Merge tag 'edac_fixes_for_3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp

Pull amd64 edac fix from Borislav Petkov:
 "A sysfs file permissions correction"

* tag 'edac_fixes_for_3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
  amd64_edac: Fix bogus sysfs file permissions
diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt
index 44afa0e..4ff6504 100644
--- a/Documentation/devicetree/bindings/net/macb.txt
+++ b/Documentation/devicetree/bindings/net/macb.txt
@@ -4,7 +4,7 @@
 - compatible: Should be "cdns,[<chip>-]{macb|gem}"
   Use "cdns,at91sam9260-macb" Atmel at91sam9260 and at91sam9263 SoCs.
   Use "cdns,at32ap7000-macb" for other 10/100 usage or use the generic form: "cdns,macb".
-  Use "cnds,pc302-gem" for Picochip picoXcell pc302 and later devices based on
+  Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on
   the Cadence GEM, or the generic form: "cdns,gem".
 - reg: Address and length of the register set for the device
 - interrupts: Should contain macb interrupt
diff --git a/Documentation/devicetree/bindings/drm/exynos/hdmi.txt b/Documentation/devicetree/bindings/video/exynos_hdmi.txt
similarity index 100%
rename from Documentation/devicetree/bindings/drm/exynos/hdmi.txt
rename to Documentation/devicetree/bindings/video/exynos_hdmi.txt
diff --git a/Documentation/devicetree/bindings/drm/exynos/hdmiddc.txt b/Documentation/devicetree/bindings/video/exynos_hdmiddc.txt
similarity index 100%
rename from Documentation/devicetree/bindings/drm/exynos/hdmiddc.txt
rename to Documentation/devicetree/bindings/video/exynos_hdmiddc.txt
diff --git a/Documentation/devicetree/bindings/drm/exynos/hdmiphy.txt b/Documentation/devicetree/bindings/video/exynos_hdmiphy.txt
similarity index 100%
rename from Documentation/devicetree/bindings/drm/exynos/hdmiphy.txt
rename to Documentation/devicetree/bindings/video/exynos_hdmiphy.txt
diff --git a/Documentation/devicetree/bindings/drm/exynos/mixer.txt b/Documentation/devicetree/bindings/video/exynos_mixer.txt
similarity index 100%
rename from Documentation/devicetree/bindings/drm/exynos/mixer.txt
rename to Documentation/devicetree/bindings/video/exynos_mixer.txt
diff --git a/Documentation/devicetree/bindings/video/simple-framebuffer.txt b/Documentation/devicetree/bindings/video/simple-framebuffer.txt
new file mode 100644
index 0000000..3ea4605
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/simple-framebuffer.txt
@@ -0,0 +1,25 @@
+Simple Framebuffer
+
+A simple frame-buffer describes a raw memory region that may be rendered to,
+with the assumption that the display hardware has already been set up to scan
+out from that buffer.
+
+Required properties:
+- compatible: "simple-framebuffer"
+- reg: Should contain the location and size of the framebuffer memory.
+- width: The width of the framebuffer in pixels.
+- height: The height of the framebuffer in pixels.
+- stride: The number of bytes in each line of the framebuffer.
+- format: The format of the framebuffer surface. Valid values are:
+  - r5g6b5 (16-bit pixels, d[15:11]=r, d[10:5]=g, d[4:0]=b).
+
+Example:
+
+	framebuffer {
+		compatible = "simple-framebuffer";
+		reg = <0x1d385000 (1600 * 1200 * 2)>;
+		width = <1600>;
+		height = <1200>;
+		stride = <(1600 * 2)>;
+		format = "r5g6b5";
+	};
diff --git a/Documentation/devicetree/usage-model.txt b/Documentation/devicetree/usage-model.txt
index ef9d06c..0efedaa 100644
--- a/Documentation/devicetree/usage-model.txt
+++ b/Documentation/devicetree/usage-model.txt
@@ -191,9 +191,11 @@
 	};
 
 The bootargs property contains the kernel arguments, and the initrd-*
-properties define the address and size of an initrd blob.  The
-chosen node may also optionally contain an arbitrary number of
-additional properties for platform-specific configuration data.
+properties define the address and size of an initrd blob.  Note that
+initrd-end is the first address after the initrd image, so this doesn't
+match the usual semantic of struct resource.  The chosen node may also
+optionally contain an arbitrary number of additional properties for
+platform-specific configuration data.
 
 During early boot, the architecture setup code calls of_scan_flat_dt()
 several times with different helper callbacks to parse device tree
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index c3bfacb..6e3b18a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3005,6 +3005,27 @@
 			Force threading of all interrupt handlers except those
 			marked explicitly IRQF_NO_THREAD.
 
+	tmem		[KNL,XEN]
+			Enable the Transcendent memory driver if built-in.
+
+	tmem.cleancache=0|1 [KNL, XEN]
+			Default is on (1). Disable the usage of the cleancache
+			API to send anonymous pages to the hypervisor.
+
+	tmem.frontswap=0|1 [KNL, XEN]
+			Default is on (1). Disable the usage of the frontswap
+			API to send swap pages to the hypervisor. If disabled
+			the selfballooning and selfshrinking are force disabled.
+
+	tmem.selfballooning=0|1 [KNL, XEN]
+			Default is on (1). Disable the driving of swap pages
+			to the hypervisor.
+
+	tmem.selfshrinking=0|1 [KNL, XEN]
+			Default is on (1). Partial swapoff that immediately
+			transfers pages from Xen hypervisor back to the
+			kernel based on different criteria.
+
 	topology=	[S390]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
new file mode 100644
index 0000000..cbf7ae4
--- /dev/null
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -0,0 +1,202 @@
+REDUCING OS JITTER DUE TO PER-CPU KTHREADS
+
+This document lists per-CPU kthreads in the Linux kernel and presents
+options to control their OS jitter.  Note that non-per-CPU kthreads are
+not listed here.  To reduce OS jitter from non-per-CPU kthreads, bind
+them to a "housekeeping" CPU dedicated to such work.
+
+
+REFERENCES
+
+o	Documentation/IRQ-affinity.txt:  Binding interrupts to sets of CPUs.
+
+o	Documentation/cgroups:  Using cgroups to bind tasks to sets of CPUs.
+
+o	man taskset:  Using the taskset command to bind tasks to sets
+	of CPUs.
+
+o	man sched_setaffinity:  Using the sched_setaffinity() system
+	call to bind tasks to sets of CPUs.
+
+o	/sys/devices/system/cpu/cpuN/online:  Control CPU N's hotplug state,
+	writing "0" to offline and "1" to online.
+
+o	In order to locate kernel-generated OS jitter on CPU N:
+
+		cd /sys/kernel/debug/tracing
+		echo 1 > max_graph_depth # Increase the "1" for more detail
+		echo function_graph > current_tracer
+		# run workload
+		cat per_cpu/cpuN/trace
+
+
+KTHREADS
+
+Name: ehca_comp/%u
+Purpose: Periodically process Infiniband-related work.
+To reduce its OS jitter, do any of the following:
+1.	Don't use eHCA Infiniband hardware, instead choosing hardware
+	that does not require per-CPU kthreads.  This will prevent these
+	kthreads from being created in the first place.  (This will
+	work for most people, as this hardware, though important, is
+	relatively old and is produced in relatively low unit volumes.)
+2.	Do all eHCA-Infiniband-related work on other CPUs, including
+	interrupts.
+3.	Rework the eHCA driver so that its per-CPU kthreads are
+	provisioned only on selected CPUs.
+
+
+Name: irq/%d-%s
+Purpose: Handle threaded interrupts.
+To reduce its OS jitter, do the following:
+1.	Use irq affinity to force the irq threads to execute on
+	some other CPU.
+
+Name: kcmtpd_ctr_%d
+Purpose: Handle Bluetooth work.
+To reduce its OS jitter, do one of the following:
+1.	Don't use Bluetooth, in which case these kthreads won't be
+	created in the first place.
+2.	Use irq affinity to force Bluetooth-related interrupts to
+	occur on some other CPU and furthermore initiate all
+	Bluetooth activity on some other CPU.
+
+Name: ksoftirqd/%u
+Purpose: Execute softirq handlers when threaded or when under heavy load.
+To reduce its OS jitter, each softirq vector must be handled
+separately as follows:
+TIMER_SOFTIRQ:  Do all of the following:
+1.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle, for example, by avoiding system calls and by forcing
+	both kernel threads and interrupts to execute elsewhere.
+2.	Build with CONFIG_HOTPLUG_CPU=y.  After boot completes, force
+	the CPU offline, then bring it back online.  This forces
+	recurring timers to migrate elsewhere.	If you are concerned
+	with multiple CPUs, force them all offline before bringing the
+	first one back online.  Once you have onlined the CPUs in question,
+	do not offline any other CPUs, because doing so could force the
+	timer back onto one of the CPUs in question.
+NET_TX_SOFTIRQ and NET_RX_SOFTIRQ:  Do all of the following:
+1.	Force networking interrupts onto other CPUs.
+2.	Initiate any network I/O on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+BLOCK_SOFTIRQ:  Do all of the following:
+1.	Force block-device interrupts onto some other CPU.
+2.	Initiate any block I/O on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+BLOCK_IOPOLL_SOFTIRQ:  Do all of the following:
+1.	Force block-device interrupts onto some other CPU.
+2.	Initiate any block I/O and block-I/O polling on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+TASKLET_SOFTIRQ: Do one or more of the following:
+1.	Avoid use of drivers that use tasklets.  (Such drivers will contain
+	calls to things like tasklet_schedule().)
+2.	Convert all drivers that you must use from tasklets to workqueues.
+3.	Force interrupts for drivers using tasklets onto other CPUs,
+	and also do I/O involving these drivers on other CPUs.
+SCHED_SOFTIRQ: Do all of the following:
+1.	Avoid sending scheduler IPIs to the CPU to be de-jittered,
+	for example, ensure that at most one runnable kthread is present
+	on that CPU.  If a thread that expects to run on the de-jittered
+	CPU awakens, the scheduler will send an IPI that can result in
+	a subsequent SCHED_SOFTIRQ.
+2.	Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+	CONFIG_NO_HZ_FULL=y, and, in addition, ensure that the CPU
+	to be de-jittered is marked as an adaptive-ticks CPU using the
+	"nohz_full=" boot parameter.  This reduces the number of
+	scheduler-clock interrupts that the de-jittered CPU receives,
+	minimizing its chances of being selected to do the load balancing
+	work that runs in SCHED_SOFTIRQ context.
+3.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle, for example, by avoiding system calls and by
+	forcing both kernel threads and interrupts to execute elsewhere.
+	This further reduces the number of scheduler-clock interrupts
+	received by the de-jittered CPU.
+HRTIMER_SOFTIRQ:  Do all of the following:
+1.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle.  For example, avoid system calls and force both
+	kernel threads and interrupts to execute elsewhere.
+2.	Build with CONFIG_HOTPLUG_CPU=y.  Once boot completes, force the
+	CPU offline, then bring it back online.  This forces recurring
+	timers to migrate elsewhere.  If you are concerned with multiple
+	CPUs, force them all offline before bringing the first one
+	back online.  Once you have onlined the CPUs in question, do not
+	offline any other CPUs, because doing so could force the timer
+	back onto one of the CPUs in question.
+RCU_SOFTIRQ:  Do at least one of the following:
+1.	Offload callbacks and keep the CPU in either dyntick-idle or
+	adaptive-ticks state by doing all of the following:
+	a.	Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+		CONFIG_NO_HZ_FULL=y, and, in addition ensure that the CPU
+		to be de-jittered is marked as an adaptive-ticks CPU using
+		the "nohz_full=" boot parameter.  Bind the rcuo kthreads
+		to housekeeping CPUs, which can tolerate OS jitter.
+	b.	To the extent possible, keep the CPU out of the kernel
+		when it is non-idle, for example, by avoiding system
+		calls and by forcing both kernel threads and interrupts
+		to execute elsewhere.
+2.	Enable RCU to do its processing remotely via dyntick-idle by
+	doing all of the following:
+	a.	Build with CONFIG_NO_HZ=y and CONFIG_RCU_FAST_NO_HZ=y.
+	b.	Ensure that the CPU goes idle frequently, allowing other
+		CPUs to detect that it has passed through an RCU quiescent
+		state.	If the kernel is built with CONFIG_NO_HZ_FULL=y,
+		userspace execution also allows other CPUs to detect that
+		the CPU in question has passed through a quiescent state.
+	c.	To the extent possible, keep the CPU out of the kernel
+		when it is non-idle, for example, by avoiding system
+		calls and by forcing both kernel threads and interrupts
+		to execute elsewhere.
+
+Name: rcuc/%u
+Purpose: Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
+To reduce its OS jitter, do at least one of the following:
+1.	Build the kernel with CONFIG_PREEMPT=n.  This prevents these
+	kthreads from being created in the first place, and also obviates
+	the need for RCU priority boosting.  This approach is feasible
+	for workloads that do not require high degrees of responsiveness.
+2.	Build the kernel with CONFIG_RCU_BOOST=n.  This prevents these
+	kthreads from being created in the first place.  This approach
+	is feasible only if your workload never requires RCU priority
+	boosting, for example, if you ensure frequent idle time on all
+	CPUs that might execute within the kernel.
+3.	Build with CONFIG_RCU_NOCB_CPU=y and CONFIG_RCU_NOCB_CPU_ALL=y,
+	which offloads all RCU callbacks to kthreads that can be moved
+	off of CPUs susceptible to OS jitter.  This approach prevents the
+	rcuc/%u kthreads from having any work to do, so that they are
+	never awakened.
+4.	Ensure that the CPU never enters the kernel, and, in particular,
+	avoid initiating any CPU hotplug operations on this CPU.  This is
+	another way of preventing any callbacks from being queued on the
+	CPU, again preventing the rcuc/%u kthreads from having any work
+	to do.
+
+Name: rcuob/%d, rcuop/%d, and rcuos/%d
+Purpose: Offload RCU callbacks from the corresponding CPU.
+To reduce its OS jitter, do at least one of the following:
+1.	Use affinity, cgroups, or other mechanism to force these kthreads
+	to execute on some other CPU.
+2.	Build with CONFIG_RCU_NOCB_CPUS=n, which will prevent these
+	kthreads from being created in the first place.  However, please
+	note that this will not eliminate OS jitter, but will instead
+	shift it to RCU_SOFTIRQ.
+
+Name: watchdog/%u
+Purpose: Detect software lockups on each CPU.
+To reduce its OS jitter, do at least one of the following:
+1.	Build with CONFIG_LOCKUP_DETECTOR=n, which will prevent these
+	kthreads from being created in the first place.
+2.	Echo a zero to /proc/sys/kernel/watchdog to disable the
+	watchdog timer.
+3.	Echo a large number of /proc/sys/kernel/watchdog_thresh in
+	order to reduce the frequency of OS jitter due to the watchdog
+	timer down to a level that is acceptable for your workload.
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 504dfe4..a66c982 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -268,7 +268,7 @@
 System Power Management Phases
 ------------------------------
 Suspending or resuming the system is done in several phases.  Different phases
-are used for standby or memory sleep states ("suspend-to-RAM") and the
+are used for freeze, standby, and memory sleep states ("suspend-to-RAM") and the
 hibernation state ("suspend-to-disk").  Each phase involves executing callbacks
 for every device before the next phase begins.  Not all busses or classes
 support all these callbacks and not all drivers use all the callbacks.  The
@@ -309,7 +309,8 @@
 
 Entering System Suspend
 -----------------------
-When the system goes into the standby or memory sleep state, the phases are:
+When the system goes into the freeze, standby or memory sleep state,
+the phases are:
 
 		prepare, suspend, suspend_late, suspend_noirq.
 
@@ -368,7 +369,7 @@
 
 Leaving System Suspend
 ----------------------
-When resuming from standby or memory sleep, the phases are:
+When resuming from freeze, standby or memory sleep, the phases are:
 
 		resume_noirq, resume_early, resume, complete.
 
@@ -433,8 +434,8 @@
 
 Entering Hibernation
 --------------------
-Hibernating the system is more complicated than putting it into the standby or
-memory sleep state, because it involves creating and saving a system image.
+Hibernating the system is more complicated than putting it into the other
+sleep states, because it involves creating and saving a system image.
 Therefore there are more phases for hibernation, with a different set of
 callbacks.  These phases always run after tasks have been frozen and memory has
 been freed.
@@ -485,8 +486,8 @@
 
 At this point the system image is saved, and the devices then need to be
 prepared for the upcoming system shutdown.  This is much like suspending them
-before putting the system into the standby or memory sleep state, and the phases
-are similar.
+before putting the system into the freeze, standby or memory sleep state,
+and the phases are similar.
 
     9.	The prepare phase is discussed above.
 
diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt
index c537834..f1f0f59a 100644
--- a/Documentation/power/interface.txt
+++ b/Documentation/power/interface.txt
@@ -7,8 +7,8 @@
 is mounted at /sys). 
 
 /sys/power/state controls system power state. Reading from this file
-returns what states are supported, which is hard-coded to 'standby'
-(Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk'
+returns what states are supported, which is hard-coded to 'freeze',
+'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk'
 (Suspend-to-Disk). 
 
 Writing to this file one of those strings causes the system to
diff --git a/Documentation/power/notifiers.txt b/Documentation/power/notifiers.txt
index c2a4a34..a81fa25 100644
--- a/Documentation/power/notifiers.txt
+++ b/Documentation/power/notifiers.txt
@@ -15,8 +15,10 @@
 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_HIBERNATION_PREPARE	The system is going to hibernate, tasks will be frozen
+			immediately. This is different from PM_SUSPEND_PREPARE
+			below because here we do additional work between notifiers
+			and drivers freezing.
 
 PM_POST_HIBERNATION	The system memory state has been restored from a
 			hibernation image or an error occurred during
diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt
index 4416b28..442d43d 100644
--- a/Documentation/power/states.txt
+++ b/Documentation/power/states.txt
@@ -2,12 +2,26 @@
 System Power Management States
 
 
-The kernel supports three power management states generically, though
-each is dependent on platform support code to implement the low-level
-details for each state. This file describes each state, what they are
+The kernel supports four power management states generically, though
+one is generic and the other three are dependent on platform support
+code to implement the low-level details for each state.
+This file describes each state, what they are
 commonly called, what ACPI state they map to, and what string to write
 to /sys/power/state to enter that state
 
+state:		Freeze / Low-Power Idle
+ACPI state:	S0
+String:		"freeze"
+
+This state is a generic, pure software, light-weight, low-power state.
+It allows more energy to be saved relative to idle by freezing user
+space and putting all I/O devices into low-power states (possibly
+lower-power than available at run time), such that the processors can
+spend more time in their idle states.
+This state can be used for platforms without Standby/Suspend-to-RAM
+support, or it can be used in addition to Suspend-to-RAM (memory sleep)
+to provide reduced resume latency.
+
 
 State:		Standby / Power-On Suspend
 ACPI State:	S1
@@ -22,9 +36,6 @@
 also offers low power savings, but low resume latency. Not all devices
 support D1, and those that don't are left on. 
 
-A transition from Standby to the On state should take about 1-2
-seconds. 
-
 
 State:		Suspend-to-RAM
 ACPI State:	S3
@@ -42,9 +53,6 @@
 For at least ACPI, STR requires some minimal boot-strapping code to
 resume the system from STR. This may be true on other platforms. 
 
-A transition from Suspend-to-RAM to the On state should take about
-3-5 seconds. 
-
 
 State:		Suspend-to-disk
 ACPI State:	S4
@@ -74,7 +82,3 @@
 down offers greater savings, and allows this mechanism to work on any
 system. However, entering a real low-power state allows the user to
 trigger wake up events (e.g. pressing a key or opening a laptop lid).
-
-A transition from Suspend-to-Disk to the On state should take about 30
-seconds, though it's typically a bit more with the current
-implementation. 
diff --git a/Documentation/rapidio/rapidio.txt b/Documentation/rapidio/rapidio.txt
index c75694b..a9c16c9 100644
--- a/Documentation/rapidio/rapidio.txt
+++ b/Documentation/rapidio/rapidio.txt
@@ -79,20 +79,63 @@
 In order to initialize the RapidIO subsystem, a platform must initialize and
 register at least one master port within the RapidIO network. To register mport
 within the subsystem controller driver initialization code calls function
-rio_register_mport() for each available master port. After all active master
-ports are registered with a RapidIO subsystem, the rio_init_mports() routine
-is called to perform enumeration and discovery.
+rio_register_mport() for each available master port.
 
-In the current PowerPC-based implementation a subsys_initcall() is specified to
-perform controller initialization and mport registration. At the end it directly
-calls rio_init_mports() to execute RapidIO enumeration and discovery.
+RapidIO subsystem uses subsys_initcall() or device_initcall() to perform
+controller initialization (depending on controller device type).
+
+After all active master ports are registered with a RapidIO subsystem,
+an enumeration and/or discovery routine may be called automatically or
+by user-space command.
 
 4. Enumeration and Discovery
 ----------------------------
 
-When rio_init_mports() is called it scans a list of registered master ports and
-calls an enumeration or discovery routine depending on the configured role of a
-master port: host or agent.
+4.1 Overview
+------------
+
+RapidIO subsystem configuration options allow users to specify enumeration and
+discovery methods as statically linked components or loadable modules.
+An enumeration/discovery method implementation and available input parameters
+define how any given method can be attached to available RapidIO mports:
+simply to all available mports OR individually to the specified mport device.
+
+Depending on selected enumeration/discovery build configuration, there are
+several methods to initiate an enumeration and/or discovery process:
+
+  (a) Statically linked enumeration and discovery process can be started
+  automatically during kernel initialization time using corresponding module
+  parameters. This was the original method used since introduction of RapidIO
+  subsystem. Now this method relies on enumerator module parameter which is
+  'rio-scan.scan' for existing basic enumeration/discovery method.
+  When automatic start of enumeration/discovery is used a user has to ensure
+  that all discovering endpoints are started before the enumerating endpoint
+  and are waiting for enumeration to be completed.
+  Configuration option CONFIG_RAPIDIO_DISC_TIMEOUT defines time that discovering
+  endpoint waits for enumeration to be completed. If the specified timeout
+  expires the discovery process is terminated without obtaining RapidIO network
+  information. NOTE: a timed out discovery process may be restarted later using
+  a user-space command as it is described later if the given endpoint was
+  enumerated successfully.
+
+  (b) Statically linked enumeration and discovery process can be started by
+  a command from user space. This initiation method provides more flexibility
+  for a system startup compared to the option (a) above. After all participating
+  endpoints have been successfully booted, an enumeration process shall be
+  started first by issuing a user-space command, after an enumeration is
+  completed a discovery process can be started on all remaining endpoints.
+
+  (c) Modular enumeration and discovery process can be started by a command from
+  user space. After an enumeration/discovery module is loaded, a network scan
+  process can be started by issuing a user-space command.
+  Similar to the option (b) above, an enumerator has to be started first.
+
+  (d) Modular enumeration and discovery process can be started by a module
+  initialization routine. In this case an enumerating module shall be loaded
+  first.
+
+When a network scan process is started it calls an enumeration or discovery
+routine depending on the configured role of a master port: host or agent.
 
 Enumeration is performed by a master port if it is configured as a host port by
 assigning a host device ID greater than or equal to zero. A host device ID is
@@ -104,8 +147,58 @@
 The enumeration and discovery routines use RapidIO maintenance transactions
 to access the configuration space of devices.
 
-The enumeration process is implemented according to the enumeration algorithm
-outlined in the RapidIO Interconnect Specification: Annex I [1].
+4.2 Automatic Start of Enumeration and Discovery
+------------------------------------------------
+
+Automatic enumeration/discovery start method is applicable only to built-in
+enumeration/discovery RapidIO configuration selection. To enable automatic
+enumeration/discovery start by existing basic enumerator method set use boot
+command line parameter "rio-scan.scan=1".
+
+This configuration requires synchronized start of all RapidIO endpoints that
+form a network which will be enumerated/discovered. Discovering endpoints have
+to be started before an enumeration starts to ensure that all RapidIO
+controllers have been initialized and are ready to be discovered. Configuration
+parameter CONFIG_RAPIDIO_DISC_TIMEOUT defines time (in seconds) which
+a discovering endpoint will wait for enumeration to be completed.
+
+When automatic enumeration/discovery start is selected, basic method's
+initialization routine calls rio_init_mports() to perform enumeration or
+discovery for all known mport devices.
+
+Depending on RapidIO network size and configuration this automatic
+enumeration/discovery start method may be difficult to use due to the
+requirement for synchronized start of all endpoints.
+
+4.3 User-space Start of Enumeration and Discovery
+-------------------------------------------------
+
+User-space start of enumeration and discovery can be used with built-in and
+modular build configurations. For user-space controlled start RapidIO subsystem
+creates the sysfs write-only attribute file '/sys/bus/rapidio/scan'. To initiate
+an enumeration or discovery process on specific mport device, a user needs to
+write mport_ID (not RapidIO destination ID) into that file. The mport_ID is a
+sequential number (0 ... RIO_MAX_MPORTS) assigned during mport device
+registration. For example for machine with single RapidIO controller, mport_ID
+for that controller always will be 0.
+
+To initiate RapidIO enumeration/discovery on all available mports a user may
+write '-1' (or RIO_MPORT_ANY) into the scan attribute file.
+
+4.4 Basic Enumeration Method
+----------------------------
+
+This is an original enumeration/discovery method which is available since
+first release of RapidIO subsystem code. The enumeration process is
+implemented according to the enumeration algorithm outlined in the RapidIO
+Interconnect Specification: Annex I [1].
+
+This method can be configured as statically linked or loadable module.
+The method's single parameter "scan" allows to trigger the enumeration/discovery
+process from module initialization routine.
+
+This enumeration/discovery method can be started only once and does not support
+unloading if it is built as a module.
 
 The enumeration process traverses the network using a recursive depth-first
 algorithm. When a new device is found, the enumerator takes ownership of that
@@ -160,6 +253,19 @@
 an agent skips RapidIO discovery and continues with remaining kernel
 initialization.
 
+4.5 Adding New Enumeration/Discovery Method
+-------------------------------------------
+
+RapidIO subsystem code organization allows addition of new enumeration/discovery
+methods as new configuration options without significant impact to to the core
+RapidIO code.
+
+A new enumeration/discovery method has to be attached to one or more mport
+devices before an enumeration/discovery process can be started. Normally,
+method's module initialization routine calls rio_register_scan() to attach
+an enumerator to a specified mport device (or devices). The basic enumerator
+implementation demonstrates this process.
+
 5. References
 -------------
 
diff --git a/Documentation/rapidio/sysfs.txt b/Documentation/rapidio/sysfs.txt
index 97f71ce..1987817 100644
--- a/Documentation/rapidio/sysfs.txt
+++ b/Documentation/rapidio/sysfs.txt
@@ -88,3 +88,20 @@
 
 IDT_GEN2:
  errlog - reads contents of device error log until it is empty.
+
+
+5. RapidIO Bus Attributes
+-------------------------
+
+RapidIO bus subdirectory /sys/bus/rapidio implements the following bus-specific
+attribute:
+
+  scan - allows to trigger enumeration discovery process from user space. This
+	 is a write-only attribute. To initiate an enumeration or discovery
+	 process on specific mport device, a user needs to write mport_ID (not
+	 RapidIO destination ID) into this file. The mport_ID is a sequential
+	 number (0 ... RIO_MAX_MPORTS) assigned to the mport device.
+	 For example, for a machine with a single RapidIO controller, mport_ID
+	 for that controller always will be 0.
+	 To initiate RapidIO enumeration/discovery on all available mports
+	 a user must write '-1' (or RIO_MPORT_ANY) into this attribute file.
diff --git a/MAINTAINERS b/MAINTAINERS
index 3d7782b..fd3a495 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3865,9 +3865,16 @@
 M:	Haiyang Zhang <haiyangz@microsoft.com>
 L:	devel@linuxdriverproject.org
 S:	Maintained
-F:	drivers/hv/
+F:	arch/x86/include/asm/mshyperv.h
+F:	arch/x86/include/uapi/asm/hyperv.h
+F:	arch/x86/kernel/cpu/mshyperv.c
 F:	drivers/hid/hid-hyperv.c
+F:	drivers/hv/
 F:	drivers/net/hyperv/
+F:	drivers/scsi/storvsc_drv.c
+F:	drivers/video/hyperv_fb.c
+F:	include/linux/hyperv.h
+F:	tools/hv/
 
 I2C OVER PARALLEL PORT
 M:	Jean Delvare <khali@linux-fr.org>
@@ -4641,12 +4648,13 @@
 F:	include/uapi/linux/sunrpc/
 
 KERNEL VIRTUAL MACHINE (KVM)
-M:	Marcelo Tosatti <mtosatti@redhat.com>
 M:	Gleb Natapov <gleb@redhat.com>
+M:	Paolo Bonzini <pbonzini@redhat.com>
 L:	kvm@vger.kernel.org
-W:	http://kvm.qumranet.com
+W:	http://linux-kvm.org
 S:	Supported
-F:	Documentation/*/kvm.txt
+F:	Documentation/*/kvm*.txt
+F:	Documentation/virtual/kvm/
 F:	arch/*/kvm/
 F:	arch/*/include/asm/kvm*
 F:	include/linux/kvm*
@@ -4976,6 +4984,13 @@
 F:	Documentation/hwmon/lm90
 F:	drivers/hwmon/lm90.c
 
+LM95234 HARDWARE MONITOR DRIVER
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	lm-sensors@lm-sensors.org
+S:	Maintained
+F:	Documentation/hwmon/lm95234
+F:	drivers/hwmon/lm95234.c
+
 LME2510 MEDIA DRIVER
 M:	Malcolm Priestley <tvboxspy@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -5509,18 +5524,18 @@
 F:	Documentation/networking/vxge.txt
 F:	drivers/net/ethernet/neterion/
 
-NETFILTER/IPTABLES/IPCHAINS
-P:	Harald Welte
-P:	Jozsef Kadlecsik
+NETFILTER/IPTABLES
 M:	Pablo Neira Ayuso <pablo@netfilter.org>
 M:	Patrick McHardy <kaber@trash.net>
+M:	Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
 L:	netfilter-devel@vger.kernel.org
 L:	netfilter@vger.kernel.org
 L:	coreteam@netfilter.org
 W:	http://www.netfilter.org/
 W:	http://www.iptables.org/
-T:	git git://1984.lsi.us.es/nf
-T:	git git://1984.lsi.us.es/nf-next
+Q:	http://patchwork.ozlabs.org/project/netfilter-devel/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git
 S:	Supported
 F:	include/linux/netfilter*
 F:	include/linux/netfilter/
@@ -6069,6 +6084,7 @@
 W:	http://www.parisc-linux.org/
 Q:	http://patchwork.kernel.org/project/linux-parisc/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/parisc-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
 S:	Maintained
 F:	arch/parisc/
 F:	drivers/parisc/
@@ -7854,7 +7870,7 @@
 L:	target-devel@vger.kernel.org
 L:	http://groups.google.com/group/linux-iscsi-target-dev
 W:	http://www.linux-iscsi.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/lio-core.git master
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
 S:	Supported
 F:	drivers/target/
 F:	include/target/
@@ -8182,6 +8198,13 @@
 F:	include/linux/mmc/tmio.h
 F:	include/linux/mmc/sh_mobile_sdhi.h
 
+TMP401 HARDWARE MONITOR DRIVER
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	lm-sensors@lm-sensors.org
+S:	Maintained
+F:	Documentation/hwmon/tmp401
+F:	drivers/hwmon/tmp401.c
+
 TMPFS (SHMEM FILESYSTEM)
 M:	Hugh Dickins <hughd@google.com>
 L:	linux-mm@kvack.org
diff --git a/Makefile b/Makefile
index cd11e88..93875f5 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index dd0e8eb..a4429bc 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -213,6 +213,9 @@
 config GENERIC_SMP_IDLE_THREAD
        bool
 
+config GENERIC_IDLE_POLL_SETUP
+       bool
+
 # Select if arch init_task initializer is different to init/init_task.c
 config ARCH_INIT_TASK
        bool
diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts
index c0fd362..0fa0d4a 100644
--- a/arch/arc/boot/dts/abilis_tb100_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts
@@ -37,7 +37,7 @@
 
 	soc100 {
 		uart@FF100000 {
-			pinctrl-names = "abilis,simple-default";
+			pinctrl-names = "default";
 			pinctrl-0 = <&pctl_uart0>;
 		};
 		ethernet@FE100000 {
diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts
index 6f8c381..a4d80ce 100644
--- a/arch/arc/boot/dts/abilis_tb101_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts
@@ -37,7 +37,7 @@
 
 	soc100 {
 		uart@FF100000 {
-			pinctrl-names = "abilis,simple-default";
+			pinctrl-names = "default";
 			pinctrl-0 = <&pctl_uart0>;
 		};
 		ethernet@FE100000 {
diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi
index a6139fc..b97e305 100644
--- a/arch/arc/boot/dts/abilis_tb10x.dtsi
+++ b/arch/arc/boot/dts/abilis_tb10x.dtsi
@@ -88,8 +88,7 @@
 		};
 
 		uart@FF100000 {
-			compatible = "snps,dw-apb-uart",
-					"abilis,simple-pinctrl";
+			compatible = "snps,dw-apb-uart";
 			reg = <0xFF100000 0x100>;
 			clock-frequency = <166666666>;
 			interrupts = <25 1>;
@@ -184,8 +183,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			cell-index = <1>;
-			compatible = "abilis,tb100-spi",
-					"abilis,simple-pinctrl";
+			compatible = "abilis,tb100-spi";
 			num-cs = <2>;
 			reg = <0xFE011000 0x20>;
 			interrupt-parent = <&tb10x_ictl>;
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index 9f841af..ef62682 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -93,14 +93,16 @@
 #endif
 }
 
-#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & 3)
+#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & 1)
 
 /*
  * checks if two addresses (after page aligning) index into same cache set
  */
 #define addr_not_cache_congruent(addr1, addr2)				\
+({									\
 	cache_is_vipt_aliasing() ? 					\
-		(CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0		\
+		(CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0;		\
+})
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 do {									\
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 374a355..ab84bf1 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -19,13 +19,6 @@
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
 #define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
 
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-
-#define clear_user_page(addr, vaddr, pg)	clear_page(addr)
-#define copy_user_page(vto, vfrom, vaddr, pg)	copy_page(vto, vfrom)
-
-#else	/* VIPT aliasing dcache */
-
 struct vm_area_struct;
 struct page;
 
@@ -35,8 +28,6 @@
 			unsigned long u_vaddr, struct vm_area_struct *vma);
 void clear_user_page(void *to, unsigned long u_vaddr, struct page *page);
 
-#endif	/* CONFIG_ARC_CACHE_VIPT_ALIASING */
-
 #undef STRICT_MM_TYPECHECKS
 
 #ifdef STRICT_MM_TYPECHECKS
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 1cc4720..95b1522 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -57,9 +57,9 @@
 
 #define _PAGE_ACCESSED      (1<<1)	/* Page is accessed (S) */
 #define _PAGE_CACHEABLE     (1<<2)	/* Page is cached (H) */
-#define _PAGE_EXECUTE       (1<<3)	/* Page has user execute perm (H) */
-#define _PAGE_WRITE         (1<<4)	/* Page has user write perm (H) */
-#define _PAGE_READ          (1<<5)	/* Page has user read perm (H) */
+#define _PAGE_U_EXECUTE     (1<<3)	/* Page has user execute perm (H) */
+#define _PAGE_U_WRITE       (1<<4)	/* Page has user write perm (H) */
+#define _PAGE_U_READ        (1<<5)	/* Page has user read perm (H) */
 #define _PAGE_K_EXECUTE     (1<<6)	/* Page has kernel execute perm (H) */
 #define _PAGE_K_WRITE       (1<<7)	/* Page has kernel write perm (H) */
 #define _PAGE_K_READ        (1<<8)	/* Page has kernel perm (H) */
@@ -72,9 +72,9 @@
 
 /* PD1 */
 #define _PAGE_CACHEABLE     (1<<0)	/* Page is cached (H) */
-#define _PAGE_EXECUTE       (1<<1)	/* Page has user execute perm (H) */
-#define _PAGE_WRITE         (1<<2)	/* Page has user write perm (H) */
-#define _PAGE_READ          (1<<3)	/* Page has user read perm (H) */
+#define _PAGE_U_EXECUTE     (1<<1)	/* Page has user execute perm (H) */
+#define _PAGE_U_WRITE       (1<<2)	/* Page has user write perm (H) */
+#define _PAGE_U_READ        (1<<3)	/* Page has user read perm (H) */
 #define _PAGE_K_EXECUTE     (1<<4)	/* Page has kernel execute perm (H) */
 #define _PAGE_K_WRITE       (1<<5)	/* Page has kernel write perm (H) */
 #define _PAGE_K_READ        (1<<6)	/* Page has kernel perm (H) */
@@ -93,7 +93,8 @@
 #endif
 
 /* Kernel allowed all permissions for all pages */
-#define _K_PAGE_PERMS  (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ)
+#define _K_PAGE_PERMS  (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ | \
+			_PAGE_GLOBAL | _PAGE_PRESENT)
 
 #ifdef CONFIG_ARC_CACHE_PAGES
 #define _PAGE_DEF_CACHEABLE _PAGE_CACHEABLE
@@ -106,7 +107,11 @@
  * -by default cached, unless config otherwise
  * -present in memory
  */
-#define ___DEF (_PAGE_PRESENT | _K_PAGE_PERMS | _PAGE_DEF_CACHEABLE)
+#define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE)
+
+#define _PAGE_READ	(_PAGE_U_READ    | _PAGE_K_READ)
+#define _PAGE_WRITE	(_PAGE_U_WRITE   | _PAGE_K_WRITE)
+#define _PAGE_EXECUTE	(_PAGE_U_EXECUTE | _PAGE_K_EXECUTE)
 
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED)
@@ -125,11 +130,10 @@
  * kernel vaddr space - visible in all addr spaces, but kernel mode only
  * Thus Global, all-kernel-access, no-user-access, cached
  */
-#define PAGE_KERNEL          __pgprot(___DEF | _PAGE_GLOBAL)
+#define PAGE_KERNEL          __pgprot(_K_PAGE_PERMS | _PAGE_DEF_CACHEABLE)
 
 /* ioremap */
-#define PAGE_KERNEL_NO_CACHE __pgprot(_PAGE_PRESENT | _K_PAGE_PERMS | \
-						     _PAGE_GLOBAL)
+#define PAGE_KERNEL_NO_CACHE __pgprot(_K_PAGE_PERMS)
 
 /**************************************************************************
  * Mapping of vm_flags (Generic VM) to PTE flags (arch specific)
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index 85b6df8..cb0c708 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -16,7 +16,7 @@
 /* Masks for actual TLB "PD"s */
 #define PTE_BITS_IN_PD0	(_PAGE_GLOBAL | _PAGE_PRESENT)
 #define PTE_BITS_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE | \
-			 _PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \
+			 _PAGE_U_EXECUTE | _PAGE_U_WRITE | _PAGE_U_READ | \
 			 _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 2f12bca..aedce19 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -610,7 +610,7 @@
 
 	local_irq_save(flags);
 	__ic_line_inv_vaddr(paddr, vaddr, len);
-	__dc_line_op(paddr, vaddr, len, OP_FLUSH);
+	__dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV);
 	local_irq_restore(flags);
 }
 
@@ -676,6 +676,17 @@
 	flush_cache_all();
 }
 
+void flush_anon_page(struct vm_area_struct *vma, struct page *page,
+		     unsigned long u_vaddr)
+{
+	/* TBD: do we really need to clear the kernel mapping */
+	__flush_dcache_page(page_address(page), u_vaddr);
+	__flush_dcache_page(page_address(page), page_address(page));
+
+}
+
+#endif
+
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long u_vaddr, struct vm_area_struct *vma)
 {
@@ -725,16 +736,6 @@
 	set_bit(PG_arch_1, &page->flags);
 }
 
-void flush_anon_page(struct vm_area_struct *vma, struct page *page,
-		     unsigned long u_vaddr)
-{
-	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
-
-}
-
-#endif
 
 /**********************************************************************
  * Explicit Cache flush request from user space via syscall
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 066145b..fe1c5a0 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -444,7 +444,8 @@
 	 *	       so userspace sees the right data.
 	 *  (Avoids the flush for Non-exec + congruent mapping case)
 	 */
-	if (vma->vm_flags & VM_EXEC || addr_not_cache_congruent(paddr, vaddr)) {
+	if ((vma->vm_flags & VM_EXEC) ||
+	     addr_not_cache_congruent(paddr, vaddr)) {
 		struct page *page = pfn_to_page(pte_pfn(*ptep));
 
 		int dirty = test_and_clear_bit(PG_arch_1, &page->flags);
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index 9df765d..3357d26 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -277,7 +277,7 @@
 	;----------------------------------------------------------------
 	; VERIFY_PTE: Check if PTE permissions approp for executing code
 	cmp_s   r2, VMALLOC_START
-	mov.lo  r2, (_PAGE_PRESENT | _PAGE_READ | _PAGE_EXECUTE)
+	mov.lo  r2, (_PAGE_PRESENT | _PAGE_U_READ | _PAGE_U_EXECUTE)
 	mov.hs  r2, (_PAGE_PRESENT | _PAGE_K_READ | _PAGE_K_EXECUTE)
 
 	and     r3, r0, r2  ; Mask out NON Flag bits from PTE
@@ -320,9 +320,9 @@
 	mov_s   r2, 0
 	lr      r3, [ecr]
 	btst_s  r3, ECR_C_BIT_DTLB_LD_MISS	; Read Access
-	or.nz   r2, r2, _PAGE_READ      	; chk for Read flag in PTE
+	or.nz   r2, r2, _PAGE_U_READ      	; chk for Read flag in PTE
 	btst_s  r3, ECR_C_BIT_DTLB_ST_MISS	; Write Access
-	or.nz   r2, r2, _PAGE_WRITE     	; chk for Write flag in PTE
+	or.nz   r2, r2, _PAGE_U_WRITE     	; chk for Write flag in PTE
 	; Above laddering takes care of XCHG access
 	;   which is both Read and Write
 
diff --git a/arch/arc/plat-tb10x/tb10x.c b/arch/arc/plat-tb10x/tb10x.c
index d356769..06cb309 100644
--- a/arch/arc/plat-tb10x/tb10x.c
+++ b/arch/arc/plat-tb10x/tb10x.c
@@ -34,31 +34,6 @@
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static void __init tb10x_platform_late_init(void)
-{
-	struct device_node *dn;
-
-	/*
-	 * Pinctrl documentation recommends setting up the iomux here for
-	 * all modules which don't require control over the pins themselves.
-	 * Modules which need this kind of assistance are compatible with
-	 * "abilis,simple-pinctrl", i.e. we can easily iterate over them.
-	 * TODO: Does this recommended method work cleanly with pins required
-	 * by modules?
-	 */
-	for_each_compatible_node(dn, NULL, "abilis,simple-pinctrl") {
-		struct platform_device *pd = of_find_device_by_node(dn);
-		struct pinctrl *pctl;
-
-		pctl = pinctrl_get_select(&pd->dev, "abilis,simple-default");
-		if (IS_ERR(pctl)) {
-			int ret = PTR_ERR(pctl);
-			dev_err(&pd->dev, "Could not set up pinctrl: %d\n",
-				ret);
-		}
-	}
-}
-
 static const char *tb10x_compat[] __initdata = {
 	"abilis,arc-tb10x",
 	NULL,
@@ -67,5 +42,4 @@
 MACHINE_START(TB10x, "tb10x")
 	.dt_compat	= tb10x_compat,
 	.init_machine	= tb10x_platform_init,
-	.init_late	= tb10x_platform_late_init,
 MACHINE_END
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d423d58..49d993c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -38,6 +38,7 @@
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_IDE if PCI || ISA || PCMCIA
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
@@ -488,7 +489,7 @@
 config ARCH_DOVE
 	bool "Marvell Dove"
 	select ARCH_REQUIRE_GPIOLIB
-	select CPU_V7
+	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
 	select MIGHT_HAVE_PCI
 	select PINCTRL
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4737408..1ba358b 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -309,7 +309,7 @@
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
   echo  '* xipImage      - XIP kernel image, if configured (arch/$(ARCH)/boot/xipImage)'
   echo  '  uImage        - U-Boot wrapped zImage'
-  echo  '  bootpImage    - Combined zImage and initial RAM disk' 
+  echo  '  bootpImage    - Combined zImage and initial RAM disk'
   echo  '                  (supply initrd image via make variable INITRD=<path>)'
   echo  '* dtbs          - Build device tree blobs for enabled boards'
   echo  '  install       - Install uncompressed kernel'
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index b9f7121..f0895c5 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -177,7 +177,9 @@
 	spear320-evb.dtb \
 	spear320-hmi.dtb
 dtb-$(CONFIG_ARCH_SPEAR6XX)+= spear600-evb.dtb
-dtb-$(CONFIG_ARCH_SUNXI) += sun4i-a10-cubieboard.dtb \
+dtb-$(CONFIG_ARCH_SUNXI) += \
+	sun4i-a10-cubieboard.dtb \
+	sun4i-a10-mini-xplus.dtb \
 	sun4i-a10-hackberry.dtb \
 	sun5i-a13-olinuxino.dtb
 dtb-$(CONFIG_ARCH_TEGRA) += tegra20-harmony.dtb \
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 272bbc6..550eb77 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -33,7 +33,8 @@
 		#size-cells = <1>;
 		compatible = "simple-bus";
 		interrupt-parent = <&mpic>;
-		ranges = <0 0 0xd0000000 0x100000>;
+		ranges = <0          0 0xd0000000 0x0100000 /* internal registers */
+			  0xe0000000 0 0xe0000000 0x8100000 /* PCIe */>;
 
 		internal-regs {
 			compatible = "simple-bus";
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index b2c1b5a..aee2b18 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -29,7 +29,8 @@
 	};
 
 	soc {
-		ranges = <0 0xd0000000 0x100000>;
+		ranges = <0          0xd0000000 0x0100000 /* internal registers */
+			  0xe0000000 0xe0000000 0x8100000 /* PCIe */>;
 		internal-regs {
 			system-controller@18200 {
 				compatible = "marvell,armada-370-xp-system-controller";
@@ -38,12 +39,12 @@
 
 			L2: l2-cache {
 				compatible = "marvell,aurora-outer-cache";
-				reg = <0xd0008000 0x1000>;
+				reg = <0x08000 0x1000>;
 				cache-id-part = <0x100>;
 				wt-override;
 			};
 
-			mpic: interrupt-controller@20000 {
+			interrupt-controller@20000 {
 				reg = <0x20a00 0x1d0>, <0x21870 0x58>;
 			};
 
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 26ad06f..3ee63d1 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -39,6 +39,9 @@
 	};
 
 	soc {
+		ranges = <0          0 0xd0000000 0x100000
+			  0xf0000000 0 0xf0000000 0x1000000>;
+
 		internal-regs {
 			serial@12000 {
 				clock-frequency = <250000000>;
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index f14d36c..46b7850 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -27,6 +27,9 @@
 	};
 
 	soc {
+		ranges = <0          0 0xd0000000 0x100000
+			  0xf0000000 0 0xf0000000 0x8000000>;
+
 		internal-regs {
 			serial@12000 {
 				clock-frequency = <250000000>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index bacab11..5b902f9 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -31,7 +31,7 @@
 				wt-override;
 			};
 
-			mpic: interrupt-controller@20000 {
+			interrupt-controller@20000 {
 			      reg = <0x20a00 0x2d0>, <0x21070 0x58>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index 70b5ccb..84c4bef 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -264,7 +264,7 @@
 						atmel,pins =
 							<0 10 0x2 0x0	/* PA10 periph B */
 							 0 11 0x2 0x0	/* PA11 periph B */
-							 0 24 0x2 0x0	/* PA24 periph B */
+							 0 22 0x2 0x0	/* PA22 periph B */
 							 0 25 0x2 0x0	/* PA25 periph B */
 							 0 26 0x2 0x0	/* PA26 periph B */
 							 0 27 0x2 0x0	/* PA27 periph B */
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 3de8e6d..8d25f88 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -57,6 +57,7 @@
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
 				reg = <0xfffff000 0x200>;
+				atmel,external-irqs = <31>;
 			};
 
 			ramc0: ramc@ffffe800 {
diff --git a/arch/arm/boot/dts/at91sam9x25ek.dts b/arch/arm/boot/dts/at91sam9x25ek.dts
index 3b40d11..315250b 100644
--- a/arch/arm/boot/dts/at91sam9x25ek.dts
+++ b/arch/arm/boot/dts/at91sam9x25ek.dts
@@ -11,7 +11,7 @@
 /include/ "at91sam9x5ek.dtsi"
 
