 sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	int must_wait;
+	unsigned long flags;
+	int must_wait = 0;
 
-	raw_spin_lock(&rnp->lock); /* irqs already disabled */
-	list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
-	list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
-	must_wait = rcu_preempted_readers_exp(rnp);
-	raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	if (list_empty(&rnp->blkd_tasks))
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	else {
+		rnp->exp_tasks = rnp->blkd_tasks.next;
+		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
+		must_wait = 1;
+	}
 	if (!must_wait)
 		rcu_report_exp_rnp(rsp, rnp);
 }
@@ -669,9 +729,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 /*
  * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
  * is to invoke synchronize_sched_expedited() to push all the tasks to
- * the ->blocked_tasks[] lists, move all entries from the first set of
- * ->blocked_tasks[] lists to the second set, and finally wait for this
- * second set to drain.
+ * the ->blkd_tasks lists and wait for this list to drain.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -703,7 +761,7 @@ void synchronize_rcu_expedited(void)
 	if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
 		goto unlock_mb_ret; /* Others did our work for us. */
 
-	/* force all RCU readers onto blocked_tasks[]. */
+	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -715,7 +773,7 @@ void synchronize_rcu_expedited(void)
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
 
-	/* Snapshot current state of ->blocked_tasks[] lists. */
+	/* Snapshot current state of ->blkd_tasks lists. */
 	rcu_for_each_leaf_node(rsp, rnp)
 		sync_rcu_preempt_exp_init(rsp, rnp);
 	if (NUM_RCU_NODES > 1)
@@ -723,7 +781,7 @@ void synchronize_rcu_expedited(void)
 
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 
-	/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);
 	wait_event(sync_rcu_preempt_exp_wq,
 		   sync_rcu_preempt_exp_done(rnp));
@@ -739,7 +797,7 @@ mb_ret:
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 /*
- * Check to see if there is any immediate preemptable-RCU-related work
+ * Check to see if there is any immediate preemptible-RCU-related work
  * to be done.
  */
 static int rcu_preempt_pending(int cpu)
@@ -749,7 +807,7 @@ static int rcu_preempt_pending(int cpu)
 }
 
 /*
- * Does preemptable RCU need the CPU to stay out of dynticks mode?
+ * Does preemptible RCU need the CPU to stay out of dynticks mode?
  */
 static int rcu_preempt_needs_cpu(int cpu)
 {
@@ -766,7 +824,7 @@ void rcu_barrier(void)
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
 /*
- * Initialize preemptable RCU's per-CPU data.
+ * Initialize preemptible RCU's per-CPU data.
  */
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 {
@@ -774,7 +832,7 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 }
 
 /*
- * Move preemptable RCU's callbacks from dying CPU to other online CPU.
+ * Move preemptible RCU's callbacks from dying CPU to other online CPU.
  */
 static void rcu_preempt_send_cbs_to_online(void)
 {
@@ -782,7 +840,7 @@ static void rcu_preempt_send_cbs_to_online(void)
 }
 
 /*
- * Initialize preemptable RCU's state structures.
+ * Initialize preemptible RCU's state structures.
  */
 static void __init __rcu_init_preempt(void)
 {
@@ -790,7 +848,7 @@ static void __init __rcu_init_preempt(void)
 }
 
 /*
- * Check for a task exiting while in a preemptable-RCU read-side
+ * Check for a task exiting while in a preemptible-RCU read-side
  * critical section, clean up if so.  No need to issue warnings,
  * as debug_check_no_locks_held() already does this if lockdep
  * is enabled.
@@ -802,11 +860,13 @@ void exit_rcu(void)
 	if (t->rcu_read_lock_nesting == 0)
 		return;
 	t->rcu_read_lock_nesting = 1;
-	rcu_read_unlock();
+	__rcu_read_unlock();
 }
 
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
+static struct rcu_state *rcu_state = &rcu_sched_state;
+
 /*
  * Tell them what RCU they are running.
  */
@@ -836,7 +896,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
 static void rcu_preempt_note_context_switch(int cpu)
@@ -844,10 +904,10 @@ static void rcu_preempt_note_context_switch(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, there are never any preempted
+ * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
 	return 0;
 }
@@ -862,10 +922,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp)
@@ -873,7 +931,7 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
 }
 
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
@@ -888,10 +946,8 @@ static void rcu_preempt_stall_reset(void)
 {
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
- * Because there is no preemptable RCU, there can be no readers blocked,
+ * Because there is no preemptible RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
@@ -903,7 +959,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 #ifdef CONFIG_HOTPLUG_CPU
 
 /*
- * Because preemptable RCU does not exist, it never needs to migrate
+ * Because preemptible RCU does not exist, it never needs to migrate
  * tasks that were blocked within RCU read-side critical sections, and
  * such non-existent tasks cannot possibly have been blocking the current
  * grace period.
@@ -916,7 +972,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 }
 
 /*
- * Because preemptable RCU does not exist, it never needs CPU-offline
+ * Because preemptible RCU does not exist, it never needs CPU-offline
  * processing.
  */
 static void rcu_preempt_offline_cpu(int cpu)
@@ -926,7 +982,7 @@ static void rcu_preempt_offline_cpu(int cpu)
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
- * Because preemptable RCU does not exist, it never has any callbacks
+ * Because preemptible RCU does not exist, it never has any callbacks
  * to check.
  */
 static void rcu_preempt_check_callbacks(int cpu)
@@ -934,7 +990,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, it never has any callbacks
+ * Because preemptible RCU does not exist, it never has any callbacks
  * to process.
  */
 static void rcu_preempt_process_callbacks(void)
@@ -943,7 +999,7 @@ static void rcu_preempt_process_callbacks(void)
 
 /*
  * Wait for an rcu-preempt grace period, but make it happen quickly.
- * But because preemptable RCU does not exist, map to rcu-sched.
+ * But because preemptible RCU does not exist, map to rcu-sched.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -954,7 +1010,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 #ifdef CONFIG_HOTPLUG_CPU
 
 /*
- * Because preemptable RCU does not exist, there is never any need to
+ * Because preemptible RCU does not exist, there is never any need to
  * report on tasks preempted in RCU read-side critical sections during
  * expedited RCU grace periods.
  */
@@ -966,7 +1022,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
- * Because preemptable RCU does not exist, it never has any work to do.
+ * Because preemptible RCU does not exist, it never has any work to do.
  */
 static int rcu_preempt_pending(int cpu)
 {
@@ -974,7 +1030,7 @@ static int rcu_preempt_pending(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, it never needs any CPU.
+ * Because preemptible RCU does not exist, it never needs any CPU.
  */
 static int rcu_preempt_needs_cpu(int cpu)
 {
@@ -982,7 +1038,7 @@ static int rcu_preempt_needs_cpu(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, rcu_barrier() is just
+ * Because preemptible RCU does not exist, rcu_barrier() is just
  * another name for rcu_barrier_sched().
  */
 void rcu_barrier(void)
@@ -992,7 +1048,7 @@ void rcu_barrier(void)
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
 /*
- * Because preemptable RCU does not exist, there is no per-CPU
+ * Because preemptible RCU does not exist, there is no per-CPU
  * data to initialize.
  */
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
@@ -1000,14 +1056,14 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 }
 
 /*
- * Because there is no preemptable RCU, there are no callbacks to move.
+ * Because there is no preemptible RCU, there are no callbacks to move.
  */
 static void rcu_preempt_send_cbs_to_online(void)
 {
 }
 
 /*
- * Because preemptable RCU does not exist, it need not be initialized.
+ * Because preemptible RCU does not exist, it need not be initialized.
  */
 static void __init __rcu_init_preempt(void)
 {
@@ -1015,6 +1071,276 @@ static void __init __rcu_init_preempt(void)
 
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
+#ifdef CONFIG_RCU_BOOST
+
+#include "rtmutex_common.h"
+
+#ifdef CONFIG_RCU_TRACE
+
+static void rcu_initiate_boost_trace(struct rcu_node *rnp)
+{
+	if (list_empty(&rnp->blkd_tasks))
+		rnp->n_balk_blkd_tasks++;
+	else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL)
+		rnp->n_balk_exp_gp_tasks++;
+	else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL)
+		rnp->n_balk_boost_tasks++;
+	else if (rnp->gp_tasks != NULL && rnp->qsmask != 0)
+		rnp->n_balk_notblocked++;
+	else if (rnp->gp_tasks != NULL &&
+		 ULONG_CMP_LT(jiffies, rnp->boost_time))
+		rnp->n_balk_notyet++;
+	else
+		rnp->n_balk_nos++;
+}
+
+#else /* #ifdef CONFIG_RCU_TRACE */
+
+static void rcu_initiate_boost_trace(struct rcu_node *rnp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Carry out RCU priority boosting on the task indicated by ->exp_tasks
+ * or ->boost_tasks, advancing the pointer to the next task in the
+ * ->blkd_tasks list.
+ *
+ * Note that irqs must be enabled: boosting the task can block.
+ * Returns 1 if there are more tasks needing to be boosted.
+ */
+static int rcu_boost(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct rt_mutex mtx;
+	struct task_struct *t;
+	struct list_head *tb;
+
+	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL)
+		return 0;  /* Nothing left to boost. */
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+
+	/*
+	 * Recheck under the lock: all tasks in need of boosting
+	 * might exit their RCU read-side critical sections on their own.
+	 */
+	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return 0;
+	}
+
+	/*
+	 * Preferentially boost tasks blocking expedited grace periods.
+	 * This cannot starve the normal grace periods because a second
+	 * expedited grace period must boost all blocked tasks, including
+	 * those blocking the pre-existing normal grace period.
+	 */
+	if (rnp->exp_tasks != NULL) {
+		tb = rnp->exp_tasks;
+		rnp->n_exp_boosts++;
+	} else {
+		tb = rnp->boost_tasks;
+		rnp->n_normal_boosts++;
+	}
+	rnp->n_tasks_boosted++;
+
+	/*
+	 * We boost task t by manufacturing an rt_mutex that appears to
+	 * be held by task t.  We leave a pointer to that rt_mutex where
+	 * task t can find it, and task t will release the mutex when it
+	 * exits its outermost RCU read-side critical section.  Then
+	 * simply acquiring this artificial rt_mutex will boost task
+	 * t's priority.  (Thanks to tglx for suggesting this approach!)
+	 *
+	 * Note that task t must acquire rnp->lock to remove itself from
+	 * the ->blkd_tasks list, which it will do from exit() if from
+	 * nowhere else.  We therefore are guaranteed that task t will
+	 * stay around at least until we drop rnp->lock.  Note that
+	 * rnp->lock also resolves races between our priority boosting
+	 * and task t's exiting its outermost RCU read-side critical
+	 * section.
+	 */
+	t = container_of(tb, struct task_struct, rcu_node_entry);
+	rt_mutex_init_proxy_locked(&mtx, t);
+	t->rcu_boost_mutex = &mtx;
+	t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
+	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
+
+	return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL;
+}
+
+/*
+ * Timer handler to initiate waking up of boost kthreads that
+ * have yielded the CPU due to excessive numbers of tasks to
+ * boost.  We wake up the per-rcu_node kthread, which in turn
+ * will wake up the booster kthread.
+ */
+static void rcu_boost_kthread_timer(unsigned long arg)
+{
+	invoke_rcu_node_kthread((struct rcu_node *)arg);
+}
+
+/*
+ * Priority-boosting kthread.  One per leaf rcu_node and one for the
+ * root rcu_node.
+ */
+static int rcu_boost_kthread(void *arg)
+{
+	struct rcu_node *rnp = (struct rcu_node *)arg;
+	int spincnt = 0;
+	int more2boost;
+
+	for (;;) {
+		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+		wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
+							rnp->exp_tasks);
+		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
+		more2boost = rcu_boost(rnp);
+		if (more2boost)
+			spincnt++;
+		else
+			spincnt = 0;
+		if (spincnt > 10) {
+			rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
+			spincnt = 0;
+		}
+	}
+	/* NOTREACHED */
+	return 0;
+}
+
+/*
+ * Check to see if it is time to start boosting RCU readers that are
+ * blocking the current grace period, and, if so, tell the per-rcu_node
+ * kthread to start boosting them.  If there is an expedited grace
+ * period in progress, it is always time to boost.
+ *
+ * The caller must hold rnp->lock, which this function releases,
+ * but irqs remain disabled.  The ->boost_kthread_task is immortal,
+ * so we don't need to worry about it going away.
+ */
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+{
+	struct task_struct *t;
+
+	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
+		rnp->n_balk_exp_gp_tasks++;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+	if (rnp->exp_tasks != NULL ||
+	    (rnp->gp_tasks != NULL &&
+	     rnp->boost_tasks == NULL &&
+	     rnp->qsmask == 0 &&
+	     ULONG_CMP_GE(jiffies, rnp->boost_time))) {
+		if (rnp->exp_tasks == NULL)
+			rnp->boost_tasks = rnp->gp_tasks;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		t = rnp->boost_kthread_task;
+		if (t != NULL)
+			wake_up_process(t);
+	} else {
+		rcu_initiate_boost_trace(rnp);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
+/*
+ * Set the affinity of the boost kthread.  The CPU-hotplug locks are
+ * held, so no one should be messing with the existence of the boost
+ * kthread.
+ */
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+					  cpumask_var_t cm)
+{
+	struct task_struct *t;
+
+	t = rnp->boost_kthread_task;
+	if (t != NULL)
+		set_cpus_allowed_ptr(rnp->boost_kthread_task, cm);
+}
+
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
+
+/*
+ * Do priority-boost accounting for the start of a new grace period.
+ */
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
+{
+	rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
+}
+
+/*
+ * Initialize the RCU-boost waitqueue.
+ */
+static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
+{
+	init_waitqueue_head(&rnp->boost_wq);
+}
+
+/*
+ * Create an RCU-boost kthread for the specified node if one does not
+ * already exist.  We only create this kthread for preemptible RCU.
+ * Returns zero if all is well, a negated errno otherwise.
+ */
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+						 struct rcu_node *rnp,
+						 int rnp_index)
+{
+	unsigned long flags;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	if (&rcu_preempt_state != rsp)
+		return 0;
+	if (rnp->boost_kthread_task != NULL)
+		return 0;
+	t = kthread_create(rcu_boost_kthread, (void *)rnp,
+			   "rcub%d", rnp_index);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	rnp->boost_kthread_task = t;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	wake_up_process(t);
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	return 0;
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+					  cpumask_var_t cm)
+{
+}
+
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
+{
+}
+
+static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
+{
+}
+
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+						 struct rcu_node *rnp,
+						 int rnp_index)
+{
+	return 0;
+}
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
 #ifndef CONFIG_SMP
 
 void synchronize_sched_expedited(void)
@@ -1187,8 +1513,8 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
  *
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
- * raise_softirq() to cause rcu_process_callbacks() to be invoked later.
- * The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ * invoke_rcu_cpu_kthread() to cause rcu_process_callbacks() to be invoked
+ * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
  */
 int rcu_needs_cpu(int cpu)
 {
@@ -1239,7 +1565,7 @@ int rcu_needs_cpu(int cpu)
 
 	/* If RCU callbacks are still pending, RCU still needs this CPU. */
 	if (c)
-		raise_softirq(RCU_SOFTIRQ);
+		invoke_rcu_cpu_kthread();
 	return c;
 }
 
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index c8e97853b97..aa0fd72b4bc 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -46,6 +46,18 @@
 #define RCU_TREE_NONCORE
 #include "rcutree.h"
 
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu);
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
+DECLARE_PER_CPU(char, rcu_cpu_has_work);
+
+static char convert_kthread_status(unsigned int kthread_status)
+{
+	if (kthread_status > RCU_KTHREAD_MAX)
+		return '?';
+	return "SRWOY"[kthread_status];
+}
+
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
@@ -64,7 +76,21 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d ktl=%x b=%ld",
+		   rdp->qlen,
+		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
+			rdp->nxttail[RCU_NEXT_TAIL]],
+		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
+			rdp->nxttail[RCU_NEXT_READY_TAIL]],
+		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
+			rdp->nxttail[RCU_WAIT_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   per_cpu(rcu_cpu_has_work, rdp->cpu),
+		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
+					  rdp->cpu)),
+		   per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
+		   per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff,
+		   rdp->blimit);
 	seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -121,7 +147,18 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, ",%ld,\"%c%c%c%c\",%d,\"%c\",%ld", rdp->qlen,
+		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
+			rdp->nxttail[RCU_NEXT_TAIL]],
+		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
+			rdp->nxttail[RCU_NEXT_READY_TAIL]],
+		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
+			rdp->nxttail[RCU_WAIT_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   per_cpu(rcu_cpu_has_work, rdp->cpu),
+		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
+					  rdp->cpu)),
+		   rdp->blimit);
 	seq_printf(m, ",%lu,%lu,%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -157,11 +194,76 @@ static const struct file_operations rcudata_csv_fops = {
 	.release = single_release,
 };
 
+#ifdef CONFIG_RCU_BOOST
+
+static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp)
+{
+	seq_printf(m,  "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu "
+		   "j=%04x bt=%04x\n",
+		   rnp->grplo, rnp->grphi,
+		   "T."[list_empty(&rnp->blkd_tasks)],
+		   "N."[!rnp->gp_tasks],
+		   "E."[!rnp->exp_tasks],
+		   "B."[!rnp->boost_tasks],
+		   convert_kthread_status(rnp->boost_kthread_status),
+		   rnp->n_tasks_boosted, rnp->n_exp_boosts,
+		   rnp->n_normal_boosts,
+		   (int)(jiffies & 0xffff),
+		   (int)(rnp->boost_time & 0xffff));
+	seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n",
+		   "     balk",
+		   rnp->n_balk_blkd_tasks,
+		   rnp->n_balk_exp_gp_tasks,
+		   rnp->n_balk_boost_tasks,
+		   rnp->n_balk_notblocked,
+		   rnp->n_balk_notyet,
+		   rnp->n_balk_nos);
+}
+
+static int show_rcu_node_boost(struct seq_file *m, void *unused)
+{
+	struct rcu_node *rnp;
+
+	rcu_for_each_leaf_node(&rcu_preempt_state, rnp)
+		print_one_rcu_node_boost(m, rnp);
+	return 0;
+}
+
+static int rcu_node_boost_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcu_node_boost, NULL);
+}
+
+static const struct file_operations rcu_node_boost_fops = {
+	.owner = THIS_MODULE,
+	.open = rcu_node_boost_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+/*
+ * Create the rcuboost debugfs entry.  Standard error return.
+ */
+static int rcu_boost_trace_create_file(struct dentry *rcudir)
+{
+	return !debugfs_create_file("rcuboost", 0444, rcudir, NULL,
+				    &rcu_node_boost_fops);
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+static int rcu_boost_trace_create_file(struct dentry *rcudir)
+{
+	return 0;  /* There cannot be an error if we didn't create it! */
+}
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
 static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 {
 	unsigned long gpnum;
 	int level = 0;
-	int phase;
 	struct rcu_node *rnp;
 
 	gpnum = rsp->gpnum;
@@ -178,13 +280,11 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		phase = gpnum & 0x1;
-		seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d    ",
+		seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d    ",
 			   rnp->qsmask, rnp->qsmaskinit,
-			   "T."[list_empty(&rnp->blocked_tasks[phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[phase + 2])],
-			   "T."[list_empty(&rnp->blocked_tasks[!phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[!phase + 2])],
+			   ".G"[rnp->gp_tasks != NULL],
+			   ".E"[rnp->exp_tasks != NULL],
+			   ".T"[!list_empty(&rnp->blkd_tasks)],
 			   rnp->grplo, rnp->grphi, rnp->grpnum);
 	}
 	seq_puts(m, "\n");
@@ -216,16 +316,35 @@ static const struct file_operations rcuhier_fops = {
 	.release = single_release,
 };
 
+static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	unsigned long completed;
+	unsigned long gpnum;
+	unsigned long gpage;
+	unsigned long gpmax;
+	struct rcu_node *rnp = &rsp->node[0];
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	completed = rsp->completed;
+	gpnum = rsp->gpnum;
+	if (rsp->completed == rsp->gpnum)
+		gpage = 0;
+	else
+		gpage = jiffies - rsp->gp_start;
+	gpmax = rsp->gp_max;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	seq_printf(m, "%s: completed=%ld  gpnum=%lu  age=%ld  max=%ld\n",
+		   rsp->name, completed, gpnum, gpage, gpmax);
+}
+
 static int show_rcugp(struct seq_file *m, void *unused)
 {
 #ifdef CONFIG_TREE_PREEMPT_RCU
-	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%lu\n",
-		   rcu_preempt_state.completed, rcu_preempt_state.gpnum);
+	show_one_rcugp(m, &rcu_preempt_state);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%lu\n",
-		   rcu_sched_state.completed, rcu_sched_state.gpnum);
-	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%lu\n",
-		   rcu_bh_state.completed, rcu_bh_state.gpnum);
+	show_one_rcugp(m, &rcu_sched_state);
+	show_one_rcugp(m, &rcu_bh_state);
 	return 0;
 }
 
@@ -298,6 +417,29 @@ static const struct file_operations rcu_pending_fops = {
 	.release = single_release,
 };
 
+static int show_rcutorture(struct seq_file *m, void *unused)
+{
+	seq_printf(m, "rcutorture test sequence: %lu %s\n",
+		   rcutorture_testseq >> 1,
+		   (rcutorture_testseq & 0x1) ? "(test in progress)" : "");
+	seq_printf(m, "rcutorture update version number: %lu\n",
+		   rcutorture_vernum);
+	return 0;
+}
+
+static int rcutorture_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcutorture, NULL);
+}
+
+static const struct file_operations rcutorture_fops = {
+	.owner = THIS_MODULE,
+	.open = rcutorture_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 static struct dentry *rcudir;
 
 static int __init rcutree_trace_init(void)
@@ -318,6 +460,9 @@ static int __init rcutree_trace_init(void)
 	if (!retval)
 		goto free_out;
 
+	if (rcu_boost_trace_create_file(rcudir))
+		goto free_out;
+
 	retval = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
 	if (!retval)
 		goto free_out;
@@ -331,6 +476,11 @@ static int __init rcutree_trace_init(void)
 						NULL, &rcu_pending_fops);
 	if (!retval)
 		goto free_out;
+
+	retval = debugfs_create_file("rcutorture", 0444, rcudir,
+						NULL, &rcutorture_fops);
+	if (!retval)
+		goto free_out;
 	return 0;
 free_out:
 	debugfs_remove_recursive(rcudir);
diff --git a/kernel/sched.c b/kernel/sched.c
index 312f8b95c2d..c62acf45d3b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,7 +231,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 #endif
 
 /*
- * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * sched_domains_mutex serializes calls to init_sched_domains,
  * detach_destroy_domains and partition_sched_domains.
  */
 static DEFINE_MUTEX(sched_domains_mutex);
@@ -312,6 +312,9 @@ struct cfs_rq {
 
 	u64 exec_clock;
 	u64 min_vruntime;
+#ifndef CONFIG_64BIT
+	u64 min_vruntime_copy;
+#endif
 
 	struct rb_root tasks_timeline;
 	struct rb_node *rb_leftmost;
@@ -325,7 +328,9 @@ struct cfs_rq {
 	 */
 	struct sched_entity *curr, *next, *last, *skip;
 
+#ifdef	CONFIG_SCHED_DEBUG
 	unsigned int nr_spread_over;
+#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
@@ -417,6 +422,7 @@ struct rt_rq {
  */
 struct root_domain {
 	atomic_t refcount;
+	struct rcu_head rcu;
 	cpumask_var_t span;
 	cpumask_var_t online;
 
@@ -460,7 +466,7 @@ struct rq {
 	u64 nohz_stamp;
 	unsigned char nohz_balance_kick;
 #endif
-	unsigned int skip_clock_update;
+	int skip_clock_update;
 
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
@@ -553,6 +559,10 @@ struct rq {
 	unsigned int ttwu_count;
 	unsigned int ttwu_local;
 #endif
+
+#ifdef CONFIG_SMP
+	struct task_struct *wake_list;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -571,7 +581,7 @@ static inline int cpu_of(struct rq *rq)
 
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
-			      rcu_read_lock_sched_held() || \
+			      rcu_read_lock_held() || \
 			      lockdep_is_held(&sched_domains_mutex))
 
 /*
@@ -596,7 +606,7 @@ static inline int cpu_of(struct rq *rq)
  * Return the group to which this tasks belongs.
  *
  * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
+ * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
  * holds that lock for each task it moves into the cgroup. Therefore
  * by holding that lock, we pin the task to the current cgroup.
  */
@@ -606,7 +616,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&task_rq(p)->lock));
+			lockdep_is_held(&p->pi_lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -642,7 +652,7 @@ static void update_rq_clock(struct rq *rq)
 {
 	s64 delta;
 
-	if (rq->skip_clock_update)
+	if (rq->skip_clock_update > 0)
 		return;
 
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
@@ -838,18 +848,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p)
 	return rq->curr == p;
 }
 
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline int task_running(struct rq *rq, struct task_struct *p)
 {
+#ifdef CONFIG_SMP
+	return p->on_cpu;
+#else
 	return task_current(rq, p);
+#endif
 }
 
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * We can optimise this out completely for !SMP, because the
+	 * SMP rebalancing from interrupt is the only thing that cares
+	 * here.
+	 */
+	next->on_cpu = 1;
+#endif
 }
 
 static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 */
+	smp_wmb();
+	prev->on_cpu = 0;
+#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq->lock.owner = current;
@@ -865,15 +896,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 }
 
 #else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline int task_running(struct rq *rq, struct task_struct *p)
-{
-#ifdef CONFIG_SMP
-	return p->oncpu;
-#else
-	return task_current(rq, p);
-#endif
-}
-
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
 #ifdef CONFIG_SMP
@@ -882,7 +904,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 	 * SMP rebalancing from interrupt is the only thing that cares
 	 * here.
 	 */
-	next->oncpu = 1;
+	next->on_cpu = 1;
 #endif
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	raw_spin_unlock_irq(&rq->lock);
@@ -895,12 +917,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->oncpu is cleared, the task can be moved to a different CPU.
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 */
 	smp_wmb();
-	prev->oncpu = 0;
+	prev->on_cpu = 0;
 #endif
 #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();
@@ -909,23 +931,15 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize ->cpus_allowed
- * against ttwu().
- */
-static inline int task_is_waking(struct task_struct *p)
-{
-	return unlikely(p->state == TASK_WAKING);
-}
-
-/*
- * __task_rq_lock - lock the runqueue a given task resides on.
- * Must be called interrupts disabled.
+ * __task_rq_lock - lock the rq @p resides on.
  */
 static inline struct rq *__task_rq_lock(struct task_struct *p)
 	__acquires(rq->lock)
 {
 	struct rq *rq;
 
+	lockdep_assert_held(&p->pi_lock);
+
 	for (;;) {
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
@@ -936,22 +950,22 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 }
 
 /*
- * task_rq_lock - lock the runqueue a given task resides on and disable
- * interrupts. Note the ordering: we can safely lookup the task_rq without
- * explicitly disabling preemption.
+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
  */
 static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(p->pi_lock)
 	__acquires(rq->lock)
 {
 	struct rq *rq;
 
 	for (;;) {
-		local_irq_save(*flags);
+		raw_spin_lock_irqsave(&p->pi_lock, *flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
 		if (likely(rq == task_rq(p)))
 			return rq;
-		raw_spin_unlock_irqrestore(&rq->lock, *flags);
+		raw_spin_unlock(&rq->lock);
+		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
 	}
 }
 
@@ -961,10 +975,13 @@ static void __task_rq_unlock(struct rq *rq)
 	raw_spin_unlock(&rq->lock);
 }
 
-static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
 	__releases(rq->lock)
+	__releases(p->pi_lock)
 {
-	raw_spin_unlock_irqrestore(&rq->lock, *flags);
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
 }
 
 /*
@@ -1193,11 +1210,17 @@ int get_nohz_timer_target(void)
 	int i;
 	struct sched_domain *sd;
 
+	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd))
-			if (!idle_cpu(i))
-				return i;
+		for_each_cpu(i, sched_domain_span(sd)) {
+			if (!idle_cpu(i)) {
+				cpu = i;
+				goto unlock;
+			}
+		}
 	}
+unlock:
+	rcu_read_unlock();
 	return cpu;
 }
 /*
@@ -1307,15 +1330,15 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
 	u64 tmp;
 
+	tmp = (u64)delta_exec * weight;
+
 	if (!lw->inv_weight) {
 		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
 			lw->inv_weight = 1;
 		else
-			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
-				/ (lw->weight+1);
+			lw->inv_weight = WMULT_CONST / lw->weight;
 	}
 
-	tmp = (u64)delta_exec * weight;
 	/*
 	 * Check whether we'd overflow the 64-bit multiplication:
 	 */
@@ -1773,7 +1796,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	update_rq_clock(rq);
 	sched_info_queued(p);
 	p->sched_class->enqueue_task(rq, p, flags);
-	p->se.on_rq = 1;
 }
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1781,7 +1803,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	update_rq_clock(rq);
 	sched_info_dequeued(p);
 	p->sched_class->dequeue_task(rq, p, flags);
-	p->se.on_rq = 0;
 }
 
 /*
@@ -2116,7 +2137,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+	if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -2162,6 +2183,11 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
+				      lockdep_is_held(&task_rq(p)->lock)));
+#endif
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
@@ -2182,19 +2208,6 @@ struct migration_arg {
 static int migration_cpu_stop(void *data);
 
 /*
- * The task's runqueue lock must be held.
- * Returns true if you have to wait for migration thread.
- */
-static bool migrate_task(struct task_struct *p, struct rq *rq)
-{
-	/*
-	 * If the task is not on a runqueue (and not running), then
-	 * the next wake-up will properly place the task.
-	 */
-	return p->se.on_rq || task_running(rq, p);
-}
-
-/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2251,11 +2264,11 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		rq = task_rq_lock(p, &flags);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
-		on_rq = p->se.on_rq;
+		on_rq = p->on_rq;
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, p, &flags);
 
 		/*
 		 * If it changed from the expected state, bail out now.
@@ -2330,7 +2343,7 @@ EXPORT_SYMBOL_GPL(kick_process);
 
 #ifdef CONFIG_SMP
 /*
- * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ * ->cpus_allowed is protected by both rq->lock and p->pi_lock
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
@@ -2363,12 +2376,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
+	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -2394,27 +2407,62 @@ static void update_avg(u64 *avg, u64 sample)
 }
 #endif
 
-static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
-				 bool is_sync, bool is_migrate, bool is_local,
-				 unsigned long en_flags)
+static void
+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
+#ifdef CONFIG_SCHEDSTATS
+	struct rq *rq = this_rq();
+
+#ifdef CONFIG_SMP
+	int this_cpu = smp_processor_id();
+
+	if (cpu == this_cpu) {
+		schedstat_inc(rq, ttwu_local);
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
+	} else {
+		struct sched_domain *sd;
+
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+		rcu_read_lock();
+		for_each_domain(this_cpu, sd) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+				schedstat_inc(sd, ttwu_wake_remote);
+				break;
+			}
+		}
+		rcu_read_unlock();
+	}
+#endif /* CONFIG_SMP */
+
+	schedstat_inc(rq, ttwu_count);
 	schedstat_inc(p, se.statistics.nr_wakeups);
-	if (is_sync)
+
+	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
-	if (is_migrate)
+
+	if (cpu != task_cpu(p))
 		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-	if (is_local)
-		schedstat_inc(p, se.statistics.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
 
+#endif /* CONFIG_SCHEDSTATS */
+}
+
+static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
+{
 	activate_task(rq, p, en_flags);
+	p->on_rq = 1;
+
+	/* if a worker is waking up, notify workqueue */
+	if (p->flags & PF_WQ_WORKER)
+		wq_worker_waking_up(p, cpu_of(rq));
 }
 
-static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
-					int wake_flags, bool success)
+/*
+ * Mark the task runnable and perform wakeup-preemption.
+ */
+static void
+ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
-	trace_sched_wakeup(p, success);
+	trace_sched_wakeup(p, true);
 	check_preempt_curr(rq, p, wake_flags);
 
 	p->state = TASK_RUNNING;
@@ -2433,9 +2481,99 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
 		rq->idle_stamp = 0;
 	}
 #endif
-	/* if a worker is waking up, notify workqueue */
-	if ((p->flags & PF_WQ_WORKER) && success)
-		wq_worker_waking_up(p, cpu_of(rq));
+}
+
+static void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
+{
+#ifdef CONFIG_SMP
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible--;
+#endif
+
+	ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
+	ttwu_do_wakeup(rq, p, wake_flags);
+}
+
+/*
+ * Called in case the task @p isn't fully descheduled from its runqueue,
+ * in this case we must do a remote wakeup. Its a 'light' wakeup though,
+ * since all we need to do is flip p->state to TASK_RUNNING, since
+ * the task is still ->on_rq.
+ */
+static int ttwu_remote(struct task_struct *p, int wake_flags)
+{
+	struct rq *rq;
+	int ret = 0;
+
+	rq = __task_rq_lock(p);
+	if (p->on_rq) {
+		ttwu_do_wakeup(rq, p, wake_flags);
+		ret = 1;
+	}
+	__task_rq_unlock(rq);
+
+	return ret;
+}
+
+#ifdef CONFIG_SMP
+static void sched_ttwu_pending(void)
+{
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	raw_spin_lock(&rq->lock);
+
+	while (list) {
+		struct task_struct *p = list;
+		list = list->wake_entry;
+		ttwu_do_activate(rq, p, 0);
+	}
+
+	raw_spin_unlock(&rq->lock);
+}
+
+void scheduler_ipi(void)
+{
+	sched_ttwu_pending();
+}
+
+static void ttwu_queue_remote(struct task_struct *p, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *next = rq->wake_list;
+
+	for (;;) {
+		struct task_struct *old = next;
+
+		p->wake_entry = next;
+		next = cmpxchg(&rq->wake_list, old, p);
+		if (next == old)
+			break;
+	}
+
+	if (!next)
+		smp_send_reschedule(cpu);
+}
+#endif
+
+static void ttwu_queue(struct task_struct *p, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE)
+	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		ttwu_queue_remote(p, cpu);
+		return;
+	}
+#endif
+
+	raw_spin_lock(&rq->lock);
+	ttwu_do_activate(rq, p, 0);
+	raw_spin_unlock(&rq->lock);
 }
 
 /**
@@ -2453,92 +2591,64 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
  * Returns %true if @p was woken up, %false if it was already running
  * or @state didn't match @p's state.
  */
-static int try_to_wake_up(struct task_struct *p, unsigned int state,
-			  int wake_flags)
+static int
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 {
-	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
-	unsigned long en_flags = ENQUEUE_WAKEUP;
-	struct rq *rq;
-
-	this_cpu = get_cpu();
+	int cpu, success = 0;
 
 	smp_wmb();
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	if (!(p->state & state))
 		goto out;
 
-	if (p->se.on_rq)
-		goto out_running;
-
+	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
-	orig_cpu = cpu;
 
-#ifdef CONFIG_SMP
-	if (unlikely(task_running(rq, p)))
-		goto out_activate;
+	if (p->on_rq && ttwu_remote(p, wake_flags))
+		goto stat;
 
+#ifdef CONFIG_SMP
 	/*
-	 * In order to handle concurrent wakeups and release the rq->lock
-	 * we put the task in TASK_WAKING state.
-	 *
-	 * First fix up the nr_uninterruptible count:
+	 * If the owning (remote) cpu is still in the middle of schedule() with
+	 * this task as prev, wait until its done referencing the task.
 	 */
-	if (task_contributes_to_load(p)) {
-		if (likely(cpu_online(orig_cpu)))
-			rq->nr_uninterruptible--;
-		else
-			this_rq()->nr_uninterruptible--;
-	}
-	p->state = TASK_WAKING;
-
-	if (p->sched_class->task_waking) {
-		p->sched_class->task_waking(rq, p);
-		en_flags |= ENQUEUE_WAKING;
+	while (p->on_cpu) {
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+		/*
+		 * If called from interrupt context we could have landed in the
+		 * middle of schedule(), in this case we should take care not
+		 * to spin on ->on_cpu if p is current, since that would
+		 * deadlock.
+		 */
+		if (p == current) {
+			ttwu_queue(p, cpu);
+			goto stat;
+		}
+#endif
+		cpu_relax();
 	}
-
-	cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu)
-		set_task_cpu(p, cpu);
-	__task_rq_unlock(rq);
-
-	rq = cpu_rq(cpu);
-	raw_spin_lock(&rq->lock);
-
 	/*
-	 * We migrated the task without holding either rq->lock, however
-	 * since the task is not on the task list itself, nobody else
-	 * will try and migrate the task, hence the rq should match the
-	 * cpu we just moved it to.
+	 * Pairs with the smp_wmb() in finish_lock_switch().
 	 */
-	WARN_ON(task_cpu(p) != cpu);
-	WARN_ON(p->state != TASK_WAKING);
+	smp_rmb();
 
-#ifdef CONFIG_SCHEDSTATS
-	schedstat_inc(rq, ttwu_count);
-	if (cpu == this_cpu)
-		schedstat_inc(rq, ttwu_local);
-	else {
-		struct sched_domain *sd;
-		for_each_domain(this_cpu, sd) {
-			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				schedstat_inc(sd, ttwu_wake_remote);
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_SCHEDSTATS */
+	p->sched_contributes_to_load = !!task_contributes_to_load(p);
+	p->state = TASK_WAKING;
+
+	if (p->sched_class->task_waking)
+		p->sched_class->task_waking(p);
 
-out_activate:
+	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	if (task_cpu(p) != cpu)
+		set_task_cpu(p, cpu);
 #endif /* CONFIG_SMP */
-	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
-		      cpu == this_cpu, en_flags);
-	success = 1;
-out_running:
-	ttwu_post_activation(p, rq, wake_flags, success);
+
+	ttwu_queue(p, cpu);
+stat:
+	ttwu_stat(p, cpu, wake_flags);
 out:
-	task_rq_unlock(rq, &flags);
-	put_cpu();
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 	return success;
 }
@@ -2547,31 +2657,34 @@ out:
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
  *
- * Put @p on the run-queue if it's not already there.  The caller must
+ * Put @p on the run-queue if it's not already there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.  this_rq() stays locked over invocation.
+ * the current task.
  */
 static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
-	bool success = false;
 
 	BUG_ON(rq != this_rq());
 	BUG_ON(p == current);
 	lockdep_assert_held(&rq->lock);
 
+	if (!raw_spin_trylock(&p->pi_lock)) {
+		raw_spin_unlock(&rq->lock);
+		raw_spin_lock(&p->pi_lock);
+		raw_spin_lock(&rq->lock);
+	}
+
 	if (!(p->state & TASK_NORMAL))
-		return;
+		goto out;
 
-	if (!p->se.on_rq) {
-		if (likely(!task_running(rq, p))) {
-			schedstat_inc(rq, ttwu_count);
-			schedstat_inc(rq, ttwu_local);
-		}
-		ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
-		success = true;
-	}
-	ttwu_post_activation(p, rq, 0, success);
+	if (!p->on_rq)
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+
+	ttwu_do_wakeup(rq, p, 0);
+	ttwu_stat(p, smp_processor_id(), 0);
+out:
+	raw_spin_unlock(&p->pi_lock);
 }
 
 /**
@@ -2604,19 +2717,21 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  */
 static void __sched_fork(struct task_struct *p)
 {
+	p->on_rq			= 0;
+
+	p->se.on_rq			= 0;
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
+	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
-	p->se.on_rq = 0;
-	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -2626,8 +2741,9 @@ static void __sched_fork(struct task_struct *p)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p, int clone_flags)
+void sched_fork(struct task_struct *p)
 {
+	unsigned long flags;
 	int cpu = get_cpu();
 
 	__sched_fork(p);
@@ -2678,16 +2794,16 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	 *
 	 * Silence PROVE_RCU.
 	 */
-	rcu_read_lock();
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	set_task_cpu(p, cpu);
-	rcu_read_unlock();
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	p->oncpu = 0;
+#if defined(CONFIG_SMP)
+	p->on_cpu = 0;
 #endif
 #ifdef CONFIG_PREEMPT
 	/* Want to start with kernel preemption disabled. */
@@ -2707,41 +2823,31 @@ void sched_fork(struct task_struct *p, int clone_flags)
  * that must be done for every newly created context, then puts the task
  * on the runqueue and wakes it.
  */
-void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
+void wake_up_new_task(struct task_struct *p)
 {
 	unsigned long flags;
 	struct rq *rq;
-	int cpu __maybe_unused = get_cpu();
 
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 #ifdef CONFIG_SMP
-	rq = task_rq_lock(p, &flags);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
-	 *
-	 * We set TASK_WAKING so that select_task_rq() can drop rq->lock
-	 * without people poking at ->cpus_allowed.
 	 */
-	cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
-	set_task_cpu(p, cpu);
-
-	p->state = TASK_RUNNING;
-	task_rq_unlock(rq, &flags);
+	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
 #endif
 
-	rq = task_rq_lock(p, &flags);
+	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
-	trace_sched_wakeup_new(p, 1);
+	p->on_rq = 1;
+	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
 		p->sched_class->task_woken(rq, p);
 #endif
-	task_rq_unlock(rq, &flags);
-	put_cpu();
+	task_rq_unlock(rq, p, &flags);
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -3450,27 +3556,22 @@ void sched_exec(void)
 {
 	struct task_struct *p = current;
 	unsigned long flags;
-	struct rq *rq;
 	int dest_cpu;
 
-	rq = task_rq_lock(p, &flags);
-	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
-	/*
-	 * select_task_rq() can race against ->cpus_allowed
-	 */
-	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
+	if (likely(cpu_active(dest_cpu))) {
 		struct migration_arg arg = { p, dest_cpu };
 
-		task_rq_unlock(rq, &flags);
-		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
 		return;
 	}
 unlock:
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 }
 