 / {
-	model = "Atmel AT91SAM9G25-EK";
+	model = "Atmel AT91SAM9X25-EK";
 	compatible = "atmel,at91sam9x25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
 
 	ahb {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 82a404d..99ba6e1 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -516,7 +516,7 @@
 		usb_otg_hs: usb_otg_hs@480ab000 {
 			compatible = "ti,omap3-musb";
 			reg = <0x480ab000 0x1000>;
-			interrupts = <0 92 0x4>, <0 93 0x4>;
+			interrupts = <92>, <93>;
 			interrupt-names = "mc", "dma";
 			ti,hwmods = "usb_otg_hs";
 			multipoint = <1>;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 2e643ea..5000e0d 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -75,11 +75,6 @@
 				compatible = "atmel,at91sam9x5-spi";
 				reg = <0xf0004000 0x100>;
 				interrupts = <24 4 3>;
-				cs-gpios = <&pioD 13 0
-					    &pioD 14 0 /* conflicts with SCK0 and CANRX0 */
-					    &pioD 15 0 /* conflicts with CTS0 and CANTX0 */
-					    &pioD 16 0 /* conflicts with RTS0 and PWMFI3 */
-					   >;
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_spi0>;
 				status = "disabled";
@@ -156,7 +151,7 @@
 			};
 
 			macb0: ethernet@f0028000 {
-				compatible = "cnds,pc302-gem", "cdns,gem";
+				compatible = "cdns,pc302-gem", "cdns,gem";
 				reg = <0xf0028000 0x100>;
 				interrupts = <34 4 3>;
 				pinctrl-names = "default";
@@ -203,11 +198,6 @@
 				compatible = "atmel,at91sam9x5-spi";
 				reg = <0xf8008000 0x100>;
 				interrupts = <25 4 3>;
-				cs-gpios = <&pioC 25 0
-					    &pioC 26 0 /* conflitcs with TWD1 and ISI_D11 */
-					    &pioC 27 0 /* conflitcs with TWCK1 and ISI_D10 */
-					    &pioC 28 0 /* conflitcs with PWMFI0 and ISI_D9 */
-					   >;
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_spi1>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/sama5d3xcm.dtsi b/arch/arm/boot/dts/sama5d3xcm.dtsi
index 1f8ed40..b336e77 100644
--- a/arch/arm/boot/dts/sama5d3xcm.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm.dtsi
@@ -32,6 +32,10 @@
 
 	ahb {
 		apb {
+			spi0: spi@f0004000 {
+				cs-gpios = <&pioD 13 0>, <0>, <0>, <0>;
+			};
+
 			macb0: ethernet@f0028000 {
 				phy-mode = "rgmii";
 			};
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index b28fbf3..6f82d93 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -14,13 +14,19 @@
 		bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk";
 	};
 
+	/* This is where the interrupt is routed on the S8815 board */
+	external-bus@34000000 {
+		ethernet@300 {
+			interrupt-parent = <&gpio3>;
+			interrupts = <8 0x1>;
+		};
+	};
+
 	/* Custom board node with GPIO pins to active etc */
 	usb-s8815 {
 		/* The S8815 is using this very GPIO pin for the SMSC91x IRQs */
 		ethernet-gpio {
-			gpios = <&gpio3 19 0x1>;
-			interrupts = <19 0x1>;
-			interrupt-parent = <&gpio3>;
+			gpios = <&gpio3 8 0x1>;
 		};
 		/* This will bias the MMC/SD card detect line */
 		mmcsd-gpio {
diff --git a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
index 4a7c35d..078ed7f 100644
--- a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
+++ b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
@@ -22,8 +22,8 @@
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
 
-	soc {
-		uart0: uart@01c28000 {
+	soc@01c20000 {
+		uart0: serial@01c28000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&uart0_pins_a>;
 			status = "okay";
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 52b88d8..3caed0d 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -15,8 +15,6 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 
-#include <linux/irqchip/arm-gic.h>
-
 #include <asm/mcpm.h>
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
@@ -49,7 +47,6 @@
 static void __cpuinit mcpm_secondary_init(unsigned int cpu)
 {
 	mcpm_cpu_powered_up();
-	gic_secondary_init(0);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 7e0ebb6..9940f7b 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -199,7 +199,6 @@
 CONFIG_USB_DEBUG=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_MON=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index c1ef64b..abbe319 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -20,6 +20,7 @@
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_ARCH_MULTI_V6=y
 CONFIG_ARCH_OMAP2PLUS=y
 CONFIG_OMAP_RESET_CLOCKS=y
 CONFIG_OMAP_MUX_DEBUG=y
@@ -204,7 +205,6 @@
 CONFIG_USB_DEBUG=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_DEVICEFS=y
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_MON=y
 CONFIG_USB_WDM=y
 CONFIG_USB_STORAGE=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index a5f0485..f7ba3161 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -153,6 +153,7 @@
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
 CONFIG_DRM=y
+CONFIG_TEGRA_HOST1X=y
 CONFIG_DRM_TEGRA=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
@@ -202,7 +203,7 @@
 CONFIG_STAGING=y
 CONFIG_SENSORS_ISL29018=y
 CONFIG_SENSORS_ISL29028=y
-CONFIG_SENSORS_AK8975=y
+CONFIG_AK8975=y
 CONFIG_MFD_NVEC=y
 CONFIG_KEYBOARD_NVEC=y
 CONFIG_SERIO_NVEC_PS2=y
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index 92c6eed..99207c4 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -195,6 +195,7 @@
 	add	r3,r3,r10			@ E+=F_00_19(B,C,D)
 	cmp	r14,sp
 	bne	.L_00_15		@ [((11+4)*5+2)*3]
+	sub	sp,sp,#25*4
 #if __ARM_ARCH__<7
 	ldrb	r10,[r1,#2]
 	ldrb	r9,[r1,#3]
@@ -290,7 +291,6 @@
 	add	r3,r3,r10			@ E+=F_00_19(B,C,D)
 
 	ldr	r8,.LK_20_39		@ [+15+16*4]
-	sub	sp,sp,#25*4
 	cmn	sp,#0			@ [+3], clear carry to denote 20_39
 .L_20_39_or_60_79:
 	ldr	r9,[r14,#15*4]
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 7eb18c1..4f009c1 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -233,15 +233,15 @@
 	((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr),	\
 						atomic64_t,		\
 						counter),		\
-					      (unsigned long)(o),	\
-					      (unsigned long)(n)))
+					      (unsigned long long)(o),	\
+					      (unsigned long long)(n)))
 
 #define cmpxchg64_local(ptr, o, n)					\
 	((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr),	\
 						local64_t,		\
 						a),			\
-					     (unsigned long)(o),	\
-					     (unsigned long)(n)))
+					     (unsigned long long)(o),	\
+					     (unsigned long long)(n)))
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/debug/ux500.S b/arch/arm/include/debug/ux500.S
index 2848857..fbd24be 100644
--- a/arch/arm/include/debug/ux500.S
+++ b/arch/arm/include/debug/ux500.S
@@ -24,9 +24,9 @@
 #define U8500_UART0_PHYS_BASE	(0x80120000)
 #define U8500_UART1_PHYS_BASE	(0x80121000)
 #define U8500_UART2_PHYS_BASE	(0x80007000)
-#define U8500_UART0_VIRT_BASE	(0xa8120000)
-#define U8500_UART1_VIRT_BASE	(0xa8121000)
-#define U8500_UART2_VIRT_BASE	(0xa8007000)
+#define U8500_UART0_VIRT_BASE	(0xf8120000)
+#define U8500_UART1_VIRT_BASE	(0xf8121000)
+#define U8500_UART2_VIRT_BASE	(0xf8007000)
 #define __UX500_PHYS_UART(n)	U8500_UART##n##_PHYS_BASE
 #define __UX500_VIRT_UART(n)	U8500_UART##n##_VIRT_BASE
 #endif
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f219703..282de48 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -411,7 +411,6 @@
 	.vm_start	= 0xffff0000,
 	.vm_end		= 0xffff0000 + PAGE_SIZE,
 	.vm_flags	= VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC,
-	.vm_mm		= &init_mm,
 };
 
 static int __init gate_vma_init(void)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 47ab905..550d63c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -251,7 +251,7 @@
 	 * this returns, power and/or clocks can be removed at any point
 	 * from this CPU and its cache by platform_cpu_kill().
 	 */
-	RCU_NONIDLE(complete(&cpu_died));
+	complete(&cpu_died);
 
 	/*
 	 * Ensure that the cache lines associated with that completion are
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 2acdff4..180b302 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -174,6 +174,7 @@
 static struct clock_event_device clkevt = {
 	.name		= "at91_tick",
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.shift		= 32,
 	.rating		= 150,
 	.set_next_event	= clkevt32k_next_event,
 	.set_mode	= clkevt32k_mode,
@@ -264,9 +265,11 @@
 	at91_st_write(AT91_ST_RTMR, 1);
 
 	/* Setup timer clockevent, with minimum of two ticks (important!!) */
+	clkevt.mult = div_sc(AT91_SLOW_CLOCK, NSEC_PER_SEC, clkevt.shift);
+	clkevt.max_delta_ns = clockevent_delta2ns(AT91_ST_ALMV, &clkevt);
+	clkevt.min_delta_ns = clockevent_delta2ns(2, &clkevt) + 1;
 	clkevt.cpumask = cpumask_of(0);
-	clockevents_config_and_register(&clkevt, AT91_SLOW_CLOCK,
-					2, AT91_ST_ALMV);
+	clockevents_register_device(&clkevt);
 
 	/* register clocksource */
 	clocksource_register_hz(&clk32k, AT91_SLOW_CLOCK);
diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c
index 13cdbcd..c7d670d 100644
--- a/arch/arm/mach-at91/at91sam9n12.c
+++ b/arch/arm/mach-at91/at91sam9n12.c
@@ -223,13 +223,7 @@
 	at91_init_sram(0, AT91SAM9N12_SRAM_BASE, AT91SAM9N12_SRAM_SIZE);
 }
 
-void __init at91sam9n12_initialize(void)
-{
-	at91_extern_irq = (1 << AT91SAM9N12_ID_IRQ0);
-}
-
 AT91_SOC_START(at91sam9n12)
 	.map_io = at91sam9n12_map_io,
 	.register_clocks = at91sam9n12_register_clocks,
-	.init = at91sam9n12_initialize,
 AT91_SOC_END
diff --git a/arch/arm/mach-at91/include/mach/at91_pmc.h b/arch/arm/mach-at91/include/mach/at91_pmc.h
index 31df120..2bd7f51 100644
--- a/arch/arm/mach-at91/include/mach/at91_pmc.h
+++ b/arch/arm/mach-at91/include/mach/at91_pmc.h
@@ -179,9 +179,9 @@
 #define		AT91_PMC_PCR_CMD	(0x1  <<  12)		/* Command (read=0, write=1) */
 #define		AT91_PMC_PCR_DIV(n)	((n)  <<  16)		/* Divisor Value */
 #define			AT91_PMC_PCR_DIV0	0x0			/* Peripheral clock is MCK */
-#define			AT91_PMC_PCR_DIV2	0x2			/* Peripheral clock is MCK/2 */
-#define			AT91_PMC_PCR_DIV4	0x4			/* Peripheral clock is MCK/4 */
-#define			AT91_PMC_PCR_DIV8	0x8			/* Peripheral clock is MCK/8 */
+#define			AT91_PMC_PCR_DIV2	0x1			/* Peripheral clock is MCK/2 */
+#define			AT91_PMC_PCR_DIV4	0x2			/* Peripheral clock is MCK/4 */
+#define			AT91_PMC_PCR_DIV8	0x3			/* Peripheral clock is MCK/8 */
 #define		AT91_PMC_PCR_EN		(0x1  <<  28)		/* Enable */
 
 #endif
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 1512590..dda9a2b 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -177,7 +177,8 @@
 static const char *step_sels[]	= { "osc", "pll2_pfd2_396m", };
 static const char *pll1_sw_sels[]	= { "pll1_sys", "step", };
 static const char *periph_pre_sels[]	= { "pll2_bus", "pll2_pfd2_396m", "pll2_pfd0_352m", "pll2_198m", };
-static const char *periph_clk2_sels[]	= { "pll3_usb_otg", "osc", };
+static const char *periph_clk2_sels[]	= { "pll3_usb_otg", "osc", "osc", "dummy", };
+static const char *periph2_clk2_sels[]	= { "pll3_usb_otg", "pll2_bus", };
 static const char *periph_sels[]	= { "periph_pre", "periph_clk2", };
 static const char *periph2_sels[]	= { "periph2_pre", "periph2_clk2", };
 static const char *axi_sels[]		= { "periph", "pll2_pfd2_396m", "pll3_pfd1_540m", };
@@ -185,7 +186,7 @@
 static const char *gpu_axi_sels[]	= { "axi", "ahb", };
 static const char *gpu2d_core_sels[]	= { "axi", "pll3_usb_otg", "pll2_pfd0_352m", "pll2_pfd2_396m", };
 static const char *gpu3d_core_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", };
-static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", };
+static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll3_pfd0_720m", };
 static const char *ipu_sels[]		= { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
 static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
 static const char *ipu_di_pre_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video_div", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", };
@@ -369,8 +370,8 @@
 	clk[pll1_sw]          = imx_clk_mux("pll1_sw",	        base + 0xc,  2,  1, pll1_sw_sels,      ARRAY_SIZE(pll1_sw_sels));
 	clk[periph_pre]       = imx_clk_mux("periph_pre",       base + 0x18, 18, 2, periph_pre_sels,   ARRAY_SIZE(periph_pre_sels));
 	clk[periph2_pre]      = imx_clk_mux("periph2_pre",      base + 0x18, 21, 2, periph_pre_sels,   ARRAY_SIZE(periph_pre_sels));
-	clk[periph_clk2_sel]  = imx_clk_mux("periph_clk2_sel",  base + 0x18, 12, 1, periph_clk2_sels,  ARRAY_SIZE(periph_clk2_sels));
-	clk[periph2_clk2_sel] = imx_clk_mux("periph2_clk2_sel", base + 0x18, 20, 1, periph_clk2_sels,  ARRAY_SIZE(periph_clk2_sels));
+	clk[periph_clk2_sel]  = imx_clk_mux("periph_clk2_sel",  base + 0x18, 12, 2, periph_clk2_sels,  ARRAY_SIZE(periph_clk2_sels));
+	clk[periph2_clk2_sel] = imx_clk_mux("periph2_clk2_sel", base + 0x18, 20, 1, periph2_clk2_sels, ARRAY_SIZE(periph2_clk2_sels));
 	clk[axi_sel]          = imx_clk_mux("axi_sel",          base + 0x14, 6,  2, axi_sels,          ARRAY_SIZE(axi_sels));
 	clk[esai_sel]         = imx_clk_mux("esai_sel",         base + 0x20, 19, 2, audio_sels,        ARRAY_SIZE(audio_sels));
 	clk[asrc_sel]         = imx_clk_mux("asrc_sel",         base + 0x30, 7,  2, audio_sels,        ARRAY_SIZE(audio_sels));
@@ -498,7 +499,7 @@
 	clk[ldb_di1]      = imx_clk_gate2("ldb_di1",       "ldb_di1_podf",      base + 0x74, 14);
 	clk[ipu2_di1]     = imx_clk_gate2("ipu2_di1",      "ipu2_di1_sel",      base + 0x74, 10);
 	clk[hsi_tx]       = imx_clk_gate2("hsi_tx",        "hsi_tx_podf",       base + 0x74, 16);
-	clk[mlb]          = imx_clk_gate2("mlb",           "pll8_mlb",          base + 0x74, 18);
+	clk[mlb]          = imx_clk_gate2("mlb",           "axi",               base + 0x74, 18);
 	clk[mmdc_ch0_axi] = imx_clk_gate2("mmdc_ch0_axi",  "mmdc_ch0_axi_podf", base + 0x74, 20);
 	clk[mmdc_ch1_axi] = imx_clk_gate2("mmdc_ch1_axi",  "mmdc_ch1_axi_podf", base + 0x74, 22);
 	clk[ocram]        = imx_clk_gate2("ocram",         "ahb",               base + 0x74, 28);
diff --git a/arch/arm/mach-imx/headsmp.S b/arch/arm/mach-imx/headsmp.S
index 67b9c48..627f16f 100644
--- a/arch/arm/mach-imx/headsmp.S
+++ b/arch/arm/mach-imx/headsmp.S
@@ -18,8 +18,20 @@
 	.section ".text.head", "ax"
 
 #ifdef CONFIG_SMP
+diag_reg_offset:
+	.word	g_diag_reg - .
+
+	.macro	set_diag_reg
+	adr	r0, diag_reg_offset
+	ldr	r1, [r0]
+	add	r1, r1, r0		@ r1 = physical &g_diag_reg
+	ldr	r0, [r1]
+	mcr	p15, 0, r0, c15, c0, 1	@ write diagnostic register
+	.endm
+
 ENTRY(v7_secondary_startup)
 	bl	v7_invalidate_l1
+	set_diag_reg
 	b	secondary_startup
 ENDPROC(v7_secondary_startup)
 #endif
diff --git a/arch/arm/mach-imx/platsmp.c b/arch/arm/mach-imx/platsmp.c
index 4a69305..c6e1ab5 100644
--- a/arch/arm/mach-imx/platsmp.c
+++ b/arch/arm/mach-imx/platsmp.c
@@ -12,6 +12,7 @@
 
 #include <linux/init.h>
 #include <linux/smp.h>
+#include <asm/cacheflush.h>
 #include <asm/page.h>
 #include <asm/smp_scu.h>
 #include <asm/mach/map.h>
@@ -21,6 +22,7 @@
 
 #define SCU_STANDBY_ENABLE	(1 << 5)
 
+u32 g_diag_reg;
 static void __iomem *scu_base;
 
 static struct map_desc scu_io_desc __initdata = {
@@ -80,6 +82,18 @@
 static void __init imx_smp_prepare_cpus(unsigned int max_cpus)
 {
 	imx_smp_prepare();
+
+	/*
+	 * The diagnostic register holds the errata bits.  Mostly bootloader
+	 * does not bring up secondary cores, so that when errata bits are set
+	 * in bootloader, they are set only for boot cpu.  But on a SMP
+	 * configuration, it should be equally done on every single core.
+	 * Read the register from boot cpu here, and will replicate it into
+	 * secondary cores when booting them.
+	 */
+	asm("mrc p15, 0, %0, c15, c0, 1" : "=r" (g_diag_reg) : : "cc");
+	__cpuc_flush_dcache_area(&g_diag_reg, sizeof(g_diag_reg));
+	outer_clean_range(__pa(&g_diag_reg), __pa(&g_diag_reg + 1));
 }
 
 struct smp_operations  imx_smp_ops __initdata = {
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index c2cae69..f389228 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -528,12 +528,6 @@
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
 
-	/*
-	 * Some Kirkwood devices allocate their coherent buffers from atomic
-	 * context. Increase size of atomic coherent pool to make sure such
-	 * the allocations won't fail.
-	 */
-	init_dma_coherent_pool_size(SZ_1M);
 	mvebu_mbus_init("marvell,kirkwood-mbus",
 			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
 			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ);
diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c
index 283abff..e1267d6 100644
--- a/arch/arm/mach-kirkwood/ts219-setup.c
+++ b/arch/arm/mach-kirkwood/ts219-setup.c
@@ -124,7 +124,7 @@
 static int __init ts219_pci_init(void)
 {
 	if (machine_is_ts219())
-		kirkwood_pcie_init(KW_PCIE0);
+		kirkwood_pcie_init(KW_PCIE1 | KW_PCIE0);
 
 	return 0;
 }
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index e11acbb..80a8bca 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -15,6 +15,7 @@
 	select MVEBU_CLK_GATING
 	select MVEBU_MBUS
 	select ZONE_DMA if ARM_LPAE
+	select ARCH_REQUIRE_GPIOLIB
 
 if ARCH_MVEBU
 
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index 42a4cb3..1c48890 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -54,13 +54,6 @@
 	char *mbus_soc_name;
 
 	/*
-	 * Some Armada 370/XP devices allocate their coherent buffers
-	 * from atomic context. Increase size of atomic coherent pool
-	 * to make sure such the allocations won't fail.
-	 */
-	init_dma_coherent_pool_size(SZ_1M);
-
-	/*
 	 * This initialization will be replaced by a DT-based
 	 * initialization once the mvebu-mbus driver gains DT support.
 	 */
diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index 68ab858..a94b3a7 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -345,6 +345,7 @@
 		dev_err(&pdev->dev,
 			"%s: Memory allocation failed for d->chan!\n",
 			__func__);
+		ret = -ENOMEM;
 		goto exit_release_d;
 	}
 
diff --git a/arch/arm/mach-omap2/cclock33xx_data.c b/arch/arm/mach-omap2/cclock33xx_data.c
index 6ebc780..af3544c 100644
--- a/arch/arm/mach-omap2/cclock33xx_data.c
+++ b/arch/arm/mach-omap2/cclock33xx_data.c
@@ -454,9 +454,29 @@
  */
 DEFINE_CLK_FIXED_FACTOR(clkdiv32k_ck, "clk_24mhz", &clk_24mhz, 0x0, 1, 732);
 
-DEFINE_CLK_GATE(clkdiv32k_ick, "clkdiv32k_ck", &clkdiv32k_ck, 0x0,
-		AM33XX_CM_PER_CLKDIV32K_CLKCTRL, AM33XX_MODULEMODE_SWCTRL_SHIFT,
-		0x0, NULL);
+static struct clk clkdiv32k_ick;
+
+static const char *clkdiv32k_ick_parent_names[] = {
+	"clkdiv32k_ck",
+};
+
+static const struct clk_ops clkdiv32k_ick_ops = {
+	.enable         = &omap2_dflt_clk_enable,
+	.disable        = &omap2_dflt_clk_disable,
+	.is_enabled     = &omap2_dflt_clk_is_enabled,
+	.init           = &omap2_init_clk_clkdm,
+};
+
+static struct clk_hw_omap clkdiv32k_ick_hw = {
+	.hw	= {
+		.clk	= &clkdiv32k_ick,
+	},
+	.enable_reg	= AM33XX_CM_PER_CLKDIV32K_CLKCTRL,
+	.enable_bit	= AM33XX_MODULEMODE_SWCTRL_SHIFT,
+	.clkdm_name	= "clk_24mhz_clkdm",
+};
+
+DEFINE_STRUCT_CLK(clkdiv32k_ick, clkdiv32k_ick_parent_names, clkdiv32k_ick_ops);
 
 /* "usbotg_fck" is an additional clock and not really a modulemode */
 DEFINE_CLK_GATE(usbotg_fck, "dpll_per_ck", &dpll_per_ck, 0x0,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index d25a95f..7341eff 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1356,13 +1356,27 @@
 
 	clkdm = _get_clkdm(oh);
 	if (sf & SYSC_HAS_SIDLEMODE) {
+		if (oh->flags & HWMOD_SWSUP_SIDLE ||
+		    oh->flags & HWMOD_SWSUP_SIDLE_ACT) {
+			idlemode = HWMOD_IDLEMODE_NO;
+		} else {
+			if (sf & SYSC_HAS_ENAWAKEUP)
+				_enable_wakeup(oh, &v);
+			if (oh->class->sysc->idlemodes & SIDLE_SMART_WKUP)
+				idlemode = HWMOD_IDLEMODE_SMART_WKUP;
+			else
+				idlemode = HWMOD_IDLEMODE_SMART;
+		}
+
+		/*
+		 * This is special handling for some IPs like
+		 * 32k sync timer. Force them to idle!
+		 */
 		clkdm_act = (clkdm && clkdm->flags & CLKDM_ACTIVE_WITH_MPU);
 		if (clkdm_act && !(oh->class->sysc->idlemodes &
 				   (SIDLE_SMART | SIDLE_SMART_WKUP)))
 			idlemode = HWMOD_IDLEMODE_FORCE;
-		else
-			idlemode = (oh->flags & HWMOD_SWSUP_SIDLE) ?
-				HWMOD_IDLEMODE_NO : HWMOD_IDLEMODE_SMART;
+
 		_set_slave_idlemode(oh, idlemode, &v);
 	}
 
@@ -1391,10 +1405,6 @@
 	    (sf & SYSC_HAS_CLOCKACTIVITY))
 		_set_clockactivity(oh, oh->class->sysc->clockact, &v);
 
-	/* If slave is in SMARTIDLE, also enable wakeup */
-	if ((sf & SYSC_HAS_SIDLEMODE) && !(oh->flags & HWMOD_SWSUP_SIDLE))
-		_enable_wakeup(oh, &v);
-
 	_write_sysconfig(v, oh);
 
 	/*
@@ -1430,13 +1440,16 @@
 	sf = oh->class->sysc->sysc_flags;
 
 	if (sf & SYSC_HAS_SIDLEMODE) {
-		/* XXX What about HWMOD_IDLEMODE_SMART_WKUP? */
-		if (oh->flags & HWMOD_SWSUP_SIDLE ||
-		    !(oh->class->sysc->idlemodes &
-		      (SIDLE_SMART | SIDLE_SMART_WKUP)))
+		if (oh->flags & HWMOD_SWSUP_SIDLE) {
 			idlemode = HWMOD_IDLEMODE_FORCE;
-		else
-			idlemode = HWMOD_IDLEMODE_SMART;
+		} else {
+			if (sf & SYSC_HAS_ENAWAKEUP)
+				_enable_wakeup(oh, &v);
+			if (oh->class->sysc->idlemodes & SIDLE_SMART_WKUP)
+				idlemode = HWMOD_IDLEMODE_SMART_WKUP;
+			else
+				idlemode = HWMOD_IDLEMODE_SMART;
+		}
 		_set_slave_idlemode(oh, idlemode, &v);
 	}
 
@@ -1455,10 +1468,6 @@
 		_set_master_standbymode(oh, idlemode, &v);
 	}
 
-	/* If slave is in SMARTIDLE, also enable wakeup */
-	if ((sf & SYSC_HAS_SIDLEMODE) && !(oh->flags & HWMOD_SWSUP_SIDLE))
-		_enable_wakeup(oh, &v);
-
 	_write_sysconfig(v, oh);
 }
 
@@ -2065,7 +2074,7 @@
  * do so is present in the hwmod data, then call it and pass along the
  * return value; otherwise, return 0.
  */
-static int __init _enable_preprogram(struct omap_hwmod *oh)
+static int _enable_preprogram(struct omap_hwmod *oh)
 {
 	if (!oh->class->enable_preprogram)
 		return 0;
@@ -2246,42 +2255,6 @@
 }
 
 /**
- * omap_hwmod_set_ocp_autoidle - set the hwmod's OCP autoidle bit
- * @oh: struct omap_hwmod *
- * @autoidle: desired AUTOIDLE bitfield value (0 or 1)
- *
- * Sets the IP block's OCP autoidle bit in hardware, and updates our
- * local copy. Intended to be used by drivers that require
- * direct manipulation of the AUTOIDLE bits.
- * Returns -EINVAL if @oh is null or is not in the ENABLED state, or passes
- * along the return value from _set_module_autoidle().
- *
- * Any users of this function should be scrutinized carefully.
- */
-int omap_hwmod_set_ocp_autoidle(struct omap_hwmod *oh, u8 autoidle)
-{
-	u32 v;
-	int retval = 0;
-	unsigned long flags;
-
-	if (!oh || oh->_state != _HWMOD_STATE_ENABLED)
-		return -EINVAL;
-
-	spin_lock_irqsave(&oh->_lock, flags);
-
-	v = oh->_sysc_cache;
-
-	retval = _set_module_autoidle(oh, autoidle, &v);
-
-	if (!retval)
-		_write_sysconfig(v, oh);
-
-	spin_unlock_irqrestore(&oh->_lock, flags);
-
-	return retval;
-}
-
-/**
  * _shutdown - shutdown an omap_hwmod
  * @oh: struct omap_hwmod *
  *
@@ -3180,38 +3153,6 @@
 }
 
 /**
- * omap_hwmod_set_slave_idlemode - set the hwmod's OCP slave idlemode
- * @oh: struct omap_hwmod *
- * @idlemode: SIDLEMODE field bits (shifted to bit 0)
- *
- * Sets the IP block's OCP slave idlemode in hardware, and updates our
- * local copy.  Intended to be used by drivers that have some erratum
- * that requires direct manipulation of the SIDLEMODE bits.  Returns
- * -EINVAL if @oh is null, or passes along the return value from
- * _set_slave_idlemode().
- *
- * XXX Does this function have any current users?  If not, we should
- * remove it; it is better to let the rest of the hwmod code handle this.
- * Any users of this function should be scrutinized carefully.
- */
-int omap_hwmod_set_slave_idlemode(struct omap_hwmod *oh, u8 idlemode)
-{
-	u32 v;
-	int retval = 0;
-
-	if (!oh)
-		return -EINVAL;
-
-	v = oh->_sysc_cache;
-
-	retval = _set_slave_idlemode(oh, idlemode, &v);
-	if (!retval)
-		_write_sysconfig(v, oh);
-
-	return retval;
-}
-
-/**
  * omap_hwmod_lookup - look up a registered omap_hwmod by name
  * @name: name of the omap_hwmod to look up
  *
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index fe59629..0c898f5 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -463,6 +463,9 @@
  *     is kept in force-standby mode. Failing to do so causes PM problems
  *     with musb on OMAP3630 at least. Note that musb has a dedicated register
  *     to control MSTANDBY signal when MIDLEMODE is set to force-standby.
+ * HWMOD_SWSUP_SIDLE_ACT: omap_hwmod code should manually bring the module
+ *     out of idle, but rely on smart-idle to the put it back in idle,
+ *     so the wakeups are still functional (Only known case for now is UART)
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -476,6 +479,7 @@
 #define HWMOD_EXT_OPT_MAIN_CLK			(1 << 9)
 #define HWMOD_BLOCK_WFI				(1 << 10)
 #define HWMOD_FORCE_MSTANDBY			(1 << 11)
+#define HWMOD_SWSUP_SIDLE_ACT			(1 << 12)
 
 /*
  * omap_hwmod._int_flags definitions
@@ -641,9 +645,6 @@
 int omap_hwmod_enable_clocks(struct omap_hwmod *oh);
 int omap_hwmod_disable_clocks(struct omap_hwmod *oh);
 
-int omap_hwmod_set_slave_idlemode(struct omap_hwmod *oh, u8 idlemode);
-int omap_hwmod_set_ocp_autoidle(struct omap_hwmod *oh, u8 autoidle);
-
 int omap_hwmod_reset(struct omap_hwmod *oh);
 void omap_hwmod_ocp_barrier(struct omap_hwmod *oh);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index c8c64b3..d05fc7b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -512,6 +512,7 @@
 	.mpu_irqs	= omap2_uart1_mpu_irqs,
 	.sdma_reqs	= omap2_uart1_sdma_reqs,
 	.main_clk	= "uart1_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -531,6 +532,7 @@
 	.mpu_irqs	= omap2_uart2_mpu_irqs,
 	.sdma_reqs	= omap2_uart2_sdma_reqs,
 	.main_clk	= "uart2_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -550,6 +552,7 @@
 	.mpu_irqs	= omap2_uart3_mpu_irqs,
 	.sdma_reqs	= omap2_uart3_sdma_reqs,
 	.main_clk	= "uart3_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 01d8f32..075f7cc 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -1995,6 +1995,7 @@
 	.name		= "uart1",
 	.class		= &uart_class,
 	.clkdm_name	= "l4_wkup_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart1_irqs,
 	.sdma_reqs	= uart1_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_wkupdm_ck",
@@ -2015,6 +2016,7 @@
 	.name		= "uart2",
 	.class		= &uart_class,
 	.clkdm_name	= "l4ls_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart2_irqs,
 	.sdma_reqs	= uart1_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
@@ -2042,6 +2044,7 @@
 	.name		= "uart3",
 	.class		= &uart_class,
 	.clkdm_name	= "l4ls_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart3_irqs,
 	.sdma_reqs	= uart3_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
@@ -2062,6 +2065,7 @@
 	.name		= "uart4",
 	.class		= &uart_class,
 	.clkdm_name	= "l4ls_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart4_irqs,
 	.sdma_reqs	= uart1_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
@@ -2082,6 +2086,7 @@
 	.name		= "uart5",
 	.class		= &uart_class,
 	.clkdm_name	= "l4ls_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart5_irqs,
 	.sdma_reqs	= uart1_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
@@ -2102,6 +2107,7 @@
 	.name		= "uart6",
 	.class		= &uart_class,
 	.clkdm_name	= "l4ls_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= am33xx_uart6_irqs,
 	.sdma_reqs	= uart1_edma_reqs,
 	.main_clk	= "dpll_per_m2_div4_ck",
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 4083606..31c7126 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -490,6 +490,7 @@
 	.mpu_irqs	= omap2_uart1_mpu_irqs,
 	.sdma_reqs	= omap2_uart1_sdma_reqs,
 	.main_clk	= "uart1_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -508,6 +509,7 @@
 	.mpu_irqs	= omap2_uart2_mpu_irqs,
 	.sdma_reqs	= omap2_uart2_sdma_reqs,
 	.main_clk	= "uart2_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = CORE_MOD,
@@ -526,6 +528,7 @@
 	.mpu_irqs	= omap2_uart3_mpu_irqs,
 	.sdma_reqs	= omap2_uart3_sdma_reqs,
 	.main_clk	= "uart3_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
@@ -555,6 +558,7 @@
 	.mpu_irqs	= uart4_mpu_irqs,
 	.sdma_reqs	= uart4_sdma_reqs,
 	.main_clk	= "uart4_fck",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.prcm		= {
 		.omap2 = {
 			.module_offs = OMAP3430_PER_MOD,
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index eaba9dc..848b6dc 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -3434,6 +3434,7 @@
 	.name		= "uart1",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= omap44xx_uart1_irqs,
 	.sdma_reqs	= omap44xx_uart1_sdma_reqs,
 	.main_clk	= "func_48m_fclk",
@@ -3462,6 +3463,7 @@
 	.name		= "uart2",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= omap44xx_uart2_irqs,
 	.sdma_reqs	= omap44xx_uart2_sdma_reqs,
 	.main_clk	= "func_48m_fclk",
@@ -3490,7 +3492,8 @@
 	.name		= "uart3",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
-	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET,
+	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET |
+				HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= omap44xx_uart3_irqs,
 	.sdma_reqs	= omap44xx_uart3_sdma_reqs,
 	.main_clk	= "func_48m_fclk",
@@ -3519,6 +3522,7 @@
 	.name		= "uart4",
 	.class		= &omap44xx_uart_hwmod_class,
 	.clkdm_name	= "l4_per_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
 	.mpu_irqs	= omap44xx_uart4_irqs,
 	.sdma_reqs	= omap44xx_uart4_sdma_reqs,
 	.main_clk	= "func_48m_fclk",
diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index 8396b5b..f660156 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -95,38 +95,9 @@
 		omap_hwmod_disable_wakeup(od->hwmods[0]);
 }
 
-/*
- * Errata i291: [UART]:Cannot Acknowledge Idle Requests
- * in Smartidle Mode When Configured for DMA Operations.
- * WA: configure uart in force idle mode.
- */
-static void omap_uart_set_noidle(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct omap_device *od = to_omap_device(pdev);
-
-	omap_hwmod_set_slave_idlemode(od->hwmods[0], HWMOD_IDLEMODE_NO);
-}
-
-static void omap_uart_set_smartidle(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct omap_device *od = to_omap_device(pdev);
-	u8 idlemode;
-
-	if (od->hwmods[0]->class->sysc->idlemodes & SIDLE_SMART_WKUP)
-		idlemode = HWMOD_IDLEMODE_SMART_WKUP;
-	else
-		idlemode = HWMOD_IDLEMODE_SMART;
-
-	omap_hwmod_set_slave_idlemode(od->hwmods[0], idlemode);
-}
-
 #else
 static void omap_uart_enable_wakeup(struct device *dev, bool enable)
 {}
-static void omap_uart_set_noidle(struct device *dev) {}
-static void omap_uart_set_smartidle(struct device *dev) {}
 #endif /* CONFIG_PM */
 
 #ifdef CONFIG_OMAP_MUX
@@ -299,8 +270,6 @@
 	omap_up.uartclk = OMAP24XX_BASE_BAUD * 16;
 	omap_up.flags = UPF_BOOT_AUTOCONF;
 	omap_up.get_context_loss_count = omap_pm_get_dev_context_loss_count;
-	omap_up.set_forceidle = omap_uart_set_smartidle;
-	omap_up.set_noidle = omap_uart_set_noidle;
 	omap_up.enable_wakeup = omap_uart_enable_wakeup;
 	omap_up.dma_rx_buf_size = info->dma_rx_buf_size;
 	omap_up.dma_rx_timeout = info->dma_rx_timeout;
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index b97fd67..f8a6db9 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -199,13 +199,6 @@
 
 	orion_time_set_base(TIMER_VIRT_BASE);
 
-	/*
-	 * Some Orion5x devices allocate their coherent buffers from atomic
-	 * context. Increase size of atomic coherent pool to make sure such
-	 * the allocations won't fail.
-	 */
-	init_dma_coherent_pool_size(SZ_1M);
-
 	/* Initialize the MBUS driver */
 	orion5x_pcie_id(&dev, &rev);
 	if (dev == MV88F5281_DEV_ID)
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index 9105285..b9594e9 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -212,8 +212,8 @@
 static struct usb_phy *phy;
 static int usb_power_on(struct platform_device *pdev)
 {
-	if (!phy)
-		return -EIO;
+	if (IS_ERR(phy))
+		return PTR_ERR(phy);
 
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
@@ -225,7 +225,7 @@
 
 static void usb_power_off(struct platform_device *pdev)
 {
-	if (!phy)
+	if (IS_ERR(phy))
 		return;
 
 	usb_phy_shutdown(phy);
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index d259c78..5b045e3 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -1,5 +1,6 @@
 config ARCH_SUNXI
 	bool "Allwinner A1X SOCs" if ARCH_MULTI_V7
+	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	select COMMON_CLK
diff --git a/arch/arm/mach-tegra/tegra2_emc.c b/arch/arm/mach-tegra/tegra2_emc.c
index 9e8bdfa..31e69a0 100644
--- a/arch/arm/mach-tegra/tegra2_emc.c
+++ b/arch/arm/mach-tegra/tegra2_emc.c
@@ -307,11 +307,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "missing register base\n");
-		return -ENOMEM;
-	}
-
 	emc_regbase = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(emc_regbase))
 		return PTR_ERR(emc_regbase);
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 6a4387e..b19b072 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -51,6 +51,7 @@
 	bool "U8500 Development platform, MOP500 versions"
 	select I2C
 	select I2C_NOMADIK
+	select REGULATOR
 	select REGULATOR_FIXED_VOLTAGE
 	select SOC_BUS
 	select UX500_SOC_DB8500
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 3cd555a..78389de 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -623,7 +623,7 @@
 	sdi0_reg_info.gpios[0].gpio = GPIO_SDMMC_1V8_3V_SEL;
 
 	mop500_pinmaps_init();
-	parent = u8500_init_devices(&ab8500_platdata);
+	parent = u8500_init_devices();
 
 	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
 		mop500_platform_devs[i]->dev.parent = parent;
@@ -660,7 +660,7 @@
 	sdi0_reg_info.gpios[0].gpio = SNOWBALL_SDMMC_1V8_3V_GPIO;
 
 	snowball_pinmaps_init();
-	parent = u8500_init_devices(&ab8500_platdata);
+	parent = u8500_init_devices();
 
 	for (i = 0; i < ARRAY_SIZE(snowball_platform_devs); i++)
 		snowball_platform_devs[i]->dev.parent = parent;
@@ -698,7 +698,7 @@
 	sdi0_reg_info.gpios[0].gpio = HREFV60_SDMMC_1V8_3V_GPIO;
 
 	hrefv60_pinmaps_init();
-	parent = u8500_init_devices(&ab8500_platdata);
+	parent = u8500_init_devices();
 
 	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
 		mop500_platform_devs[i]->dev.parent = parent;
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index e90b5ab..46cca52 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -206,7 +206,7 @@
 /*
  * This function is called from the board init
  */
-struct device * __init u8500_init_devices(struct ab8500_platform_data *ab8500)
+struct device * __init u8500_init_devices(void)
 {
 	struct device *parent;
 	int i;
@@ -220,8 +220,6 @@
 	for (i = 0; i < ARRAY_SIZE(platform_devs); i++)
 		platform_devs[i]->dev.parent = parent;
 
-	db8500_prcmu_device.dev.platform_data = ab8500;
-
 	platform_add_devices(platform_devs, ARRAY_SIZE(platform_devs));
 
 	return parent;
@@ -278,7 +276,7 @@
 	OF_DEV_AUXDATA("st,nomadik-i2c", 0x8012a000, "nmk-i2c.4", NULL),
 	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu",
 			&db8500_prcmu_pdata),
-	OF_DEV_AUXDATA("smsc,lan9115", 0x50000000, "smsc911x", NULL),
+	OF_DEV_AUXDATA("smsc,lan9115", 0x50000000, "smsc911x.0", NULL),
 	/* Requires device name bindings. */
 	OF_DEV_AUXDATA("stericsson,nmk-pinctrl", U8500_PRCMU_BASE,
 		"pinctrl-db8500", NULL),
diff --git a/arch/arm/mach-ux500/setup.h b/arch/arm/mach-ux500/setup.h
index bddce2b..cad3ca8 100644
--- a/arch/arm/mach-ux500/setup.h
+++ b/arch/arm/mach-ux500/setup.h
@@ -18,7 +18,7 @@
 void __init ux500_map_io(void);
 extern void __init u8500_map_io(void);
 
-extern struct device * __init u8500_init_devices(struct ab8500_platform_data *ab8500);
+extern struct device * __init u8500_init_devices(void);
 
 extern void __init ux500_init_irq(void);
 extern void __init ux500_init_late(void);
diff --git a/arch/arm/mach-vt8500/vt8500.c b/arch/arm/mach-vt8500/vt8500.c
index 1dd281e..f5c33df 100644
--- a/arch/arm/mach-vt8500/vt8500.c
+++ b/arch/arm/mach-vt8500/vt8500.c
@@ -173,6 +173,7 @@
 	"wm,wm8505",
 	"wm,wm8750",
 	"wm,wm8850",
+	NULL
 };
 
 DT_MACHINE_START(WMT_DT, "VIA/Wondermedia SoC (Device Tree Support)")
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 251f827..c019b7a 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -383,7 +383,7 @@
 
 static struct platform_device orion_ge10_shared = {
 	.name		= MV643XX_ETH_SHARED_NAME,
-	.id		= 1,
+	.id		= 2,
 	.dev		= {
 		.platform_data	= &orion_ge10_shared_data,
 	},
@@ -398,8 +398,8 @@
 
 static struct platform_device orion_ge10 = {
 	.name		= MV643XX_ETH_NAME,
-	.id		= 1,
-	.num_resources	= 2,
+	.id		= 2,
+	.num_resources	= 1,
 	.resource	= orion_ge10_resources,
 	.dev		= {
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
@@ -432,7 +432,7 @@
 
 static struct platform_device orion_ge11_shared = {
 	.name		= MV643XX_ETH_SHARED_NAME,
-	.id		= 1,
+	.id		= 3,
 	.dev		= {
 		.platform_data	= &orion_ge11_shared_data,
 	},
@@ -447,8 +447,8 @@
 
 static struct platform_device orion_ge11 = {
 	.name		= MV643XX_ETH_NAME,
-	.id		= 1,
-	.num_resources	= 2,
+	.id		= 3,
+	.num_resources	= 1,
 	.resource	= orion_ge11_resources,
 	.dev		= {
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
diff --git a/arch/arm/plat-orion/include/plat/common.h b/arch/arm/plat-orion/include/plat/common.h
index e06fc5f..d9a24f6 100644
--- a/arch/arm/plat-orion/include/plat/common.h
+++ b/arch/arm/plat-orion/include/plat/common.h
@@ -10,6 +10,7 @@
 
 #ifndef __PLAT_COMMON_H
 #include <linux/mv643xx_eth.h>
+#include <linux/platform_data/usb-ehci-orion.h>
 
 struct dsa_platform_data;
 struct mv_sata_platform_data;
diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c
index ca07cb1..79690f2 100644
--- a/arch/arm/plat-samsung/adc.c
+++ b/arch/arm/plat-samsung/adc.c
@@ -381,11 +381,6 @@
 	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs) {
-		dev_err(dev, "failed to find registers\n");
-		return -ENXIO;
-	}
-
 	adc->regs = devm_ioremap_resource(dev, regs);
 	if (IS_ERR(adc->regs))
 		return PTR_ERR(adc->regs);
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index 323ce1a..46e1749 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -60,7 +60,7 @@
 	str	r11, [r10, #TI_PREEMPT]
 #endif
 	ldr	r0, VFP_arch_address
-	str	r5, [r0]		@ known non-zero value
+	str	r0, [r0]		@ set to non-zero value
 	mov	pc, r9			@ we have handled the fault
 ENDPROC(vfp_testing_entry)
 
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index d30042e..13609e0 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -152,11 +152,12 @@
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
 
-static int __init xen_secondary_init(unsigned int cpu)
+static void __init xen_percpu_init(void *unused)
 {
 	struct vcpu_register_vcpu_info info;
 	struct vcpu_info *vcpup;
 	int err;
+	int cpu = get_cpu();
 
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
@@ -165,14 +166,10 @@
 	info.offset = offset_in_page(vcpup);
 
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
-	if (err) {
-		pr_debug("register_vcpu_info failed: err=%d\n", err);
-	} else {
-		/* This cpu is using the registered vcpu info, even if
-		   later ones fail to. */
-		per_cpu(xen_vcpu, cpu) = vcpup;
-	}
-	return 0;
+	BUG_ON(err);
+	per_cpu(xen_vcpu, cpu) = vcpup;
+
+	enable_percpu_irq(xen_events_irq, 0);
 }
 
 static void xen_restart(char str, const char *cmd)
@@ -208,7 +205,6 @@
 	const char *version = NULL;
 	const char *xen_prefix = "xen,xen-";
 	struct resource res;
-	int i;
 
 	node = of_find_compatible_node(NULL, NULL, "xen,xen");
 	if (!node) {
@@ -265,19 +261,23 @@
 			                       sizeof(struct vcpu_info));
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
-	for_each_online_cpu(i)
-		xen_secondary_init(i);
 
 	gnttab_init();
 	if (!xen_initial_domain())
 		xenbus_probe(NULL);
 
+	return 0;
+}
+core_initcall(xen_guest_init);
+
+static int __init xen_pm_init(void)
+{
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
 
 	return 0;
 }
-core_initcall(xen_guest_init);
+subsys_initcall(xen_pm_init);
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
@@ -285,11 +285,6 @@
 	return IRQ_HANDLED;
 }
 
-static __init void xen_percpu_enable_events(void *unused)
-{
-	enable_percpu_irq(xen_events_irq, 0);
-}
-
 static int __init xen_init_events(void)
 {
 	if (!xen_domain() || xen_events_irq < 0)
@@ -303,7 +298,7 @@
 		return -EINVAL;
 	}
 
-	on_each_cpu(xen_percpu_enable_events, NULL, 0);
+	on_each_cpu(xen_percpu_init, NULL, 0);
 
 	return 0;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 48347dc..56b3f6d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -122,8 +122,6 @@
 
 menu "Kernel Features"
 
-source "kernel/time/Kconfig"
-
 config ARM64_64K_PAGES
 	bool "Enable 64KB pages support"
 	help
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index c8eedc6..5aceb83 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -82,7 +82,7 @@
 
 	.macro	enable_dbg_if_not_stepping, tmp
 	mrs	\tmp, mdscr_el1
-	tbnz	\tmp, #1, 9990f
+	tbnz	\tmp, #0, 9990f
 	enable_dbg
 9990:
 	.endm
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 0c3ba9f..f4726dc 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -136,8 +136,6 @@
  */
 static void clear_os_lock(void *unused)
 {
-	asm volatile("msr mdscr_el1, %0" : : "r" (0));
-	isb();
 	asm volatile("msr oslar_el1, %0" : : "r" (0));
 	isb();
 }
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
index ac974f4..fbb6e18 100644
--- a/arch/arm64/kernel/early_printk.c
+++ b/arch/arm64/kernel/early_printk.c
@@ -95,7 +95,7 @@
 	}
 }
 
-static struct console early_console = {
+static struct console early_console_dev = {
 	.name =		"earlycon",
 	.write =	early_write,
 	.flags =	CON_PRINTBUFFER | CON_BOOT,
@@ -145,7 +145,8 @@
 		early_base = early_io_map(paddr, EARLYCON_IOBASE);
 
 	printch = match->printch;
-	register_console(&early_console);
+	early_console = &early_console_dev;
+	register_console(&early_console_dev);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 6a9a532..add6ea6 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -282,12 +282,13 @@
 #endif
 }
 
-static int __init arm64_of_clk_init(void)
+static int __init arm64_device_init(void)
 {
 	of_clk_init(NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
-arch_initcall(arm64_of_clk_init);
+arch_initcall(arm64_device_init);
 
 static DEFINE_PER_CPU(struct cpu, cpu_data);
 
@@ -305,13 +306,6 @@
 }
 subsys_initcall(topology_init);
 