 #endif
@@ -3507,7 +3608,7 @@ unsigned long long task_delta_exec(struct task_struct *p)
 
 	rq = task_rq_lock(p, &flags);
 	ns = do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -3525,7 +3626,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 
 	rq = task_rq_lock(p, &flags);
 	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -3549,7 +3650,7 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p)
 	rq = task_rq_lock(p, &flags);
 	thread_group_cputime(p, &totals);
 	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -3903,9 +4004,6 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
- *
- * It also gets called by the fork code, when changing the parent's
- * timeslices.
  */
 void scheduler_tick(void)
 {
@@ -4025,17 +4123,11 @@ static inline void schedule_debug(struct task_struct *prev)
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
 	schedstat_inc(this_rq(), sched_count);
-#ifdef CONFIG_SCHEDSTATS
-	if (unlikely(prev->lock_depth >= 0)) {
-		schedstat_inc(this_rq(), rq_sched_info.bkl_count);
-		schedstat_inc(prev, sched_info.bkl_count);
-	}
-#endif
 }
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->se.on_rq)
+	if (prev->on_rq || rq->skip_clock_update < 0)
 		update_rq_clock(rq);
 	prev->sched_class->put_prev_task(rq, prev);
 }
@@ -4097,11 +4189,13 @@ need_resched:
 		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
+			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			prev->on_rq = 0;
+
 			/*
-			 * If a worker is going to sleep, notify and
-			 * ask workqueue whether it wants to wake up a
-			 * task to maintain concurrency.  If so, wake
-			 * up the task.
+			 * If a worker went to sleep, notify and ask workqueue
+			 * whether it wants to wake up a task to maintain
+			 * concurrency.
 			 */
 			if (prev->flags & PF_WQ_WORKER) {
 				struct task_struct *to_wakeup;
@@ -4110,11 +4204,10 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 
 			/*
-			 * If we are going to sleep and we have plugged IO queued, make
-			 * sure to submit it to avoid deadlocks.
+			 * If we are going to sleep and we have plugged IO
+			 * queued, make sure to submit it to avoid deadlocks.
 			 */
 			if (blk_needs_flush_plug(prev)) {
 				raw_spin_unlock(&rq->lock);
@@ -4161,70 +4254,53 @@ need_resched:
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
- */
-int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
-{
-	unsigned int cpu;
-	struct rq *rq;
 
-	if (!sched_feat(OWNER_SPIN))
-		return 0;
+static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+{
+	bool ret = false;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * Need to access the cpu field knowing that
-	 * DEBUG_PAGEALLOC could have unmapped it if
-	 * the mutex owner just released it and exited.
-	 */
-	if (probe_kernel_address(&owner->cpu, cpu))
-		return 0;
-#else
-	cpu = owner->cpu;
-#endif
+	rcu_read_lock();
+	if (lock->owner != owner)
+		goto fail;
 
 	/*
-	 * Even if the access succeeded (likely case),
-	 * the cpu field may no longer be valid.
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * lock->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
 	 */
-	if (cpu >= nr_cpumask_bits)
-		return 0;
+	barrier();
 
-	/*
-	 * We need to validate that we can do a
-	 * get_cpu() and that we have the percpu area.
-	 */
-	if (!cpu_online(cpu))
-		return 0;
+	ret = owner->on_cpu;
+fail:
+	rcu_read_unlock();
 
-	rq = cpu_rq(cpu);
+	return ret;
+}
 
-	for (;;) {
-		/*
-		 * Owner changed, break to re-assess state.
-		 */
-		if (lock->owner != owner) {
-			/*
-			 * If the lock has switched to a different owner,
-			 * we likely have heavy contention. Return 0 to quit
-			 * optimistic spinning and not contend further:
-			 */
-			if (lock->owner)
-				return 0;
-			break;
-		}
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+{
+	if (!sched_feat(OWNER_SPIN))
+		return 0;
 
-		/*
-		 * Is that owner really running on that cpu?
-		 */
-		if (task_thread_info(rq->curr) != owner || need_resched())
+	while (owner_running(lock, owner)) {
+		if (need_resched())
 			return 0;
 
 		arch_mutex_cpu_relax();
 	}
 
+	/*
+	 * If the owner changed to another task there is likely
+	 * heavy contention, stop spinning.
+	 */
+	if (lock->owner)
+		return 0;
+
 	return 1;
 }
 #endif
@@ -4684,19 +4760,18 @@ EXPORT_SYMBOL(sleep_on_timeout);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	unsigned long flags;
 	int oldprio, on_rq, running;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
-	rq = task_rq_lock(p, &flags);
+	rq = __task_rq_lock(p);
 
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		dequeue_task(rq, p, 0);
@@ -4716,7 +4791,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
-	task_rq_unlock(rq, &flags);
+	__task_rq_unlock(rq);
 }
 
 #endif
@@ -4744,7 +4819,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
 
@@ -4764,7 +4839,7 @@ void set_user_nice(struct task_struct *p, long nice)
 			resched_task(rq->curr);
 	}
 out_unlock:
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 }
 EXPORT_SYMBOL(set_user_nice);
 
@@ -4878,8 +4953,6 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 static void
 __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 {
-	BUG_ON(p->se.on_rq);
-
 	p->policy = policy;
 	p->rt_priority = prio;
 	p->normal_prio = normal_prio(p);
@@ -4994,20 +5067,17 @@ recheck:
 	/*
 	 * make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
-	 */
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	/*
+	 *
 	 * To be able to change p->policy safely, the appropriate
 	 * runqueue lock must be held.
 	 */
-	rq = __task_rq_lock(p);
+	rq = task_rq_lock(p, &flags);
 
 	/*
 	 * Changing the policy of the stop threads its a very bad idea
 	 */
 	if (p == rq->stop) {
-		__task_rq_unlock(rq);
-		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		task_rq_unlock(rq, p, &flags);
 		return -EINVAL;
 	}
 
@@ -5031,8 +5101,7 @@ recheck:
 		if (rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
-			__task_rq_unlock(rq);
-			raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+			task_rq_unlock(rq, p, &flags);
 			return -EPERM;
 		}
 	}
@@ -5041,11 +5110,10 @@ recheck:
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
-		__task_rq_unlock(rq);
-		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		task_rq_unlock(rq, p, &flags);
 		goto recheck;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		deactivate_task(rq, p, 0);
@@ -5064,8 +5132,7 @@ recheck:
 		activate_task(rq, p, 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
-	__task_rq_unlock(rq);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+	task_rq_unlock(rq, p, &flags);
 
 	rt_mutex_adjust_pi(p);
 
@@ -5316,7 +5383,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
 	unsigned long flags;
-	struct rq *rq;
 	int retval;
 
 	get_online_cpus();
@@ -5331,9 +5397,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 	if (retval)
 		goto out_unlock;
 
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
 	rcu_read_unlock();
@@ -5658,7 +5724,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 
 	rq = task_rq_lock(p, &flags);
 	time_slice = p->sched_class->get_rr_interval(rq, p);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	rcu_read_unlock();
 	jiffies_to_timespec(time_slice, &t);
@@ -5776,17 +5842,14 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	idle->oncpu = 1;
+#if defined(CONFIG_SMP)
+	idle->on_cpu = 1;
 #endif
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-#if defined(CONFIG_PREEMPT)
-	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
-#else
 	task_thread_info(idle)->preempt_count = 0;
-#endif
+
 	/*
 	 * The idle tasks have their own, simple scheduling class:
 	 */
@@ -5881,26 +5944,17 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	unsigned int dest_cpu;
 	int ret = 0;
 
-	/*
-	 * Serialize against TASK_WAKING so that ttwu() and wunt() can
-	 * drop the rq->lock and still rely on ->cpus_allowed.
-	 */
-again:
-	while (task_is_waking(p))
-		cpu_relax();
 	rq = task_rq_lock(p, &flags);
-	if (task_is_waking(p)) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
+
+	if (cpumask_equal(&p->cpus_allowed, new_mask))
+		goto out;
 
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
-		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -5917,16 +5971,16 @@ again:
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (migrate_task(p, rq)) {
+	if (p->on_rq) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, p, &flags);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
 	}
 out:
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ret;
 }
@@ -5954,6 +6008,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	rq_src = cpu_rq(src_cpu);
 	rq_dest = cpu_rq(dest_cpu);
 
+	raw_spin_lock(&p->pi_lock);
 	double_rq_lock(rq_src, rq_dest);
 	/* Already moved. */
 	if (task_cpu(p) != src_cpu)
@@ -5966,7 +6021,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
-	if (p->se.on_rq) {
+	if (p->on_rq) {
 		deactivate_task(rq_src, p, 0);
 		set_task_cpu(p, dest_cpu);
 		activate_task(rq_dest, p, 0);
@@ -5976,6 +6031,7 @@ done:
 	ret = 1;
 fail:
 	double_rq_unlock(rq_src, rq_dest);
+	raw_spin_unlock(&p->pi_lock);
 	return ret;
 }
 
@@ -6316,6 +6372,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DYING:
+		sched_ttwu_pending();
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
@@ -6394,6 +6451,8 @@ early_initcall(migration_init);
 
 #ifdef CONFIG_SMP
 
+static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
+
 #ifdef CONFIG_SCHED_DEBUG
 
 static __read_mostly int sched_domain_debug_enabled;
@@ -6489,7 +6548,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 static void sched_domain_debug(struct sched_domain *sd, int cpu)
 {
-	cpumask_var_t groupmask;
 	int level = 0;
 
 	if (!sched_domain_debug_enabled)
@@ -6502,20 +6560,14 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 
 	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
 
-	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
-		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
-		return;
-	}
-
 	for (;;) {
-		if (sched_domain_debug_one(sd, cpu, level, groupmask))
+		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
 			break;
 		level++;
 		sd = sd->parent;
 		if (!sd)
 			break;
 	}
-	free_cpumask_var(groupmask);
 }
 #else /* !CONFIG_SCHED_DEBUG */
 # define sched_domain_debug(sd, cpu) do { } while (0)
@@ -6572,12 +6624,11 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
-static void free_rootdomain(struct root_domain *rd)
+static void free_rootdomain(struct rcu_head *rcu)
 {
-	synchronize_sched();
+	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
-
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -6618,7 +6669,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	if (old_rd)
-		free_rootdomain(old_rd);
+		call_rcu_sched(&old_rd->rcu, free_rootdomain);
 }
 
 static int init_rootdomain(struct root_domain *rd)
@@ -6669,6 +6720,25 @@ static struct root_domain *alloc_rootdomain(void)
 	return rd;
 }
 
+static void free_sched_domain(struct rcu_head *rcu)
+{
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+	if (atomic_dec_and_test(&sd->groups->ref))
+		kfree(sd->groups);
+	kfree(sd);
+}
+
+static void destroy_sched_domain(struct sched_domain *sd, int cpu)
+{
+	call_rcu(&sd->rcu, free_sched_domain);
+}
+
+static void destroy_sched_domains(struct sched_domain *sd, int cpu)
+{
+	for (; sd; sd = sd->parent)
+		destroy_sched_domain(sd, cpu);
+}
+
 /*
  * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
  * hold the hotplug lock.
@@ -6679,9 +6749,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
 
-	for (tmp = sd; tmp; tmp = tmp->parent)
-		tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
-
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
 		struct sched_domain *parent = tmp->parent;
@@ -6692,12 +6759,15 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			tmp->parent = parent->parent;
 			if (parent->parent)
 				parent->parent->child = tmp;
+			destroy_sched_domain(parent, cpu);
 		} else
 			tmp = tmp->parent;
 	}
 
 	if (sd && sd_degenerate(sd)) {
+		tmp = sd;
 		sd = sd->parent;
+		destroy_sched_domain(tmp, cpu);
 		if (sd)
 			sd->child = NULL;
 	}
@@ -6705,7 +6775,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);
+	tmp = rq->sd;
 	rcu_assign_pointer(rq->sd, sd);
+	destroy_sched_domains(tmp, cpu);
 }
 
 /* cpus with isolated domains */
@@ -6721,56 +6793,6 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-/*
- * init_sched_build_groups takes the cpumask we wish to span, and a pointer
- * to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
- * (due to the fact that we keep track of groups covered with a struct cpumask).
- *
- * init_sched_build_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_power to 0.
- */
-static void
-init_sched_build_groups(const struct cpumask *span,
-			const struct cpumask *cpu_map,
-			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
-					struct sched_group **sg,
-					struct cpumask *tmpmask),
-			struct cpumask *covered, struct cpumask *tmpmask)
-{
-	struct sched_group *first = NULL, *last = NULL;
-	int i;
-
-	cpumask_clear(covered);
-
-	for_each_cpu(i, span) {
-		struct sched_group *sg;
-		int group = group_fn(i, cpu_map, &sg, tmpmask);
-		int j;
-
-		if (cpumask_test_cpu(i, covered))
-			continue;
-
-		cpumask_clear(sched_group_cpus(sg));
-		sg->cpu_power = 0;
-
-		for_each_cpu(j, span) {
-			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
-		if (!first)
-			first = sg;
-		if (last)
-			last->next = sg;
-		last = sg;
-	}
-	last->next = first;
-}
-
 #define SD_NODES_PER_DOMAIN 16
 
 #ifdef CONFIG_NUMA
@@ -6787,7 +6809,7 @@ init_sched_build_groups(const struct cpumask *span,
  */
 static int find_next_best_node(int node, nodemask_t *used_nodes)
 {
-	int i, n, val, min_val, best_node = 0;
+	int i, n, val, min_val, best_node = -1;
 
 	min_val = INT_MAX;
 
@@ -6811,7 +6833,8 @@ static int find_next_best_node(int node, nodemask_t *used_nodes)
 		}
 	}
 
-	node_set(best_node, *used_nodes);
+	if (best_node != -1)
+		node_set(best_node, *used_nodes);
 	return best_node;
 }
 
@@ -6837,315 +6860,130 @@ static void sched_domain_node_span(int node, struct cpumask *span)
 
 	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
 		int next_node = find_next_best_node(node, &used_nodes);
-
+		if (next_node < 0)
+			break;
 		cpumask_or(span, span, cpumask_of_node(next_node));
 	}
 }
+
+static const struct cpumask *cpu_node_mask(int cpu)
+{
+	lockdep_assert_held(&sched_domains_mutex);
+
+	sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask);
+
+	return sched_domains_tmpmask;
+}
+
+static const struct cpumask *cpu_allnodes_mask(int cpu)
+{
+	return cpu_possible_mask;
+}
 #endif /* CONFIG_NUMA */
 
-int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+static const struct cpumask *cpu_cpu_mask(int cpu)
+{
+	return cpumask_of_node(cpu_to_node(cpu));
+}
 
-/*
- * The cpus mask in sched_group and sched_domain hangs off the end.
- *
- * ( See the the comments in include/linux/sched.h:struct sched_group
- *   and struct sched_domain. )
- */
-struct static_sched_group {
-	struct sched_group sg;
-	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
-};
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
-struct static_sched_domain {
-	struct sched_domain sd;
-	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_group **__percpu sg;
 };
 
 struct s_data {
-#ifdef CONFIG_NUMA
-	int			sd_allnodes;
-	cpumask_var_t		domainspan;
-	cpumask_var_t		covered;
-	cpumask_var_t		notcovered;
-#endif
-	cpumask_var_t		nodemask;
-	cpumask_var_t		this_sibling_map;
-	cpumask_var_t		this_core_map;
-	cpumask_var_t		this_book_map;
-	cpumask_var_t		send_covered;
-	cpumask_var_t		tmpmask;
-	struct sched_group	**sched_group_nodes;
+	struct sched_domain ** __percpu sd;
 	struct root_domain	*rd;
 };
 
 enum s_alloc {
-	sa_sched_groups = 0,
 	sa_rootdomain,
-	sa_tmpmask,
-	sa_send_covered,
-	sa_this_book_map,
-	sa_this_core_map,
-	sa_this_sibling_map,
-	sa_nodemask,
-	sa_sched_group_nodes,
-#ifdef CONFIG_NUMA
-	sa_notcovered,
-	sa_covered,
-	sa_domainspan,
-#endif
+	sa_sd,
+	sa_sd_storage,
 	sa_none,
 };
 
-/*
- * SMT sched-domains:
- */
-#ifdef CONFIG_SCHED_SMT
-static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
+struct sched_domain_topology_level;
 
-static int
-cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
-		 struct sched_group **sg, struct cpumask *unused)
-{
-	if (sg)
-		*sg = &per_cpu(sched_groups, cpu).sg;
-	return cpu;
-}
-#endif /* CONFIG_SCHED_SMT */
+typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 
-/*
- * multi-core sched-domains:
- */
-#ifdef CONFIG_SCHED_MC
-static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-
-static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
-{
-	int group;
-#ifdef CONFIG_SCHED_SMT
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#else
-	group = cpu;
-#endif
-	if (sg)
-		*sg = &per_cpu(sched_group_core, group).sg;
-	return group;
-}
-#endif /* CONFIG_SCHED_MC */
+struct sched_domain_topology_level {
+	sched_domain_init_f init;
+	sched_domain_mask_f mask;
+	struct sd_data      data;
+};
 
 /*
- * book sched-domains:
+ * Assumes the sched_domain tree is fully constructed
  */
-#ifdef CONFIG_SCHED_BOOK
-static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
-
-static int
-cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
+static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 {
-	int group = cpu;
-#ifdef CONFIG_SCHED_MC
-	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#endif
-	if (sg)
-		*sg = &per_cpu(sched_group_book, group).sg;
-	return group;
-}
-#endif /* CONFIG_SCHED_BOOK */
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	struct sched_domain *child = sd->child;
 
-static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
+	if (child)
+		cpu = cpumask_first(sched_domain_span(child));
 
-static int
-cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *mask)
-{
-	int group;
-#ifdef CONFIG_SCHED_BOOK
-	cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_MC)
-	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
-	group = cpumask_first(mask);
-#else
-	group = cpu;
-#endif
 	if (sg)
-		*sg = &per_cpu(sched_group_phys, group).sg;
-	return group;
+		*sg = *per_cpu_ptr(sdd->sg, cpu);
+
+	return cpu;
 }
 
-#ifdef CONFIG_NUMA
 /*
- * The init_sched_build_groups can't handle what we want to do with node
- * groups, so roll our own. Now each node has its own list of groups which
- * gets dynamically allocated.
+ * build_sched_groups takes the cpumask we wish to span, and a pointer
+ * to a function which identifies what group(along with sched group) a CPU
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
+ *
+ * build_sched_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
  */
-static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
-static struct sched_group ***sched_group_nodes_bycpu;
-
-static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
-
-static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
-				 struct sched_group **sg,
-				 struct cpumask *nodemask)
-{
-	int group;
-
-	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
-	group = cpumask_first(nodemask);
-
-	if (sg)
-		*sg = &per_cpu(sched_group_allnodes, group).sg;
-	return group;
-}
-
-static void init_numa_sched_groups_power(struct sched_group *group_head)
-{
-	struct sched_group *sg = group_head;
-	int j;
-
-	if (!sg)
-		return;
-	do {
-		for_each_cpu(j, sched_group_cpus(sg)) {
-			struct sched_domain *sd;
-
-			sd = &per_cpu(phys_domains, j).sd;
-			if (j != group_first_cpu(sd->groups)) {
-				/*
-				 * Only add "power" once for each
-				 * physical package.
-				 */
-				continue;
-			}
-
-			sg->cpu_power += sd->groups->cpu_power;
-		}
-		sg = sg->next;
-	} while (sg != group_head);
-}
-
-static int build_numa_sched_groups(struct s_data *d,
-				   const struct cpumask *cpu_map, int num)
+static void
+build_sched_groups(struct sched_domain *sd)
 {
-	struct sched_domain *sd;
-	struct sched_group *sg, *prev;
-	int n, j;
-
-	cpumask_clear(d->covered);
-	cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
-	if (cpumask_empty(d->nodemask)) {
-		d->sched_group_nodes[num] = NULL;
-		goto out;
-	}
-
-	sched_domain_node_span(num, d->domainspan);
-	cpumask_and(d->domainspan, d->domainspan, cpu_map);
-
-	sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-			  GFP_KERNEL, num);
-	if (!sg) {
-		printk(KERN_WARNING "Can not alloc domain group for node %d\n",
-		       num);
-		return -ENOMEM;
-	}
-	d->sched_group_nodes[num] = sg;
-
-	for_each_cpu(j, d->nodemask) {
-		sd = &per_cpu(node_domains, j).sd;
-		sd->groups = sg;
-	}
-
-	sg->cpu_power = 0;
-	cpumask_copy(sched_group_cpus(sg), d->nodemask);
-	sg->next = sg;
-	cpumask_or(d->covered, d->covered, d->nodemask);
+	struct sched_group *first = NULL, *last = NULL;
+	struct sd_data *sdd = sd->private;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered;
+	int i;
 
-	prev = sg;
-	for (j = 0; j < nr_node_ids; j++) {
-		n = (num + j) % nr_node_ids;
-		cpumask_complement(d->notcovered, d->covered);
-		cpumask_and(d->tmpmask, d->notcovered, cpu_map);
-		cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
-		if (cpumask_empty(d->tmpmask))
-			break;
-		cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
-		if (cpumask_empty(d->tmpmask))
-			continue;
-		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				  GFP_KERNEL, num);
-		if (!sg) {
-			printk(KERN_WARNING
-			       "Can not alloc domain group for node %d\n", j);
-			return -ENOMEM;
-		}
-		sg->cpu_power = 0;
-		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
-		sg->next = prev->next;
-		cpumask_or(d->covered, d->covered, d->tmpmask);
-		prev->next = sg;
-		prev = sg;
-	}
-out:
-	return 0;
-}
-#endif /* CONFIG_NUMA */
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
 
-#ifdef CONFIG_NUMA
-/* Free memory allocated for various sched_group structures */
-static void free_sched_groups(const struct cpumask *cpu_map,
-			      struct cpumask *nodemask)
-{
-	int cpu, i;
+	cpumask_clear(covered);
 
-	for_each_cpu(cpu, cpu_map) {
-		struct sched_group **sched_group_nodes
-			= sched_group_nodes_bycpu[cpu];
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group = get_group(i, sdd, &sg);
+		int j;
 
-		if (!sched_group_nodes)
+		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		for (i = 0; i < nr_node_ids; i++) {
-			struct sched_group *oldsg, *sg = sched_group_nodes[i];
+		cpumask_clear(sched_group_cpus(sg));
+		sg->cpu_power = 0;
 
-			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
-			if (cpumask_empty(nodemask))
+		for_each_cpu(j, span) {
+			if (get_group(j, sdd, NULL) != group)
 				continue;
 
-			if (sg == NULL)
-				continue;
-			sg = sg->next;
-next_sg:
-			oldsg = sg;
-			sg = sg->next;
-			kfree(oldsg);
-			if (oldsg != sched_group_nodes[i])
-				goto next_sg;
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
 		}
-		kfree(sched_group_nodes);
-		sched_group_nodes_bycpu[cpu] = NULL;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
 	}
+	last->next = first;
 }
-#else /* !CONFIG_NUMA */
-static void free_sched_groups(const struct cpumask *cpu_map,
-			      struct cpumask *nodemask)
-{
-}
-#endif /* CONFIG_NUMA */
 
 /*
  * Initialize sched groups cpu_power.
@@ -7159,11 +6997,6 @@ static void free_sched_groups(const struct cpumask *cpu_map,
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
-	struct sched_domain *child;
-	struct sched_group *group;
-	long power;
-	int weight;
-
 	WARN_ON(!sd || !sd->groups);
 
 	if (cpu != group_first_cpu(sd->groups))
@@ -7171,36 +7004,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
 
-	child = sd->child;
-
-	sd->groups->cpu_power = 0;
-
-	if (!child) {
-		power = SCHED_LOAD_SCALE;
-		weight = cpumask_weight(sched_domain_span(sd));
-		/*
-		 * SMT siblings share the power of a single core.
-		 * Usually multiple threads get a better yield out of
-		 * that one core than a single thread would have,
-		 * reflect that in sd->smt_gain.
-		 */
-		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-			power *= sd->smt_gain;
-			power /= weight;
-			power >>= SCHED_LOAD_SHIFT;
-		}
-		sd->groups->cpu_power += power;
-		return;
-	}
-
-	/*
-	 * Add cpu_power of each child group to this groups cpu_power.
-	 */
-	group = child->groups;
-	do {
-		sd->groups->cpu_power += group->cpu_power;
-		group = group->next;
-	} while (group != child->groups);
+	update_group_power(sd, cpu);
 }
 
 /*
@@ -7214,15 +7018,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 # define SD_INIT_NAME(sd, type)		do { } while (0)
 #endif
 
-#define	SD_INIT(sd, type)	sd_init_##type(sd)
-
-#define SD_INIT_FUNC(type)	\
-static noinline void sd_init_##type(struct sched_domain *sd)	\
-{								\
-	memset(sd, 0, sizeof(*sd));				\
-	*sd = SD_##type##_INIT;					\
-	sd->level = SD_LV_##type;				\
-	SD_INIT_NAME(sd, type);					\
+#define SD_INIT_FUNC(type)						\
+static noinline struct sched_domain *					\
+sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
+{									\
+	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
+	*sd = SD_##type##_INIT;						\
+	SD_INIT_NAME(sd, type);						\
+	sd->private = &tl->data;					\
+	return sd;							\
 }
 
 SD_INIT_FUNC(CPU)
@@ -7241,13 +7045,14 @@ SD_INIT_FUNC(CPU)
 #endif
 
 static int default_relax_domain_level = -1;
+int sched_domain_level_max;
 
 static int __init setup_relax_domain_level(char *str)
 {
 	unsigned long val;
 
 	val = simple_strtoul(str, NULL, 0);
-	if (val < SD_LV_MAX)
+	if (val < sched_domain_level_max)
 		default_relax_domain_level = val;
 
 	return 1;
@@ -7275,37 +7080,20 @@ static void set_domain_attribute(struct sched_domain *sd,
 	}
 }
 
+static void __sdt_free(const struct cpumask *cpu_map);
+static int __sdt_alloc(const struct cpumask *cpu_map);
+
 static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 				 const struct cpumask *cpu_map)
 {
 	switch (what) {
-	case sa_sched_groups:
-		free_sched_groups(cpu_map, d->tmpmask); /* fall through */
-		d->sched_group_nodes = NULL;
 	case sa_rootdomain:
-		free_rootdomain(d->rd); /* fall through */
-	case sa_tmpmask:
-		free_cpumask_var(d->tmpmask); /* fall through */
-	case sa_send_covered:
-		free_cpumask_var(d->send_covered); /* fall through */
-	case sa_this_book_map:
-		free_cpumask_var(d->this_book_map); /* fall through */
-	case sa_this_core_map:
-		free_cpumask_var(d->this_core_map); /* fall through */
-	case sa_this_sibling_map:
-		free_cpumask_var(d->this_sibling_map); /* fall through */
-	case sa_nodemask:
-		free_cpumask_var(d->nodemask); /* fall through */
-	case sa_sched_group_nodes:
-#ifdef CONFIG_NUMA
-		kfree(d->sched_group_nodes); /* fall through */
-	case sa_notcovered:
-		free_cpumask_var(d->notcovered); /* fall through */
-	case sa_covered:
-		free_cpumask_var(d->covered); /* fall through */
-	case sa_domainspan:
-		free_cpumask_var(d->domainspan); /* fall through */
-#endif
+		if (!atomic_read(&d->rd->refcount))
+			free_rootdomain(&d->rd->rcu); /* fall through */
+	case sa_sd:
+		free_percpu(d->sd); /* fall through */
+	case sa_sd_storage:
+		__sdt_free(cpu_map); /* fall through */
 	case sa_none:
 		break;
 	}
@@ -7314,308 +7102,212 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
 						   const struct cpumask *cpu_map)
 {
-#ifdef CONFIG_NUMA
-	if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
-		return sa_none;
-	if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
-		return sa_domainspan;
-	if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
-		return sa_covered;
-	/* Allocate the per-node list of sched groups */
-	d->sched_group_nodes = kcalloc(nr_node_ids,
-				      sizeof(struct sched_group *), GFP_KERNEL);
-	if (!d->sched_group_nodes) {
-		printk(KERN_WARNING "Can not alloc sched group node list\n");
-		return sa_notcovered;
-	}
-	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
-#endif
-	if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
-		return sa_sched_group_nodes;
-	if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
-		return sa_nodemask;
-	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
-		return sa_this_sibling_map;
-	if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
-		return sa_this_core_map;
-	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
-		return sa_this_book_map;
-	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
-		return sa_send_covered;
+	memset(d, 0, sizeof(*d));
+
+	if (__sdt_alloc(cpu_map))
+		return sa_sd_storage;
+	d->sd = alloc_percpu(struct sched_domain *);
+	if (!d->sd)
+		return sa_sd_storage;
 	d->rd = alloc_rootdomain();
-	if (!d->rd) {
-		printk(KERN_WARNING "Cannot alloc root domain\n");
-		return sa_tmpmask;
-	}
+	if (!d->rd)
+		return sa_sd;
 	return sa_rootdomain;
 }
 
-static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+/*
+ * NULL the sd_data elements we've used to build the sched_domain and
+ * sched_group structure so that the subsequent __free_domain_allocs()
+ * will not free the data we're using.
+ */
+static void claim_allocations(int cpu, struct sched_domain *sd)
 {
-	struct sched_domain *sd = NULL;
-#ifdef CONFIG_NUMA
-	struct sched_domain *parent;
-
-	d->sd_allnodes = 0;
-	if (cpumask_weight(cpu_map) >
-	    SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
-		sd = &per_cpu(allnodes_domains, i).sd;
-		SD_INIT(sd, ALLNODES);
-		set_domain_attribute(sd, attr);
-		cpumask_copy(sched_domain_span(sd), cpu_map);
-		cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
-		d->sd_allnodes = 1;
-	}
-	parent = sd;
-
-	sd = &per_cpu(node_domains, i).sd;
-	SD_INIT(sd, NODE);
-	set_domain_attribute(sd, attr);
-	sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
-	sd->parent = parent;
-	if (parent)
-		parent->child = sd;
-	cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
-#endif
-	return sd;
-}
+	struct sd_data *sdd = sd->private;
+	struct sched_group *sg = sd->groups;
 
-static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd;
-	sd = &per_cpu(phys_domains, i).sd;
-	SD_INIT(sd, CPU);
-	set_domain_attribute(sd, attr);
-	cpumask_copy(sched_domain_span(sd), d->nodemask);
-	sd->parent = parent;
-	if (parent)
-		parent->child = sd;
-	cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
-	return sd;
-}
+	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
+	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
-static struct sched_domain *__build_book_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_BOOK
-	sd = &per_cpu(book_domains, i).sd;
-	SD_INIT(sd, BOOK);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
-#endif
-	return sd;
+	if (cpu == cpumask_first(sched_group_cpus(sg))) {
+		WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg);
+		*per_cpu_ptr(sdd->sg, cpu) = NULL;
+	}
 }
 
-static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *cpu_smt_mask(int cpu)
 {
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_MC
-	sd = &per_cpu(core_domains, i).sd;
-	SD_INIT(sd, MC);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
-#endif
-	return sd;
+	return topology_thread_cpumask(cpu);
 }
-
-static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
-	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-	struct sched_domain *parent, int i)
-{
-	struct sched_domain *sd = parent;
-#ifdef CONFIG_SCHED_SMT
-	sd = &per_cpu(cpu_domains, i).sd;
-	SD_INIT(sd, SIBLING);
-	set_domain_attribute(sd, attr);
-	cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
-	sd->parent = parent;
-	parent->child = sd;
-	cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
 #endif
-	return sd;
-}
 
-static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
-			       const struct cpumask *cpu_map, int cpu)
-{
-	switch (l) {
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	case SD_LV_SIBLING: /* set up CPU (sibling) groups */
-		cpumask_and(d->this_sibling_map, cpu_map,
-			    topology_thread_cpumask(cpu));
-		if (cpu == cpumask_first(d->this_sibling_map))
-			init_sched_build_groups(d->this_sibling_map, cpu_map,
-						&cpu_to_cpu_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_SIBLING, cpu_smt_mask, },
 #endif
 #ifdef CONFIG_SCHED_MC
-	case SD_LV_MC: /* set up multi-core groups */
-		cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
-		if (cpu == cpumask_first(d->this_core_map))
-			init_sched_build_groups(d->this_core_map, cpu_map,
-						&cpu_to_core_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_MC, cpu_coregroup_mask, },
 #endif
 #ifdef CONFIG_SCHED_BOOK
-	case SD_LV_BOOK: /* set up book groups */
-		cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
-		if (cpu == cpumask_first(d->this_book_map))
-			init_sched_build_groups(d->this_book_map, cpu_map,
-						&cpu_to_book_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_BOOK, cpu_book_mask, },
 #endif
-	case SD_LV_CPU: /* set up physical groups */
-		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
-		if (!cpumask_empty(d->nodemask))
-			init_sched_build_groups(d->nodemask, cpu_map,
-						&cpu_to_phys_group,
-						d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_CPU, cpu_cpu_mask, },
 #ifdef CONFIG_NUMA
-	case SD_LV_ALLNODES:
-		init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
-					d->send_covered, d->tmpmask);
-		break;
+	{ sd_init_NODE, cpu_node_mask, },
+	{ sd_init_ALLNODES, cpu_allnodes_mask, },
 #endif
-	default:
-		break;
+	{ NULL, },
+};
+
+static struct sched_domain_topology_level *sched_domain_topology = default_topology;
+
+static int __sdt_alloc(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		sdd->sd = alloc_percpu(struct sched_domain *);
+		if (!sdd->sd)
+			return -ENOMEM;
+
+		sdd->sg = alloc_percpu(struct sched_group *);
+		if (!sdd->sg)
+			return -ENOMEM;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd;
+			struct sched_group *sg;
+
+		       	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sd)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sd, j) = sd;
+
+			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sg)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sg, j) = sg;
+		}
+	}
+
+	return 0;
+}
+
+static void __sdt_free(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		for_each_cpu(j, cpu_map) {
+			kfree(*per_cpu_ptr(sdd->sd, j));
+			kfree(*per_cpu_ptr(sdd->sg, j));
+		}
+		free_percpu(sdd->sd);
+		free_percpu(sdd->sg);
+	}
+}
+
+struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+		struct s_data *d, const struct cpumask *cpu_map,
+		struct sched_domain_attr *attr, struct sched_domain *child,
+		int cpu)
+{
+	struct sched_domain *sd = tl->init(tl, cpu);
+	if (!sd)
+		return child;
+
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	if (child) {
+		sd->level = child->level + 1;
+		sched_domain_level_max = max(sched_domain_level_max, sd->level);
+		child->parent = sd;
 	}
+	sd->child = child;
+
+	return sd;
 }
 
 /*
  * Build sched domains for a given set of cpus and attach the sched domains
  * to the individual cpus
  */
-static int __build_sched_domains(const struct cpumask *cpu_map,
-				 struct sched_domain_attr *attr)
+static int build_sched_domains(const struct cpumask *cpu_map,
+			       struct sched_domain_attr *attr)
 {
 	enum s_alloc alloc_state = sa_none;
-	struct s_data d;
 	struct sched_domain *sd;
-	int i;
-#ifdef CONFIG_NUMA
-	d.sd_allnodes = 0;
-#endif
+	struct s_data d;
+	int i, ret = -ENOMEM;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
 	if (alloc_state != sa_rootdomain)
 		goto error;
-	alloc_state = sa_sched_groups;
 
-	/*
-	 * Set up domains for cpus specified by the cpu_map.
-	 */
+	/* Set up domains for cpus specified by the cpu_map. */
 	for_each_cpu(i, cpu_map) {
-		cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
-			    cpu_map);
+		struct sched_domain_topology_level *tl;
 
-		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
-		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
-		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
-	}
-
-	for_each_cpu(i, cpu_map) {
-		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
-		build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
-		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
-	}
-
-	/* Set up physical groups */
-	for (i = 0; i < nr_node_ids; i++)
-		build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
+		sd = NULL;
+		for (tl = sched_domain_topology; tl->init; tl++)
+			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
 
-#ifdef CONFIG_NUMA
-	/* Set up node groups */
-	if (d.sd_allnodes)
-		build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
-
-	for (i = 0; i < nr_node_ids; i++)
-		if (build_numa_sched_groups(&d, cpu_map, i))
-			goto error;
-#endif
+		while (sd->child)
+			sd = sd->child;
 
-	/* Calculate CPU power for physical packages and nodes */
-#ifdef CONFIG_SCHED_SMT
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(cpu_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
-#endif
-#ifdef CONFIG_SCHED_MC
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(core_domains, i).sd;
-		init_sched_groups_power(i, sd);
+		*per_cpu_ptr(d.sd, i) = sd;
 	}
-#endif
-#ifdef CONFIG_SCHED_BOOK
-	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(book_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
-#endif
 
+	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
-		sd = &per_cpu(phys_domains, i).sd;
-		init_sched_groups_power(i, sd);
-	}
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			sd->span_weight = cpumask_weight(sched_domain_span(sd));
+			get_group(i, sd->private, &sd->groups);
+			atomic_inc(&sd->groups->ref);
 
-#ifdef CONFIG_NUMA
-	for (i = 0; i < nr_node_ids; i++)
-		init_numa_sched_groups_power(d.sched_group_nodes[i]);
+			if (i != cpumask_first(sched_domain_span(sd)))
+				continue;
 
-	if (d.sd_allnodes) {
-		struct sched_group *sg;
+			build_sched_groups(sd);
+		}
+	}
 
-		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
-								d.tmpmask);
-		init_numa_sched_groups_power(sg);
+	/* Calculate CPU power for physical packages and nodes */
+	for (i = nr_cpumask_bits-1; i >= 0; i--) {
+		if (!cpumask_test_cpu(i, cpu_map))
+			continue;
+
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			claim_allocations(i, sd);
+			init_sched_groups_power(i, sd);
+		}
 	}
-#endif
 
 	/* Attach the domains */
+	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-#ifdef CONFIG_SCHED_SMT
-		sd = &per_cpu(cpu_domains, i).sd;
-#elif defined(CONFIG_SCHED_MC)
-		sd = &per_cpu(core_domains, i).sd;
-#elif defined(CONFIG_SCHED_BOOK)
-		sd = &per_cpu(book_domains, i).sd;
-#else
-		sd = &per_cpu(phys_domains, i).sd;
-#endif
+		sd = *per_cpu_ptr(d.sd, i);
 		cpu_attach_domain(sd, d.rd, i);
 	}
+	rcu_read_unlock();
 
-	d.sched_group_nodes = NULL; /* don't free this we still need it */
-	__free_domain_allocs(&d, sa_tmpmask, cpu_map);
-	return 0;
-
+	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);
-	return -ENOMEM;
-}
-
-static int build_sched_domains(const struct cpumask *cpu_map)
-{
-	return __build_sched_domains(cpu_map, NULL);
+	return ret;
 }
 
 static cpumask_var_t *doms_cur;	/* current sched domains */
@@ -7670,7 +7362,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
  */
-static int arch_init_sched_domains(const struct cpumask *cpu_map)
+static int init_sched_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
@@ -7681,32 +7373,24 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map)
 		doms_cur = &fallback_doms;
 	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
 	dattr_cur = NULL;
-	err = build_sched_domains(doms_cur[0]);
+	err = build_sched_domains(doms_cur[0], NULL);
 	register_sched_domain_sysctl();
 
 	return err;
 }
 
-static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
-				       struct cpumask *tmpmask)
-{
-	free_sched_groups(cpu_map, tmpmask);
-}
-
 /*
  * Detach sched domains from a group of cpus specified in cpu_map
  * These cpus will now be attached to the NULL domain
  */
 static void detach_destroy_domains(const struct cpumask *cpu_map)
 {
-	/* Save because hotplug lock held. */
-	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
 	int i;
 
+	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
-	synchronize_sched();
-	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
+	rcu_read_unlock();
 }
 
 /* handle null as "default" */
@@ -7795,8 +7479,7 @@ match1:
 				goto match2;
 		}
 		/* no match - add a new doms_new */
-		__build_sched_domains(doms_new[i],
-					dattr_new ? dattr_new + i : NULL);
+		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
 match2:
 		;
 	}
@@ -7815,7 +7498,7 @@ match2:
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-static void arch_reinit_sched_domains(void)
+static void reinit_sched_domains(void)
 {
 	get_online_cpus();
 
@@ -7848,7 +7531,7 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 	else
 		sched_mc_power_savings = level;
 
-	arch_reinit_sched_domains();
+	reinit_sched_domains();
 
 	return count;
 }
@@ -7967,14 +7650,9 @@ void __init sched_init_smp(void)
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
 	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
-#if defined(CONFIG_NUMA)
-	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
-								GFP_KERNEL);
-	BUG_ON(sched_group_nodes_bycpu == NULL);
-#endif
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
-	arch_init_sched_domains(cpu_active_mask);
+	init_sched_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
@@ -8281,6 +7959,7 @@ void __init sched_init(void)
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
 	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_NO_HZ
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT);
@@ -8340,7 +8019,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	int old_prio = p->prio;
 	int on_rq;
 
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		deactivate_task(rq, p, 0);
 	__setscheduler(rq, p, SCHED_NORMAL, 0);
@@ -8553,7 +8232,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct rt_rq *rt_rq;
 	struct sched_rt_entity *rt_se;
-	struct rq *rq;
 	int i;
 
 	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8567,8 +8245,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		rt_rq = kzalloc_node(sizeof(struct rt_rq),
 				     GFP_KERNEL, cpu_to_node(i));
 		if (!rt_rq)
@@ -8683,7 +8359,7 @@ void sched_move_task(struct task_struct *tsk)
 	rq = task_rq_lock(tsk, &flags);
 
 	running = task_current(rq, tsk);
-	on_rq = tsk->se.on_rq;
+	on_rq = tsk->on_rq;
 
 	if (on_rq)
 		dequeue_task(rq, tsk, 0);
@@ -8702,7 +8378,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (on_rq)
 		enqueue_task(rq, tsk, 0);
 
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, tsk, &flags);
 }
 #endif /* CONFIG_CGROUP_SCHED */
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 7bacd83a415..a6710a112b4 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, p) {
-		if (!p->se.on_rq || task_cpu(p) != rq_cpu)
+		if (!p->on_rq || task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);
@@ -296,9 +296,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 	P(ttwu_count);
 	P(ttwu_local);
 
-	SEQ_printf(m, "  .%-30s: %d\n", "bkl_count",
-				rq->rq_sched_info.bkl_count);
-
 #undef P
 #undef P64
 #endif
@@ -441,7 +438,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.statistics.wait_count);
 	PN(se.statistics.iowait_sum);
 	P(se.statistics.iowait_count);
-	P(sched_info.bkl_count);
 	P(se.nr_migrations);
 	P(se.statistics.nr_migrations_cold);
 	P(se.statistics.nr_failed_migrations_affine);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6fa833ab2cb..37f22626225 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -358,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+#ifndef CONFIG_64BIT
+	smp_wmb();
+	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
+#endif
 }
 
 /*
@@ -1340,6 +1344,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	hrtick_update(rq);
 }
 
+static void set_next_buddy(struct sched_entity *se);
+
 /*
  * The dequeue_task method is called before nr_running is
  * decreased. We remove the task from the rbtree and
@@ -1349,14 +1355,22 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
+	int task_sleep = flags & DEQUEUE_SLEEP;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
 		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight)
+		if (cfs_rq->load.weight) {
+			/*
+			 * Bias pick_next to pick a task from this cfs_rq, as
+			 * p is sleeping when it is within its sched_slice.
+			 */
+			if (task_sleep && parent_entity(se))
+				set_next_buddy(parent_entity(se));
 			break;
+		}
 		flags |= DEQUEUE_SLEEP;
 	}
 
@@ -1372,12 +1386,25 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
-static void task_waking_fair(struct rq *rq, struct task_struct *p)
+static void task_waking_fair(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 min_vruntime;
 
-	se->vruntime -= cfs_rq->min_vruntime;
+#ifndef CONFIG_64BIT
+	u64 min_vruntime_copy;
+
+	do {
+		min_vruntime_copy = cfs_rq->min_vruntime_copy;
+		smp_rmb();
+		min_vruntime = cfs_rq->min_vruntime;
+	} while (min_vruntime != min_vruntime_copy);
+#else
+	min_vruntime = cfs_rq->min_vruntime;
+#endif
+
+	se->vruntime -= min_vruntime;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1622,6 +1649,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
+	rcu_read_lock();
 	for_each_domain(target, sd) {
 		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
 			break;
@@ -1641,6 +1669,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
 			break;
 	}
+	rcu_read_unlock();
 
 	return target;
 }
@@ -1657,7 +1686,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
@@ -1673,6 +1702,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 		new_cpu = prev_cpu;
 	}
 
+	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
 		if (!(tmp->flags & SD_LOAD_BALANCE))
 			continue;
@@ -1723,9 +1753,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 
 	if (affine_sd) {
 		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
-			return select_idle_sibling(p, cpu);
-		else
-			return select_idle_sibling(p, prev_cpu);
+			prev_cpu = cpu;
+
+		new_cpu = select_idle_sibling(p, prev_cpu);
+		goto unlock;
 	}
 
 	while (sd) {
@@ -1766,6 +1797,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 		}
 		/* while loop will break here if sd == NULL */
 	}
+unlock:
+	rcu_read_unlock();
 
 	return new_cpu;
 }
@@ -1789,10 +1822,7 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 	 * This is especially important for buddies when the leftmost
 	 * task is higher priority than the buddy.
 	 */
-	if (unlikely(se->load.weight != NICE_0_LOAD))
-		gran = calc_delta_fair(gran, se);
-
-	return gran;
+	return calc_delta_fair(gran, se);
 }
 
 /*
@@ -1826,26 +1856,26 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->last = se;
-	}
+	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+		return;
+
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->last = se;
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->next = se;
-	}
+	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+		return;
+
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->next = se;
 }
 
 static void set_skip_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->skip = se;
-	}
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->skip = se;
 }
 
 /*
@@ -1857,12 +1887,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
+	int next_buddy_marked = 0;
 
 	if (unlikely(se == pse))
 		return;
 
-	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
+	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
 		set_next_buddy(pse);
+		next_buddy_marked = 1;
+	}
 
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
@@ -1890,8 +1923,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	update_curr(cfs_rq);
 	find_matching_se(&se, &pse);
 	BUG_ON(!pse);
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
+		/*
+		 * Bias pick_next to pick the sched entity that is
+		 * triggering this preemption.
+		 */
+		if (!next_buddy_marked)
+			set_next_buddy(pse);
 		goto preempt;
+	}
 
 	return;
 
@@ -2102,7 +2142,7 @@ static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	      unsigned long max_load_move, struct sched_domain *sd,
 	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
+	      struct cfs_rq *busiest_cfs_rq)
 {
 	int loops = 0, pulled = 0;
 	long rem_load_move = max_load_move;
@@ -2140,9 +2180,6 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		 */
 		if (rem_load_move <= 0)
 			break;
-
-		if (p->prio < *this_best_prio)
-			*this_best_prio = p->prio;
 	}
 out:
 	/*
@@ -2202,7 +2239,7 @@ static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
+		  int *all_pinned)
 {
 	long rem_load_move = max_load_move;
 	int busiest_cpu = cpu_of(busiest);
@@ -2227,7 +2264,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
 		moved_load = balance_tasks(this_rq, this_cpu, busiest,
-				rem_load, sd, idle, all_pinned, this_best_prio,
+				rem_load, sd, idle, all_pinned,
 				busiest_cfs_rq);
 
 		if (!moved_load)
@@ -2253,11 +2290,11 @@ static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
+		  int *all_pinned)
 {
 	return balance_tasks(this_rq, this_cpu, busiest,
 			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &busiest->cfs);
+			&busiest->cfs);
 }
 #endif
 
@@ -2274,12 +2311,11 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		      int *all_pinned)
 {
 	unsigned long total_load_moved = 0, load_moved;
-	int this_best_prio = this_rq->curr->prio;
 
 	do {
 		load_moved = load_balance_fair(this_rq, this_cpu, busiest,
 				max_load_move - total_load_moved,
-				sd, idle, all_pinned, &this_best_prio);
+				sd, idle, all_pinned);
 
 		total_load_moved += load_moved;
 
@@ -2648,7 +2684,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 	/*
 	 * Only siblings can have significantly less than SCHED_LOAD_SCALE
 	 */
-	if (sd->level != SD_LV_SIBLING)
+	if (!(sd->flags & SD_SHARE_CPUPOWER))
 		return 0;
 
 	/*
@@ -3465,6 +3501,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	raw_spin_unlock(&this_rq->lock);
 
 	update_shares(this_cpu);
+	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 		int balance = 1;
@@ -3486,6 +3523,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 			break;
 		}
 	}
+	rcu_read_unlock();
 
 	raw_spin_lock(&this_rq->lock);
 
@@ -3534,6 +3572,7 @@ static int active_load_balance_cpu_stop(void *data)
 	double_lock_balance(busiest_rq, target_rq);
 
 	/* Search for an sd spanning us and the target CPU. */
+	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
 		if ((sd->flags & SD_LOAD_BALANCE) &&
 		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
@@ -3549,6 +3588,7 @@ static int active_load_balance_cpu_stop(void *data)
 		else
 			schedstat_inc(sd, alb_failed);
 	}
+	rcu_read_unlock();
 	double_unlock_balance(busiest_rq, target_rq);
 out_unlock:
 	busiest_rq->active_balance = 0;
@@ -3675,6 +3715,7 @@ static int find_new_ilb(int cpu)
 {
 	struct sched_domain *sd;
 	struct sched_group *ilb_group;
+	int ilb = nr_cpu_ids;
 
 	/*
 	 * Have idle load balancer selection from semi-idle packages only
@@ -3690,20 +3731,25 @@ static int find_new_ilb(int cpu)
 	if (cpumask_weight(nohz.idle_cpus_mask) < 2)
 		goto out_done;
 
+	rcu_read_lock();
 	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.grp_idle_mask);
+			if (is_semi_idle_group(ilb_group)) {
+				ilb = cpumask_first(nohz.grp_idle_mask);
+				goto unlock;
+			}
 
 			ilb_group = ilb_group->next;
 
 		} while (ilb_group != sd->groups);
 	}
+unlock:
+	rcu_read_unlock();
 
 out_done:
-	return nr_cpu_ids;
+	return ilb;
 }
 #else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
 static inline int find_new_ilb(int call_cpu)
@@ -3848,6 +3894,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 
 	update_shares(cpu);
 
+	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
@@ -3893,6 +3940,7 @@ out:
 		if (!balance)
 			break;
 	}
+	rcu_read_unlock();
 
 	/*
 	 * next_balance will be updated only when there is a need.
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 68e69acc29b..be40f7371ee 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1)
  * Decrement CPU power based on irq activity
  */
 SCHED_FEAT(NONIRQ_POWER, 1)
+
+/*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+SCHED_FEAT(TTWU_QUEUE, 1)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a776a639642..0a51882534e 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -7,7 +7,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index e7cebdc65f8..64b2a37c07d 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -183,6 +183,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
 }
 
+typedef struct task_group *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for (iter = list_entry_rcu(task_groups.next, typeof(*iter), list); \
+	     (&iter->list != &task_groups) && \
+	     (rt_rq = iter->rt_rq[cpu_of(rq)]); \
+	     iter = list_entry_rcu(iter->list.next, typeof(*iter), list))
+
 static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
 {
 	list_add_rcu(&rt_rq->leaf_rt_rq_list,
@@ -288,6 +296,11 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(def_rt_bandwidth.rt_period);
 }
 
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
 static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
 {
 }
@@ -402,12 +415,13 @@ next:
 static void __disable_runtime(struct rq *rq)
 {
 	struct root_domain *rd = rq->rd;
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	if (unlikely(!scheduler_running))
 		return;
 
-	for_each_leaf_rt_rq(rt_rq, rq) {
+	for_each_rt_rq(rt_rq, iter, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 		s64 want;
 		int i;
@@ -487,6 +501,7 @@ static void disable_runtime(struct rq *rq)
 
 static void __enable_runtime(struct rq *rq)
 {
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	if (unlikely(!scheduler_running))
@@ -495,7 +510,7 @@ static void __enable_runtime(struct rq *rq)
 	/*
 	 * Reset each runqueue's bandwidth settings
 	 */
-	for_each_leaf_rt_rq(rt_rq, rq) {
+	for_each_rt_rq(rt_rq, iter, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 
 		raw_spin_lock(&rt_b->rt_runtime_lock);
@@ -562,6 +577,13 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
 				rt_rq->rt_throttled = 0;
 				enqueue = 1;
+
+				/*
+				 * Force a clock update if the CPU was idle,
+				 * lest wakeup -> unthrottle time accumulate.
+				 */
+				if (rt_rq->rt_nr_running && rq->curr == rq->idle)
+					rq->skip_clock_update = -1;
 			}
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
@@ -977,13 +999,23 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 {
+	struct task_struct *curr;
+	struct rq *rq;
+	int cpu;
+
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
+	cpu = task_cpu(p);
+	rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
 	/*
-	 * If the current task is an RT task, then
+	 * If the current task on @p's runqueue is an RT task, then
 	 * try to see if we can wake this RT task up on another
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.
@@ -997,21 +1029,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 	 * lock?
 	 *
 	 * For equal prio tasks, we just let the scheduler sort it out.
+	 *
+	 * Otherwise, just let it ride on the affined RQ and the
+	 * post-schedule router will push the preempted task away
+	 *
+	 * This test is optimistic, if we get it wrong the load-balancer
+	 * will have to sort it out.
 	 */
-	if (unlikely(rt_task(rq->curr)) &&
-	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio) &&
+	if (curr && unlikely(rt_task(curr)) &&
+	    (curr->rt.nr_cpus_allowed < 2 ||
+	     curr->prio < p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
-		int cpu = find_lowest_rq(p);
+		int target = find_lowest_rq(p);
 
-		return (cpu == -1) ? task_cpu(p) : cpu;
+		if (target != -1)
+			cpu = target;
 	}
+	rcu_read_unlock();
 
-	/*
-	 * Otherwise, just let it ride on the affined RQ and the
-	 * post-schedule router will push the preempted task away
-	 */
-	return task_cpu(p);
+	return cpu;
 }
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
@@ -1136,7 +1172,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
 	 */
-	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+	if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
@@ -1287,7 +1323,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(lowest_rq->cpu,
 						       &task->cpus_allowed) ||
 				     task_running(rq, task) ||
-				     !task->se.on_rq)) {
+				     !task->on_rq)) {
 
 				raw_spin_unlock(&lowest_rq->lock);
 				lowest_rq = NULL;
@@ -1321,7 +1357,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
 	BUG_ON(task_current(rq, p));
 	BUG_ON(p->rt.nr_cpus_allowed <= 1);
 
-	BUG_ON(!p->se.on_rq);
+	BUG_ON(!p->on_rq);
 	BUG_ON(!rt_task(p));
 
 	return p;
@@ -1467,7 +1503,7 @@ static int pull_rt_task(struct rq *this_rq)
 		 */
 		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
 			WARN_ON(p == src_rq->curr);
-			WARN_ON(!p->se.on_rq);
+			WARN_ON(!p->on_rq);
 
 			/*
 			 * There's a chance that p is higher in priority
@@ -1538,7 +1574,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 	 * Update the migration status of the RQ if we have an RT task
 	 * which is running AND changing its weight value.
 	 */
-	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
+	if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
 		struct rq *rq = task_rq(p);
 
 		if (!task_current(rq, p)) {
@@ -1608,7 +1644,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (p->se.on_rq && !rq->rt.rt_nr_running)
+	if (p->on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 
@@ -1638,7 +1674,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (p->se.on_rq && rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */
@@ -1657,7 +1693,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 static void
 prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (!p->se.on_rq)
+	if (!p->on_rq)
 		return;
 
 	if (rq->curr == p) {
@@ -1796,10 +1832,11 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 
 static void print_rt_stats(struct seq_file *m, int cpu)
 {
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	rcu_read_lock();
-	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+	for_each_rt_rq(rt_rq, iter, cpu_rq(cpu))
 		print_rt_rq(m, cpu, rt_rq);
 	rcu_read_unlock();
 }
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 1ba2bd40fda..6f437632afa 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -9,8 +9,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct rq *rq, struct task_struct *p,
-		    int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
@@ -26,7 +25,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->se.on_rq)
+	if (stop && stop->on_rq)
 		return stop;
 
 	return NULL;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 174f976c287..13960170cad 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
-	"TASKLET", "SCHED", "HRTIMER",	"RCU"
+	"TASKLET", "SCHED", "HRTIMER"
 };
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index af468edf096..e4128b278f2 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -314,8 +314,8 @@ void kernel_restart_prepare(char *cmd)
 {
 	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
 	system_state = SYSTEM_RESTART;
+	usermodehelper_disable();
 	device_shutdown();
-	sysdev_shutdown();
 	syscore_shutdown();
 }
 
@@ -344,6 +344,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 	blocking_notifier_call_chain(&reboot_notifier_list,
 		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
 	system_state = state;
+	usermodehelper_disable();
 	device_shutdown();
 }
 /**
@@ -354,7 +355,6 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -374,7 +374,6 @@ void kernel_power_off(void)
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
 	disable_nonboot_cpus();
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index b0425991e9a..e2fd74b8e8c 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,5 +1,5 @@
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
-obj-y += timeconv.o posix-clock.o
+obj-y += timeconv.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
new file mode 100644
index 00000000000..9265014cb4d
--- /dev/null
+++ b/kernel/time/alarmtimer.c
@@ -0,0 +1,694 @@
+/*
+ * Alarmtimer interface
+ *
+ * This interface provides a timer which is similarto hrtimers,
+ * but triggers a RTC alarm if the box is suspend.
+ *
+ * This interface is influenced by the Android RTC Alarm timer
+ * interface.
+ *
+ * Copyright (C) 2010 IBM Corperation
+ *
+ * Author: John Stultz <john.stultz@linaro.org>
+ *
+ * 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/time.h>
+#include <linux/hrtimer.h>
+#include <linux/timerqueue.h>
+#include <linux/rtc.h>
+#include <linux/alarmtimer.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/posix-timers.h>
+#include <linux/workqueue.h>
+#include <linux/freezer.h>
+
+/**
+ * struct alarm_base - Alarm timer bases
+ * @lock:		Lock for syncrhonized access to the base
+ * @timerqueue:		Timerqueue head managing the list of events
+ * @timer: 		hrtimer used to schedule events while running
+ * @gettime:		Function to read the time correlating to the base
+ * @base_clockid:	clockid for the base
+ */
+static struct alarm_base {
+	spinlock_t		lock;
+	struct timerqueue_head	timerqueue;
+	struct hrtimer		timer;
+	ktime_t			(*gettime)(void);
+	clockid_t		base_clockid;
+} alarm_bases[ALARM_NUMTYPE];
+
+#ifdef CONFIG_RTC_CLASS
+/* rtc timer and device for setting alarm wakeups at suspend */
+static struct rtc_timer		rtctimer;
+static struct rtc_device	*rtcdev;
+#endif
+
+/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */
+static ktime_t freezer_delta;
+static DEFINE_SPINLOCK(freezer_delta_lock);
+
+
+/**
+ * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue
+ * @base: pointer to the base where the timer is being run
+ * @alarm: pointer to alarm being enqueued.
+ *
+ * Adds alarm to a alarm_base timerqueue and if necessary sets
+ * an hrtimer to run.
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm)
+{
+	timerqueue_add(&base->timerqueue, &alarm->node);
+	if (&alarm->node == timerqueue_getnext(&base->timerqueue)) {
+		hrtimer_try_to_cancel(&base->timer);
+		hrtimer_start(&base->timer, alarm->node.expires,
+				HRTIMER_MODE_ABS);
+	}
+}
+
+/**
+ * alarmtimer_remove - Removes an alarm timer from an alarm_base timerqueue
+ * @base: pointer to the base where the timer is running
+ * @alarm: pointer to alarm being removed
+ *
+ * Removes alarm to a alarm_base timerqueue and if necessary sets
+ * a new timer to run.
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm)
+{
+	struct timerqueue_node *next = timerqueue_getnext(&base->timerqueue);
+
+	timerqueue_del(&base->timerqueue, &alarm->node);
+	if (next == &alarm->node) {
+		hrtimer_try_to_cancel(&base->timer);
+		next = timerqueue_getnext(&base->timerqueue);
+		if (!next)
+			return;
+		hrtimer_start(&base->timer, next->expires, HRTIMER_MODE_ABS);
+	}
+}
+
+
+/**
+ * alarmtimer_fired - Handles alarm hrtimer being fired.
+ * @timer: pointer to hrtimer being run
+ *
+ * When a alarm timer fires, this runs through the timerqueue to
+ * see which alarms expired, and runs those. If there are more alarm
+ * timers queued for the future, we set the hrtimer to fire when
+ * when the next future alarm timer expires.
+ */
+static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
+{
+	struct alarm_base *base = container_of(timer, struct alarm_base, timer);
+	struct timerqueue_node *next;
+	unsigned long flags;
+	ktime_t now;
+	int ret = HRTIMER_NORESTART;
+
+	spin_lock_irqsave(&base->lock, flags);
+	now = base->gettime();
+	while ((next = timerqueue_getnext(&base->timerqueue))) {
+		struct alarm *alarm;
+		ktime_t expired = next->expires;
+
+		if (expired.tv64 >= now.tv64)
+			break;
+
+		alarm = container_of(next, struct alarm, node);
+
+		timerqueue_del(&base->timerqueue, &alarm->node);
+		alarm->enabled = 0;
+		/* Re-add periodic timers */
+		if (alarm->period.tv64) {
+			alarm->node.expires = ktime_add(expired, alarm->period);
+			timerqueue_add(&base->timerqueue, &alarm->node);
+			alarm->enabled = 1;
+		}
+		spin_unlock_irqrestore(&base->lock, flags);
+		if (alarm->function)
+			alarm->function(alarm);
+		spin_lock_irqsave(&base->lock, flags);
+	}
+
+	if (next) {
+		hrtimer_set_expires(&base->timer, next->expires);
+		ret = HRTIMER_RESTART;
+	}
+	spin_unlock_irqrestore(&base->lock, flags);
+
+	return ret;
+
+}
+
+#ifdef CONFIG_RTC_CLASS
+/**
+ * alarmtimer_suspend - Suspend time callback
+ * @dev: unused
+ * @state: unused
+ *
+ * When we are going into suspend, we look through the bases
+ * to see which is the soonest timer to expire. We then
+ * set an rtc timer to fire that far into the future, which
+ * will wake us from suspend.
+ */
+static int alarmtimer_suspend(struct device *dev)
+{
+	struct rtc_time tm;
+	ktime_t min, now;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&freezer_delta_lock, flags);
+	min = freezer_delta;
+	freezer_delta = ktime_set(0, 0);
+	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+
+	/* If we have no rtcdev, just return */
+	if (!rtcdev)
+		return 0;
+
+	/* Find the soonest timer to expire*/
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		struct alarm_base *base = &alarm_bases[i];
+		struct timerqueue_node *next;
+		ktime_t delta;
+
+		spin_lock_irqsave(&base->lock, flags);
+		next = timerqueue_getnext(&base->timerqueue);
+		spin_unlock_irqrestore(&base->lock, flags);
+		if (!next)
+			continue;
+		delta = ktime_sub(next->expires, base->gettime());
+		if (!min.tv64 || (delta.tv64 < min.tv64))
+			min = delta;
+	}
+	if (min.tv64 == 0)
+		return 0;
+
+	/* XXX - Should we enforce a minimum sleep time? */
+	WARN_ON(min.tv64 < NSEC_PER_SEC);
+
+	/* Setup an rtc timer to fire that far in the future */
+	rtc_timer_cancel(rtcdev, &rtctimer);
+	rtc_read_time(rtcdev, &tm);
+	now = rtc_tm_to_ktime(tm);
+	now = ktime_add(now, min);
+
+	rtc_timer_start(rtcdev, &rtctimer, now, ktime_set(0, 0));
+
+	return 0;
+}
+#else
+static int alarmtimer_suspend(struct device *dev)
+{
+	return 0;
+}
+#endif
+
+static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
+{
+	ktime_t delta;
+	unsigned long flags;
+	struct alarm_base *base = &alarm_bases[type];
+
+	delta = ktime_sub(absexp, base->gettime());
+
+	spin_lock_irqsave(&freezer_delta_lock, flags);
+	if (!freezer_delta.tv64 || (delta.tv64 < freezer_delta.tv64))
+		freezer_delta = delta;
+	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+}
+
+
+/**
+ * alarm_init - Initialize an alarm structure
+ * @alarm: ptr to alarm to be initialized
+ * @type: the type of the alarm
+ * @function: callback that is run when the alarm fires
+ */
+void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
+		void (*function)(struct alarm *))
+{
+	timerqueue_init(&alarm->node);
+	alarm->period = ktime_set(0, 0);
+	alarm->function = function;
+	alarm->type = type;
+	alarm->enabled = 0;
+}
+
+/**
+ * alarm_start - Sets an alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time to run the alarm
+ * @period: period at which the alarm will recur
+ */
+void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+
+	spin_lock_irqsave(&base->lock, flags);
+	if (alarm->enabled)
+		alarmtimer_remove(base, alarm);
+	alarm->node.expires = start;
+	alarm->period = period;
+	alarmtimer_enqueue(base, alarm);
+	alarm->enabled = 1;
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
+ * alarm_cancel - Tries to cancel an alarm timer
+ * @alarm: ptr to alarm to be canceled
+ */
+void alarm_cancel(struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+
+	spin_lock_irqsave(&base->lock, flags);
+	if (alarm->enabled)
+		alarmtimer_remove(base, alarm);
+	alarm->enabled = 0;
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+
+
+/**
+ * clock2alarm - helper that converts from clockid to alarmtypes
+ * @clockid: clockid.
+ */
+static enum alarmtimer_type clock2alarm(clockid_t clockid)
+{
+	if (clockid == CLOCK_REALTIME_ALARM)
+		return ALARM_REALTIME;
+	if (clockid == CLOCK_BOOTTIME_ALARM)
+		return ALARM_BOOTTIME;
+	return -1;
+}
+
+/**
+ * alarm_handle_timer - Callback for posix timers
+ * @alarm: alarm that fired
+ *
+ * Posix timer callback for expired alarm timers.
+ */
+static void alarm_handle_timer(struct alarm *alarm)
+{
+	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
+						it.alarmtimer);
+	if (posix_timer_event(ptr, 0) != 0)
+		ptr->it_overrun++;
+}
+
+/**
+ * alarm_clock_getres - posix getres interface
+ * @which_clock: clockid
+ * @tp: timespec to fill
+ *
+ * Returns the granularity of underlying alarm base clock
+ */
+static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
+{
+	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
+
+	return hrtimer_get_res(baseid, tp);
+}
+
+/**
+ * alarm_clock_get - posix clock_get interface
+ * @which_clock: clockid
+ * @tp: timespec to fill.
+ *
+ * Provides the underlying alarm base time.
+ */
+static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
+{
+	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+	*tp = ktime_to_timespec(base->gettime());
+	return 0;
+}
+
+/**
+ * alarm_timer_create - posix timer_create interface
+ * @new_timer: k_itimer pointer to manage
+ *
+ * Initializes the k_itimer structure.
+ */
+static int alarm_timer_create(struct k_itimer *new_timer)
+{
+	enum  alarmtimer_type type;
+	struct alarm_base *base;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	type = clock2alarm(new_timer->it_clock);
+	base = &alarm_bases[type];
+	alarm_init(&new_timer->it.alarmtimer, type, alarm_handle_timer);
+	return 0;
+}
+
+/**
+ * alarm_timer_get - posix timer_get interface
+ * @new_timer: k_itimer pointer
+ * @cur_setting: itimerspec data to fill
+ *
+ * Copies the itimerspec data out from the k_itimer
+ */
+static void alarm_timer_get(struct k_itimer *timr,
+				struct itimerspec *cur_setting)
+{
+	cur_setting->it_interval =
+			ktime_to_timespec(timr->it.alarmtimer.period);
+	cur_setting->it_value =
+			ktime_to_timespec(timr->it.alarmtimer.node.expires);
+	return;
+}
+
+/**
+ * alarm_timer_del - posix timer_del interface
+ * @timr: k_itimer pointer to be deleted
+ *
+ * Cancels any programmed alarms for the given timer.
+ */
+static int alarm_timer_del(struct k_itimer *timr)
+{
+	alarm_cancel(&timr->it.alarmtimer);
+	return 0;
+}
+
+/**
+ * alarm_timer_set - posix timer_set interface
+ * @timr: k_itimer pointer to be deleted
+ * @flags: timer flags
+ * @new_setting: itimerspec to be used
+ * @old_setting: itimerspec being replaced
+ *
+ * Sets the timer to new_setting, and starts the timer.
+ */
+static int alarm_timer_set(struct k_itimer *timr, int flags,
+				struct itimerspec *new_setting,
+				struct itimerspec *old_setting)
+{
+	/* Save old values */
+	old_setting->it_interval =
+			ktime_to_timespec(timr->it.alarmtimer.period);
+	old_setting->it_value =
+			ktime_to_timespec(timr->it.alarmtimer.node.expires);
+
+	/* If the timer was already set, cancel it */
+	alarm_cancel(&timr->it.alarmtimer);
+
+	/* start the timer */
+	alarm_start(&timr->it.alarmtimer,
+			timespec_to_ktime(new_setting->it_value),
+			timespec_to_ktime(new_setting->it_interval));
+	return 0;
+}
+
+/**
+ * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep
+ * @alarm: ptr to alarm that fired
+ *
+ * Wakes up the task that set the alarmtimer
+ */
+static void alarmtimer_nsleep_wakeup(struct alarm *alarm)
+{
+	struct task_struct *task = (struct task_struct *)alarm->data;
+
+	alarm->data = NULL;
+	if (task)
+		wake_up_process(task);
+}
+
+/**
+ * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation
+ * @alarm: ptr to alarmtimer
+ * @absexp: absolute expiration time
+ *
+ * Sets the alarm timer and sleeps until it is fired or interrupted.
+ */
+static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp)
+{
+	alarm->data = (void *)current;
+	do {
+		set_current_state(TASK_INTERRUPTIBLE);
+		alarm_start(alarm, absexp, ktime_set(0, 0));
+		if (likely(alarm->data))
+			schedule();
+
+		alarm_cancel(alarm);
+	} while (alarm->data && !signal_pending(current));
+
+	__set_current_state(TASK_RUNNING);
+
+	return (alarm->data == NULL);
+}
+
+
+/**
+ * update_rmtp - Update remaining timespec value
+ * @exp: expiration time
+ * @type: timer type
+ * @rmtp: user pointer to remaining timepsec value
+ *
+ * Helper function that fills in rmtp value with time between
+ * now and the exp value
+ */
+static int update_rmtp(ktime_t exp, enum  alarmtimer_type type,
+			struct timespec __user *rmtp)
+{
+	struct timespec rmt;
+	ktime_t rem;
+
+	rem = ktime_sub(exp, alarm_bases[type].gettime());
+
+	if (rem.tv64 <= 0)
+		return 0;
+	rmt = ktime_to_timespec(rem);
+
+	if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
+		return -EFAULT;
+
+	return 1;
+
+}
+
+/**
+ * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep
+ * @restart: ptr to restart block
+ *
+ * Handles restarted clock_nanosleep calls
+ */
+static long __sched alarm_timer_nsleep_restart(struct restart_block *restart)
+{
+	enum  alarmtimer_type type = restart->nanosleep.index;
+	ktime_t exp;
+	struct timespec __user  *rmtp;
+	struct alarm alarm;
+	int ret = 0;
+
+	exp.tv64 = restart->nanosleep.expires;
+	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	if (alarmtimer_do_nsleep(&alarm, exp))
+		goto out;
+
+	if (freezing(current))
+		alarmtimer_freezerset(exp, type);
+
+	rmtp = restart->nanosleep.rmtp;
+	if (rmtp) {
+		ret = update_rmtp(exp, type, rmtp);
+		if (ret <= 0)
+			goto out;
+	}
+
+
+	/* The other values in restart are already filled in */
+	ret = -ERESTART_RESTARTBLOCK;
+out:
+	return ret;
+}
+
+/**
+ * alarm_timer_nsleep - alarmtimer nanosleep
+ * @which_clock: clockid
+ * @flags: determins abstime or relative
+ * @tsreq: requested sleep time (abs or rel)
+ * @rmtp: remaining sleep time saved
+ *
+ * Handles clock_nanosleep calls against _ALARM clockids
+ */
+static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
+		     struct timespec *tsreq, struct timespec __user *rmtp)
+{
+	enum  alarmtimer_type type = clock2alarm(which_clock);
+	struct alarm alarm;
+	ktime_t exp;
+	int ret = 0;
+	struct restart_block *restart;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	exp = timespec_to_ktime(*tsreq);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now = alarm_bases[type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	if (alarmtimer_do_nsleep(&alarm, exp))
+		goto out;
+
+	if (freezing(current))
+		alarmtimer_freezerset(exp, type);
+
+	/* abs timers don't set remaining time or restart */
+	if (flags == TIMER_ABSTIME) {
+		ret = -ERESTARTNOHAND;
+		goto out;
+	}
+
+	if (rmtp) {
+		ret = update_rmtp(exp, type, rmtp);
+		if (ret <= 0)
+			goto out;
+	}
+
+	restart = &current_thread_info()->restart_block;
+	restart->fn = alarm_timer_nsleep_restart;
+	restart->nanosleep.index = type;
+	restart->nanosleep.expires = exp.tv64;
+	restart->nanosleep.rmtp = rmtp;
+	ret = -ERESTART_RESTARTBLOCK;
+
+out:
+	return ret;
+}
+
+
+/* Suspend hook structures */
+static const struct dev_pm_ops alarmtimer_pm_ops = {
+	.suspend = alarmtimer_suspend,
+};
+
+static struct platform_driver alarmtimer_driver = {
+	.driver = {
+		.name = "alarmtimer",
+		.pm = &alarmtimer_pm_ops,
+	}
+};
+
+/**
+ * alarmtimer_init - Initialize alarm timer code
+ *
+ * This function initializes the alarm bases and registers
+ * the posix clock ids.
+ */
+static int __init alarmtimer_init(void)
+{
+	int error = 0;
+	int i;
+	struct k_clock alarm_clock = {
+		.clock_getres	= alarm_clock_getres,
+		.clock_get	= alarm_clock_get,
+		.timer_create	= alarm_timer_create,
+		.timer_set	= alarm_timer_set,
+		.timer_del	= alarm_timer_del,
+		.timer_get	= alarm_timer_get,
+		.nsleep		= alarm_timer_nsleep,
+	};
+
+	posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
+	posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
+
+	/* Initialize alarm bases */
+	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
+	alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real;
+	alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
+	alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime;
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		timerqueue_init_head(&alarm_bases[i].timerqueue);
+		spin_lock_init(&alarm_bases[i].lock);
+		hrtimer_init(&alarm_bases[i].timer,
+				alarm_bases[i].base_clockid,
+				HRTIMER_MODE_ABS);
+		alarm_bases[i].timer.function = alarmtimer_fired;
+	}
+	error = platform_driver_register(&alarmtimer_driver);
+	platform_device_register_simple("alarmtimer", -1, NULL, 0);
+
+	return error;
+}
+device_initcall(alarmtimer_init);
+
+#ifdef CONFIG_RTC_CLASS
+/**
+ * has_wakealarm - check rtc device has wakealarm ability
+ * @dev: current device
+ * @name_ptr: name to be returned
+ *
+ * This helper function checks to see if the rtc device can wake
+ * from suspend.
+ */
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+	struct rtc_device *candidate = to_rtc_device(dev);
+
+	if (!candidate->ops->set_alarm)
+		return 0;
+	if (!device_may_wakeup(candidate->dev.parent))
+		return 0;
+
+	*(const char **)name_ptr = dev_name(dev);
+	return 1;
+}
+
+/**
+ * alarmtimer_init_late - Late initializing of alarmtimer code
+ *
+ * This function locates a rtc device to use for wakealarms.
+ * Run as late_initcall to make sure rtc devices have been
+ * registered.
+ */
+static int __init alarmtimer_init_late(void)
+{
+	char *str;
+
+	/* Find an rtc device and init the rtc_timer */
+	class_find_device(rtc_class, NULL, &str, has_wakealarm);
+	if (str)
+		rtcdev = rtc_class_open(str);
+	if (!rtcdev) {
+		printk(KERN_WARNING "No RTC device found, ALARM timers will"
+			" not wake from suspend");
+	}
+	rtc_timer_init(&rtctimer, NULL, NULL);
+
+	return 0;
+}
+#else
+static int __init alarmtimer_init_late(void)
+{
+	printk(KERN_WARNING "Kernel not built with RTC support, ALARM timers"
+		" will not wake from suspend");
+	return 0;
+}
+#endif
+late_initcall(alarmtimer_init_late);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 0d74b9ba90c..22a9da9a9c9 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -194,6 +194,70 @@ void clockevents_register_device(struct clock_event_device *dev)
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
+static void clockevents_config(struct clock_event_device *dev,
+			       u32 freq)
+{
+	unsigned long sec;
+
+	if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return;
+
+	/*
+	 * Calculate the maximum number of seconds we can sleep. Limit
+	 * to 10 minutes for hardware which can program more than
+	 * 32bit ticks so we still get reasonable conversion values.
+	 */
+	sec = dev->max_delta_ticks;
+	do_div(sec, freq);
+	if (!sec)
+		sec = 1;
+	else if (sec > 600 && dev->max_delta_ticks > UINT_MAX)
+		sec = 600;
+
+	clockevents_calc_mult_shift(dev, freq, sec);
+	dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
+	dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+}
+
+/**
+ * clockevents_config_and_register - Configure and register a clock event device
+ * @dev:	device to register
+ * @freq:	The clock frequency
+ * @min_delta:	The minimum clock ticks to program in oneshot mode
+ * @max_delta:	The maximum clock ticks to program in oneshot mode
+ *
+ * min/max_delta can be 0 for devices which do not support oneshot mode.
+ */
+void clockevents_config_and_register(struct clock_event_device *dev,
+				     u32 freq, unsigned long min_delta,
+				     unsigned long max_delta)
+{
+	dev->min_delta_ticks = min_delta;
+	dev->max_delta_ticks = max_delta;
+	clockevents_config(dev, freq);
+	clockevents_register_device(dev);
+}
+
+/**
+ * clockevents_update_freq - Update frequency and reprogram a clock event device.
+ * @dev:	device to modify
+ * @freq:	new device frequency
+ *
+ * Reconfigure and reprogram a clock event device in oneshot
+ * mode. Must be called on the cpu for which the device delivers per
+ * cpu timer events with interrupts disabled!  Returns 0 on success,
+ * -ETIME when the event is in the past.
+ */
+int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+	clockevents_config(dev, freq);
+
+	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+		return 0;
+
+	return clockevents_program_event(dev, dev->next_event, ktime_get());
+}
+
 /*
  * Noop handler when we shut down an event device
  */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 0e17c10f8a9..d9d5f8c885f 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -626,19 +626,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 	list_add(&cs->list, entry);
 }
 
-
-/*
- * Maximum time we expect to go between ticks. This includes idle
- * tickless time. It provides the trade off between selecting a
- * mult/shift pair that is very precise but can only handle a short
- * period of time, vs. a mult/shift pair that can handle long periods
- * of time but isn't as precise.
- *
- * This is a subsystem constant, and actual hardware limitations
- * may override it (ie: clocksources that wrap every 3 seconds).
- */
-#define MAX_UPDATE_LENGTH 5 /* Seconds */
-
 /**
  * __clocksource_updatefreq_scale - Used update clocksource with new freq
  * @t:		clocksource to be registered
@@ -652,15 +639,28 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	unsigned long sec;
+
 	/*
-	 * Ideally we want to use  some of the limits used in
-	 * clocksource_max_deferment, to provide a more informed
-	 * MAX_UPDATE_LENGTH. But for now this just gets the
-	 * register interface working properly.
+	 * Calc the maximum number of seconds which we can run before
+	 * wrapping around. For clocksources which have a mask > 32bit
+	 * we need to limit the max sleep time to have a good
+	 * conversion precision. 10 minutes is still a reasonable
+	 * amount. That results in a shift value of 24 for a
+	 * clocksource with mask >= 40bit and f >= 4GHz. That maps to
+	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
+	 * margin as we do in clocksource_max_deferment()
 	 */
+	sec = (cs->mask - (cs->mask >> 5));
+	do_div(sec, freq);
+	do_div(sec, scale);
+	if (!sec)
+		sec = 1;
+	else if (sec > 600 && cs->mask > UINT_MAX)
+		sec = 600;
+
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-				      NSEC_PER_SEC/scale,
-				      MAX_UPDATE_LENGTH*scale);
+			       NSEC_PER_SEC / scale, sec * scale);
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 8ad5d576755..8e6a05a5915 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -596,6 +596,58 @@ void __init timekeeping_init(void)
 static struct timespec timekeeping_suspend_time;
 
 /**
+ * __timekeeping_inject_sleeptime - Internal function to add sleep interval
+ * @delta: pointer to a timespec delta value
+ *
+ * Takes a timespec offset measuring a suspend interval and properly
+ * adds the sleep offset to the timekeeping variables.
+ */
+static void __timekeeping_inject_sleeptime(struct timespec *delta)
+{
+	xtime = timespec_add(xtime, *delta);
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
+	total_sleep_time = timespec_add(total_sleep_time, *delta);
+}
+
+
+/**
+ * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values
+ * @delta: pointer to a timespec delta value
+ *
+ * This hook is for architectures that cannot support read_persistent_clock
+ * because their RTC/persistent clock is only accessible when irqs are enabled.
+ *
+ * This function should only be called by rtc_resume(), and allows
+ * a suspend offset to be injected into the timekeeping values.
+ */
+void timekeeping_inject_sleeptime(struct timespec *delta)
+{
+	unsigned long flags;
+	struct timespec ts;
+
+	/* Make sure we don't set the clock twice */
+	read_persistent_clock(&ts);
+	if (!(ts.tv_sec == 0 && ts.tv_nsec == 0))
+		return;
+
+	write_seqlock_irqsave(&xtime_lock, flags);
+	timekeeping_forward_now();
+
+	__timekeeping_inject_sleeptime(delta);
+
+	timekeeper.ntp_error = 0;
+	ntp_clear();
+	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+				timekeeper.mult);
+
+	write_sequnlock_irqrestore(&xtime_lock, flags);
+
+	/* signal hrtimers about time change */
+	clock_was_set();
+}
+
+
+/**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
  *
  * This is for the generic clocksource timekeeping.
@@ -615,9 +667,7 @@ static void timekeeping_resume(void)
 
 	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
 		ts = timespec_sub(ts, timekeeping_suspend_time);
-		xtime = timespec_add(xtime, ts);
-		wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
-		total_sleep_time = timespec_add(total_sleep_time, ts);
+		__timekeeping_inject_sleeptime(&ts);
 	}
 	/* re-base the last cycle value */
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ee24fa1935a..d017c2c82c4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -39,20 +39,26 @@
 #include "trace_stat.h"
 
 #define FTRACE_WARN_ON(cond)			\
-	do {					\
-		if (WARN_ON(cond))		\
+	({					\
+		int ___r = cond;		\
+		if (WARN_ON(___r))		\
 			ftrace_kill();		\
-	} while (0)
+		___r;				\
+	})
 
 #define FTRACE_WARN_ON_ONCE(cond)		\
-	do {					\
-		if (WARN_ON_ONCE(cond))		\
+	({					\
+		int ___r = cond;		\
+		if (WARN_ON_ONCE(___r))		\
 			ftrace_kill();		\
-	} while (0)
+		___r;				\
+	})
 
 /* hash bits for specific function selection */
 #define FTRACE_HASH_BITS 7
 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS)
+#define FTRACE_HASH_DEFAULT_BITS 10
+#define FTRACE_HASH_MAX_BITS 12
 
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
@@ -81,23 +87,29 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
 	.func		= ftrace_stub,
 };
 
-static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
+static struct ftrace_ops global_ops;
+
+static void
+ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 
 /*
- * Traverse the ftrace_list, invoking all entries.  The reason that we
+ * Traverse the ftrace_global_list, invoking all entries.  The reason that we
  * can use rcu_dereference_raw() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
  * mechanism.  The rcu_dereference_raw() calls are needed to handle
- * concurrent insertions into the ftrace_list.
+ * concurrent insertions into the ftrace_global_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
-static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
+static void ftrace_global_list_func(unsigned long ip,
+				    unsigned long parent_ip)
 {
-	struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
+	struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 
 	while (op != &ftrace_list_end) {
 		op->func(ip, parent_ip);
@@ -147,46 +159,69 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
 }
 #endif
 
-static int __register_ftrace_function(struct ftrace_ops *ops)
+static void update_global_ops(void)
 {
-	ops->next = ftrace_list;
+	ftrace_func_t func;
+
 	/*
-	 * We are entering ops into the ftrace_list but another
-	 * CPU might be walking that list. We need to make sure
-	 * the ops->next pointer is valid before another CPU sees
-	 * the ops pointer included into the ftrace_list.
+	 * If there's only one function registered, then call that
+	 * function directly. Otherwise, we need to iterate over the
+	 * registered callers.
 	 */
-	rcu_assign_pointer(ftrace_list, ops);
+	if (ftrace_global_list == &ftrace_list_end ||
+	    ftrace_global_list->next == &ftrace_list_end)
+		func = ftrace_global_list->func;
+	else
+		func = ftrace_global_list_func;
 
-	if (ftrace_enabled) {
-		ftrace_func_t func;
+	/* If we filter on pids, update to use the pid function */
+	if (!list_empty(&ftrace_pids)) {
+		set_ftrace_pid_function(func);
+		func = ftrace_pid_func;
+	}
 