-static int __init arm64_device_probe(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	return 0;
-}
-device_initcall(arm64_device_probe);
-
 static const char *hwcap_str[] = {
 	"fp",
 	"asimd",
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index abe69b8..48a3860 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -52,7 +52,7 @@
 	add	x2, x2, #4			// add 4 (line length offset)
 	mov	x4, #0x3ff
 	and	x4, x4, x1, lsr #3		// find maximum number on the way size
-	clz	x5, x4				// find bit position of way size increment
+	clz	w5, w4				// find bit position of way size increment
 	mov	x7, #0x7fff
 	and	x7, x7, x1, lsr #13		// extract max number of the index size
 loop2:
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index f1d8b9b..a82ae88 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -119,8 +119,7 @@
 
 	mov	x0, #3 << 20
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
-	mov	x0, #1
-	msr	oslar_el1, x0			// Set the debug OS lock
+	msr	mdscr_el1, xzr			// Reset mdscr_el1
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	/*
 	 * Memory region attributes for LPAE:
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index bdc3558..549903c 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -205,6 +205,11 @@
 config ARCH_SPARSEMEM_ENABLE
 	def_bool n
 
+config NODES_SHIFT
+	int
+	default "2"
+	depends on NEED_MULTIPLE_NODES
+
 source "mm/Kconfig"
 
 config OWNERSHIP_TRACE
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 4dd4f78..d22af85 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y	+= clkdev.h
 generic-y	+= exec.h
 generic-y	+= trace_clock.h
+generic-y	+= param.h
diff --git a/arch/avr32/include/asm/numnodes.h b/arch/avr32/include/asm/numnodes.h
deleted file mode 100644
index 0b864d7..0000000
--- a/arch/avr32/include/asm/numnodes.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_AVR32_NUMNODES_H
-#define __ASM_AVR32_NUMNODES_H
-
-/* Max 4 nodes */
-#define NODES_SHIFT	2
-
-#endif /* __ASM_AVR32_NUMNODES_H */
diff --git a/arch/avr32/include/asm/param.h b/arch/avr32/include/asm/param.h
deleted file mode 100644
index 009a167..0000000
--- a/arch/avr32/include/asm/param.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_AVR32_PARAM_H
-#define __ASM_AVR32_PARAM_H
-
-#include <uapi/asm/param.h>
-
-# define HZ		CONFIG_HZ
-# define USER_HZ	100		/* User interfaces are in "ticks" */
-# define CLOCKS_PER_SEC	(USER_HZ)	/* frequency at which times() counts */
-#endif /* __ASM_AVR32_PARAM_H */
diff --git a/arch/avr32/include/uapi/asm/Kbuild b/arch/avr32/include/uapi/asm/Kbuild
index df53e7a..3b85ead 100644
--- a/arch/avr32/include/uapi/asm/Kbuild
+++ b/arch/avr32/include/uapi/asm/Kbuild
@@ -33,3 +33,4 @@
 header-y += termios.h
 header-y += types.h
 header-y += unistd.h
+generic-y += param.h
diff --git a/arch/avr32/include/uapi/asm/param.h b/arch/avr32/include/uapi/asm/param.h
deleted file mode 100644
index d28aa5e..0000000
--- a/arch/avr32/include/uapi/asm/param.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef _UAPI__ASM_AVR32_PARAM_H
-#define _UAPI__ASM_AVR32_PARAM_H
-
-
-#ifndef HZ
-# define HZ		100
-#endif
-
-/* TODO: Should be configurable */
-#define EXEC_PAGESIZE	4096
-
-#ifndef NOGROUP
-# define NOGROUP	(-1)
-#endif
-
-#define MAXHOSTNAMELEN	64
-
-#endif /* _UAPI__ASM_AVR32_PARAM_H */
diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
index 596f730..2c94129 100644
--- a/arch/avr32/kernel/module.c
+++ b/arch/avr32/kernel/module.c
@@ -264,7 +264,7 @@
 			break;
 		case R_AVR32_GOT18SW:
 			if ((relocation & 0xfffe0003) != 0
-			    && (relocation & 0xfffc0003) != 0xffff0000)
+			    && (relocation & 0xfffc0000) != 0xfffc0000)
 				return reloc_overflow(module, "R_AVR32_GOT18SW",
 						     relocation);
 			relocation >>= 2;
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index cb0f6af..9edc35f 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -31,6 +31,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c-gpio.h>
 #include <asm/bootinfo.h>
+#include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <prom.h>
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index 38afb11..93fa586 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -36,6 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 
+#include <asm/idle.h>
 #include <asm/processor.h>
 #include <asm/time.h>
 #include <asm/mach-au1x00/au1000.h>
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index a0233a2..8be4e85 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -19,6 +19,7 @@
 #include <linux/clk.h>
 
 #include <asm/bootinfo.h>
+#include <asm/idle.h>
 #include <asm/time.h>		/* for mips_hpt_frequency */
 #include <asm/reboot.h>		/* for _machine_{restart,halt} */
 #include <asm/mips_machine.h>
diff --git a/arch/mips/cobalt/reset.c b/arch/mips/cobalt/reset.c
index 516b442..4eedd48 100644
--- a/arch/mips/cobalt/reset.c
+++ b/arch/mips/cobalt/reset.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/leds.h>
 
+#include <asm/idle.h>
 #include <asm/processor.h>
 
 #include <cobalt.h>
diff --git a/arch/mips/configs/db1000_defconfig b/arch/mips/configs/db1000_defconfig
index face9d2..bac26b9 100644
--- a/arch/mips/configs/db1000_defconfig
+++ b/arch/mips/configs/db1000_defconfig
@@ -228,7 +228,6 @@
 CONFIG_USB_HID=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB=y
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
diff --git a/arch/mips/configs/db1235_defconfig b/arch/mips/configs/db1235_defconfig
index 14752dd..e2b4ad5 100644
--- a/arch/mips/configs/db1235_defconfig
+++ b/arch/mips/configs/db1235_defconfig
@@ -344,7 +344,6 @@
 CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
 CONFIG_USB_DYNAMIC_MINORS=y
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index b6acd2f..343bebc 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -300,7 +300,6 @@
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_DYNAMIC_MINORS=y
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_OTG_WHITELIST=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
diff --git a/arch/mips/include/asm/clock.h b/arch/mips/include/asm/clock.h
index c9456e7..778e32d 100644
--- a/arch/mips/include/asm/clock.h
+++ b/arch/mips/include/asm/clock.h
@@ -6,8 +6,6 @@
 #include <linux/seq_file.h>
 #include <linux/clk.h>
 
-extern void (*cpu_wait) (void);
-
 struct clk;
 
 struct clk_ops {
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
new file mode 100644
index 0000000..d192158
--- /dev/null
+++ b/arch/mips/include/asm/idle.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_IDLE_H
+#define __ASM_IDLE_H
+
+#include <linux/linkage.h>
+
+extern void (*cpu_wait)(void);
+extern void r4k_wait(void);
+extern asmlinkage void __r4k_wait(void);
+extern void r4k_wait_irqoff(void);
+extern void __pastwait(void);
+
+static inline int using_rollback_handler(void)
+{
+	return cpu_wait == r4k_wait;
+}
+
+static inline int address_is_in_r4k_wait_irqoff(unsigned long addr)
+{
+	return addr >= (unsigned long)r4k_wait_irqoff &&
+	       addr < (unsigned long)__pastwait;
+}
+
+#endif /* __ASM_IDLE_H  */
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 1be1372..b7e5985 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -118,7 +118,7 @@
  */
 static inline unsigned long virt_to_phys(volatile const void *address)
 {
-	return (unsigned long)address - PAGE_OFFSET + PHYS_OFFSET;
+	return __pa(address);
 }
 
 /*
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index e68781e..143875c 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -336,7 +336,7 @@
 #define VPN2_MASK           0xffffe000
 #define TLB_IS_GLOBAL(x)    (((x).tlb_lo0 & MIPS3_PG_G) && ((x).tlb_lo1 & MIPS3_PG_G))
 #define TLB_VPN2(x)         ((x).tlb_hi & VPN2_MASK)
-#define TLB_ASID(x)         (ASID_MASK((x).tlb_hi))
+#define TLB_ASID(x)         ((x).tlb_hi & ASID_MASK)
 #define TLB_IS_VALID(x, va) (((va) & (1 << PAGE_SHIFT)) ? ((x).tlb_lo1 & MIPS3_PG_V) : ((x).tlb_lo0 & MIPS3_PG_V))
 
 struct kvm_mips_tlb {
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 1554721..8201160 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -67,68 +67,45 @@
 	TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir)
 #endif
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT*/
+#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
-#define ASID_INC(asid)						\
-({								\
-	unsigned long __asid = asid;				\
-	__asm__("1:\taddiu\t%0,1\t\t\t\t# patched\n\t"		\
-	".section\t__asid_inc,\"a\"\n\t"			\
-	".word\t1b\n\t"						\
-	".previous"						\
-	:"=r" (__asid)						\
-	:"0" (__asid));						\
-	__asid;							\
-})
-#define ASID_MASK(asid)						\
-({								\
-	unsigned long __asid = asid;				\
-	__asm__("1:\tandi\t%0,%1,0xfc0\t\t\t# patched\n\t"	\
-	".section\t__asid_mask,\"a\"\n\t"			\
-	".word\t1b\n\t"						\
-	".previous"						\
-	:"=r" (__asid)						\
-	:"r" (__asid));						\
-	__asid;							\
-})
-#define ASID_VERSION_MASK					\
-({								\
-	unsigned long __asid;					\
-	__asm__("1:\taddiu\t%0,$0,0xff00\t\t\t\t# patched\n\t"	\
-	".section\t__asid_version_mask,\"a\"\n\t"		\
-	".word\t1b\n\t"						\
-	".previous"						\
-	:"=r" (__asid));					\
-	__asid;							\
-})
-#define ASID_FIRST_VERSION					\
-({								\
-	unsigned long __asid = asid;				\
-	__asm__("1:\tli\t%0,0x100\t\t\t\t# patched\n\t"		\
-	".section\t__asid_first_version,\"a\"\n\t"		\
-	".word\t1b\n\t"						\
-	".previous"						\
-	:"=r" (__asid));					\
-	__asid;							\
-})
+#define ASID_INC	0x40
+#define ASID_MASK	0xfc0
 
-#define ASID_FIRST_VERSION_R3000	0x1000
-#define ASID_FIRST_VERSION_R4000	0x100
-#define ASID_FIRST_VERSION_R8000	0x1000
-#define ASID_FIRST_VERSION_RM9000	0x1000
+#elif defined(CONFIG_CPU_R8000)
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#define SMTC_HW_ASID_MASK		0xff
-extern unsigned int smtc_asid_mask;
+#define ASID_INC	0x10
+#define ASID_MASK	0xff0
+
+#elif defined(CONFIG_MIPS_MT_SMTC)
+
+#define ASID_INC	0x1
+extern unsigned long smtc_asid_mask;
+#define ASID_MASK	(smtc_asid_mask)
+#define HW_ASID_MASK	0xff
+/* End SMTC/34K debug hack */
+#else /* FIXME: not correct for R6000 */
+
+#define ASID_INC	0x1
+#define ASID_MASK	0xff
+
 #endif
 
 #define cpu_context(cpu, mm)	((mm)->context.asid[cpu])
-#define cpu_asid(cpu, mm)	ASID_MASK(cpu_context((cpu), (mm)))
+#define cpu_asid(cpu, mm)	(cpu_context((cpu), (mm)) & ASID_MASK)
 #define asid_cache(cpu)		(cpu_data[cpu].asid_cache)
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
 
+/*
+ *  All unused by hardware upper bits will be considered
+ *  as a software asid extension.
+ */
+#define ASID_VERSION_MASK  ((unsigned long)~(ASID_MASK|(ASID_MASK-1)))
+#define ASID_FIRST_VERSION ((unsigned long)(~ASID_VERSION_MASK) + 1)
+
 #ifndef CONFIG_MIPS_MT_SMTC
 /* Normal, classic MIPS get_new_mmu_context */
 static inline void
@@ -137,7 +114,7 @@
 	extern void kvm_local_flush_tlb_all(void);
 	unsigned long asid = asid_cache(cpu);
 
-	if (!ASID_MASK((asid = ASID_INC(asid)))) {
+	if (! ((asid += ASID_INC) & ASID_MASK) ) {
 		if (cpu_has_vtag_icache)
 			flush_icache_all();
 #ifdef CONFIG_VIRTUALIZATION
@@ -200,7 +177,7 @@
 	 * free up the ASID value for use and flush any old
 	 * instances of it from the TLB.
 	 */
-	oldasid = ASID_MASK(read_c0_entryhi());
+	oldasid = (read_c0_entryhi() & ASID_MASK);
 	if(smtc_live_asid[mytlb][oldasid]) {
 		smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
 		if(smtc_live_asid[mytlb][oldasid] == 0)
@@ -211,7 +188,7 @@
 	 * having ASID_MASK smaller than the hardware maximum,
 	 * make sure no "soft" bits become "hard"...
 	 */
-	write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK) |
+	write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) |
 			 cpu_asid(cpu, next));
 	ehb(); /* Make sure it propagates to TCStatus */
 	evpe(mtflags);
@@ -264,15 +241,15 @@
 #ifdef CONFIG_MIPS_MT_SMTC
 	/* See comments for similar code above */
 	mtflags = dvpe();
-	oldasid = ASID_MASK(read_c0_entryhi());
+	oldasid = read_c0_entryhi() & ASID_MASK;
 	if(smtc_live_asid[mytlb][oldasid]) {
 		smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
 		if(smtc_live_asid[mytlb][oldasid] == 0)
 			 smtc_flush_tlb_asid(oldasid);
 	}
 	/* See comments for similar code above */
-	write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK) |
-	                 cpu_asid(cpu, next));
+	write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) |
+			 cpu_asid(cpu, next));
 	ehb(); /* Make sure it propagates to TCStatus */
 	evpe(mtflags);
 #else
@@ -309,14 +286,14 @@
 #ifdef CONFIG_MIPS_MT_SMTC
 		/* See comments for similar code above */
 		prevvpe = dvpe();
-		oldasid = ASID_MASK(read_c0_entryhi());
+		oldasid = (read_c0_entryhi() & ASID_MASK);
 		if (smtc_live_asid[mytlb][oldasid]) {
 			smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
 			if(smtc_live_asid[mytlb][oldasid] == 0)
 				smtc_flush_tlb_asid(oldasid);
 		}
 		/* See comments for similar code above */
-		write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK)
+		write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK)
 				| cpu_asid(cpu, mm));
 		ehb(); /* Make sure it propagates to TCStatus */
 		evpe(prevvpe);
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index eab99e5..f59552f 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -46,7 +46,6 @@
 #endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */
 
 #include <linux/pfn.h>
-#include <asm/io.h>
 
 extern void build_clear_page(void);
 extern void build_copy_page(void);
@@ -151,6 +150,7 @@
     ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET)
 #endif
 #define __va(x)		((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET))
+#include <asm/io.h>
 
 /*
  * RELOC_HIDE was originally added by 6007b903dfe5f1d13e0c711ac2894bdd4a61b1ad
@@ -171,14 +171,13 @@
 
 #ifdef CONFIG_FLATMEM
 
-#define pfn_valid(pfn)							\
-({									\
-	unsigned long __pfn = (pfn);					\
-	/* avoid <linux/bootmem.h> include hell */			\
-	extern unsigned long min_low_pfn;				\
-									\
-	__pfn >= min_low_pfn && __pfn < max_mapnr;			\
-})
+static inline int pfn_valid(unsigned long pfn)
+{
+	/* avoid <linux/mm.h> include hell */
+	extern unsigned long max_mapnr;
+
+	return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr;
+}
 
 #elif defined(CONFIG_SPARSEMEM)
 
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 71686c8..1470b7b 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -28,7 +28,6 @@
 /*
  * System setup and hardware flags..
  */
-extern void (*cpu_wait)(void);
 
 extern unsigned int vced_count, vcei_count;
 
diff --git a/arch/mips/include/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h
similarity index 100%
rename from arch/mips/include/asm/kvm.h
rename to arch/mips/include/uapi/asm/kvm.h
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 16338b8..1dee279 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -694,16 +694,17 @@
 #define __NR_process_vm_writev		(__NR_Linux + 305)
 #define __NR_kcmp			(__NR_Linux + 306)
 #define __NR_finit_module		(__NR_Linux + 307)
+#define __NR_getdents64			(__NR_Linux + 308)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		307
+#define __NR_Linux_syscalls		308
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		307
+#define __NR_64_Linux_syscalls		308
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 6ad9e04..423d871 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -4,7 +4,7 @@
 
 extra-y		:= head.o vmlinux.lds
 
-obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
+obj-y		+= cpu-probe.o branch.o entry.o genex.o idle.o irq.o process.o \
 		   prom.o ptrace.o reset.o setup.o signal.o syscall.o \
 		   time.o topology.o traps.o unaligned.o watch.o vdso.o
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 4bbffdb..c6568bf 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -27,105 +27,6 @@
 #include <asm/spram.h>
 #include <asm/uaccess.h>
 
-/*
- * Not all of the MIPS CPUs have the "wait" instruction available. Moreover,
- * the implementation of the "wait" feature differs between CPU families. This
- * points to the function that implements CPU specific wait.
- * The wait instruction stops the pipeline and reduces the power consumption of
- * the CPU very much.
- */
-void (*cpu_wait)(void);
-EXPORT_SYMBOL(cpu_wait);
-
-static void r3081_wait(void)
-{
-	unsigned long cfg = read_c0_conf();
-	write_c0_conf(cfg | R30XX_CONF_HALT);
-}
-
-static void r39xx_wait(void)
-{
-	local_irq_disable();
-	if (!need_resched())
-		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
-	local_irq_enable();
-}
-
-extern void r4k_wait(void);
-
-/*
- * This variant is preferable as it allows testing need_resched and going to
- * sleep depending on the outcome atomically.  Unfortunately the "It is
- * implementation-dependent whether the pipeline restarts when a non-enabled
- * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
- * using this version a gamble.
- */
-void r4k_wait_irqoff(void)
-{
-	local_irq_disable();
-	if (!need_resched())
-		__asm__("	.set	push		\n"
-			"	.set	mips3		\n"
-			"	wait			\n"
-			"	.set	pop		\n");
-	local_irq_enable();
-	__asm__("	.globl __pastwait	\n"
-		"__pastwait:			\n");
-}
-
-/*
- * The RM7000 variant has to handle erratum 38.	 The workaround is to not
- * have any pending stores when the WAIT instruction is executed.
- */
-static void rm7k_wait_irqoff(void)
-{
-	local_irq_disable();
-	if (!need_resched())
-		__asm__(
-		"	.set	push					\n"
-		"	.set	mips3					\n"
-		"	.set	noat					\n"
-		"	mfc0	$1, $12					\n"
-		"	sync						\n"
-		"	mtc0	$1, $12		# stalls until W stage	\n"
-		"	wait						\n"
-		"	mtc0	$1, $12		# stalls until W stage	\n"
-		"	.set	pop					\n");
-	local_irq_enable();
-}
-
-/*
- * The Au1xxx wait is available only if using 32khz counter or
- * external timer source, but specifically not CP0 Counter.
- * alchemy/common/time.c may override cpu_wait!
- */
-static void au1k_wait(void)
-{
-	__asm__("	.set	mips3			\n"
-		"	cache	0x14, 0(%0)		\n"
-		"	cache	0x14, 32(%0)		\n"
-		"	sync				\n"
-		"	nop				\n"
-		"	wait				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	.set	mips0			\n"
-		: : "r" (au1k_wait));
-}
-
-static int __initdata nowait;
-
-static int __init wait_disable(char *s)
-{
-	nowait = 1;
-
-	return 1;
-}
-
-__setup("nowait", wait_disable);
-
 static int __cpuinitdata mips_fpu_disabled;
 
 static int __init fpu_disable(char *s)
@@ -150,105 +51,6 @@
 
 __setup("nodsp", dsp_disable);
 
-void __init check_wait(void)
-{
-	struct cpuinfo_mips *c = &current_cpu_data;
-
-	if (nowait) {
-		printk("Wait instruction disabled.\n");
-		return;
-	}
-
-	switch (c->cputype) {
-	case CPU_R3081:
-	case CPU_R3081E:
-		cpu_wait = r3081_wait;
-		break;
-	case CPU_TX3927:
-		cpu_wait = r39xx_wait;
-		break;
-	case CPU_R4200:
-/*	case CPU_R4300: */
-	case CPU_R4600:
-	case CPU_R4640:
-	case CPU_R4650:
-	case CPU_R4700:
-	case CPU_R5000:
-	case CPU_R5500:
-	case CPU_NEVADA:
-	case CPU_4KC:
-	case CPU_4KEC:
-	case CPU_4KSC:
-	case CPU_5KC:
-	case CPU_25KF:
-	case CPU_PR4450:
-	case CPU_BMIPS3300:
-	case CPU_BMIPS4350:
-	case CPU_BMIPS4380:
-	case CPU_BMIPS5000:
-	case CPU_CAVIUM_OCTEON:
-	case CPU_CAVIUM_OCTEON_PLUS:
-	case CPU_CAVIUM_OCTEON2:
-	case CPU_JZRISC:
-	case CPU_LOONGSON1:
-	case CPU_XLR:
-	case CPU_XLP:
-		cpu_wait = r4k_wait;
-		break;
-
-	case CPU_RM7000:
-		cpu_wait = rm7k_wait_irqoff;
-		break;
-
-	case CPU_M14KC:
-	case CPU_M14KEC:
-	case CPU_24K:
-	case CPU_34K:
-	case CPU_1004K:
-		cpu_wait = r4k_wait;
-		if (read_c0_config7() & MIPS_CONF7_WII)
-			cpu_wait = r4k_wait_irqoff;
-		break;
-
-	case CPU_74K:
-		cpu_wait = r4k_wait;
-		if ((c->processor_id & 0xff) >= PRID_REV_ENCODE_332(2, 1, 0))
-			cpu_wait = r4k_wait_irqoff;
-		break;
-
-	case CPU_TX49XX:
-		cpu_wait = r4k_wait_irqoff;
-		break;
-	case CPU_ALCHEMY:
-		cpu_wait = au1k_wait;
-		break;
-	case CPU_20KC:
-		/*
-		 * WAIT on Rev1.0 has E1, E2, E3 and E16.
-		 * WAIT on Rev2.0 and Rev3.0 has E16.
-		 * Rev3.1 WAIT is nop, why bother
-		 */
-		if ((c->processor_id & 0xff) <= 0x64)
-			break;
-
-		/*
-		 * Another rev is incremeting c0_count at a reduced clock
-		 * rate while in WAIT mode.  So we basically have the choice
-		 * between using the cp0 timer as clocksource or avoiding
-		 * the WAIT instruction.  Until more details are known,
-		 * disable the use of WAIT for 20Kc entirely.
-		   cpu_wait = r4k_wait;
-		 */
-		break;
-	case CPU_RM9000:
-		if ((c->processor_id & 0x00ff) >= 0x40)
-			cpu_wait = r4k_wait;
-		break;
-	default:
-		break;
-	}
-}
-
 static inline void check_errata(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c
index 35bed0d..3be9e7b 100644
--- a/arch/mips/kernel/crash_dump.c
+++ b/arch/mips/kernel/crash_dump.c
@@ -2,6 +2,7 @@
 #include <linux/bootmem.h>
 #include <linux/crash_dump.h>
 #include <asm/uaccess.h>
+#include <linux/slab.h>
 
 static int __init parse_savemaxmem(char *p)
 {
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 5c2ba9f..31fa856 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -122,7 +122,7 @@
 	__FINIT
 
 	.align	5	/* 32 byte rollback region */
-LEAF(r4k_wait)
+LEAF(__r4k_wait)
 	.set	push
 	.set	noreorder
 	/* start of rollback region */
@@ -146,14 +146,14 @@
 	jr	ra
 	nop
 	.set	pop
-	END(r4k_wait)
+	END(__r4k_wait)
 
 	.macro	BUILD_ROLLBACK_PROLOGUE handler
 	FEXPORT(rollback_\handler)
 	.set	push
 	.set	noat
 	MFC0	k0, CP0_EPC
-	PTR_LA	k1, r4k_wait
+	PTR_LA	k1, __r4k_wait
 	ori	k0, 0x1f	/* 32 byte rollback region */
 	xori	k0, 0x1f
 	bne	k0, k1, 9f
@@ -493,7 +493,7 @@
 	.set	noreorder
 	/* check if TLB contains a entry for EPC */
 	MFC0	k1, CP0_ENTRYHI
-	andi	k1, 0xff	/* ASID_MASK patched at run-time!! */
+	andi	k1, 0xff	/* ASID_MASK */
 	MFC0	k0, CP0_EPC
 	PTR_SRL k0, _PAGE_SHIFT + 1
 	PTR_SLL k0, _PAGE_SHIFT + 1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
new file mode 100644
index 0000000..3b09b88
--- /dev/null
+++ b/arch/mips/kernel/idle.c
@@ -0,0 +1,244 @@
+/*
+ * MIPS idle loop and WAIT instruction support.
+ *
+ * Copyright (C) xxxx  the Anonymous
+ * Copyright (C) 1994 - 2006 Ralf Baechle
+ * Copyright (C) 2003, 2004  Maciej W. Rozycki
+ * Copyright (C) 2001, 2004, 2011, 2012	 MIPS Technologies, Inc.
+ *
+ * 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.
+ */
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/irqflags.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <asm/cpu.h>
+#include <asm/cpu-info.h>
+#include <asm/idle.h>
+#include <asm/mipsregs.h>
+
+/*
+ * Not all of the MIPS CPUs have the "wait" instruction available. Moreover,
+ * the implementation of the "wait" feature differs between CPU families. This
+ * points to the function that implements CPU specific wait.
+ * The wait instruction stops the pipeline and reduces the power consumption of
+ * the CPU very much.
+ */
+void (*cpu_wait)(void);
+EXPORT_SYMBOL(cpu_wait);
+
+static void r3081_wait(void)
+{
+	unsigned long cfg = read_c0_conf();
+	write_c0_conf(cfg | R30XX_CONF_HALT);
+	local_irq_enable();
+}
+
+static void r39xx_wait(void)
+{
+	if (!need_resched())
+		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
+	local_irq_enable();
+}
+
+void r4k_wait(void)
+{
+	local_irq_enable();
+	__r4k_wait();
+}
+
+/*
+ * This variant is preferable as it allows testing need_resched and going to
+ * sleep depending on the outcome atomically.  Unfortunately the "It is
+ * implementation-dependent whether the pipeline restarts when a non-enabled
+ * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
+ * using this version a gamble.
+ */
+void r4k_wait_irqoff(void)
+{
+	if (!need_resched())
+		__asm__(
+		"	.set	push		\n"
+		"	.set	mips3		\n"
+		"	wait			\n"
+		"	.set	pop		\n");
+	local_irq_enable();
+	__asm__(
+	"	.globl __pastwait	\n"
+	"__pastwait:			\n");
+}
+
+/*
+ * The RM7000 variant has to handle erratum 38.	 The workaround is to not
+ * have any pending stores when the WAIT instruction is executed.
+ */
+static void rm7k_wait_irqoff(void)
+{
+	if (!need_resched())
+		__asm__(
+		"	.set	push					\n"
+		"	.set	mips3					\n"
+		"	.set	noat					\n"
+		"	mfc0	$1, $12					\n"
+		"	sync						\n"
+		"	mtc0	$1, $12		# stalls until W stage	\n"
+		"	wait						\n"
+		"	mtc0	$1, $12		# stalls until W stage	\n"
+		"	.set	pop					\n");
+	local_irq_enable();
+}
+
+/*
+ * The Au1xxx wait is available only if using 32khz counter or
+ * external timer source, but specifically not CP0 Counter.
+ * alchemy/common/time.c may override cpu_wait!
+ */
+static void au1k_wait(void)
+{
+	__asm__(
+	"	.set	mips3			\n"
+	"	cache	0x14, 0(%0)		\n"
+	"	cache	0x14, 32(%0)		\n"
+	"	sync				\n"
+	"	nop				\n"
+	"	wait				\n"
+	"	nop				\n"
+	"	nop				\n"
+	"	nop				\n"
+	"	nop				\n"
+	"	.set	mips0			\n"
+	: : "r" (au1k_wait));
+	local_irq_enable();
+}
+
+static int __initdata nowait;
+
+static int __init wait_disable(char *s)
+{
+	nowait = 1;
+
+	return 1;
+}
+
+__setup("nowait", wait_disable);
+
+void __init check_wait(void)
+{
+	struct cpuinfo_mips *c = &current_cpu_data;
+
+	if (nowait) {
+		printk("Wait instruction disabled.\n");
+		return;
+	}
+
+	switch (c->cputype) {
+	case CPU_R3081:
+	case CPU_R3081E:
+		cpu_wait = r3081_wait;
+		break;
+	case CPU_TX3927:
+		cpu_wait = r39xx_wait;
+		break;
+	case CPU_R4200:
+/*	case CPU_R4300: */
+	case CPU_R4600:
+	case CPU_R4640:
+	case CPU_R4650:
+	case CPU_R4700:
+	case CPU_R5000:
+	case CPU_R5500:
+	case CPU_NEVADA:
+	case CPU_4KC:
+	case CPU_4KEC:
+	case CPU_4KSC:
+	case CPU_5KC:
+	case CPU_25KF:
+	case CPU_PR4450:
+	case CPU_BMIPS3300:
+	case CPU_BMIPS4350:
+	case CPU_BMIPS4380:
+	case CPU_BMIPS5000:
+	case CPU_CAVIUM_OCTEON:
+	case CPU_CAVIUM_OCTEON_PLUS:
+	case CPU_CAVIUM_OCTEON2:
+	case CPU_JZRISC:
+	case CPU_LOONGSON1:
+	case CPU_XLR:
+	case CPU_XLP:
+		cpu_wait = r4k_wait;
+		break;
+
+	case CPU_RM7000:
+		cpu_wait = rm7k_wait_irqoff;
+		break;
+
+	case CPU_M14KC:
+	case CPU_M14KEC:
+	case CPU_24K:
+	case CPU_34K:
+	case CPU_1004K:
+		cpu_wait = r4k_wait;
+		if (read_c0_config7() & MIPS_CONF7_WII)
+			cpu_wait = r4k_wait_irqoff;
+		break;
+
+	case CPU_74K:
+		cpu_wait = r4k_wait;
+		if ((c->processor_id & 0xff) >= PRID_REV_ENCODE_332(2, 1, 0))
+			cpu_wait = r4k_wait_irqoff;
+		break;
+
+	case CPU_TX49XX:
+		cpu_wait = r4k_wait_irqoff;
+		break;
+	case CPU_ALCHEMY:
+		cpu_wait = au1k_wait;
+		break;
+	case CPU_20KC:
+		/*
+		 * WAIT on Rev1.0 has E1, E2, E3 and E16.
+		 * WAIT on Rev2.0 and Rev3.0 has E16.
+		 * Rev3.1 WAIT is nop, why bother
+		 */
+		if ((c->processor_id & 0xff) <= 0x64)
+			break;
+
+		/*
+		 * Another rev is incremeting c0_count at a reduced clock
+		 * rate while in WAIT mode.  So we basically have the choice
+		 * between using the cp0 timer as clocksource or avoiding
+		 * the WAIT instruction.  Until more details are known,
+		 * disable the use of WAIT for 20Kc entirely.
+		   cpu_wait = r4k_wait;
+		 */
+		break;
+	case CPU_RM9000:
+		if ((c->processor_id & 0x00ff) >= 0x40)
+			cpu_wait = r4k_wait;
+		break;
+	default:
+		break;
+	}
+}
+
+static void smtc_idle_hook(void)
+{
+#ifdef CONFIG_MIPS_MT_SMTC
+	void smtc_idle_loop_hook(void);
+
+	smtc_idle_loop_hook();
+#endif
+}
+
+void arch_cpu_idle(void)
+{
+	smtc_idle_hook();
+	if (cpu_wait)
+		cpu_wait();
+	else
+		local_irq_enable();
+}
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 12bc4eb..1f8187a 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -207,7 +207,10 @@
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
-	free_insn_slot(p->ainsn.insn, 0);
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, 0);
+		p->ainsn.insn = NULL;
+	}
 }
 
 static void save_previous_kprobe(struct kprobe_ctlblk *kcb)
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index a3e4614..acb3437 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -10,6 +10,7 @@
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
+#include <asm/idle.h>
 #include <asm/mipsregs.h>
 #include <asm/processor.h>
 #include <asm/prom.h>
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index eb902c1..c6a041d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -51,19 +51,6 @@
 }
 #endif
 
-void arch_cpu_idle(void)
-{
-#ifdef CONFIG_MIPS_MT_SMTC
-	extern void smtc_idle_loop_hook(void);
-
-	smtc_idle_loop_hook();
-#endif
-	if (cpu_wait)
-		(*cpu_wait)();
-	else
-		local_irq_enable();
-}
-
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
@@ -224,6 +211,9 @@
 	int		pc_offset;
 };
 
+#define J_TARGET(pc,target)	\
+		(((unsigned long)(pc) & 0xf0000000) | ((target) << 2))
+
 static inline int is_ra_save_ins(union mips_instruction *ip)
 {
 #ifdef CONFIG_CPU_MICROMIPS
@@ -264,7 +254,7 @@
 #endif
 }
 
-static inline int is_jal_jalr_jr_ins(union mips_instruction *ip)
+static inline int is_jump_ins(union mips_instruction *ip)
 {
 #ifdef CONFIG_CPU_MICROMIPS
 	/*
@@ -288,6 +278,8 @@
 		return 0;
 	return (((ip->u_format.uimmediate >> 6) & mm_jalr_op) == mm_jalr_op);
 #else
+	if (ip->j_format.opcode == j_op)
+		return 1;
 	if (ip->j_format.opcode == jal_op)
 		return 1;
 	if (ip->r_format.opcode != spec_op)
@@ -350,7 +342,7 @@
 
 	for (i = 0; i < max_insns; i++, ip++) {
 
-		if (is_jal_jalr_jr_ins(ip))
+		if (is_jump_ins(ip))
 			break;
 		if (!info->frame_size) {
 			if (is_sp_move_ins(ip))
@@ -393,15 +385,42 @@
 
 static struct mips_frame_info schedule_mfi __read_mostly;
 
+#ifdef CONFIG_KALLSYMS
+static unsigned long get___schedule_addr(void)
+{
+	return kallsyms_lookup_name("__schedule");
+}
+#else
+static unsigned long get___schedule_addr(void)
+{
+	union mips_instruction *ip = (void *)schedule;
+	int max_insns = 8;
+	int i;
+
+	for (i = 0; i < max_insns; i++, ip++) {
+		if (ip->j_format.opcode == j_op)
+			return J_TARGET(ip, ip->j_format.target);
+	}
+	return 0;
+}
+#endif
+
 static int __init frame_info_init(void)
 {
 	unsigned long size = 0;
 #ifdef CONFIG_KALLSYMS
 	unsigned long ofs;
-
-	kallsyms_lookup_size_offset((unsigned long)schedule, &size, &ofs);
 #endif
-	schedule_mfi.func = schedule;
+	unsigned long addr;
+
+	addr = get___schedule_addr();
+	if (!addr)
+		addr = (unsigned long)schedule;
+
+#ifdef CONFIG_KALLSYMS
+	kallsyms_lookup_size_offset(addr, &size, &ofs);
+#endif
+	schedule_mfi.func = (void *)addr;
 	schedule_mfi.func_size = size;
 
 	get_frame_info(&schedule_mfi);
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 36cfd40..97a5909 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -423,4 +423,5 @@
 	PTR	sys_process_vm_writev		/* 5305 */
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_getdents64
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index c17619f..6e7862a 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -37,6 +37,7 @@
 #include <linux/atomic.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
+#include <asm/idle.h>
 #include <asm/r4k-timer.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 31d22f3..75a4fd7 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -34,6 +34,7 @@
 #include <asm/hardirq.h>
 #include <asm/hazards.h>
 #include <asm/irq.h>
+#include <asm/idle.h>
 #include <asm/mmu_context.h>
 #include <asm/mipsregs.h>
 #include <asm/cacheflush.h>
@@ -111,7 +112,7 @@
 static int ipibuffers;
 static int nostlb;
 static int asidmask;
-unsigned int smtc_asid_mask = 0xff;
+unsigned long smtc_asid_mask = 0xff;
 
 static int __init vpe0tcs(char *str)
 {
@@ -858,7 +859,6 @@
 	unsigned long flags;
 	int mtflags;
 	unsigned long tcrestart;
-	extern void r4k_wait_irqoff(void), __pastwait(void);
 	int set_resched_flag = (type == LINUX_SMP_IPI &&
 				action == SMP_RESCHEDULE_YOURSELF);
 
@@ -914,8 +914,7 @@
 			 */
 			if (cpu_wait == r4k_wait_irqoff) {
 				tcrestart = read_tc_c0_tcrestart();
-				if (tcrestart >= (unsigned long)r4k_wait_irqoff
-				    && tcrestart < (unsigned long)__pastwait) {
+				if (address_is_in_r4k_wait_irqoff(tcrestart)) {
 					write_tc_c0_tcrestart(__pastwait);
 					tcstatus &= ~TCSTATUS_IXMT;
 					write_tc_c0_tcstatus(tcstatus);
@@ -1395,7 +1394,7 @@
 	asid = asid_cache(cpu);
 
 	do {
-		if (!ASID_MASK(ASID_INC(asid))) {
+		if (!((asid += ASID_INC) & ASID_MASK) ) {
 			if (cpu_has_vtag_icache)
 				flush_icache_all();
 			/* Traverse all online CPUs (hack requires contiguous range) */
@@ -1414,7 +1413,7 @@
 						mips_ihb();
 					}
 					tcstat = read_tc_c0_tcstatus();
-					smtc_live_asid[tlb][ASID_MASK(tcstat)] |= (asiduse)(0x1 << i);
+					smtc_live_asid[tlb][(tcstat & ASID_MASK)] |= (asiduse)(0x1 << i);
 					if (!prevhalt)
 						write_tc_c0_tchalt(0);
 				}
@@ -1423,7 +1422,7 @@
 				asid = ASID_FIRST_VERSION;
 			local_flush_tlb_all();	/* start new asid cycle */
 		}
-	} while (smtc_live_asid[tlb][ASID_MASK(asid)]);
+	} while (smtc_live_asid[tlb][(asid & ASID_MASK)]);
 
 	/*
 	 * SMTC shares the TLB within VPEs and possibly across all VPEs.
@@ -1461,7 +1460,7 @@
 		tlb_read();
 		ehb();
 		ehi = read_c0_entryhi();
-		if (ASID_MASK(ehi) == asid) {
+		if ((ehi & ASID_MASK) == asid) {
 		    /*
 		     * Invalidate only entries with specified ASID,
 		     * makiing sure all entries differ.
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 77cff1f..e3be670 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -41,6 +41,7 @@
 #include <asm/dsp.h>
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
+#include <asm/idle.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/module.h>
@@ -57,7 +58,6 @@
 #include <asm/uasm.h>
 
 extern void check_wait(void);
-extern asmlinkage void r4k_wait(void);
 extern asmlinkage void rollback_handle_int(void);
 extern asmlinkage void handle_int(void);
 extern u32 handle_tlbl[];
@@ -1542,7 +1542,7 @@
 		extern char except_vec_vi, except_vec_vi_lui;
 		extern char except_vec_vi_ori, except_vec_vi_end;
 		extern char rollback_except_vec_vi;
-		char *vec_start = (cpu_wait == r4k_wait) ?
+		char *vec_start = using_rollback_handler() ?
 			&rollback_except_vec_vi : &except_vec_vi;
 #ifdef CONFIG_MIPS_MT_SMTC
 		/*
@@ -1656,7 +1656,6 @@
 	unsigned int cpu = smp_processor_id();
 	unsigned int status_set = ST0_CU0;
 	unsigned int hwrena = cpu_hwrena_impl_bits;
-	unsigned long asid = 0;
 #ifdef CONFIG_MIPS_MT_SMTC
 	int secondaryTC = 0;
 	int bootTC = (cpu == 0);
@@ -1740,9 +1739,8 @@
 	}
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-	asid = ASID_FIRST_VERSION;
-	cpu_data[cpu].asid_cache = asid;
-	TLBMISS_HANDLER_SETUP();
+	if (!cpu_data[cpu].asid_cache)
+		cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
 
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
@@ -1814,10 +1812,8 @@
 	extern char except_vec4;
 	extern char except_vec3_r4000;
 	unsigned long i;
-	int rollback;
 
 	check_wait();
-	rollback = (cpu_wait == r4k_wait);
 
 #if defined(CONFIG_KGDB)
 	if (kgdb_early_setup)
@@ -1894,7 +1890,8 @@
 	if (board_be_init)
 		board_be_init();
 
-	set_except_vector(0, rollback ? rollback_handle_int : handle_int);
+	set_except_vector(0, using_rollback_handler() ? rollback_handle_int
+						      : handle_int);
 	set_except_vector(1, handle_tlbm);
 	set_except_vector(2, handle_tlbl);
 	set_except_vector(3, handle_tlbs);
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c
index 2b2bac9..4b6274b 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/kvm_mips_emul.c
@@ -525,16 +525,18 @@
 				printk("MTCz, cop0->reg[EBASE]: %#lx\n",
 				       kvm_read_c0_guest_ebase(cop0));
 			} else if (rd == MIPS_CP0_TLB_HI && sel == 0) {
-				uint32_t nasid = ASID_MASK(vcpu->arch.gprs[rt]);
+				uint32_t nasid =
+				    vcpu->arch.gprs[rt] & ASID_MASK;
 				if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0)
 				    &&
-				    (ASID_MASK(kvm_read_c0_guest_entryhi(cop0))
-				      != nasid)) {
+				    ((kvm_read_c0_guest_entryhi(cop0) &
+				      ASID_MASK) != nasid)) {
 
 					kvm_debug
 					    ("MTCz, change ASID from %#lx to %#lx\n",
-					     ASID_MASK(kvm_read_c0_guest_entryhi(cop0)),
-					     ASID_MASK(vcpu->arch.gprs[rt]));
+					     kvm_read_c0_guest_entryhi(cop0) &
+					     ASID_MASK,
+					     vcpu->arch.gprs[rt] & ASID_MASK);
 
 					/* Blow away the shadow host TLBs */
 					kvm_mips_flush_host_tlb(1);
@@ -986,7 +988,8 @@
 		 * resulting handler will do the right thing
 		 */
 		index = kvm_mips_guest_tlb_lookup(vcpu, (va & VPN2_MASK) |
-						  ASID_MASK(kvm_read_c0_guest_entryhi(cop0)));
+						  (kvm_read_c0_guest_entryhi
+						   (cop0) & ASID_MASK));
 
 		if (index < 0) {
 			vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
@@ -1151,7 +1154,7 @@
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.  host_cp0_badvaddr & VPN2_MASK) |
-				ASID_MASK(kvm_read_c0_guest_entryhi(cop0));
+				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1198,7 +1201,7 @@
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi =
 		(vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
-		ASID_MASK(kvm_read_c0_guest_entryhi(cop0));
+		(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1243,7 +1246,7 @@
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
-				ASID_MASK(kvm_read_c0_guest_entryhi(cop0));
+				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1287,7 +1290,7 @@
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
-		ASID_MASK(kvm_read_c0_guest_entryhi(cop0));
+		(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1356,7 +1359,7 @@
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
-				ASID_MASK(kvm_read_c0_guest_entryhi(cop0));
+				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
 
@@ -1783,8 +1786,8 @@
 	 */
 	index = kvm_mips_guest_tlb_lookup(vcpu,
 					  (va & VPN2_MASK) |
-					  ASID_MASK(kvm_read_c0_guest_entryhi
-					   (vcpu->arch.cop0)));
+					  (kvm_read_c0_guest_entryhi
+					   (vcpu->arch.cop0) & ASID_MASK));
 	if (index < 0) {
 		if (exccode == T_TLB_LD_MISS) {
 			er = kvm_mips_emulate_tlbmiss_ld(cause, opc, run, vcpu);
diff --git a/arch/mips/kvm/kvm_tlb.c b/arch/mips/kvm/kvm_tlb.c
index 89511a9..c777dd3 100644
--- a/arch/mips/kvm/kvm_tlb.c
+++ b/arch/mips/kvm/kvm_tlb.c
@@ -17,6 +17,8 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/kvm_host.h>
+#include <linux/srcu.h>
+
 
 #include <asm/cpu.h>
 #include <asm/bootinfo.h>
@@ -51,13 +53,13 @@
 
 uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
 {
-	return ASID_MASK(vcpu->arch.guest_kernel_asid[smp_processor_id()]);
+	return vcpu->arch.guest_kernel_asid[smp_processor_id()] & ASID_MASK;
 }
 
 
 uint32_t kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
 {
-	return ASID_MASK(vcpu->arch.guest_user_asid[smp_processor_id()]);
+	return vcpu->arch.guest_user_asid[smp_processor_id()] & ASID_MASK;
 }
 
 inline uint32_t kvm_mips_get_commpage_asid (struct kvm_vcpu *vcpu)
@@ -84,7 +86,7 @@
 	old_pagemask = read_c0_pagemask();
 
 	printk("HOST TLBs:\n");
-	printk("ASID: %#lx\n", ASID_MASK(read_c0_entryhi()));
+	printk("ASID: %#lx\n", read_c0_entryhi() & ASID_MASK);
 
 	for (i = 0; i < current_cpu_data.tlbsize; i++) {
 		write_c0_index(i);
@@ -169,21 +171,27 @@
 	}
 }
 
-static void kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
+static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 {
+	int srcu_idx, err = 0;
 	pfn_t pfn;
 
 	if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE)
-		return;
+		return 0;
 
+        srcu_idx = srcu_read_lock(&kvm->srcu);
 	pfn = kvm_mips_gfn_to_pfn(kvm, gfn);
 
 	if (kvm_mips_is_error_pfn(pfn)) {
-		panic("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn);
+		kvm_err("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn);
+		err = -EFAULT;
+		goto out;
 	}
 
 	kvm->arch.guest_pmap[gfn] = pfn;
-	return;
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return err;
 }
 
 /* Translate guest KSEG0 addresses to Host PA */
@@ -207,7 +215,10 @@
 			gva);
 		return KVM_INVALID_PAGE;
 	}
-	kvm_mips_map_page(vcpu->kvm, gfn);
+
+	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
+		return KVM_INVALID_ADDR;
+
 	return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset;
 }
 
@@ -310,8 +321,11 @@
 	even = !(gfn & 0x1);
 	vaddr = badvaddr & (PAGE_MASK << 1);
 
-	kvm_mips_map_page(vcpu->kvm, gfn);
-	kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1);
+	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1) < 0)
+		return -1;
 
 	if (even) {
 		pfn0 = kvm->arch.guest_pmap[gfn];
@@ -389,8 +403,11 @@
 		pfn0 = 0;
 		pfn1 = 0;
 	} else {
-		kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT);
-		kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT);
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT) < 0)
+			return -1;
+
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT) < 0)
+			return -1;
 
 		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT];
 		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT];
@@ -428,7 +445,7 @@
 
 	for (i = 0; i < KVM_MIPS_GUEST_TLB_SIZE; i++) {
 		if (((TLB_VPN2(tlb[i]) & ~tlb[i].tlb_mask) == ((entryhi & VPN2_MASK) & ~tlb[i].tlb_mask)) &&
-			(TLB_IS_GLOBAL(tlb[i]) || (TLB_ASID(tlb[i]) == ASID_MASK(entryhi)))) {
+			(TLB_IS_GLOBAL(tlb[i]) || (TLB_ASID(tlb[i]) == (entryhi & ASID_MASK)))) {
 			index = i;
 			break;
 		}
@@ -626,7 +643,7 @@
 {
 	unsigned long asid = asid_cache(cpu);
 
-	if (!(ASID_MASK(ASID_INC(asid)))) {
+	if (!((asid += ASID_INC) & ASID_MASK)) {
 		if (cpu_has_vtag_icache) {
 			flush_icache_all();
 		}
@@ -804,7 +821,8 @@
 	if (!newasid) {
 		/* If we preempted while the guest was executing, then reload the pre-empted ASID */
 		if (current->flags & PF_VCPU) {
-			write_c0_entryhi(ASID_MASK(vcpu->arch.preempt_entryhi));
+			write_c0_entryhi(vcpu->arch.
+					 preempt_entryhi & ASID_MASK);
 			ehb();
 		}
 	} else {
@@ -816,11 +834,13 @@
 		 */
 		if (current->flags & PF_VCPU) {
 			if (KVM_GUEST_KERNEL_MODE(vcpu))
-				write_c0_entryhi(ASID_MASK(vcpu->arch.
-						 guest_kernel_asid[cpu]));
+				write_c0_entryhi(vcpu->arch.
+						 guest_kernel_asid[cpu] &
+						 ASID_MASK);
 			else
-				write_c0_entryhi(ASID_MASK(vcpu->arch.
-						 guest_user_asid[cpu]));
+				write_c0_entryhi(vcpu->arch.
+						 guest_user_asid[cpu] &
+						 ASID_MASK);
 			ehb();
 		}
 	}
@@ -879,7 +899,8 @@
 			    kvm_mips_guest_tlb_lookup(vcpu,
 						      ((unsigned long) opc & VPN2_MASK)
 						      |
-						      ASID_MASK(kvm_read_c0_guest_entryhi(cop0)));
+						      (kvm_read_c0_guest_entryhi
+						       (cop0) & ASID_MASK));
 			if (index < 0) {
 				kvm_err
 				    ("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n",
diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c
index 9861c86..850821d 100644
--- a/arch/mips/lantiq/xway/gptu.c
+++ b/arch/mips/lantiq/xway/gptu.c
@@ -144,10 +144,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Failed to get resource\n");
-		return -ENOMEM;
-	}
 