-		if (ops->next == &ftrace_list_end)
-			func = ops->func;
-		else
-			func = ftrace_list_func;
+	global_ops.func = func;
+}
 
-		if (!list_empty(&ftrace_pids)) {
-			set_ftrace_pid_function(func);
-			func = ftrace_pid_func;
-		}
+static void update_ftrace_function(void)
+{
+	ftrace_func_t func;
+
+	update_global_ops();
+
+	/*
+	 * If we are at the end of the list and this ops is
+	 * not dynamic, then have the mcount trampoline call
+	 * the function directly
+	 */
+	if (ftrace_ops_list == &ftrace_list_end ||
+	    (ftrace_ops_list->next == &ftrace_list_end &&
+	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC)))
+		func = ftrace_ops_list->func;
+	else
+		func = ftrace_ops_list_func;
 
-		/*
-		 * For one func, simply call it directly.
-		 * For more than one func, call the chain.
-		 */
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-		ftrace_trace_function = func;
+	ftrace_trace_function = func;
 #else
-		__ftrace_trace_function = func;
-		ftrace_trace_function = ftrace_test_stop_func;
+	__ftrace_trace_function = func;
+	ftrace_trace_function = ftrace_test_stop_func;
 #endif
-	}
+}
 
-	return 0;
+static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+{
+	ops->next = *list;
+	/*
+	 * We are entering ops into the list but another
+	 * CPU might be walking that list. We need to make sure
+	 * the ops->next pointer is valid before another CPU sees
+	 * the ops pointer included into the list.
+	 */
+	rcu_assign_pointer(*list, ops);
 }
 
-static int __unregister_ftrace_function(struct ftrace_ops *ops)
+static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 {
 	struct ftrace_ops **p;
 
@@ -194,13 +229,12 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	 * If we are removing the last function, then simply point
 	 * to the ftrace_stub.
 	 */
-	if (ftrace_list == ops && ops->next == &ftrace_list_end) {
-		ftrace_trace_function = ftrace_stub;
-		ftrace_list = &ftrace_list_end;
+	if (*list == ops && ops->next == &ftrace_list_end) {
+		*list = &ftrace_list_end;
 		return 0;
 	}
 
-	for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next)
+	for (p = list; *p != &ftrace_list_end; p = &(*p)->next)
 		if (*p == ops)
 			break;
 
@@ -208,53 +242,83 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 		return -1;
 
 	*p = (*p)->next;
+	return 0;
+}
 
-	if (ftrace_enabled) {
-		/* If we only have one func left, then call that directly */
-		if (ftrace_list->next == &ftrace_list_end) {
-			ftrace_func_t func = ftrace_list->func;
+static int __register_ftrace_function(struct ftrace_ops *ops)
+{
+	if (ftrace_disabled)
+		return -ENODEV;
 
-			if (!list_empty(&ftrace_pids)) {
-				set_ftrace_pid_function(func);
-				func = ftrace_pid_func;
-			}
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-			ftrace_trace_function = func;
-#else
-			__ftrace_trace_function = func;
-#endif
-		}
-	}
+	if (FTRACE_WARN_ON(ops == &global_ops))
+		return -EINVAL;
+
+	if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EBUSY;
+
+	if (!core_kernel_data((unsigned long)ops))
+		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
+
+	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
+		int first = ftrace_global_list == &ftrace_list_end;
+		add_ftrace_ops(&ftrace_global_list, ops);
+		ops->flags |= FTRACE_OPS_FL_ENABLED;
+		if (first)
+			add_ftrace_ops(&ftrace_ops_list, &global_ops);
+	} else
+		add_ftrace_ops(&ftrace_ops_list, ops);
+
+	if (ftrace_enabled)
+		update_ftrace_function();
 
 	return 0;
 }
 
-static void ftrace_update_pid_func(void)
+static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
-	ftrace_func_t func;
+	int ret;
 
-	if (ftrace_trace_function == ftrace_stub)
-		return;
+	if (ftrace_disabled)
+		return -ENODEV;
 
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	func = ftrace_trace_function;
-#else
-	func = __ftrace_trace_function;
-#endif
+	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
+		return -EBUSY;
 
-	if (!list_empty(&ftrace_pids)) {
-		set_ftrace_pid_function(func);
-		func = ftrace_pid_func;
-	} else {
-		if (func == ftrace_pid_func)
-			func = ftrace_pid_function;
-	}
+	if (FTRACE_WARN_ON(ops == &global_ops))
+		return -EINVAL;
 
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	ftrace_trace_function = func;
-#else
-	__ftrace_trace_function = func;
-#endif
+	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
+		ret = remove_ftrace_ops(&ftrace_global_list, ops);
+		if (!ret && ftrace_global_list == &ftrace_list_end)
+			ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops);
+		if (!ret)
+			ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+	} else
+		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
+
+	if (ret < 0)
+		return ret;
+
+	if (ftrace_enabled)
+		update_ftrace_function();
+
+	/*
+	 * Dynamic ops may be freed, we must make sure that all
+	 * callers are done before leaving this function.
+	 */
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+		synchronize_sched();
+
+	return 0;
+}
+
+static void ftrace_update_pid_func(void)
+{
+	/* Only do something if we are tracing something */
+	if (ftrace_trace_function == ftrace_stub)
+		return;
+
+	update_ftrace_function();
 }
 
 #ifdef CONFIG_FUNCTION_PROFILER
@@ -888,8 +952,35 @@ enum {
 	FTRACE_START_FUNC_RET		= (1 << 3),
 	FTRACE_STOP_FUNC_RET		= (1 << 4),
 };
+struct ftrace_func_entry {
+	struct hlist_node hlist;
+	unsigned long ip;
+};
 
-static int ftrace_filtered;
+struct ftrace_hash {
+	unsigned long		size_bits;
+	struct hlist_head	*buckets;
+	unsigned long		count;
+	struct rcu_head		rcu;
+};
+
+/*
+ * We make these constant because no one should touch them,
+ * but they are used as the default "empty hash", to avoid allocating
+ * it all the time. These are in a read only section such that if
+ * anyone does try to modify it, it will cause an exception.
+ */
+static const struct hlist_head empty_buckets[1];
+static const struct ftrace_hash empty_hash = {
+	.buckets = (struct hlist_head *)empty_buckets,
+};
+#define EMPTY_HASH	((struct ftrace_hash *)&empty_hash)
+
+static struct ftrace_ops global_ops = {
+	.func			= ftrace_stub,
+	.notrace_hash		= EMPTY_HASH,
+	.filter_hash		= EMPTY_HASH,
+};
 
 static struct dyn_ftrace *ftrace_new_addrs;
 
@@ -912,6 +1003,269 @@ static struct ftrace_page	*ftrace_pages;
 
 static struct dyn_ftrace *ftrace_free_records;
 
+static struct ftrace_func_entry *
+ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
+{
+	unsigned long key;
+	struct ftrace_func_entry *entry;
+	struct hlist_head *hhd;
+	struct hlist_node *n;
+
+	if (!hash->count)
+		return NULL;
+
+	if (hash->size_bits > 0)
+		key = hash_long(ip, hash->size_bits);
+	else
+		key = 0;
+
+	hhd = &hash->buckets[key];
+
+	hlist_for_each_entry_rcu(entry, n, hhd, hlist) {
+		if (entry->ip == ip)
+			return entry;
+	}
+	return NULL;
+}
+
+static void __add_hash_entry(struct ftrace_hash *hash,
+			     struct ftrace_func_entry *entry)
+{
+	struct hlist_head *hhd;
+	unsigned long key;
+
+	if (hash->size_bits)
+		key = hash_long(entry->ip, hash->size_bits);
+	else
+		key = 0;
+
+	hhd = &hash->buckets[key];
+	hlist_add_head(&entry->hlist, hhd);
+	hash->count++;
+}
+
+static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
+{
+	struct ftrace_func_entry *entry;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->ip = ip;
+	__add_hash_entry(hash, entry);
+
+	return 0;
+}
+
+static void
+free_hash_entry(struct ftrace_hash *hash,
+		  struct ftrace_func_entry *entry)
+{
+	hlist_del(&entry->hlist);
+	kfree(entry);
+	hash->count--;
+}
+
+static void
+remove_hash_entry(struct ftrace_hash *hash,
+		  struct ftrace_func_entry *entry)
+{
+	hlist_del(&entry->hlist);
+	hash->count--;
+}
+
+static void ftrace_hash_clear(struct ftrace_hash *hash)
+{
+	struct hlist_head *hhd;
+	struct hlist_node *tp, *tn;
+	struct ftrace_func_entry *entry;
+	int size = 1 << hash->size_bits;
+	int i;
+
+	if (!hash->count)
+		return;
+
+	for (i = 0; i < size; i++) {
+		hhd = &hash->buckets[i];
+		hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist)
+			free_hash_entry(hash, entry);
+	}
+	FTRACE_WARN_ON(hash->count);
+}
+
+static void free_ftrace_hash(struct ftrace_hash *hash)
+{
+	if (!hash || hash == EMPTY_HASH)
+		return;
+	ftrace_hash_clear(hash);
+	kfree(hash->buckets);
+	kfree(hash);
+}
+
+static void __free_ftrace_hash_rcu(struct rcu_head *rcu)
+{
+	struct ftrace_hash *hash;
+
+	hash = container_of(rcu, struct ftrace_hash, rcu);
+	free_ftrace_hash(hash);
+}
+
+static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
+{
+	if (!hash || hash == EMPTY_HASH)
+		return;
+	call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
+}
+
+static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
+{
+	struct ftrace_hash *hash;
+	int size;
+
+	hash = kzalloc(sizeof(*hash), GFP_KERNEL);
+	if (!hash)
+		return NULL;
+
+	size = 1 << size_bits;
+	hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL);
+
+	if (!hash->buckets) {
+		kfree(hash);
+		return NULL;
+	}
+
+	hash->size_bits = size_bits;
+
+	return hash;
+}
+
+static struct ftrace_hash *
+alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
+{
+	struct ftrace_func_entry *entry;
+	struct ftrace_hash *new_hash;
+	struct hlist_node *tp;
+	int size;
+	int ret;
+	int i;
+
+	new_hash = alloc_ftrace_hash(size_bits);
+	if (!new_hash)
+		return NULL;
+
+	/* Empty hash? */
+	if (!hash || !hash->count)
+		return new_hash;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, tp, &hash->buckets[i], hlist) {
+			ret = add_hash_entry(new_hash, entry->ip);
+			if (ret < 0)
+				goto free_hash;
+		}
+	}
+
+	FTRACE_WARN_ON(new_hash->count != hash->count);
+
+	return new_hash;
+
+ free_hash:
+	free_ftrace_hash(new_hash);
+	return NULL;
+}
+
+static int
+ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
+{
+	struct ftrace_func_entry *entry;
+	struct hlist_node *tp, *tn;
+	struct hlist_head *hhd;
+	struct ftrace_hash *old_hash;
+	struct ftrace_hash *new_hash;
+	unsigned long key;
+	int size = src->count;
+	int bits = 0;
+	int i;
+
+	/*
+	 * If the new source is empty, just free dst and assign it
+	 * the empty_hash.
+	 */
+	if (!src->count) {
+		free_ftrace_hash_rcu(*dst);
+		rcu_assign_pointer(*dst, EMPTY_HASH);
+		return 0;
+	}
+
+	/*
+	 * Make the hash size about 1/2 the # found
+	 */
+	for (size /= 2; size; size >>= 1)
+		bits++;
+
+	/* Don't allocate too much */
+	if (bits > FTRACE_HASH_MAX_BITS)
+		bits = FTRACE_HASH_MAX_BITS;
+
+	new_hash = alloc_ftrace_hash(bits);
+	if (!new_hash)
+		return -ENOMEM;
+
+	size = 1 << src->size_bits;
+	for (i = 0; i < size; i++) {
+		hhd = &src->buckets[i];
+		hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) {
+			if (bits > 0)
+				key = hash_long(entry->ip, bits);
+			else
+				key = 0;
+			remove_hash_entry(src, entry);
+			__add_hash_entry(new_hash, entry);
+		}
+	}
+
+	old_hash = *dst;
+	rcu_assign_pointer(*dst, new_hash);
+	free_ftrace_hash_rcu(old_hash);
+
+	return 0;
+}
+
+/*
+ * Test the hashes for this ops to see if we want to call
+ * the ops->func or not.
+ *
+ * It's a match if the ip is in the ops->filter_hash or
+ * the filter_hash does not exist or is empty,
+ *  AND
+ * the ip is not in the ops->notrace_hash.
+ *
+ * This needs to be called with preemption disabled as
+ * the hashes are freed with call_rcu_sched().
+ */
+static int
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+{
+	struct ftrace_hash *filter_hash;
+	struct ftrace_hash *notrace_hash;
+	int ret;
+
+	filter_hash = rcu_dereference_raw(ops->filter_hash);
+	notrace_hash = rcu_dereference_raw(ops->notrace_hash);
+
+	if ((!filter_hash || !filter_hash->count ||
+	     ftrace_lookup_ip(filter_hash, ip)) &&
+	    (!notrace_hash || !notrace_hash->count ||
+	     !ftrace_lookup_ip(notrace_hash, ip)))
+		ret = 1;
+	else
+		ret = 0;
+
+	return ret;
+}
+
 /*
  * This is a double for. Do not use 'break' to break out of the loop,
  * you must use a goto.
@@ -926,6 +1280,105 @@ static struct dyn_ftrace *ftrace_free_records;
 		}				\
 	}
 
+static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
+				     int filter_hash,
+				     bool inc)
+{
+	struct ftrace_hash *hash;
+	struct ftrace_hash *other_hash;
+	struct ftrace_page *pg;
+	struct dyn_ftrace *rec;
+	int count = 0;
+	int all = 0;
+
+	/* Only update if the ops has been registered */
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return;
+
+	/*
+	 * In the filter_hash case:
+	 *   If the count is zero, we update all records.
+	 *   Otherwise we just update the items in the hash.
+	 *
+	 * In the notrace_hash case:
+	 *   We enable the update in the hash.
+	 *   As disabling notrace means enabling the tracing,
+	 *   and enabling notrace means disabling, the inc variable
+	 *   gets inversed.
+	 */
+	if (filter_hash) {
+		hash = ops->filter_hash;
+		other_hash = ops->notrace_hash;
+		if (!hash || !hash->count)
+			all = 1;
+	} else {
+		inc = !inc;
+		hash = ops->notrace_hash;
+		other_hash = ops->filter_hash;
+		/*
+		 * If the notrace hash has no items,
+		 * then there's nothing to do.
+		 */
+		if (hash && !hash->count)
+			return;
+	}
+
+	do_for_each_ftrace_rec(pg, rec) {
+		int in_other_hash = 0;
+		int in_hash = 0;
+		int match = 0;
+
+		if (all) {
+			/*
+			 * Only the filter_hash affects all records.
+			 * Update if the record is not in the notrace hash.
+			 */
+			if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip))
+				match = 1;
+		} else {
+			in_hash = hash && !!ftrace_lookup_ip(hash, rec->ip);
+			in_other_hash = other_hash && !!ftrace_lookup_ip(other_hash, rec->ip);
+
+			/*
+			 *
+			 */
+			if (filter_hash && in_hash && !in_other_hash)
+				match = 1;
+			else if (!filter_hash && in_hash &&
+				 (in_other_hash || !other_hash->count))
+				match = 1;
+		}
+		if (!match)
+			continue;
+
+		if (inc) {
+			rec->flags++;
+			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX))
+				return;
+		} else {
+			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0))
+				return;
+			rec->flags--;
+		}
+		count++;
+		/* Shortcut, if we handled all records, we are done. */
+		if (!all && count == hash->count)
+			return;
+	} while_for_each_ftrace_rec();
+}
+
+static void ftrace_hash_rec_disable(struct ftrace_ops *ops,
+				    int filter_hash)
+{
+	__ftrace_hash_rec_update(ops, filter_hash, 0);
+}
+
+static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
+				   int filter_hash)
+{
+	__ftrace_hash_rec_update(ops, filter_hash, 1);
+}
+
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
 	rec->freelist = ftrace_free_records;
@@ -1047,18 +1500,18 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
 	/*
-	 * If this record is not to be traced or we want to disable it,
-	 * then disable it.
+	 * If we are enabling tracing:
+	 *
+	 *   If the record has a ref count, then we need to enable it
+	 *   because someone is using it.
 	 *
-	 * If we want to enable it and filtering is off, then enable it.
+	 *   Otherwise we make sure its disabled.
 	 *
-	 * If we want to enable it and filtering is on, enable it only if
-	 * it's filtered
+	 * If we are disabling tracing, then disable all records that
+	 * are enabled.
 	 */
-	if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
-		if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
-			flag = FTRACE_FL_ENABLED;
-	}
+	if (enable && (rec->flags & ~FTRACE_FL_MASK))
+		flag = FTRACE_FL_ENABLED;
 
 	/* If the state of this record hasn't changed, then do nothing */
 	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
@@ -1079,19 +1532,16 @@ static void ftrace_replace_code(int enable)
 	struct ftrace_page *pg;
 	int failed;
 
+	if (unlikely(ftrace_disabled))
+		return;
+
 	do_for_each_ftrace_rec(pg, rec) {
-		/*
-		 * Skip over free records, records that have
-		 * failed and not converted.
-		 */
-		if (rec->flags & FTRACE_FL_FREE ||
-		    rec->flags & FTRACE_FL_FAILED ||
-		    !(rec->flags & FTRACE_FL_CONVERTED))
+		/* Skip over free records */
+		if (rec->flags & FTRACE_FL_FREE)
 			continue;
 
 		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
-			rec->flags |= FTRACE_FL_FAILED;
 			ftrace_bug(failed, rec->ip);
 			/* Stop processing */
 			return;
@@ -1107,10 +1557,12 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 
 	ip = rec->ip;
 
+	if (unlikely(ftrace_disabled))
+		return 0;
+
 	ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
 	if (ret) {
 		ftrace_bug(ret, ip);
-		rec->flags |= FTRACE_FL_FAILED;
 		return 0;
 	}
 	return 1;
@@ -1171,6 +1623,7 @@ static void ftrace_run_update_code(int command)
 
 static ftrace_func_t saved_ftrace_func;
 static int ftrace_start_up;
+static int global_start_up;
 
 static void ftrace_startup_enable(int command)
 {
@@ -1185,19 +1638,36 @@ static void ftrace_startup_enable(int command)
 	ftrace_run_update_code(command);
 }
 
-static void ftrace_startup(int command)
+static void ftrace_startup(struct ftrace_ops *ops, int command)
 {
+	bool hash_enable = true;
+
 	if (unlikely(ftrace_disabled))
 		return;
 
 	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
 
+	/* ops marked global share the filter hashes */
+	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
+		ops = &global_ops;
+		/* Don't update hash if global is already set */
+		if (global_start_up)
+			hash_enable = false;
+		global_start_up++;
+	}
+
+	ops->flags |= FTRACE_OPS_FL_ENABLED;
+	if (hash_enable)
+		ftrace_hash_rec_enable(ops, 1);
+
 	ftrace_startup_enable(command);
 }
 
-static void ftrace_shutdown(int command)
+static void ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
+	bool hash_disable = true;
+
 	if (unlikely(ftrace_disabled))
 		return;
 
@@ -1209,6 +1679,23 @@ static void ftrace_shutdown(int command)
 	 */
 	WARN_ON_ONCE(ftrace_start_up < 0);
 
+	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
+		ops = &global_ops;
+		global_start_up--;
+		WARN_ON_ONCE(global_start_up < 0);
+		/* Don't update hash if global still has users */
+		if (global_start_up) {
+			WARN_ON_ONCE(!ftrace_start_up);
+			hash_disable = false;
+		}
+	}
+
+	if (hash_disable)
+		ftrace_hash_rec_disable(ops, 1);
+
+	if (ops != &global_ops || !global_start_up)
+		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+
 	if (!ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
@@ -1273,10 +1760,10 @@ static int ftrace_update_code(struct module *mod)
 		 */
 		if (!ftrace_code_disable(mod, p)) {
 			ftrace_free_rec(p);
-			continue;
+			/* Game over */
+			break;
 		}
 
-		p->flags |= FTRACE_FL_CONVERTED;
 		ftrace_update_cnt++;
 
 		/*
@@ -1351,9 +1838,9 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
 enum {
 	FTRACE_ITER_FILTER	= (1 << 0),
 	FTRACE_ITER_NOTRACE	= (1 << 1),
-	FTRACE_ITER_FAILURES	= (1 << 2),
-	FTRACE_ITER_PRINTALL	= (1 << 3),
-	FTRACE_ITER_HASH	= (1 << 4),
+	FTRACE_ITER_PRINTALL	= (1 << 2),
+	FTRACE_ITER_HASH	= (1 << 3),
+	FTRACE_ITER_ENABLED	= (1 << 4),
 };
 
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
@@ -1365,6 +1852,8 @@ struct ftrace_iterator {
 	struct dyn_ftrace		*func;
 	struct ftrace_func_probe	*probe;
 	struct trace_parser		parser;
+	struct ftrace_hash		*hash;
+	struct ftrace_ops		*ops;
 	int				hidx;
 	int				idx;
 	unsigned			flags;
@@ -1461,8 +1950,12 @@ static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
+	struct ftrace_ops *ops = &global_ops;
 	struct dyn_ftrace *rec = NULL;
 
+	if (unlikely(ftrace_disabled))
+		return NULL;
+
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_next(m, pos);
 
@@ -1483,17 +1976,15 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		rec = &iter->pg->records[iter->idx++];
 		if ((rec->flags & FTRACE_FL_FREE) ||
 
-		    (!(iter->flags & FTRACE_ITER_FAILURES) &&
-		     (rec->flags & FTRACE_FL_FAILED)) ||
-
-		    ((iter->flags & FTRACE_ITER_FAILURES) &&
-		     !(rec->flags & FTRACE_FL_FAILED)) ||
-
 		    ((iter->flags & FTRACE_ITER_FILTER) &&
-		     !(rec->flags & FTRACE_FL_FILTER)) ||
+		     !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) ||
 
 		    ((iter->flags & FTRACE_ITER_NOTRACE) &&
-		     !(rec->flags & FTRACE_FL_NOTRACE))) {
+		     !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) ||
+
+		    ((iter->flags & FTRACE_ITER_ENABLED) &&
+		     !(rec->flags & ~FTRACE_FL_MASK))) {
+
 			rec = NULL;
 			goto retry;
 		}
@@ -1517,10 +2008,15 @@ static void reset_iter_read(struct ftrace_iterator *iter)
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
+	struct ftrace_ops *ops = &global_ops;
 	void *p = NULL;
 	loff_t l;
 
 	mutex_lock(&ftrace_lock);
+
+	if (unlikely(ftrace_disabled))
+		return NULL;
+
 	/*
 	 * If an lseek was done, then reset and start from beginning.
 	 */
@@ -1532,7 +2028,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	 * off, we can short cut and just print out that all
 	 * functions are enabled.
 	 */
-	if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) {
+	if (iter->flags & FTRACE_ITER_FILTER && !ops->filter_hash->count) {
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
@@ -1590,7 +2086,11 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	seq_printf(m, "%ps\n", (void *)rec->ip);
+	seq_printf(m, "%ps", (void *)rec->ip);
+	if (iter->flags & FTRACE_ITER_ENABLED)
+		seq_printf(m, " (%ld)",
+			   rec->flags & ~FTRACE_FL_MASK);
+	seq_printf(m, "\n");
 
 	return 0;
 }
@@ -1630,44 +2130,46 @@ ftrace_avail_open(struct inode *inode, struct file *file)
 }
 
 static int
-ftrace_failures_open(struct inode *inode, struct file *file)
+ftrace_enabled_open(struct inode *inode, struct file *file)
 {
-	int ret;
-	struct seq_file *m;
 	struct ftrace_iterator *iter;
+	int ret;
+
+	if (unlikely(ftrace_disabled))
+		return -ENODEV;
+
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return -ENOMEM;
+
+	iter->pg = ftrace_pages_start;
+	iter->flags = FTRACE_ITER_ENABLED;
 
-	ret = ftrace_avail_open(inode, file);
+	ret = seq_open(file, &show_ftrace_seq_ops);
 	if (!ret) {
-		m = file->private_data;
-		iter = m->private;
-		iter->flags = FTRACE_ITER_FAILURES;
+		struct seq_file *m = file->private_data;
+
+		m->private = iter;
+	} else {
+		kfree(iter);
 	}
 
 	return ret;
 }
 
-
-static void ftrace_filter_reset(int enable)
+static void ftrace_filter_reset(struct ftrace_hash *hash)
 {
-	struct ftrace_page *pg;
-	struct dyn_ftrace *rec;
-	unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
-
 	mutex_lock(&ftrace_lock);
-	if (enable)
-		ftrace_filtered = 0;
-	do_for_each_ftrace_rec(pg, rec) {
-		if (rec->flags & FTRACE_FL_FAILED)
-			continue;
-		rec->flags &= ~type;
-	} while_for_each_ftrace_rec();
+	ftrace_hash_clear(hash);
 	mutex_unlock(&ftrace_lock);
 }
 
 static int
-ftrace_regex_open(struct inode *inode, struct file *file, int enable)
+ftrace_regex_open(struct ftrace_ops *ops, int flag,
+		  struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
+	struct ftrace_hash *hash;
 	int ret = 0;
 
 	if (unlikely(ftrace_disabled))
@@ -1682,21 +2184,42 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 		return -ENOMEM;
 	}
 
+	if (flag & FTRACE_ITER_NOTRACE)
+		hash = ops->notrace_hash;
+	else
+		hash = ops->filter_hash;
+
+	iter->ops = ops;
+	iter->flags = flag;
+
+	if (file->f_mode & FMODE_WRITE) {
+		mutex_lock(&ftrace_lock);
+		iter->hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, hash);
+		mutex_unlock(&ftrace_lock);
+
+		if (!iter->hash) {
+			trace_parser_put(&iter->parser);
+			kfree(iter);
+			return -ENOMEM;
+		}
+	}
+
 	mutex_lock(&ftrace_regex_lock);
+
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		ftrace_filter_reset(enable);
+		ftrace_filter_reset(iter->hash);
 
 	if (file->f_mode & FMODE_READ) {
 		iter->pg = ftrace_pages_start;
-		iter->flags = enable ? FTRACE_ITER_FILTER :
-			FTRACE_ITER_NOTRACE;
 
 		ret = seq_open(file, &show_ftrace_seq_ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = iter;
 		} else {
+			/* Failed */
+			free_ftrace_hash(iter->hash);
 			trace_parser_put(&iter->parser);
 			kfree(iter);
 		}
@@ -1710,13 +2233,15 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 static int
 ftrace_filter_open(struct inode *inode, struct file *file)
 {
-	return ftrace_regex_open(inode, file, 1);
+	return ftrace_regex_open(&global_ops, FTRACE_ITER_FILTER,
+				 inode, file);
 }
 
 static int
 ftrace_notrace_open(struct inode *inode, struct file *file)
 {
-	return ftrace_regex_open(inode, file, 0);
+	return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE,
+				 inode, file);
 }
 
 static loff_t
@@ -1761,86 +2286,99 @@ static int ftrace_match(char *str, char *regex, int len, int type)
 }
 
 static int
-ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type)
+enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not)
+{
+	struct ftrace_func_entry *entry;
+	int ret = 0;
+
+	entry = ftrace_lookup_ip(hash, rec->ip);
+	if (not) {
+		/* Do nothing if it doesn't exist */
+		if (!entry)
+			return 0;
+
+		free_hash_entry(hash, entry);
+	} else {
+		/* Do nothing if it exists */
+		if (entry)
+			return 0;
+
+		ret = add_hash_entry(hash, rec->ip);
+	}
+	return ret;
+}
+
+static int
+ftrace_match_record(struct dyn_ftrace *rec, char *mod,
+		    char *regex, int len, int type)
 {
 	char str[KSYM_SYMBOL_LEN];
+	char *modname;
+
+	kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
+
+	if (mod) {
+		/* module lookup requires matching the module */
+		if (!modname || strcmp(modname, mod))
+			return 0;
+
+		/* blank search means to match all funcs in the mod */
+		if (!len)
+			return 1;
+	}
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
 	return ftrace_match(str, regex, len, type);
 }
 
-static int ftrace_match_records(char *buff, int len, int enable)
+static int
+match_records(struct ftrace_hash *hash, char *buff,
+	      int len, char *mod, int not)
 {
-	unsigned int search_len;
+	unsigned search_len = 0;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
-	unsigned long flag;
-	char *search;
-	int type;
-	int not;
+	int type = MATCH_FULL;
+	char *search = buff;
 	int found = 0;
+	int ret;
 
-	flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
-	type = filter_parse_regex(buff, len, &search, &not);
-
-	search_len = strlen(search);
+	if (len) {
+		type = filter_parse_regex(buff, len, &search, &not);
+		search_len = strlen(search);
+	}
 
 	mutex_lock(&ftrace_lock);
-	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & FTRACE_FL_FAILED)
-			continue;
+	if (unlikely(ftrace_disabled))
+		goto out_unlock;
 
-		if (ftrace_match_record(rec, search, search_len, type)) {
-			if (not)
-				rec->flags &= ~flag;
-			else
-				rec->flags |= flag;
+	do_for_each_ftrace_rec(pg, rec) {
+
+		if (ftrace_match_record(rec, mod, search, search_len, type)) {
+			ret = enter_record(hash, rec, not);
+			if (ret < 0) {
+				found = ret;
+				goto out_unlock;
+			}
 			found = 1;
 		}
-		/*
-		 * Only enable filtering if we have a function that
-		 * is filtered on.
-		 */
-		if (enable && (rec->flags & FTRACE_FL_FILTER))
-			ftrace_filtered = 1;
 	} while_for_each_ftrace_rec();
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
 
 	return found;
 }
 
 static int
-ftrace_match_module_record(struct dyn_ftrace *rec, char *mod,
-			   char *regex, int len, int type)
+ftrace_match_records(struct ftrace_hash *hash, char *buff, int len)
 {
-	char str[KSYM_SYMBOL_LEN];
-	char *modname;
-
-	kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
-
-	if (!modname || strcmp(modname, mod))
-		return 0;
-
-	/* blank search means to match all funcs in the mod */
-	if (len)
-		return ftrace_match(str, regex, len, type);
-	else
-		return 1;
+	return match_records(hash, buff, len, NULL, 0);
 }
 
-static int ftrace_match_module_records(char *buff, char *mod, int enable)
+static int
+ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod)
 {
-	unsigned search_len = 0;
-	struct ftrace_page *pg;
-	struct dyn_ftrace *rec;
-	int type = MATCH_FULL;
-	char *search = buff;
-	unsigned long flag;
 	int not = 0;
-	int found = 0;
-
-	flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
 
 	/* blank or '*' mean the same */
 	if (strcmp(buff, "*") == 0)
@@ -1852,32 +2390,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable)
 		not = 1;
 	}
 
-	if (strlen(buff)) {
-		type = filter_parse_regex(buff, strlen(buff), &search, &not);
-		search_len = strlen(search);
-	}
-
-	mutex_lock(&ftrace_lock);
-	do_for_each_ftrace_rec(pg, rec) {
-
-		if (rec->flags & FTRACE_FL_FAILED)
-			continue;
-
-		if (ftrace_match_module_record(rec, mod,
-					       search, search_len, type)) {
-			if (not)
-				rec->flags &= ~flag;
-			else
-				rec->flags |= flag;
-			found = 1;
-		}
-		if (enable && (rec->flags & FTRACE_FL_FILTER))
-			ftrace_filtered = 1;
-
-	} while_for_each_ftrace_rec();
-	mutex_unlock(&ftrace_lock);
-
-	return found;
+	return match_records(hash, buff, strlen(buff), mod, not);
 }
 
 /*
@@ -1888,7 +2401,10 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable)
 static int
 ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
 {
+	struct ftrace_ops *ops = &global_ops;
+	struct ftrace_hash *hash;
 	char *mod;
+	int ret = -EINVAL;
 
 	/*
 	 * cmd == 'mod' because we only registered this func
@@ -1900,15 +2416,24 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
 
 	/* we must have a module name */
 	if (!param)
-		return -EINVAL;
+		return ret;
 
 	mod = strsep(&param, ":");
 	if (!strlen(mod))
-		return -EINVAL;
+		return ret;
 
-	if (ftrace_match_module_records(func, mod, enable))
-		return 0;
-	return -EINVAL;
+	if (enable)
+		hash = ops->filter_hash;
+	else
+		hash = ops->notrace_hash;
+
+	ret = ftrace_match_module_records(hash, func, mod);
+	if (!ret)
+		ret = -EINVAL;
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static struct ftrace_func_command ftrace_mod_cmd = {
@@ -1959,6 +2484,7 @@ static int ftrace_probe_registered;
 
 static void __enable_ftrace_function_probe(void)
 {
+	int ret;
 	int i;
 
 	if (ftrace_probe_registered)
@@ -1973,13 +2499,16 @@ static void __enable_ftrace_function_probe(void)
 	if (i == FTRACE_FUNC_HASHSIZE)
 		return;
 
-	__register_ftrace_function(&trace_probe_ops);
-	ftrace_startup(0);
+	ret = __register_ftrace_function(&trace_probe_ops);
+	if (!ret)
+		ftrace_startup(&trace_probe_ops, 0);
+
 	ftrace_probe_registered = 1;
 }
 
 static void __disable_ftrace_function_probe(void)
 {
+	int ret;
 	int i;
 
 	if (!ftrace_probe_registered)
@@ -1992,8 +2521,10 @@ static void __disable_ftrace_function_probe(void)
 	}
 
 	/* no more funcs left */
-	__unregister_ftrace_function(&trace_probe_ops);
-	ftrace_shutdown(0);
+	ret = __unregister_ftrace_function(&trace_probe_ops);
+	if (!ret)
+		ftrace_shutdown(&trace_probe_ops, 0);
+
 	ftrace_probe_registered = 0;
 }
 
@@ -2029,12 +2560,13 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		return -EINVAL;
 
 	mutex_lock(&ftrace_lock);
-	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & FTRACE_FL_FAILED)
-			continue;
+	if (unlikely(ftrace_disabled))
+		goto out_unlock;
+
+	do_for_each_ftrace_rec(pg, rec) {
 
-		if (!ftrace_match_record(rec, search, len, type))
+		if (!ftrace_match_record(rec, NULL, search, len, type))
 			continue;
 
 		entry = kmalloc(sizeof(*entry), GFP_KERNEL);
@@ -2195,18 +2727,22 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd)
 	return ret;
 }
 
-static int ftrace_process_regex(char *buff, int len, int enable)
+static int ftrace_process_regex(struct ftrace_hash *hash,
+				char *buff, int len, int enable)
 {
 	char *func, *command, *next = buff;
 	struct ftrace_func_command *p;
-	int ret = -EINVAL;
+	int ret;
 
 	func = strsep(&next, ":");
 
 	if (!next) {
-		if (ftrace_match_records(func, len, enable))
-			return 0;
-		return ret;
+		ret = ftrace_match_records(hash, func, len);
+		if (!ret)
+			ret = -EINVAL;
+		if (ret < 0)
+			return ret;
+		return 0;
 	}
 
 	/* command found */
@@ -2239,6 +2775,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 
 	mutex_lock(&ftrace_regex_lock);
 
+	ret = -ENODEV;
+	if (unlikely(ftrace_disabled))
+		goto out_unlock;
+
 	if (file->f_mode & FMODE_READ) {
 		struct seq_file *m = file->private_data;
 		iter = m->private;
@@ -2250,7 +2790,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 
 	if (read >= 0 && trace_parser_loaded(parser) &&
 	    !trace_parser_cont(parser)) {
-		ret = ftrace_process_regex(parser->buffer,
+		ret = ftrace_process_regex(iter->hash, parser->buffer,
 					   parser->idx, enable);
 		trace_parser_clear(parser);
 		if (ret)
@@ -2278,22 +2818,49 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf,
 	return ftrace_regex_write(file, ubuf, cnt, ppos, 0);
 }
 
-static void
-ftrace_set_regex(unsigned char *buf, int len, int reset, int enable)
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+		 int reset, int enable)
 {
+	struct ftrace_hash **orig_hash;
+	struct ftrace_hash *hash;
+	int ret;
+
+	/* All global ops uses the global ops filters */
+	if (ops->flags & FTRACE_OPS_FL_GLOBAL)
+		ops = &global_ops;
+
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
+
+	if (enable)
+		orig_hash = &ops->filter_hash;
+	else
+		orig_hash = &ops->notrace_hash;
+
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (!hash)
+		return -ENOMEM;
 
 	mutex_lock(&ftrace_regex_lock);
 	if (reset)
-		ftrace_filter_reset(enable);
+		ftrace_filter_reset(hash);
 	if (buf)
-		ftrace_match_records(buf, len, enable);
+		ftrace_match_records(hash, buf, len);
+
+	mutex_lock(&ftrace_lock);
+	ret = ftrace_hash_move(orig_hash, hash);
+	mutex_unlock(&ftrace_lock);
+
 	mutex_unlock(&ftrace_regex_lock);
+
+	free_ftrace_hash(hash);
+	return ret;
 }
 
 /**
  * ftrace_set_filter - set a function to filter on in ftrace
+ * @ops - the ops to set the filter with
  * @buf - the string that holds the function filter text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -2301,13 +2868,16 @@ ftrace_set_regex(unsigned char *buf, int len, int reset, int enable)
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
  */
-void ftrace_set_filter(unsigned char *buf, int len, int reset)
+void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+		       int len, int reset)
 {
-	ftrace_set_regex(buf, len, reset, 1);
+	ftrace_set_regex(ops, buf, len, reset, 1);
 }
+EXPORT_SYMBOL_GPL(ftrace_set_filter);
 
 /**
  * ftrace_set_notrace - set a function to not trace in ftrace
+ * @ops - the ops to set the notrace filter with
  * @buf - the string that holds the function notrace text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -2316,10 +2886,44 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset)
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
  * for tracing.
  */
-void ftrace_set_notrace(unsigned char *buf, int len, int reset)
+void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+			int len, int reset)
 {
-	ftrace_set_regex(buf, len, reset, 0);
+	ftrace_set_regex(ops, buf, len, reset, 0);
 }
+EXPORT_SYMBOL_GPL(ftrace_set_notrace);
+/**
+ * ftrace_set_filter - set a function to filter on in ftrace
+ * @ops - the ops to set the filter with
+ * @buf - the string that holds the function filter text.
+ * @len - the length of the string.
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled.
+ * If @buf is NULL and reset is set, all functions will be enabled for tracing.
+ */
+void ftrace_set_global_filter(unsigned char *buf, int len, int reset)
+{
+	ftrace_set_regex(&global_ops, buf, len, reset, 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_global_filter);
+
+/**
+ * ftrace_set_notrace - set a function to not trace in ftrace
+ * @ops - the ops to set the notrace filter with
+ * @buf - the string that holds the function notrace text.
+ * @len - the length of the string.
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Notrace Filters denote which functions should not be enabled when tracing
+ * is enabled. If @buf is NULL and reset is set, all functions will be enabled
+ * for tracing.
+ */
+void ftrace_set_global_notrace(unsigned char *buf, int len, int reset)
+{
+	ftrace_set_regex(&global_ops, buf, len, reset, 0);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_global_notrace);
 
 /*
  * command line interface to allow users to set filters on boot up.
@@ -2370,22 +2974,23 @@ static void __init set_ftrace_early_graph(char *buf)
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-static void __init set_ftrace_early_filter(char *buf, int enable)
+static void __init
+set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable)
 {
 	char *func;
 
 	while (buf) {
 		func = strsep(&buf, ",");
-		ftrace_set_regex(func, strlen(func), 0, enable);
+		ftrace_set_regex(ops, 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);
+		set_ftrace_early_filter(&global_ops, ftrace_filter_buf, 1);
 	if (ftrace_notrace_buf[0])
-		set_ftrace_early_filter(ftrace_notrace_buf, 0);
+		set_ftrace_early_filter(&global_ops, ftrace_notrace_buf, 0);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (ftrace_graph_buf[0])
 		set_ftrace_early_graph(ftrace_graph_buf);
@@ -2393,11 +2998,14 @@ static void __init set_ftrace_early_filters(void)
 }
 
 static int
-ftrace_regex_release(struct inode *inode, struct file *file, int enable)
+ftrace_regex_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
 	struct ftrace_iterator *iter;
+	struct ftrace_hash **orig_hash;
 	struct trace_parser *parser;
+	int filter_hash;
+	int ret;
 
 	mutex_lock(&ftrace_regex_lock);
 	if (file->f_mode & FMODE_READ) {
@@ -2410,33 +3018,41 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 	parser = &iter->parser;
 	if (trace_parser_loaded(parser)) {
 		parser->buffer[parser->idx] = 0;
-		ftrace_match_records(parser->buffer, parser->idx, enable);
+		ftrace_match_records(iter->hash, parser->buffer, parser->idx);
 	}
 
-	mutex_lock(&ftrace_lock);
-	if (ftrace_start_up && ftrace_enabled)
-		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-	mutex_unlock(&ftrace_lock);
-
 	trace_parser_put(parser);
+
+	if (file->f_mode & FMODE_WRITE) {
+		filter_hash = !!(iter->flags & FTRACE_ITER_FILTER);
+
+		if (filter_hash)
+			orig_hash = &iter->ops->filter_hash;
+		else
+			orig_hash = &iter->ops->notrace_hash;
+
+		mutex_lock(&ftrace_lock);
+		/*
+		 * Remove the current set, update the hash and add
+		 * them back.
+		 */
+		ftrace_hash_rec_disable(iter->ops, filter_hash);
+		ret = ftrace_hash_move(orig_hash, iter->hash);
+		if (!ret) {
+			ftrace_hash_rec_enable(iter->ops, filter_hash);
+			if (iter->ops->flags & FTRACE_OPS_FL_ENABLED
+			    && ftrace_enabled)
+				ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+		}
+		mutex_unlock(&ftrace_lock);
+	}
+	free_ftrace_hash(iter->hash);
 	kfree(iter);
 
 	mutex_unlock(&ftrace_regex_lock);
 	return 0;
 }
 
-static int
-ftrace_filter_release(struct inode *inode, struct file *file)
-{
-	return ftrace_regex_release(inode, file, 1);
-}
-
-static int
-ftrace_notrace_release(struct inode *inode, struct file *file)
-{
-	return ftrace_regex_release(inode, file, 0);
-}
-
 static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_avail_open,
 	.read = seq_read,
@@ -2444,8 +3060,8 @@ static const struct file_operations ftrace_avail_fops = {
 	.release = seq_release_private,
 };
 