 	/* remap gptu register range */
 	gptu_membase = devm_ioremap_resource(&pdev->dev, res);
@@ -169,6 +165,8 @@
 	if (((gptu_r32(GPTU_ID) >> 8) & 0xff) != GPTU_MAGIC) {
 		dev_err(&pdev->dev, "Failed to find magic\n");
 		gptu_hwexit();
+		clk_disable(clk);
+		clk_put(clk);
 		return -ENAVAIL;
 	}
 
diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c
index 8a12d00..32b9f21 100644
--- a/arch/mips/lib/dump_tlb.c
+++ b/arch/mips/lib/dump_tlb.c
@@ -11,7 +11,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/tlbdebug.h>
-#include <asm/mmu_context.h>
 
 static inline const char *msk2str(unsigned int mask)
 {
@@ -56,7 +55,7 @@
 	s_pagemask = read_c0_pagemask();
 	s_entryhi = read_c0_entryhi();
 	s_index = read_c0_index();
-	asid = ASID_MASK(s_entryhi);
+	asid = s_entryhi & 0xff;
 
 	for (i = first; i <= last; i++) {
 		write_c0_index(i);
@@ -86,7 +85,7 @@
 
 			printk("va=%0*lx asid=%02lx\n",
 			       width, (entryhi & ~0x1fffUL),
-			       ASID_MASK(entryhi));
+			       entryhi & 0xff);
 			printk("\t[pa=%0*llx c=%d d=%d v=%d g=%d] ",
 			       width,
 			       (entrylo0 << 6) & PAGE_MASK, c0,
diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c
index 8327698..91615c2 100644
--- a/arch/mips/lib/r3k_dump_tlb.c
+++ b/arch/mips/lib/r3k_dump_tlb.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 
 #include <asm/mipsregs.h>
-#include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/tlbdebug.h>
@@ -22,7 +21,7 @@
 	unsigned int asid;
 	unsigned long entryhi, entrylo0;
 
-	asid = ASID_MASK(read_c0_entryhi());
+	asid = read_c0_entryhi() & 0xfc0;
 
 	for (i = first; i <= last; i++) {
 		write_c0_index(i<<8);
@@ -36,7 +35,7 @@
 
 		/* Unused entries have a virtual address of KSEG0.  */
 		if ((entryhi & 0xffffe000) != 0x80000000
-		    && (ASID_MASK(entryhi) == asid)) {
+		    && (entryhi & 0xfc0) == asid) {
 			/*
 			 * Only print entries in use
 			 */
@@ -45,7 +44,7 @@
 			printk("va=%08lx asid=%08lx"
 			       "  [pa=%06lx n=%d d=%d v=%d g=%d]",
 			       (entryhi & 0xffffe000),
-			       ASID_MASK(entryhi),
+			       entryhi & 0xfc0,
 			       entrylo0 & PAGE_MASK,
 			       (entrylo0 & (1 << 11)) ? 1 : 0,
 			       (entrylo0 & (1 << 10)) ? 1 : 0,
diff --git a/arch/mips/loongson/common/reset.c b/arch/mips/loongson/common/reset.c
index 35c8c64..65bfbb5 100644
--- a/arch/mips/loongson/common/reset.c
+++ b/arch/mips/loongson/common/reset.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/pm.h>
 
+#include <asm/idle.h>
 #include <asm/reboot.h>
 
 #include <loongson.h>
diff --git a/arch/mips/loongson1/common/reset.c b/arch/mips/loongson1/common/reset.c
index d4f610f..547f34b 100644
--- a/arch/mips/loongson1/common/reset.c
+++ b/arch/mips/loongson1/common/reset.c
@@ -9,6 +9,7 @@
 
 #include <linux/io.h>
 #include <linux/pm.h>
+#include <asm/idle.h>
 #include <asm/reboot.h>
 
 #include <loongson1.h>
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 4a13c15..a63d1ed 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -51,7 +51,7 @@
 #endif
 
 	local_irq_save(flags);
-	old_ctx = ASID_MASK(read_c0_entryhi());
+	old_ctx = read_c0_entryhi() & ASID_MASK;
 	write_c0_entrylo0(0);
 	entry = r3k_have_wired_reg ? read_c0_wired() : 8;
 	for (; entry < current_cpu_data.tlbsize; entry++) {
@@ -87,13 +87,13 @@
 
 #ifdef DEBUG_TLB
 		printk("[tlbrange<%lu,0x%08lx,0x%08lx>]",
-			ASID_MASK(cpu_context(cpu, mm)), start, end);
+			cpu_context(cpu, mm) & ASID_MASK, start, end);
 #endif
 		local_irq_save(flags);
 		size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 		if (size <= current_cpu_data.tlbsize) {
-			int oldpid = ASID_MASK(read_c0_entryhi());
-			int newpid = ASID_MASK(cpu_context(cpu, mm));
+			int oldpid = read_c0_entryhi() & ASID_MASK;
+			int newpid = cpu_context(cpu, mm) & ASID_MASK;
 
 			start &= PAGE_MASK;
 			end += PAGE_SIZE - 1;
@@ -166,10 +166,10 @@
 #ifdef DEBUG_TLB
 		printk("[tlbpage<%lu,0x%08lx>]", cpu_context(cpu, vma->vm_mm), page);
 #endif
-		newpid = ASID_MASK(cpu_context(cpu, vma->vm_mm));
+		newpid = cpu_context(cpu, vma->vm_mm) & ASID_MASK;
 		page &= PAGE_MASK;
 		local_irq_save(flags);
-		oldpid = ASID_MASK(read_c0_entryhi());
+		oldpid = read_c0_entryhi() & ASID_MASK;
 		write_c0_entryhi(page | newpid);
 		BARRIER;
 		tlb_probe();
@@ -197,10 +197,10 @@
 	if (current->active_mm != vma->vm_mm)
 		return;
 
-	pid = ASID_MASK(read_c0_entryhi());
+	pid = read_c0_entryhi() & ASID_MASK;
 
 #ifdef DEBUG_TLB
-	if ((pid != ASID_MASK(cpu_context(cpu, vma->vm_mm))) || (cpu_context(cpu, vma->vm_mm) == 0)) {
+	if ((pid != (cpu_context(cpu, vma->vm_mm) & ASID_MASK)) || (cpu_context(cpu, vma->vm_mm) == 0)) {
 		printk("update_mmu_cache: Wheee, bogus tlbpid mmpid=%lu tlbpid=%d\n",
 		       (cpu_context(cpu, vma->vm_mm)), pid);
 	}
@@ -241,7 +241,7 @@
 
 		local_irq_save(flags);
 		/* Save old context and create impossible VPN2 value */
-		old_ctx = ASID_MASK(read_c0_entryhi());
+		old_ctx = read_c0_entryhi() & ASID_MASK;
 		old_pagemask = read_c0_pagemask();
 		w = read_c0_wired();
 		write_c0_wired(w + 1);
@@ -264,7 +264,7 @@
 #endif
 
 		local_irq_save(flags);
-		old_ctx = ASID_MASK(read_c0_entryhi());
+		old_ctx = read_c0_entryhi() & ASID_MASK;
 		write_c0_entrylo0(entrylo0);
 		write_c0_entryhi(entryhi);
 		write_c0_index(wired);
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 09653b2..c643de4 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -287,7 +287,7 @@
 
 	ENTER_CRITICAL(flags);
 
-	pid = ASID_MASK(read_c0_entryhi());
+	pid = read_c0_entryhi() & ASID_MASK;
 	address &= (PAGE_MASK << 1);
 	write_c0_entryhi(address | pid);
 	pgdp = pgd_offset(vma->vm_mm, address);
diff --git a/arch/mips/mm/tlb-r8k.c b/arch/mips/mm/tlb-r8k.c
index 122f920..91c2499 100644
--- a/arch/mips/mm/tlb-r8k.c
+++ b/arch/mips/mm/tlb-r8k.c
@@ -195,7 +195,7 @@
 	if (current->active_mm != vma->vm_mm)
 		return;
 
-	pid = ASID_MASK(read_c0_entryhi());
+	pid = read_c0_entryhi() & ASID_MASK;
 
 	local_irq_save(flags);
 	address &= PAGE_MASK;
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 4d46d37..ce9818e 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -29,7 +29,6 @@
 #include <linux/init.h>
 #include <linux/cache.h>
 
-#include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/war.h>
@@ -306,78 +305,6 @@
 static int check_for_high_segbits __cpuinitdata;
 #endif
 
-static void __cpuinit insn_fixup(unsigned int **start, unsigned int **stop,
-					unsigned int i_const)
-{
-	unsigned int **p;
-
-	for (p = start; p < stop; p++) {
-#ifndef CONFIG_CPU_MICROMIPS
-		unsigned int *ip;
-
-		ip = *p;
-		*ip = (*ip & 0xffff0000) | i_const;
-#else
-		unsigned short *ip;
-
-		ip = ((unsigned short *)((unsigned int)*p - 1));
-		if ((*ip & 0xf000) == 0x4000) {
-			*ip &= 0xfff1;
-			*ip |= (i_const << 1);
-		} else if ((*ip & 0xf000) == 0x6000) {
-			*ip &= 0xfff1;
-			*ip |= ((i_const >> 2) << 1);
-		} else {
-			ip++;
-			*ip = i_const;
-		}
-#endif
-		local_flush_icache_range((unsigned long)ip,
-					 (unsigned long)ip + sizeof(*ip));
-	}
-}
-
-#define asid_insn_fixup(section, const)					\
-do {									\
-	extern unsigned int *__start_ ## section;			\
-	extern unsigned int *__stop_ ## section;			\
-	insn_fixup(&__start_ ## section, &__stop_ ## section, const);	\
-} while(0)
-
-/*
- * Caller is assumed to flush the caches before the first context switch.
- */
-static void __cpuinit setup_asid(unsigned int inc, unsigned int mask,
-				 unsigned int version_mask,
-				 unsigned int first_version)
-{
-	extern asmlinkage void handle_ri_rdhwr_vivt(void);
-	unsigned long *vivt_exc;
-
-#ifdef CONFIG_CPU_MICROMIPS
-	/*
-	 * Worst case optimised microMIPS addiu instructions support
-	 * only a 3-bit immediate value.
-	 */
-	if(inc > 7)
-		panic("Invalid ASID increment value!");
-#endif
-	asid_insn_fixup(__asid_inc, inc);
-	asid_insn_fixup(__asid_mask, mask);
-	asid_insn_fixup(__asid_version_mask, version_mask);
-	asid_insn_fixup(__asid_first_version, first_version);
-
-	/* Patch up the 'handle_ri_rdhwr_vivt' handler. */
-	vivt_exc = (unsigned long *) &handle_ri_rdhwr_vivt;
-#ifdef CONFIG_CPU_MICROMIPS
-	vivt_exc = (unsigned long *)((unsigned long) vivt_exc - 1);
-#endif
-	vivt_exc++;
-	*vivt_exc = (*vivt_exc & ~mask) | mask;
-
-	current_cpu_data.asid_cache = first_version;
-}
-
 static int check_for_high_segbits __cpuinitdata;
 
 static unsigned int kscratch_used_mask __cpuinitdata;
@@ -2256,7 +2183,6 @@
 	case CPU_TX3922:
 	case CPU_TX3927:
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
-		setup_asid(0x40, 0xfc0, 0xf000, ASID_FIRST_VERSION_R3000);
 		if (cpu_has_local_ebase)
 			build_r3000_tlb_refill_handler();
 		if (!run_once) {
@@ -2282,11 +2208,6 @@
 		break;
 
 	default:
-#ifndef CONFIG_MIPS_MT_SMTC
-		setup_asid(0x1, 0xff, 0xff00, ASID_FIRST_VERSION_R4000);
-#else
-		setup_asid(0x1, smtc_asid_mask, 0xff00, ASID_FIRST_VERSION_R4000);
-#endif
 		if (!run_once) {
 			scratch_reg = allocate_kscratch();
 #ifdef CONFIG_MIPS_PGD_C0_CONTEXT
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index af31914..eaa99d2 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -37,6 +37,7 @@
 #include <linux/pm.h>
 #include <linux/bootmem.h>
 
+#include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/time.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index e3e0941..89c8c10 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -36,6 +36,7 @@
 #include <linux/serial_8250.h>
 #include <linux/pm.h>
 
+#include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/time.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c
index 0edb89a..1c98975 100644
--- a/arch/mips/pmcs-msp71xx/msp_prom.c
+++ b/arch/mips/pmcs-msp71xx/msp_prom.c
@@ -83,7 +83,7 @@
 	return 0; /* foo */
 }
 
-static inline int str2eaddr(unsigned char *ea, unsigned char *str)
+int str2eaddr(unsigned char *ea, unsigned char *str)
 {
 	int index = 0;
 	unsigned char num = 0;
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 1651cfd..396b296 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -12,6 +12,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/cacheflush.h>
+#include <asm/idle.h>
 #include <asm/r4kcache.h>
 #include <asm/reboot.h>
 #include <asm/smp-ops.h>
diff --git a/arch/mips/ralink/dts/rt3050.dtsi b/arch/mips/ralink/dts/rt3050.dtsi
index ef7da1e..e3203d4 100644
--- a/arch/mips/ralink/dts/rt3050.dtsi
+++ b/arch/mips/ralink/dts/rt3050.dtsi
@@ -55,4 +55,14 @@
 			reg-shift = <2>;
 		};
 	};
+
+	usb@101c0000 {
+		compatible = "ralink,rt3050-usb", "snps,dwc2";
+		reg = <0x101c0000 40000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <18>;
+
+		status = "disabled";
+	};
 };
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts
index c18c9a8..0ac73ea 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/ralink/dts/rt3052_eval.dts
@@ -43,4 +43,8 @@
 			reg = <0x50000 0x7b0000>;
 		};
 	};
+
+	usb@101c0000 {
+		status = "ok";
+	};
 };
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 5364aab..681e7f8 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/irq.h>
 #include <asm/bootinfo.h>
+#include <asm/idle.h>
 #include <asm/time.h>
 #include <asm/reboot.h>
 #include <asm/r4kcache.h>
diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c
index 70a3f90..d7f7558 100644
--- a/arch/mips/vr41xx/common/pmu.c
+++ b/arch/mips/vr41xx/common/pmu.c
@@ -27,6 +27,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
+#include <asm/idle.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/reboot.h>
diff --git a/arch/mips/wrppmc/reset.c b/arch/mips/wrppmc/reset.c
index cc5474b..80beb18 100644
--- a/arch/mips/wrppmc/reset.c
+++ b/arch/mips/wrppmc/reset.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 
 #include <asm/cacheflush.h>
+#include <asm/idle.h>
 #include <asm/mipsregs.h>
 #include <asm/processor.h>
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index cad060f..6507dab 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -245,7 +245,7 @@
 
 config IRQSTACKS
 	bool "Use separate kernel stacks when processing interrupts"
-	default n
+	default y
 	help
 	  If you say Y here the kernel will use separate kernel stacks
 	  for handling hard and soft interrupts.  This can help avoid
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 2f967cc..1976900 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -23,24 +23,21 @@
 CHECKFLAGS	+= -D__hppa__=1
 LIBGCC		= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
-MACHINE		:= $(shell uname -m)
-NATIVE		:= $(if $(filter parisc%,$(MACHINE)),1,0)
-
 ifdef CONFIG_64BIT
 UTS_MACHINE	:= parisc64
 CHECKFLAGS	+= -D__LP64__=1 -m64
-WIDTH		:= 64
+CC_ARCHES	= hppa64
 else # 32-bit
-WIDTH		:=
+CC_ARCHES	= hppa hppa2.0 hppa1.1
 endif
 
-# attempt to help out folks who are cross-compiling
-ifeq ($(NATIVE),1)
-CROSS_COMPILE	:= hppa$(WIDTH)-linux-
-else
- ifeq ($(CROSS_COMPILE),)
- CROSS_COMPILE	:= hppa$(WIDTH)-linux-gnu-
- endif
+ifneq ($(SUBARCH),$(UTS_MACHINE))
+	ifeq ($(CROSS_COMPILE),)
+		CC_SUFFIXES = linux linux-gnu unknown-linux-gnu
+		CROSS_COMPILE := $(call cc-cross-prefix, \
+			$(foreach a,$(CC_ARCHES), \
+			$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
+	endif
 endif
 
 OBJCOPY_FLAGS =-O binary -R .note -R .comment -S
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 89fb400..0da8482 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -438,7 +438,6 @@
 	SAVE_SP  (%sr4, PT_SR4 (\regs))
 	SAVE_SP  (%sr5, PT_SR5 (\regs))
 	SAVE_SP  (%sr6, PT_SR6 (\regs))
-	SAVE_SP  (%sr7, PT_SR7 (\regs))
 
 	SAVE_CR  (%cr17, PT_IASQ0(\regs))
 	mtctl	 %r0,	%cr17
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
index 12373c4..241c345 100644
--- a/arch/parisc/include/asm/hardirq.h
+++ b/arch/parisc/include/asm/hardirq.h
@@ -11,15 +11,20 @@
 #include <linux/threads.h>
 #include <linux/irq.h>
 
+#ifdef CONFIG_IRQSTACKS
+#define __ARCH_HAS_DO_SOFTIRQ
+#endif
+
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	unsigned int kernel_stack_usage;
-#endif
+	unsigned int irq_stack_usage;
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
 #endif
+	unsigned int irq_unaligned_count;
+	unsigned int irq_fpassist_count;
 	unsigned int irq_tlb_count;
 } ____cacheline_aligned irq_cpustat_t;
 
@@ -28,6 +33,7 @@
 #define __ARCH_IRQ_STAT
 #define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
+#define __inc_irq_stat(member)	__this_cpu_inc(irq_stat.member)
 #define local_softirq_pending()	this_cpu_read(irq_stat.__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 0640155..cc2290a 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -17,7 +17,6 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
-
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -59,23 +58,6 @@
 #ifndef __ASSEMBLY__
 
 /*
- * IRQ STACK - used for irq handler
- */
-#ifdef __KERNEL__
-
-#define IRQ_STACK_SIZE      (4096 << 2) /* 16k irq stack size */
-
-union irq_stack_union {
-	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];
-};
-
-DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
-
-void call_on_stack(unsigned long p1, void *func, unsigned long new_stack);
-
-#endif /* __KERNEL__ */
-
-/*
  * Data detected about CPUs at boot time which is the same for all CPU's.
  * HP boxes are SMP - ie identical processors.
  *
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 4bb96ad..e8f07dd 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -65,15 +65,11 @@
 	rsm	PSW_SM_I, %r0	/* barrier for "Relied upon Translation */
 	mtsp	%r0, %sr4
 	mtsp	%r0, %sr5
-	mfsp	%sr7, %r1
-	or,=    %r0,%r1,%r0	/* Only save sr7 in sr3 if sr7 != 0 */
-	mtsp	%r1, %sr3
+	mtsp	%r0, %sr6
 	tovirt_r1 %r29
 	load32	KERNEL_PSW, %r1
 
 	rsm     PSW_SM_QUIET,%r0	/* second "heavy weight" ctl op */
-	mtsp	%r0, %sr6
-	mtsp	%r0, %sr7
 	mtctl	%r0, %cr17	/* Clear IIASQ tail */
 	mtctl	%r0, %cr17	/* Clear IIASQ head */
 	mtctl	%r1, %ipsw
@@ -119,17 +115,20 @@
 
 	/* we save the registers in the task struct */
 
+	copy	%r30, %r17
 	mfctl   %cr30, %r1
+	ldo	THREAD_SZ_ALGN(%r1), %r30
+	mtsp	%r0,%sr7
+	mtsp	%r16,%sr3
 	tophys  %r1,%r9
 	LDREG	TI_TASK(%r9), %r1	/* thread_info -> task_struct */
 	tophys  %r1,%r9
 	ldo     TASK_REGS(%r9),%r9
-	STREG   %r30, PT_GR30(%r9)
+	STREG   %r17,PT_GR30(%r9)
 	STREG   %r29,PT_GR29(%r9)
 	STREG   %r26,PT_GR26(%r9)
+	STREG	%r16,PT_SR7(%r9)
 	copy    %r9,%r29
-	mfctl   %cr30, %r1
-	ldo	THREAD_SZ_ALGN(%r1), %r30
 	.endm
 
 	.macro  get_stack_use_r30
@@ -137,10 +136,12 @@
 	/* we put a struct pt_regs on the stack and save the registers there */
 
 	tophys  %r30,%r9
-	STREG   %r30,PT_GR30(%r9)
+	copy	%r30,%r1
 	ldo	PT_SZ_ALGN(%r30),%r30
+	STREG   %r1,PT_GR30(%r9)
 	STREG   %r29,PT_GR29(%r9)
 	STREG   %r26,PT_GR26(%r9)
+	STREG	%r16,PT_SR7(%r9)
 	copy    %r9,%r29
 	.endm
 
@@ -452,9 +453,41 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
+	/* Acquire pa_dbit_lock lock. */
+	.macro		dbit_lock	spc,tmp,tmp1
+#ifdef CONFIG_SMP
+	cmpib,COND(=),n	0,\spc,2f
+	load32		PA(pa_dbit_lock),\tmp
+1:	LDCW		0(\tmp),\tmp1
+	cmpib,COND(=)	0,\tmp1,1b
+	nop
+2:
+#endif
+	.endm
+
+	/* Release pa_dbit_lock lock without reloading lock address. */
+	.macro		dbit_unlock0	spc,tmp
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	stw             \spc,0(\tmp)
+#endif
+	.endm
+
+	/* Release pa_dbit_lock lock. */
+	.macro		dbit_unlock1	spc,tmp
+#ifdef CONFIG_SMP
+	load32		PA(pa_dbit_lock),\tmp
+	dbit_unlock0	\spc,\tmp
+#endif
+	.endm
+
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	ptep,pte,tmp,tmp1
+	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	LDREG		0(\ptep),\pte
+#endif
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
@@ -463,7 +496,11 @@
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	ptep,pte,tmp
+	.macro		update_dirty	spc,ptep,pte,tmp
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	LDREG		0(\ptep),\pte
+#endif
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
 	STREG		\pte,0(\ptep)
@@ -1111,11 +1148,13 @@
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1135,11 +1174,13 @@
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1161,7 +1202,8 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1172,6 +1214,7 @@
 	idtlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1192,7 +1235,8 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1204,6 +1248,7 @@
 	idtlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1224,13 +1269,15 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1250,13 +1297,15 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 	
         idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1357,11 +1406,13 @@
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1379,11 +1430,13 @@
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1405,7 +1458,8 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1416,6 +1470,7 @@
 	iitlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1427,7 +1482,8 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1438,6 +1494,7 @@
 	iitlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1459,13 +1516,15 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0	
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1477,13 +1536,15 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1507,29 +1568,13 @@
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_20w
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_20w:
-	LDCW		0(t0),t1
-	cmpib,COND(=)         0,t1,dbit_spin_20w
-	nop
-
-dbit_nolock_20w:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_20w
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_20w:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
@@ -1543,18 +1588,8 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_11
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_11:
-	LDCW		0(t0),t1
-	cmpib,=         0,t1,dbit_spin_11
-	nop
-
-dbit_nolock_11:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1565,13 +1600,7 @@
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_11
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_11:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
@@ -1583,32 +1612,15 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_20
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_20:
-	LDCW		0(t0),t1
-	cmpib,=         0,t1,dbit_spin_20
-	nop
-
-dbit_nolock_20:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
         idtlbt          pte,prot
-
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_20
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_20:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index f7752f6..9e2d2e4 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -222,6 +222,7 @@
 	{HPHW_NPROC,0x5DD,0x4,0x81,"Duet W2"},
 	{HPHW_NPROC,0x5DE,0x4,0x81,"Piccolo W+"},
 	{HPHW_NPROC,0x5DF,0x4,0x81,"Cantata W2"},
+	{HPHW_NPROC,0x5DF,0x0,0x00,"Marcato W+? (rp5470)"},
 	{HPHW_NPROC,0x5E0,0x4,0x91,"Cantata DC- W2"},
 	{HPHW_NPROC,0x5E1,0x4,0x91,"Crescendo DC- W2"},
 	{HPHW_NPROC,0x5E2,0x4,0x91,"Crescendo 650 W2"},
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index e255db0..2e6443b 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -27,11 +27,11 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/seq_file.h>
-#include <linux/spinlock.h>
 #include <linux/types.h>
 #include <asm/io.h>
 
 #include <asm/smp.h>
+#include <asm/ldcw.h>
 
 #undef PARISC_IRQ_CR16_COUNTS
 
@@ -166,22 +166,36 @@
 	seq_printf(p, "%*s: ", prec, "STK");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->kernel_stack_usage);
-	seq_printf(p, "  Kernel stack usage\n");
+	seq_puts(p, "  Kernel stack usage\n");
+# ifdef CONFIG_IRQSTACKS
+	seq_printf(p, "%*s: ", prec, "IST");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_stack_usage);
+	seq_puts(p, "  Interrupt stack usage\n");
+# endif
 #endif
 #ifdef CONFIG_SMP
 	seq_printf(p, "%*s: ", prec, "RES");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
-	seq_printf(p, "  Rescheduling interrupts\n");
+	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
-	seq_printf(p, "  Function call interrupts\n");
+	seq_puts(p, "  Function call interrupts\n");
 #endif
+	seq_printf(p, "%*s: ", prec, "UAH");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_unaligned_count);
+	seq_puts(p, "  Unaligned access handler traps\n");
+	seq_printf(p, "%*s: ", prec, "FPA");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_fpassist_count);
+	seq_puts(p, "  Floating point assist traps\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
-	seq_printf(p, "  TLB shootdowns\n");
+	seq_puts(p, "  TLB shootdowns\n");
 	return 0;
 }
 
@@ -366,6 +380,24 @@
 	return (BITS_PER_LONG - bit) + TIMER_IRQ;
 }
 
+#ifdef CONFIG_IRQSTACKS
+/*
+ * IRQ STACK - used for irq handler
+ */
+#define IRQ_STACK_SIZE      (4096 << 2) /* 16k irq stack size */
+
+union irq_stack_union {
+	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];
+	volatile unsigned int slock[4];
+	volatile unsigned int lock[1];
+};
+
+DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = {
+		.slock = { 1,1,1,1 },
+	};
+#endif
+
+
 int sysctl_panic_on_stackoverflow = 1;
 
 static inline void stack_overflow_check(struct pt_regs *regs)
@@ -378,6 +410,7 @@
 	unsigned long sp = regs->gr[30];
 	unsigned long stack_usage;
 	unsigned int *last_usage;
+	int cpu = smp_processor_id();
 
 	/* if sr7 != 0, we interrupted a userspace process which we do not want
 	 * to check for stack overflow. We will only check the kernel stack. */
@@ -386,7 +419,31 @@
 
 	/* calculate kernel stack usage */
 	stack_usage = sp - stack_start;
-	last_usage = &per_cpu(irq_stat.kernel_stack_usage, smp_processor_id());
+#ifdef CONFIG_IRQSTACKS
+	if (likely(stack_usage <= THREAD_SIZE))
+		goto check_kernel_stack; /* found kernel stack */
+
+	/* check irq stack usage */
+	stack_start = (unsigned long) &per_cpu(irq_stack_union, cpu).stack;
+	stack_usage = sp - stack_start;
+
+	last_usage = &per_cpu(irq_stat.irq_stack_usage, cpu);
+	if (unlikely(stack_usage > *last_usage))
+		*last_usage = stack_usage;
+
+	if (likely(stack_usage < (IRQ_STACK_SIZE - STACK_MARGIN)))
+		return;
+
+	pr_emerg("stackcheck: %s will most likely overflow irq stack "
+		 "(sp:%lx, stk bottom-top:%lx-%lx)\n",
+		current->comm, sp, stack_start, stack_start + IRQ_STACK_SIZE);
+	goto panic_check;
+
+check_kernel_stack:
+#endif
+
+	/* check kernel stack usage */
+	last_usage = &per_cpu(irq_stat.kernel_stack_usage, cpu);
 
 	if (unlikely(stack_usage > *last_usage))
 		*last_usage = stack_usage;
@@ -398,31 +455,66 @@
 		 "(sp:%lx, stk bottom-top:%lx-%lx)\n",
 		current->comm, sp, stack_start, stack_start + THREAD_SIZE);
 
+#ifdef CONFIG_IRQSTACKS
+panic_check:
+#endif
 	if (sysctl_panic_on_stackoverflow)
 		panic("low stack detected by irq handler - check messages\n");
 #endif
 }
 
 #ifdef CONFIG_IRQSTACKS
-DEFINE_PER_CPU(union irq_stack_union, irq_stack_union);
+/* in entry.S: */
+void call_on_stack(unsigned long p1, void *func, unsigned long new_stack);
 
 static void execute_on_irq_stack(void *func, unsigned long param1)
 {
-	unsigned long *irq_stack_start;
+	union irq_stack_union *union_ptr;
 	unsigned long irq_stack;
-	int cpu = smp_processor_id();
+	volatile unsigned int *irq_stack_in_use;
 
-	irq_stack_start = &per_cpu(irq_stack_union, cpu).stack[0];
-	irq_stack = (unsigned long) irq_stack_start;
-	irq_stack = ALIGN(irq_stack, 16); /* align for stack frame usage */
+	union_ptr = &per_cpu(irq_stack_union, smp_processor_id());
+	irq_stack = (unsigned long) &union_ptr->stack;
+	irq_stack = ALIGN(irq_stack + sizeof(irq_stack_union.slock),
+			 64); /* align for stack frame usage */
 
-	BUG_ON(*irq_stack_start); /* report bug if we were called recursive. */
-	*irq_stack_start = 1;
+	/* We may be called recursive. If we are already using the irq stack,
+	 * just continue to use it. Use spinlocks to serialize
+	 * the irq stack usage.
+	 */
+	irq_stack_in_use = (volatile unsigned int *)__ldcw_align(union_ptr);
+	if (!__ldcw(irq_stack_in_use)) {
+		void (*direct_call)(unsigned long p1) = func;
+
+		/* We are using the IRQ stack already.
+		 * Do direct call on current stack. */
+		direct_call(param1);
+		return;
+	}
 
 	/* This is where we switch to the IRQ stack. */
 	call_on_stack(param1, func, irq_stack);
 
-	*irq_stack_start = 0;
+	/* free up irq stack usage. */
+	*irq_stack_in_use = 1;
+}
+
+asmlinkage void do_softirq(void)
+{
+	__u32 pending;
+	unsigned long flags;
+
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+
+	pending = local_softirq_pending();
+
+	if (pending)
+		execute_on_irq_stack(__do_softirq, 0);
+
+	local_irq_restore(flags);
 }
 #endif /* CONFIG_IRQSTACKS */
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 5e1de60..36d7f40 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -605,14 +605,14 @@
 	convert_phys_for_tlb_insert20 %r26	/* convert phys addr to tlb insert format */
 	convert_phys_for_tlb_insert20 %r23	/* convert phys addr to tlb insert format */
 	depd		%r24,63,22, %r28	/* Form aliased virtual address 'to' */
-	depdi		0, 63,PAGE_SHIFT, %r28  /* Clear any offset bits */
+	depdi		0, 63,PAGE_SHIFT, %r28	/* Clear any offset bits */
 	copy		%r28, %r29
 	depdi		1, 41,1, %r29		/* Form aliased virtual address 'from' */
 #else
 	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
 	extrw,u		%r23, 24,25, %r23	/* convert phys addr to tlb insert format */
 	depw		%r24, 31,22, %r28	/* Form aliased virtual address 'to' */
-	depwi		0, 31,12, %r28		/* Clear any offset bits */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 	copy		%r28, %r29
 	depwi		1, 9,1, %r29		/* Form aliased virtual address 'from' */
 #endif
@@ -762,7 +762,7 @@
 #else
 	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
 	depw		%r25, 31,22, %r28	/* Form aliased virtual address 'to' */
-	depwi		0, 31,12, %r28		/* Clear any offset bits */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #endif
 
 	/* Purge any old translation */
@@ -846,7 +846,7 @@
 #else
 	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
 	depw		%r25, 31,22, %r28	/* Form aliased virtual address 'to' */
-	depwi		0, 31,12, %r28		/* Clear any offset bits */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #endif
 
 	/* Purge any old translation */
@@ -918,11 +918,11 @@
 #endif
 	convert_phys_for_tlb_insert20 %r26	/* convert phys addr to tlb insert format */
 	depd		%r25, 63,22, %r28	/* Form aliased virtual address 'to' */
-	depdi		0, 63,PAGE_SHIFT, %r28  /* Clear any offset bits */
+	depdi		0, 63,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #else
 	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
 	depw		%r25, 31,22, %r28	/* Form aliased virtual address 'to' */
-	depwi		0, 31,12, %r28		/* Clear any offset bits */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #endif
 
 	/* Purge any old translation */
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index fe41a98..04e47c6 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -646,6 +646,7 @@
 	case 14:
 		/* Assist Exception Trap, i.e. floating point exception. */
 		die_if_kernel("Floating point exception", regs, 0); /* quiet */
+		__inc_irq_stat(irq_fpassist_count);
 		handle_fpe(regs);
 		return;
 
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 234e368..d7c0acb 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -27,6 +27,7 @@
 #include <linux/signal.h>
 #include <linux/ratelimit.h>
 #include <asm/uaccess.h>
+#include <asm/hardirq.h>
 
 /* #define DEBUG_UNALIGNED 1 */
 
@@ -454,6 +455,8 @@
 	struct siginfo si;
 	register int flop=0;	/* true if this is a flop */
 
+	__inc_irq_stat(irq_unaligned_count);
+
 	/* log a message with pacing */
 	if (user_mode(regs)) {
 		if (current->thread.flags & PARISC_UAC_SIGBUS) {
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ce939ac..1c96564 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -1069,7 +1069,7 @@
 {
 	int do_recycle;
 
-	inc_irq_stat(irq_tlb_count);
+	__inc_irq_stat(irq_tlb_count);
 	do_recycle = 0;
 	spin_lock(&sid_lock);
 	if (dirty_space_ids > RECYCLE_THRESHOLD) {
@@ -1090,7 +1090,7 @@
 #else
 void flush_tlb_all(void)
 {
-	inc_irq_stat(irq_tlb_count);
+	__inc_irq_stat(irq_tlb_count);
 	spin_lock(&sid_lock);
 	flush_tlb_all_local(NULL);
 	recycle_sids();
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 5416e28..863d877 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -262,8 +262,31 @@
 	  Select this to enable early debugging for the PowerNV platform
 	  using an "hvsi" console
 
+config PPC_EARLY_DEBUG_MEMCONS
+	bool "In memory console"
+	help
+	  Select this to enable early debugging using an in memory console.
+	  This console provides input and output buffers stored within the
+	  kernel BSS and should be safe to select on any system. A debugger
+	  can then be used to read kernel output or send input to the console.
 endchoice
 
+config PPC_MEMCONS_OUTPUT_SIZE
+	int "In memory console output buffer size"
+	depends on PPC_EARLY_DEBUG_MEMCONS
+	default 4096
+	help
+	  Selects the size of the output buffer (in bytes) of the in memory
+	  console.
+
+config PPC_MEMCONS_INPUT_SIZE
+	int "In memory console input buffer size"
+	depends on PPC_EARLY_DEBUG_MEMCONS
+	default 128
+	help
+	  Selects the size of the input buffer (in bytes) of the in memory
+	  console.
+
 config PPC_EARLY_DEBUG_OPAL
 	def_bool y
 	depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index f791962..139a830 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -136,7 +136,6 @@
 CONFIG_USB_HIDDEV=y
 CONFIG_USB=m
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_SUSPEND=y
 CONFIG_USB_MON=m
 CONFIG_USB_EHCI_HCD=m
 # CONFIG_USB_EHCI_HCD_PPC_OF is not set
diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
new file mode 100644
index 0000000..b6f5a33
--- /dev/null
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
+#define _ASM_POWERPC_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#define SCHEDULE_USER bl	.schedule_user
+#else
+#define SCHEDULE_USER bl	.schedule
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 0df5464..681bc03 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -52,6 +52,7 @@
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
+#define FW_FEATURE_OPALv3	ASM_CONST(0x0000000400000000)
 
 #ifndef __ASSEMBLY__
 
@@ -69,7 +70,8 @@
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
-	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
+	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 |
+		FW_FEATURE_OPALv3,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index d615b28..ba713f1 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -96,11 +96,12 @@
 #endif
 
 #define hard_irq_disable()	do {			\
+	u8 _was_enabled = get_paca()->soft_enabled;	\
 	__hard_irq_disable();				\
-	if (local_paca->soft_enabled)			\
-		trace_hardirqs_off();			\
 	get_paca()->soft_enabled = 0;			\
 	get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;	\
+	if (_was_enabled)				\
+		trace_hardirqs_off();			\
 } while(0)
 
 static inline bool lazy_irq_pending(void)
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index b6c8b58..cbb9305 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -243,7 +243,8 @@
 
 enum OpalThreadStatus {
 	OPAL_THREAD_INACTIVE = 0x0,
-	OPAL_THREAD_STARTED = 0x1
+	OPAL_THREAD_STARTED = 0x1,
+	OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */
 };
 
 enum OpalPciBusCompare {
@@ -563,6 +564,8 @@
 
 extern int opal_machine_check(struct pt_regs *regs);
 
+extern void opal_shutdown(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_H */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 8b11b5b..2c1d8cb 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -174,6 +174,8 @@
 /* Get the pointer to a device_node's pci_dn */
 #define PCI_DN(dn)	((struct pci_dn *) (dn)->data)
 
+extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
+
 extern void * update_dn_pci_info(struct device_node *dn, void *data);
 
 static inline int pci_device_from_OF_node(struct device_node *np,
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 91acb12..b66ae72 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -186,7 +186,7 @@
 
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE);
+	return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index d7e67ca..594db6b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -284,6 +284,12 @@
 	unsigned long	ebbrr;
 	unsigned long	ebbhr;
 	unsigned long	bescr;
+	unsigned long	siar;
+	unsigned long	sdar;
+	unsigned long	sier;
+	unsigned long	mmcr0;
+	unsigned long	mmcr2;
+	unsigned long	mmcra;
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 3e13e23..d836d94 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -47,7 +47,7 @@
  * generic accessors and iterators here
  */
 #define __real_pte(e,p) 	((real_pte_t) { \
-			(e), ((e) & _PAGE_COMBO) ? \
+			(e), (pte_val(e) & _PAGE_COMBO) ? \
 				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
 #define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
         (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index a8bc2bb..34fd704 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -264,6 +264,8 @@
 extern void rtas_initialize(void);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
+extern int rtas_online_cpus_mask(cpumask_var_t cpus);
+extern int rtas_offline_cpus_mask(cpumask_var_t cpus);
 extern int rtas_ibm_suspend_me(struct rtas_args *);
 
 struct rtc_time;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8ceea14..ba7b197 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -97,7 +97,7 @@
 #define TIF_PERFMON_CTXSW	6	/* perfmon needs ctxsw calls */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
-#define TIF_MEMDIE		9	/* is terminating due to OOM killer */
+#define TIF_NOHZ		9	/* in adaptive nohz mode */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -106,6 +106,7 @@
 #define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
 #define TIF_EMULATE_STACK_STORE	16	/* Is an instruction emulation
 						for stack store? */
+#define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -124,8 +125,10 @@
 #define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
+#define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
+				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
+				 _TIF_NOHZ)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 5a7510e..dc59091 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -52,6 +52,7 @@
 extern void __init udbg_init_cpm(void);
 extern void __init udbg_init_usbgecko(void);
 extern void __init udbg_init_wsp(void);
+extern void __init udbg_init_memcons(void);
 extern void __init udbg_init_ehv_bc(void);
 extern void __init udbg_init_ps3gelic(void);
 extern void __init udbg_init_debug_opal_raw(void);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b51a97c..6f16ffa 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -127,6 +127,12 @@
 	DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
 	DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
 	DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
+	DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
+	DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
+	DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
+	DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
+	DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
+	DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra));
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index a283b64..18b5b9c 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -135,8 +135,12 @@
 	blr
 
 __init_TLB:
-	/* Clear the TLB */
-	li	r6,128
+	/*
+	 * Clear the TLB using the "IS 3" form of tlbiel instruction
+	 * (invalidate by congruence class). P7 has 128 CCs, P8 has 512
+	 * so we just always do 512
+	 */
+	li	r6,512
 	mtctr	r6
 	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e514de5..d22e73e 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -439,8 +439,6 @@
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	li	r3,0
-	stw	r3,0(r1)
 	mtlr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 915fbb4..0e9095e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -33,6 +33,7 @@
 #include <asm/irqflags.h>
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
+#include <asm/context_tracking.h>
 
 /*
  * System calls.
@@ -376,8 +377,6 @@
 _GLOBAL(ret_from_kernel_thread)
 	bl	.schedule_tail
 	REST_NVGPRS(r1)
-	li	r3,0
-	std	r3,0(r1)
 	ld	r14, 0(r14)
 	mtlr	r14
 	mr	r3,r15
@@ -466,6 +465,20 @@
 	std	r0, THREAD_EBBHR(r3)
 	mfspr	r0, SPRN_EBBRR
 	std	r0, THREAD_EBBRR(r3)
+
+	/* PMU registers made user read/(write) by EBB */
+	mfspr	r0, SPRN_SIAR
+	std	r0, THREAD_SIAR(r3)
+	mfspr	r0, SPRN_SDAR
+	std	r0, THREAD_SDAR(r3)
+	mfspr	r0, SPRN_SIER
+	std	r0, THREAD_SIER(r3)
+	mfspr	r0, SPRN_MMCR0
+	std	r0, THREAD_MMCR0(r3)
+	mfspr	r0, SPRN_MMCR2
+	std	r0, THREAD_MMCR2(r3)
+	mfspr	r0, SPRN_MMCRA
+	std	r0, THREAD_MMCRA(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 #endif
 
@@ -561,6 +574,20 @@
 	ld	r0, THREAD_EBBRR(r4)
 	mtspr	SPRN_EBBRR, r0
 
+	/* PMU registers made user read/(write) by EBB */
+	ld	r0, THREAD_SIAR(r4)
+	mtspr	SPRN_SIAR, r0
+	ld	r0, THREAD_SDAR(r4)
+	mtspr	SPRN_SDAR, r0
+	ld	r0, THREAD_SIER(r4)
+	mtspr	SPRN_SIER, r0
+	ld	r0, THREAD_MMCR0(r4)
+	mtspr	SPRN_MMCR0, r0
+	ld	r0, THREAD_MMCR2(r4)
+	mtspr	SPRN_MMCR2, r0
+	ld	r0, THREAD_MMCRA(r4)
+	mtspr	SPRN_MMCRA, r0
+
 	ld	r0,THREAD_TAR(r4)
 	mtspr	SPRN_TAR,r0
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
@@ -634,7 +661,7 @@
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts
-	bl	.schedule
+	SCHEDULE_USER
 	b	.ret_from_except_lite
 
 1:	bl	.save_nvgprs
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 42a756e..645170a 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -489,7 +489,7 @@
 	 */
 
 	mfspr	r14,SPRN_DBSR		/* check single-step/branch taken */
-	andis.	r15,r14,DBSR_IC@h
+	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -500,7 +500,7 @@
 	bge+	cr1,1f
 
 	/* here it looks like we got an inappropriate debug exception. */
-	lis	r14,DBSR_IC@h		/* clear the IC event */
+	lis	r14,(DBSR_IC|DBSR_BT)@h		/* clear the event */
 	rlwinm	r11,r11,0,~MSR_DE	/* clear DE in the CSRR1 value */
 	mtspr	SPRN_DBSR,r14
 	mtspr	SPRN_CSRR1,r11
@@ -555,7 +555,7 @@
 	 */
 
 	mfspr	r14,SPRN_DBSR		/* check single-step/branch taken */
-	andis.	r15,r14,DBSR_IC@h
+	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -566,7 +566,7 @@
 	bge+	cr1,1f
 
 	/* here it looks like we got an inappropriate debug exception. */
-	lis	r14,DBSR_IC@h		/* clear the IC event */
+	lis	r14,(DBSR_IC|DBSR_BT)@h		/* clear the event */
 	rlwinm	r11,r11,0,~MSR_DE	/* clear DE in the DSRR1 value */
 	mtspr	SPRN_DBSR,r14
 	mtspr	SPRN_DSRR1,r11
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 466a290..611acdf 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/cpu.h>
+#include <linux/hardirq.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -335,10 +336,13 @@
 	pr_debug("kexec: Starting switchover sequence.\n");
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
+	 * We setup preempt_count to avoid using VMX in memcpy.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
 	kexec_stack.thread_info.task = current_thread_info()->task;
 	kexec_stack.thread_info.flags = 0;
+	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
+	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
 	 * it.  Also poison per_cpu_offset to catch anyone using non-static
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 19e096b..e469f30 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -657,6 +657,17 @@
 	li	r3,2
 	blr
 
+_GLOBAL(__bswapdi2)
+	rotlwi  r9,r4,8
+	rotlwi  r10,r3,8
+	rlwimi  r9,r4,24,0,7
+	rlwimi  r10,r3,24,0,7
+	rlwimi  r9,r4,24,16,23
+	rlwimi  r10,r3,24,16,23
+	mr      r3,r9
+	mr      r4,r10
+	blr
+
 _GLOBAL(abs)
 	srawi	r4,r3,31
 	xor	r3,r3,r4
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 5cfa800..6820e45 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -234,6 +234,17 @@
 	isync
 	blr
 
+_GLOBAL(__bswapdi2)
+	srdi	r8,r3,32
+	rlwinm	r7,r3,8,0xffffffff
+	rlwimi	r7,r3,24,0,7
+	rlwinm	r9,r8,8,0xffffffff
+	rlwimi	r7,r3,24,16,23
+	rlwimi	r9,r8,24,0,7
+	rlwimi	r9,r8,24,16,23
+	sldi	r7,r7,32
+	or	r3,r7,r9
+	blr
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
 /*
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f5c5c90..e9acf50 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -359,7 +359,6 @@
 				      enum pci_mmap_state mmap_state,
 				      int write_combine)
 {
-	unsigned long prot = pgprot_val(protection);
 
 	/* Write combine is always 0 on non-memory space mappings. On
 	 * memory space, if the user didn't pass 1, we check for a
@@ -376,9 +375,9 @@
 
 	/* XXX would be nice to have a way to ask for write-through */
 	if (write_combine)
-		return pgprot_noncached_wc(prot);
+		return pgprot_noncached_wc(protection);
 	else
-		return pgprot_noncached(prot);
+		return pgprot_noncached(protection);
 }
 
 /*
@@ -1521,9 +1520,10 @@
 	for (i = 0; i < 3; ++i) {
 		res = &hose->mem_resources[i];
 		if (!res->flags) {
-			printk(KERN_ERR "PCI: Memory resource 0 not set for "
-			       "host bridge %s (domain %d)\n",
-			       hose->dn->full_name, hose->global_number);
+			if (i == 0)
+				printk(KERN_ERR "PCI: Memory resource 0 not set for "
+				       "host bridge %s (domain %d)\n",
+				       hose->dn->full_name, hose->global_number);
 			continue;
 		}
 		offset = hose->mem_offset[i];
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 873050d..2e86296 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -266,3 +266,13 @@
 }
 EXPORT_SYMBOL(pcibus_to_node);
 #endif
+
+static void quirk_radeon_32bit_msi(struct pci_dev *dev)
+{
+	struct pci_dn *pdn = pci_get_pdn(dev);
+
+	if (pdn)
+		pdn->force_32bit_msi = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index e7af165..df03844 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -32,6 +32,14 @@
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
 
+struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
+{
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+	if (!dn)
+		return NULL;
+	return PCI_DN(dn);
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 78b8766..c296665 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -143,7 +143,8 @@
 int __ucmpdi2(unsigned long long, unsigned long long);
 EXPORT_SYMBOL(__ucmpdi2);
 #endif
-
+long long __bswapdi2(long long);
+EXPORT_SYMBOL(__bswapdi2);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ceb4e7b..a902723 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,6 +339,13 @@
 
 static void prime_debug_regs(struct thread_struct *thread)
 {
+	/*
+	 * We could have inherited MSR_DE from userspace, since
+	 * it doesn't get cleared on exception entry.  Make sure
+	 * MSR_DE is clear before we enable any debug events.
+	 */
+	mtmsr(mfmsr() & ~MSR_DE);
+
 	mtspr(SPRN_IAC1, thread->iac1);
 	mtspr(SPRN_IAC2, thread->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
@@ -971,6 +978,7 @@
 	 * do some house keeping and then return from the fork or clone
 	 * system call, using the stack frame created above.
 	 */
+	((unsigned long *)sp)[0] = 0;
 	sp -= sizeof(struct pt_regs);
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 3b14d32..98c2fc1 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <trace/syscall.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/context_tracking.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -1788,6 +1789,8 @@
 {
 	long ret = 0;
 
+	user_exit();
+
 	secure_computing_strict(regs->gpr[0]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
@@ -1832,4 +1835,6 @@
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
+
+	user_enter();
 }
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 1fd6e7b..52add6f 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
+#include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
@@ -807,6 +808,95 @@
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
+enum rtas_cpu_state {
+	DOWN,
+	UP,
+};
+
+#ifndef CONFIG_SMP
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	if (!cpumask_empty(cpus)) {
+		cpumask_clear(cpus);
+		return -EINVAL;
+	} else
+		return 0;
+}
+#else
+/* On return cpumask will be altered to indicate CPUs changed.
+ * CPUs with states changed will be set in the mask,
+ * CPUs with status unchanged will be unset in the mask. */
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	int cpu;
+	int cpuret = 0;
+	int ret = 0;
+
+	if (cpumask_empty(cpus))
+		return 0;
+
+	for_each_cpu(cpu, cpus) {
+		switch (state) {
+		case DOWN:
+			cpuret = cpu_down(cpu);
+			break;
+		case UP:
+			cpuret = cpu_up(cpu);
+			break;
+		}
+		if (cpuret) {
+			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
+					__func__,
+					((state == UP) ? "up" : "down"),
+					cpu, cpuret);
+			if (!ret)
+				ret = cpuret;
+			if (state == UP) {
+				/* clear bits for unchanged cpus, return */
+				cpumask_shift_right(cpus, cpus, cpu);
+				cpumask_shift_left(cpus, cpus, cpu);
+				break;
+			} else {
+				/* clear bit for unchanged cpu, continue */
+				cpumask_clear_cpu(cpu, cpus);
+			}
+		}
+	}
+
+	return ret;
+}
+#endif
+
+int rtas_online_cpus_mask(cpumask_var_t cpus)
+{
+	int ret;
+
+	ret = rtas_cpu_state_change_mask(UP, cpus);
+
+	if (ret) {
+		cpumask_var_t tmp_mask;
+
+		if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY))
+			return ret;
+
+		/* Use tmp_mask to preserve cpus mask from first failure */
+		cpumask_copy(tmp_mask, cpus);
+		rtas_offline_cpus_mask(tmp_mask);
+		free_cpumask_var(tmp_mask);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(rtas_online_cpus_mask);
+
+int rtas_offline_cpus_mask(cpumask_var_t cpus)
+{
+	return rtas_cpu_state_change_mask(DOWN, cpus);
+}
+EXPORT_SYMBOL(rtas_offline_cpus_mask);
+
 int rtas_ibm_suspend_me(struct rtas_args *args)
 {
 	long state;
@@ -814,6 +904,8 @@
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 	struct rtas_suspend_me_data data;
 	DECLARE_COMPLETION_ONSTACK(done);
+	cpumask_var_t offline_mask;
+	int cpuret;
 
 	if (!rtas_service_present("ibm,suspend-me"))
 		return -ENOSYS;
@@ -837,11 +929,24 @@
 		return 0;
 	}
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	atomic_set(&data.working, 0);
 	atomic_set(&data.done, 0);
 	atomic_set(&data.error, 0);
 	data.token = rtas_token("ibm,suspend-me");
 	data.complete = &done;
+
+	/* All present CPUs must be online */
+	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
+	cpuret = rtas_online_cpus_mask(offline_mask);
+	if (cpuret) {
+		pr_err("%s: Could not bring present CPUs online.\n", __func__);
+		atomic_set(&data.error, cpuret);
+		goto out;
+	}
+
 	stop_topology_update();
 
 	/* Call function on all CPUs.  One of us will make the
@@ -857,6 +962,14 @@
 
 	start_topology_update();
 
+	/* Take down CPUs not online prior to suspend */
+	cpuret = rtas_offline_cpus_mask(offline_mask);
+	if (cpuret)
+		pr_warn("%s: Could not restore CPUs to offline state.\n",
+				__func__);
+
+out:
+	free_cpumask_var(offline_mask);
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 5b30224..2f3cdb0 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -89,6 +89,7 @@
 
 /* Array sizes */
 #define VALIDATE_BUF_SIZE 4096    
+#define VALIDATE_MSG_LEN  256
 #define RTAS_MSG_MAXLEN   64
 
 /* Quirk - RTAS requires 4k list length and block size */
@@ -466,7 +467,7 @@
 }
 
 static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, 
-		                   char *msg)
+		                   char *msg, int msglen)
 {
 	int n;
 
@@ -474,7 +475,8 @@
 		n = sprintf(msg, "%d\n", args_buf->update_results);
 		if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) ||
 		    (args_buf->update_results == VALIDATE_TMP_UPDATE))
-			n += sprintf(msg + n, "%s\n", args_buf->buf);
+			n += snprintf(msg + n, msglen - n, "%s\n",
+					args_buf->buf);
 	} else {
 		n = sprintf(msg, "%d\n", args_buf->status);
 	}
@@ -486,11 +488,11 @@
 {
 	struct rtas_validate_flash_t *const args_buf =
 		&rtas_validate_flash_data;
-	char msg[RTAS_MSG_MAXLEN];
+	char msg[VALIDATE_MSG_LEN];
 	int msglen;
 
 	mutex_lock(&rtas_validate_flash_mutex);
-	msglen = get_validate_flash_msg(args_buf, msg);
+	msglen = get_validate_flash_msg(args_buf, msg, VALIDATE_MSG_LEN);
 	mutex_unlock(&rtas_validate_flash_mutex);
 
 	return simple_read_from_buffer(buf, count, ppos, msg, msglen);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index cf12eae..577a8aa 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -13,6 +13,7 @@
 #include <linux/signal.h>
 #include <linux/uprobes.h>
 #include <linux/key.h>
+#include <linux/context_tracking.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -24,7 +25,7 @@
  * through debug.exception-trace sysctl.
  */
 
-int show_unhandled_signals = 0;
+int show_unhandled_signals = 1;
 
 /*
  * Allocate space for the signal frame
@@ -159,6 +160,8 @@
 
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
+	user_exit();
+
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
@@ -169,4 +172,6 @@
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	user_enter();
 }
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 83efa2f..a7a648f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -35,6 +35,7 @@
 #include <linux/kdebug.h>
 #include <linux/debugfs.h>
 #include <linux/ratelimit.h>
+#include <linux/context_tracking.h>
 
 #include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
@@ -667,6 +668,7 @@
 
 void machine_check_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	int recover = 0;
 
 	__get_cpu_var(irq_stat).mce_exceptions++;
@@ -683,7 +685,7 @@
 		recover = cur_cpu_spec->machine_check(regs);
 
 	if (recover > 0)
-		return;
+		goto bail;
 
 #if defined(CONFIG_8xx) && defined(CONFIG_PCI)
 	/* the qspan pci read routines can cause machine checks -- Cort
@@ -693,20 +695,23 @@
 	 * -- BenH
 	 */
 	bad_page_fault(regs, regs->dar, SIGBUS);
-	return;
+	goto bail;
 #endif
 
 	if (debugger_fault_handler(regs))
-		return;
+		goto bail;
 
 	if (check_io_access(regs))
-		return;
+		goto bail;
 
 	die("Machine check", regs, SIGBUS);
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		panic("Unrecoverable Machine check");
+
+bail:
+	exception_exit(prev_state);
 }
 
 void SMIException(struct pt_regs *regs)
@@ -716,20 +721,29 @@
 
 void unknown_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
 	_exception(SIGTRAP, regs, 0, 0);
+
+	exception_exit(prev_state);
 }
 
 void instruction_breakpoint_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto bail;
 	if (debugger_iabr_match(regs))
-		return;
+		goto bail;
 	_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void RunModeException(struct pt_regs *regs)
@@ -739,15 +753,20 @@
 
 void __kprobes single_step_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	clear_single_step(regs);
 
 	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto bail;
 	if (debugger_sstep(regs))
-		return;
+		goto bail;
 
 	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 /*
@@ -1005,6 +1024,7 @@
 
 void __kprobes program_check_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
 	extern int do_mathemu(struct pt_regs *regs);
 
@@ -1014,26 +1034,26 @@
 	if (reason & REASON_FP) {
 		/* IEEE FP exception */
 		parse_fpe(regs);
-		return;
+		goto bail;
 	}
 	if (reason & REASON_TRAP) {
 		/* Debugger is first in line to stop recursive faults in
 		 * rcu_lock, notify_die, or atomic_notifier_call_chain */
 		if (debugger_bpt(regs))
-			return;
+			goto bail;
 
 		/* trap exception */
 		if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
 				== NOTIFY_STOP)
-			return;
+			goto bail;
 
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			return;
+			goto bail;
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
+		goto bail;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1049,7 +1069,7 @@
 		if (!user_mode(regs) &&
 		    report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			return;
+			goto bail;
 		}
 		/* If usermode caused this, it's done something illegal and
 		 * gets a SIGILL slap on the wrist.  We call it an illegal
@@ -1059,7 +1079,7 @@
 		 */
 		if (user_mode(regs)) {
 			_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
-			return;
+			goto bail;
 		} else {
 			printk(KERN_EMERG "Unexpected TM Bad Thing exception "
 			       "at %lx (msr 0x%x)\n", regs->nip, reason);
@@ -1083,16 +1103,16 @@
 	switch (do_mathemu(regs)) {
 	case 0:
 		emulate_single_step(regs);
-		return;
+		goto bail;
 	case 1: {
 			int code = 0;
 			code = __parse_fpscr(current->thread.fpscr.val);
 			_exception(SIGFPE, regs, code, regs->nip);
-			return;
+			goto bail;
 		}
 	case -EFAULT:
 		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
+		goto bail;
 	}
 	/* fall through on any other errors */
 #endif /* CONFIG_MATH_EMULATION */
@@ -1103,10 +1123,10 @@
 		case 0:
 			regs->nip += 4;
 			emulate_single_step(regs);
-			return;
+			goto bail;
 		case -EFAULT:
 			_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-			return;
+			goto bail;
 		}
 	}
 
@@ -1114,10 +1134,14 @@
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void alignment_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	int sig, code, fixed = 0;
 
 	/* We restore the interrupt state now */
@@ -1131,7 +1155,7 @@
 	if (fixed == 1) {
 		regs->nip += 4;	/* skip over emulated instruction */
 		emulate_single_step(regs);
-		return;
+		goto bail;
 	}
 
 	/* Operand address was bad */
@@ -1146,6 +1170,9 @@
 		_exception(sig, regs, code, regs->dar);
 	else
 		bad_page_fault(regs, regs->dar, sig);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void StackOverflow(struct pt_regs *regs)
@@ -1174,23 +1201,32 @@
 
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
 			  "%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
+
+	exception_exit(prev_state);
 }
 
 void altivec_unavailable_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (user_mode(regs)) {
 		/* A user program has executed an altivec instruction,
 		   but this kernel doesn't support altivec. */
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
+		goto bail;
 	}
 
 	printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
 			"%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void vsx_unavailable_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 13b8670..9d3fdcd 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -64,6 +64,9 @@
 	udbg_init_usbgecko();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
 	udbg_init_wsp();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS)
+	/* In memory console */
+	udbg_init_memcons();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC)
 	udbg_init_ehv_bc();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 229951f..8726779 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -32,6 +32,7 @@
 #include <linux/perf_event.h>
 #include <linux/magic.h>
 #include <linux/ratelimit.h>
+#include <linux/context_tracking.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -196,6 +197,7 @@
 int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 			    unsigned long error_code)
 {
+	enum ctx_state prev_state = exception_enter();
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -204,6 +206,7 @@
 	int trap = TRAP(regs);
  	int is_exec = trap == 0x400;
 	int fault;
+	int rc = 0;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
 	/*
@@ -230,28 +233,30 @@
 	 * look at it
 	 */
 	if (error_code & ICSWX_DSI_UCT) {
-		int rc = acop_handle_fault(regs, address, error_code);
+		rc = acop_handle_fault(regs, address, error_code);
 		if (rc)
-			return rc;
+			goto bail;
 	}
 #endif /* CONFIG_PPC_ICSWX */
 
 	if (notify_page_fault(regs))
-		return 0;
+		goto bail;
 
 	if (unlikely(debugger_fault_handler(regs)))
-		return 0;
+		goto bail;
 
 	/* On a kernel SLB miss we can only check for a valid exception entry */
-	if (!user_mode(regs) && (address >= TASK_SIZE))
-		return SIGSEGV;
+	if (!user_mode(regs) && (address >= TASK_SIZE)) {
+		rc = SIGSEGV;
+		goto bail;
+	}
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \
 			     defined(CONFIG_PPC_BOOK3S_64))
   	if (error_code & DSISR_DABRMATCH) {
 		/* breakpoint match */
 		do_break(regs, address, error_code);
-		return 0;
+		goto bail;
 	}
 #endif
 
@@ -260,8 +265,10 @@
 		local_irq_enable();
 
 	if (in_atomic() || mm == NULL) {
-		if (!user_mode(regs))
-			return SIGSEGV;
+		if (!user_mode(regs)) {
+			rc = SIGSEGV;
+			goto bail;
+		}
 		/* in_atomic() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
@@ -417,9 +424,11 @@
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		int rc = mm_fault_error(regs, address, fault);
+		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
-			return rc;
+			goto bail;
+		else
+			rc = 0;
 	}
 
 	/*
@@ -454,7 +463,7 @@
 	}
 
 	up_read(&mm->mmap_sem);
-	return 0;
+	goto bail;
 
 bad_area:
 	up_read(&mm->mmap_sem);
@@ -463,7 +472,7 @@
 	/* User mode accesses cause a SIGSEGV */
 	if (user_mode(regs)) {
 		_exception(SIGSEGV, regs, code, address);
-		return 0;
+		goto bail;
 	}
 
 	if (is_exec && (error_code & DSISR_PROTFAULT))
@@ -471,7 +480,11 @@
 				   " page (%lx) - exploit attempt? (uid: %d)\n",
 				   address, from_kuid(&init_user_ns, current_uid()));
 
-	return SIGSEGV;
+	rc = SIGSEGV;
+
+bail:
+	exception_exit(prev_state);
+	return rc;
 
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 88ac0ee..e303a6d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -33,6 +33,7 @@
 #include <linux/init.h>
 #include <linux/signal.h>
 #include <linux/memblock.h>
+#include <linux/context_tracking.h>
 
 #include <asm/processor.h>
 #include <asm/pgtable.h>
@@ -954,6 +955,7 @@
  */
 int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 {
+	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
 	struct mm_struct *mm;
@@ -973,7 +975,8 @@
 		mm = current->mm;
 		if (! mm) {
 			DBG_LOW(" user region with no mm !\n");
-			return 1;
+			rc = 1;
+			goto bail;
 		}
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
@@ -992,19 +995,23 @@
 		/* Not a valid range
 		 * Send the problem up to do_page_fault 
 		 */
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 	DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);
 
 	/* Bad address. */
 	if (!vsid) {
 		DBG_LOW("Bad address!\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 	/* Get pgdir */
 	pgdir = mm->pgd;
-	if (pgdir == NULL)
-		return 1;
+	if (pgdir == NULL) {
+		rc = 1;
+		goto bail;
+	}
 
 	/* Check CPU locality */
 	tmp = cpumask_of(smp_processor_id());
@@ -1027,7 +1034,8 @@
 	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift);
 	if (ptep == NULL || !pte_present(*ptep)) {
 		DBG_LOW(" no PTE !\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 
 	/* Add _PAGE_PRESENT to the required access perm */
@@ -1038,13 +1046,16 @@
 	 */
 	if (access & ~pte_val(*ptep)) {
 		DBG_LOW(" no access !\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 
 #ifdef CONFIG_HUGETLB_PAGE
-	if (hugeshift)
-		return __hash_page_huge(ea, access, vsid, ptep, trap, local,
+	if (hugeshift) {
+		rc = __hash_page_huge(ea, access, vsid, ptep, trap, local,
 					ssize, hugeshift, psize);
+		goto bail;
+	}
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -1124,6 +1135,9 @@
 		pte_val(*(ptep + PTRS_PER_PTE)));
 #endif
 	DBG_LOW(" -> rc=%d\n", rc);
+
+bail:
+	exception_exit(prev_state);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(hash_page);
@@ -1259,6 +1273,8 @@
  */
 void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (user_mode(regs)) {
 #ifdef CONFIG_PPC_SUBPAGE_PROT
 		if (rc == -2)
@@ -1268,6 +1284,8 @@
 			_exception(SIGBUS, regs, BUS_ADRERR, address);
 	} else
 		bad_page_fault(regs, address, SIGBUS);
+
+	exception_exit(prev_state);
 }
 
 long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index c2787bf..a90b9c4 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -215,7 +215,8 @@
 					     unsigned long phys)
 {
 	int  mapped = htab_bolt_mapping(start, start + page_size, phys,
-					PAGE_KERNEL, mmu_vmemmap_psize,
+					pgprot_val(PAGE_KERNEL),
+					mmu_vmemmap_psize,
 					mmu_kernel_ssize);
 	BUG_ON(mapped < 0);
 }
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index c627843..426180b 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -13,11 +13,13 @@
 #include <linux/perf_event.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <asm/reg.h>
 #include <asm/pmc.h>
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
+#include <asm/code-patching.h>
 
 #define BHRB_MAX_ENTRIES	32
 #define BHRB_TARGET		0x0000000000000002
@@ -100,6 +102,10 @@
 	return 1;
 }
 
+static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
+static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
+void power_pmu_flush_branch_stack(void) {}
+static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 #endif /* CONFIG_PPC32 */
 
 static bool regs_use_siar(struct pt_regs *regs)
@@ -308,6 +314,159 @@
 	return 1;
 }
 
+
+/* Reset all possible BHRB entries */
+static void power_pmu_bhrb_reset(void)
+{
+	asm volatile(PPC_CLRBHRB);
+}
+
+static void power_pmu_bhrb_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	if (!ppmu->bhrb_nr)
+		return;
+
+	/* Clear BHRB if we changed task context to avoid data leaks */
+	if (event->ctx->task && cpuhw->bhrb_context != event->ctx) {
+		power_pmu_bhrb_reset();
+		cpuhw->bhrb_context = event->ctx;
+	}
+	cpuhw->bhrb_users++;
+}
+
+static void power_pmu_bhrb_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	if (!ppmu->bhrb_nr)
+		return;
+
+	cpuhw->bhrb_users--;
+	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
+
+	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
+		/* BHRB cannot be turned off when other
+		 * events are active on the PMU.
+		 */
+
+		/* avoid stale pointer */
+		cpuhw->bhrb_context = NULL;
+	}
+}
+
+/* Called from ctxsw to prevent one process's branch entries to
+ * mingle with the other process's entries during context switch.
+ */
+void power_pmu_flush_branch_stack(void)
+{
+	if (ppmu->bhrb_nr)
+		power_pmu_bhrb_reset();
+}
+/* Calculate the to address for a branch */
+static __u64 power_pmu_bhrb_to(u64 addr)
+{
+	unsigned int instr;
+	int ret;
+	__u64 target;
+
+	if (is_kernel_addr(addr))
+		return branch_target((unsigned int *)addr);
+
+	/* Userspace: need copy instruction here then translate it */
+	pagefault_disable();
+	ret = __get_user_inatomic(instr, (unsigned int __user *)addr);
+	if (ret) {
+		pagefault_enable();
+		return 0;
+	}
+	pagefault_enable();
+
+	target = branch_target(&instr);
+	if ((!target) || (instr & BRANCH_ABSOLUTE))
+		return target;
+
+	/* Translate relative branch target from kernel to user address */
+	return target - (unsigned long)&instr + addr;
+}
+
+/* Processing BHRB entries */
+void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+{
+	u64 val;
+	u64 addr;
+	int r_index, u_index, pred;
+
+	r_index = 0;
+	u_index = 0;
+	while (r_index < ppmu->bhrb_nr) {
+		/* Assembly read function */
+		val = read_bhrb(r_index++);
+		if (!val)
+			/* Terminal marker: End of valid BHRB entries */
+			break;
+		else {
+			addr = val & BHRB_EA;
+			pred = val & BHRB_PREDICTION;
+
+			if (!addr)
+				/* invalid entry */
+				continue;
+
+			/* Branches are read most recent first (ie. mfbhrb 0 is
+			 * the most recent branch).
+			 * There are two types of valid entries:
+			 * 1) a target entry which is the to address of a
+			 *    computed goto like a blr,bctr,btar.  The next
+			 *    entry read from the bhrb will be branch
+			 *    corresponding to this target (ie. the actual
+			 *    blr/bctr/btar instruction).
+			 * 2) a from address which is an actual branch.  If a
+			 *    target entry proceeds this, then this is the
+			 *    matching branch for that target.  If this is not
+			 *    following a target entry, then this is a branch
+			 *    where the target is given as an immediate field
+			 *    in the instruction (ie. an i or b form branch).
+			 *    In this case we need to read the instruction from
+			 *    memory to determine the target/to address.
+			 */
+
+			if (val & BHRB_TARGET) {
+				/* Target branches use two entries
+				 * (ie. computed gotos/XL form)
+				 */
+				cpuhw->bhrb_entries[u_index].to = addr;
+				cpuhw->bhrb_entries[u_index].mispred = pred;
+				cpuhw->bhrb_entries[u_index].predicted = ~pred;
+
+				/* Get from address in next entry */
+				val = read_bhrb(r_index++);
+				addr = val & BHRB_EA;
+				if (val & BHRB_TARGET) {
+					/* Shouldn't have two targets in a
+					   row.. Reset index and try again */
+					r_index--;
+					addr = 0;
+				}
+				cpuhw->bhrb_entries[u_index].from = addr;
+			} else {
+				/* Branches to immediate field 
+				   (ie I or B form) */
+				cpuhw->bhrb_entries[u_index].from = addr;
+				cpuhw->bhrb_entries[u_index].to =
+					power_pmu_bhrb_to(addr);
+				cpuhw->bhrb_entries[u_index].mispred = pred;
+				cpuhw->bhrb_entries[u_index].predicted = ~pred;
+			}
+			u_index++;
+
+		}
+	}
+	cpuhw->bhrb_stack.nr = u_index;
+	return;
+}
+
 #endif /* CONFIG_PPC64 */
 
 static void perf_event_interrupt(struct pt_regs *regs);
@@ -904,47 +1063,6 @@
 	return n;
 }
 
-/* Reset all possible BHRB entries */
-static void power_pmu_bhrb_reset(void)
-{
-	asm volatile(PPC_CLRBHRB);
-}
-
-void power_pmu_bhrb_enable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
-
-	if (!ppmu->bhrb_nr)
-		return;
-
-	/* Clear BHRB if we changed task context to avoid data leaks */
-	if (event->ctx->task && cpuhw->bhrb_context != event->ctx) {
-		power_pmu_bhrb_reset();
-		cpuhw->bhrb_context = event->ctx;
-	}
-	cpuhw->bhrb_users++;
-}
-
-void power_pmu_bhrb_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
-
-	if (!ppmu->bhrb_nr)
-		return;
-
-	cpuhw->bhrb_users--;
-	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
-
-	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
-		/* BHRB cannot be turned off when other
-		 * events are active on the PMU.
-		 */
-
-		/* avoid stale pointer */
-		cpuhw->bhrb_context = NULL;
-	}
-}
-
 /*
  * Add a event to the PMU.
  * If all events are not already frozen, then we disable and
@@ -1180,15 +1298,6 @@
 	return 0;
 }
 
-/* Called from ctxsw to prevent one process's branch entries to
- * mingle with the other process's entries during context switch.
- */
-void power_pmu_flush_branch_stack(void)
-{
-	if (ppmu->bhrb_nr)
-		power_pmu_bhrb_reset();
-}
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1458,77 +1567,6 @@
 	.flush_branch_stack = power_pmu_flush_branch_stack,
 };
 
-/* Processing BHRB entries */
-void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
-{
-	u64 val;
-	u64 addr;
-	int r_index, u_index, target, pred;
-
-	r_index = 0;
-	u_index = 0;
-	while (r_index < ppmu->bhrb_nr) {
-		/* Assembly read function */
-		val = read_bhrb(r_index);
-
-		/* Terminal marker: End of valid BHRB entries */
-		if (val == 0) {
-			break;
-		} else {
-			/* BHRB field break up */
-			addr = val & BHRB_EA;
-			pred = val & BHRB_PREDICTION;
-			target = val & BHRB_TARGET;
-
-			/* Probable Missed entry: Not applicable for POWER8 */
-			if ((addr == 0) && (target == 0) && (pred == 1)) {
-				r_index++;
-				continue;
-			}
-
-			/* Real Missed entry: Power8 based missed entry */
-			if ((addr == 0) && (target == 1) && (pred == 1)) {
-				r_index++;
-				continue;
-			}
-
-			/* Reserved condition: Not a valid entry  */
-			if ((addr == 0) && (target == 1) && (pred == 0)) {
-				r_index++;
-				continue;
-			}
-
-			/* Is a target address */
-			if (val & BHRB_TARGET) {
-				/* First address cannot be a target address */
-				if (r_index == 0) {
-					r_index++;
-					continue;
-				}
-
-				/* Update target address for the previous entry */
-				cpuhw->bhrb_entries[u_index - 1].to = addr;
-				cpuhw->bhrb_entries[u_index - 1].mispred = pred;
-				cpuhw->bhrb_entries[u_index - 1].predicted = ~pred;
-
-				/* Dont increment u_index */
-				r_index++;
-			} else {
-				/* Update address, flags for current entry */
-				cpuhw->bhrb_entries[u_index].from = addr;
-				cpuhw->bhrb_entries[u_index].mispred = pred;
-				cpuhw->bhrb_entries[u_index].predicted = ~pred;
-
-				/* Successfully popullated one entry */
-				u_index++;
-				r_index++;
-			}
-		}
-	}
-	cpuhw->bhrb_stack.nr = u_index;
-	return;
-}
-
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a881232..b62aab3 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -128,7 +128,7 @@
 
 config RTAS_PROC
 	bool "Proc interface to RTAS"
-	depends on PPC_RTAS
+	depends on PPC_RTAS && PROC_FS
 	default y
 
 config RTAS_FLASH
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index d3e840d..c24684c 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -6,6 +6,7 @@
 	select PPC_ICP_NATIVE
 	select PPC_P7_NAP
 	select PPC_PCI_CHOICE if EMBEDDED
+	select EPAPR_BOOT
 	default y
 
 config POWERNV_MSI
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index ade4463..628c564 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/slab.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 
@@ -28,6 +29,8 @@
 static struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
+static unsigned int *opal_irqs;
+static unsigned int opal_irq_count;
 
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
@@ -53,7 +56,11 @@
 		 opal.entry, entryp, entrysz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
-	if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		powerpc_firmware_features |= FW_FEATURE_OPALv3;
+		printk("OPAL V3 detected !\n");
+	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
 		printk("OPAL V2 detected !\n");
 	} else {
@@ -144,6 +151,13 @@
 				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
 		len = total_len;
 		rc = opal_console_write(vtermno, &len, data);
+
+		/* Closed or other error drop */
+		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
+		    rc != OPAL_BUSY_EVENT) {
+			written = total_len;
+			break;
+		}
 		if (rc == OPAL_SUCCESS) {
 			total_len -= len;
 			data += len;
@@ -316,6 +330,8 @@
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
 	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
 		 irqs ? (irqlen / 4) : 0);
+	opal_irq_count = irqlen / 4;
+	opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
 	for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
 		unsigned int hwirq = be32_to_cpup(irqs);
 		unsigned int irq = irq_create_mapping(NULL, hwirq);
@@ -327,7 +343,19 @@
 		if (rc)
 			pr_warning("opal: Error %d requesting irq %d"
 				   " (0x%x)\n", rc, irq, hwirq);
+		opal_irqs[i] = irq;
 	}
 	return 0;
 }
 subsys_initcall(opal_init);
+
+void opal_shutdown(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < opal_irq_count; i++) {
+		if (opal_irqs[i])
+			free_irq(opal_irqs[i], 0);
+		opal_irqs[i] = 0;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1da578b..9c9d15e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -68,16 +68,6 @@
 define_pe_printk_level(pe_warn, KERN_WARNING);
 define_pe_printk_level(pe_info, KERN_INFO);
 
-static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev)
-{
-	struct device_node *np;
-
-	np = pci_device_to_OF_node(dev);
-	if (!np)
-		return NULL;
-	return PCI_DN(np);
-}
-
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -110,7 +100,7 @@
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+	struct pci_dn *pdn = pci_get_pdn(dev);
 
 	if (!pdn)
 		return NULL;
@@ -173,7 +163,7 @@
 
 	/* Add to all parents PELT-V */
 	while (parent) {
-		struct pci_dn *pdn = pnv_ioda_get_pdn(parent);
+		struct pci_dn *pdn = pci_get_pdn(parent);
 		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
 			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
 						pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
@@ -252,7 +242,7 @@
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct pnv_ioda_pe *pe;
 	int pe_num;
 
@@ -323,7 +313,7 @@
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+		struct pci_dn *pdn = pci_get_pdn(dev);
 
 		if (pdn == NULL) {
 			pr_warn("%s: No device node associated with device !\n",
@@ -436,7 +426,7 @@
 
 static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
 {
-	struct pci_dn *pdn = pnv_ioda_get_pdn(pdev);
+	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
 	/*
@@ -768,6 +758,7 @@
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
+	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct irq_data *idata;
 	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
@@ -783,6 +774,10 @@
 	if (pe->mve_number < 0)
 		return -ENXIO;
 
+	/* Force 32-bit MSI on some broken devices */
+	if (pdn && pdn->force_32bit_msi)
+		is_64 = 0;
+
 	/* Assign XIVE to PE */
 	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
 	if (rc) {
@@ -1035,7 +1030,7 @@
 	if (!phb->initialized)
 		return 0;
 
-	pdn = pnv_ioda_get_pdn(dev);
+	pdn = pci_get_pdn(dev);
 	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
 		return -EINVAL;
 
@@ -1048,6 +1043,12 @@
 	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
 }
 
+static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+{
+	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+		       OPAL_ASSERT_RESET);
+}
+
 void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 {
 	struct pci_controller *hose;
@@ -1178,6 +1179,9 @@
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 
+	/* Setup shutdown function for kexec */
+	phb->shutdown = pnv_pci_ioda_shutdown;
+
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 55dfca844..277343c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -47,6 +47,10 @@
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+
+	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
+		return -ENODEV;
 
 	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
 }
@@ -367,7 +371,7 @@
 	while (npages--)
 		*(tcep++) = 0;
 
-	if (tbl->it_type & TCE_PCI_SWINV_CREATE)
+	if (tbl->it_type & TCE_PCI_SWINV_FREE)
 		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
 }
 
@@ -450,6 +454,18 @@
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+void pnv_pci_shutdown(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		struct pnv_phb *phb = hose->private_data;
+
+		if (phb && phb->shutdown)
+			phb->shutdown(phb);
+	}
+}
+
 /* Fixup wrong class code in p7ioc and p8 root complex */
 static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48dc4bb..25d76c4 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -86,6 +86,7 @@
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+	void (*shutdown)(struct pnv_phb *phb);
 
 	union {
 		struct {
@@ -158,4 +159,5 @@
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 					u64 *startp, u64 *endp);
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 8a9df7f..a1c6f83 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -9,8 +9,10 @@
 
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
+extern void pnv_pci_shutdown(void);
 #else
 static inline void pnv_pci_init(void) { }
+static inline void pnv_pci_shutdown(void) { }
 #endif
 
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index db1ad1c..d4459bf 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -78,7 +78,9 @@
 	if (root)
 		model = of_get_property(root, "model", NULL);
 	seq_printf(m, "machine\t\t: PowerNV %s\n", model);
-	if (firmware_has_feature(FW_FEATURE_OPALv2))
+	if (firmware_has_feature(FW_FEATURE_OPALv3))
+		seq_printf(m, "firmware\t: OPAL v3\n");
+	else if (firmware_has_feature(FW_FEATURE_OPALv2))
 		seq_printf(m, "firmware\t: OPAL v2\n");
 	else if (firmware_has_feature(FW_FEATURE_OPAL))
 		seq_printf(m, "firmware\t: OPAL v1\n");
@@ -126,6 +128,17 @@
 {
 }
 
+static void pnv_shutdown(void)
+{
+	/* Let the PCI code clear up IODA tables */
+	pnv_pci_shutdown();
+
+	/* And unregister all OPAL interrupts so they don't fire
+	 * up while we kexec
+	 */
+	opal_shutdown();
+}
+
 #ifdef CONFIG_KEXEC
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
@@ -187,6 +200,7 @@
 	.init_IRQ		= pnv_init_IRQ,
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.progress		= pnv_progress,
+	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 6a3ecca..88c9459 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -71,18 +71,68 @@
 
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
-	/* On OPAL v2 the CPU are still spinning inside OPAL itself,
-	 * get them back now
+	/*
+	 * If we already started or OPALv2 is not supported, we just
+	 * kick the CPU via the PACA
 	 */
-	if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) {
-		pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
-		rc = opal_start_cpu(pcpu, start_here);
+	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2))
+		goto kick;
+
+	/*
+	 * At this point, the CPU can either be spinning on the way in
+	 * from kexec or be inside OPAL waiting to be started for the
+	 * first time. OPAL v3 allows us to query OPAL to know if it
+	 * has the CPUs, so we do that
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3)) {
+		uint8_t status;
+
+		rc = opal_query_cpu_status(pcpu, &status);
 		if (rc != OPAL_SUCCESS) {
-			pr_warn("OPAL Error %ld starting CPU %d\n",
+			pr_warn("OPAL Error %ld querying CPU %d state\n",
 				rc, nr);
 			return -ENODEV;
 		}
+
+		/*
+		 * Already started, just kick it, probably coming from
+		 * kexec and spinning
+		 */
+		if (status == OPAL_THREAD_STARTED)
+			goto kick;
+
+		/*
+		 * Available/inactive, let's kick it
+		 */
+		if (status == OPAL_THREAD_INACTIVE) {
+			pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n",
+				 nr, pcpu);
+			rc = opal_start_cpu(pcpu, start_here);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("OPAL Error %ld starting CPU %d\n",
+					rc, nr);
+				return -ENODEV;
+			}
+		} else {
+			/*
+			 * An unavailable CPU (or any other unknown status)
+			 * shouldn't be started. It should also
+			 * not be in the possible map but currently it can
+			 * happen
+			 */
+			pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable"
+				 " (status %d)...\n", nr, pcpu, status);
+			return -ENODEV;
+		}
+	} else {
+		/*
+		 * On OPAL v2, we just kick it and hope for the best,
+		 * we must not test the error from opal_start_cpu() or
+		 * we would fail to get CPUs from kexec.
+		 */
+		opal_start_cpu(pcpu, start_here);
 	}
+ kick:
 	return smp_generic_kick_cpu(nr);
 }
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 9a0941b..023b288 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -18,6 +18,7 @@
 	select PPC_PCI_CHOICE if EXPERT
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
+	select HAVE_CONTEXT_TRACKING
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 420524e..6d2f0ab 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -26,26 +26,6 @@
 #define RTAS_CHANGE_MSIX_FN	4
 #define RTAS_CHANGE_32MSI_FN	5
 
-static struct pci_dn *get_pdn(struct pci_dev *pdev)
-{
-	struct device_node *dn;
-	struct pci_dn *pdn;
-
-	dn = pci_device_to_OF_node(pdev);
-	if (!dn) {
-		dev_dbg(&pdev->dev, "rtas_msi: No OF device node\n");
-		return NULL;
-	}
-
-	pdn = PCI_DN(dn);
-	if (!pdn) {
-		dev_dbg(&pdev->dev, "rtas_msi: No PCI DN\n");
-		return NULL;
-	}
-
-	return pdn;
-}
-
 /* RTAS Helpers */
 
 static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs)
@@ -91,7 +71,7 @@
 {
 	struct pci_dn *pdn;
 
-	pdn = get_pdn(pdev);
+	pdn = pci_get_pdn(pdev);
 	if (!pdn)
 		return;
 
@@ -152,7 +132,7 @@
 	struct pci_dn *pdn;
 	const u32 *req_msi;
 
-	pdn = get_pdn(pdev);
+	pdn = pci_get_pdn(pdev);
 	if (!pdn)
 		return -ENODEV;
 
@@ -394,6 +374,23 @@
 	return 0;
 }
 
+static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev)
+{
+	u32 addr_hi, addr_lo;
+
+	/*
+	 * We should only get in here for IODA1 configs. This is based on the
+	 * fact that we using RTAS for MSIs, we don't have the 32 bit MSI RTAS
+	 * support, and we are in a PCIe Gen2 slot.
+	 */
+	dev_info(&pdev->dev,
+		 "rtas_msi: No 32 bit MSI firmware support, forcing 32 bit MSI\n");
+	pci_read_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, &addr_hi);
+	addr_lo = 0xffff0000 | ((addr_hi >> (48 - 32)) << 4);
+	pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, addr_lo);
+	pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0);
+}
+
 static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 {
 	struct pci_dn *pdn;
@@ -401,8 +398,9 @@
 	struct msi_desc *entry;
 	struct msi_msg msg;
 	int nvec = nvec_in;
+	int use_32bit_msi_hack = 0;
 
-	pdn = get_pdn(pdev);
+	pdn = pci_get_pdn(pdev);
 	if (!pdn)
 		return -ENODEV;
 
@@ -428,15 +426,31 @@
 	 */
 again:
 	if (type == PCI_CAP_ID_MSI) {
-		if (pdn->force_32bit_msi)
+		if (pdn->force_32bit_msi) {
 			rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec);
-		else
+			if (rc < 0) {
+				/*
+				 * We only want to run the 32 bit MSI hack below if
+				 * the max bus speed is Gen2 speed
+				 */
+				if (pdev->bus->max_bus_speed != PCIE_SPEED_5_0GT)
+					return rc;
+
+				use_32bit_msi_hack = 1;
+			}
+		} else
+			rc = -1;
+
+		if (rc < 0)
 			rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec);
 
-		if (rc < 0 && !pdn->force_32bit_msi) {
+		if (rc < 0) {
 			pr_debug("rtas_msi: trying the old firmware call.\n");
 			rc = rtas_change_msi(pdn, RTAS_CHANGE_FN, nvec);
 		}
+
+		if (use_32bit_msi_hack && rc > 0)
+			rtas_hack_32bit_msi_gen2(pdev);
 	} else
 		rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
 
@@ -518,12 +532,3 @@
 }
 arch_initcall(rtas_msi_init);
 
-static void quirk_radeon(struct pci_dev *dev)
-{
-	struct pci_dn *pdn = get_pdn(dev);
-
-	if (pdn)
-		pdn->force_32bit_msi = 1;
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon);
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 47226e0..5f997e7 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -16,6 +16,7 @@
   * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
   */
 
+#include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/suspend.h>
 #include <linux/stat.h>
@@ -126,11 +127,15 @@
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
+	cpumask_var_t offline_mask;
 	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	stream_id = simple_strtoul(buf, NULL, 16);
 
 	do {
@@ -140,15 +145,32 @@
 	} while (rc == -EAGAIN);
 
 	if (!rc) {
+		/* All present CPUs must be online */
+		cpumask_andnot(offline_mask, cpu_present_mask,
+				cpu_online_mask);
+		rc = rtas_online_cpus_mask(offline_mask);
+		if (rc) {
+			pr_err("%s: Could not bring present CPUs online.\n",
+					__func__);
+			goto out;
+		}
+
 		stop_topology_update();
 		rc = pm_suspend(PM_SUSPEND_MEM);
 		start_topology_update();
+
+		/* Take down CPUs not online prior to suspend */
+		if (!rtas_offline_cpus_mask(offline_mask))
+			pr_warn("%s: Could not restore CPUs to offline "
+					"state.\n", __func__);
 	}
 
 	stream_id = 0;
 
 	if (!rc)
 		rc = count;
+out:
+	free_cpumask_var(offline_mask);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 97fe82e..2d3b1dd 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -361,7 +361,7 @@
 	xive = xive_set_server(xive, get_irq_server(ics, hw_irq));
 	wsp_ics_set_xive(ics, hw_irq, xive);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip wsp_irq_chip = {
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index b0a518e..99464a7 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -64,6 +64,8 @@
 
 obj-$(CONFIG_PPC_SCOM)		+= scom.o
 
+obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS)	+= udbg_memcons.o
+
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PPC_XICS)		+= xics/
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index 6e0e100..9cd0e60 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -81,7 +81,7 @@
 	ev_int_set_config(src, config, prio, cpuid);
 	spin_unlock_irqrestore(&ehv_pic_lock, flags);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static unsigned int ehv_pic_type_to_vecpri(unsigned int type)
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index ee21b5e..0a13ecb 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -836,7 +836,7 @@
 			       mpic_physmask(mask));
 	}
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
new file mode 100644
index 0000000..ce5a7b4
--- /dev/null
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -0,0 +1,105 @@
+/*
+ * A udbg backend which logs messages and reads input from in memory
+ * buffers.
+ *
+ * The console output can be read from memcons_output which is a
+ * circular buffer whose next write position is stored in memcons.output_pos.
+ *
+ * Input may be passed by writing into the memcons_input buffer when it is
+ * empty. The input buffer is empty when both input_pos == input_start and
+ * *input_start == '\0'.
+ *
+ * Copyright (C) 2003-2005 Anton Blanchard and Milton Miller, IBM Corp
+ * Copyright (C) 2013 Alistair Popple, IBM Corp
+ *
+ *      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.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/barrier.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/udbg.h>
+
+struct memcons {
+	char *output_start;
+	char *output_pos;
+	char *output_end;
+	char *input_start;
+	char *input_pos;
+	char *input_end;
+};
+
+static char memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE];
+static char memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE];
+
+struct memcons memcons = {
+	.output_start = memcons_output,
+	.output_pos = memcons_output,
+	.output_end = &memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE],
+	.input_start = memcons_input,
+	.input_pos = memcons_input,
+	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
+};
+
+void memcons_putc(char c)
+{
+	char *new_output_pos;
+
+	*memcons.output_pos = c;
+	wmb();
+	new_output_pos = memcons.output_pos + 1;
+	if (new_output_pos >= memcons.output_end)
+		new_output_pos = memcons.output_start;
+
+	memcons.output_pos = new_output_pos;
+}
+
+int memcons_getc_poll(void)
+{
+	char c;
+	char *new_input_pos;
+
+	if (*memcons.input_pos) {
+		c = *memcons.input_pos;
+
+		new_input_pos = memcons.input_pos + 1;
+		if (new_input_pos >= memcons.input_end)
+			new_input_pos = memcons.input_start;
+		else if (*new_input_pos == '\0')
+			new_input_pos = memcons.input_start;
+
+		*memcons.input_pos = '\0';
+		wmb();
+		memcons.input_pos = new_input_pos;
+		return c;
+	}
+
+	return -1;
+}
+
+int memcons_getc(void)
+{
+	int c;
+
+	while (1) {
+		c = memcons_getc_poll();
+		if (c == -1)
+			cpu_relax();
+		else
+			break;
+	}
+
+	return c;
+}
+
+void udbg_init_memcons(void)
+{
+	udbg_putc = memcons_putc;
+	udbg_getc = memcons_getc;
+	udbg_getc_poll = memcons_getc_poll;
+}
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index f7e8609..39d7221 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -148,7 +148,7 @@
 		       __func__, d->irq, hw_irq, server, rc);
 		return -1;
 	}
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip ics_opal_irq_chip = {
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 2c9789d..da183c5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -98,7 +98,6 @@
 	select CLONE_BACKWARDS2
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES if !SMP
-	select GENERIC_KERNEL_THREAD
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index b7931fa..bf246da 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -9,11 +9,6 @@
 
 #define MCOUNT_ADDR ((long)_mcount)
 
-#ifdef CONFIG_64BIT
-#define MCOUNT_INSN_SIZE  12
-#else
-#define MCOUNT_INSN_SIZE  20
-#endif
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
@@ -21,4 +16,11 @@
 }
 
 #endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_64BIT
+#define MCOUNT_INSN_SIZE  12
+#else
+#define MCOUNT_INSN_SIZE  22
+#endif
+
 #endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 75ce9b0..5d64fb7 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -32,7 +32,7 @@
 
 void storage_key_init_range(unsigned long start, unsigned long end);
 
-static unsigned long pfmf(unsigned long function, unsigned long address)
+static inline unsigned long pfmf(unsigned long function, unsigned long address)
 {
 	asm volatile(
 		"	.insn	rre,0xb9af0000,%[function],%[address]"
@@ -44,17 +44,13 @@
 
 static inline void clear_page(void *page)
 {
-	if (MACHINE_HAS_PFMF) {
-		pfmf(0x10000, (unsigned long)page);
-	} else {
-		register unsigned long reg1 asm ("1") = 0;
-		register void *reg2 asm ("2") = page;
-		register unsigned long reg3 asm ("3") = 4096;
-		asm volatile(
-			"	mvcl	2,0"
-			: "+d" (reg2), "+d" (reg3) : "d" (reg1)
-			: "memory", "cc");
-	}
+	register unsigned long reg1 asm ("1") = 0;
+	register void *reg2 asm ("2") = page;
+	register unsigned long reg3 asm ("3") = 4096;
+	asm volatile(
+		"	mvcl	2,0"
+		: "+d" (reg2), "+d" (reg3) : "d" (reg1)
+		: "memory", "cc");
 }
 
 static inline void copy_page(void *to, void *from)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 4105b82..0f0de30 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -306,7 +306,7 @@
 #define RCP_HC_BIT	0x00200000UL
 #define RCP_GR_BIT	0x00040000UL
 #define RCP_GC_BIT	0x00020000UL
-#define RCP_IN_BIT	0x00008000UL	/* IPTE notify bit */
+#define RCP_IN_BIT	0x00002000UL	/* IPTE notify bit */
 
 /* User dirty / referenced bit for KVM's migration feature */
 #define KVM_UR_BIT	0x00008000UL
@@ -374,7 +374,7 @@
 #define RCP_HC_BIT	0x0020000000000000UL
 #define RCP_GR_BIT	0x0004000000000000UL
 #define RCP_GC_BIT	0x0002000000000000UL
-#define RCP_IN_BIT	0x0000800000000000UL	/* IPTE notify bit */
+#define RCP_IN_BIT	0x0000200000000000UL	/* IPTE notify bit */
 
 /* User dirty / referenced bit for KVM's migration feature */
 #define KVM_UR_BIT	0x0000800000000000UL
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 7f4a4a8..be87d3e 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1862,6 +1862,8 @@
 	while (len) {
 		ptr = buffer;
 		opsize = insn_length(*code);
+		if (opsize > len)
+			break;
 		ptr += sprintf(ptr, "%p: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 78bdf0e..e3043ae 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -16,12 +16,6 @@
 #include <trace/syscall.h>
 #include <asm/asm-offsets.h>
 
-#ifdef CONFIG_64BIT
-#define MCOUNT_OFFSET_RET 12
-#else
-#define MCOUNT_OFFSET_RET 22
-#endif
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 void ftrace_disable_code(void);
@@ -155,9 +149,10 @@
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
+	ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE;
 	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
 		goto out;
-	trace.func = (ip & PSW_ADDR_INSN) - MCOUNT_OFFSET_RET;
+	trace.func = ip;
 	/* Only trace if the calling function expects to. */
 	if (!ftrace_graph_entry(&trace)) {
 		current->curr_ret_stack--;
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 4567ce2..08dcf21 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -7,6 +7,7 @@
 
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
 
 	.section .kprobes.text, "ax"
 
@@ -33,6 +34,7 @@
 	la	%r2,0(%r14)
 	st	%r0,__SF_BACKCHAIN(%r15)
 	la	%r3,0(%r3)
+	ahi	%r2,-MCOUNT_INSN_SIZE
 	l	%r14,0b-0b(%r1)
 	l	%r14,0(%r14)
 	basr	%r14,%r14
diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S
index 1133219..1c52eae 100644
--- a/arch/s390/kernel/mcount64.S
+++ b/arch/s390/kernel/mcount64.S
@@ -7,6 +7,7 @@
 
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
 
 	.section .kprobes.text, "ax"
 