-static const struct file_operations ftrace_failures_fops = {
-	.open = ftrace_failures_open,
+static const struct file_operations ftrace_enabled_fops = {
+	.open = ftrace_enabled_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
 	.release = seq_release_private,
@@ -2456,7 +3072,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.read = seq_read,
 	.write = ftrace_filter_write,
 	.llseek = ftrace_regex_lseek,
-	.release = ftrace_filter_release,
+	.release = ftrace_regex_release,
 };
 
 static const struct file_operations ftrace_notrace_fops = {
@@ -2464,7 +3080,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.read = seq_read,
 	.write = ftrace_notrace_write,
 	.llseek = ftrace_regex_lseek,
-	.release = ftrace_notrace_release,
+	.release = ftrace_regex_release,
 };
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -2573,9 +3189,6 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 	bool exists;
 	int i;
 
-	if (ftrace_disabled)
-		return -ENODEV;
-
 	/* decode regex */
 	type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
 	if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
@@ -2584,12 +3197,18 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 	search_len = strlen(search);
 
 	mutex_lock(&ftrace_lock);
+
+	if (unlikely(ftrace_disabled)) {
+		mutex_unlock(&ftrace_lock);
+		return -ENODEV;
+	}
+
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
+		if (rec->flags & FTRACE_FL_FREE)
 			continue;
 
-		if (ftrace_match_record(rec, search, search_len, type)) {
+		if (ftrace_match_record(rec, NULL, search, search_len, type)) {
 			/* if it is in the array */
 			exists = false;
 			for (i = 0; i < *idx; i++) {
@@ -2679,8 +3298,8 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 	trace_create_file("available_filter_functions", 0444,
 			d_tracer, NULL, &ftrace_avail_fops);
 
-	trace_create_file("failures", 0444,
-			d_tracer, NULL, &ftrace_failures_fops);
+	trace_create_file("enabled_functions", 0444,
+			d_tracer, NULL, &ftrace_enabled_fops);
 
 	trace_create_file("set_ftrace_filter", 0644, d_tracer,
 			NULL, &ftrace_filter_fops);
@@ -2703,7 +3322,6 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
-	unsigned long flags;
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -2720,10 +3338,7 @@ static int ftrace_process_locs(struct module *mod,
 		ftrace_record_ip(addr);
 	}
 
-	/* disable interrupts to prevent kstop machine */
-	local_irq_save(flags);
 	ftrace_update_code(mod);
-	local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
@@ -2735,10 +3350,11 @@ void ftrace_release_mod(struct module *mod)
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
 
+	mutex_lock(&ftrace_lock);
+
 	if (ftrace_disabled)
-		return;
+		goto out_unlock;
 
-	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
 		if (within_module_core(rec->ip, mod)) {
 			/*
@@ -2749,6 +3365,7 @@ void ftrace_release_mod(struct module *mod)
 			ftrace_free_rec(rec);
 		}
 	} while_for_each_ftrace_rec();
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
 }
 
@@ -2835,6 +3452,10 @@ void __init ftrace_init(void)
 
 #else
 
+static struct ftrace_ops global_ops = {
+	.func			= ftrace_stub,
+};
+
 static int __init ftrace_nodyn_init(void)
 {
 	ftrace_enabled = 1;
@@ -2845,12 +3466,38 @@ device_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(command)	do { } while (0)
-# define ftrace_shutdown(command)	do { } while (0)
+# define ftrace_startup(ops, command)	do { } while (0)
+# define ftrace_shutdown(ops, command)	do { } while (0)
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
+
+static inline int
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+{
+	return 1;
+}
+
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+static void
+ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_ops *op;
+
+	/*
+	 * Some of the ops may be dynamically allocated,
+	 * they must be freed after a synchronize_sched().
+	 */
+	preempt_disable_notrace();
+	op = rcu_dereference_raw(ftrace_ops_list);
+	while (op != &ftrace_list_end) {
+		if (ftrace_ops_test(op, ip))
+			op->func(ip, parent_ip);
+		op = rcu_dereference_raw(op->next);
+	};
+	preempt_enable_notrace();
+}
+
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
@@ -3143,19 +3790,23 @@ void ftrace_kill(void)
  */
 int register_ftrace_function(struct ftrace_ops *ops)
 {
-	int ret;
-
-	if (unlikely(ftrace_disabled))
-		return -1;
+	int ret = -1;
 
 	mutex_lock(&ftrace_lock);
 
+	if (unlikely(ftrace_disabled))
+		goto out_unlock;
+
 	ret = __register_ftrace_function(ops);
-	ftrace_startup(0);
+	if (!ret)
+		ftrace_startup(ops, 0);
 
+
+ out_unlock:
 	mutex_unlock(&ftrace_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(register_ftrace_function);
 
 /**
  * unregister_ftrace_function - unregister a function for profiling.
@@ -3169,25 +3820,27 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_lock);
 	ret = __unregister_ftrace_function(ops);
-	ftrace_shutdown(0);
+	if (!ret)
+		ftrace_shutdown(ops, 0);
 	mutex_unlock(&ftrace_lock);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(unregister_ftrace_function);
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp,
 		     loff_t *ppos)
 {
-	int ret;
-
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
+	int ret = -ENODEV;
 
 	mutex_lock(&ftrace_lock);
 
-	ret  = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (unlikely(ftrace_disabled))
+		goto out;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
 		goto out;
@@ -3199,11 +3852,11 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 		ftrace_startup_sysctl();
 
 		/* we are starting ftrace again */
-		if (ftrace_list != &ftrace_list_end) {
-			if (ftrace_list->next == &ftrace_list_end)
-				ftrace_trace_function = ftrace_list->func;
+		if (ftrace_ops_list != &ftrace_list_end) {
+			if (ftrace_ops_list->next == &ftrace_list_end)
+				ftrace_trace_function = ftrace_ops_list->func;
 			else
-				ftrace_trace_function = ftrace_list_func;
+				ftrace_trace_function = ftrace_ops_list_func;
 		}
 
 	} else {
@@ -3392,7 +4045,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_return = retfunc;
 	ftrace_graph_entry = entryfunc;
 
-	ftrace_startup(FTRACE_START_FUNC_RET);
+	ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -3409,7 +4062,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1cb49be7c7f..ee9c921d7f2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2014,9 +2014,10 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
-	if (iter->lost_events)
-		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
-				 iter->cpu, iter->lost_events);
+	if (iter->lost_events &&
+	    !trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events))
+		return TRACE_TYPE_PARTIAL_LINE;
 
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
@@ -3230,6 +3231,14 @@ waitagain:
 
 		if (iter->seq.len >= cnt)
 			break;
+
+		/*
+		 * Setting the full flag means we reached the trace_seq buffer
+		 * size and we should leave by partial output condition above.
+		 * One of the trace_seq_* functions is not used properly.
+		 */
+		WARN_ONCE(iter->seq.full, "full flag set for trace type %d",
+			  iter->ent->type);
 	}
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5e9dfc6286d..6b69c4bd306 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -419,6 +419,8 @@ extern void trace_find_cmdline(int pid, char comm[]);
 extern unsigned long ftrace_update_tot_cnt;
 #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
 extern int DYN_FTRACE_TEST_NAME(void);
+#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
+extern int DYN_FTRACE_TEST_NAME2(void);
 #endif
 
 extern int ring_buffer_expanded;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 16aee4d44e8..8d0e1cc4e97 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -149,11 +149,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = function_trace_call,
+	.flags = FTRACE_OPS_FL_GLOBAL,
 };
 
 static struct ftrace_ops trace_stack_ops __read_mostly =
 {
 	.func = function_stack_trace_call,
+	.flags = FTRACE_OPS_FL_GLOBAL,
 };
 
 /* Our two options */
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index a4969b47afc..c77424be284 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -153,6 +153,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = irqsoff_tracer_call,
+	.flags = FTRACE_OPS_FL_GLOBAL,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 35d55a38614..f925c45f0af 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -53,7 +53,6 @@ const char *reserved_field_names[] = {
 	"common_preempt_count",
 	"common_pid",
 	"common_tgid",
-	"common_lock_depth",
 	FIELD_STRING_IP,
 	FIELD_STRING_RETIP,
 	FIELD_STRING_FUNC,
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 456be9063c2..cf535ccedc8 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -830,6 +830,9 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
 enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
 				  struct trace_event *event)
 {
+	if (!trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type))
+		return TRACE_TYPE_PARTIAL_LINE;
+
 	return TRACE_TYPE_HANDLED;
 }
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 2547d8813cf..dff763b7baf 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -32,7 +32,7 @@ static DEFINE_MUTEX(btrace_mutex);
 
 struct trace_bprintk_fmt {
 	struct list_head list;
-	char fmt[0];
+	const char *fmt;
 };
 
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
@@ -49,6 +49,7 @@ static
 void hold_module_trace_bprintk_format(const char **start, const char **end)
 {
 	const char **iter;
+	char *fmt;
 
 	mutex_lock(&btrace_mutex);
 	for (iter = start; iter < end; iter++) {
@@ -58,14 +59,18 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 			continue;
 		}
 
-		tb_fmt = kmalloc(offsetof(struct trace_bprintk_fmt, fmt)
-				+ strlen(*iter) + 1, GFP_KERNEL);
-		if (tb_fmt) {
+		tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL);
+		if (tb_fmt)
+			fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL);
+		if (tb_fmt && fmt) {
 			list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list);
-			strcpy(tb_fmt->fmt, *iter);
+			strcpy(fmt, *iter);
+			tb_fmt->fmt = fmt;
 			*iter = tb_fmt->fmt;
-		} else
+		} else {
+			kfree(tb_fmt);
 			*iter = NULL;
+		}
 	}
 	mutex_unlock(&btrace_mutex);
 }
@@ -84,6 +89,76 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self,
 	return 0;
 }
 
+/*
+ * The debugfs/tracing/printk_formats file maps the addresses with
+ * the ASCII formats that are used in the bprintk events in the
+ * buffer. For userspace tools to be able to decode the events from
+ * the buffer, they need to be able to map the address with the format.
+ *
+ * The addresses of the bprintk formats are in their own section
+ * __trace_printk_fmt. But for modules we copy them into a link list.
+ * The code to print the formats and their addresses passes around the
+ * address of the fmt string. If the fmt address passed into the seq
+ * functions is within the kernel core __trace_printk_fmt section, then
+ * it simply uses the next pointer in the list.
+ *
+ * When the fmt pointer is outside the kernel core __trace_printk_fmt
+ * section, then we need to read the link list pointers. The trick is
+ * we pass the address of the string to the seq function just like
+ * we do for the kernel core formats. To get back the structure that
+ * holds the format, we simply use containerof() and then go to the
+ * next format in the list.
+ */
+static const char **
+find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos)
+{
+	struct trace_bprintk_fmt *mod_fmt;
+
+	if (list_empty(&trace_bprintk_fmt_list))
+		return NULL;
+
+	/*
+	 * v will point to the address of the fmt record from t_next
+	 * v will be NULL from t_start.
+	 * If this is the first pointer or called from start
+	 * then we need to walk the list.
+	 */
+	if (!v || start_index == *pos) {
+		struct trace_bprintk_fmt *p;
+
+		/* search the module list */
+		list_for_each_entry(p, &trace_bprintk_fmt_list, list) {
+			if (start_index == *pos)
+				return &p->fmt;
+			start_index++;
+		}
+		/* pos > index */
+		return NULL;
+	}
+
+	/*
+	 * v points to the address of the fmt field in the mod list
+	 * structure that holds the module print format.
+	 */
+	mod_fmt = container_of(v, typeof(*mod_fmt), fmt);
+	if (mod_fmt->list.next == &trace_bprintk_fmt_list)
+		return NULL;
+
+	mod_fmt = container_of(mod_fmt->list.next, typeof(*mod_fmt), list);
+
+	return &mod_fmt->fmt;
+}
+
+static void format_mod_start(void)
+{
+	mutex_lock(&btrace_mutex);
+}
+
+static void format_mod_stop(void)
+{
+	mutex_unlock(&btrace_mutex);
+}
+
 #else /* !CONFIG_MODULES */
 __init static int
 module_trace_bprintk_format_notify(struct notifier_block *self,
@@ -91,6 +166,13 @@ module_trace_bprintk_format_notify(struct notifier_block *self,
 {
 	return 0;
 }
+static inline const char **
+find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos)
+{
+	return NULL;
+}
+static inline void format_mod_start(void) { }
+static inline void format_mod_stop(void) { }
 #endif /* CONFIG_MODULES */
 
 
@@ -153,20 +235,33 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 }
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
+static const char **find_next(void *v, loff_t *pos)
+{
+	const char **fmt = v;
+	int start_index;
+
+	if (!fmt)
+		fmt = __start___trace_bprintk_fmt + *pos;
+
+	start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
+
+	if (*pos < start_index)
+		return fmt;
+
+	return find_next_mod_format(start_index, v, fmt, pos);
+}
+
 static void *
 t_start(struct seq_file *m, loff_t *pos)
 {
-	const char **fmt = __start___trace_bprintk_fmt + *pos;
-
-	if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
-		return NULL;
-	return fmt;
+	format_mod_start();
+	return find_next(NULL, pos);
 }
 
 static void *t_next(struct seq_file *m, void * v, loff_t *pos)
 {
 	(*pos)++;
-	return t_start(m, pos);
+	return find_next(v, pos);
 }
 
 static int t_show(struct seq_file *m, void *v)
@@ -205,6 +300,7 @@ static int t_show(struct seq_file *m, void *v)
 
 static void t_stop(struct seq_file *m, void *p)
 {
+	format_mod_stop();
 }
 
 static const struct seq_operations show_format_seq_ops = {
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 7319559ed59..f029dd4fd2c 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -129,6 +129,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = wakeup_tracer_call,
+	.flags = FTRACE_OPS_FL_GLOBAL,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 659732eba07..288541f977f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -101,6 +101,206 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+static int trace_selftest_test_probe1_cnt;
+static void trace_selftest_test_probe1_func(unsigned long ip,
+					    unsigned long pip)
+{
+	trace_selftest_test_probe1_cnt++;
+}
+
+static int trace_selftest_test_probe2_cnt;
+static void trace_selftest_test_probe2_func(unsigned long ip,
+					    unsigned long pip)
+{
+	trace_selftest_test_probe2_cnt++;
+}
+
+static int trace_selftest_test_probe3_cnt;
+static void trace_selftest_test_probe3_func(unsigned long ip,
+					    unsigned long pip)
+{
+	trace_selftest_test_probe3_cnt++;
+}
+
+static int trace_selftest_test_global_cnt;
+static void trace_selftest_test_global_func(unsigned long ip,
+					    unsigned long pip)
+{
+	trace_selftest_test_global_cnt++;
+}
+
+static int trace_selftest_test_dyn_cnt;
+static void trace_selftest_test_dyn_func(unsigned long ip,
+					 unsigned long pip)
+{
+	trace_selftest_test_dyn_cnt++;
+}
+
+static struct ftrace_ops test_probe1 = {
+	.func			= trace_selftest_test_probe1_func,
+};
+
+static struct ftrace_ops test_probe2 = {
+	.func			= trace_selftest_test_probe2_func,
+};
+
+static struct ftrace_ops test_probe3 = {
+	.func			= trace_selftest_test_probe3_func,
+};
+
+static struct ftrace_ops test_global = {
+	.func			= trace_selftest_test_global_func,
+	.flags			= FTRACE_OPS_FL_GLOBAL,
+};
+
+static void print_counts(void)
+{
+	printk("(%d %d %d %d %d) ",
+	       trace_selftest_test_probe1_cnt,
+	       trace_selftest_test_probe2_cnt,
+	       trace_selftest_test_probe3_cnt,
+	       trace_selftest_test_global_cnt,
+	       trace_selftest_test_dyn_cnt);
+}
+
+static void reset_counts(void)
+{
+	trace_selftest_test_probe1_cnt = 0;
+	trace_selftest_test_probe2_cnt = 0;
+	trace_selftest_test_probe3_cnt = 0;
+	trace_selftest_test_global_cnt = 0;
+	trace_selftest_test_dyn_cnt = 0;
+}
+
+static int trace_selftest_ops(int cnt)
+{
+	int save_ftrace_enabled = ftrace_enabled;
+	struct ftrace_ops *dyn_ops;
+	char *func1_name;
+	char *func2_name;
+	int len1;
+	int len2;
+	int ret = -1;
+
+	printk(KERN_CONT "PASSED\n");
+	pr_info("Testing dynamic ftrace ops #%d: ", cnt);
+
+	ftrace_enabled = 1;
+	reset_counts();
+
+	/* Handle PPC64 '.' name */
+	func1_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	func2_name = "*" __stringify(DYN_FTRACE_TEST_NAME2);
+	len1 = strlen(func1_name);
+	len2 = strlen(func2_name);
+
+	/*
+	 * Probe 1 will trace function 1.
+	 * Probe 2 will trace function 2.
+	 * Probe 3 will trace functions 1 and 2.
+	 */
+	ftrace_set_filter(&test_probe1, func1_name, len1, 1);
+	ftrace_set_filter(&test_probe2, func2_name, len2, 1);
+	ftrace_set_filter(&test_probe3, func1_name, len1, 1);
+	ftrace_set_filter(&test_probe3, func2_name, len2, 0);
+
+	register_ftrace_function(&test_probe1);
+	register_ftrace_function(&test_probe2);
+	register_ftrace_function(&test_probe3);
+	register_ftrace_function(&test_global);
+
+	DYN_FTRACE_TEST_NAME();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 1)
+		goto out;
+	if (trace_selftest_test_probe2_cnt != 0)
+		goto out;
+	if (trace_selftest_test_probe3_cnt != 1)
+		goto out;
+	if (trace_selftest_test_global_cnt == 0)
+		goto out;
+
+	DYN_FTRACE_TEST_NAME2();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 1)
+		goto out;
+	if (trace_selftest_test_probe2_cnt != 1)
+		goto out;
+	if (trace_selftest_test_probe3_cnt != 2)
+		goto out;
+
+	/* Add a dynamic probe */
+	dyn_ops = kzalloc(sizeof(*dyn_ops), GFP_KERNEL);
+	if (!dyn_ops) {
+		printk("MEMORY ERROR ");
+		goto out;
+	}
+
+	dyn_ops->func = trace_selftest_test_dyn_func;
+
+	register_ftrace_function(dyn_ops);
+
+	trace_selftest_test_global_cnt = 0;
+
+	DYN_FTRACE_TEST_NAME();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 2)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 1)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_global_cnt == 0)
+		goto out;
+	if (trace_selftest_test_dyn_cnt == 0)
+		goto out_free;
+
+	DYN_FTRACE_TEST_NAME2();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 2)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 2)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 4)
+		goto out_free;
+
+	ret = 0;
+ out_free:
+	unregister_ftrace_function(dyn_ops);
+	kfree(dyn_ops);
+
+ out:
+	/* Purposely unregister in the same order */
+	unregister_ftrace_function(&test_probe1);
+	unregister_ftrace_function(&test_probe2);
+	unregister_ftrace_function(&test_probe3);
+	unregister_ftrace_function(&test_global);
+
+	/* Make sure everything is off */
+	reset_counts();
+	DYN_FTRACE_TEST_NAME();
+	DYN_FTRACE_TEST_NAME();
+
+	if (trace_selftest_test_probe1_cnt ||
+	    trace_selftest_test_probe2_cnt ||
+	    trace_selftest_test_probe3_cnt ||
+	    trace_selftest_test_global_cnt ||
+	    trace_selftest_test_dyn_cnt)
+		ret = -1;
+
+	ftrace_enabled = save_ftrace_enabled;
+
+	return ret;
+}
+
 /* Test dynamic code modification and ftrace filters */
 int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 					   struct trace_array *tr,
@@ -131,7 +331,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
 
 	/* filter only on our function */
-	ftrace_set_filter(func_name, strlen(func_name), 1);
+	ftrace_set_global_filter(func_name, strlen(func_name), 1);
 
 	/* enable tracing */
 	ret = tracer_init(trace, tr);
@@ -166,22 +366,30 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
-	trace->reset(tr);
 	tracing_start();
 
 	/* we should only have one item */
 	if (!ret && count != 1) {
+		trace->reset(tr);
 		printk(KERN_CONT ".. filter failed count=%ld ..", count);
 		ret = -1;
 		goto out;
 	}
 
+	/* Test the ops with global tracing running */
+	ret = trace_selftest_ops(1);
+	trace->reset(tr);
+
  out:
 	ftrace_enabled = save_ftrace_enabled;
 	tracer_enabled = save_tracer_enabled;
 
 	/* Enable tracing on all functions again */
-	ftrace_set_filter(NULL, 0, 1);
+	ftrace_set_global_filter(NULL, 0, 1);
+
+	/* Test the ops with global tracing off */
+	if (!ret)
+		ret = trace_selftest_ops(2);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c
index 54dd77cce5b..b4c475a0a48 100644
--- a/kernel/trace/trace_selftest_dynamic.c
+++ b/kernel/trace/trace_selftest_dynamic.c
@@ -5,3 +5,9 @@ int DYN_FTRACE_TEST_NAME(void)
 	/* used to call mcount */
 	return 0;
 }
+
+int DYN_FTRACE_TEST_NAME2(void)
+{
+	/* used to call mcount */
+	return 0;
+}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 4c5dead0c23..b0b53b8e4c2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -133,6 +133,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = stack_trace_call,
+	.flags = FTRACE_OPS_FL_GLOBAL,
 };
 
 static ssize_t
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 68187af4889..b219f1449c5 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -251,9 +251,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 {
 	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
 
-	if (elem->regfunc && !elem->state && active)
+	if (elem->regfunc && !jump_label_enabled(&elem->key) && active)
 		elem->regfunc();
-	else if (elem->unregfunc && elem->state && !active)
+	else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active)
 		elem->unregfunc();
 
 	/*
@@ -264,13 +264,10 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 	 * is used.
 	 */
 	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	if (!elem->state && active) {
-		jump_label_enable(&elem->state);
-		elem->state = active;
-	} else if (elem->state && !active) {
-		jump_label_disable(&elem->state);
-		elem->state = active;
-	}
+	if (active && !jump_label_enabled(&elem->key))
+		jump_label_inc(&elem->key);
+	else if (!active && jump_label_enabled(&elem->key))
+		jump_label_dec(&elem->key);
 }
 
 /*
@@ -281,13 +278,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
  */
 static void disable_tracepoint(struct tracepoint *elem)
 {
-	if (elem->unregfunc && elem->state)
+	if (elem->unregfunc && jump_label_enabled(&elem->key))
 		elem->unregfunc();
 
-	if (elem->state) {
-		jump_label_disable(&elem->state);
-		elem->state = 0;
-	}
+	if (jump_label_enabled(&elem->key))
+		jump_label_dec(&elem->key);
 	rcu_assign_pointer(elem->funcs, NULL);
 }
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c768bcdda1b..10ef6198114 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -238,6 +238,21 @@ config DETECT_HUNG_TASK
 	  enabled then all held locks will also be reported. This
 	  feature has negligible overhead.
 
+config DEFAULT_HUNG_TASK_TIMEOUT
+	int "Default timeout for hung task detection (in seconds)"
+	depends on DETECT_HUNG_TASK
+	default 120
+	help
+	  This option controls the default timeout (in seconds) used
+	  to determine when a task has become non-responsive and should
+	  be considered hung.
+
+	  It can be adjusted at runtime via the kernel.hung_task_timeout
+	  sysctl or by writing a value to /proc/sys/kernel/hung_task_timeout.
+
+	  A timeout of 0 disables the check.  The default is two minutes.
+	  Keeping the default should be fine in most cases.
+
 config BOOTPARAM_HUNG_TASK_PANIC
 	bool "Panic (Reboot) On Hung Tasks"
 	depends on DETECT_HUNG_TASK
@@ -337,7 +352,7 @@ config DEBUG_OBJECTS_WORK
 
 config DEBUG_OBJECTS_RCU_HEAD
 	bool "Debug RCU callbacks objects"
-	depends on DEBUG_OBJECTS && PREEMPT
+	depends on DEBUG_OBJECTS
 	help
 	  Enable this to turn on debugging of RCU list heads (call_rcu() usage).
 
@@ -398,9 +413,9 @@ config SLUB_STATS
 config DEBUG_KMEMLEAK
 	bool "Kernel memory leak detector"
 	depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
-		(X86 || ARM || PPC || S390 || SPARC64 || SUPERH || MICROBLAZE || TILE)
+		(X86 || ARM || PPC || MIPS || S390 || SPARC64 || SUPERH || MICROBLAZE || TILE)
 
-	select DEBUG_FS if SYSFS
+	select DEBUG_FS
 	select STACKTRACE if STACKTRACE_SUPPORT
 	select KALLSYMS
 	select CRC32
@@ -875,22 +890,9 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
-config RCU_CPU_STALL_DETECTOR
-	bool "Check for stalled CPUs delaying RCU grace periods"
-	depends on TREE_RCU || TREE_PREEMPT_RCU
-	default y
-	help
-	  This option causes RCU to printk information on which
-	  CPUs are delaying the current grace period, but only when
-	  the grace period extends for excessive time periods.
-
-	  Say N if you want to disable such checks.
-
-	  Say Y if you are unsure.
-
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
-	depends on RCU_CPU_STALL_DETECTOR
+	depends on TREE_RCU || TREE_PREEMPT_RCU
 	range 3 300
 	default 60
 	help
@@ -899,22 +901,9 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
-config RCU_CPU_STALL_DETECTOR_RUNNABLE
-	bool "RCU CPU stall checking starts automatically at boot"
-	depends on RCU_CPU_STALL_DETECTOR
-	default y
-	help
-	  If set, start checking for RCU CPU stalls immediately on
-	  boot.  Otherwise, RCU CPU stall checking must be manually
-	  enabled.
-
-	  Say Y if you are unsure.
-
-	  Say N if you wish to suppress RCU CPU stall checking during boot.
-
 config RCU_CPU_STALL_VERBOSE
 	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
-	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
+	depends on TREE_PREEMPT_RCU
 	default y
 	help
 	  This option causes RCU to printk detailed per-task information
diff --git a/lib/Makefile b/lib/Makefile
index ef0f2857115..4b49a249064 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -21,7 +21,8 @@ lib-y	+= kobject.o kref.o klist.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
-	 string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o
+	 string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \
+	 bsearch.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 
diff --git a/lib/bsearch.c b/lib/bsearch.c
new file mode 100644
index 00000000000..5b54758e2af
--- /dev/null
+++ b/lib/bsearch.c
@@ -0,0 +1,53 @@
+/*
+ * A generic implementation of binary search for the Linux kernel
+ *
+ * Copyright (C) 2008-2009 Ksplice, Inc.
+ * Author: Tim Abbott <tabbott@ksplice.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/bsearch.h>
+
+/*
+ * bsearch - binary search an array of elements
+ * @key: pointer to item being searched for
+ * @base: pointer to first element to search
+ * @num: number of elements
+ * @size: size of each element
+ * @cmp: pointer to comparison function
+ *
+ * This function does a binary search on the given array.  The
+ * contents of the array should already be in ascending sorted order
+ * under the provided comparison function.
+ *
+ * Note that the key need not have the same type as the elements in
+ * the array, e.g. key could be a string and the comparison function
+ * could compare the string with the struct's name field.  However, if
+ * the key and elements in the array are of the same type, you can use
+ * the same comparison function for both sort() and bsearch().
+ */
+void *bsearch(const void *key, const void *base, size_t num, size_t size,
+	      int (*cmp)(const void *key, const void *elt))
+{
+	size_t start = 0, end = num;
+	int result;
+
+	while (start < end) {
+		size_t mid = start + (end - start) / 2;
+
+		result = cmp(key, base + mid * size);
+		if (result < 0)
+			end = mid;
+		else if (result > 0)
+			start = mid + 1;
+		else
+			return (void *)base + mid * size;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(bsearch);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 4bfb0471f10..db07bfd9298 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -649,7 +649,7 @@ out_err:
 	return -ENOMEM;
 }
 
-static int device_dma_allocations(struct device *dev)
+static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
 {
 	struct dma_debug_entry *entry;
 	unsigned long flags;
@@ -660,8 +660,10 @@ static int device_dma_allocations(struct device *dev)
 	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)
+			if (entry->dev == dev) {
 				count += 1;
+				*out_entry = entry;
+			}
 		}
 		spin_unlock(&dma_entry_hash[i].lock);
 	}
@@ -674,6 +676,7 @@ static int device_dma_allocations(struct device *dev)
 static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct device *dev = data;
+	struct dma_debug_entry *uninitialized_var(entry);
 	int count;
 
 	if (global_disable)
@@ -681,12 +684,17 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
 
 	switch (action) {
 	case BUS_NOTIFY_UNBOUND_DRIVER:
-		count = device_dma_allocations(dev);
+		count = device_dma_allocations(dev, &entry);
 		if (count == 0)
 			break;
-		err_printk(dev, NULL, "DMA-API: device driver has pending "
+		err_printk(dev, entry, "DMA-API: device driver has pending "
 				"DMA allocations while released from device "
-				"[count=%d]\n", count);
+				"[count=%d]\n"
+				"One of leaked entries details: "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [mapped as %s]\n",
+			count, entry->dev_addr, entry->size,
+			dir2name[entry->direction], type2name[entry->type]);
 		break;
 	default:
 		break;
diff --git a/lib/string.c b/lib/string.c
index f71bead1be3..01fad9b203e 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -535,6 +535,35 @@ bool sysfs_streq(const char *s1, const char *s2)
 }
 EXPORT_SYMBOL(sysfs_streq);
 
+/**
+ * strtobool - convert common user inputs into boolean values
+ * @s: input string
+ * @res: result
+ *
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
+ * Otherwise it will return -EINVAL.  Value pointed to by res is
+ * updated upon finding a match.
+ */
+int strtobool(const char *s, bool *res)
+{
+	switch (s[0]) {
+	case 'y':
+	case 'Y':
+	case '1':
+		*res = true;
+		break;
+	case 'n':
+	case 'N':
+	case '0':
+		*res = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(strtobool);
+
 #ifndef __HAVE_ARCH_MEMSET
 /**
  * memset - Fill a region of memory with the given value
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c1d5867543e..aacee45616f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1414,9 +1414,12 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++(*pos);
 
 	list_for_each_continue_rcu(n, &object_list) {
-		next_obj = list_entry(n, struct kmemleak_object, object_list);
-		if (get_object(next_obj))
+		struct kmemleak_object *obj =
+			list_entry(n, struct kmemleak_object, object_list);
+		if (get_object(obj)) {
+			next_obj = obj;
 			break;
+		}
 	}
 
 	put_object(prev_obj);
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 3cc43558cf9..150b6ce23df 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -28,18 +28,10 @@
 #include <linux/udp.h>
 #include <linux/if_vlan.h>
 
-static void gw_node_free_rcu(struct rcu_head *rcu)
-{
-	struct gw_node *gw_node;
-
-	gw_node = container_of(rcu, struct gw_node, rcu);
-	kfree(gw_node);
-}
-
 static void gw_node_free_ref(struct gw_node *gw_node)
 {
 	if (atomic_dec_and_test(&gw_node->refcount))
-		call_rcu(&gw_node->rcu, gw_node_free_rcu);
+		kfree_rcu(gw_node, rcu);
 }
 
 void *gw_get_selected(struct bat_priv *bat_priv)
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 0b9133022d2..ed23a5895d6 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -56,18 +56,10 @@ err:
 	return 0;
 }
 
-static void neigh_node_free_rcu(struct rcu_head *rcu)
-{
-	struct neigh_node *neigh_node;
-
-	neigh_node = container_of(rcu, struct neigh_node, rcu);
-	kfree(neigh_node);
-}
-
 void neigh_node_free_ref(struct neigh_node *neigh_node)
 {
 	if (atomic_dec_and_test(&neigh_node->refcount))
-		call_rcu(&neigh_node->rcu, neigh_node_free_rcu);
+		kfree_rcu(neigh_node, rcu);
 }
 
 struct neigh_node *create_neighbor(struct orig_node *orig_node,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 824e1f6e50f..04efe022c13 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -76,18 +76,10 @@ int my_skb_head_push(struct sk_buff *skb, unsigned int len)
 	return 0;
 }
 
-static void softif_neigh_free_rcu(struct rcu_head *rcu)
-{
-	struct softif_neigh *softif_neigh;
-
-	softif_neigh = container_of(rcu, struct softif_neigh, rcu);
-	kfree(softif_neigh);
-}
-
 static void softif_neigh_free_ref(struct softif_neigh *softif_neigh)
 {
 	if (atomic_dec_and_test(&softif_neigh->refcount))
-		call_rcu(&softif_neigh->rcu, softif_neigh_free_rcu);
+		kfree_rcu(softif_neigh, rcu);
 }
 
 void softif_neigh_purge(struct bat_priv *bat_priv)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 7b39f3ed2fd..e2e66939ed0 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -68,14 +68,6 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr,
 	return __hw_addr_add_ex(list, addr, addr_len, addr_type, false);
 }
 
-static void ha_rcu_free(struct rcu_head *head)
-{
-	struct netdev_hw_addr *ha;
-
-	ha = container_of(head, struct netdev_hw_addr, rcu_head);
-	kfree(ha);
-}
-
 static int __hw_addr_del_ex(struct netdev_hw_addr_list *list,
 			    unsigned char *addr, int addr_len,
 			    unsigned char addr_type, bool global)
@@ -94,7 +86,7 @@ static int __hw_addr_del_ex(struct netdev_hw_addr_list *list,
 			if (--ha->refcount)
 				return 0;
 			list_del_rcu(&ha->list);
-			call_rcu(&ha->rcu_head, ha_rcu_free);
+			kfree_rcu(ha, rcu_head);
 			list->count--;
 			return 0;
 		}
@@ -197,7 +189,7 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list)
 
 	list_for_each_entry_safe(ha, tmp, &list->list, list) {
 		list_del_rcu(&ha->list);
-		call_rcu(&ha->rcu_head, ha_rcu_free);
+		kfree_rcu(ha, rcu_head);
 	}
 	list->count = 0;
 }
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 706502ff64a..7f36b38e060 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -207,14 +207,6 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
 	rcu_read_unlock();
 }
 
-
-static void free_dm_hw_stat(struct rcu_head *head)
-{
-	struct dm_hw_stat_delta *n;
-	n = container_of(head, struct dm_hw_stat_delta, rcu);
-	kfree(n);
-}
-
 static int set_all_monitor_traces(int state)
 {
 	int rc = 0;
@@ -245,7 +237,7 @@ static int set_all_monitor_traces(int state)
 		list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) {
 			if (new_stat->dev == NULL) {
 				list_del_rcu(&new_stat->list);
-				call_rcu(&new_stat->rcu, free_dm_hw_stat);
+				kfree_rcu(new_stat, rcu);
 			}
 		}
 		break;
@@ -314,7 +306,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 				new_stat->dev = NULL;
 				if (trace_state == TRACE_OFF) {
 					list_del_rcu(&new_stat->list);
-					call_rcu(&new_stat->rcu, free_dm_hw_stat);
+					kfree_rcu(new_stat, rcu);
 					break;
 				}
 			}
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 7c2373321b7..43b03dd71e8 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -249,13 +249,6 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 }
 EXPORT_SYMBOL(gen_new_estimator);
 
-static void __gen_kill_estimator(struct rcu_head *head)
-{
-	struct gen_estimator *e = container_of(head,
-					struct gen_estimator, e_rcu);
-	kfree(e);
-}
-
 /**
  * gen_kill_estimator - remove a rate estimator
  * @bstats: basic statistics
@@ -279,7 +272,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 		write_unlock(&est_lock);
 
 		list_del_rcu(&e->list);
-		call_rcu(&e->e_rcu, __gen_kill_estimator);
+		kfree_rcu(e, e_rcu);
 	}
 	spin_unlock_bh(&est_tree_lock);
 }
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 5ceb257e860..80b2aad3b73 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -565,13 +565,6 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 	return len;
 }
 
-static void rps_map_release(struct rcu_head *rcu)
-{
-	struct rps_map *map = container_of(rcu, struct rps_map, rcu);
-
-	kfree(map);
-}
-
 static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 		      struct rx_queue_attribute *attribute,
 		      const char *buf, size_t len)
@@ -619,7 +612,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	spin_unlock(&rps_map_lock);
 
 	if (old_map)
-		call_rcu(&old_map->rcu, rps_map_release);
+		kfree_rcu(old_map, rcu);
 
 	free_cpumask_var(mask);
 	return len;
@@ -728,7 +721,7 @@ static void rx_queue_release(struct kobject *kobj)
 	map = rcu_dereference_raw(queue->rps_map);
 	if (map) {
 		RCU_INIT_POINTER(queue->rps_map, NULL);
-		call_rcu(&map->rcu, rps_map_release);
+		kfree_rcu(map, rcu);
 	}
 
 	flow_table = rcu_dereference_raw(queue->rps_flow_table);
@@ -898,21 +891,6 @@ static ssize_t show_xps_map(struct netdev_queue *queue,
 	return len;
 }
 
-static void xps_map_release(struct rcu_head *rcu)
-{
-	struct xps_map *map = container_of(rcu, struct xps_map, rcu);
-
-	kfree(map);
-}
-
-static void xps_dev_maps_release(struct rcu_head *rcu)
-{
-	struct xps_dev_maps *dev_maps =
-	    container_of(rcu, struct xps_dev_maps, rcu);
-
-	kfree(dev_maps);
-}
-
 static DEFINE_MUTEX(xps_map_mutex);
 #define xmap_dereference(P)		\
 	rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
@@ -1009,7 +987,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
 		map = dev_maps ?
 			xmap_dereference(dev_maps->cpu_map[cpu]) : NULL;
 		if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map)
-			call_rcu(&map->rcu, xps_map_release);
+			kfree_rcu(map, rcu);
 		if (new_dev_maps->cpu_map[cpu])
 			nonempty = 1;
 	}
@@ -1022,7 +1000,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
 	}
 
 	if (dev_maps)
-		call_rcu(&dev_maps->rcu, xps_dev_maps_release);
+		kfree_rcu(dev_maps, rcu);
 
 	netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node :
 					    NUMA_NO_NODE);
@@ -1084,7 +1062,7 @@ static void netdev_queue_release(struct kobject *kobj)
 				else {
 					RCU_INIT_POINTER(dev_maps->cpu_map[i],
 					    NULL);
-					call_rcu(&map->rcu, xps_map_release);
+					kfree_rcu(map, rcu);
 					map = NULL;
 				}
 			}
@@ -1094,7 +1072,7 @@ static void netdev_queue_release(struct kobject *kobj)
 
 		if (!nonempty) {
 			RCU_INIT_POINTER(dev->xps_maps, NULL);
-			call_rcu(&dev_maps->rcu, xps_dev_maps_release);
+			kfree_rcu(dev_maps, rcu);
 		}
 	}
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3f860261c5e..297bb927224 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -27,14 +27,6 @@ EXPORT_SYMBOL(init_net);
 
 #define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */
 
-static void net_generic_release(struct rcu_head *rcu)
-{
-	struct net_generic *ng;
-
-	ng = container_of(rcu, struct net_generic, rcu);
-	kfree(ng);
-}
-
 static int net_assign_generic(struct net *net, int id, void *data)
 {
 	struct net_generic *ng, *old_ng;
@@ -68,7 +60,7 @@ static int net_assign_generic(struct net *net, int id, void *data)
 	memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
 
 	rcu_assign_pointer(net->gen, ng);
-	call_rcu(&old_ng->rcu, net_generic_release);
+	kfree_rcu(old_ng, rcu);
 assign:
 	ng->ptr[id - 1] = data;
 	return 0;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 0dcaa903e00..4c27615340d 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -332,14 +332,9 @@ static struct dn_ifaddr *dn_dev_alloc_ifa(void)
 	return ifa;
 }
 
-static void dn_dev_free_ifa_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct dn_ifaddr, rcu));
-}
-
 static void dn_dev_free_ifa(struct dn_ifaddr *ifa)
 {
-	call_rcu(&ifa->rcu, dn_dev_free_ifa_rcu);
+	kfree_rcu(ifa, rcu);
 }
 
 static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 641a5a2a9f9..33e2c35b74b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -141,18 +141,8 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
 	},
 };
 
-
 /* Release a nexthop info record */
 
-static void free_fib_info_rcu(struct rcu_head *head)
-{
-	struct fib_info *fi = container_of(head, struct fib_info, rcu);
-
-	if (fi->fib_metrics != (u32 *) dst_default_metrics)
-		kfree(fi->fib_metrics);
-	kfree(fi);
-}
-
 void free_fib_info(struct fib_info *fi)
 {
 	if (fi->fib_dead == 0) {
@@ -166,7 +156,7 @@ void free_fib_info(struct fib_info *fi)
 	} endfor_nexthops(fi);
 	fib_info_cnt--;
 	release_net(fi->fib_net);
-	call_rcu(&fi->rcu, free_fib_info_rcu);
+	kfree_rcu(fi, rcu);
 }
 
 void fib_release_info(struct fib_info *fi)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 5fe9b8b41df..11d4d28190b 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -350,14 +350,9 @@ static inline void free_leaf(struct leaf *l)
 	call_rcu_bh(&l->rcu, __leaf_free_rcu);
 }
 
-static void __leaf_info_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct leaf_info, rcu));
-}
-
 static inline void free_leaf_info(struct leaf_info *leaf)
 {
-	call_rcu(&leaf->rcu, __leaf_info_free_rcu);
+	kfree_rcu(leaf, rcu);
 }
 
 static struct tnode *tnode_alloc(size_t size)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1fd3d9ce839..8f62d66d085 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -149,17 +149,11 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc);
 static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 			 int sfcount, __be32 *psfsrc, int delta);
 
-
-static void ip_mc_list_reclaim(struct rcu_head *head)
-{
-	kfree(container_of(head, struct ip_mc_list, rcu));
-}
-
 static void ip_ma_put(struct ip_mc_list *im)
 {
 	if (atomic_dec_and_test(&im->refcnt)) {
 		in_dev_put(im->interface);
-		call_rcu(&im->rcu, ip_mc_list_reclaim);
+		kfree_rcu(im, rcu);
 	}
 }
 
@@ -1836,12 +1830,6 @@ done:
 }
 EXPORT_SYMBOL(ip_mc_join_group);
 
-static void ip_sf_socklist_reclaim(struct rcu_head *rp)
-{
-	kfree(container_of(rp, struct ip_sf_socklist, rcu));
-	/* sk_omem_alloc should have been decreased by the caller*/
-}
-
 static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 			   struct in_device *in_dev)
 {
@@ -1858,18 +1846,10 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 	rcu_assign_pointer(iml->sflist, NULL);
 	/* decrease mem now to avoid the memleak warning */
 	atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc);
-	call_rcu(&psf->rcu, ip_sf_socklist_reclaim);
+	kfree_rcu(psf, rcu);
 	return err;
 }
 