@@ -29,6 +30,7 @@
 	stg	%r1,__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r14
 	lg	%r3,168(%r15)
+	aghi	%r2,-MCOUNT_INSN_SIZE
 	larl	%r14,ftrace_trace_function
 	lg	%r14,0(%r14)
 	basr	%r14,%r14
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 8074cb4..05674b6 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -645,7 +645,7 @@
 			continue;
 		pcpu = pcpu_devices + cpu;
 		pcpu->address = info->cpu[i].address;
-		pcpu->state = (cpu >= info->configured) ?
+		pcpu->state = (i >= info->configured) ?
 			CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
 		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
 		set_cpu_present(cpu, true);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 7805ddc..18dc417 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -677,8 +677,7 @@
 			break;
 		}
 		/* Get the page mapped */
-		if (get_user_pages(current, gmap->mm, addr, 1, 1, 0,
-				   NULL, NULL) != 1) {
+		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) {
 			rc = -EFAULT;
 			break;
 		}
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index d8f988a..0940682 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -41,8 +41,6 @@
 unsigned long empty_zero_page;
 EXPORT_SYMBOL_GPL(empty_zero_page);
 
-static struct kcore_list kcore_mem, kcore_vmalloc;
-
 static void setup_zero_page(void)
 {
 	struct page *page;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a154a9..685692c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,7 +108,6 @@
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL if X86_64
 	select KTIME_SCALAR if X86_32
-	select ALWAYS_USE_PERSISTENT_CLOCK
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index dab95a8..55b6761 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -34,7 +34,7 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 static unsigned int __initdata next_early_pgt = 2;
-pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
+pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index d893e8e..2e9e128 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -487,6 +487,7 @@
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 /*
  * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
  * hot added or resumes.
@@ -507,7 +508,7 @@
 	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
 	 * hotplug.
 	 */
-	cpu_hotplug_driver_lock();
+	mutex_lock(&x86_cpu_microcode_mutex);
 
 	mc_saved_count_init = mc_saved_data.mc_saved_count;
 	mc_saved_count = mc_saved_data.mc_saved_count;
@@ -544,7 +545,7 @@
 	}
 
 out:
-	cpu_hotplug_driver_unlock();
+	mutex_unlock(&x86_cpu_microcode_mutex);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 607af0d..4e7a37f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -312,6 +312,8 @@
 {
 	if (cpuidle_idle_call())
 		x86_idle();
+	else
+		local_irq_enable();
 }
 
 /*
@@ -368,9 +370,6 @@
  */
 static void amd_e400_idle(void)
 {
-	if (need_resched())
-		return;
-
 	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca..eaac174 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -359,7 +359,17 @@
 }
 
 /*
- * would have hole in the middle or ends, and only ram parts will be mapped.
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
  */
 static unsigned long __init init_range_memory_mapping(
 					   unsigned long r_start,
@@ -419,6 +429,13 @@
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
 	while (last_start > ISA_END_ADDRESS) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 0e0fabf..6eb18c4 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -141,11 +141,6 @@
  */
 static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 {
-	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
-				|| devfn == PCI_DEVFN(0, 0)
-				|| devfn == PCI_DEVFN(3, 0)))
-		return 1;
-
 	/* This is a workaround for A0 LNC bug where PCI status register does
 	 * not have new CAP bit set. can not be written by SW either.
 	 *
@@ -155,7 +150,10 @@
 	 */
 	if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
 		return 0;
-
+	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
+				|| devfn == PCI_DEVFN(0, 0)
+				|| devfn == PCI_DEVFN(3, 0)))
+		return 1;
 	return 0; /* langwell on others */
 }
 
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index ecb743b..536562c 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -24,7 +24,7 @@
 # Power management related files
 acpi-y				+= wakeup.o
 acpi-y				+= sleep.o
-acpi-$(CONFIG_PM)		+= device_pm.o
+acpi-y				+= device_pm.o
 acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 
 
@@ -38,7 +38,6 @@
 acpi-y				+= ec.o
 acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
 acpi-y				+= pci_root.o pci_link.o pci_irq.o
-acpi-y				+= csrt.o
 acpi-$(CONFIG_X86_INTEL_LPSS)	+= acpi_lpss.o
 acpi-y				+= acpi_platform.o
 acpi-y				+= power.o
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 00d2efd..4f4e741 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -28,6 +28,8 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/dmi.h>
+#include <linux/delay.h>
 #ifdef CONFIG_ACPI_PROCFS_POWER
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
@@ -74,6 +76,8 @@
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
 
+static int ac_sleep_before_get_state_ms;
+
 static struct acpi_driver acpi_ac_driver = {
 	.name = "ac",
 	.class = ACPI_AC_CLASS,
@@ -252,6 +256,16 @@
 	case ACPI_AC_NOTIFY_STATUS:
 	case ACPI_NOTIFY_BUS_CHECK:
 	case ACPI_NOTIFY_DEVICE_CHECK:
+		/*
+		 * A buggy BIOS may notify AC first and then sleep for
+		 * a specific time before doing actual operations in the
+		 * EC event handler (_Qxx). This will cause the AC state
+		 * reported by the ACPI event to be incorrect, so wait for a
+		 * specific time for the EC event handler to make progress.
+		 */
+		if (ac_sleep_before_get_state_ms > 0)
+			msleep(ac_sleep_before_get_state_ms);
+
 		acpi_ac_get_state(ac);
 		acpi_bus_generate_proc_event(device, event, (u32) ac->state);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
@@ -264,6 +278,24 @@
 	return;
 }
 
+static int thinkpad_e530_quirk(const struct dmi_system_id *d)
+{
+	ac_sleep_before_get_state_ms = 1000;
+	return 0;
+}
+
+static struct dmi_system_id ac_dmi_table[] = {
+	{
+	.callback = thinkpad_e530_quirk,
+	.ident = "thinkpad e530",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "32597CG"),
+		},
+	},
+	{},
+};
+
 static int acpi_ac_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -312,6 +344,7 @@
 		kfree(ac);
 	}
 
+	dmi_check_system(ac_dmi_table);
 	return result;
 }
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index b1c9542..652fd5c 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -35,11 +35,16 @@
 
 struct lpss_device_desc {
 	bool clk_required;
-	const char *clk_parent;
+	const char *clkdev_name;
 	bool ltr_required;
 	unsigned int prv_offset;
 };
 
+static struct lpss_device_desc lpss_dma_desc = {
+	.clk_required = true,
+	.clkdev_name = "hclk",
+};
+
 struct lpss_private_data {
 	void __iomem *mmio_base;
 	resource_size_t mmio_size;
@@ -49,7 +54,6 @@
 
 static struct lpss_device_desc lpt_dev_desc = {
 	.clk_required = true,
-	.clk_parent = "lpss_clk",
 	.prv_offset = 0x800,
 	.ltr_required = true,
 };
@@ -60,6 +64,9 @@
 };
 
 static const struct acpi_device_id acpi_lpss_device_ids[] = {
+	/* Generic LPSS devices */
+	{ "INTL9C60", (unsigned long)&lpss_dma_desc },
+
 	/* Lynxpoint LPSS devices */
 	{ "INT33C0", (unsigned long)&lpt_dev_desc },
 	{ "INT33C1", (unsigned long)&lpt_dev_desc },
@@ -91,16 +98,27 @@
 				 struct lpss_private_data *pdata)
 {
 	const struct lpss_device_desc *dev_desc = pdata->dev_desc;
+	struct lpss_clk_data *clk_data;
 
 	if (!lpss_clk_dev)
 		lpt_register_clock_device();
 
-	if (!dev_desc->clk_parent || !pdata->mmio_base
+	clk_data = platform_get_drvdata(lpss_clk_dev);
+	if (!clk_data)
+		return -ENODEV;
+
+	if (dev_desc->clkdev_name) {
+		clk_register_clkdev(clk_data->clk, dev_desc->clkdev_name,
+				    dev_name(&adev->dev));
+		return 0;
+	}
+
+	if (!pdata->mmio_base
 	    || pdata->mmio_size < dev_desc->prv_offset + LPSS_CLK_SIZE)
 		return -ENODATA;
 
 	pdata->clk = clk_register_gate(NULL, dev_name(&adev->dev),
-				       dev_desc->clk_parent, 0,
+				       clk_data->name, 0,
 				       pdata->mmio_base + dev_desc->prv_offset,
 				       0, 0, NULL);
 	if (IS_ERR(pdata->clk))
diff --git a/drivers/acpi/csrt.c b/drivers/acpi/csrt.c
deleted file mode 100644
index 5c15a91..0000000
--- a/drivers/acpi/csrt.c
+++ /dev/null
@@ -1,159 +0,0 @@
-/*
- * Support for Core System Resources Table (CSRT)
- *
- * Copyright (C) 2013, Intel Corporation
- * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
- *	    Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define pr_fmt(fmt) "ACPI: CSRT: " fmt
-
-#include <linux/acpi.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/sizes.h>
-
-ACPI_MODULE_NAME("CSRT");
-
-static int __init acpi_csrt_parse_shared_info(struct platform_device *pdev,
-					      const struct acpi_csrt_group *grp)
-{
-	const struct acpi_csrt_shared_info *si;
-	struct resource res[3];
-	size_t nres;
-	int ret;
-
-	memset(res, 0, sizeof(res));
-	nres = 0;
-
-	si = (const struct acpi_csrt_shared_info *)&grp[1];
-	/*
-	 * The peripherals that are listed on CSRT typically support only
-	 * 32-bit addresses so we only use the low part of MMIO base for
-	 * now.
-	 */
-	if (!si->mmio_base_high && si->mmio_base_low) {
-		/*
-		 * There is no size of the memory resource in shared_info
-		 * so we assume that it is 4k here.
-		 */
-		res[nres].start = si->mmio_base_low;
-		res[nres].end = res[0].start + SZ_4K - 1;
-		res[nres++].flags = IORESOURCE_MEM;
-	}
-
-	if (si->gsi_interrupt) {
-		int irq = acpi_register_gsi(NULL, si->gsi_interrupt,
-					    si->interrupt_mode,
-					    si->interrupt_polarity);
-		res[nres].start = irq;
-		res[nres].end = irq;
-		res[nres++].flags = IORESOURCE_IRQ;
-	}
-
-	if (si->base_request_line || si->num_handshake_signals) {
-		/*
-		 * We pass the driver a DMA resource describing the range
-		 * of request lines the device supports.
-		 */
-		res[nres].start = si->base_request_line;
-		res[nres].end = res[nres].start + si->num_handshake_signals - 1;
-		res[nres++].flags = IORESOURCE_DMA;
-	}
-
-	ret = platform_device_add_resources(pdev, res, nres);
-	if (ret) {
-		if (si->gsi_interrupt)
-			acpi_unregister_gsi(si->gsi_interrupt);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int __init
-acpi_csrt_parse_resource_group(const struct acpi_csrt_group *grp)
-{
-	struct platform_device *pdev;
-	char vendor[5], name[16];
-	int ret, i;
-
-	vendor[0] = grp->vendor_id;
-	vendor[1] = grp->vendor_id >> 8;
-	vendor[2] = grp->vendor_id >> 16;
-	vendor[3] = grp->vendor_id >> 24;
-	vendor[4] = '\0';
-
-	if (grp->shared_info_length != sizeof(struct acpi_csrt_shared_info))
-		return -ENODEV;
-
-	snprintf(name, sizeof(name), "%s%04X", vendor, grp->device_id);
-	pdev = platform_device_alloc(name, PLATFORM_DEVID_AUTO);
-	if (!pdev)
-		return -ENOMEM;
-
-	/* Add resources based on the shared info */
-	ret = acpi_csrt_parse_shared_info(pdev, grp);
-	if (ret)
-		goto fail;
-
-	ret = platform_device_add(pdev);
-	if (ret)
-		goto fail;
-
-	for (i = 0; i < pdev->num_resources; i++)
-		dev_dbg(&pdev->dev, "%pR\n", &pdev->resource[i]);
-
-	return 0;
-
-fail:
-	platform_device_put(pdev);
-	return ret;
-}
-
-/*
- * CSRT or Core System Resources Table is a proprietary ACPI table
- * introduced by Microsoft. This table can contain devices that are not in
- * the system DSDT table. In particular DMA controllers might be described
- * here.
- *
- * We present these devices as normal platform devices that don't have ACPI
- * IDs or handle. The platform device name will be something like
- * <VENDOR><DEVID>.<n>.auto for example: INTL9C06.0.auto.
- */
-void __init acpi_csrt_init(void)
-{
-	struct acpi_csrt_group *grp, *end;
-	struct acpi_table_csrt *csrt;
-	acpi_status status;
-	int ret;
-
-	status = acpi_get_table(ACPI_SIG_CSRT, 0,
-				(struct acpi_table_header **)&csrt);
-	if (ACPI_FAILURE(status)) {
-		if (status != AE_NOT_FOUND)
-			pr_warn("failed to get the CSRT table\n");
-		return;
-	}
-
-	pr_debug("parsing CSRT table for devices\n");
-
-	grp = (struct acpi_csrt_group *)(csrt + 1);
-	end = (struct acpi_csrt_group *)((void *)csrt + csrt->header.length);
-
-	while (grp < end) {
-		ret = acpi_csrt_parse_resource_group(grp);
-		if (ret) {
-			pr_warn("error in parsing resource group: %d\n", ret);
-			return;
-		}
-
-		grp = (struct acpi_csrt_group *)((void *)grp + grp->length);
-	}
-}
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 96de787..bc493aa 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -37,68 +37,6 @@
 #define _COMPONENT	ACPI_POWER_COMPONENT
 ACPI_MODULE_NAME("device_pm");
 
-static DEFINE_MUTEX(acpi_pm_notifier_lock);
-
-/**
- * acpi_add_pm_notifier - Register PM notifier for given ACPI device.
- * @adev: ACPI device to add the notifier for.
- * @context: Context information to pass to the notifier routine.
- *
- * NOTE: @adev need not be a run-wake or wakeup device to be a valid source of
- * PM wakeup events.  For example, wakeup events may be generated for bridges
- * if one of the devices below the bridge is signaling wakeup, even if the
- * bridge itself doesn't have a wakeup GPE associated with it.
- */
-acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
-				 acpi_notify_handler handler, void *context)
-{
-	acpi_status status = AE_ALREADY_EXISTS;
-
-	mutex_lock(&acpi_pm_notifier_lock);
-
-	if (adev->wakeup.flags.notifier_present)
-		goto out;
-
-	status = acpi_install_notify_handler(adev->handle,
-					     ACPI_SYSTEM_NOTIFY,
-					     handler, context);
-	if (ACPI_FAILURE(status))
-		goto out;
-
-	adev->wakeup.flags.notifier_present = true;
-
- out:
-	mutex_unlock(&acpi_pm_notifier_lock);
-	return status;
-}
-
-/**
- * acpi_remove_pm_notifier - Unregister PM notifier from given ACPI device.
- * @adev: ACPI device to remove the notifier from.
- */
-acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
-				    acpi_notify_handler handler)
-{
-	acpi_status status = AE_BAD_PARAMETER;
-
-	mutex_lock(&acpi_pm_notifier_lock);
-
-	if (!adev->wakeup.flags.notifier_present)
-		goto out;
-
-	status = acpi_remove_notify_handler(adev->handle,
-					    ACPI_SYSTEM_NOTIFY,
-					    handler);
-	if (ACPI_FAILURE(status))
-		goto out;
-
-	adev->wakeup.flags.notifier_present = false;
-
- out:
-	mutex_unlock(&acpi_pm_notifier_lock);
-	return status;
-}
-
 /**
  * acpi_power_state_string - String representation of ACPI device power state.
  * @state: ACPI device power state to return the string representation of.
@@ -385,6 +323,69 @@
 }
 EXPORT_SYMBOL(acpi_bus_power_manageable);
 
+#ifdef CONFIG_PM
+static DEFINE_MUTEX(acpi_pm_notifier_lock);
+
+/**
+ * acpi_add_pm_notifier - Register PM notifier for given ACPI device.
+ * @adev: ACPI device to add the notifier for.
+ * @context: Context information to pass to the notifier routine.
+ *
+ * NOTE: @adev need not be a run-wake or wakeup device to be a valid source of
+ * PM wakeup events.  For example, wakeup events may be generated for bridges
+ * if one of the devices below the bridge is signaling wakeup, even if the
+ * bridge itself doesn't have a wakeup GPE associated with it.
+ */
+acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
+				 acpi_notify_handler handler, void *context)
+{
+	acpi_status status = AE_ALREADY_EXISTS;
+
+	mutex_lock(&acpi_pm_notifier_lock);
+
+	if (adev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_install_notify_handler(adev->handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     handler, context);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	adev->wakeup.flags.notifier_present = true;
+
+ out:
+	mutex_unlock(&acpi_pm_notifier_lock);
+	return status;
+}
+
+/**
+ * acpi_remove_pm_notifier - Unregister PM notifier from given ACPI device.
+ * @adev: ACPI device to remove the notifier from.
+ */
+acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
+				    acpi_notify_handler handler)
+{
+	acpi_status status = AE_BAD_PARAMETER;
+
+	mutex_lock(&acpi_pm_notifier_lock);
+
+	if (!adev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_remove_notify_handler(adev->handle,
+					    ACPI_SYSTEM_NOTIFY,
+					    handler);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	adev->wakeup.flags.notifier_present = false;
+
+ out:
+	mutex_unlock(&acpi_pm_notifier_lock);
+	return status;
+}
+
 bool acpi_bus_can_wakeup(acpi_handle handle)
 {
 	struct acpi_device *device;
@@ -1023,3 +1024,4 @@
 	mutex_unlock(&adev->physical_node_lock);
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_remove_dependent);
+#endif /* CONFIG_PM */
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index d45b287..edc0081 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -223,7 +223,7 @@
 static int ec_poll(struct acpi_ec *ec)
 {
 	unsigned long flags;
-	int repeat = 2; /* number of command restarts */
+	int repeat = 5; /* number of command restarts */
 	while (repeat--) {
 		unsigned long delay = jiffies +
 			msecs_to_jiffies(ec_delay);
@@ -241,8 +241,6 @@
 			}
 			advance_transaction(ec, acpi_ec_read_status(ec));
 		} while (time_before(jiffies, delay));
-		if (acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF)
-			break;
 		pr_debug(PREFIX "controller reset, restart transaction\n");
 		spin_lock_irqsave(&ec->lock, flags);
 		start_transaction(ec);
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 6f1afd9..297cbf4 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -35,7 +35,6 @@
 void acpi_pci_root_hp_init(void);
 void acpi_platform_init(void);
 int acpi_sysfs_init(void);
-void acpi_csrt_init(void);
 #ifdef CONFIG_ACPI_CONTAINER
 void acpi_container_init(void);
 #else
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 1dd6f6c..e427dc5 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -641,7 +641,9 @@
 		/* bus enumerate */
 		printk(KERN_DEBUG "%s: Bus check notify on %s\n", __func__,
 				 (char *)buffer.pointer);
-		if (!root)
+		if (root)
+			acpiphp_check_host_bridge(handle);
+		else
 			handle_root_bridge_insertion(handle);
 
 		break;
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index bec717f..c266cdc 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -95,9 +95,6 @@
 };
 MODULE_DEVICE_TABLE(acpi, processor_device_ids);
 
-static SIMPLE_DEV_PM_OPS(acpi_processor_pm,
-			 acpi_processor_suspend, acpi_processor_resume);
-
 static struct acpi_driver acpi_processor_driver = {
 	.name = "processor",
 	.class = ACPI_PROCESSOR_CLASS,
@@ -107,7 +104,6 @@
 		.remove = acpi_processor_remove,
 		.notify = acpi_processor_notify,
 		},
-	.drv.pm = &acpi_processor_pm,
 };
 
 #define INSTALL_NOTIFY_HANDLER		1
@@ -934,6 +930,8 @@
 	if (result < 0)
 		return result;
 
+	acpi_processor_syscore_init();
+
 	acpi_processor_install_hotplug_notify();
 
 	acpi_thermal_cpufreq_init();
@@ -956,6 +954,8 @@
 
 	acpi_processor_uninstall_hotplug_notify();
 
+	acpi_processor_syscore_exit();
+
 	acpi_bus_unregister_driver(&acpi_processor_driver);
 
 	return;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f0df2c9..eb133c7 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -34,6 +34,7 @@
 #include <linux/sched.h>       /* need_resched() */
 #include <linux/clockchips.h>
 #include <linux/cpuidle.h>
+#include <linux/syscore_ops.h>
 
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
@@ -210,33 +211,41 @@
 
 #endif
 
+#ifdef CONFIG_PM_SLEEP
 static u32 saved_bm_rld;
 
-static void acpi_idle_bm_rld_save(void)
+int acpi_processor_suspend(void)
 {
 	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld);
+	return 0;
 }
-static void acpi_idle_bm_rld_restore(void)
+
+void acpi_processor_resume(void)
 {
 	u32 resumed_bm_rld;
 
 	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld);
+	if (resumed_bm_rld == saved_bm_rld)
+		return;
 
-	if (resumed_bm_rld != saved_bm_rld)
-		acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld);
+	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld);
 }
 
-int acpi_processor_suspend(struct device *dev)
+static struct syscore_ops acpi_processor_syscore_ops = {
+	.suspend = acpi_processor_suspend,
+	.resume = acpi_processor_resume,
+};
+
+void acpi_processor_syscore_init(void)
 {
-	acpi_idle_bm_rld_save();
-	return 0;
+	register_syscore_ops(&acpi_processor_syscore_ops);
 }
 
-int acpi_processor_resume(struct device *dev)
+void acpi_processor_syscore_exit(void)
 {
-	acpi_idle_bm_rld_restore();
-	return 0;
+	unregister_syscore_ops(&acpi_processor_syscore_ops);
 }
+#endif /* CONFIG_PM_SLEEP */
 
 #if defined(CONFIG_X86)
 static void tsc_check_state(int state)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fe158fd..44225cb 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1785,7 +1785,7 @@
 	acpi_set_pnp_ids(handle, &pnp, type);
 
 	if (!pnp.type.hardware_id)
-		return;
+		goto out;
 
 	/*
 	 * This relies on the fact that acpi_install_notify_handler() will not
@@ -1800,6 +1800,7 @@
 		}
 	}
 
+out:
 	acpi_free_pnp_ids(&pnp);
 }
 
@@ -2042,7 +2043,6 @@
 	acpi_pci_link_init();
 	acpi_platform_init();
 	acpi_lpss_init();
-	acpi_csrt_init();
 	acpi_container_init();
 	acpi_memory_hotplug_init();
 
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index c3932d0..5b32e15 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -456,6 +456,14 @@
 		DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dm4 Notebook PC"),
 		},
 	},
+	{
+	 .callback = video_ignore_initial_backlight,
+	 .ident = "HP 1000 Notebook PC",
+	 .matches = {
+		DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP 1000 Notebook PC"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 66f6762..e6bd910 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -161,6 +161,14 @@
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30VT"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Asus UL30A",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c
index c1bfaf4..980b88e 100644
--- a/drivers/ata/pata_ep93xx.c
+++ b/drivers/ata/pata_ep93xx.c
@@ -933,11 +933,6 @@
 	}
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem_res) {
-		err = -ENXIO;
-		goto err_rel_gpio;
-	}
-
 	ide_base = devm_ioremap_resource(&pdev->dev, mem_res);
 	if (IS_ERR(ide_base)) {
 		err = PTR_ERR(ide_base);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 1a68f94..d414331 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1295,6 +1295,7 @@
 
 	return subsys_register(subsys, groups, virtual_dir);
 }
+EXPORT_SYMBOL_GPL(subsys_virtual_register);
 
 int __init buses_init(void)
 {
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 016312437..2499cef 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -572,9 +572,11 @@
 
 	if (dev) {
 		WARN(((attr->attr.mode & S_IWUGO) && !attr->store),
-				"Write permission without 'store'\n");
+			"Attribute %s: write permission without 'store'\n",
+			attr->attr.name);
 		WARN(((attr->attr.mode & S_IRUGO) && !attr->show),
-				"Read permission without 'show'\n");
+			"Attribute %s: read permission without 'show'\n",
+			attr->attr.name);
 		error = sysfs_create_file(&dev->kobj, &attr->attr);
 	}
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index 39c3252..5da9140 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -61,24 +61,24 @@
 int dev_pm_put_subsys_data(struct device *dev)
 {
 	struct pm_subsys_data *psd;
-	int ret = 0;
+	int ret = 1;
 
 	spin_lock_irq(&dev->power.lock);
 
 	psd = dev_to_psd(dev);
-	if (!psd) {
-		ret = -EINVAL;
+	if (!psd)
 		goto out;
-	}
 
 	if (--psd->refcount == 0) {
 		dev->power.subsys_data = NULL;
-		kfree(psd);
-		ret = 1;
+	} else {
+		psd = NULL;
+		ret = 0;
 	}
 
  out:
 	spin_unlock_irq(&dev->power.lock);
+	kfree(psd);
 
 	return ret;
 }
diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index bca9c80..8bffa5c 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -84,6 +84,8 @@
 	{ BCMA_CORE_I2S, "I2S" },
 	{ BCMA_CORE_SDR_DDR1_MEM_CTL, "SDR/DDR1 Memory Controller" },
 	{ BCMA_CORE_SHIM, "SHIM" },
+	{ BCMA_CORE_PCIE2, "PCIe Gen2" },
+	{ BCMA_CORE_ARM_CR4, "ARM CR4" },
 	{ BCMA_CORE_DEFAULT, "Default" },
 };
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index f1a29f8..9bf4371 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -117,13 +117,13 @@
 
 	spin_lock(&brd->brd_lock);
 	idx = sector >> PAGE_SECTORS_SHIFT;
+	page->index = idx;
 	if (radix_tree_insert(&brd->brd_pages, idx, page)) {
 		__free_page(page);
 		page = radix_tree_lookup(&brd->brd_pages, idx);
 		BUG_ON(!page);
 		BUG_ON(page->index != idx);
-	} else
-		page->index = idx;
+	}
 	spin_unlock(&brd->brd_lock);
 
 	radix_tree_preload_end();
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index ca63104..d6d3140 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -55,6 +55,39 @@
 #define	SECTOR_SHIFT	9
 #define	SECTOR_SIZE	(1ULL << SECTOR_SHIFT)
 
+/*
+ * Increment the given counter and return its updated value.
+ * If the counter is already 0 it will not be incremented.
+ * If the counter is already at its maximum value returns
+ * -EINVAL without updating it.
+ */
+static int atomic_inc_return_safe(atomic_t *v)
+{
+	unsigned int counter;
+
+	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	if (counter <= (unsigned int)INT_MAX)
+		return (int)counter;
+
+	atomic_dec(v);
+
+	return -EINVAL;
+}
+
+/* Decrement the counter.  Return the resulting value, or -EINVAL */
+static int atomic_dec_return_safe(atomic_t *v)
+{
+	int counter;
+
+	counter = atomic_dec_return(v);
+	if (counter >= 0)
+		return counter;
+
+	atomic_inc(v);
+
+	return -EINVAL;
+}
+
 #define RBD_DRV_NAME "rbd"
 #define RBD_DRV_NAME_LONG "rbd (rados block device)"
 
@@ -100,21 +133,20 @@
  * block device image metadata (in-memory version)
  */
 struct rbd_image_header {
-	/* These four fields never change for a given rbd image */
+	/* These six fields never change for a given rbd image */
 	char *object_prefix;
-	u64 features;
 	__u8 obj_order;
 	__u8 crypt_type;
 	__u8 comp_type;
+	u64 stripe_unit;
+	u64 stripe_count;
+	u64 features;		/* Might be changeable someday? */
 
 	/* The remaining fields need to be updated occasionally */
 	u64 image_size;
 	struct ceph_snap_context *snapc;
-	char *snap_names;
-	u64 *snap_sizes;
-
-	u64 stripe_unit;
-	u64 stripe_count;
+	char *snap_names;	/* format 1 only */
+	u64 *snap_sizes;	/* format 1 only */
 };
 
 /*
@@ -225,6 +257,7 @@
 		};
 	};
 	struct page		**copyup_pages;
+	u32			copyup_page_count;
 
 	struct ceph_osd_request	*osd_req;
 
@@ -257,6 +290,7 @@
 		struct rbd_obj_request	*obj_request;	/* obj req initiator */
 	};
 	struct page		**copyup_pages;
+	u32			copyup_page_count;
 	spinlock_t		completion_lock;/* protects next_completion */
 	u32			next_completion;
 	rbd_img_callback_t	callback;
@@ -311,6 +345,7 @@
 
 	struct rbd_spec		*parent_spec;
 	u64			parent_overlap;
+	atomic_t		parent_ref;
 	struct rbd_device	*parent;
 
 	/* protects updating the header */
@@ -359,7 +394,8 @@
 		       size_t count);
 static ssize_t rbd_remove(struct bus_type *bus, const char *buf,
 			  size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static void rbd_spec_put(struct rbd_spec *spec);
 
 static struct bus_attribute rbd_bus_attrs[] = {
 	__ATTR(add, S_IWUSR, NULL, rbd_add),
@@ -426,7 +462,8 @@
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
 
 static int rbd_dev_refresh(struct rbd_device *rbd_dev);
-static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev);
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev);
+static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev);
 static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev,
 					u64 snap_id);
 static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
@@ -726,88 +763,123 @@
 }
 
 /*
- * Create a new header structure, translate header format from the on-disk
- * header.
+ * Fill an rbd image header with information from the given format 1
+ * on-disk header.
  */
-static int rbd_header_from_disk(struct rbd_image_header *header,
+static int rbd_header_from_disk(struct rbd_device *rbd_dev,
 				 struct rbd_image_header_ondisk *ondisk)
 {
+	struct rbd_image_header *header = &rbd_dev->header;
+	bool first_time = header->object_prefix == NULL;
+	struct ceph_snap_context *snapc;
+	char *object_prefix = NULL;
+	char *snap_names = NULL;
+	u64 *snap_sizes = NULL;
 	u32 snap_count;
-	size_t len;
 	size_t size;
+	int ret = -ENOMEM;
 	u32 i;
 
-	memset(header, 0, sizeof (*header));
+	/* Allocate this now to avoid having to handle failure below */
+
+	if (first_time) {
+		size_t len;
+
+		len = strnlen(ondisk->object_prefix,
+				sizeof (ondisk->object_prefix));
+		object_prefix = kmalloc(len + 1, GFP_KERNEL);
+		if (!object_prefix)
+			return -ENOMEM;
+		memcpy(object_prefix, ondisk->object_prefix, len);
+		object_prefix[len] = '\0';
+	}
+
+	/* Allocate the snapshot context and fill it in */
 
 	snap_count = le32_to_cpu(ondisk->snap_count);
-
-	len = strnlen(ondisk->object_prefix, sizeof (ondisk->object_prefix));
-	header->object_prefix = kmalloc(len + 1, GFP_KERNEL);
-	if (!header->object_prefix)
-		return -ENOMEM;
-	memcpy(header->object_prefix, ondisk->object_prefix, len);
-	header->object_prefix[len] = '\0';
-
+	snapc = ceph_create_snap_context(snap_count, GFP_KERNEL);
+	if (!snapc)
+		goto out_err;
+	snapc->seq = le64_to_cpu(ondisk->snap_seq);
 	if (snap_count) {
+		struct rbd_image_snap_ondisk *snaps;
 		u64 snap_names_len = le64_to_cpu(ondisk->snap_names_len);
 
-		/* Save a copy of the snapshot names */
+		/* We'll keep a copy of the snapshot names... */
 
-		if (snap_names_len > (u64) SIZE_MAX)
-			return -EIO;
-		header->snap_names = kmalloc(snap_names_len, GFP_KERNEL);
-		if (!header->snap_names)
+		if (snap_names_len > (u64)SIZE_MAX)
+			goto out_2big;
+		snap_names = kmalloc(snap_names_len, GFP_KERNEL);
+		if (!snap_names)
 			goto out_err;
+
+		/* ...as well as the array of their sizes. */
+
+		size = snap_count * sizeof (*header->snap_sizes);
+		snap_sizes = kmalloc(size, GFP_KERNEL);
+		if (!snap_sizes)
+			goto out_err;
+
 		/*
-		 * Note that rbd_dev_v1_header_read() guarantees
-		 * the ondisk buffer we're working with has
+		 * Copy the names, and fill in each snapshot's id
+		 * and size.
+		 *
+		 * Note that rbd_dev_v1_header_info() guarantees the
+		 * ondisk buffer we're working with has
 		 * snap_names_len bytes beyond the end of the
 		 * snapshot id array, this memcpy() is safe.
 		 */
-		memcpy(header->snap_names, &ondisk->snaps[snap_count],
-			snap_names_len);
-
-		/* Record each snapshot's size */
-
-		size = snap_count * sizeof (*header->snap_sizes);
-		header->snap_sizes = kmalloc(size, GFP_KERNEL);
-		if (!header->snap_sizes)
-			goto out_err;
-		for (i = 0; i < snap_count; i++)
-			header->snap_sizes[i] =
-				le64_to_cpu(ondisk->snaps[i].image_size);
-	} else {
-		header->snap_names = NULL;
-		header->snap_sizes = NULL;
+		memcpy(snap_names, &ondisk->snaps[snap_count], snap_names_len);
+		snaps = ondisk->snaps;
+		for (i = 0; i < snap_count; i++) {
+			snapc->snaps[i] = le64_to_cpu(snaps[i].id);
+			snap_sizes[i] = le64_to_cpu(snaps[i].image_size);
+		}
 	}
 
-	header->features = 0;	/* No features support in v1 images */
-	header->obj_order = ondisk->options.order;
-	header->crypt_type = ondisk->options.crypt_type;
-	header->comp_type = ondisk->options.comp_type;
+	/* We won't fail any more, fill in the header */
 
-	/* Allocate and fill in the snapshot context */
+	down_write(&rbd_dev->header_rwsem);
+	if (first_time) {
+		header->object_prefix = object_prefix;
+		header->obj_order = ondisk->options.order;
+		header->crypt_type = ondisk->options.crypt_type;
+		header->comp_type = ondisk->options.comp_type;
+		/* The rest aren't used for format 1 images */
+		header->stripe_unit = 0;
+		header->stripe_count = 0;
+		header->features = 0;
+	} else {
+		ceph_put_snap_context(header->snapc);
+		kfree(header->snap_names);
+		kfree(header->snap_sizes);
+	}
+
+	/* The remaining fields always get updated (when we refresh) */
 
 	header->image_size = le64_to_cpu(ondisk->image_size);
+	header->snapc = snapc;
+	header->snap_names = snap_names;
+	header->snap_sizes = snap_sizes;
 
-	header->snapc = ceph_create_snap_context(snap_count, GFP_KERNEL);
-	if (!header->snapc)
-		goto out_err;
-	header->snapc->seq = le64_to_cpu(ondisk->snap_seq);
-	for (i = 0; i < snap_count; i++)
-		header->snapc->snaps[i] = le64_to_cpu(ondisk->snaps[i].id);
+	/* Make sure mapping size is consistent with header info */
+
+	if (rbd_dev->spec->snap_id == CEPH_NOSNAP || first_time)
+		if (rbd_dev->mapping.size != header->image_size)
+			rbd_dev->mapping.size = header->image_size;
+
+	up_write(&rbd_dev->header_rwsem);
 
 	return 0;
-
+out_2big:
+	ret = -EIO;
 out_err:
-	kfree(header->snap_sizes);
-	header->snap_sizes = NULL;
-	kfree(header->snap_names);
-	header->snap_names = NULL;
-	kfree(header->object_prefix);
-	header->object_prefix = NULL;
+	kfree(snap_sizes);
+	kfree(snap_names);
+	ceph_put_snap_context(snapc);
+	kfree(object_prefix);
 
-	return -ENOMEM;
+	return ret;
 }
 
 static const char *_rbd_dev_v1_snap_name(struct rbd_device *rbd_dev, u32 which)
@@ -934,20 +1006,11 @@
 
 static int rbd_dev_mapping_set(struct rbd_device *rbd_dev)
 {
-	const char *snap_name = rbd_dev->spec->snap_name;
-	u64 snap_id;
+	u64 snap_id = rbd_dev->spec->snap_id;
 	u64 size = 0;
 	u64 features = 0;
 	int ret;
 
-	if (strcmp(snap_name, RBD_SNAP_HEAD_NAME)) {
-		snap_id = rbd_snap_id_by_name(rbd_dev, snap_name);
-		if (snap_id == CEPH_NOSNAP)
-			return -ENOENT;
-	} else {
-		snap_id = CEPH_NOSNAP;
-	}
-
 	ret = rbd_snap_size(rbd_dev, snap_id, &size);
 	if (ret)
 		return ret;
@@ -958,11 +1021,6 @@
 	rbd_dev->mapping.size = size;
 	rbd_dev->mapping.features = features;
 
-	/* If we are mapping a snapshot it must be marked read-only */
-
-	if (snap_id != CEPH_NOSNAP)
-		rbd_dev->mapping.read_only = true;
-
 	return 0;
 }
 
@@ -970,14 +1028,6 @@
 {
 	rbd_dev->mapping.size = 0;
 	rbd_dev->mapping.features = 0;
-	rbd_dev->mapping.read_only = true;
-}
-
-static void rbd_dev_clear_mapping(struct rbd_device *rbd_dev)
-{
-	rbd_dev->mapping.size = 0;
-	rbd_dev->mapping.features = 0;
-	rbd_dev->mapping.read_only = true;
 }
 
 static const char *rbd_segment_name(struct rbd_device *rbd_dev, u64 offset)
@@ -1342,20 +1392,18 @@
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
-static void rbd_img_request_get(struct rbd_img_request *img_request)
-{
-	dout("%s: img %p (was %d)\n", __func__, img_request,
-		atomic_read(&img_request->kref.refcount));
-	kref_get(&img_request->kref);
-}
-
+static bool img_request_child_test(struct rbd_img_request *img_request);
+static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
 static void rbd_img_request_put(struct rbd_img_request *img_request)
 {
 	rbd_assert(img_request != NULL);
 	dout("%s: img %p (was %d)\n", __func__, img_request,
 		atomic_read(&img_request->kref.refcount));
-	kref_put(&img_request->kref, rbd_img_request_destroy);
+	if (img_request_child_test(img_request))
+		kref_put(&img_request->kref, rbd_parent_request_destroy);
+	else
+		kref_put(&img_request->kref, rbd_img_request_destroy);
 }
 
 static inline void rbd_img_obj_request_add(struct rbd_img_request *img_request,
@@ -1472,6 +1520,12 @@
 	smp_mb();
 }
 
+static void img_request_child_clear(struct rbd_img_request *img_request)
+{
+	clear_bit(IMG_REQ_CHILD, &img_request->flags);
+	smp_mb();
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request)
 {
 	smp_mb();
@@ -1484,6 +1538,12 @@
 	smp_mb();
 }
 
+static void img_request_layered_clear(struct rbd_img_request *img_request)
+{
+	clear_bit(IMG_REQ_LAYERED, &img_request->flags);
+	smp_mb();
+}
+
 static bool img_request_layered_test(struct rbd_img_request *img_request)
 {
 	smp_mb();
@@ -1827,6 +1887,74 @@
 	kmem_cache_free(rbd_obj_request_cache, obj_request);
 }
 
+/* It's OK to call this for a device with no parent */
+
+static void rbd_spec_put(struct rbd_spec *spec);
+static void rbd_dev_unparent(struct rbd_device *rbd_dev)
+{
+	rbd_dev_remove_parent(rbd_dev);
+	rbd_spec_put(rbd_dev->parent_spec);
+	rbd_dev->parent_spec = NULL;
+	rbd_dev->parent_overlap = 0;
+}
+
+/*
+ * Parent image reference counting is used to determine when an
+ * image's parent fields can be safely torn down--after there are no
+ * more in-flight requests to the parent image.  When the last
+ * reference is dropped, cleaning them up is safe.
+ */
+static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
+{
+	int counter;
+
+	if (!rbd_dev->parent_spec)
+		return;
+
+	counter = atomic_dec_return_safe(&rbd_dev->parent_ref);
+	if (counter > 0)
+		return;
+
+	/* Last reference; clean up parent data structures */
+
+	if (!counter)
+		rbd_dev_unparent(rbd_dev);
+	else
+		rbd_warn(rbd_dev, "parent reference underflow\n");
+}
+
+/*
+ * If an image has a non-zero parent overlap, get a reference to its
+ * parent.
+ *
+ * We must get the reference before checking for the overlap to
+ * coordinate properly with zeroing the parent overlap in
+ * rbd_dev_v2_parent_info() when an image gets flattened.  We
+ * drop it again if there is no overlap.
+ *
+ * Returns true if the rbd device has a parent with a non-zero
+ * overlap and a reference for it was successfully taken, or
+ * false otherwise.
+ */
+static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
+{
+	int counter;
+
+	if (!rbd_dev->parent_spec)
+		return false;
+
+	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	if (counter > 0 && rbd_dev->parent_overlap)
+		return true;
+
+	/* Image was flattened, but parent is not yet torn down */
+
+	if (counter < 0)
+		rbd_warn(rbd_dev, "parent reference overflow\n");
+
+	return false;
+}
+
 /*
  * Caller is responsible for filling in the list of object requests
  * that comprises the image request, and the Linux request pointer
@@ -1835,8 +1963,7 @@
 static struct rbd_img_request *rbd_img_request_create(
 					struct rbd_device *rbd_dev,
 					u64 offset, u64 length,
-					bool write_request,
-					bool child_request)
+					bool write_request)
 {
 	struct rbd_img_request *img_request;
 
@@ -1861,9 +1988,7 @@
 	} else {
 		img_request->snap_id = rbd_dev->spec->snap_id;
 	}
-	if (child_request)
-		img_request_child_set(img_request);
-	if (rbd_dev->parent_spec)
+	if (rbd_dev_parent_get(rbd_dev))
 		img_request_layered_set(img_request);
 	spin_lock_init(&img_request->completion_lock);
 	img_request->next_completion = 0;
@@ -1873,9 +1998,6 @@
 	INIT_LIST_HEAD(&img_request->obj_requests);
 	kref_init(&img_request->kref);
 
-	rbd_img_request_get(img_request);	/* Avoid a warning */
-	rbd_img_request_put(img_request);	/* TEMPORARY */
-
 	dout("%s: rbd_dev %p %s %llu/%llu -> img %p\n", __func__, rbd_dev,
 		write_request ? "write" : "read", offset, length,
 		img_request);
@@ -1897,15 +2019,54 @@
 		rbd_img_obj_request_del(img_request, obj_request);
 	rbd_assert(img_request->obj_request_count == 0);
 
+	if (img_request_layered_test(img_request)) {
+		img_request_layered_clear(img_request);
+		rbd_dev_parent_put(img_request->rbd_dev);
+	}
+
 	if (img_request_write_test(img_request))
 		ceph_put_snap_context(img_request->snapc);
 
-	if (img_request_child_test(img_request))
-		rbd_obj_request_put(img_request->obj_request);
-
 	kmem_cache_free(rbd_img_request_cache, img_request);
 }
 
+static struct rbd_img_request *rbd_parent_request_create(
+					struct rbd_obj_request *obj_request,
+					u64 img_offset, u64 length)
+{
+	struct rbd_img_request *parent_request;
+	struct rbd_device *rbd_dev;
+
+	rbd_assert(obj_request->img_request);
+	rbd_dev = obj_request->img_request->rbd_dev;
+
+	parent_request = rbd_img_request_create(rbd_dev->parent,
+						img_offset, length, false);
+	if (!parent_request)
+		return NULL;
+
+	img_request_child_set(parent_request);
+	rbd_obj_request_get(obj_request);
+	parent_request->obj_request = obj_request;
+
+	return parent_request;
+}
+
+static void rbd_parent_request_destroy(struct kref *kref)
+{
+	struct rbd_img_request *parent_request;
+	struct rbd_obj_request *orig_request;
+
+	parent_request = container_of(kref, struct rbd_img_request, kref);
+	orig_request = parent_request->obj_request;
+
+	parent_request->obj_request = NULL;
+	rbd_obj_request_put(orig_request);
+	img_request_child_clear(parent_request);
+
+	rbd_img_request_destroy(kref);
+}
+
 static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
@@ -2114,7 +2275,7 @@
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
-	u64 length;
+	struct page **pages;
 	u32 page_count;
 
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
@@ -2124,12 +2285,14 @@
 
 	rbd_dev = img_request->rbd_dev;
 	rbd_assert(rbd_dev);
-	length = (u64)1 << rbd_dev->header.obj_order;
-	page_count = (u32)calc_pages_for(0, length);
 
-	rbd_assert(obj_request->copyup_pages);
-	ceph_release_page_vector(obj_request->copyup_pages, page_count);
+	pages = obj_request->copyup_pages;
+	rbd_assert(pages != NULL);
 	obj_request->copyup_pages = NULL;
+	page_count = obj_request->copyup_page_count;
+	rbd_assert(page_count);
+	obj_request->copyup_page_count = 0;
+	ceph_release_page_vector(pages, page_count);
 
 	/*
 	 * We want the transfer count to reflect the size of the
@@ -2153,9 +2316,11 @@
 	struct ceph_osd_client *osdc;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
-	int result;
-	u64 obj_size;
-	u64 xferred;
+	u32 page_count;
+	int img_result;
+	u64 parent_length;
+	u64 offset;
+	u64 length;
 
 	rbd_assert(img_request_child_test(img_request));
 
@@ -2164,46 +2329,74 @@
 	pages = img_request->copyup_pages;
 	rbd_assert(pages != NULL);
 	img_request->copyup_pages = NULL;
+	page_count = img_request->copyup_page_count;
+	rbd_assert(page_count);
+	img_request->copyup_page_count = 0;
 
 	orig_request = img_request->obj_request;
 	rbd_assert(orig_request != NULL);
-	rbd_assert(orig_request->type == OBJ_REQUEST_BIO);
-	result = img_request->result;
-	obj_size = img_request->length;
-	xferred = img_request->xferred;
-
-	rbd_dev = img_request->rbd_dev;
-	rbd_assert(rbd_dev);
-	rbd_assert(obj_size == (u64)1 << rbd_dev->header.obj_order);
-
+	rbd_assert(obj_request_type_valid(orig_request->type));
+	img_result = img_request->result;
+	parent_length = img_request->length;
+	rbd_assert(parent_length == img_request->xferred);
 	rbd_img_request_put(img_request);
 
-	if (result)
+	rbd_assert(orig_request->img_request);
+	rbd_dev = orig_request->img_request->rbd_dev;
+	rbd_assert(rbd_dev);
+
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to free the pages
+	 * and re-submit the original write request.
+	 */
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
+
+		ceph_release_page_vector(pages, page_count);
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		img_result = rbd_obj_request_submit(osdc, orig_request);
+		if (!img_result)
+			return;
+	}
+
+	if (img_result)
 		goto out_err;
 
-	/* Allocate the new copyup osd request for the original request */
-
-	result = -ENOMEM;
-	rbd_assert(!orig_request->osd_req);
+	/*
+	 * The original osd request is of no use to use any more.
+	 * We need a new one that can hold the two ops in a copyup
+	 * request.  Allocate the new copyup osd request for the
+	 * original request, and release the old one.
+	 */
+	img_result = -ENOMEM;
 	osd_req = rbd_osd_req_create_copyup(orig_request);
 	if (!osd_req)
 		goto out_err;
+	rbd_osd_req_destroy(orig_request->osd_req);
 	orig_request->osd_req = osd_req;
 	orig_request->copyup_pages = pages;
+	orig_request->copyup_page_count = page_count;
 
 	/* Initialize the copyup op */
 
 	osd_req_op_cls_init(osd_req, 0, CEPH_OSD_OP_CALL, "rbd", "copyup");
-	osd_req_op_cls_request_data_pages(osd_req, 0, pages, obj_size, 0,
+	osd_req_op_cls_request_data_pages(osd_req, 0, pages, parent_length, 0,
 						false, false);
 
 	/* Then the original write request op */
 
+	offset = orig_request->offset;
+	length = orig_request->length;
 	osd_req_op_extent_init(osd_req, 1, CEPH_OSD_OP_WRITE,
-					orig_request->offset,
-					orig_request->length, 0, 0);
-	osd_req_op_extent_osd_data_bio(osd_req, 1, orig_request->bio_list,
-					orig_request->length);
+					offset, length, 0, 0);
+	if (orig_request->type == OBJ_REQUEST_BIO)
+		osd_req_op_extent_osd_data_bio(osd_req, 1,
+					orig_request->bio_list, length);
+	else
+		osd_req_op_extent_osd_data_pages(osd_req, 1,
+					orig_request->pages, length,
+					offset & ~PAGE_MASK, false, false);
 
 	rbd_osd_req_format_write(orig_request);
 
@@ -2211,13 +2404,13 @@
 
 	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
-	result = rbd_obj_request_submit(osdc, orig_request);
-	if (!result)
+	img_result = rbd_obj_request_submit(osdc, orig_request);
+	if (!img_result)
 		return;
 out_err:
 	/* Record the error code and complete the request */
 