-
-static void ip_mc_socklist_reclaim(struct rcu_head *rp)
-{
-	kfree(container_of(rp, struct ip_mc_socklist, rcu));
-	/* sk_omem_alloc should have been decreased by the caller*/
-}
-
-
 /*
  *	Ask a socket to leave a group.
  */
@@ -1909,7 +1889,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 		rtnl_unlock();
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
-		call_rcu(&iml->rcu, ip_mc_socklist_reclaim);
+		kfree_rcu(iml, rcu);
 		return 0;
 	}
 	if (!in_dev)
@@ -2026,7 +2006,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 				newpsl->sl_addr[i] = psl->sl_addr[i];
 			/* decrease mem now to avoid the memleak warning */
 			atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
-			call_rcu(&psl->rcu, ip_sf_socklist_reclaim);
+			kfree_rcu(psl, rcu);
 		}
 		rcu_assign_pointer(pmc->sflist, newpsl);
 		psl = newpsl;
@@ -2127,7 +2107,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
 			psl->sl_count, psl->sl_addr, 0);
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
-		call_rcu(&psl->rcu, ip_sf_socklist_reclaim);
+		kfree_rcu(psl, rcu);
 	} else
 		(void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode,
 			0, NULL, 0);
@@ -2324,7 +2304,7 @@ void ip_mc_drop_socket(struct sock *sk)
 			ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr);
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
-		call_rcu(&iml->rcu, ip_mc_socklist_reclaim);
+		kfree_rcu(iml, rcu);
 	}
 	rtnl_unlock();
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a7bda075705..8f13d88d7db 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -317,12 +317,6 @@ static void snmp6_free_dev(struct inet6_dev *idev)
 
 /* Nobody refers to this device, we may destroy it. */
 
-static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
-{
-	struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
-	kfree(idev);
-}
-
 void in6_dev_finish_destroy(struct inet6_dev *idev)
 {
 	struct net_device *dev = idev->dev;
@@ -339,7 +333,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
 		return;
 	}
 	snmp6_free_dev(idev);
-	call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
+	kfree_rcu(idev, rcu);
 }
 
 EXPORT_SYMBOL(in6_dev_finish_destroy);
@@ -535,12 +529,6 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
 }
 #endif
 
-static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head)
-{
-	struct inet6_ifaddr *ifp = container_of(head, struct inet6_ifaddr, rcu);
-	kfree(ifp);
-}
-
 /* Nobody refers to this ifaddr, destroy it */
 void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 {
@@ -561,7 +549,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 	}
 	dst_release(&ifp->rt->dst);
 
-	call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu);
+	kfree_rcu(ifp, rcu);
 }
 
 static void
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 76b893771e6..f2d98ca7588 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -201,10 +201,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	return 0;
 }
 
-static void ipv6_mc_socklist_reclaim(struct rcu_head *head)
-{
-	kfree(container_of(head, struct ipv6_mc_socklist, rcu));
-}
 /*
  *	socket leave on multicast group
  */
@@ -239,7 +235,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
 			rcu_read_unlock();
 			atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
-			call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim);
+			kfree_rcu(mc_lst, rcu);
 			return 0;
 		}
 	}
@@ -307,7 +303,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 		rcu_read_unlock();
 
 		atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
-		call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim);
+		kfree_rcu(mc_lst, rcu);
 
 		spin_lock(&ipv6_sk_mc_lock);
 	}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 43b33373adb..5f35d595e4a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -401,11 +401,6 @@ out:
 	return err;
 }
 
-static void prl_entry_destroy_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head));
-}
-
 static void prl_list_destroy_rcu(struct rcu_head *head)
 {
 	struct ip_tunnel_prl_entry *p, *n;
@@ -433,7 +428,7 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
 		     p = &x->next) {
 			if (x->addr == a->addr) {
 				*p = x->next;
-				call_rcu(&x->rcu_head, prl_entry_destroy_rcu);
+				kfree_rcu(x, rcu_head);
 				t->prl_count--;
 				goto out;
 			}
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 63d852cb4ca..53defafb9aa 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -136,14 +136,6 @@ void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u1
 	ieee80211_tx_skb(sdata, skb);
 }
 
-static void kfree_tid_tx(struct rcu_head *rcu_head)
-{
-	struct tid_ampdu_tx *tid_tx =
-	    container_of(rcu_head, struct tid_ampdu_tx, rcu_head);
-
-	kfree(tid_tx);
-}
-
 int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 				    enum ieee80211_back_parties initiator,
 				    bool tx)
@@ -163,7 +155,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 		/* not even started yet! */
 		rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], NULL);
 		spin_unlock_bh(&sta->lock);
-		call_rcu(&tid_tx->rcu_head, kfree_tid_tx);
+		kfree_rcu(tid_tx, rcu_head);
 		return 0;
 	}
 
@@ -322,7 +314,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 		spin_unlock_bh(&sta->lock);
 
 		ieee80211_wake_queue_agg(local, tid);
-		call_rcu(&tid_tx->rcu_head, kfree_tid_tx);
+		kfree_rcu(tid_tx, rcu_head);
 		return;
 	}
 
@@ -701,7 +693,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
 
 	ieee80211_agg_splice_finish(local, tid);
 
-	call_rcu(&tid_tx->rcu_head, kfree_tid_tx);
+	kfree_rcu(tid_tx, rcu_head);
 
  unlock_sta:
 	spin_unlock_bh(&sta->lock);
diff --git a/net/mac80211/work.c b/net/mac80211/work.c
index e73c8cae036..ac3549690b8 100644
--- a/net/mac80211/work.c
+++ b/net/mac80211/work.c
@@ -65,17 +65,9 @@ static void run_again(struct ieee80211_local *local,
 		mod_timer(&local->work_timer, timeout);
 }
 
-static void work_free_rcu(struct rcu_head *head)
-{
-	struct ieee80211_work *wk =
-		container_of(head, struct ieee80211_work, rcu_head);
-
-	kfree(wk);
-}
-
 void free_work(struct ieee80211_work *wk)
 {
-	call_rcu(&wk->rcu_head, work_free_rcu);
+	kfree_rcu(wk, rcu_head);
 }
 
 static int ieee80211_compatible_rates(const u8 *supp_rates, int supp_rates_len,
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 80a23ed62bb..05ecdc281a5 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -68,12 +68,6 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp)
 	return (void *)(*ext) + off;
 }
 
-static void __nf_ct_ext_free_rcu(struct rcu_head *head)
-{
-	struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu);
-	kfree(ext);
-}
-
 void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 {
 	struct nf_ct_ext *old, *new;
@@ -114,7 +108,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 					(void *)old + old->offset[i]);
 			rcu_read_unlock();
 		}
-		call_rcu(&old->rcu, __nf_ct_ext_free_rcu);
+		kfree_rcu(old, rcu);
 		ct->ext = new;
 	}
 
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 4327e101c04..846f895cb65 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -62,13 +62,6 @@ static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = {
 	[OSF_ATTR_FINGER]	= { .len = sizeof(struct xt_osf_user_finger) },
 };
 
-static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head)
-{
-	struct xt_osf_finger *f = container_of(rcu_head, struct xt_osf_finger, rcu_head);
-
-	kfree(f);
-}
-
 static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb,
 			       const struct nlmsghdr *nlh,
 			       const struct nlattr * const osf_attrs[])
@@ -133,7 +126,7 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb,
 		 * We are protected by nfnl mutex.
 		 */
 		list_del_rcu(&sf->finger_entry);
-		call_rcu(&sf->rcu_head, xt_osf_finger_free_rcu);
+		kfree_rcu(sf, rcu_head);
 
 		err = 0;
 		break;
@@ -414,7 +407,7 @@ static void __exit xt_osf_fini(void)
 
 		list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) {
 			list_del_rcu(&f->finger_entry);
-			call_rcu(&f->rcu_head, xt_osf_finger_free_rcu);
+			kfree_rcu(f, rcu_head);
 		}
 	}
 	rcu_read_unlock();
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index e2b0a680dd5..9c38658fba8 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -154,44 +154,6 @@ static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1
  */
 
 /**
- * netlbl_unlhsh_free_addr4 - Frees an IPv4 address entry from the hash table
- * @entry: the entry's RCU field
- *
- * Description:
- * This function is designed to be used as a callback to the call_rcu()
- * function so that memory allocated to a hash table address entry can be
- * released safely.
- *
- */
-static void netlbl_unlhsh_free_addr4(struct rcu_head *entry)
-{
-	struct netlbl_unlhsh_addr4 *ptr;
-
-	ptr = container_of(entry, struct netlbl_unlhsh_addr4, rcu);
-	kfree(ptr);
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-/**
- * netlbl_unlhsh_free_addr6 - Frees an IPv6 address entry from the hash table
- * @entry: the entry's RCU field
- *
- * Description:
- * This function is designed to be used as a callback to the call_rcu()
- * function so that memory allocated to a hash table address entry can be
- * released safely.
- *
- */
-static void netlbl_unlhsh_free_addr6(struct rcu_head *entry)
-{
-	struct netlbl_unlhsh_addr6 *ptr;
-
-	ptr = container_of(entry, struct netlbl_unlhsh_addr6, rcu);
-	kfree(ptr);
-}
-#endif /* IPv6 */
-
-/**
  * netlbl_unlhsh_free_iface - Frees an interface entry from the hash table
  * @entry: the entry's RCU field
  *
@@ -568,7 +530,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net,
 	if (entry == NULL)
 		return -ENOENT;
 
-	call_rcu(&entry->rcu, netlbl_unlhsh_free_addr4);
+	kfree_rcu(entry, rcu);
 	return 0;
 }
 
@@ -629,7 +591,7 @@ static int netlbl_unlhsh_remove_addr6(struct net *net,
 	if (entry == NULL)
 		return -ENOENT;
 
-	call_rcu(&entry->rcu, netlbl_unlhsh_free_addr6);
+	kfree_rcu(entry, rcu);
 	return 0;
 }
 #endif /* IPv6 */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c8f35b5d2ee..5fe4f3b04ed 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1566,12 +1566,6 @@ netlink_kernel_release(struct sock *sk)
 }
 EXPORT_SYMBOL(netlink_kernel_release);
 
-
-static void listeners_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct listeners, rcu));
-}
-
 int __netlink_change_ngroups(struct sock *sk, unsigned int groups)
 {
 	struct listeners *new, *old;
@@ -1588,7 +1582,7 @@ int __netlink_change_ngroups(struct sock *sk, unsigned int groups)
 		memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups));
 		rcu_assign_pointer(tbl->listeners, new);
 
-		call_rcu(&old->rcu, listeners_free_rcu);
+		kfree_rcu(old, rcu);
 	}
 	tbl->groups = groups;
 
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 947038ddd04..1566672235d 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -162,14 +162,6 @@ int phonet_address_add(struct net_device *dev, u8 addr)
 	return err;
 }
 
-static void phonet_device_rcu_free(struct rcu_head *head)
-{
-	struct phonet_device *pnd;
-
-	pnd = container_of(head, struct phonet_device, rcu);
-	kfree(pnd);
-}
-
 int phonet_address_del(struct net_device *dev, u8 addr)
 {
 	struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev));
@@ -188,7 +180,7 @@ int phonet_address_del(struct net_device *dev, u8 addr)
 	mutex_unlock(&pndevs->lock);
 
 	if (pnd)
-		call_rcu(&pnd->rcu, phonet_device_rcu_free);
+		kfree_rcu(pnd, rcu);
 
 	return err;
 }
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 14b42f4ad79..a606025814a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -26,11 +26,6 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
-static void tcf_common_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct tcf_common, tcfc_rcu));
-}
-
 void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 {
 	unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
@@ -47,7 +42,7 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
 			 * gen_estimator est_timer() might access p->tcfc_lock
 			 * or bstats, wait a RCU grace period before freeing p
 			 */
-			call_rcu(&p->tcfc_rcu, tcf_common_free_rcu);
+			kfree_rcu(p, tcfc_rcu);
 			return;
 		}
 	}
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8a1630774fd..b3b9b32f4e0 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -96,11 +96,6 @@ nla_put_failure:
 	goto done;
 }
 
-static void tcf_police_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct tcf_police, tcf_rcu));
-}
-
 static void tcf_police_destroy(struct tcf_police *p)
 {
 	unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK);
@@ -121,7 +116,7 @@ static void tcf_police_destroy(struct tcf_police *p)
 			 * gen_estimator est_timer() might access p->tcf_lock
 			 * or bstats, wait a RCU grace period before freeing p
 			 */
-			call_rcu(&p->tcf_rcu, tcf_police_free_rcu);
+			kfree_rcu(p, tcf_rcu);
 			return;
 		}
 	}
@@ -401,7 +396,6 @@ static void __exit
 police_cleanup_module(void)
 {
 	tcf_unregister_action(&act_police_ops);
-	rcu_barrier(); /* Wait for completion of call_rcu()'s (tcf_police_free_rcu) */
 }
 
 module_init(police_init_module);
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index faf71d179e4..3c06c87cd28 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -219,7 +219,7 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr)
 	}
 
 	if (found) {
-		call_rcu(&addr->rcu, sctp_local_addr_free);
+		kfree_rcu(addr, rcu);
 		SCTP_DBG_OBJCNT_DEC(addr);
 		return 0;
 	}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 865ce7ba4e1..185fe058db1 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -123,7 +123,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 		}
 		spin_unlock_bh(&sctp_local_addr_lock);
 		if (found)
-			call_rcu(&addr->rcu, sctp_local_addr_free);
+			kfree_rcu(addr, rcu);
 		break;
 	}
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d5bf91d04f6..065d99958ce 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -230,13 +230,6 @@ static void sctp_free_local_addr_list(void)
 	}
 }
 
-void sctp_local_addr_free(struct rcu_head *head)
-{
-	struct sctp_sockaddr_entry *e = container_of(head,
-				struct sctp_sockaddr_entry, rcu);
-	kfree(e);
-}
-
 /* Copy the local addresses which are valid for 'scope' into 'bp'.  */
 int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
 			      gfp_t gfp, int copy_flags)
@@ -681,7 +674,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
 		}
 		spin_unlock_bh(&sctp_local_addr_lock);
 		if (found)
-			call_rcu(&addr->rcu, sctp_local_addr_free);
+			kfree_rcu(addr, rcu);
 		break;
 	}
 
diff --git a/net/socket.c b/net/socket.c
index 310d16b1b3c..c2ed7c95ce8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -263,15 +263,6 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-
-
-static void wq_free_rcu(struct rcu_head *head)
-{
-	struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
-
-	kfree(wq);
-}
-
 static void sock_destroy_inode(struct inode *inode)
 {
 	struct socket_alloc *ei;
@@ -279,7 +270,7 @@ static void sock_destroy_inode(struct inode *inode)
 
 	ei = container_of(inode, struct socket_alloc, vfs_inode);
 	wq = rcu_dereference_protected(ei->socket.wq, 1);
-	call_rcu(&wq->rcu, wq_free_rcu);
+	kfree_rcu(wq, rcu);
 	kmem_cache_free(sock_inode_cachep, ei);
 }
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d5f925abe4d..6165622c3e2 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -244,14 +244,19 @@ endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
 ifdef BUILD_C_RECORDMCOUNT
+ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
+  RECORDMCOUNT_FLAGS = -w
+endif
 # Due to recursion, we must skip empty.o.
 # The empty.o file is created in the make process in order to determine
 #  the target endianness and word size. It is made before all other C
 #  files, including recordmcount.
 sub_cmd_record_mcount =					\
 	if [ $(@) != "scripts/mod/empty.o" ]; then	\
-		$(objtree)/scripts/recordmcount "$(@)";	\
+		$(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)";	\
 	fi;
+recordmcount_source := $(srctree)/scripts/recordmcount.c \
+		    $(srctree)/scripts/recordmcount.h
 else
 sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
@@ -259,6 +264,7 @@ sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH
 	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
 	"$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
+recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif
 cmd_record_mcount = 						\
 	if [ "$(findstring -pg,$(_c_flags))" = "-pg" ]; then	\
@@ -279,13 +285,13 @@ define rule_cc_o_c
 endef
 
 # Built-in and composite module parts
-$(obj)/%.o: $(src)/%.c FORCE
+$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
 # Single-part modules are special since we need to mark them in $(MODVERDIR)
 
-$(single-used-m): $(obj)/%.o: $(src)/%.c FORCE
+$(single-used-m): $(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 	@{ echo $(@:.o=.ko); echo $@; } > $(MODVERDIR)/$(@F:.o=.mod)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index cd104afcc5f..413c53693e6 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -420,11 +420,10 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		return 0;
 	}
 
-	if (hdr->e_shnum == 0) {
+	if (hdr->e_shnum == SHN_UNDEF) {
 		/*
 		 * There are more than 64k sections,
 		 * read count from .sh_size.
-		 * note: it doesn't need shndx2secindex()
 		 */
 		info->num_sections = TO_NATIVE(sechdrs[0].sh_size);
 	}
@@ -432,8 +431,7 @@ static int parse_elf(struct elf_info *info, const char *filename)
 		info->num_sections = hdr->e_shnum;
 	}
 	if (hdr->e_shstrndx == SHN_XINDEX) {
-		info->secindex_strings =
-		    shndx2secindex(TO_NATIVE(sechdrs[0].sh_link));
+		info->secindex_strings = TO_NATIVE(sechdrs[0].sh_link);
 	}
 	else {
 		info->secindex_strings = hdr->e_shstrndx;
@@ -489,7 +487,7 @@ static int parse_elf(struct elf_info *info, const char *filename)
 			    sechdrs[i].sh_offset;
 			info->symtab_stop  = (void *)hdr +
 			    sechdrs[i].sh_offset + sechdrs[i].sh_size;
-			sh_link_idx = shndx2secindex(sechdrs[i].sh_link);
+			sh_link_idx = sechdrs[i].sh_link;
 			info->strtab       = (void *)hdr +
 			    sechdrs[sh_link_idx].sh_offset;
 		}
@@ -516,11 +514,9 @@ static int parse_elf(struct elf_info *info, const char *filename)
 
 	if (symtab_shndx_idx != ~0U) {
 		Elf32_Word *p;
-		if (symtab_idx !=
-		    shndx2secindex(sechdrs[symtab_shndx_idx].sh_link))
+		if (symtab_idx != sechdrs[symtab_shndx_idx].sh_link)
 			fatal("%s: SYMTAB_SHNDX has bad sh_link: %u!=%u\n",
-			      filename,
-			      shndx2secindex(sechdrs[symtab_shndx_idx].sh_link),
+			      filename, sechdrs[symtab_shndx_idx].sh_link,
 			      symtab_idx);
 		/* Fix endianness */
 		for (p = info->symtab_shndx_start; p < info->symtab_shndx_stop;
@@ -1446,7 +1442,7 @@ static unsigned int *reloc_location(struct elf_info *elf,
 				    Elf_Shdr *sechdr, Elf_Rela *r)
 {
 	Elf_Shdr *sechdrs = elf->sechdrs;
-	int section = shndx2secindex(sechdr->sh_info);
+	int section = sechdr->sh_info;
 
 	return (void *)elf->hdr + sechdrs[section].sh_offset +
 		r->r_offset;
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 0388cfccac8..2031119080d 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -145,33 +145,22 @@ static inline int is_shndx_special(unsigned int i)
 	return i != SHN_XINDEX && i >= SHN_LORESERVE && i <= SHN_HIRESERVE;
 }
 
-/* shndx is in [0..SHN_LORESERVE) U (SHN_HIRESERVE, 0xfffffff], thus:
- * shndx == 0               <=> sechdrs[0]
- * ......
- * shndx == SHN_LORESERVE-1 <=> sechdrs[SHN_LORESERVE-1]
- * shndx == SHN_HIRESERVE+1 <=> sechdrs[SHN_LORESERVE]
- * shndx == SHN_HIRESERVE+2 <=> sechdrs[SHN_LORESERVE+1]
- * ......
- * fyi: sym->st_shndx is uint16, SHN_LORESERVE = ff00, SHN_HIRESERVE = ffff,
- * so basically we map  0000..feff -> 0000..feff
- *                      ff00..ffff -> (you are a bad boy, dont do it)
- *                     10000..xxxx -> ff00..(xxxx-0x100)
+/*
+ * Move reserved section indices SHN_LORESERVE..SHN_HIRESERVE out of
+ * the way to -256..-1, to avoid conflicting with real section
+ * indices.
  */
-static inline unsigned int shndx2secindex(unsigned int i)
-{
-	if (i <= SHN_HIRESERVE)
-		return i;
-	return i - (SHN_HIRESERVE + 1 - SHN_LORESERVE);
-}
+#define SPECIAL(i) ((i) - (SHN_HIRESERVE + 1))
 
 /* Accessor for sym->st_shndx, hides ugliness of "64k sections" */
 static inline unsigned int get_secindex(const struct elf_info *info,
 					const Elf_Sym *sym)
 {
+	if (is_shndx_special(sym->st_shndx))
+		return SPECIAL(sym->st_shndx);
 	if (sym->st_shndx != SHN_XINDEX)
 		return sym->st_shndx;
-	return shndx2secindex(info->symtab_shndx_start[sym -
-						       info->symtab_start]);
+	return info->symtab_shndx_start[sym - info->symtab_start];
 }
 
 /* file2alias.c */
diff --git a/scripts/module-common.lds b/scripts/module-common.lds
index 47a1f9ae0ed..0865b3e752b 100644
--- a/scripts/module-common.lds
+++ b/scripts/module-common.lds
@@ -5,4 +5,15 @@
  */
 SECTIONS {
 	/DISCARD/ : { *(.discard) }
+
+	__ksymtab		: { *(SORT(___ksymtab+*)) }
+	__ksymtab_gpl		: { *(SORT(___ksymtab_gpl+*)) }
+	__ksymtab_unused	: { *(SORT(___ksymtab_unused+*)) }
+	__ksymtab_unused_gpl	: { *(SORT(___ksymtab_unused_gpl+*)) }
+	__ksymtab_gpl_future	: { *(SORT(___ksymtab_gpl_future+*)) }
+	__kcrctab		: { *(SORT(___kcrctab+*)) }
+	__kcrctab_gpl		: { *(SORT(___kcrctab_gpl+*)) }
+	__kcrctab_unused	: { *(SORT(___kcrctab_unused+*)) }
+	__kcrctab_unused_gpl	: { *(SORT(___kcrctab_unused_gpl+*)) }
+	__kcrctab_gpl_future	: { *(SORT(___kcrctab_gpl_future+*)) }
 }
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index f9f6f52db77..ee52cb8e17a 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -24,6 +24,7 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
+#include <getopt.h>
 #include <elf.h>
 #include <fcntl.h>
 #include <setjmp.h>
@@ -39,6 +40,7 @@ static char gpfx;	/* prefix for global symbol name (sometimes '_') */
 static struct stat sb;	/* Remember .st_size, etc. */
 static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
 static const char *altmcount;	/* alternate mcount symbol name */
+static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
 
 /* setjmp() return values */
 enum {
@@ -78,7 +80,7 @@ static off_t
 ulseek(int const fd, off_t const offset, int const whence)
 {
 	off_t const w = lseek(fd, offset, whence);
-	if ((off_t)-1 == w) {
+	if (w == (off_t)-1) {
 		perror("lseek");
 		fail_file();
 	}
@@ -111,13 +113,41 @@ static void *
 umalloc(size_t size)
 {
 	void *const addr = malloc(size);
-	if (0 == addr) {
+	if (addr == 0) {
 		fprintf(stderr, "malloc failed: %zu bytes\n", size);
 		fail_file();
 	}
 	return addr;
 }
 
+static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+static unsigned char *ideal_nop;
+
+static char rel_type_nop;
+
+static int (*make_nop)(void *map, size_t const offset);
+
+static int make_nop_x86(void *map, size_t const offset)
+{
+	uint32_t *ptr;
+	unsigned char *op;
+
+	/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
+	ptr = map + offset;
+	if (*ptr != 0)
+		return -1;
+
+	op = map + offset - 1;
+	if (*op != 0xe8)
+		return -1;
+
+	/* convert to nop */
+	ulseek(fd_map, offset - 1, SEEK_SET);
+	uwrite(fd_map, ideal_nop, 5);
+	return 0;
+}
+
 /*
  * Get the whole file as a programming convenience in order to avoid
  * malloc+lseek+read+free of many pieces.  If successful, then mmap
@@ -136,7 +166,7 @@ static void *mmap_file(char const *fname)
 	void *addr;
 
 	fd_map = open(fname, O_RDWR);
-	if (0 > fd_map || 0 > fstat(fd_map, &sb)) {
+	if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
 		perror(fname);
 		fail_file();
 	}
@@ -147,7 +177,7 @@ static void *mmap_file(char const *fname)
 	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
 		    fd_map, 0);
 	mmap_failed = 0;
-	if (MAP_FAILED == addr) {
+	if (addr == MAP_FAILED) {
 		mmap_failed = 1;
 		addr = umalloc(sb.st_size);
 		uread(fd_map, addr, sb.st_size);
@@ -206,12 +236,13 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return 0 == strcmp(".text",           txtname) ||
-		0 == strcmp(".ref.text",      txtname) ||
-		0 == strcmp(".sched.text",    txtname) ||
-		0 == strcmp(".spinlock.text", txtname) ||
-		0 == strcmp(".irqentry.text", txtname) ||
-		0 == strcmp(".text.unlikely", txtname);
+	return strcmp(".text",           txtname) == 0 ||
+		strcmp(".ref.text",      txtname) == 0 ||
+		strcmp(".sched.text",    txtname) == 0 ||
+		strcmp(".spinlock.text", txtname) == 0 ||
+		strcmp(".irqentry.text", txtname) == 0 ||
+		strcmp(".kprobes.text", txtname) == 0 ||
+		strcmp(".text.unlikely", txtname) == 0;
 }
 
 /* 32 bit and 64 bit are very similar */
@@ -264,43 +295,48 @@ do_file(char const *const fname)
 	w8 = w8nat;
 	switch (ehdr->e_ident[EI_DATA]) {
 		static unsigned int const endian = 1;
-	default: {
+	default:
 		fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
 			ehdr->e_ident[EI_DATA], fname);
 		fail_file();
-	} break;
-	case ELFDATA2LSB: {
-		if (1 != *(unsigned char const *)&endian) {
+		break;
+	case ELFDATA2LSB:
+		if (*(unsigned char const *)&endian != 1) {
 			/* main() is big endian, file.o is little endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
-	case ELFDATA2MSB: {
-		if (0 != *(unsigned char const *)&endian) {
+		break;
+	case ELFDATA2MSB:
+		if (*(unsigned char const *)&endian != 0) {
 			/* main() is little endian, file.o is big endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
+		break;
 	}  /* end switch */
-	if (0 != memcmp(ELFMAG, ehdr->e_ident, SELFMAG)
-	||  ET_REL != w2(ehdr->e_type)
-	||  EV_CURRENT != ehdr->e_ident[EI_VERSION]) {
+	if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0
+	||  w2(ehdr->e_type) != ET_REL
+	||  ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
 		fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
 		fail_file();
 	}
 
 	gpfx = 0;
 	switch (w2(ehdr->e_machine)) {
-	default: {
+	default:
 		fprintf(stderr, "unrecognized e_machine %d %s\n",
 			w2(ehdr->e_machine), fname);
 		fail_file();
-	} break;
-	case EM_386:	 reltype = R_386_32;                   break;
+		break;
+	case EM_386:
+		reltype = R_386_32;
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_32;
+		mcount_adjust_32 = -1;
+		break;
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
@@ -311,67 +347,91 @@ do_file(char const *const fname)
 	case EM_S390:    /* reltype: e_class    */ gpfx = '_'; break;
 	case EM_SH:	 reltype = R_SH_DIR32;                 break;
 	case EM_SPARCV9: reltype = R_SPARC_64;     gpfx = '_'; break;
-	case EM_X86_64:	 reltype = R_X86_64_64;                break;
+	case EM_X86_64:
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_64;
+		reltype = R_X86_64_64;
+		mcount_adjust_64 = -1;
+		break;
 	}  /* end switch */
 
 	switch (ehdr->e_ident[EI_CLASS]) {
-	default: {
+	default:
 		fprintf(stderr, "unrecognized ELF class %d %s\n",
 			ehdr->e_ident[EI_CLASS], fname);
 		fail_file();
-	} break;
-	case ELFCLASS32: {
-		if (sizeof(Elf32_Ehdr) != w2(ehdr->e_ehsize)
-		||  sizeof(Elf32_Shdr) != w2(ehdr->e_shentsize)) {
+		break;
+	case ELFCLASS32:
+		if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
+		||  w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ehdr->e_machine))
+		if (w2(ehdr->e_machine) == EM_S390) {
 			reltype = R_390_32;
-		if (EM_MIPS == w2(ehdr->e_machine)) {
+			mcount_adjust_32 = -4;
+		}
+		if (w2(ehdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_32;
 			is_fake_mcount32 = MIPS32_is_fake_mcount;
 		}
 		do32(ehdr, fname, reltype);
-	} break;
+		break;
 	case ELFCLASS64: {
 		Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
-		if (sizeof(Elf64_Ehdr) != w2(ghdr->e_ehsize)
-		||  sizeof(Elf64_Shdr) != w2(ghdr->e_shentsize)) {
+		if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr)
+		||  w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ghdr->e_machine))
+		if (w2(ghdr->e_machine) == EM_S390) {
 			reltype = R_390_64;
-		if (EM_MIPS == w2(ghdr->e_machine)) {
+			mcount_adjust_64 = -8;
+		}
+		if (w2(ghdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_64;
 			Elf64_r_sym = MIPS64_r_sym;
 			Elf64_r_info = MIPS64_r_info;
 			is_fake_mcount64 = MIPS64_is_fake_mcount;
 		}
 		do64(ghdr, fname, reltype);
-	} break;
+		break;
+	}
 	}  /* end switch */
 
 	cleanup();
 }
 
 int
-main(int argc, char const *argv[])
+main(int argc, char *argv[])
 {
 	const char ftrace[] = "/ftrace.o";
 	int ftrace_size = sizeof(ftrace) - 1;
 	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+	int c;
+	int i;
+
+	while ((c = getopt(argc, argv, "w")) >= 0) {
+		switch (c) {
+		case 'w':
+			warn_on_notrace_sect = 1;
+			break;
+		default:
+			fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
+			return 0;
+		}
+	}
 
-	if (argc <= 1) {
-		fprintf(stderr, "usage: recordmcount file.o...\n");
+	if ((argc - optind) < 1) {
+		fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
 		return 0;
 	}
 
 	/* Process each file in turn, allowing deep failure. */
-	for (--argc, ++argv; 0 < argc; --argc, ++argv) {
+	for (i = optind; i < argc; i++) {
+		char *file = argv[i];
 		int const sjval = setjmp(jmpenv);
 		int len;
 
@@ -380,29 +440,29 @@ main(int argc, char const *argv[])
 		 * function but does not call it. Since ftrace.o should
 		 * not be traced anyway, we just skip it.
 		 */
-		len = strlen(argv[0]);
+		len = strlen(file);
 		if (len >= ftrace_size &&
-		    strcmp(argv[0] + (len - ftrace_size), ftrace) == 0)
+		    strcmp(file + (len - ftrace_size), ftrace) == 0)
 			continue;
 
 		switch (sjval) {
-		default: {
-			fprintf(stderr, "internal error: %s\n", argv[0]);
+		default:
+			fprintf(stderr, "internal error: %s\n", file);
 			exit(1);
-		} break;
-		case SJ_SETJMP: {  /* normal sequence */
+			break;
+		case SJ_SETJMP:    /* normal sequence */
 			/* Avoid problems if early cleanup() */
 			fd_map = -1;
 			ehdr_curr = NULL;
 			mmap_failed = 1;
-			do_file(argv[0]);
-		} break;
-		case SJ_FAIL: {  /* error in do_file or below */
+			do_file(file);
+			break;
+		case SJ_FAIL:    /* error in do_file or below */
 			++n_error;
-		} break;
-		case SJ_SUCCEED: {  /* premature success */
+			break;
+		case SJ_SUCCEED:    /* premature success */
 			/* do nothing */
-		} break;
+			break;
 		}  /* end switch */
 	}
 	return !!n_error;
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index baf187bee98..4be60364a40 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -22,11 +22,15 @@
 #undef is_fake_mcount
 #undef fn_is_fake_mcount
 #undef MIPS_is_fake_mcount
+#undef mcount_adjust
 #undef sift_rel_mcount
+#undef nop_mcount
 #undef find_secsym_ndx
 #undef __has_rel_mcount
 #undef has_rel_mcount
 #undef tot_relsize
+#undef get_mcountsym
+#undef get_sym_str_and_relp
 #undef do_func
 #undef Elf_Addr
 #undef Elf_Ehdr
@@ -49,14 +53,18 @@
 #ifdef RECORD_MCOUNT_64
 # define append_func		append64
 # define sift_rel_mcount	sift64_rel_mcount
+# define nop_mcount		nop_mcount_64
 # define find_secsym_ndx	find64_secsym_ndx
 # define __has_rel_mcount	__has64_rel_mcount
 # define has_rel_mcount		has64_rel_mcount
 # define tot_relsize		tot64_relsize
+# define get_sym_str_and_relp	get_sym_str_and_relp_64
 # define do_func		do64
+# define get_mcountsym		get_mcountsym_64
 # define is_fake_mcount		is_fake_mcount64
 # define fn_is_fake_mcount	fn_is_fake_mcount64
 # define MIPS_is_fake_mcount	MIPS64_is_fake_mcount
+# define mcount_adjust		mcount_adjust_64
 # define Elf_Addr		Elf64_Addr
 # define Elf_Ehdr		Elf64_Ehdr
 # define Elf_Shdr		Elf64_Shdr
@@ -77,14 +85,18 @@
 #else
 # define append_func		append32
 # define sift_rel_mcount	sift32_rel_mcount
+# define nop_mcount		nop_mcount_32
 # define find_secsym_ndx	find32_secsym_ndx
 # define __has_rel_mcount	__has32_rel_mcount
 # define has_rel_mcount		has32_rel_mcount
 # define tot_relsize		tot32_relsize
+# define get_sym_str_and_relp	get_sym_str_and_relp_32
 # define do_func		do32
+# define get_mcountsym		get_mcountsym_32
 # define is_fake_mcount		is_fake_mcount32
 # define fn_is_fake_mcount	fn_is_fake_mcount32
 # define MIPS_is_fake_mcount	MIPS32_is_fake_mcount
+# define mcount_adjust		mcount_adjust_32
 # define Elf_Addr		Elf32_Addr
 # define Elf_Ehdr		Elf32_Ehdr
 # define Elf_Shdr		Elf32_Shdr
@@ -123,6 +135,8 @@ static void fn_ELF_R_INFO(Elf_Rel *const rp, unsigned sym, unsigned type)
 }
 static void (*Elf_r_info)(Elf_Rel *const rp, unsigned sym, unsigned type) = fn_ELF_R_INFO;
 
+static int mcount_adjust = 0;
+
 /*
  * MIPS mcount long call has 2 _mcount symbols, only the position of the 1st
  * _mcount symbol is needed for dynamic function tracer, with it, to disable
@@ -234,6 +248,49 @@ static void append_func(Elf_Ehdr *const ehdr,
 	uwrite(fd_map, ehdr, sizeof(*ehdr));
 }
 
+static unsigned get_mcountsym(Elf_Sym const *const sym0,
+			      Elf_Rel const *relp,
+			      char const *const str0)
+{
+	unsigned mcountsym = 0;
+
+	Elf_Sym const *const symp =
+		&sym0[Elf_r_sym(relp)];
+	char const *symname = &str0[w(symp->st_name)];
+	char const *mcount = gpfx == '_' ? "_mcount" : "mcount";
+
+	if (symname[0] == '.')
+		++symname;  /* ppc64 hack */
+	if (strcmp(mcount, symname) == 0 ||
+	    (altmcount && strcmp(altmcount, symname) == 0))
+		mcountsym = Elf_r_sym(relp);
+
+	return mcountsym;
+}
+
+static void get_sym_str_and_relp(Elf_Shdr const *const relhdr,
+				 Elf_Ehdr const *const ehdr,
+				 Elf_Sym const **sym0,
+				 char const **str0,
+				 Elf_Rel const **relp)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const symsec_sh_link = w(relhdr->sh_link);
+	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
+	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
+	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
+		+ (void *)ehdr);
+
+	*sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
+				  + (void *)ehdr);
+
+	*str0 = (char const *)(_w(strsec->sh_offset)
+			       + (void *)ehdr);
+
+	*relp = rel0;
+}
+
 /*
  * Look at the relocations in order to find the calls to mcount.
  * Accumulate the section offsets that are found, and their relocation info,
@@ -250,47 +307,27 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 {
 	uint_t *const mloc0 = mlocp;
 	Elf_Rel *mrelp = *mrelpp;
-	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
-		+ (void *)ehdr);
-	unsigned const symsec_sh_link = w(relhdr->sh_link);
-	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
-	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
-		+ (void *)ehdr);
-
-	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
-	char const *const str0 = (char const *)(_w(strsec->sh_offset)
-		+ (void *)ehdr);
-
-	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
-		+ (void *)ehdr);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
 	unsigned rel_entsize = _w(relhdr->sh_entsize);
 	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
-	Elf_Rel const *relp = rel0;
-
 	unsigned mcountsym = 0;
 	unsigned t;
 
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
 	for (t = nrel; t; --t) {
-		if (!mcountsym) {
-			Elf_Sym const *const symp =
-				&sym0[Elf_r_sym(relp)];
-			char const *symname = &str0[w(symp->st_name)];
-			char const *mcount = '_' == gpfx ? "_mcount" : "mcount";
-
-			if ('.' == symname[0])
-				++symname;  /* ppc64 hack */
-			if (0 == strcmp(mcount, symname) ||
-			    (altmcount && 0 == strcmp(altmcount, symname)))
-				mcountsym = Elf_r_sym(relp);
-		}
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
-			uint_t const addend = _w(_w(relp->r_offset) - recval);
-
+			uint_t const addend =
+				_w(_w(relp->r_offset) - recval + mcount_adjust);
 			mrelp->r_offset = _w(offbase
 				+ ((void *)mlocp - (void *)mloc0));
 			Elf_r_info(mrelp, recsym, reltype);
-			if (sizeof(Elf_Rela) == rel_entsize) {
+			if (rel_entsize == sizeof(Elf_Rela)) {
 				((Elf_Rela *)mrelp)->r_addend = addend;
 				*mlocp++ = 0;
 			} else
@@ -304,6 +341,63 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 	return mlocp;
 }
 
+/*
+ * Read the relocation table again, but this time its called on sections
+ * that are not going to be traced. The mcount calls here will be converted
+ * into nops.
+ */
+static void nop_mcount(Elf_Shdr const *const relhdr,
+		       Elf_Ehdr const *const ehdr,
+		       const char *const txtname)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
+	Elf_Shdr const *const shdr = &shdr0[w(relhdr->sh_info)];
+	unsigned rel_entsize = _w(relhdr->sh_entsize);
+	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
+	unsigned mcountsym = 0;
+	unsigned t;
+	int once = 0;
+
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
+	for (t = nrel; t; --t) {
+		int ret = -1;
+
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
+
+		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
+			if (make_nop)
+				ret = make_nop((void *)ehdr, shdr->sh_offset + relp->r_offset);
+			if (warn_on_notrace_sect && !once) {
+				printf("Section %s has mcount callers being ignored\n",
+				       txtname);
+				once = 1;
+				/* just warn? */
+				if (!make_nop)
+					return;
+			}
+		}
+
+		/*
+		 * If we successfully removed the mcount, mark the relocation
+		 * as a nop (don't do anything with it).
+		 */
+		if (!ret) {
+			Elf_Rel rel;
+			rel = *(Elf_Rel *)relp;
+			Elf_r_info(&rel, Elf_r_sym(relp), rel_type_nop);
+			ulseek(fd_map, (void *)relp - (void *)ehdr, SEEK_SET);
+			uwrite(fd_map, &rel, sizeof(rel));
+		}
+		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
+	}
+}
+
 
 /*
  * Find a symbol in the given section, to be used as the base for relocating
@@ -354,13 +448,13 @@ __has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
 	Elf_Shdr const *const txthdr = &shdr0[w(relhdr->sh_info)];
 	char const *const txtname = &shstrtab[w(txthdr->sh_name)];
 
-	if (0 == strcmp("__mcount_loc", txtname)) {
+	if (strcmp("__mcount_loc", txtname) == 0) {
 		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
 			fname);
 		succeed_file();
 	}
-	if (SHT_PROGBITS != w(txthdr->sh_type) ||
-	    !is_mcounted_section_name(txtname))
+	if (w(txthdr->sh_type) != SHT_PROGBITS ||
+	    !(w(txthdr->sh_flags) & SHF_EXECINSTR))
 		return NULL;
 	return txtname;
 }
@@ -370,7 +464,7 @@ static char const *has_rel_mcount(Elf_Shdr const *const relhdr,
 				  char const *const shstrtab,
 				  char const *const fname)
 {
-	if (SHT_REL  != w(relhdr->sh_type) && SHT_RELA != w(relhdr->sh_type))
+	if (w(relhdr->sh_type) != SHT_REL && w(relhdr->sh_type) != SHT_RELA)
 		return NULL;
 	return __has_rel_mcount(relhdr, shdr0, shstrtab, fname);
 }
@@ -383,9 +477,11 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,
 {
 	unsigned totrelsz = 0;
 	Elf_Shdr const *shdrp = shdr0;
+	char const *txtname;
 
 	for (; nhdr; --nhdr, ++shdrp) {
-		if (has_rel_mcount(shdrp, shdr0, shstrtab, fname))
+		txtname = has_rel_mcount(shdrp, shdr0, shstrtab, fname);
+		if (txtname && is_mcounted_section_name(txtname))
 			totrelsz += _w(shdrp->sh_size);
 	}
 	return totrelsz;
@@ -421,7 +517,7 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
 		char const *const txtname = has_rel_mcount(relhdr, shdr0,
 			shstrtab, fname);
-		if (txtname) {
+		if (txtname && is_mcounted_section_name(txtname)) {
 			uint_t recval = 0;
 			unsigned const recsym = find_secsym_ndx(
 				w(relhdr->sh_info), txtname, &recval,
@@ -432,6 +528,12 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 			mlocp = sift_rel_mcount(mlocp,
 				(void *)mlocp - (void *)mloc0, &mrelp,
 				relhdr, ehdr, recsym, recval, reltype);
+		} else if (txtname && (warn_on_notrace_sect || make_nop)) {
+			/*
+			 * This section is ignored by ftrace, but still
+			 * has mcount calls. Convert them to nops now.
+			 */
+			nop_mcount(relhdr, ehdr, txtname);
 		}
 	}
 	if (mloc0 != mlocp) {
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 4be0deea71c..858966ab019 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -134,6 +134,7 @@ my %text_sections = (
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,
+     ".kprobes.text" => 1,
      ".text.unlikely" => 1,
 );
 
@@ -222,6 +223,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
     $type = ".quad";
     $alignment = 8;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_x86_64";
@@ -231,6 +233,7 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "i386") {
     $alignment = 4;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_i386";
@@ -240,12 +243,14 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "s390" && $bits == 32) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_32\\s+_mcount\$";
+    $mcount_adjust = -4;
     $alignment = 4;
     $ld .= " -m elf_s390";
     $cc .= " -m31";
 
 } elsif ($arch eq "s390" && $bits == 64) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
+    $mcount_adjust = -8;
     $alignment = 8;
     $type = ".quad";
     $ld .= " -m elf64_s390";
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index c6ca8662a46..f66baf44f32 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -69,18 +69,6 @@ error:
 EXPORT_SYMBOL_GPL(user_instantiate);
 
 /*
- * dispose of the old data from an updated user defined key
- */
-static void user_update_rcu_disposal(struct rcu_head *rcu)
-{
-	struct user_key_payload *upayload;
-
-	upayload = container_of(rcu, struct user_key_payload, rcu);
-
-	kfree(upayload);
-}
-
-/*
  * update a user defined key
  * - the key's semaphore is write-locked
  */
@@ -114,7 +102,7 @@ int user_update(struct key *key, const void *data, size_t datalen)
 		key->expiry = 0;
 	}
 
-	call_rcu(&zap->rcu, user_update_rcu_disposal);
+	kfree_rcu(zap, rcu);
 
 error:
 	return ret;
@@ -145,7 +133,7 @@ void user_revoke(struct key *key)
 
 	if (upayload) {
 		rcu_assign_pointer(key->payload.data, NULL);
-		call_rcu(&upayload->rcu, user_update_rcu_disposal);
+		kfree_rcu(upayload, rcu);
 	}
 }
 
diff --git a/security/selinux/netif.c b/security/selinux/netif.c
index d6095d63d83..58cc481c93d 100644
--- a/security/selinux/netif.c
+++ b/security/selinux/netif.c
@@ -104,22 +104,6 @@ static int sel_netif_insert(struct sel_netif *netif)
 }
 
 /**
- * sel_netif_free - Frees an interface entry
- * @p: the entry's RCU field
- *
- * Description:
- * This function is designed to be used as a callback to the call_rcu()
- * function so that memory allocated to a hash table interface entry can be
- * released safely.
- *
- */
-static void sel_netif_free(struct rcu_head *p)
-{
-	struct sel_netif *netif = container_of(p, struct sel_netif, rcu_head);
-	kfree(netif);
-}
-
-/**
  * sel_netif_destroy - Remove an interface record from the table
  * @netif: the existing interface record
  *
@@ -131,7 +115,7 @@ static void sel_netif_destroy(struct sel_netif *netif)
 {
 	list_del_rcu(&netif->list);
 	sel_netif_total--;
-	call_rcu(&netif->rcu_head, sel_netif_free);
+	kfree_rcu(netif, rcu_head);
 }
 
 /**
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 5bb41e55a3a..3152cca1550 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 36b38277422..47102206911 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 66f040b3072..86c87e214b1 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -113,13 +113,61 @@ OPTIONS
         Do various checks like samples ordering and lost events.
 