-	orig_request->result = result;
+	orig_request->result = img_result;
 	orig_request->xferred = 0;
 	obj_request_done_set(orig_request);
 	rbd_obj_request_complete(orig_request);
@@ -2249,7 +2442,7 @@
 	int result;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
-	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+	rbd_assert(obj_request_type_valid(obj_request->type));
 
 	img_request = obj_request->img_request;
 	rbd_assert(img_request != NULL);
@@ -2257,15 +2450,6 @@
 	rbd_assert(rbd_dev->parent != NULL);
 
 	/*
-	 * First things first.  The original osd request is of no
-	 * use to use any more, we'll need a new one that can hold
-	 * the two ops in a copyup request.  We'll get that later,
-	 * but for now we can release the old one.
-	 */
-	rbd_osd_req_destroy(obj_request->osd_req);
-	obj_request->osd_req = NULL;
-
-	/*
 	 * Determine the byte range covered by the object in the
 	 * child image to which the original request was to be sent.
 	 */
@@ -2295,18 +2479,16 @@
 	}
 
 	result = -ENOMEM;
-	parent_request = rbd_img_request_create(rbd_dev->parent,
-						img_offset, length,
-						false, true);
+	parent_request = rbd_parent_request_create(obj_request,
+						img_offset, length);
 	if (!parent_request)
 		goto out_err;
-	rbd_obj_request_get(obj_request);
-	parent_request->obj_request = obj_request;
 
 	result = rbd_img_request_fill(parent_request, OBJ_REQUEST_PAGES, pages);
 	if (result)
 		goto out_err;
 	parent_request->copyup_pages = pages;
+	parent_request->copyup_page_count = page_count;
 
 	parent_request->callback = rbd_img_obj_parent_read_full_callback;
 	result = rbd_img_request_submit(parent_request);
@@ -2314,6 +2496,7 @@
 		return 0;
 
 	parent_request->copyup_pages = NULL;
+	parent_request->copyup_page_count = 0;
 	parent_request->obj_request = NULL;
 	rbd_obj_request_put(obj_request);
 out_err:
@@ -2331,6 +2514,7 @@
 static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_obj_request *orig_request;
+	struct rbd_device *rbd_dev;
 	int result;
 
 	rbd_assert(!obj_request_img_data_test(obj_request));
@@ -2353,8 +2537,21 @@
 		obj_request->xferred, obj_request->length);
 	rbd_obj_request_put(obj_request);
 
-	rbd_assert(orig_request);
-	rbd_assert(orig_request->img_request);
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to free the pages
+	 * and re-submit the original write request.
+	 */
+	rbd_dev = orig_request->img_request->rbd_dev;
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
+
+		rbd_obj_request_put(orig_request);
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		result = rbd_obj_request_submit(osdc, orig_request);
+		if (!result)
+			return;
+	}
 
 	/*
 	 * Our only purpose here is to determine whether the object
@@ -2512,14 +2709,36 @@
 	struct rbd_obj_request *obj_request;
 	struct rbd_device *rbd_dev;
 	u64 obj_end;
+	u64 img_xferred;
+	int img_result;
 
 	rbd_assert(img_request_child_test(img_request));
 
+	/* First get what we need from the image request and release it */
+
 	obj_request = img_request->obj_request;
+	img_xferred = img_request->xferred;
+	img_result = img_request->result;
+	rbd_img_request_put(img_request);
+
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to re-submit the
+	 * original request.
+	 */
 	rbd_assert(obj_request);
 	rbd_assert(obj_request->img_request);
+	rbd_dev = obj_request->img_request->rbd_dev;
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
 
-	obj_request->result = img_request->result;
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		img_result = rbd_obj_request_submit(osdc, obj_request);
+		if (!img_result)
+			return;
+	}
+
+	obj_request->result = img_result;
 	if (obj_request->result)
 		goto out;
 
@@ -2532,7 +2751,6 @@
 	 */
 	rbd_assert(obj_request->img_offset < U64_MAX - obj_request->length);
 	obj_end = obj_request->img_offset + obj_request->length;
-	rbd_dev = obj_request->img_request->rbd_dev;
 	if (obj_end > rbd_dev->parent_overlap) {
 		u64 xferred = 0;
 
@@ -2540,43 +2758,39 @@
 			xferred = rbd_dev->parent_overlap -
 					obj_request->img_offset;
 
-		obj_request->xferred = min(img_request->xferred, xferred);
+		obj_request->xferred = min(img_xferred, xferred);
 	} else {
-		obj_request->xferred = img_request->xferred;
+		obj_request->xferred = img_xferred;
 	}
 out:
-	rbd_img_request_put(img_request);
 	rbd_img_obj_request_read_callback(obj_request);
 	rbd_obj_request_complete(obj_request);
 }
 
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request)
 {
-	struct rbd_device *rbd_dev;
 	struct rbd_img_request *img_request;
 	int result;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
 	rbd_assert(obj_request->img_request != NULL);
 	rbd_assert(obj_request->result == (s32) -ENOENT);
-	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+	rbd_assert(obj_request_type_valid(obj_request->type));
 
-	rbd_dev = obj_request->img_request->rbd_dev;
-	rbd_assert(rbd_dev->parent != NULL);
 	/* rbd_read_finish(obj_request, obj_request->length); */
-	img_request = rbd_img_request_create(rbd_dev->parent,
+	img_request = rbd_parent_request_create(obj_request,
 						obj_request->img_offset,
-						obj_request->length,
-						false, true);
+						obj_request->length);
 	result = -ENOMEM;
 	if (!img_request)
 		goto out_err;
 
-	rbd_obj_request_get(obj_request);
-	img_request->obj_request = obj_request;
-
-	result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
-					obj_request->bio_list);
+	if (obj_request->type == OBJ_REQUEST_BIO)
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
+						obj_request->bio_list);
+	else
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_PAGES,
+						obj_request->pages);
 	if (result)
 		goto out_err;
 
@@ -2626,6 +2840,7 @@
 static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 {
 	struct rbd_device *rbd_dev = (struct rbd_device *)data;
+	int ret;
 
 	if (!rbd_dev)
 		return;
@@ -2633,7 +2848,9 @@
 	dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__,
 		rbd_dev->header_name, (unsigned long long)notify_id,
 		(unsigned int)opcode);
-	(void)rbd_dev_refresh(rbd_dev);
+	ret = rbd_dev_refresh(rbd_dev);
+	if (ret)
+		rbd_warn(rbd_dev, ": header refresh error (%d)\n", ret);
 
 	rbd_obj_notify_ack(rbd_dev, notify_id);
 }
@@ -2642,7 +2859,7 @@
  * Request sync osd watch/unwatch.  The value of "start" determines
  * whether a watch request is being initiated or torn down.
  */
-static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, int start)
+static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
 	struct rbd_obj_request *obj_request;
@@ -2676,7 +2893,7 @@
 					rbd_dev->watch_request->osd_req);
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
-				rbd_dev->watch_event->cookie, 0, start);
+				rbd_dev->watch_event->cookie, 0, start ? 1 : 0);
 	rbd_osd_req_format_write(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
@@ -2869,9 +3086,16 @@
 			goto end_request;	/* Shouldn't happen */
 		}
 
+		result = -EIO;
+		if (offset + length > rbd_dev->mapping.size) {
+			rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)\n",
+				offset, length, rbd_dev->mapping.size);
+			goto end_request;
+		}
+
 		result = -ENOMEM;
 		img_request = rbd_img_request_create(rbd_dev, offset, length,
-							write_request, false);
+							write_request);
 		if (!img_request)
 			goto end_request;
 
@@ -3022,17 +3246,11 @@
 }
 
 /*
- * Read the complete header for the given rbd device.
- *
- * Returns a pointer to a dynamically-allocated buffer containing
- * the complete and validated header.  Caller can pass the address
- * of a variable that will be filled in with the version of the
- * header object at the time it was read.
- *
- * Returns a pointer-coded errno if a failure occurs.
+ * Read the complete header for the given rbd device.  On successful
+ * return, the rbd_dev->header field will contain up-to-date
+ * information about the image.
  */
-static struct rbd_image_header_ondisk *
-rbd_dev_v1_header_read(struct rbd_device *rbd_dev)
+static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header_ondisk *ondisk = NULL;
 	u32 snap_count = 0;
@@ -3057,22 +3275,22 @@
 		size += names_size;
 		ondisk = kmalloc(size, GFP_KERNEL);
 		if (!ondisk)
-			return ERR_PTR(-ENOMEM);
+			return -ENOMEM;
 
 		ret = rbd_obj_read_sync(rbd_dev, rbd_dev->header_name,
 				       0, size, ondisk);
 		if (ret < 0)
-			goto out_err;
+			goto out;
 		if ((size_t)ret < size) {
 			ret = -ENXIO;
 			rbd_warn(rbd_dev, "short header read (want %zd got %d)",
 				size, ret);
-			goto out_err;
+			goto out;
 		}
 		if (!rbd_dev_ondisk_valid(ondisk)) {
 			ret = -ENXIO;
 			rbd_warn(rbd_dev, "invalid header");
-			goto out_err;
+			goto out;
 		}
 
 		names_size = le64_to_cpu(ondisk->snap_names_len);
@@ -3080,82 +3298,10 @@
 		snap_count = le32_to_cpu(ondisk->snap_count);
 	} while (snap_count != want_count);
 
-	return ondisk;
-
-out_err:
+	ret = rbd_header_from_disk(rbd_dev, ondisk);
+out:
 	kfree(ondisk);
 
-	return ERR_PTR(ret);
-}
-
-/*
- * reload the ondisk the header
- */
-static int rbd_read_header(struct rbd_device *rbd_dev,
-			   struct rbd_image_header *header)
-{
-	struct rbd_image_header_ondisk *ondisk;
-	int ret;
-
-	ondisk = rbd_dev_v1_header_read(rbd_dev);
-	if (IS_ERR(ondisk))
-		return PTR_ERR(ondisk);
-	ret = rbd_header_from_disk(header, ondisk);
-	kfree(ondisk);
-
-	return ret;
-}
-
-static void rbd_update_mapping_size(struct rbd_device *rbd_dev)
-{
-	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
-		return;
-
-	if (rbd_dev->mapping.size != rbd_dev->header.image_size) {
-		sector_t size;
-
-		rbd_dev->mapping.size = rbd_dev->header.image_size;
-		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
-		dout("setting size to %llu sectors", (unsigned long long)size);
-		set_capacity(rbd_dev->disk, size);
-	}
-}
-
-/*
- * only read the first part of the ondisk header, without the snaps info
- */
-static int rbd_dev_v1_refresh(struct rbd_device *rbd_dev)
-{
-	int ret;
-	struct rbd_image_header h;
-
-	ret = rbd_read_header(rbd_dev, &h);
-	if (ret < 0)
-		return ret;
-
-	down_write(&rbd_dev->header_rwsem);
-
-	/* Update image size, and check for resize of mapped image */
-	rbd_dev->header.image_size = h.image_size;
-	rbd_update_mapping_size(rbd_dev);
-
-	/* rbd_dev->header.object_prefix shouldn't change */
-	kfree(rbd_dev->header.snap_sizes);
-	kfree(rbd_dev->header.snap_names);
-	/* osd requests may still refer to snapc */
-	ceph_put_snap_context(rbd_dev->header.snapc);
-
-	rbd_dev->header.image_size = h.image_size;
-	rbd_dev->header.snapc = h.snapc;
-	rbd_dev->header.snap_names = h.snap_names;
-	rbd_dev->header.snap_sizes = h.snap_sizes;
-	/* Free the extra copy of the object prefix */
-	if (strcmp(rbd_dev->header.object_prefix, h.object_prefix))
-		rbd_warn(rbd_dev, "object prefix changed (ignoring)");
-	kfree(h.object_prefix);
-
-	up_write(&rbd_dev->header_rwsem);
-
 	return ret;
 }
 
@@ -3180,26 +3326,29 @@
 
 static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 {
-	u64 image_size;
+	u64 mapping_size;
 	int ret;
 
 	rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
-	image_size = rbd_dev->header.image_size;
+	mapping_size = rbd_dev->mapping.size;
 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
 	if (rbd_dev->image_format == 1)
-		ret = rbd_dev_v1_refresh(rbd_dev);
+		ret = rbd_dev_v1_header_info(rbd_dev);
 	else
-		ret = rbd_dev_v2_refresh(rbd_dev);
+		ret = rbd_dev_v2_header_info(rbd_dev);
 
 	/* If it's a mapped snapshot, validate its EXISTS flag */
 
 	rbd_exists_validate(rbd_dev);
 	mutex_unlock(&ctl_mutex);
-	if (ret)
-		rbd_warn(rbd_dev, "got notification but failed to "
-			   " update snaps: %d\n", ret);
-	if (image_size != rbd_dev->header.image_size)
+	if (mapping_size != rbd_dev->mapping.size) {
+		sector_t size;
+
+		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
+		dout("setting size to %llu sectors", (unsigned long long)size);
+		set_capacity(rbd_dev->disk, size);
 		revalidate_disk(rbd_dev->disk);
+	}
 
 	return ret;
 }
@@ -3403,6 +3552,8 @@
 	int ret;
 
 	ret = rbd_dev_refresh(rbd_dev);
+	if (ret)
+		rbd_warn(rbd_dev, ": manual header refresh error (%d)\n", ret);
 
 	return ret < 0 ? ret : size;
 }
@@ -3501,6 +3652,7 @@
 
 	spin_lock_init(&rbd_dev->lock);
 	rbd_dev->flags = 0;
+	atomic_set(&rbd_dev->parent_ref, 0);
 	INIT_LIST_HEAD(&rbd_dev->node);
 	init_rwsem(&rbd_dev->header_rwsem);
 
@@ -3650,6 +3802,7 @@
 	__le64 snapid;
 	void *p;
 	void *end;
+	u64 pool_id;
 	char *image_id;
 	u64 overlap;
 	int ret;
@@ -3680,18 +3833,37 @@
 	p = reply_buf;
 	end = reply_buf + ret;
 	ret = -ERANGE;
-	ceph_decode_64_safe(&p, end, parent_spec->pool_id, out_err);
-	if (parent_spec->pool_id == CEPH_NOPOOL)
+	ceph_decode_64_safe(&p, end, pool_id, out_err);
+	if (pool_id == CEPH_NOPOOL) {
+		/*
+		 * Either the parent never existed, or we have
+		 * record of it but the image got flattened so it no
+		 * longer has a parent.  When the parent of a
+		 * layered image disappears we immediately set the
+		 * overlap to 0.  The effect of this is that all new
+		 * requests will be treated as if the image had no
+		 * parent.
+		 */
+		if (rbd_dev->parent_overlap) {
+			rbd_dev->parent_overlap = 0;
+			smp_mb();
+			rbd_dev_parent_put(rbd_dev);
+			pr_info("%s: clone image has been flattened\n",
+				rbd_dev->disk->disk_name);
+		}
+
 		goto out;	/* No parent?  No problem. */
+	}
 
 	/* The ceph file layout needs to fit pool id in 32 bits */
 
 	ret = -EIO;
-	if (parent_spec->pool_id > (u64)U32_MAX) {
+	if (pool_id > (u64)U32_MAX) {
 		rbd_warn(NULL, "parent pool id too large (%llu > %u)\n",
-			(unsigned long long)parent_spec->pool_id, U32_MAX);
+			(unsigned long long)pool_id, U32_MAX);
 		goto out_err;
 	}
+	parent_spec->pool_id = pool_id;
 
 	image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL);
 	if (IS_ERR(image_id)) {
@@ -3702,9 +3874,14 @@
 	ceph_decode_64_safe(&p, end, parent_spec->snap_id, out_err);
 	ceph_decode_64_safe(&p, end, overlap, out_err);
 
-	rbd_dev->parent_overlap = overlap;
-	rbd_dev->parent_spec = parent_spec;
-	parent_spec = NULL;	/* rbd_dev now owns this */
+	if (overlap) {
+		rbd_spec_put(rbd_dev->parent_spec);
+		rbd_dev->parent_spec = parent_spec;
+		parent_spec = NULL;	/* rbd_dev now owns this */
+		rbd_dev->parent_overlap = overlap;
+	} else {
+		rbd_warn(rbd_dev, "ignoring parent of clone with overlap 0\n");
+	}
 out:
 	ret = 0;
 out_err:
@@ -4002,6 +4179,7 @@
 	for (i = 0; i < snap_count; i++)
 		snapc->snaps[i] = ceph_decode_64(&p);
 
+	ceph_put_snap_context(rbd_dev->header.snapc);
 	rbd_dev->header.snapc = snapc;
 
 	dout("  snap context seq = %llu, snap_count = %u\n",
@@ -4053,21 +4231,56 @@
 	return snap_name;
 }
 
-static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
 {
+	bool first_time = rbd_dev->header.object_prefix == NULL;
 	int ret;
 
 	down_write(&rbd_dev->header_rwsem);
 
+	if (first_time) {
+		ret = rbd_dev_v2_header_onetime(rbd_dev);
+		if (ret)
+			goto out;
+	}
+
+	/*
+	 * If the image supports layering, get the parent info.  We
+	 * need to probe the first time regardless.  Thereafter we
+	 * only need to if there's a parent, to see if it has
+	 * disappeared due to the mapped image getting flattened.
+	 */
+	if (rbd_dev->header.features & RBD_FEATURE_LAYERING &&
+			(first_time || rbd_dev->parent_spec)) {
+		bool warn;
+
+		ret = rbd_dev_v2_parent_info(rbd_dev);
+		if (ret)
+			goto out;
+
+		/*
+		 * Print a warning if this is the initial probe and
+		 * the image has a parent.  Don't print it if the
+		 * image now being probed is itself a parent.  We
+		 * can tell at this point because we won't know its
+		 * pool name yet (just its pool id).
+		 */
+		warn = rbd_dev->parent_spec && rbd_dev->spec->pool_name;
+		if (first_time && warn)
+			rbd_warn(rbd_dev, "WARNING: kernel layering "
+					"is EXPERIMENTAL!");
+	}
+
 	ret = rbd_dev_v2_image_size(rbd_dev);
 	if (ret)
 		goto out;
-	rbd_update_mapping_size(rbd_dev);
+
+	if (rbd_dev->spec->snap_id == CEPH_NOSNAP)
+		if (rbd_dev->mapping.size != rbd_dev->header.image_size)
+			rbd_dev->mapping.size = rbd_dev->header.image_size;
 
 	ret = rbd_dev_v2_snap_context(rbd_dev);
 	dout("rbd_dev_v2_snap_context returned %d\n", ret);
-	if (ret)
-		goto out;
 out:
 	up_write(&rbd_dev->header_rwsem);
 
@@ -4490,10 +4703,10 @@
 {
 	struct rbd_image_header	*header;
 
-	rbd_dev_remove_parent(rbd_dev);
-	rbd_spec_put(rbd_dev->parent_spec);
-	rbd_dev->parent_spec = NULL;
-	rbd_dev->parent_overlap = 0;
+	/* Drop parent reference unless it's already been done (or none) */
+
+	if (rbd_dev->parent_overlap)
+		rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
@@ -4505,72 +4718,22 @@
 	memset(header, 0, sizeof (*header));
 }
 
-static int rbd_dev_v1_probe(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev)
 {
 	int ret;
 
-	/* Populate rbd image metadata */
-
-	ret = rbd_read_header(rbd_dev, &rbd_dev->header);
-	if (ret < 0)
-		goto out_err;
-
-	/* Version 1 images have no parent (no layering) */
-
-	rbd_dev->parent_spec = NULL;
-	rbd_dev->parent_overlap = 0;
-
-	dout("discovered version 1 image, header name is %s\n",
-		rbd_dev->header_name);
-
-	return 0;
-
-out_err:
-	kfree(rbd_dev->header_name);
-	rbd_dev->header_name = NULL;
-	kfree(rbd_dev->spec->image_id);
-	rbd_dev->spec->image_id = NULL;
-
-	return ret;
-}
-
-static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
-{
-	int ret;
-
-	ret = rbd_dev_v2_image_size(rbd_dev);
-	if (ret)
-		goto out_err;
-
-	/* Get the object prefix (a.k.a. block_name) for the image */
-
 	ret = rbd_dev_v2_object_prefix(rbd_dev);
 	if (ret)
 		goto out_err;
 
-	/* Get the and check features for the image */
-
+	/*
+	 * Get the and check features for the image.  Currently the
+	 * features are assumed to never change.
+	 */
 	ret = rbd_dev_v2_features(rbd_dev);
 	if (ret)
 		goto out_err;
 
-	/* If the image supports layering, get the parent info */
-
-	if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
-		ret = rbd_dev_v2_parent_info(rbd_dev);
-		if (ret)
-			goto out_err;
-
-		/*
-		 * Don't print a warning for parent images.  We can
-		 * tell this point because we won't know its pool
-		 * name yet (just its pool id).
-		 */
-		if (rbd_dev->spec->pool_name)
-			rbd_warn(rbd_dev, "WARNING: kernel layering "
-					"is EXPERIMENTAL!");
-	}
-
 	/* If the image supports fancy striping, get its parameters */
 
 	if (rbd_dev->header.features & RBD_FEATURE_STRIPINGV2) {
@@ -4578,28 +4741,11 @@
 		if (ret < 0)
 			goto out_err;
 	}
-
-	/* crypto and compression type aren't (yet) supported for v2 images */
-
-	rbd_dev->header.crypt_type = 0;
-	rbd_dev->header.comp_type = 0;
-
-	/* Get the snapshot context, plus the header version */
-
-	ret = rbd_dev_v2_snap_context(rbd_dev);
-	if (ret)
-		goto out_err;
-
-	dout("discovered version 2 image, header name is %s\n",
-		rbd_dev->header_name);
+	/* No support for crypto and compression type format 2 images */
 
 	return 0;
 out_err:
-	rbd_dev->parent_overlap = 0;
-	rbd_spec_put(rbd_dev->parent_spec);
-	rbd_dev->parent_spec = NULL;
-	kfree(rbd_dev->header_name);
-	rbd_dev->header_name = NULL;
+	rbd_dev->header.features = 0;
 	kfree(rbd_dev->header.object_prefix);
 	rbd_dev->header.object_prefix = NULL;
 
@@ -4628,15 +4774,16 @@
 	if (!parent)
 		goto out_err;
 
-	ret = rbd_dev_image_probe(parent);
+	ret = rbd_dev_image_probe(parent, false);
 	if (ret < 0)
 		goto out_err;
 	rbd_dev->parent = parent;
+	atomic_set(&rbd_dev->parent_ref, 1);
 
 	return 0;
 out_err:
 	if (parent) {
-		rbd_spec_put(rbd_dev->parent_spec);
+		rbd_dev_unparent(rbd_dev);
 		kfree(rbd_dev->header_name);
 		rbd_dev_destroy(parent);
 	} else {
@@ -4651,10 +4798,6 @@
 {
 	int ret;
 
-	ret = rbd_dev_mapping_set(rbd_dev);
-	if (ret)
-		return ret;
-
 	/* generate unique id: find highest unique id, add one */
 	rbd_dev_id_get(rbd_dev);
 
@@ -4676,13 +4819,17 @@
 	if (ret)
 		goto err_out_blkdev;
 
-	ret = rbd_bus_add_dev(rbd_dev);
+	ret = rbd_dev_mapping_set(rbd_dev);
 	if (ret)
 		goto err_out_disk;
+	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
+
+	ret = rbd_bus_add_dev(rbd_dev);
+	if (ret)
+		goto err_out_mapping;
 
 	/* Everything's ready.  Announce the disk to the world. */
 
-	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
 	set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
 	add_disk(rbd_dev->disk);
 
@@ -4691,6 +4838,8 @@
 
 	return ret;
 
+err_out_mapping:
+	rbd_dev_mapping_clear(rbd_dev);
 err_out_disk:
 	rbd_free_disk(rbd_dev);
 err_out_blkdev:
@@ -4731,12 +4880,7 @@
 
 static void rbd_dev_image_release(struct rbd_device *rbd_dev)
 {
-	int ret;
-
 	rbd_dev_unprobe(rbd_dev);
-	ret = rbd_dev_header_watch_sync(rbd_dev, 0);
-	if (ret)
-		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
 	rbd_dev->image_format = 0;
@@ -4748,10 +4892,11 @@
 
 /*
  * Probe for the existence of the header object for the given rbd
- * device.  For format 2 images this includes determining the image
- * id.
+ * device.  If this image is the one being mapped (i.e., not a
+ * parent), initiate a watch on its header object before using that
+ * object to get detailed information about the rbd image.
  */
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 {
 	int ret;
 	int tmp;
@@ -4771,14 +4916,16 @@
 	if (ret)
 		goto err_out_format;
 
-	ret = rbd_dev_header_watch_sync(rbd_dev, 1);
-	if (ret)
-		goto out_header_name;
+	if (mapping) {
+		ret = rbd_dev_header_watch_sync(rbd_dev, true);
+		if (ret)
+			goto out_header_name;
+	}
 
 	if (rbd_dev->image_format == 1)
-		ret = rbd_dev_v1_probe(rbd_dev);
+		ret = rbd_dev_v1_header_info(rbd_dev);
 	else
-		ret = rbd_dev_v2_probe(rbd_dev);
+		ret = rbd_dev_v2_header_info(rbd_dev);
 	if (ret)
 		goto err_out_watch;
 
@@ -4787,15 +4934,22 @@
 		goto err_out_probe;
 
 	ret = rbd_dev_probe_parent(rbd_dev);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto err_out_probe;
 
+	dout("discovered format %u image, header name is %s\n",
+		rbd_dev->image_format, rbd_dev->header_name);
+
+	return 0;
 err_out_probe:
 	rbd_dev_unprobe(rbd_dev);
 err_out_watch:
-	tmp = rbd_dev_header_watch_sync(rbd_dev, 0);
-	if (tmp)
-		rbd_warn(rbd_dev, "unable to tear down watch request\n");
+	if (mapping) {
+		tmp = rbd_dev_header_watch_sync(rbd_dev, false);
+		if (tmp)
+			rbd_warn(rbd_dev, "unable to tear down "
+					"watch request (%d)\n", tmp);
+	}
 out_header_name:
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
@@ -4819,6 +4973,7 @@
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
 	struct ceph_osd_client *osdc;
+	bool read_only;
 	int rc = -ENOMEM;
 
 	if (!try_module_get(THIS_MODULE))
@@ -4828,6 +4983,9 @@
 	rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec);
 	if (rc < 0)
 		goto err_out_module;
+	read_only = rbd_opts->read_only;
+	kfree(rbd_opts);
+	rbd_opts = NULL;	/* done with this */
 
 	rbdc = rbd_get_client(ceph_opts);
 	if (IS_ERR(rbdc)) {
@@ -4858,14 +5016,16 @@
 	rbdc = NULL;		/* rbd_dev now owns this */
 	spec = NULL;		/* rbd_dev now owns this */
 
-	rbd_dev->mapping.read_only = rbd_opts->read_only;
-	kfree(rbd_opts);
-	rbd_opts = NULL;	/* done with this */
-
-	rc = rbd_dev_image_probe(rbd_dev);
+	rc = rbd_dev_image_probe(rbd_dev, true);
 	if (rc < 0)
 		goto err_out_rbd_dev;
 
+	/* If we are mapping a snapshot it must be marked read-only */
+
+	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
+		read_only = true;
+	rbd_dev->mapping.read_only = read_only;
+
 	rc = rbd_dev_device_setup(rbd_dev);
 	if (!rc)
 		return count;
@@ -4911,7 +5071,7 @@
 
 	rbd_free_disk(rbd_dev);
 	clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
-	rbd_dev_clear_mapping(rbd_dev);
+	rbd_dev_mapping_clear(rbd_dev);
 	unregister_blkdev(rbd_dev->major, rbd_dev->name);
 	rbd_dev->major = 0;
 	rbd_dev_id_put(rbd_dev);
@@ -4978,10 +5138,13 @@
 	spin_unlock_irq(&rbd_dev->lock);
 	if (ret < 0)
 		goto done;
-	ret = count;
 	rbd_bus_del_dev(rbd_dev);
+	ret = rbd_dev_header_watch_sync(rbd_dev, false);
+	if (ret)
+		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
 	rbd_dev_image_release(rbd_dev);
 	module_put(THIS_MODULE);
+	ret = count;
 done:
 	mutex_unlock(&ctl_mutex);
 
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index f8ef15f..3fd130f 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1160,8 +1160,7 @@
 	dev_dbg(&dev->dev, "ace_probe(%p)\n", dev);
 
 	/* device id and bus width */
-	of_property_read_u32(dev->dev.of_node, "port-number", &id);
-	if (id < 0)
+	if (of_property_read_u32(dev->dev.of_node, "port-number", &id))
 		id = 0;
 	if (of_find_property(dev->dev.of_node, "8-bit", NULL))
 		bus_width = ACE_BUS_WIDTH_8;
diff --git a/drivers/char/hw_random/mxc-rnga.c b/drivers/char/hw_random/mxc-rnga.c
index 4ca35e8..19a12ac 100644
--- a/drivers/char/hw_random/mxc-rnga.c
+++ b/drivers/char/hw_random/mxc-rnga.c
@@ -167,11 +167,6 @@
 	clk_prepare_enable(mxc_rng->clk);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		err = -ENOENT;
-		goto err_region;
-	}
-
 	mxc_rng->mem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(mxc_rng->mem)) {
 		err = PTR_ERR(mxc_rng->mem);
@@ -189,7 +184,6 @@
 	return 0;
 
 err_ioremap:
-err_region:
 	clk_disable_unprepare(mxc_rng->clk);
 
 out:
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 749dc16..d2903e7 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -119,11 +119,6 @@
 	dev_set_drvdata(&pdev->dev, priv);
 
 	priv->mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!priv->mem_res) {
-		ret = -ENOENT;
-		goto err_ioremap;
-	}
-
 	priv->base = devm_ioremap_resource(&pdev->dev, priv->mem_res);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index cdd4c09f..a22a7a5 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -95,9 +95,9 @@
 	enum bt_states	state;
 	unsigned char	seq;		/* BT sequence number */
 	struct si_sm_io	*io;
-	unsigned char	write_data[IPMI_MAX_MSG_LENGTH];
+	unsigned char	write_data[IPMI_MAX_MSG_LENGTH + 2]; /* +2 for memcpy */
 	int		write_count;
-	unsigned char	read_data[IPMI_MAX_MSG_LENGTH];
+	unsigned char	read_data[IPMI_MAX_MSG_LENGTH + 2]; /* +2 for memcpy */
 	int		read_count;
 	int		truncated;
 	long		timeout;	/* microseconds countdown */
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index 9eb360f..d5a5f02 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -837,13 +837,25 @@
 		return ipmi_ioctl(filep, cmd, arg);
 	}
 }
+
+static long unlocked_compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
+				       unsigned long arg)
+{
+	int ret;
+
+	mutex_lock(&ipmi_mutex);
+	ret = compat_ipmi_ioctl(filep, cmd, arg);
+	mutex_unlock(&ipmi_mutex);
+
+	return ret;
+}
 #endif
 
 static const struct file_operations ipmi_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= ipmi_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl   = compat_ipmi_ioctl,
+	.compat_ioctl   = unlocked_compat_ipmi_ioctl,
 #endif
 	.open		= ipmi_open,
 	.release	= ipmi_release,
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 4d439d2..4445fa1 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -2037,12 +2037,11 @@
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
-	entry->name = kmalloc(strlen(name)+1, GFP_KERNEL);
+	entry->name = kstrdup(name, GFP_KERNEL);
 	if (!entry->name) {
 		kfree(entry);
 		return -ENOMEM;
 	}
-	strcpy(entry->name, name);
 
 	file = proc_create_data(name, 0, smi->proc_dir, proc_ops, data);
 	if (!file) {
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 313538a..af4b23f 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -663,8 +663,10 @@
 		/* We got the flags from the SMI, now handle them. */
 		smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
 		if (msg[2] != 0) {
-			dev_warn(smi_info->dev, "Could not enable interrupts"
-				 ", failed get, using polled mode.\n");
+			dev_warn(smi_info->dev,
+				 "Couldn't get irq info: %x.\n", msg[2]);
+			dev_warn(smi_info->dev,
+				 "Maybe ok, but ipmi might run very slowly.\n");
 			smi_info->si_state = SI_NORMAL;
 		} else {
 			msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
@@ -685,10 +687,12 @@
 
 		/* We got the flags from the SMI, now handle them. */
 		smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
-		if (msg[2] != 0)
-			dev_warn(smi_info->dev, "Could not enable interrupts"
-				 ", failed set, using polled mode.\n");
-		else
+		if (msg[2] != 0) {
+			dev_warn(smi_info->dev,
+				 "Couldn't set irq info: %x.\n", msg[2]);
+			dev_warn(smi_info->dev,
+				 "Maybe ok, but ipmi might run very slowly.\n");
+		} else
 			smi_info->interrupt_disabled = 0;
 		smi_info->si_state = SI_NORMAL;
 		break;
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index dafd9ac..0913d79 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -622,9 +622,12 @@
 				return -EFAULT;
 			break;
 		case LPGETSTATUS:
+			if (mutex_lock_interruptible(&lp_table[minor].port_mutex))
+				return -EINTR;
 			lp_claim_parport_or_block (&lp_table[minor]);
 			status = r_str(minor);
 			lp_release_parport (&lp_table[minor]);
+			mutex_unlock(&lp_table[minor].port_mutex);
 
 			if (copy_to_user(argp, &status, sizeof(int)))
 				return -EFAULT;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index cd9a621..35487e8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -865,16 +865,24 @@
 	if (r->entropy_count / 8 < min + reserved) {
 		nbytes = 0;
 	} else {
+		int entropy_count, orig;
+retry:
+		entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 		/* If limited, never pull more than available */
-		if (r->limit && nbytes + reserved >= r->entropy_count / 8)
-			nbytes = r->entropy_count/8 - reserved;
+		if (r->limit && nbytes + reserved >= entropy_count / 8)
+			nbytes = entropy_count/8 - reserved;
 
-		if (r->entropy_count / 8 >= nbytes + reserved)
-			r->entropy_count -= nbytes*8;
-		else
-			r->entropy_count = reserved;
+		if (entropy_count / 8 >= nbytes + reserved) {
+			entropy_count -= nbytes*8;
+			if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+				goto retry;
+		} else {
+			entropy_count = reserved;
+			if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+				goto retry;
+		}
 
-		if (r->entropy_count < random_write_wakeup_thresh)
+		if (entropy_count < random_write_wakeup_thresh)
 			wakeup_write = 1;
 	}
 
@@ -957,10 +965,23 @@
 {
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
+	unsigned long flags;
 
 	/* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */
-	if (fips_enabled && !r->last_data_init)
-		nbytes += EXTRACT_SIZE;
+	if (fips_enabled) {
+		spin_lock_irqsave(&r->lock, flags);
+		if (!r->last_data_init) {
+			r->last_data_init = true;
+			spin_unlock_irqrestore(&r->lock, flags);
+			trace_extract_entropy(r->name, EXTRACT_SIZE,
+					      r->entropy_count, _RET_IP_);
+			xfer_secondary_pool(r, EXTRACT_SIZE);
+			extract_buf(r, tmp);
+			spin_lock_irqsave(&r->lock, flags);
+			memcpy(r->last_data, tmp, EXTRACT_SIZE);
+		}
+		spin_unlock_irqrestore(&r->lock, flags);
+	}
 
 	trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
@@ -970,19 +991,6 @@
 		extract_buf(r, tmp);
 
 		if (fips_enabled) {
-			unsigned long flags;
-
-
-			/* prime last_data value if need be, per fips 140-2 */
-			if (!r->last_data_init) {
-				spin_lock_irqsave(&r->lock, flags);
-				memcpy(r->last_data, tmp, EXTRACT_SIZE);
-				r->last_data_init = true;
-				nbytes -= EXTRACT_SIZE;
-				spin_unlock_irqrestore(&r->lock, flags);
-				extract_buf(r, tmp);
-			}
-
 			spin_lock_irqsave(&r->lock, flags);
 			if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
 				panic("Hardware RNG duplicated output!\n");
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index 4945bd3..d5d2e4a 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -179,7 +179,6 @@
 {
 	int ret = -ENOMEM;
 
-	tpk_port.port.ops = &null_ops;
 	mutex_init(&tpk_port.port_write_mutex);
 
 	ttyprintk_driver = tty_alloc_driver(1,
@@ -190,6 +189,7 @@
 		return PTR_ERR(ttyprintk_driver);
 
 	tty_port_init(&tpk_port.port);
+	tpk_port.port.ops = &null_ops;
 
 	ttyprintk_driver->driver_name = "ttyprintk";
 	ttyprintk_driver->name = "ttyprintk";
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index 8292a00..075db0c 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -872,6 +872,14 @@
 	struct clk *clk;
 	int i;
 
+	/* ac97 */
+	clk = tegra_clk_register_periph_gate("ac97", "pll_a_out0",
+				    TEGRA_PERIPH_ON_APB,
+				    clk_base, 0, 3, &periph_l_regs,
+				    periph_clk_enb_refcnt);
+	clk_register_clkdev(clk, NULL, "tegra20-ac97");
+	clks[ac97] = clk;
+
 	/* apbdma */
 	clk = tegra_clk_register_periph_gate("apbdma", "pclk", 0, clk_base,
 				    0, 34, &periph_h_regs,
@@ -1234,9 +1242,6 @@
 	{uartc, pll_p, 0, 0},
 	{uartd, pll_p, 0, 0},
 	{uarte, pll_p, 0, 0},
-	{usbd, clk_max, 12000000, 0},
-	{usb2, clk_max, 12000000, 0},
-	{usb3, clk_max, 12000000, 0},
 	{pll_a, clk_max, 56448000, 1},
 	{pll_a_out0, clk_max, 11289600, 1},
 	{cdev1, clk_max, 0, 1},
diff --git a/drivers/clk/x86/clk-lpt.c b/drivers/clk/x86/clk-lpt.c
index 5cf4f46..4f45eee 100644
--- a/drivers/clk/x86/clk-lpt.c
+++ b/drivers/clk/x86/clk-lpt.c
@@ -15,22 +15,29 @@
 #include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/platform_data/clk-lpss.h>
 #include <linux/platform_device.h>
 
 #define PRV_CLOCK_PARAMS 0x800
 
 static int lpt_clk_probe(struct platform_device *pdev)
 {
+	struct lpss_clk_data *drvdata;
 	struct clk *clk;
 
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
 	/* LPSS free running clock */
-	clk = clk_register_fixed_rate(&pdev->dev, "lpss_clk", NULL, CLK_IS_ROOT,
-				      100000000);
+	drvdata->name = "lpss_clk";
+	clk = clk_register_fixed_rate(&pdev->dev, drvdata->name, NULL,
+				      CLK_IS_ROOT, 100000000);
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
-	/* Shared DMA clock */
-	clk_register_clkdev(clk, "hclk", "INTL9C60.0.auto");
+	drvdata->clk = clk;
+	platform_set_drvdata(pdev, drvdata);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index a1488f5..534fcb8 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -47,7 +47,7 @@
 
 choice
 	prompt "Default CPUFreq governor"
-	default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110
+	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
 	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	help
 	  This option sets which CPUFreq governor shall be loaded at
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index f3af18b..6e57543 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -3,16 +3,17 @@
 #
 
 config ARM_BIG_LITTLE_CPUFREQ
-	tristate
-	depends on ARM_CPU_TOPOLOGY
+	tristate "Generic ARM big LITTLE CPUfreq driver"
+	depends on ARM_CPU_TOPOLOGY && PM_OPP && HAVE_CLK
+	help
+	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
 
 config ARM_DT_BL_CPUFREQ
-	tristate "Generic ARM big LITTLE CPUfreq driver probed via DT"
-	select ARM_BIG_LITTLE_CPUFREQ
-	depends on OF && HAVE_CLK
+	tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && OF
 	help
-	  This enables the Generic CPUfreq driver for ARM big.LITTLE platform.
-	  This gets frequency tables from DT.
+	  This enables probing via DT for Generic CPUfreq driver for ARM
+	  big.LITTLE platform. This gets frequency tables from DT.
 
 config ARM_EXYNOS_CPUFREQ
 	bool "SAMSUNG EXYNOS SoCs"
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 2b8a8c3..6bd63d6 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -272,7 +272,7 @@
 config X86_E_POWERSAVER
 	tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
 	select CPU_FREQ_TABLE
-	depends on X86_32
+	depends on X86_32 && ACPI_PROCESSOR
 	help
 	  This adds the CPUFreq driver for VIA C7 processors.  However, this driver
 	  does not have any safeguards to prevent operating the CPU out of spec
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index dbdf677..5d7f53f 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -40,11 +40,6 @@
 static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS];
 static atomic_t cluster_usage[MAX_CLUSTERS] = {ATOMIC_INIT(0), ATOMIC_INIT(0)};
 
-static int cpu_to_cluster(int cpu)
-{
-	return topology_physical_package_id(cpu);
-}
-
 static unsigned int bL_cpufreq_get(unsigned int cpu)
 {
 	u32 cur_cluster = cpu_to_cluster(cpu);
@@ -192,7 +187,7 @@
 
 	cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
 
-	dev_info(cpu_dev, "CPU %d initialized\n", policy->cpu);
+	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index 70f18fc..79b2ce1 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -34,6 +34,11 @@
 	int (*init_opp_table)(struct device *cpu_dev);
 };
 
+static inline int cpu_to_cluster(int cpu)
+{
+	return topology_physical_package_id(cpu);
+}
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
 void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops);
 
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index 44be311..fd9e3ea 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -19,69 +19,75 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/opp.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include "arm_big_little.h"
 
-static int dt_init_opp_table(struct device *cpu_dev)
+/* get cpu node with valid operating-points */
+static struct device_node *get_cpu_node_with_valid_op(int cpu)
 {
-	struct device_node *np, *parent;
-	int count = 0, ret;
-
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
-	}
-
-	for_each_child_of_node(parent, np) {
-		if (count++ != cpu_dev->id)
-			continue;
-		if (!of_get_property(np, "operating-points", NULL)) {
-			ret = -ENODATA;
-		} else {
-			cpu_dev->of_node = np;
-			ret = of_init_opp_table(cpu_dev);
-		}
-		of_node_put(np);
-		of_node_put(parent);
-
-		return ret;
-	}
-
-	return -ENODEV;
-}
-
-static int dt_get_transition_latency(struct device *cpu_dev)
-{
-	struct device_node *np, *parent;
-	u32 transition_latency = CPUFREQ_ETERNAL;
+	struct device_node *np = NULL, *parent;
 	int count = 0;
 
 	parent = of_find_node_by_path("/cpus");
 	if (!parent) {
 		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
+		return NULL;
 	}
 
 	for_each_child_of_node(parent, np) {
-		if (count++ != cpu_dev->id)
+		if (count++ != cpu)
 			continue;
+		if (!of_get_property(np, "operating-points", NULL)) {
+			of_node_put(np);
+			np = NULL;
+		}
 
-		of_property_read_u32(np, "clock-latency", &transition_latency);
-		of_node_put(np);
-		of_node_put(parent);
-
-		return 0;
+		break;
 	}
 
-	return -ENODEV;
+	of_node_put(parent);
+	return np;
+}
+
+static int dt_init_opp_table(struct device *cpu_dev)
+{
+	struct device_node *np;
+	int ret;
+
+	np = get_cpu_node_with_valid_op(cpu_dev->id);
+	if (!np)
+		return -ENODATA;
+
+	cpu_dev->of_node = np;
+	ret = of_init_opp_table(cpu_dev);
+	of_node_put(np);
+
+	return ret;
+}
+
+static int dt_get_transition_latency(struct device *cpu_dev)
+{
+	struct device_node *np;
+	u32 transition_latency = CPUFREQ_ETERNAL;
+
+	np = get_cpu_node_with_valid_op(cpu_dev->id);
+	if (!np)
+		return CPUFREQ_ETERNAL;
+
+	of_property_read_u32(np, "clock-latency", &transition_latency);
+	of_node_put(np);
+
+	pr_debug("%s: clock-latency: %d\n", __func__, transition_latency);
+	return transition_latency;
 }
 
 static struct cpufreq_arm_bL_ops dt_bL_ops = {
@@ -90,17 +96,33 @@
 	.init_opp_table = dt_init_opp_table,
 };
 
-static int generic_bL_init(void)
+static int generic_bL_probe(struct platform_device *pdev)
 {
+	struct device_node *np;
+
+	np = get_cpu_node_with_valid_op(0);
+	if (!np)
+		return -ENODEV;
+
+	of_node_put(np);
 	return bL_cpufreq_register(&dt_bL_ops);
 }
-module_init(generic_bL_init);
 
-static void generic_bL_exit(void)
+static int generic_bL_remove(struct platform_device *pdev)
 {
-	return bL_cpufreq_unregister(&dt_bL_ops);
+	bL_cpufreq_unregister(&dt_bL_ops);
+	return 0;
 }
-module_exit(generic_bL_exit);
+
+static struct platform_driver generic_bL_platdrv = {
+	.driver = {
+		.name	= "arm-bL-cpufreq-dt",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= generic_bL_probe,
+	.remove		= generic_bL_remove,
+};
+module_platform_driver(generic_bL_platdrv);
 
 MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
 MODULE_DESCRIPTION("Generic ARM big LITTLE cpufreq driver via DT");
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 3ab8294..a64eb8b 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -189,12 +189,29 @@
 
 	if (!np) {
 		pr_err("failed to find cpu0 node\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out_put_parent;
 	}
 
 	cpu_dev = &pdev->dev;
 	cpu_dev->of_node = np;
 
+	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
+	if (IS_ERR(cpu_reg)) {
+		/*
+		 * If cpu0 regulator supply node is present, but regulator is
+		 * not yet registered, we should try defering probe.
+		 */
+		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
+			dev_err(cpu_dev, "cpu0 regulator not ready, retry\n");
+			ret = -EPROBE_DEFER;
+			goto out_put_node;
+		}
+		pr_warn("failed to get cpu0 regulator: %ld\n",
+			PTR_ERR(cpu_reg));
+		cpu_reg = NULL;
+	}
+
 	cpu_clk = devm_clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
@@ -202,12 +219,6 @@
 		goto out_put_node;
 	}
 
-	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
-	if (IS_ERR(cpu_reg)) {
-		pr_warn("failed to get cpu0 regulator\n");
-		cpu_reg = NULL;
-	}
-
 	ret = of_init_opp_table(cpu_dev);
 	if (ret) {
 		pr_err("failed to init OPP table: %d\n", ret);
@@ -264,6 +275,8 @@
 	opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_put_node:
 	of_node_put(np);
+out_put_parent:
+	of_node_put(parent);
 	return ret;
 }
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1b8a48e..2d53f47 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1075,14 +1075,14 @@
 				__func__, cpu_dev->id, cpu);
 	}
 
+	if ((cpus == 1) && (cpufreq_driver->target))
+		__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
 	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
 	cpufreq_cpu_put(data);
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target)
-			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
 		lock_policy_rwsem_read(cpu);
 		kobj = &data->kobj;
 		cmp = &data->kobj_unregister;
@@ -1729,18 +1729,23 @@
 			/* end old governor */
 			if (data->governor) {
 				__cpufreq_governor(data, CPUFREQ_GOV_STOP);
+				unlock_policy_rwsem_write(policy->cpu);
 				__cpufreq_governor(data,
 						CPUFREQ_GOV_POLICY_EXIT);
+				lock_policy_rwsem_write(policy->cpu);
 			}
 
 			/* start new governor */
 			data->governor = policy->governor;
 			if (!__cpufreq_governor(data, CPUFREQ_GOV_POLICY_INIT)) {
-				if (!__cpufreq_governor(data, CPUFREQ_GOV_START))
+				if (!__cpufreq_governor(data, CPUFREQ_GOV_START)) {
 					failed = 0;
-				else
+				} else {
+					unlock_policy_rwsem_write(policy->cpu);
 					__cpufreq_governor(data,
 							CPUFREQ_GOV_POLICY_EXIT);
+					lock_policy_rwsem_write(policy->cpu);
+				}
 			}
 
 			if (failed) {
@@ -1832,15 +1837,13 @@
 	if (dev) {
 		switch (action) {
 		case CPU_ONLINE:
-		case CPU_ONLINE_FROZEN:
 			cpufreq_add_dev(dev, NULL);
 			break;
 		case CPU_DOWN_PREPARE:
-		case CPU_DOWN_PREPARE_FROZEN:
+		case CPU_UP_CANCELED_FROZEN:
 			__cpufreq_remove_dev(dev, NULL);
 			break;
 		case CPU_DOWN_FAILED:
-		case CPU_DOWN_FAILED_FROZEN:
 			cpufreq_add_dev(dev, NULL);
 			break;
 		}
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 443442d..5af40ad 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -255,6 +255,7 @@
 		if (have_governor_per_policy()) {
 			WARN_ON(dbs_data);
 		} else if (dbs_data) {
+			dbs_data->usage_count++;
 			policy->governor_data = dbs_data;
 			return 0;
 		}
@@ -266,6 +267,7 @@
 		}
 
 		dbs_data->cdata = cdata;
+		dbs_data->usage_count = 1;
 		rc = cdata->init(dbs_data);
 		if (rc) {
 			pr_err("%s: POLICY_INIT: init() failed\n", __func__);
@@ -294,7 +296,8 @@
 		set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
 					latency * LATENCY_MULTIPLIER));
 