 -f::
---fields
+--fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, sym. Field
-        list must be prepended with the type, trace, sw or hw,
+        list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,sym  and -f trace:time,cpu,trace
 
+		perf script -f <fields>
+
+	is equivalent to:
+
+		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+    
+	i.e., the specified fields apply to all event types if the type string
+	is not given.
+    
+	The arguments are processed in the order received. A later usage can
+	reset a prior request. e.g.:
+    
+		-f trace: -f comm,tid,time,sym
+    
+	The first -f suppresses trace events (field list is ""), but then the
+	second invocation sets the fields to comm,tid,time,sym. In this case a
+	warning is given to the user:
+    
+		"Overriding previous field request for all events."
+    
+	Alternativey, consider the order:
+    
+		-f comm,tid,time,sym -f trace:
+    
+	The first -f sets the fields for all events and the second -f
+	suppresses trace events. The user is given a warning message about
+	the override, and the result of the above is that only S/W and H/W
+	events are displayed with the given fields.
+    
+	For the 'wildcard' option if a user selected field is invalid for an
+	event type, a message is displayed to the user that the option is
+	ignored for that type. For example:
+    
+		$ perf script -f comm,tid,trace
+		'trace' not valid for hardware events. Ignoring.
+		'trace' not valid for software events. Ignoring.
+    
+	Alternatively, if the type is given an invalid field is specified it
+	is an error. For example:
+    
+        perf script -v -f sw:comm,tid,trace
+        'trace' not valid for software events.
+    
+	At this point usage is displayed, and perf-script exits.
+    
+	Finally, a user may not set fields to none for all event types.
+	i.e., -f "" is not allowed.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0c542563ea6..1455413ec7a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -5,6 +5,8 @@ endif
 # The default target of this Makefile is...
 all:
 
+include config/utilities.mak
+
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
 OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
@@ -13,6 +15,12 @@ endif
 
 # Define V to have a more verbose compile.
 #
+# Define PYTHON to point to the python binary if the default
+# `python' is not correct; for example: PYTHON=python2
+#
+# Define PYTHON_CONFIG to point to the python-config binary if
+# the default `$(PYTHON)-config' is not correct.
+#
 # Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
 #
 # Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
@@ -134,7 +142,7 @@ INSTALL = install
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
--include feature-tests.mak
+-include config/feature-tests.mak
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
 	CFLAGS := $(CFLAGS) -fstack-protector-all
@@ -169,12 +177,10 @@ grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
-	$(QUIET_GEN)( \
-		export CFLAGS="$(BASIC_CFLAGS)"; \
-		python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
-			--build-temp='$(OUTPUT)python/temp' \
-	)
-
+	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
+	  --quiet build_ext \
+	  --build-lib='$(OUTPUT)python' \
+	  --build-temp='$(OUTPUT)python/temp'
 #
 # No Perl scripts right now:
 #
@@ -479,24 +485,74 @@ else
 	endif
 endif
 
-ifdef NO_LIBPYTHON
-	BASIC_CFLAGS += -DNO_LIBPYTHON
+disable-python = $(eval $(disable-python_code))
+define disable-python_code
+  BASIC_CFLAGS += -DNO_LIBPYTHON
+  $(if $(1),$(warning No $(1) was found))
+  $(warning Python support won't be built)
+endef
+
+override PYTHON := \
+  $(call get-executable-or-default,PYTHON,python)
+
+ifndef PYTHON
+  $(call disable-python,python interpreter)
+  python-clean :=
 else
-       PYTHON_EMBED_LDOPTS = $(shell python-config --ldflags 2>/dev/null)
-       PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-       PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-	PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
-	FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-	ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
-		msg := $(warning No Python.h found, install python-dev[el] to have python support in 'perf script' and to build the python bindings)
-		BASIC_CFLAGS += -DNO_LIBPYTHON
-	else
-               ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
-               EXTLIBS += $(PYTHON_EMBED_LIBADD)
-		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-		LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-		LANG_BINDINGS += $(OUTPUT)python/perf.so
-	endif
+
+  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
+
+  python-clean := $(PYTHON_WORD) util/setup.py clean \
+    --build-lib='$(OUTPUT)python' \
+    --build-temp='$(OUTPUT)python/temp'
+
+  ifdef NO_LIBPYTHON
+    $(call disable-python)
+  else
+
+    override PYTHON_CONFIG := \
+      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+
+    ifndef PYTHON_CONFIG
+      $(call disable-python,python-config tool)
+    else
+
+      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+
+      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED)),y)
+          $(warning Python 3 is not yet supported; please set)
+          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
+          $(warning If you also have Python 2 installed, then)
+          $(warning try something like:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make PYTHON=python2)
+          $(warning $(and ,))
+          $(warning Otherwise, disable Python support entirely:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make NO_LIBPYTHON=1)
+          $(warning $(and ,))
+          $(error   $(and ,))
+        else
+          ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+          EXTLIBS += $(PYTHON_EMBED_LIBADD)
+          LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+          LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+          LANG_BINDINGS += $(OUTPUT)python/perf.so
+        endif
+
+      endif
+    endif
+  endif
 endif
 
 ifdef NO_DEMANGLE
@@ -837,8 +893,7 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	@python util/setup.py clean --build-lib='$(OUTPUT)python' \
-				   --build-temp='$(OUTPUT)python/temp'
+	$(python-clean)
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ac574ea2391..974f6d3f4e5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -49,57 +49,169 @@ struct output_option {
 };
 
 /* default set to maintain compatibility with current format */
-static u64 output_fields[PERF_TYPE_MAX] = {
-	[PERF_TYPE_HARDWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
-
-	[PERF_TYPE_SOFTWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
-
-	[PERF_TYPE_TRACEPOINT] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-				 PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-				 PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+static struct {
+	bool user_set;
+	bool wildcard_set;
+	u64 fields;
+	u64 invalid_fields;
+} output[PERF_TYPE_MAX] = {
+
+	[PERF_TYPE_HARDWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_SOFTWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_TRACEPOINT] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_RAW] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
 };
 
-static bool output_set_by_user;
+static bool output_set_by_user(void)
+{
+	int j;
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		if (output[j].user_set)
+			return true;
+	}
+	return false;
+}
+
+static const char *output_field2str(enum perf_output_field field)
+{
+	int i, imax = ARRAY_SIZE(all_output_options);
+	const char *str = "";
+
+	for (i = 0; i < imax; ++i) {
+		if (all_output_options[i].field == field) {
+			str = all_output_options[i].str;
+			break;
+		}
+	}
+	return str;
+}
 
-#define PRINT_FIELD(x)  (output_fields[attr->type] & PERF_OUTPUT_##x)
+#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_session__check_attr(struct perf_session *session,
-				    struct perf_event_attr *attr)
+static int perf_event_attr__check_stype(struct perf_event_attr *attr,
+				  u64 sample_type, const char *sample_msg,
+				  enum perf_output_field field)
 {
+	int type = attr->type;
+	const char *evname;
+
+	if (attr->sample_type & sample_type)
+		return 0;
+
+	if (output[type].user_set) {
+		evname = __event_name(attr->type, attr->config);
+		pr_err("Samples for '%s' event do not have %s attribute set. "
+		       "Cannot print '%s' field.\n",
+		       evname, sample_msg, output_field2str(field));
+		return -1;
+	}
+
+	/* user did not ask for it explicitly so remove from the default list */
+	output[type].fields &= ~field;
+	evname = __event_name(attr->type, attr->config);
+	pr_debug("Samples for '%s' event do not have %s attribute set. "
+		 "Skipping '%s' field.\n",
+		 evname, sample_msg, output_field2str(field));
+
+	return 0;
+}
+
+static int perf_evsel__check_attr(struct perf_evsel *evsel,
+				  struct perf_session *session)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM)) {
-		if (!(session->sample_type & PERF_SAMPLE_IP)) {
-			pr_err("Samples do not contain IP data.\n");
+		if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
+					   PERF_OUTPUT_SYM))
 			return -EINVAL;
-		}
+
 		if (!no_callchain &&
-		    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
 			symbol_conf.use_callchain = false;
 	}
 
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
-		!(session->sample_type & PERF_SAMPLE_TID)) {
-		pr_err("Samples do not contain TID/PID data.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
+				       PERF_OUTPUT_TID|PERF_OUTPUT_PID))
 		return -EINVAL;
-	}
 
 	if (PRINT_FIELD(TIME) &&
-		!(session->sample_type & PERF_SAMPLE_TIME)) {
-		pr_err("Samples do not contain timestamps.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME",
+				       PERF_OUTPUT_TIME))
 		return -EINVAL;
-	}
 
 	if (PRINT_FIELD(CPU) &&
-		!(session->sample_type & PERF_SAMPLE_CPU)) {
-		pr_err("Samples do not contain cpu.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU",
+				       PERF_OUTPUT_CPU))
 		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * verify all user requested events exist and the samples
+ * have the expected data
+ */
+static int perf_session__check_output_opt(struct perf_session *session)
+{
+	int j;
+	struct perf_evsel *evsel;
+
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		evsel = perf_session__find_first_evtype(session, j);
+
+		/*
+		 * even if fields is set to 0 (ie., show nothing) event must
+		 * exist if user explicitly includes it on the command line
+		 */
+		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+			pr_err("%s events do not exist. "
+			       "Remove corresponding -f option to proceed.\n",
+			       event_type(j));
+			return -1;
+		}
+
+		if (evsel && output[j].fields &&
+			perf_evsel__check_attr(evsel, session))
+			return -1;
 	}
 
 	return 0;
@@ -168,10 +280,7 @@ static void process_event(union perf_event *event __unused,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
-	if (output_fields[attr->type] == 0)
-		return;
-
-	if (perf_session__check_attr(session, attr) < 0)
+	if (output[attr->type].fields == 0)
 		return;
 
 	print_sample_start(sample, thread, attr);
@@ -451,6 +560,7 @@ static int parse_output_fields(const struct option *opt __used,
 {
 	char *tok;
 	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
+	int j;
 	int rc = 0;
 	char *str = strdup(arg);
 	int type = -1;
@@ -458,52 +568,99 @@ static int parse_output_fields(const struct option *opt __used,
 	if (!str)
 		return -ENOMEM;
 
-	tok = strtok(str, ":");
-	if (!tok) {
-		fprintf(stderr,
-			"Invalid field string - not prepended with type.");
-		return -EINVAL;
-	}
-
-	/* first word should state which event type user
-	 * is specifying the fields
+	/* first word can state for which event type the user is specifying
+	 * the fields. If no type exists, the specified fields apply to all
+	 * event types found in the file minus the invalid fields for a type.
 	 */
-	if (!strcmp(tok, "hw"))
-		type = PERF_TYPE_HARDWARE;
-	else if (!strcmp(tok, "sw"))
-		type = PERF_TYPE_SOFTWARE;
-	else if (!strcmp(tok, "trace"))
-		type = PERF_TYPE_TRACEPOINT;
-	else {
-		fprintf(stderr, "Invalid event type in field string.");
-		return -EINVAL;
+	tok = strchr(str, ':');
+	if (tok) {
+		*tok = '\0';
+		tok++;
+		if (!strcmp(str, "hw"))
+			type = PERF_TYPE_HARDWARE;
+		else if (!strcmp(str, "sw"))
+			type = PERF_TYPE_SOFTWARE;
+		else if (!strcmp(str, "trace"))
+			type = PERF_TYPE_TRACEPOINT;
+		else if (!strcmp(str, "raw"))
+			type = PERF_TYPE_RAW;
+		else {
+			fprintf(stderr, "Invalid event type in field string.\n");
+			return -EINVAL;
+		}
+
+		if (output[type].user_set)
+			pr_warning("Overriding previous field request for %s events.\n",
+				   event_type(type));
+
+		output[type].fields = 0;
+		output[type].user_set = true;
+		output[type].wildcard_set = false;
+
+	} else {
+		tok = str;
+		if (strlen(str) == 0) {
+			fprintf(stderr,
+				"Cannot set fields to 'none' for all event types.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (output_set_by_user())
+			pr_warning("Overriding previous field request for all events.\n");
+
+		for (j = 0; j < PERF_TYPE_MAX; ++j) {
+			output[j].fields = 0;
+			output[j].user_set = true;
+			output[j].wildcard_set = true;
+		}
 	}
 
-	output_fields[type] = 0;
-	while (1) {
-		tok = strtok(NULL, ",");
-		if (!tok)
-			break;
+	tok = strtok(tok, ",");
+	while (tok) {
 		for (i = 0; i < imax; ++i) {
-			if (strcmp(tok, all_output_options[i].str) == 0) {
-				output_fields[type] |= all_output_options[i].field;
+			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
-			}
 		}
 		if (i == imax) {
-			fprintf(stderr, "Invalid field requested.");
+			fprintf(stderr, "Invalid field requested.\n");
 			rc = -EINVAL;
-			break;
+			goto out;
 		}
-	}
 
-	if (output_fields[type] == 0) {
-		pr_debug("No fields requested for %s type. "
-			 "Events will not be displayed\n", event_type(type));
+		if (type == -1) {
+			/* add user option to all events types for
+			 * which it is valid
+			 */
+			for (j = 0; j < PERF_TYPE_MAX; ++j) {
+				if (output[j].invalid_fields & all_output_options[i].field) {
+					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
+						   all_output_options[i].str, event_type(j));
+				} else
+					output[j].fields |= all_output_options[i].field;
+			}
+		} else {
+			if (output[type].invalid_fields & all_output_options[i].field) {
+				fprintf(stderr, "\'%s\' not valid for %s events.\n",
+					 all_output_options[i].str, event_type(type));
+
+				rc = -EINVAL;
+				goto out;
+			}
+			output[type].fields |= all_output_options[i].field;
+		}
+
+		tok = strtok(NULL, ",");
 	}
 
-	output_set_by_user = true;
+	if (type >= 0) {
+		if (output[type].fields == 0) {
+			pr_debug("No fields requested for %s type. "
+				 "Events will not be displayed.\n", event_type(type));
+		}
+	}
 
+out:
 	free(str);
 	return rc;
 }
@@ -829,7 +986,7 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK('f', "fields", NULL, "str",
-		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace. Fields: comm,tid,pid,time,cpu,event,trace,sym",
+		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,sym",
 		     parse_output_fields),
 
 	OPT_END()
@@ -1020,7 +1177,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 		struct stat perf_stat;
 		int input;
 
-		if (output_set_by_user) {
+		if (output_set_by_user()) {
 			fprintf(stderr,
 				"custom fields not supported for generated scripts");
 			return -1;
@@ -1060,6 +1217,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 		pr_debug("perf script started with script %s\n\n", script_name);
 	}
 
+
+	err = perf_session__check_output_opt(session);
+	if (err < 0)
+		goto out;
+
 	err = __cmd_script(session);
 
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 03f0e45f147..a9f06715e44 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -6,24 +6,28 @@
  *
  * Sample output:
 
-   $ perf stat ~/hackbench 10
-   Time: 0.104
+   $ perf stat ./hackbench 10
 
-    Performance counter stats for '/home/mingo/hackbench':
+  Time: 0.118
 
-       1255.538611  task clock ticks     #      10.143 CPU utilization factor
-             54011  context switches     #       0.043 M/sec
-               385  CPU migrations       #       0.000 M/sec
-             17755  pagefaults           #       0.014 M/sec
-        3808323185  CPU cycles           #    3033.219 M/sec
-        1575111190  instructions         #    1254.530 M/sec
-          17367895  cache references     #      13.833 M/sec
-           7674421  cache misses         #       6.112 M/sec
+  Performance counter stats for './hackbench 10':
 
-    Wall-clock time elapsed:   123.786620 msecs
+       1708.761321 task-clock                #   11.037 CPUs utilized
+            41,190 context-switches          #    0.024 M/sec
+             6,735 CPU-migrations            #    0.004 M/sec
+            17,318 page-faults               #    0.010 M/sec
+     5,205,202,243 cycles                    #    3.046 GHz
+     3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
+     1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
+     2,603,501,247 instructions              #    0.50  insns per cycle
+                                             #    1.48  stalled cycles per insn
+       484,357,498 branches                  #  283.455 M/sec
+         6,388,934 branch-misses             #    1.32% of all branches
+
+        0.154822978  seconds time elapsed
 
  *
- * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -46,6 +50,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/color.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
@@ -65,14 +70,107 @@ static struct perf_event_attr default_attrs[] = {
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES		},
 
 };
 
+/*
+ * Detailed stats (-d), covering the L1 and last level data caches:
+ */
+static struct perf_event_attr detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+/*
+ * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
+ */
+static struct perf_event_attr very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+};
+
+/*
+ * Very, very detailed stats (-d -d -d), adding prefetch events:
+ */
+static struct perf_event_attr very_very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+
+
 struct perf_evlist		*evsel_list;
 
 static bool			system_wide			=  false;
@@ -86,6 +184,8 @@ static pid_t			target_pid			= -1;
 static pid_t			target_tid			= -1;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
+static int			detailed_run			=  0;
+static bool			sync_run			=  false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*cpu_list;
@@ -156,7 +256,15 @@ static double stddev_stats(struct stats *stats)
 
 struct stats			runtime_nsecs_stats[MAX_NR_CPUS];
 struct stats			runtime_cycles_stats[MAX_NR_CPUS];
+struct stats			runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
+struct stats			runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
 struct stats			runtime_branches_stats[MAX_NR_CPUS];
+struct stats			runtime_cacherefs_stats[MAX_NR_CPUS];
+struct stats			runtime_l1_dcache_stats[MAX_NR_CPUS];
+struct stats			runtime_l1_icache_stats[MAX_NR_CPUS];
+struct stats			runtime_ll_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_itlb_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats			walltime_nsecs_stats;
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -193,6 +301,37 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 }
 
 /*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+{
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_l1_icache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[0], count[0]);
+}
+
+/*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode
  */
@@ -217,12 +356,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-		update_stats(&runtime_nsecs_stats[0], count[0]);
-	if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[0], count[0]);
-	if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[0], count[0]);
+	update_shadow_stats(counter, count);
 
 	return 0;
 }
@@ -242,12 +376,7 @@ static int read_counter(struct perf_evsel *counter)
 
 		count = counter->counts->cpu[cpu].values;
 
-		if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-			update_stats(&runtime_nsecs_stats[cpu], count[0]);
-		if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-			update_stats(&runtime_cycles_stats[cpu], count[0]);
-		if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-			update_stats(&runtime_branches_stats[cpu], count[0]);
+		update_shadow_stats(counter, count);
 	}
 
 	return 0;
@@ -315,13 +444,18 @@ static int run_perf_stat(int argc __used, const char **argv)
 
 	list_for_each_entry(counter, &evsel_list->entries, node) {
 		if (create_perf_stat_counter(counter) < 0) {
-			if (errno == -EPERM || errno == -EACCES) {
+			if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
+				if (verbose)
+					ui__warning("%s event is not supported by the kernel.\n",
+						    event_name(counter));
+				continue;
+			}
+
+			if (errno == EPERM || errno == EACCES) {
 				error("You may not have permission to collect %sstats.\n"
 				      "\t Consider tweaking"
 				      " /proc/sys/kernel/perf_event_paranoid or running as root.",
 				      system_wide ? "system-wide " : "");
-			} else if (errno == ENOENT) {
-				error("%s event is not supported. ", event_name(counter));
 			} else {
 				error("open_counter returned with %d (%s). "
 				      "/bin/dmesg may provide additional information.\n",
@@ -372,6 +506,16 @@ static int run_perf_stat(int argc __used, const char **argv)
 	return WEXITSTATUS(status);
 }
 
+static void print_noise_pct(double total, double avg)
+{
+	double pct = 0.0;
+
+	if (avg)
+		pct = 100.0*total/avg;
+
+	fprintf(stderr, "  ( +-%6.2f%% )", pct);
+}
+
 static void print_noise(struct perf_evsel *evsel, double avg)
 {
 	struct perf_stat *ps;
@@ -380,15 +524,14 @@ static void print_noise(struct perf_evsel *evsel, double avg)
 		return;
 
 	ps = evsel->priv;
-	fprintf(stderr, "   ( +- %7.3f%% )",
-			100 * stddev_stats(&ps->res_stats[0]) / avg);
+	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
 static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	char cpustr[16] = { '\0', };
-	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-24s";
+	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -404,8 +547,191 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(stderr, " # %10.3f CPUs ",
-				avg / avg_stats(&walltime_nsecs_stats));
+		fprintf(stderr, " # %8.3f CPUs utilized          ", avg / avg_stats(&walltime_nsecs_stats));
+}
+
+static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_cycles_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 50.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 30.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_cycles_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 75.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 50.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 20.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_branches_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_icache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_ll_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all LL-cache hits   ");
 }
 
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
@@ -417,9 +743,9 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (csv_output)
 		fmt = "%s%.0f%s%s";
 	else if (big_num)
-		fmt = "%s%'18.0f%s%-24s";
+		fmt = "%s%'18.0f%s%-25s";
 	else
-		fmt = "%s%18.0f%s%-24s";
+		fmt = "%s%18.0f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -442,23 +768,83 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 		if (total)
 			ratio = avg / total;
 
-		fprintf(stderr, " # %10.3f IPC  ", ratio);
+		fprintf(stderr, " #   %5.2f  insns per cycle        ", ratio);
+
+		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(stderr, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+		}
+
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
 			runtime_branches_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_branches_stats[cpu]);
+		print_branch_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[cpu].n != 0) {
+		print_l1_dcache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[cpu].n != 0) {
+		print_l1_icache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[cpu].n != 0) {
+		print_dtlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[cpu].n != 0) {
+		print_itlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[cpu].n != 0) {
+		print_ll_cache_misses(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(stderr, " # %10.3f %%    ", ratio);
+		fprintf(stderr, " # %8.3f %% of all cache refs    ", ratio);
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
+		if (total)
+			ratio = 1.0 * avg / total;
+
+		fprintf(stderr, " # %8.3f GHz                    ", ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
 
-		fprintf(stderr, " # %10.3f M/sec", ratio);
+		fprintf(stderr, " # %8.3f M/sec                  ", ratio);
+	} else {
+		fprintf(stderr, "                                   ");
 	}
 }
 
@@ -505,8 +891,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 		avg_enabled = avg_stats(&ps->res_stats[1]);
 		avg_running = avg_stats(&ps->res_stats[2]);
 
-		fprintf(stderr, "  (scaled from %.2f%%)",
-				100 * avg_running / avg_enabled);
+		fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
 	}
 	fprintf(stderr, "\n");
 }
@@ -548,10 +933,8 @@ static void print_counter(struct perf_evsel *counter)
 		if (!csv_output) {
 			print_noise(counter, 1.0);
 
-			if (run != ena) {
-				fprintf(stderr, "  (scaled from %.2f%%)",
-					100.0 * run / ena);
-			}
+			if (run != ena)
+				fprintf(stderr, "  (%.2f%%)", 100.0 * run / ena);
 		}
 		fputc('\n', stderr);
 	}
@@ -591,13 +974,14 @@ static void print_stat(int argc, const char **argv)
 	}
 
 	if (!csv_output) {
-		fprintf(stderr, "\n");
-		fprintf(stderr, " %18.9f  seconds time elapsed",
+		if (!null_run)
+			fprintf(stderr, "\n");
+		fprintf(stderr, " %17.9f seconds time elapsed",
 				avg_stats(&walltime_nsecs_stats)/1e9);
 		if (run_count > 1) {
-			fprintf(stderr, "   ( +- %7.3f%% )",
-				100*stddev_stats(&walltime_nsecs_stats) /
-				avg_stats(&walltime_nsecs_stats));
+			fprintf(stderr, "                                        ");
+			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+					avg_stats(&walltime_nsecs_stats));
 		}
 		fprintf(stderr, "\n\n");
 	}
@@ -659,6 +1043,10 @@ static const struct option options[] = {
 		    "repeat command and print average + stddev (max: 100)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
 	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
 			   "print large numbers with thousands\' separators",
 			   stat__set_big_num),
@@ -674,6 +1062,70 @@ static const struct option options[] = {
 	OPT_END()
 };
 
+/*
+ * Add default attributes, if there were no attributes specified or
+ * if -d/--detailed, -d -d or -d -d -d is used:
+ */
+static int add_default_attributes(void)
+{
+	struct perf_evsel *pos;
+	size_t attr_nr = 0;
+	size_t c;
+
+	/* Set attrs if no event is selected and !null_run: */
+	if (null_run)
+		return 0;
+
+	if (!evsel_list->nr_entries) {
+		for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
+			pos = perf_evsel__new(default_attrs + c, c + attr_nr);
+			if (pos == NULL)
+				return -1;
+			perf_evlist__add(evsel_list, pos);
+		}
+		attr_nr += c;
+	}
+
+	/* Detailed events get appended to the event list: */
+
+	if (detailed_run <  1)
+		return 0;
+
+	/* Append detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
+		pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+	attr_nr += c;
+
+	if (detailed_run < 2)
+		return 0;
+
+	/* Append very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+	if (detailed_run < 3)
+		return 0;
+
+	/* Append very, very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+
+	return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	struct perf_evsel *pos;
@@ -719,17 +1171,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(stat_usage, options);
 	}
 
-	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (!null_run && !evsel_list->nr_entries) {
-		size_t c;
-
-		for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
-			pos = perf_evsel__new(&default_attrs[c], c);
-			if (pos == NULL)
-				goto out;
-			perf_evlist__add(evsel_list, pos);
-		}
-	}
+	if (add_default_attributes())
+		goto out;
 
 	if (target_pid != -1)
 		target_tid = target_pid;
@@ -773,6 +1216,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	for (run_idx = 0; run_idx < run_count; run_idx++) {
 		if (run_count != 1 && verbose)
 			fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+
+		if (sync_run)
+			sync();
+
 		status = run_perf_stat(argc, argv);
 	}
 
diff --git a/tools/perf/feature-tests.mak b/tools/perf/config/feature-tests.mak
index b041ca67a2c..6170fd2531b 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -79,9 +79,15 @@ endef
 endif
 
 ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_VERSION
+#include <Python.h>
+#if PY_VERSION_HEX >= 0x03000000
+	#error
+#endif
+int main(void){}
+endef
 define SOURCE_PYTHON_EMBED
 #include <Python.h>
-
 int main(void)
 {
 	Py_Initialize();
@@ -120,11 +126,3 @@ int main(void)
 	return 0;
 }
 endef
-
-# try-cc
-# Usage: option = $(call try-cc, source-to-build, cc-options)
-try-cc = $(shell sh -c						  \
-	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
-	 echo "$(1)" |						  \
-	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
-	 rm -f "$$TMP"')
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
new file mode 100644
index 00000000000..8046182a19e
--- /dev/null
+++ b/tools/perf/config/utilities.mak
@@ -0,0 +1,188 @@
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+#       in an `awk' program that is delimited by shell
+#       single-quotes, so be wary of the characters
+#       that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+#       expression constant in an `awk' program that is
+#       delimited by shell single-quotes, so be wary
+#       of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+#  misinterpreted as a brace expansion; this can be
+#  overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq =  $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+#  |define text
+#  |hello
+#  |world
+#  |endef
+#  |
+#  |target:
+#  |	echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c						  \
+	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
+	 echo "$(1)" |						  \
+	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+	 rm -f "$$TMP"')
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 00000000000..6789d788d49
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 952b4ae3d95..41982c373fa 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -31,34 +31,36 @@ char debugfs_path[MAXPATHLEN];
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
 
 static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),		"cpu-cycles",		"cycles"	},
-  { CHW(INSTRUCTIONS),		"instructions",		""		},
-  { CHW(CACHE_REFERENCES),	"cache-references",	""		},
-  { CHW(CACHE_MISSES),		"cache-misses",		""		},
-  { CHW(BRANCH_INSTRUCTIONS),	"branch-instructions",	"branches"	},
-  { CHW(BRANCH_MISSES),		"branch-misses",	""		},
-  { CHW(BUS_CYCLES),		"bus-cycles",		""		},
-
-  { CSW(CPU_CLOCK),		"cpu-clock",		""		},
-  { CSW(TASK_CLOCK),		"task-clock",		""		},
-  { CSW(PAGE_FAULTS),		"page-faults",		"faults"	},
-  { CSW(PAGE_FAULTS_MIN),	"minor-faults",		""		},
-  { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
-  { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
-  { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
-  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
-  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
+  { CHW(CPU_CYCLES),			"cpu-cycles",			"cycles"		},
+  { CHW(STALLED_CYCLES_FRONTEND),	"stalled-cycles-frontend",	"idle-cycles-frontend"	},
+  { CHW(STALLED_CYCLES_BACKEND),	"stalled-cycles-backend",	"idle-cycles-backend"	},
+  { CHW(INSTRUCTIONS),			"instructions",			""			},
+  { CHW(CACHE_REFERENCES),		"cache-references",		""			},
+  { CHW(CACHE_MISSES),			"cache-misses",			""			},
+  { CHW(BRANCH_INSTRUCTIONS),		"branch-instructions",		"branches"		},
+  { CHW(BRANCH_MISSES),			"branch-misses",		""			},
+  { CHW(BUS_CYCLES),			"bus-cycles",			""			},
+
+  { CSW(CPU_CLOCK),			"cpu-clock",			""			},
+  { CSW(TASK_CLOCK),			"task-clock",			""			},
+  { CSW(PAGE_FAULTS),			"page-faults",			"faults"		},
+  { CSW(PAGE_FAULTS_MIN),		"minor-faults",			""			},
+  { CSW(PAGE_FAULTS_MAJ),		"major-faults",			""			},
+  { CSW(CONTEXT_SWITCHES),		"context-switches",		"cs"			},
+  { CSW(CPU_MIGRATIONS),		"cpu-migrations",		"migrations"		},
+  { CSW(ALIGNMENT_FAULTS),		"alignment-faults",		""			},
+  { CSW(EMULATION_FAULTS),		"emulation-faults",		""			},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
 	((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
-#define PERF_EVENT_RAW(config)	__PERF_EVENT_FIELD(config, RAW)
+#define PERF_EVENT_RAW(config)		__PERF_EVENT_FIELD(config, RAW)
 #define PERF_EVENT_CONFIG(config)	__PERF_EVENT_FIELD(config, CONFIG)
-#define PERF_EVENT_TYPE(config)	__PERF_EVENT_FIELD(config, TYPE)
+#define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[] = {
+static const char *hw_event_names[PERF_COUNT_HW_MAX] = {
 	"cycles",
 	"instructions",
 	"cache-references",
@@ -66,11 +68,13 @@ static const char *hw_event_names[] = {
 	"branches",
 	"branch-misses",
 	"bus-cycles",
+	"stalled-cycles-frontend",
+	"stalled-cycles-backend",
 };
 
-static const char *sw_event_names[] = {
-	"cpu-clock-msecs",
-	"task-clock-msecs",
+static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
+	"cpu-clock",
+	"task-clock",
 	"page-faults",
 	"context-switches",
 	"CPU-migrations",
@@ -307,7 +311,7 @@ const char *__event_name(int type, u64 config)
 
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
-		if (config < PERF_COUNT_HW_MAX)
+		if (config < PERF_COUNT_HW_MAX && hw_event_names[config])
 			return hw_event_names[config];
 		return "unknown-hardware";
 
@@ -333,7 +337,7 @@ const char *__event_name(int type, u64 config)
 	}
 
 	case PERF_TYPE_SOFTWARE:
-		if (config < PERF_COUNT_SW_MAX)
+		if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
 			return sw_event_names[config];
 		return "unknown-software";
 
@@ -648,13 +652,15 @@ static int check_events(const char *str, unsigned int i)
 	int n;
 
 	n = strlen(event_symbols[i].symbol);
-	if (!strncmp(str, event_symbols[i].symbol, n))
+	if (!strncasecmp(str, event_symbols[i].symbol, n))
 		return n;
 
 	n = strlen(event_symbols[i].alias);
-	if (n)
-		if (!strncmp(str, event_symbols[i].alias, n))
+	if (n) {
+		if (!strncasecmp(str, event_symbols[i].alias, n))
 			return n;
+	}
+
 	return 0;
 }
 
@@ -718,15 +724,22 @@ parse_numeric_event(const char **strp, struct perf_event_attr *attr)
 	return EVT_FAILED;
 }
 
-static enum event_result
+static int
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
 	int exclude = 0;
 	int eu = 0, ek = 0, eh = 0, precise = 0;
 
-	if (*str++ != ':')
+	if (!*str)
+		return 0;
+
+	if (*str == ',')
 		return 0;
+
+	if (*str++ != ':')
+		return -1;
+
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -747,14 +760,16 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
 		++str;
 	}
-	if (str >= *strp + 2) {
-		*strp = str;
-		attr->exclude_user   = eu;
-		attr->exclude_kernel = ek;
-		attr->exclude_hv     = eh;
-		attr->precise_ip     = precise;
-		return 1;
-	}
+	if (str < *strp + 2)
+		return -1;
+
+	*strp = str;
+
+	attr->exclude_user   = eu;
+	attr->exclude_kernel = ek;
+	attr->exclude_hv     = eh;
+	attr->precise_ip     = precise;
+
 	return 0;
 }
 
@@ -797,7 +812,12 @@ parse_event_symbols(const struct option *opt, const char **str,
 	return EVT_FAILED;
 
 modifier:
-	parse_event_modifier(str, attr);
+	if (parse_event_modifier(str, attr) < 0) {
+		fprintf(stderr, "invalid event modifier: '%s'\n", *str);
+		fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
+
+		return EVT_FAILED;
+	}
 
 	return ret;
 }
@@ -912,7 +932,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
-			printf("  %-42s [%s]\n", evt_path,
+			printf("  %-50s [%s]\n", evt_path,
 				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
 		}
 		closedir(evt_dir);
@@ -977,7 +997,7 @@ void print_events_type(u8 type)
 		else
 			snprintf(name, sizeof(name), "%s", syms->symbol);
 
-		printf("  %-42s [%s]\n", name,
+		printf("  %-50s [%s]\n", name,
 			event_type_descriptors[type]);
 	}
 }
@@ -995,11 +1015,10 @@ int print_hwcache_events(const char *event_glob)
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
 				char *name = event_cache_name(type, op, i);
 
-				if (event_glob != NULL && 
-				    !strglobmatch(name, event_glob))
+				if (event_glob != NULL && !strglobmatch(name, event_glob))
 					continue;
 
-				printf("  %-42s [%s]\n", name,
+				printf("  %-50s [%s]\n", name,
 					event_type_descriptors[PERF_TYPE_HW_CACHE]);
 				++printed;
 			}
@@ -1009,14 +1028,16 @@ int print_hwcache_events(const char *event_glob)
 	return printed;
 }
 
+#define MAX_NAME_LEN 100
+
 /*
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob)
 {
-	struct event_symbol *syms = event_symbols;
 	unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
-	char name[40];
+	struct event_symbol *syms = event_symbols;
+	char name[MAX_NAME_LEN];
 
 	printf("\n");
 	printf("List of pre-defined events (to be used in -e):\n");
@@ -1036,10 +1057,10 @@ void print_events(const char *event_glob)
 			continue;
 
 		if (strlen(syms->alias))
-			sprintf(name, "%s OR %s", syms->symbol, syms->alias);
+			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
 		else
-			strcpy(name, syms->symbol);
-		printf("  %-42s [%s]\n", name,
+			strncpy(name, syms->symbol, MAX_NAME_LEN);
+		printf("  %-50s [%s]\n", name,
 			event_type_descriptors[type]);
 
 		prev_type = type;
@@ -1056,12 +1077,12 @@ void print_events(const char *event_glob)
 		return;
 
 	printf("\n");
-	printf("  %-42s [%s]\n",
+	printf("  %-50s [%s]\n",
 		"rNNN (see 'perf list --help' on how to encode it)",
 	       event_type_descriptors[PERF_TYPE_RAW]);
 	printf("\n");
 
-	printf("  %-42s [%s]\n",
+	printf("  %-50s [%s]\n",
 			"mem:<addr>[:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
 	printf("\n");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index b7c85ce466a..3b9d0b800d5 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1471,6 +1471,38 @@ static int find_probe_point_by_func(struct probe_finder *pf)
 	return _param.retval;
 }
 
+struct pubname_callback_param {
+	char *function;
+	char *file;
+	Dwarf_Die *cu_die;
+	Dwarf_Die *sp_die;
+	int found;
+};
+
+static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
+{
+	struct pubname_callback_param *param = data;
+
+	if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) {
+		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
+			return DWARF_CB_OK;
+
+		if (die_compare_name(param->sp_die, param->function)) {
+			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
+				return DWARF_CB_OK;
+
+			if (param->file &&
+			    strtailcmp(param->file, dwarf_decl_file(param->sp_die)))
+				return DWARF_CB_OK;
+
+			param->found = 1;
+			return DWARF_CB_ABORT;
+		}
+	}
+
+	return DWARF_CB_OK;
+}
+
 /* Find probe points from debuginfo */
 static int find_probes(int fd, struct probe_finder *pf)
 {
@@ -1498,6 +1530,28 @@ static int find_probes(int fd, struct probe_finder *pf)
 
 	off = 0;
 	line_list__init(&pf->lcache);
+
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (pp->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = pp->function,
+			.file	  = pp->file,
+			.cu_die	  = &pf->cu_die,
+			.sp_die	  = &pf->sp_die,
+			.found	  = 0,
+		};
+		struct dwarf_callback_param probe_param = {
+			.data = pf,
+		};
+
+		dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+		if (pubname_param.found) {
+			ret = probe_point_search_cb(&pf->sp_die, &probe_param);
+			if (ret)
+				goto found;
+		}
+	}
+
 	/* Loop on CUs (Compilation Unit) */
 	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
@@ -1525,6 +1579,8 @@ static int find_probes(int fd, struct probe_finder *pf)
 		}
 		off = noff;
 	}
+
+found:
 	line_list__free(&pf->lcache);
 	if (dwfl)
 		dwfl_end(dwfl);
@@ -1946,6 +2002,22 @@ int find_line_range(int fd, struct line_range *lr)
 		return -EBADF;
 	}
 
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (lr->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = lr->function, .file = lr->file,
+			.cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0};
+		struct dwarf_callback_param line_range_param = {
+			.data = (void *)&lf, .retval = 0};
+
+		dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+		if (pubname_param.found) {
+			line_range_search_cb(&lf.sp_die, &line_range_param);
+			if (lf.found)
+				goto found;
+		}
+	}
+
 	/* Loop on CUs (Compilation Unit) */
 	while (!lf.found && ret >= 0) {
 		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
@@ -1974,6 +2046,7 @@ int find_line_range(int fd, struct line_range *lr)
 		off = noff;
 	}
 
+found:
 	/* Store comp_dir */
 	if (lf.found) {
 		comp_dir = cu_get_comp_dir(&lf.cu_die);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index beaefc3c122..605730a366d 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -49,6 +49,7 @@ struct probe_finder {
 	Dwarf_Addr		addr;		/* Address */
 	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
+	Dwarf_Die		sp_die;
 	struct list_head	lcache;		/* Line cache for lazy match */
 
 	/* For variable searching */
@@ -83,6 +84,7 @@ struct line_finder {
 	int			lno_s;		/* Start line number */
 	int			lno_e;		/* End line number */
 	Dwarf_Die		cu_die;		/* Current CU */
+	Dwarf_Die		sp_die;
 	int			found;
 };
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 99c722672f8..b5c7d818001 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -810,6 +810,9 @@ static struct {
 	{ "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
 	{ "COUNT_HW_CACHE_RESULT_MISS",   PERF_COUNT_HW_CACHE_RESULT_MISS },
 
+	{ "COUNT_HW_STALLED_CYCLES_FRONTEND",	  PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+	{ "COUNT_HW_STALLED_CYCLES_BACKEND",	  PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+
 	{ "COUNT_SW_CPU_CLOCK",	       PERF_COUNT_SW_CPU_CLOCK },
 	{ "COUNT_SW_TASK_CLOCK",       PERF_COUNT_SW_TASK_CLOCK },
 	{ "COUNT_SW_PAGE_FAULTS",      PERF_COUNT_SW_PAGE_FAULTS },
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index caa224522fe..fff66741f18 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1156,6 +1156,18 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	return ret;
 }
 
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					      unsigned int type)
+{
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &session->evlist->entries, node) {
+		if (pos->attr.type == type)
+			return pos;
+	}
+	return NULL;
+}
+
 void perf_session__print_symbols(union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_session *session)
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 1ac481fc110..8daaa2d1539 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -162,6 +162,9 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 					session->sample_id_all, sample);
 }
 
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					    unsigned int type);
+
 void perf_session__print_symbols(union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_session *session);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f06c10f092b..516876dfbe5 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -31,13 +31,13 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id);
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 			symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
@@ -49,27 +49,27 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
-int dso__name_len(const struct dso *self)
+int dso__name_len(const struct dso *dso)
 {
 	if (verbose)
-		return self->long_name_len;
+		return dso->long_name_len;
 
-	return self->short_name_len;
+	return dso->short_name_len;
 }
 
-bool dso__loaded(const struct dso *self, enum map_type type)
+bool dso__loaded(const struct dso *dso, enum map_type type)
 {
-	return self->loaded & (1 << type);
+	return dso->loaded & (1 << type);
 }
 
-bool dso__sorted_by_name(const struct dso *self, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
 {
-	return self->sorted_by_name & (1 << type);
+	return dso->sorted_by_name & (1 << type);
 }
 
-static void dso__set_sorted_by_name(struct dso *self, enum map_type type)
+static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 {
-	self->sorted_by_name |= (1 << type);
+	dso->sorted_by_name |= (1 << type);
 }
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
@@ -84,9 +84,9 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 	}
 }
 
-static void symbols__fixup_end(struct rb_root *self)
+static void symbols__fixup_end(struct rb_root *symbols)
 {
-	struct rb_node *nd, *prevnd = rb_first(self);
+	struct rb_node *nd, *prevnd = rb_first(symbols);
 	struct symbol *curr, *prev;
 
 	if (prevnd == NULL)
@@ -107,10 +107,10 @@ static void symbols__fixup_end(struct rb_root *self)
 		curr->end = roundup(curr->start, 4096);
 }
 
-static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
+static void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
 	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&self->maps[type]);
+	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
 
 	if (prevnd == NULL)
 		return;
@@ -130,128 +130,128 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
 	curr->end = ~0ULL;
 }
 
-static void map_groups__fixup_end(struct map_groups *self)
+static void map_groups__fixup_end(struct map_groups *mg)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(self, i);
+		__map_groups__fixup_end(mg, i);
 }
 
 static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
 				  const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = calloc(1, (symbol_conf.priv_size +
-					 sizeof(*self) + namelen));
-	if (self == NULL)
+	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
+					sizeof(*sym) + namelen));
+	if (sym == NULL)
 		return NULL;
 
 	if (symbol_conf.priv_size)
-		self = ((void *)self) + symbol_conf.priv_size;
-
-	self->start   = start;
-	self->end     = len ? start + len - 1 : start;
-	self->binding = binding;
-	self->namelen = namelen - 1;
+		sym = ((void *)sym) + symbol_conf.priv_size;
 
-	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n", __func__, name, start, self->end);
+	sym->start   = start;
+	sym->end     = len ? start + len - 1 : start;
+	sym->binding = binding;
+	sym->namelen = namelen - 1;
 
-	memcpy(self->name, name, namelen);
+	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
+		  __func__, name, start, sym->end);
+	memcpy(sym->name, name, namelen);
 
-	return self;
+	return sym;
 }
 
-void symbol__delete(struct symbol *self)
+void symbol__delete(struct symbol *sym)
 {
-	free(((void *)self) - symbol_conf.priv_size);
+	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-static size_t symbol__fprintf(struct symbol *self, FILE *fp)
+static size_t symbol__fprintf(struct symbol *sym, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
-		       self->start, self->end,
-		       self->binding == STB_GLOBAL ? 'g' :
-		       self->binding == STB_LOCAL  ? 'l' : 'w',
-		       self->name);
+		       sym->start, sym->end,
+		       sym->binding == STB_GLOBAL ? 'g' :
+		       sym->binding == STB_LOCAL  ? 'l' : 'w',
+		       sym->name);
 }
 
-void dso__set_long_name(struct dso *self, char *name)
+void dso__set_long_name(struct dso *dso, char *name)
 {
 	if (name == NULL)
 		return;
-	self->long_name = name;
-	self->long_name_len = strlen(name);
+	dso->long_name = name;
+	dso->long_name_len = strlen(name);
 }
 
-static void dso__set_short_name(struct dso *self, const char *name)
+static void dso__set_short_name(struct dso *dso, const char *name)
 {
 	if (name == NULL)
 		return;
-	self->short_name = name;
-	self->short_name_len = strlen(name);
+	dso->short_name = name;
+	dso->short_name_len = strlen(name);
 }
 
-static void dso__set_basename(struct dso *self)
+static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(self, basename(self->long_name));
+	dso__set_short_name(dso, basename(dso->long_name));
 }
 
 struct dso *dso__new(const char *name)
 {
-	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
+	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
 
-	if (self != NULL) {
+	if (dso != NULL) {
 		int i;
-		strcpy(self->name, name);
-		dso__set_long_name(self, self->name);
-		dso__set_short_name(self, self->name);
+		strcpy(dso->name, name);
+		dso__set_long_name(dso, dso->name);
+		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
-			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-		self->symtab_type = SYMTAB__NOT_FOUND;
-		self->loaded = 0;
-		self->sorted_by_name = 0;
-		self->has_build_id = 0;
-		self->kernel = DSO_TYPE_USER;
-		INIT_LIST_HEAD(&self->node);
+			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->loaded = 0;
+		dso->sorted_by_name = 0;
+		dso->has_build_id = 0;
+		dso->kernel = DSO_TYPE_USER;
+		INIT_LIST_HEAD(&dso->node);
 	}
 
-	return self;
+	return dso;
 }
 
-static void symbols__delete(struct rb_root *self)
+static void symbols__delete(struct rb_root *symbols)
 {
 	struct symbol *pos;
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(symbols);
 
 	while (next) {
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, symbols);
 		symbol__delete(pos);
 	}
 }
 
-void dso__delete(struct dso *self)
+void dso__delete(struct dso *dso)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		symbols__delete(&self->symbols[i]);
-	if (self->sname_alloc)
-		free((char *)self->short_name);
-	if (self->lname_alloc)
-		free(self->long_name);
-	free(self);
+		symbols__delete(&dso->symbols[i]);
+	if (dso->sname_alloc)
+		free((char *)dso->short_name);
+	if (dso->lname_alloc)
+		free(dso->long_name);
+	free(dso);
 }
 
-void dso__set_build_id(struct dso *self, void *build_id)
+void dso__set_build_id(struct dso *dso, void *build_id)
 {
-	memcpy(self->build_id, build_id, sizeof(self->build_id));
-	self->has_build_id = 1;
+	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
+	dso->has_build_id = 1;
 }
 
-static void symbols__insert(struct rb_root *self, struct symbol *sym)
+static void symbols__insert(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
@@ -265,17 +265,17 @@ static void symbols__insert(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&sym->rb_node, parent, p);
-	rb_insert_color(&sym->rb_node, self);
+	rb_insert_color(&sym->rb_node, symbols);
 }
 
-static struct symbol *symbols__find(struct rb_root *self, u64 ip)
+static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol *s = rb_entry(n, struct symbol, rb_node);
@@ -296,9 +296,9 @@ struct symbol_name_rb_node {
 	struct symbol	sym;
 };
 
-static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	struct symbol_name_rb_node *symn, *s;
 
@@ -313,27 +313,29 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color(&symn->rb_node, self);
+	rb_insert_color(&symn->rb_node, symbols);
 }
 
-static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root *symbols,
+				  struct rb_root *source)
 {
 	struct rb_node *nd;
 
 	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-		symbols__insert_by_name(self, pos);
+		symbols__insert_by_name(symbols, pos);
 	}
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name)
+static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+					    const char *name)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol_name_rb_node *s;
@@ -353,29 +355,29 @@ static struct symbol *symbols__find_by_name(struct rb_root *self, const char *na
 	return NULL;
 }
 
-struct symbol *dso__find_symbol(struct dso *self,
+struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
-	return symbols__find(&self->symbols[type], addr);
+	return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
-	return symbols__find_by_name(&self->symbol_names[type], name);
+	return symbols__find_by_name(&dso->symbol_names[type], name);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type)
+void dso__sort_by_name(struct dso *dso, enum map_type type)
 {
-	dso__set_sorted_by_name(self, type);
-	return symbols__sort_by_name(&self->symbol_names[type],
-				     &self->symbols[type]);
+	dso__set_sorted_by_name(dso, type);
+	return symbols__sort_by_name(&dso->symbol_names[type],
+				     &dso->symbols[type]);
 }
 
-int build_id__sprintf(const u8 *self, int len, char *bf)
+int build_id__sprintf(const u8 *build_id, int len, char *bf)
 {
 	char *bid = bf;
-	const u8 *raw = self;
+	const u8 *raw = build_id;
 	int i;
 
 	for (i = 0; i < len; ++i) {
@@ -384,24 +386,25 @@ int build_id__sprintf(const u8 *self, int len, char *bf)
 		bid += 2;
 	}
 
-	return raw - self;
+	return raw - build_id;
 }
 
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp)
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-	build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id);
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 	return fprintf(fp, "%s", sbuild_id);
 }
 
-size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp)
 {
 	size_t ret = 0;
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&self->symbol_names[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}
@@ -409,18 +412,18 @@ size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *
 	return ret;
 }
 
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = fprintf(fp, "dso: %s (", self->short_name);
+	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
 
-	if (self->short_name != self->long_name)
-		ret += fprintf(fp, "%s, ", self->long_name);
+	if (dso->short_name != dso->long_name)
+		ret += fprintf(fp, "%s, ", dso->long_name);
 	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       self->loaded ? "" : "NOT ");
-	ret += dso__fprintf_buildid(self, fp);
+		       dso->loaded ? "" : "NOT ");
+	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
@@ -543,10 +546,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *self, const char *filename,
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
 				  struct map *map)
 {
-	struct process_kallsyms_args args = { .map = map, .dso = self, };
+	struct process_kallsyms_args args = { .map = map, .dso = dso, };
 	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
@@ -555,7 +558,7 @@ static int dso__load_all_kallsyms(struct dso *self, const char *filename,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *self, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
@@ -563,7 +566,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 	struct map *curr_map = map;
 	struct symbol *pos;
 	int count = 0, moved = 0;	
-	struct rb_root *root = &self->symbols[map->type];
+	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
 
@@ -582,7 +585,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 
 			if (strcmp(curr_map->dso->short_name, module)) {
 				if (curr_map != map &&
-				    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 				    machine__is_default_guest(machine)) {
 					/*
 					 * We assume all symbols of a module are
@@ -618,14 +621,14 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
 		} else if (curr_map != map) {
 			char dso_name[PATH_MAX];
-			struct dso *dso;
+			struct dso *ndso;
 
 			if (count == 0) {
 				curr_map = map;
 				goto filter_symbol;
 			}
 
-			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
 					kernel_range++);
@@ -634,15 +637,15 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 					"[kernel].%d",
 					kernel_range++);
 
-			dso = dso__new(dso_name);
-			if (dso == NULL)
+			ndso = dso__new(dso_name);
+			if (ndso == NULL)
 				return -1;
 
-			dso->kernel = self->kernel;
+			ndso->kernel = dso->kernel;
 
-			curr_map = map__new2(pos->start, dso, map->type);
+			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(dso);
+				dso__delete(ndso);
 				return -1;
 			}
 
@@ -665,7 +668,7 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	}
 
 	if (curr_map != map &&
-	    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 	    machine__is_default_guest(kmaps->machine)) {
 		dso__set_loaded(curr_map->dso, curr_map->type);
 	}
@@ -673,21 +676,21 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	return count + moved;
 }
 
-int dso__load_kallsyms(struct dso *self, const char *filename,
+int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
-	if (dso__load_all_kallsyms(self, filename, map) < 0)
+	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
-	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		self->symtab_type = SYMTAB__GUEST_KALLSYMS;
+	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
-		self->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = SYMTAB__KALLSYMS;
 
-	return dso__split_kallsyms(self, map, filter);
+	return dso__split_kallsyms(dso, map, filter);
 }
 
-static int dso__load_perf_map(struct dso *self, struct map *map,
+static int dso__load_perf_map(struct dso *dso, struct map *map,
 			      symbol_filter_t filter)
 {
 	char *line = NULL;
@@ -695,7 +698,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
 	FILE *file;
 	int nr_syms = 0;
 
-	file = fopen(self->long_name, "r");
+	file = fopen(dso->long_name, "r");
 	if (file == NULL)
 		goto out_failure;
 
@@ -733,7 +736,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
 		if (filter && filter(map, sym))
 			symbol__delete(sym);
 		else {
-			symbols__insert(&self->symbols[map->type], sym);
+			symbols__insert(&dso->symbols[map->type], sym);
 			nr_syms++;
 		}
 	}
@@ -752,7 +755,7 @@ out_failure:
 /**
  * elf_symtab__for_each_symbol - iterate thru all the symbols
  *
- * @self: struct elf_symtab instance to iterate
+ * @syms: struct elf_symtab instance to iterate
  * @idx: uint32_t idx
  * @sym: GElf_Sym iterator
  */
@@ -852,7 +855,7 @@ static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
+static int dso__synthesize_plt_symbols(struct  dso *dso, struct map *map,
 				       symbol_filter_t filter)
 {
 	uint32_t nr_rel_entries, idx;
@@ -871,7 +874,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 	char name[PATH_MAX];
 
 	snprintf(name, sizeof(name), "%s%s",
-		 symbol_conf.symfs, self->long_name);
+		 symbol_conf.symfs, dso->long_name);
 	fd = open(name, O_RDONLY);
 	if (fd < 0)
 		goto out;
@@ -947,7 +950,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 			if (filter && filter(map, f))
 				symbol__delete(f);
 			else {
-				symbols__insert(&self->symbols[map->type], f);
+				symbols__insert(&dso->symbols[map->type], f);
 				++nr;
 			}
 		}
@@ -969,7 +972,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 			if (filter && filter(map, f))
 				symbol__delete(f);
 			else {
-				symbols__insert(&self->symbols[map->type], f);
+				symbols__insert(&dso->symbols[map->type], f);
 				++nr;
 			}
 		}
@@ -985,29 +988,30 @@ out_close:
 		return nr;
 out:
 	pr_debug("%s: problems reading %s PLT info.\n",
-		 __func__, self->long_name);
+		 __func__, dso->long_name);
 	return 0;
 }
 
-static bool elf_sym__is_a(GElf_Sym *self, enum map_type type)
+static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
 {
 	switch (type) {
 	case MAP__FUNCTION:
-		return elf_sym__is_function(self);
+		return elf_sym__is_function(sym);
 	case MAP__VARIABLE:
-		return elf_sym__is_object(self);
+		return elf_sym__is_object(sym);
 	default:
 		return false;
 	}
 }
 
-static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type)
+static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
+			  enum map_type type)
 {
 	switch (type) {
 	case MAP__FUNCTION:
-		return elf_sec__is_text(self, secstrs);
+		return elf_sec__is_text(shdr, secstrs);
 	case MAP__VARIABLE:
-		return elf_sec__is_data(self, secstrs);
+		return elf_sec__is_data(shdr, secstrs);
 	default:
 		return false;
 	}
@@ -1032,13 +1036,13 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
-static int dso__load_sym(struct dso *self, struct map *map, const char *name,
+static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 			 int fd, symbol_filter_t filter, int kmodule,
 			 int want_symtab)
 {
-	struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
+	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
 	struct map *curr_map = map;
-	struct dso *curr_dso = self;
+	struct dso *curr_dso = dso;
 	Elf_Data *symstrs, *secstrs;
 	uint32_t nr_syms;
 	int err = -1;
@@ -1064,14 +1068,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	}
 
 	/* Always reject images with a mismatched build-id: */
-	if (self->has_build_id) {
+	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
 
 		if (elf_read_build_id(elf, build_id,
 				      BUILD_ID_SIZE) != BUILD_ID_SIZE)
 			goto out_elf_end;
 
-		if (!dso__build_id_equal(self, build_id))
+		if (!dso__build_id_equal(dso, build_id))
 			goto out_elf_end;
 	}
 
@@ -1112,13 +1116,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	nr_syms = shdr.sh_size / shdr.sh_entsize;
 
 	memset(&sym, 0, sizeof(sym));
-	if (self->kernel == DSO_TYPE_USER) {
-		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+	if (dso->kernel == DSO_TYPE_USER) {
+		dso->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
-	} else self->adjust_symbols = 0;
-
+	} else {
+		dso->adjust_symbols = 0;
+	}
 	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
 		struct symbol *f;
 		const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1168,22 +1173,22 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
-		if (self->kernel != DSO_TYPE_USER || kmodule) {
+		if (dso->kernel != DSO_TYPE_USER || kmodule) {
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
 				   (curr_dso->short_name +
-				    self->short_name_len)) == 0)
+				    dso->short_name_len)) == 0)
 				goto new_symbol;
 
 			if (strcmp(section_name, ".text") == 0) {
 				curr_map = map;
-				curr_dso = self;
+				curr_dso = dso;
 				goto new_symbol;
 			}
 
 			snprintf(dso_name, sizeof(dso_name),
-				 "%s%s", self->short_name, section_name);
+				 "%s%s", dso->short_name, section_name);
 
 			curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
 			if (curr_map == NULL) {
@@ -1195,9 +1200,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				curr_dso = dso__new(dso_name);
 				if (curr_dso == NULL)
 					goto out_elf_end;
-				curr_dso->kernel = self->kernel;
-				curr_dso->long_name = self->long_name;
-				curr_dso->long_name_len = self->long_name_len;
+				curr_dso->kernel = dso->kernel;
+				curr_dso->long_name = dso->long_name;
+				curr_dso->long_name_len = dso->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1206,9 +1211,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->symtab_type = self->symtab_type;
+				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&self->node, curr_dso);
+				dsos__add(&dso->node, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
@@ -1250,7 +1255,7 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&self->symbols[map->type]);
+		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
@@ -1266,9 +1271,9 @@ out_close:
 	return err;
 }
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
 {
-	return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
+	return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
 }
 
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
@@ -1429,7 +1434,7 @@ out:
 	return err;
 }
 
-char dso__symtab_origin(const struct dso *self)
+char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
 		[SYMTAB__KALLSYMS]	      = 'k',
@@ -1444,12 +1449,12 @@ char dso__symtab_origin(const struct dso *self)
 		[SYMTAB__GUEST_KMODULE]	      =  'G',
 	};
 
-	if (self == NULL || self->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
 		return '!';
-	return origin[self->symtab_type];
+	return origin[dso->symtab_type];
 }
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
 	int size = PATH_MAX;
 	char *name;
@@ -1459,12 +1464,12 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	const char *root_dir;
 	int want_symtab;
 
-	dso__set_loaded(self, map->type);
+	dso__set_loaded(dso, map->type);
 
-	if (self->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(self, map, filter);
-	else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(self, map, filter);
+	if (dso->kernel == DSO_TYPE_KERNEL)
+		return dso__load_kernel_sym(dso, map, filter);
+	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		return dso__load_guest_kernel_sym(dso, map, filter);
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1475,11 +1480,11 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	if (!name)
 		return -1;
 
-	self->adjust_symbols = 0;
+	dso->adjust_symbols = 0;
 
-	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
-		ret = dso__load_perf_map(self, map, filter);
-		self->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
+	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+		ret = dso__load_perf_map(dso, map, filter);
+		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
 					      SYMTAB__NOT_FOUND;
 		return ret;
 	}
@@ -1490,33 +1495,33 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	 */
 	want_symtab = 1;
 restart:
-	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE;
-	     self->symtab_type != SYMTAB__NOT_FOUND;
-	     self->symtab_type++) {
-		switch (self->symtab_type) {
+	for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
+	     dso->symtab_type != SYMTAB__NOT_FOUND;
+	     dso->symtab_type++) {
+		switch (dso->symtab_type) {
 		case SYMTAB__BUILD_ID_CACHE:
 			/* skip the locally configured cache if a symfs is given */
 			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(self, name, size) == NULL)) {
+			    (dso__build_id_filename(dso, name, size) == NULL)) {
 				continue;
 			}
 			break;
 		case SYMTAB__FEDORA_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, self->long_name);
+				 symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__UBUNTU_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, self->long_name);
+				 symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__BUILDID_DEBUGINFO: {
 			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
-			if (!self->has_build_id)
+			if (!dso->has_build_id)
 				continue;
 
-			build_id__sprintf(self->build_id,
-					  sizeof(self->build_id),
+			build_id__sprintf(dso->build_id,
+					  sizeof(dso->build_id),
 					  build_id_hex);
 			snprintf(name, size,
 				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
@@ -1525,7 +1530,7 @@ restart:
 			break;
 		case SYMTAB__SYSTEM_PATH_DSO:
 			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, self->long_name);
+			     symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__GUEST_KMODULE:
 			if (map->groups && machine)
@@ -1533,12 +1538,12 @@ restart:
 			else
 				root_dir = "";
 			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, self->long_name);
+				 root_dir, dso->long_name);
 			break;
 
 		case SYMTAB__SYSTEM_PATH_KMODULE:
 			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 self->long_name);
+				 dso->long_name);
 			break;
 		default:;
 		}
@@ -1548,7 +1553,7 @@ restart:
 		if (fd < 0)
 			continue;
 
-		ret = dso__load_sym(self, map, name, fd, filter, 0,
+		ret = dso__load_sym(dso, map, name, fd, filter, 0,
 				    want_symtab);
 		close(fd);
 
@@ -1560,7 +1565,8 @@ restart:
 			continue;
 
 		if (ret > 0) {
-			int nr_plt = dso__synthesize_plt_symbols(self, map, filter);
+			int nr_plt = dso__synthesize_plt_symbols(dso, map,
+								 filter);
 			if (nr_plt > 0)
 				ret += nr_plt;
 			break;
@@ -1577,17 +1583,17 @@ restart:
 	}
 
 	free(name);
-	if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
+	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
 		return 0;
 	return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *map = rb_entry(nd, struct map, rb_node);
 
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1597,28 +1603,28 @@ struct map *map_groups__find_by_name(struct map_groups *self,
 	return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self,
-				const char *root_dir)
+static int dso__kernel_module_get_build_id(struct dso *dso,
+					   const char *root_dir)
 {
 	char filename[PATH_MAX];
 	/*
 	 * kernel module short names are of the form "[module]" and
 	 * we need just "module" here.
 	 */
-	const char *name = self->short_name + 1;
+	const char *name = dso->short_name + 1;
 
 	snprintf(filename, sizeof(filename),
 		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
 		 root_dir, (int)strlen(name) - 1, name);
 
-	if (sysfs__read_build_id(filename, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
+	if (sysfs__read_build_id(filename, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
 
 	return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self,
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
 				const char *dir_name)
 {
 	struct dirent *dent;
@@ -1646,7 +1652,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 
 			snprintf(path, sizeof(path), "%s/%s",
 				 dir_name, dent->d_name);
-			ret = map_groups__set_modules_path_dir(self, path);
+			ret = map_groups__set_modules_path_dir(mg, path);
 			if (ret < 0)
 				goto out;
 		} else {
@@ -1661,7 +1667,8 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 				 (int)(dot - dent->d_name), dent->d_name);
 
 			strxfrchar(dso_name, '-', '_');
-			map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name);
+			map = map_groups__find_by_name(mg, MAP__FUNCTION,
+						       dso_name);
 			if (map == NULL)
 				continue;
 
@@ -1711,20 +1718,20 @@ static char *get_kernel_version(const char *root_dir)
 	return strdup(name);
 }
 
-static int machine__set_modules_path(struct machine *self)
+static int machine__set_modules_path(struct machine *machine)
 {
 	char *version;
 	char modules_path[PATH_MAX];
 
-	version = get_kernel_version(self->root_dir);
+	version = get_kernel_version(machine->root_dir);
 	if (!version)
 		return -1;
 
 	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-		 self->root_dir, version);
+		 machine->root_dir, version);
 	free(version);
 
-	return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
 }
 
 /*
@@ -1734,23 +1741,23 @@ static int machine__set_modules_path(struct machine *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-	struct map *self = calloc(1, (sizeof(*self) +
-				      (dso->kernel ? sizeof(struct kmap) : 0)));
-	if (self != NULL) {
+	struct map *map = calloc(1, (sizeof(*map) +
+				     (dso->kernel ? sizeof(struct kmap) : 0)));
+	if (map != NULL) {
 		/*
 		 * ->end will be filled after we load all the symbols
 		 */
-		map__init(self, type, start, 0, 0, dso);
+		map__init(map, type, start, 0, 0, dso);
 	}
 
-	return self;
+	return map;
 }
 
-struct map *machine__new_module(struct machine *self, u64 start,
+struct map *machine__new_module(struct machine *machine, u64 start,
 				const char *filename)
 {
 	struct map *map;
-	struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
 
 	if (dso == NULL)
 		return NULL;
@@ -1759,15 +1766,15 @@ struct map *machine__new_module(struct machine *self, u64 start,
 	if (map == NULL)
 		return NULL;
 
-	if (machine__is_host(self))
+	if (machine__is_host(machine))
 		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
 	else
 		dso->symtab_type = SYMTAB__GUEST_KMODULE;
-	map_groups__insert(&self->kmaps, map);
+	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
 
-static int machine__create_modules(struct machine *self)
+static int machine__create_modules(struct machine *machine)
 {
 	char *line = NULL;
 	size_t n;
@@ -1776,10 +1783,10 @@ static int machine__create_modules(struct machine *self)
 	const char *modules;
 	char path[PATH_MAX];
 
-	if (machine__is_default_guest(self))
+	if (machine__is_default_guest(machine))
 		modules = symbol_conf.default_guest_modules;
 	else {
-		sprintf(path, "%s/proc/modules", self->root_dir);
+		sprintf(path, "%s/proc/modules", machine->root_dir);
 		modules = path;
 	}
 
@@ -1815,16 +1822,16 @@ static int machine__create_modules(struct machine *self)
 		*sep = '\0';
 
 		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(self, start, name);
+		map = machine__new_module(machine, start, name);
 		if (map == NULL)
 			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, self->root_dir);
+		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
 	}
 
 	free(line);
 	fclose(file);
 
-	return machine__set_modules_path(self);
+	return machine__set_modules_path(machine);
 
 out_delete_line:
 	free(line);
@@ -1832,7 +1839,7 @@ out_failure:
 	return -1;
 }
 
-int dso__load_vmlinux(struct dso *self, struct map *map,
+int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter)
 {
 	int err = -1, fd;
@@ -1844,9 +1851,9 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	if (fd < 0)
 		return -1;
 
-	dso__set_long_name(self, (char *)vmlinux);
-	dso__set_loaded(self, map->type);
-	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
+	dso__set_long_name(dso, (char *)vmlinux);
+	dso__set_loaded(dso, map->type);
+	err = dso__load_sym(dso, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
 
 	if (err > 0)
@@ -1855,7 +1862,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	return err;
 }
 
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
@@ -1864,20 +1871,20 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
 	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
 		 vmlinux_path__nr_entries + 1);
 
-	filename = dso__build_id_filename(self, NULL, 0);
+	filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
-		err = dso__load_vmlinux(self, map, filename, filter);
+		err = dso__load_vmlinux(dso, map, filename, filter);
 		if (err > 0) {
-			dso__set_long_name(self, filename);
+			dso__set_long_name(dso, filename);
 			goto out;
 		}
 		free(filename);
 	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
 		if (err > 0) {
-			dso__set_long_name(self, strdup(vmlinux_path[i]));
+			dso__set_long_name(dso, strdup(vmlinux_path[i]));
 			break;
 		}
 	}
@@ -1885,7 +1892,7 @@ out:
 	return err;
 }
 
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter)
 {
 	int err;
@@ -1912,10 +1919,10 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 	if (symbol_conf.vmlinux_name != NULL) {
-		err = dso__load_vmlinux(self, map,
+		err = dso__load_vmlinux(dso, map,
 					symbol_conf.vmlinux_name, filter);
 		if (err > 0) {
-			dso__set_long_name(self,
+			dso__set_long_name(dso,
 					   strdup(symbol_conf.vmlinux_name));
 			goto out_fixup;
 		}
@@ -1923,7 +1930,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 	if (vmlinux_path != NULL) {
-		err = dso__load_vmlinux_path(self, map, filter);
+		err = dso__load_vmlinux_path(dso, map, filter);
 		if (err > 0)
 			goto out_fixup;
 	}
@@ -1937,13 +1944,13 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	 * we have a build-id, so check if it is the same as the running kernel,
 	 * using it if it is.
 	 */
-	if (self->has_build_id) {
+	if (dso->has_build_id) {
 		u8 kallsyms_build_id[BUILD_ID_SIZE];
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 		if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
 					 sizeof(kallsyms_build_id)) == 0) {
-			if (dso__build_id_equal(self, kallsyms_build_id)) {
+			if (dso__build_id_equal(dso, kallsyms_build_id)) {
 				kallsyms_filename = "/proc/kallsyms";
 				goto do_kallsyms;
 			}
@@ -1952,7 +1959,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 		 * Now look if we have it on the build-id cache in
 		 * $HOME/.debug/[kernel.kallsyms].
 		 */
-		build_id__sprintf(self->build_id, sizeof(self->build_id),
+		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
 
 		if (asprintf(&kallsyms_allocated_filename,
@@ -1979,7 +1986,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 do_kallsyms:
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	free(kallsyms_allocated_filename);
@@ -1987,7 +1994,7 @@ do_kallsyms:
 	if (err > 0) {
 out_fixup:
 		if (kallsyms_filename != NULL)
-			dso__set_long_name(self, strdup("[kernel.kallsyms]"));
+			dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1995,8 +2002,8 @@ out_fixup:
 	return err;
 }
 
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
-				symbol_filter_t filter)
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
+				      symbol_filter_t filter)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
@@ -2016,7 +2023,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		 * Or use file guest_kallsyms inputted by user on commandline
 		 */
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
-			err = dso__load_vmlinux(self, map,
+			err = dso__load_vmlinux(dso, map,
 				symbol_conf.default_guest_vmlinux_name, filter);
 			goto out_try_fixup;
 		}
@@ -2029,7 +2036,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		kallsyms_filename = path;
 	}
 
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 
@@ -2037,7 +2044,7 @@ out_try_fixup:
 	if (err > 0) {
 		if (kallsyms_filename != NULL) {
 			machine__mmap_name(machine, path, sizeof(path));
-			dso__set_long_name(self, strdup(path));
+			dso__set_long_name(dso, strdup(path));
 		}
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -2090,12 +2097,12 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 	return ret;
 }
 
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
 
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
 		ret += __dsos__fprintf(&pos->user_dsos, fp);
@@ -2119,18 +2126,20 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
 	return ret;
 }
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits)
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool with_hits)
 {
-	return __dsos__fprintf_buildid(&self->kernel_dsos, fp, with_hits) +
-	       __dsos__fprintf_buildid(&self->user_dsos, fp, with_hits);
+	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
+	       __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
 }
 
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+				      FILE *fp, bool with_hits)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
 
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
 	}
@@ -2139,59 +2148,59 @@ size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_
 
 struct dso *dso__new_kernel(const char *name)
 {
-	struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
+	struct dso *dso = dso__new(name ?: "[kernel.kallsyms]");
 
-	if (self != NULL) {
-		dso__set_short_name(self, "[kernel]");
-		self->kernel = DSO_TYPE_KERNEL;
+	if (dso != NULL) {
+		dso__set_short_name(dso, "[kernel]");
+		dso->kernel = DSO_TYPE_KERNEL;
 	}
 
-	return self;
+	return dso;
 }
 
 static struct dso *dso__new_guest_kernel(struct machine *machine,
 					const char *name)
 {
 	char bf[PATH_MAX];
-	struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
-
-	if (self != NULL) {
-		dso__set_short_name(self, "[guest.kernel]");
-		self->kernel = DSO_TYPE_GUEST_KERNEL;
+	struct dso *dso = dso__new(name ?: machine__mmap_name(machine, bf,
+							      sizeof(bf)));
+	if (dso != NULL) {
+		dso__set_short_name(dso, "[guest.kernel]");
+		dso->kernel = DSO_TYPE_GUEST_KERNEL;
 	}
 
-	return self;
+	return dso;
 }
 
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
+void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
 {
 	char path[PATH_MAX];
 
 	if (machine__is_default_guest(machine))
 		return;
 	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
-	if (sysfs__read_build_id(path, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
+	if (sysfs__read_build_id(path, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
 }
 
-static struct dso *machine__create_kernel(struct machine *self)
+static struct dso *machine__create_kernel(struct machine *machine)
 {
 	const char *vmlinux_name = NULL;
 	struct dso *kernel;
 
-	if (machine__is_host(self)) {
+	if (machine__is_host(machine)) {
 		vmlinux_name = symbol_conf.vmlinux_name;
 		kernel = dso__new_kernel(vmlinux_name);
 	} else {
-		if (machine__is_default_guest(self))
+		if (machine__is_default_guest(machine))
 			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		kernel = dso__new_guest_kernel(self, vmlinux_name);
+		kernel = dso__new_guest_kernel(machine, vmlinux_name);
 	}
 
 	if (kernel != NULL) {
-		dso__read_running_kernel_build_id(kernel, self);
-		dsos__add(&self->kernel_dsos, kernel);
+		dso__read_running_kernel_build_id(kernel, machine);
+		dsos__add(&machine->kernel_dsos, kernel);
 	}
 	return kernel;
 }
@@ -2236,41 +2245,43 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 	return args.start;
 }
 
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(self);
+	u64 start = machine__get_kernel_start_addr(machine);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		self->vmlinux_maps[type] = map__new2(start, kernel, type);
-		if (self->vmlinux_maps[type] == NULL)
+		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		if (machine->vmlinux_maps[type] == NULL)
 			return -1;
 
-		self->vmlinux_maps[type]->map_ip =
-			self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
-
-		kmap = map__kmap(self->vmlinux_maps[type]);
-		kmap->kmaps = &self->kmaps;
-		map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
+		machine->vmlinux_maps[type]->map_ip =
+			machine->vmlinux_maps[type]->unmap_ip =
+				identity__map_ip;
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		kmap->kmaps = &machine->kmaps;
+		map_groups__insert(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
 	}
 
 	return 0;
 }
 
-void machine__destroy_kernel_maps(struct machine *self)
+void machine__destroy_kernel_maps(struct machine *machine)
 {
 	enum map_type type;
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		if (self->vmlinux_maps[type] == NULL)
+		if (machine->vmlinux_maps[type] == NULL)
 			continue;
 
-		kmap = map__kmap(self->vmlinux_maps[type]);
-		map_groups__remove(&self->kmaps, self->vmlinux_maps[type]);
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map_groups__remove(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
 		if (kmap->ref_reloc_sym) {
 			/*
 			 * ref_reloc_sym is shared among all maps, so free just
@@ -2284,25 +2295,25 @@ void machine__destroy_kernel_maps(struct machine *self)
 			kmap->ref_reloc_sym = NULL;
 		}
 
-		map__delete(self->vmlinux_maps[type]);
-		self->vmlinux_maps[type] = NULL;
+		map__delete(machine->vmlinux_maps[type]);
+		machine->vmlinux_maps[type] = NULL;
 	}
 }
 
-int machine__create_kernel_maps(struct machine *self)
+int machine__create_kernel_maps(struct machine *machine)
 {
-	struct dso *kernel = machine__create_kernel(self);
+	struct dso *kernel = machine__create_kernel(machine);
 
 	if (kernel == NULL ||
-	    __machine__create_kernel_maps(self, kernel) < 0)
+	    __machine__create_kernel_maps(machine, kernel) < 0)
 		return -1;
 
-	if (symbol_conf.use_modules && machine__create_modules(self) < 0)
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
 		pr_debug("Problems creating module maps, continuing anyway...\n");
 	/*
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
-	map_groups__fixup_end(&self->kmaps);
+	map_groups__fixup_end(&machine->kmaps);
 	return 0;
 }
 
@@ -2366,11 +2377,11 @@ out_fail:
 	return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 {
 	int i;
 	size_t printed = 0;
-	struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
+	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
 
 	if (kdso->has_build_id) {
 		char filename[PATH_MAX];
@@ -2467,9 +2478,9 @@ void symbol__exit(void)
 	symbol_conf.initialized = false;
 }
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
 {
-	struct machine *machine = machines__findnew(self, pid);
+	struct machine *machine = machines__findnew(machines, pid);
 
 	if (machine == NULL)
 		return -1;
@@ -2520,7 +2531,7 @@ char *strxfrchar(char *s, char from, char to)
 	return s;
 }
 
-int machines__create_guest_kernel_maps(struct rb_root *self)
+int machines__create_guest_kernel_maps(struct rb_root *machines)
 {
 	int ret = 0;
 	struct dirent **namelist = NULL;
@@ -2531,7 +2542,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
 	if (symbol_conf.default_guest_vmlinux_name ||
 	    symbol_conf.default_guest_modules ||
 	    symbol_conf.default_guest_kallsyms) {
-		machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
+		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
 	}
 
 	if (symbol_conf.guestmount) {
@@ -2552,7 +2563,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
 				pr_debug("Can't access file %s\n", path);
 				goto failure;
 			}
-			machines__create_kernel_maps(self, pid);
+			machines__create_kernel_maps(machines, pid);
 		}
 failure:
 		free(namelist);
@@ -2561,23 +2572,23 @@ failure:
 	return ret;
 }
 
-void machines__destroy_guest_kernel_maps(struct rb_root *self)
+void machines__destroy_guest_kernel_maps(struct rb_root *machines)
 {
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(machines);
 
 	while (next) {
 		struct machine *pos = rb_entry(next, struct machine, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, machines);
 		machine__delete(pos);
 	}
 }
 
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter)
 {
-	struct map *map = self->vmlinux_maps[type];
+	struct map *map = machine->vmlinux_maps[type];
 	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
 
 	if (ret > 0) {
@@ -2587,16 +2598,16 @@ int machine__load_kallsyms(struct machine *self, const char *filename,
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		__map_groups__fixup_end(&self->kmaps, type);
+		__map_groups__fixup_end(&machine->kmaps, type);
 	}
 
 	return ret;
 }
 
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter)
 {
-	struct map *map = self->vmlinux_maps[type];
+	struct map *map = machine->vmlinux_maps[type];
 	int ret = dso__load_vmlinux_path(map->dso, map, filter);
 
 	if (ret > 0) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 713b0b40cc4..242de0101a8 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -62,7 +62,7 @@ struct symbol {
 	char		name[0];
 };
 
-void symbol__delete(struct symbol *self);
+void symbol__delete(struct symbol *sym);
 
 struct strlist;
 
@@ -96,9 +96,9 @@ struct symbol_conf {
 
 extern struct symbol_conf symbol_conf;
 
-static inline void *symbol__priv(struct symbol *self)
+static inline void *symbol__priv(struct symbol *sym)
 {
-	return ((void *)self) - symbol_conf.priv_size;
+	return ((void *)sym) - symbol_conf.priv_size;
 }
 
 struct ref_reloc_sym {
@@ -155,43 +155,45 @@ struct dso {
 
 struct dso *dso__new(const char *name);
 struct dso *dso__new_kernel(const char *name);
-void dso__delete(struct dso *self);
+void dso__delete(struct dso *dso);
 
-int dso__name_len(const struct dso *self);
+int dso__name_len(const struct dso *dso);
 
-bool dso__loaded(const struct dso *self, enum map_type type);
-bool dso__sorted_by_name(const struct dso *self, enum map_type type);
+bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
 
-static inline void dso__set_loaded(struct dso *self, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
-	self->loaded |= (1 << type);
+	dso->loaded |= (1 << type);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type);
+void dso__sort_by_name(struct dso *dso, enum map_type type);
 
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
-int dso__load_vmlinux(struct dso *self, struct map *map,
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 		       symbol_filter_t filter);
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter);
 
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
-
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
-size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp);
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
+size_t machine__fprintf_dsos_buildid(struct machine *machine,
+				     FILE *fp, bool with_hits);
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+				      FILE *fp, bool with_hits);
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp);
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
 enum symtab_type {
 	SYMTAB__KALLSYMS = 0,
@@ -207,34 +209,36 @@ enum symtab_type {
 	SYMTAB__NOT_FOUND,
 };
 
-char dso__symtab_origin(const struct dso *self);
-void dso__set_long_name(struct dso *self, char *name);
-void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
-struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+char dso__symtab_origin(const struct dso *dso);
+void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_build_id(struct dso *dso, void *build_id);
+void dso__read_running_kernel_build_id(struct dso *dso,
+				       struct machine *machine);
+struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
+				u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-int build_id__sprintf(const u8 *self, int len, char *bf);
+int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start, u64 end));
 
-void machine__destroy_kernel_maps(struct machine *self);
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
-int machine__create_kernel_maps(struct machine *self);
+void machine__destroy_kernel_maps(struct machine *machine);
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *machine);
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *self);
-void machines__destroy_guest_kernel_maps(struct rb_root *self);
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *machines);
+void machines__destroy_guest_kernel_maps(struct rb_root *machines);
 
 int symbol__init(void);
 void symbol__exit(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 0a7ed5b5e28..1e88485c16a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -2187,7 +2187,6 @@ static const struct flag flags[] = {
 	{ "TASKLET_SOFTIRQ", 6 },
 	{ "SCHED_SOFTIRQ", 7 },
 	{ "HRTIMER_SOFTIRQ", 8 },
-	{ "RCU_SOFTIRQ", 9 },
 
 	{ "HRTIMER_NORESTART", 0 },
 	{ "HRTIMER_RESTART", 1 },