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+		if ((cdata->governor == GOV_CONSERVATIVE) &&
+				(!policy->governor->initialized)) {
 			struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 			cpufreq_register_notifier(cs_ops->notifier_block,
@@ -306,12 +309,12 @@
 
 		return 0;
 	case CPUFREQ_GOV_POLICY_EXIT:
-		if ((policy->governor->initialized == 1) ||
-				have_governor_per_policy()) {
+		if (!--dbs_data->usage_count) {
 			sysfs_remove_group(get_governor_parent_kobj(policy),
 					get_sysfs_attr(dbs_data));
 
-			if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+			if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
+				(policy->governor->initialized == 1)) {
 				struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 				cpufreq_unregister_notifier(cs_ops->notifier_block,
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 8ac3353..e16a961 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -211,6 +211,7 @@
 struct dbs_data {
 	struct common_dbs_data *cdata;
 	unsigned int min_sampling_rate;
+	int usage_count;
 	void *tuners;
 
 	/* dbs_mutex protects dbs_enable in governor start/stop */
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index b0ffef9..4b9bb5d 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -547,7 +547,6 @@
 	tuners->io_is_busy = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
-	pr_info("%s: tuners %p\n", __func__, tuners);
 	mutex_init(&dbs_data->mutex);
 	return 0;
 }
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index bfd6273..fb65dec 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -349,15 +349,16 @@
 
 	switch (action) {
 	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
 		cpufreq_update_policy(cpu);
 		break;
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		cpufreq_stats_free_sysfs(cpu);
 		break;
 	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
+		cpufreq_stats_free_table(cpu);
+		break;
+	case CPU_UP_CANCELED_FROZEN:
+		cpufreq_stats_free_sysfs(cpu);
 		cpufreq_stats_free_table(cpu);
 		break;
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index cc3a8e6..07f2840 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -48,12 +48,7 @@
 }
 
 struct sample {
-	ktime_t start_time;
-	ktime_t end_time;
 	int core_pct_busy;
-	int pstate_pct_busy;
-	u64 duration_us;
-	u64 idletime_us;
 	u64 aperf;
 	u64 mperf;
 	int freq;
@@ -86,13 +81,9 @@
 	struct pstate_adjust_policy *pstate_policy;
 	struct pstate_data pstate;
 	struct _pid pid;
-	struct _pid idle_pid;
 
 	int min_pstate_count;
-	int idle_mode;
 
-	ktime_t prev_sample;
-	u64	prev_idle_time_us;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	int	sample_ptr;
@@ -124,6 +115,8 @@
 	int min_perf_pct;
 	int32_t max_perf;
 	int32_t min_perf;
+	int max_policy_pct;
+	int max_sysfs_pct;
 };
 
 static struct perf_limits limits = {
@@ -132,6 +125,8 @@
 	.max_perf = int_tofp(1),
 	.min_perf_pct = 0,
 	.min_perf = 0,
+	.max_policy_pct = 100,
+	.max_sysfs_pct = 100,
 };
 
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
@@ -202,19 +197,6 @@
 		0);
 }
 
-static inline void intel_pstate_idle_pid_reset(struct cpudata *cpu)
-{
-	pid_p_gain_set(&cpu->idle_pid, cpu->pstate_policy->p_gain_pct);
-	pid_d_gain_set(&cpu->idle_pid, cpu->pstate_policy->d_gain_pct);
-	pid_i_gain_set(&cpu->idle_pid, cpu->pstate_policy->i_gain_pct);
-
-	pid_reset(&cpu->idle_pid,
-		75,
-		50,
-		cpu->pstate_policy->deadband,
-		0);
-}
-
 static inline void intel_pstate_reset_all_pid(void)
 {
 	unsigned int cpu;
@@ -302,7 +284,8 @@
 	if (ret != 1)
 		return -EINVAL;
 
-	limits.max_perf_pct = clamp_t(int, input, 0 , 100);
+	limits.max_sysfs_pct = clamp_t(int, input, 0 , 100);
+	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
 	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 	return count;
 }
@@ -408,9 +391,8 @@
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-#ifndef MODULE
 	trace_cpu_frequency(pstate * 100000, cpu->cpu);
-#endif
+
 	cpu->pstate.current_pstate = pstate;
 	wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
 
@@ -450,48 +432,26 @@
 					struct sample *sample)
 {
 	u64 core_pct;
-	sample->pstate_pct_busy = 100 - div64_u64(
-					sample->idletime_us * 100,
-					sample->duration_us);
 	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
 	sample->freq = cpu->pstate.max_pstate * core_pct * 1000;
 
-	sample->core_pct_busy = div_s64((sample->pstate_pct_busy * core_pct),
-					100);
+	sample->core_pct_busy = core_pct;
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
-	ktime_t now;
-	u64 idle_time_us;
 	u64 aperf, mperf;
 
-	now = ktime_get();
-	idle_time_us = get_cpu_idle_time_us(cpu->cpu, NULL);
-
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	/* for the first sample, don't actually record a sample, just
-	 * set the baseline */
-	if (cpu->prev_idle_time_us > 0) {
-		cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
-		cpu->samples[cpu->sample_ptr].start_time = cpu->prev_sample;
-		cpu->samples[cpu->sample_ptr].end_time = now;
-		cpu->samples[cpu->sample_ptr].duration_us =
-			ktime_us_delta(now, cpu->prev_sample);
-		cpu->samples[cpu->sample_ptr].idletime_us =
-			idle_time_us - cpu->prev_idle_time_us;
+	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
+	cpu->samples[cpu->sample_ptr].aperf = aperf;
+	cpu->samples[cpu->sample_ptr].mperf = mperf;
+	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
+	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
 
-		cpu->samples[cpu->sample_ptr].aperf = aperf;
-		cpu->samples[cpu->sample_ptr].mperf = mperf;
-		cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
-		cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
 
-		intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
-	}
-
-	cpu->prev_sample = now;
-	cpu->prev_idle_time_us = idle_time_us;
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
 }
@@ -505,16 +465,6 @@
 	mod_timer_pinned(&cpu->timer, jiffies + delay);
 }
 
-static inline void intel_pstate_idle_mode(struct cpudata *cpu)
-{
-	cpu->idle_mode = 1;
-}
-
-static inline void intel_pstate_normal_mode(struct cpudata *cpu)
-{
-	cpu->idle_mode = 0;
-}
-
 static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
 	int32_t busy_scaled;
@@ -547,50 +497,21 @@
 		intel_pstate_pstate_decrease(cpu, steps);
 }
 
-static inline void intel_pstate_adjust_idle_pstate(struct cpudata *cpu)
-{
-	int busy_scaled;
-	struct _pid *pid;
-	int ctl = 0;
-	int steps;
-
-	pid = &cpu->idle_pid;
-
-	busy_scaled = intel_pstate_get_scaled_busy(cpu);
-
-	ctl = pid_calc(pid, 100 - busy_scaled);
-
-	steps = abs(ctl);
-	if (ctl < 0)
-		intel_pstate_pstate_decrease(cpu, steps);
-	else
-		intel_pstate_pstate_increase(cpu, steps);
-
-	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate)
-		intel_pstate_normal_mode(cpu);
-}
-
 static void intel_pstate_timer_func(unsigned long __data)
 {
 	struct cpudata *cpu = (struct cpudata *) __data;
 
 	intel_pstate_sample(cpu);
+	intel_pstate_adjust_busy_pstate(cpu);
 
-	if (!cpu->idle_mode)
-		intel_pstate_adjust_busy_pstate(cpu);
-	else
-		intel_pstate_adjust_idle_pstate(cpu);
-
-#if defined(XPERF_FIX)
 	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate) {
 		cpu->min_pstate_count++;
 		if (!(cpu->min_pstate_count % 5)) {
 			intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
-			intel_pstate_idle_mode(cpu);
 		}
 	} else
 		cpu->min_pstate_count = 0;
-#endif
+
 	intel_pstate_set_sample_time(cpu);
 }
 
@@ -600,6 +521,7 @@
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, default_policy),
 	ICPU(0x2d, default_policy),
+	ICPU(0x3a, default_policy),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -631,7 +553,6 @@
 		(unsigned long)cpu;
 	cpu->timer.expires = jiffies + HZ/100;
 	intel_pstate_busy_pid_reset(cpu);
-	intel_pstate_idle_pid_reset(cpu);
 	intel_pstate_sample(cpu);
 	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
 
@@ -675,8 +596,9 @@
 	limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100);
 	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
 
-	limits.max_perf_pct = policy->max * 100 / policy->cpuinfo.max_freq;
-	limits.max_perf_pct = clamp_t(int, limits.max_perf_pct, 0 , 100);
+	limits.max_policy_pct = policy->max * 100 / policy->cpuinfo.max_freq;
+	limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
+	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
 	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 
 	return 0;
@@ -788,10 +710,9 @@
 
 	pr_info("Intel P-state driver initializing.\n");
 
-	all_cpu_data = vmalloc(sizeof(void *) * num_possible_cpus());
+	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
-	memset(all_cpu_data, 0, sizeof(void *) * num_possible_cpus());
 
 	rc = cpufreq_register_driver(&intel_pstate_driver);
 	if (rc)
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index d36ea8d..b2644af 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -171,10 +171,6 @@
 	priv.dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Cannot get memory resource\n");
-		return -ENODEV;
-	}
 	priv.base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(priv.base))
 		return PTR_ERR(priv.base);
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index 8488957..d539127 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -18,6 +18,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/clock.h>
+#include <asm/idle.h>
 
 #include <asm/mach-loongson/loongson.h>
 
@@ -200,6 +201,7 @@
 	LOONGSON_CHIPCFG0 &= ~0x7;	/* Put CPU into wait mode */
 	LOONGSON_CHIPCFG0 = cpu_freq;	/* Restore CPU state */
 	spin_unlock_irqrestore(&loongson2_wait_lock, flags);
+	local_irq_enable();
 }
 
 static int __init cpufreq_init(void)
diff --git a/drivers/crypto/nx/nx-aes-cbc.c b/drivers/crypto/nx/nx-aes-cbc.c
index a76d4c4..35d483f 100644
--- a/drivers/crypto/nx/nx-aes-cbc.c
+++ b/drivers/crypto/nx/nx-aes-cbc.c
@@ -126,6 +126,7 @@
 	.cra_blocksize   = AES_BLOCK_SIZE,
 	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
 	.cra_type        = &crypto_blkcipher_type,
+	.cra_alignmask   = 0xf,
 	.cra_module      = THIS_MODULE,
 	.cra_init        = nx_crypto_ctx_aes_cbc_init,
 	.cra_exit        = nx_crypto_ctx_exit,
diff --git a/drivers/crypto/nx/nx-aes-ecb.c b/drivers/crypto/nx/nx-aes-ecb.c
index ba5f161..7bbc9a8 100644
--- a/drivers/crypto/nx/nx-aes-ecb.c
+++ b/drivers/crypto/nx/nx-aes-ecb.c
@@ -123,6 +123,7 @@
 	.cra_priority    = 300,
 	.cra_flags       = CRYPTO_ALG_TYPE_BLKCIPHER,
 	.cra_blocksize   = AES_BLOCK_SIZE,
+	.cra_alignmask   = 0xf,
 	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
 	.cra_type        = &crypto_blkcipher_type,
 	.cra_module      = THIS_MODULE,
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index c8109ed..6cca6c3 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -219,7 +219,7 @@
 	if (enc)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 	else
-		nbytes -= AES_BLOCK_SIZE;
+		nbytes -= crypto_aead_authsize(crypto_aead_reqtfm(req));
 
 	csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
 
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 9767315..67024f2 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -69,7 +69,7 @@
 	 *  1: <= SHA256_BLOCK_SIZE: copy into state, return 0
 	 *  2: > SHA256_BLOCK_SIZE: process X blocks, copy in leftover
 	 */
-	if (len + sctx->count <= SHA256_BLOCK_SIZE) {
+	if (len + sctx->count < SHA256_BLOCK_SIZE) {
 		memcpy(sctx->buf + sctx->count, data, len);
 		sctx->count += len;
 		goto out;
@@ -110,7 +110,8 @@
 	atomic_inc(&(nx_ctx->stats->sha256_ops));
 
 	/* copy the leftover back into the state struct */
-	memcpy(sctx->buf, data + len - leftover, leftover);
+	if (leftover)
+		memcpy(sctx->buf, data + len - leftover, leftover);
 	sctx->count = leftover;
 
 	csbcpb->cpb.sha256.message_bit_length += (u64)
@@ -130,6 +131,7 @@
 	struct nx_sg *in_sg, *out_sg;
 	int rc;
 
+
 	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
 		/* we've hit the nx chip previously, now we're finalizing,
 		 * so copy over the partial digest */
@@ -162,7 +164,7 @@
 
 	atomic_inc(&(nx_ctx->stats->sha256_ops));
 
-	atomic64_add(csbcpb->cpb.sha256.message_bit_length,
+	atomic64_add(csbcpb->cpb.sha256.message_bit_length / 8,
 		     &(nx_ctx->stats->sha256_bytes));
 	memcpy(out, csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
 out:
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index 3177b8c..08eee11 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -69,7 +69,7 @@
 	 *  1: <= SHA512_BLOCK_SIZE: copy into state, return 0
 	 *  2: > SHA512_BLOCK_SIZE: process X blocks, copy in leftover
 	 */
-	if ((u64)len + sctx->count[0] <= SHA512_BLOCK_SIZE) {
+	if ((u64)len + sctx->count[0] < SHA512_BLOCK_SIZE) {
 		memcpy(sctx->buf + sctx->count[0], data, len);
 		sctx->count[0] += len;
 		goto out;
@@ -110,7 +110,8 @@
 	atomic_inc(&(nx_ctx->stats->sha512_ops));
 
 	/* copy the leftover back into the state struct */
-	memcpy(sctx->buf, data + len - leftover, leftover);
+	if (leftover)
+		memcpy(sctx->buf, data + len - leftover, leftover);
 	sctx->count[0] = leftover;
 
 	spbc_bits = csbcpb->cpb.sha512.spbc * 8;
@@ -168,7 +169,7 @@
 		goto out;
 
 	atomic_inc(&(nx_ctx->stats->sha512_ops));
-	atomic64_add(csbcpb->cpb.sha512.message_bit_length_lo,
+	atomic64_add(csbcpb->cpb.sha512.message_bit_length_lo / 8,
 		     &(nx_ctx->stats->sha512_bytes));
 
 	memcpy(out, csbcpb->cpb.sha512.message_digest, SHA512_DIGEST_SIZE);
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index c767f23..bbdab6e 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -211,44 +211,20 @@
 {
 	struct nx_sg *nx_insg = nx_ctx->in_sg;
 	struct nx_sg *nx_outsg = nx_ctx->out_sg;
-	struct blkcipher_walk walk;
-	int rc;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	rc = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
-	if (rc)
-		goto out;
 
 	if (iv)
-		memcpy(iv, walk.iv, AES_BLOCK_SIZE);
+		memcpy(iv, desc->info, AES_BLOCK_SIZE);
 
-	while (walk.nbytes) {
-		nx_insg = nx_build_sg_list(nx_insg, walk.src.virt.addr,
-					   walk.nbytes, nx_ctx->ap->sglen);
-		nx_outsg = nx_build_sg_list(nx_outsg, walk.dst.virt.addr,
-					    walk.nbytes, nx_ctx->ap->sglen);
-
-		rc = blkcipher_walk_done(desc, &walk, 0);
-		if (rc)
-			break;
-	}
-
-	if (walk.nbytes) {
-		nx_insg = nx_build_sg_list(nx_insg, walk.src.virt.addr,
-					   walk.nbytes, nx_ctx->ap->sglen);
-		nx_outsg = nx_build_sg_list(nx_outsg, walk.dst.virt.addr,
-					    walk.nbytes, nx_ctx->ap->sglen);
-
-		rc = 0;
-	}
+	nx_insg = nx_walk_and_build(nx_insg, nx_ctx->ap->sglen, src, 0, nbytes);
+	nx_outsg = nx_walk_and_build(nx_outsg, nx_ctx->ap->sglen, dst, 0, nbytes);
 
 	/* these lengths should be negative, which will indicate to phyp that
 	 * the input and output parameters are scatterlists, not linear
 	 * buffers */
 	nx_ctx->op.inlen = (nx_ctx->in_sg - nx_insg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - nx_outsg) * sizeof(struct nx_sg);
-out:
-	return rc;
+
+	return 0;
 }
 
 /**
@@ -454,6 +430,8 @@
 	if (rc)
 		goto out;
 
+	nx_driver.of.status = NX_OKAY;
+
 	rc = crypto_register_alg(&nx_ecb_aes_alg);
 	if (rc)
 		goto out;
@@ -498,8 +476,6 @@
 	if (rc)
 		goto out_unreg_s512;
 
-	nx_driver.of.status = NX_OKAY;
-
 	goto out;
 
 out_unreg_s512:
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index ba6fc62..5a18f82 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -4,7 +4,8 @@
  * Based on of-dma.c
  *
  * Copyright (C) 2013, Intel Corporation
- * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *	    Mika Westerberg <mika.westerberg@linux.intel.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -16,6 +17,7 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/ioport.h>
 #include <linux/acpi.h>
 #include <linux/acpi_dma.h>
 
@@ -23,6 +25,117 @@
 static DEFINE_MUTEX(acpi_dma_lock);
 
 /**
+ * acpi_dma_parse_resource_group - match device and parse resource group
+ * @grp:	CSRT resource group
+ * @adev:	ACPI device to match with
+ * @adma:	struct acpi_dma of the given DMA controller
+ *
+ * Returns 1 on success, 0 when no information is available, or appropriate
+ * errno value on error.
+ *
+ * In order to match a device from DSDT table to the corresponding CSRT device
+ * we use MMIO address and IRQ.
+ */
+static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
+		struct acpi_device *adev, struct acpi_dma *adma)
+{
+	const struct acpi_csrt_shared_info *si;
+	struct list_head resource_list;
+	struct resource_list_entry *rentry;
+	resource_size_t mem = 0, irq = 0;
+	u32 vendor_id;
+	int ret;
+
+	if (grp->shared_info_length != sizeof(struct acpi_csrt_shared_info))
+		return -ENODEV;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
+	if (ret <= 0)
+		return 0;
+
+	list_for_each_entry(rentry, &resource_list, node) {
+		if (resource_type(&rentry->res) == IORESOURCE_MEM)
+			mem = rentry->res.start;
+		else if (resource_type(&rentry->res) == IORESOURCE_IRQ)
+			irq = rentry->res.start;
+	}
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	/* Consider initial zero values as resource not found */
+	if (mem == 0 && irq == 0)
+		return 0;
+
+	si = (const struct acpi_csrt_shared_info *)&grp[1];
+
+	/* Match device by MMIO and IRQ */
+	if (si->mmio_base_low != mem || si->gsi_interrupt != irq)
+		return 0;
+
+	vendor_id = le32_to_cpu(grp->vendor_id);
+	dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n",
+		(char *)&vendor_id, grp->device_id, grp->revision);
+
+	/* Check if the request line range is available */
+	if (si->base_request_line == 0 && si->num_handshake_signals == 0)
+		return 0;
+
+	adma->base_request_line = si->base_request_line;
+	adma->end_request_line = si->base_request_line +
+				 si->num_handshake_signals - 1;
+
+	dev_dbg(&adev->dev, "request line base: 0x%04x end: 0x%04x\n",
+		adma->base_request_line, adma->end_request_line);
+
+	return 1;
+}
+
+/**
+ * acpi_dma_parse_csrt - parse CSRT to exctract additional DMA resources
+ * @adev:	ACPI device to match with
+ * @adma:	struct acpi_dma of the given DMA controller
+ *
+ * CSRT or Core System Resources Table is a proprietary ACPI table
+ * introduced by Microsoft. This table can contain devices that are not in
+ * the system DSDT table. In particular DMA controllers might be described
+ * here.
+ *
+ * We are using this table to get the request line range of the specific DMA
+ * controller to be used later.
+ *
+ */
+static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
+{
+	struct acpi_csrt_group *grp, *end;
+	struct acpi_table_csrt *csrt;
+	acpi_status status;
+	int ret;
+
+	status = acpi_get_table(ACPI_SIG_CSRT, 0,
+				(struct acpi_table_header **)&csrt);
+	if (ACPI_FAILURE(status)) {
+		if (status != AE_NOT_FOUND)
+			dev_warn(&adev->dev, "failed to get the CSRT table\n");
+		return;
+	}
+
+	grp = (struct acpi_csrt_group *)(csrt + 1);
+	end = (struct acpi_csrt_group *)((void *)csrt + csrt->header.length);
+
+	while (grp < end) {
+		ret = acpi_dma_parse_resource_group(grp, adev, adma);
+		if (ret < 0) {
+			dev_warn(&adev->dev,
+				 "error in parsing resource group\n");
+			return;
+		}
+
+		grp = (struct acpi_csrt_group *)((void *)grp + grp->length);
+	}
+}
+
+/**
  * acpi_dma_controller_register - Register a DMA controller to ACPI DMA helpers
  * @dev:		struct device of DMA controller
  * @acpi_dma_xlate:	translation function which converts a dma specifier
@@ -61,6 +174,8 @@
 	adma->acpi_dma_xlate = acpi_dma_xlate;
 	adma->data = data;
 
+	acpi_dma_parse_csrt(adev, adma);
+
 	/* Now queue acpi_dma controller structure in list */
 	mutex_lock(&acpi_dma_lock);
 	list_add_tail(&adma->dma_controllers, &acpi_dma_list);
@@ -149,6 +264,45 @@
 }
 EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free);
 
+/**
+ * acpi_dma_update_dma_spec - prepare dma specifier to pass to translation function
+ * @adma:	struct acpi_dma of DMA controller
+ * @dma_spec:	dma specifier to update
+ *
+ * Returns 0, if no information is avaiable, -1 on mismatch, and 1 otherwise.
+ *
+ * Accordingly to ACPI 5.0 Specification Table 6-170 "Fixed DMA Resource
+ * Descriptor":
+ *	DMA Request Line bits is a platform-relative number uniquely
+ *	identifying the request line assigned. Request line-to-Controller
+ *	mapping is done in a controller-specific OS driver.
+ * That's why we can safely adjust slave_id when the appropriate controller is
+ * found.
+ */
+static int acpi_dma_update_dma_spec(struct acpi_dma *adma,
+		struct acpi_dma_spec *dma_spec)
+{
+	/* Set link to the DMA controller device */
+	dma_spec->dev = adma->dev;
+
+	/* Check if the request line range is available */
+	if (adma->base_request_line == 0 && adma->end_request_line == 0)
+		return 0;
+
+	/* Check if slave_id falls to the range */
+	if (dma_spec->slave_id < adma->base_request_line ||
+	    dma_spec->slave_id > adma->end_request_line)
+		return -1;
+
+	/*
+	 * Here we adjust slave_id. It should be a relative number to the base
+	 * request line.
+	 */
+	dma_spec->slave_id -= adma->base_request_line;
+
+	return 1;
+}
+
 struct acpi_dma_parser_data {
 	struct acpi_dma_spec dma_spec;
 	size_t index;
@@ -193,6 +347,7 @@
 	struct acpi_device *adev;
 	struct acpi_dma *adma;
 	struct dma_chan *chan = NULL;
+	int found;
 
 	/* Check if the device was enumerated by ACPI */
 	if (!dev || !ACPI_HANDLE(dev))
@@ -219,9 +374,20 @@
 	mutex_lock(&acpi_dma_lock);
 
 	list_for_each_entry(adma, &acpi_dma_list, dma_controllers) {
-		dma_spec->dev = adma->dev;
+		/*
+		 * We are not going to call translation function if slave_id
+		 * doesn't fall to the request range.
+		 */
+		found = acpi_dma_update_dma_spec(adma, dma_spec);
+		if (found < 0)
+			continue;
 		chan = adma->acpi_dma_xlate(dma_spec, adma);
-		if (chan)
+		/*
+		 * Try to get a channel only from the DMA controller that
+		 * matches the slave_id. See acpi_dma_update_dma_spec()
+		 * description for the details.
+		 */
+		if (found > 0 || chan)
 			break;
 	}
 
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index ce19340..33f59ec 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -1273,11 +1273,6 @@
 	platform_set_drvdata(pdev, tdma);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "No mem resource for DMA\n");
-		return -EINVAL;
-	}
-
 	tdma->base_addr = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(tdma->base_addr))
 		return PTR_ERR(tdma->base_addr);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 87d5670..573c449 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -636,7 +636,7 @@
 
 config GPIO_MCP23S08
 	tristate "Microchip MCP23xxx I/O expander"
-	depends on SPI_MASTER || I2C
+	depends on (SPI_MASTER && !I2C) || I2C
 	help
 	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
 	  I/O expanders.
diff --git a/drivers/gpio/gpio-langwell.c b/drivers/gpio/gpio-langwell.c
index 634c3d3..62ef10a 100644
--- a/drivers/gpio/gpio-langwell.c
+++ b/drivers/gpio/gpio-langwell.c
@@ -324,6 +324,7 @@
 	resource_size_t start, len;
 	struct lnw_gpio *lnw;
 	u32 gpio_base;
+	u32 irq_base;
 	int retval;
 	int ngpio = id->driver_data;
 
@@ -345,6 +346,7 @@
 		retval = -EFAULT;
 		goto err_ioremap;
 	}
+	irq_base = *(u32 *)base;
 	gpio_base = *((u32 *)base + 1);
 	/* release the IO mapping, since we already get the info from bar1 */
 	iounmap(base);
@@ -365,13 +367,6 @@
 		goto err_ioremap;
 	}
 
-	lnw->domain = irq_domain_add_linear(pdev->dev.of_node, ngpio,
-					    &lnw_gpio_irq_ops, lnw);
-	if (!lnw->domain) {
-		retval = -ENOMEM;
-		goto err_ioremap;
-	}
-
 	lnw->reg_base = base;
 	lnw->chip.label = dev_name(&pdev->dev);
 	lnw->chip.request = lnw_gpio_request;
@@ -384,6 +379,14 @@
 	lnw->chip.ngpio = ngpio;
 	lnw->chip.can_sleep = 0;
 	lnw->pdev = pdev;
+
+	lnw->domain = irq_domain_add_simple(pdev->dev.of_node, ngpio, irq_base,
+					    &lnw_gpio_irq_ops, lnw);
+	if (!lnw->domain) {
+		retval = -ENOMEM;
+		goto err_ioremap;
+	}
+
 	pci_set_drvdata(pdev, lnw);
 	retval = gpiochip_add(&lnw->chip);
 	if (retval) {
diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c
index b733665..0966f26 100644
--- a/drivers/gpio/gpio-ml-ioh.c
+++ b/drivers/gpio/gpio-ml-ioh.c
@@ -496,8 +496,7 @@
 err_gpiochip_add:
 	while (--i >= 0) {
 		chip--;
-		ret = gpiochip_remove(&chip->gpio);
-		if (ret)
+		if (gpiochip_remove(&chip->gpio))
 			dev_err(&pdev->dev, "Failed gpiochip_remove(%d)\n", i);
 	}
 	kfree(chip_save);
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index bf69a7e..3a4816a 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -619,11 +619,6 @@
 	 * per-CPU registers */
 	if (soc_variant == MVEBU_GPIO_SOC_VARIANT_ARMADAXP) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		if (!res) {
-			dev_err(&pdev->dev, "Cannot get memory resource\n");
-			return -ENODEV;
-		}
-
 		mvchip->percpu_membase = devm_ioremap_resource(&pdev->dev,
 							       res);
 		if (IS_ERR(mvchip->percpu_membase))
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index 25000b0..f8e6af2 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -326,7 +326,8 @@
 
 	err = bgpio_init(&port->bgc, &pdev->dev, 4,
 			 port->base + PINCTRL_DIN(port),
-			 port->base + PINCTRL_DOUT(port), NULL,
+			 port->base + PINCTRL_DOUT(port) + MXS_SET,
+			 port->base + PINCTRL_DOUT(port) + MXS_CLR,
 			 port->base + PINCTRL_DOE(port), NULL, 0);
 	if (err)
 		goto out_irqdesc_free;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 2050891..d3f7d2d 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -69,6 +69,7 @@
 	bool is_mpuio;
 	bool dbck_flag;
 	bool loses_context;
+	bool context_valid;
 	int stride;
 	u32 width;
 	int context_loss_count;
@@ -1128,6 +1129,10 @@
 			bank->loses_context = true;
 	} else {
 		bank->loses_context = pdata->loses_context;
+
+		if (bank->loses_context)
+			bank->get_context_loss_count =
+				pdata->get_context_loss_count;
 	}
 
 
@@ -1178,9 +1183,6 @@
 	omap_gpio_chip_init(bank);
 	omap_gpio_show_rev(bank);
 
-	if (bank->loses_context)
-		bank->get_context_loss_count = pdata->get_context_loss_count;
-
 	pm_runtime_put(bank->dev);
 
 	list_add_tail(&bank->node, &omap_gpio_list);
@@ -1259,6 +1261,8 @@
 	return 0;
 }
 
+static void omap_gpio_init_context(struct gpio_bank *p);
+
 static int omap_gpio_runtime_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -1268,6 +1272,20 @@
 	int c;
 
 	spin_lock_irqsave(&bank->lock, flags);
+
+	/*
+	 * On the first resume during the probe, the context has not
+	 * been initialised and so initialise it now. Also initialise
+	 * the context loss count.
+	 */
+	if (bank->loses_context && !bank->context_valid) {
+		omap_gpio_init_context(bank);
+
+		if (bank->get_context_loss_count)
+			bank->context_loss_count =
+				bank->get_context_loss_count(bank->dev);
+	}
+
 	_gpio_dbck_enable(bank);
 
 	/*
@@ -1384,6 +1402,29 @@
 }
 
 #if defined(CONFIG_PM_RUNTIME)
+static void omap_gpio_init_context(struct gpio_bank *p)
+{
+	struct omap_gpio_reg_offs *regs = p->regs;
+	void __iomem *base = p->base;
+
+	p->context.ctrl		= __raw_readl(base + regs->ctrl);
+	p->context.oe		= __raw_readl(base + regs->direction);
+	p->context.wake_en	= __raw_readl(base + regs->wkup_en);
+	p->context.leveldetect0	= __raw_readl(base + regs->leveldetect0);
+	p->context.leveldetect1	= __raw_readl(base + regs->leveldetect1);
+	p->context.risingdetect	= __raw_readl(base + regs->risingdetect);
+	p->context.fallingdetect = __raw_readl(base + regs->fallingdetect);
+	p->context.irqenable1	= __raw_readl(base + regs->irqenable);
+	p->context.irqenable2	= __raw_readl(base + regs->irqenable2);
+
+	if (regs->set_dataout && p->regs->clr_dataout)
+		p->context.dataout = __raw_readl(base + regs->set_dataout);
+	else
+		p->context.dataout = __raw_readl(base + regs->dataout);
+
+	p->context_valid = true;
+}
+
 static void omap_gpio_restore_context(struct gpio_bank *bank)
 {
 	__raw_writel(bank->context.wake_en,
@@ -1421,6 +1462,7 @@
 #else
 #define omap_gpio_runtime_suspend NULL
 #define omap_gpio_runtime_resume NULL
+static void omap_gpio_init_context(struct gpio_bank *p) {}
 #endif
 
 static const struct dev_pm_ops gpio_pm_ops = {
diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c
index cdf5996..0fec097 100644
--- a/drivers/gpio/gpio-pch.c
+++ b/drivers/gpio/gpio-pch.c
@@ -424,8 +424,7 @@
 err_request_irq:
 	irq_free_descs(irq_base, gpio_pins[chip->ioh]);
 
-	ret = gpiochip_remove(&chip->gpio);
-	if (ret)
+	if (gpiochip_remove(&chip->gpio))
 		dev_err(&pdev->dev, "%s gpiochip_remove failed\n", __func__);
 
 err_gpiochip_add:
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 1e4de16..5af6571 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -272,10 +272,8 @@
 	return 0;
 
 err_sch_gpio_resume:
-	err = gpiochip_remove(&sch_gpio_core);
-	if (err)
-		dev_err(&pdev->dev, "%s failed, %d\n",
-				"gpiochip_remove()", err);
+	if (gpiochip_remove(&sch_gpio_core))
+		dev_err(&pdev->dev, "%s gpiochip_remove failed\n", __func__);
 
 err_sch_gpio_core:
 	release_region(res->start, resource_size(res));
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index da4cb5b..9a62672 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -463,11 +463,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Missing MEM resource\n");
-		return -ENODEV;
-	}
-
 	regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
diff --git a/drivers/gpio/gpio-viperboard.c b/drivers/gpio/gpio-viperboard.c
index 095ab14..5ac2919 100644
--- a/drivers/gpio/gpio-viperboard.c
+++ b/drivers/gpio/gpio-viperboard.c
@@ -446,7 +446,8 @@
 	return ret;
 
 err_gpiob:
-	ret = gpiochip_remove(&vb_gpio->gpioa);
+	if (gpiochip_remove(&vb_gpio->gpioa))
+		dev_err(&pdev->dev, "%s gpiochip_remove failed\n", __func__);
 
 err_gpioa:
 	return ret;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 3a8f7e6d..e7e9242 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -78,6 +78,10 @@
 {
 	struct drm_crtc *crtc;
 
+	/* Locking is currently fubar in the panic handler. */
+	if (oops_in_progress)
+		return;
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		WARN_ON(!mutex_is_locked(&crtc->mutex));
 
@@ -246,6 +250,7 @@
 	else
 		return "unknown";
 }
+EXPORT_SYMBOL(drm_get_connector_status_name);
 
 /**
  * drm_mode_object_get - allocate a new modeset identifier
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index e974f93..ed1334e 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -121,6 +121,7 @@
 		connector->helper_private;
 	int count = 0;
 	int mode_flags = 0;
+	bool verbose_prune = true;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id,
 			drm_get_connector_name(connector));
@@ -149,6 +150,7 @@
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, drm_get_connector_name(connector));
 		drm_mode_connector_update_edid_property(connector, NULL);
+		verbose_prune = false;
 		goto prune;
 	}
 
@@ -182,7 +184,7 @@
 	}
 
 prune:
-	drm_mode_prune_invalid(dev, &connector->modes, true);
+	drm_mode_prune_invalid(dev, &connector->modes, verbose_prune);
 
 	if (list_empty(&connector->modes))
 		return 0;
@@ -1005,12 +1007,20 @@
 			continue;
 
 		connector->status = connector->funcs->detect(connector, false);
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %d to %d\n",
-			      connector->base.id,
-			      drm_get_connector_name(connector),
-			      old_status, connector->status);
-		if (old_status != connector->status)
+		if (old_status != connector->status) {
+			const char *old, *new;
+
+			old = drm_get_connector_status_name(old_status);
+			new = drm_get_connector_status_name(connector->status);
+
+			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] "
+				      "status updated from %s to %s\n",
+				      connector->base.id,
+				      drm_get_connector_name(connector),
+				      old, new);
+
 			changed = true;
+		}
 	}
 
 	mutex_unlock(&dev->mode_config.mutex);
@@ -1083,10 +1093,11 @@
 		old_status = connector->status;
 
 		connector->status = connector->funcs->detect(connector, false);
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %d to %d\n",
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n",
 			      connector->base.id,
 			      drm_get_connector_name(connector),
-			      old_status, connector->status);
+			      drm_get_connector_status_name(old_status),
+			      drm_get_connector_status_name(connector->status));
 		if (old_status != connector->status)
 			changed = true;
 	}
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 8d4f290..9cc247f 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -57,7 +57,7 @@
 		       struct drm_file *file_priv);
 
 #define DRM_IOCTL_DEF(ioctl, _func, _flags) \
-	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0}
+	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
@@ -375,7 +375,7 @@
 {
 	struct drm_file *file_priv = filp->private_data;
 	struct drm_device *dev;
-	const struct drm_ioctl_desc *ioctl;
+	const struct drm_ioctl_desc *ioctl = NULL;
 	drm_ioctl_t *func;
 	unsigned int nr = DRM_IOCTL_NR(cmd);
 	int retcode = -EINVAL;
@@ -392,11 +392,6 @@
 	atomic_inc(&dev->counts[_DRM_STAT_IOCTLS]);
 	++file_priv->ioctl_count;
 
-	DRM_DEBUG("pid=%d, cmd=0x%02x, nr=0x%02x, dev 0x%lx, auth=%d\n",
-		  task_pid_nr(current), cmd, nr,
-		  (long)old_encode_dev(file_priv->minor->device),
-		  file_priv->authenticated);
-
 	if ((nr >= DRM_CORE_IOCTL_COUNT) &&
 	    ((nr < DRM_COMMAND_BASE) || (nr >= DRM_COMMAND_END)))
 		goto err_i1;
@@ -417,6 +412,11 @@
 	} else
 		goto err_i1;
 
+	DRM_DEBUG("pid=%d, dev=0x%lx, auth=%d, %s\n",
+		  task_pid_nr(current),
+		  (long)old_encode_dev(file_priv->minor->device),
+		  file_priv->authenticated, ioctl->name);
+
 	/* Do not trust userspace, use our own definition */
 	func = ioctl->func;
 	/* is there a local override? */
@@ -471,6 +471,12 @@
 	}
 
       err_i1:
+	if (!ioctl)
+		DRM_DEBUG("invalid iotcl: pid=%d, dev=0x%lx, auth=%d, cmd=0x%02x, nr=0x%02x\n",
+			  task_pid_nr(current),
+			  (long)old_encode_dev(file_priv->minor->device),
+			  file_priv->authenticated, cmd, nr);
+
 	if (kdata != stack_kdata)
 		kfree(kdata);
 	atomic_dec(&dev->ioctl_count);
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index 48c52f7..0cfb60f 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -54,16 +54,12 @@
 			 struct i2c_adapter *adap,
 			 const struct i2c_board_info *info)
 {
-	char modalias[sizeof(I2C_MODULE_PREFIX)
-		      + I2C_NAME_SIZE];
 	struct module *module = NULL;
 	struct i2c_client *client;
 	struct drm_i2c_encoder_driver *encoder_drv;
 	int err = 0;
 
-	snprintf(modalias, sizeof(modalias),
-		 "%s%s", I2C_MODULE_PREFIX, info->type);
-	request_module(modalias);
+	request_module("%s%s", I2C_MODULE_PREFIX, info->type);
 
 	client = i2c_new_device(adap, info);
 	if (!client) {
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index db1e2d6..07cf99c 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -755,33 +755,35 @@
 EXPORT_SYMBOL(drm_mm_debug_table);
 
 #if defined(CONFIG_DEBUG_FS)
+static unsigned long drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry)
+{
+	unsigned long hole_start, hole_end, hole_size;
+
+	if (entry->hole_follows) {
+		hole_start = drm_mm_hole_node_start(entry);
+		hole_end = drm_mm_hole_node_end(entry);
+		hole_size = hole_end - hole_start;
+		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
+				hole_start, hole_end, hole_size);
+		return hole_size;
+	}
+
+	return 0;
+}
+
 int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
 {
 	struct drm_mm_node *entry;
 	unsigned long total_used = 0, total_free = 0, total = 0;
-	unsigned long hole_start, hole_end, hole_size;
 
-	hole_start = drm_mm_hole_node_start(&mm->head_node);
-	hole_end = drm_mm_hole_node_end(&mm->head_node);
-	hole_size = hole_end - hole_start;
-	if (hole_size)
-		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
-				hole_start, hole_end, hole_size);
-	total_free += hole_size;
+	total_free += drm_mm_dump_hole(m, &mm->head_node);
 
 	drm_mm_for_each_node(entry, mm) {
 		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: used\n",
 				entry->start, entry->start + entry->size,
 				entry->size);
 		total_used += entry->size;
-		if (entry->hole_follows) {
-			hole_start = drm_mm_hole_node_start(entry);
-			hole_end = drm_mm_hole_node_end(entry);
-			hole_size = hole_end - hole_start;
-			seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
-					hole_start, hole_end, hole_size);
-			total_free += hole_size;
-		}
+		total_free += drm_mm_dump_hole(m, entry);
 	}
 	total = total_free + total_used;
 
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index faa79df..a371ff8 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1143,6 +1143,7 @@
 				was_digit = false;
 			} else
 				goto done;
+			break;
 		case '0' ... '9':
 			was_digit = true;
 			break;
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index bbfc384..6652597 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -2005,11 +2005,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		DRM_ERROR("failed to find registers\n");
-		return -ENOENT;
-	}
-
 	hdata->regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(hdata->regs))
 		return PTR_ERR(hdata->regs);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6be940e..6165535 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1045,6 +1045,8 @@
 	if (timeout) {
 		struct timespec sleep_time = timespec_sub(now, before);
 		*timeout = timespec_sub(*timeout, sleep_time);
+		if (!timespec_valid(timeout)) /* i.e. negative time remains */
+			set_normalized_timespec(timeout, 0, 0);
 	}
 
 	switch (end) {
@@ -1053,8 +1055,6 @@
 	case -ERESTARTSYS: /* Signal */
 		return (int)end;
 	case 0: /* Timeout */
-		if (timeout)
-			set_normalized_timespec(timeout, 0, 0);
 		return -ETIME;
 	default: /* Completed */
 		WARN_ON(end < 0); /* We're not aware of other errors */
@@ -2377,10 +2377,8 @@
 	mutex_unlock(&dev->struct_mutex);
 
 	ret = __wait_seqno(ring, seqno, reset_counter, true, timeout);
-	if (timeout) {
-		WARN_ON(!timespec_valid(timeout));
+	if (timeout)
 		args->timeout_ns = timespec_to_ns(timeout);
-	}
 	return ret;
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index dca614d..bdb0d77 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -709,15 +709,6 @@
 	return snb_gmch_ctl << 25; /* 32 MB units */
 }
 
-static inline size_t gen7_get_stolen_size(u16 snb_gmch_ctl)
-{
-	static const int stolen_decoder[] = {
-		0, 0, 0, 0, 0, 32, 48, 64, 128, 256, 96, 160, 224, 352};
-	snb_gmch_ctl >>= IVB_GMCH_GMS_SHIFT;
-	snb_gmch_ctl &= IVB_GMCH_GMS_MASK;
-	return stolen_decoder[snb_gmch_ctl] << 20;
-}
-
 static int gen6_gmch_probe(struct drm_device *dev,
 			   size_t *gtt_total,
 			   size_t *stolen,
@@ -747,11 +738,7 @@
 	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
 
-	if (IS_GEN7(dev) && !IS_VALLEYVIEW(dev))
-		*stolen = gen7_get_stolen_size(snb_gmch_ctl);
-	else
-		*stolen = gen6_get_stolen_size(snb_gmch_ctl);
-
+	*stolen = gen6_get_stolen_size(snb_gmch_ctl);
 	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
 
 	/* For Modern GENs the PTEs and register space are split in the BAR */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 83f9c26..2d6b62e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -46,8 +46,6 @@
 #define    SNB_GMCH_GGMS_MASK	0x3
 #define    SNB_GMCH_GMS_SHIFT   3 /* Graphics Mode Select */
 #define    SNB_GMCH_GMS_MASK    0x1f
-#define    IVB_GMCH_GMS_SHIFT   4
-#define    IVB_GMCH_GMS_MASK    0xf
 
 
 /* PCI config space */
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 26a0a57..fb961bb 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1265,6 +1265,8 @@
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
+		if (port != PORT_A)
+			intel_dp_stop_link_train(intel_dp);
 	}
 }
 
@@ -1326,6 +1328,9 @@
 	} else if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
+		if (port == PORT_A)
+			intel_dp_stop_link_train(intel_dp);
+
 		ironlake_edp_backlight_on(intel_dp);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index fb2fbc1..3d704b7 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -702,6 +702,9 @@
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
 	 * bpc in between. */
 	bpp = min_t(int, 8*3, pipe_config->pipe_bpp);
+	if (is_edp(intel_dp) && dev_priv->edp.bpp)
+		bpp = min_t(int, bpp, dev_priv->edp.bpp);
+
 	for (; bpp >= 6*3; bpp -= 2*3) {
 		mode_rate = intel_dp_link_required(target_clock, bpp);
 
@@ -739,6 +742,7 @@
 	intel_dp->link_bw = bws[clock];
 	intel_dp->lane_count = lane_count;
 	adjusted_mode->clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
+	pipe_config->pipe_bpp = bpp;
 	pipe_config->pixel_target_clock = target_clock;
 
 	DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n",
@@ -751,20 +755,6 @@
 			       target_clock, adjusted_mode->clock,
 			       &pipe_config->dp_m_n);
 
-	/*
-	 * XXX: We have a strange regression where using the vbt edp bpp value
-	 * for the link bw computation results in black screens, the panel only
-	 * works when we do the computation at the usual 24bpp (but still
-	 * requires us to use 18bpp). Until that's fully debugged, stay
-	 * bug-for-bug compatible with the old code.
-	 */
-	if (is_edp(intel_dp) && dev_priv->edp.bpp) {
-		DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n",
-			      bpp, dev_priv->edp.bpp);
-		bpp = min_t(int, bpp, dev_priv->edp.bpp);
-	}
-	pipe_config->pipe_bpp = bpp;
-
 	return true;
 }
 
@@ -1389,6 +1379,7 @@
 	ironlake_edp_panel_on(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, true);
 	intel_dp_complete_link_train(intel_dp);
+	intel_dp_stop_link_train(intel_dp);
 	ironlake_edp_backlight_on(intel_dp);
 }
 
@@ -1711,10 +1702,9 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum port port = intel_dig_port->port;
 	int ret;
-	uint32_t temp;
 
 	if (HAS_DDI(dev)) {
-		temp = I915_READ(DP_TP_CTL(port));
+		uint32_t temp = I915_READ(DP_TP_CTL(port));
 
 		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
 			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
@@ -1724,18 +1714,6 @@
 		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
 		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
 		case DP_TRAINING_PATTERN_DISABLE:
-
-			if (port != PORT_A) {
-				temp |= DP_TP_CTL_LINK_TRAIN_IDLE;
-				I915_WRITE(DP_TP_CTL(port), temp);
-
-				if (wait_for((I915_READ(DP_TP_STATUS(port)) &
-					      DP_TP_STATUS_IDLE_DONE), 1))
-					DRM_ERROR("Timed out waiting for DP idle patterns\n");
-
-				temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-			}
-
 			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
 
 			break;
@@ -1811,6 +1789,37 @@
 	return true;
 }
 
+static void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum port port = intel_dig_port->port;
+	uint32_t val;
+
+	if (!HAS_DDI(dev))
+		return;
+
+	val = I915_READ(DP_TP_CTL(port));
+	val &= ~DP_TP_CTL_LINK_TRAIN_MASK;
+	val |= DP_TP_CTL_LINK_TRAIN_IDLE;
+	I915_WRITE(DP_TP_CTL(port), val);
+
+	/*
+	 * On PORT_A we can have only eDP in SST mode. There the only reason
+	 * we need to set idle transmission mode is to work around a HW issue
+	 * where we enable the pipe while not in idle link-training mode.
+	 * In this case there is requirement to wait for a minimum number of
+	 * idle patterns to be sent.
+	 */
+	if (port == PORT_A)
+		return;
+
+	if (wait_for((I915_READ(DP_TP_STATUS(port)) & DP_TP_STATUS_IDLE_DONE),
+		     1))
+		DRM_ERROR("Timed out waiting for DP idle patterns\n");
+}
+
 /* Enable corresponding port and start training pattern 1 */
 void
 intel_dp_start_link_train(struct intel_dp *intel_dp)
@@ -1953,10 +1962,19 @@
 		++tries;
 	}
 
+	intel_dp_set_idle_link_train(intel_dp);
+
+	intel_dp->DP = DP;
+
 	if (channel_eq)
 		DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
 
-	intel_dp_set_link_train(intel_dp, DP, DP_TRAINING_PATTERN_DISABLE);
+}
+
+void intel_dp_stop_link_train(struct intel_dp *intel_dp)
+{
+	intel_dp_set_link_train(intel_dp, intel_dp->DP,
+				DP_TRAINING_PATTERN_DISABLE);
 }
 
 static void
@@ -2164,6 +2182,7 @@
 			      drm_get_encoder_name(&intel_encoder->base));
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
+		intel_dp_stop_link_train(intel_dp);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b5b6d19..624a9e6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -499,6 +499,7 @@
 extern void intel_dp_init_link_config(struct intel_dp *intel_dp);
 extern void intel_dp_start_link_train(struct intel_dp *intel_dp);
 extern void intel_dp_complete_link_train(struct intel_dp *intel_dp);
+extern void intel_dp_stop_link_train(struct intel_dp *intel_dp);
 extern void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 extern void intel_dp_encoder_destroy(struct drm_encoder *encoder);
 extern void intel_dp_check_link_status(struct intel_dp *intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 0e19e57..6b7c3ca 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -262,10 +262,22 @@
 void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	if (!dev_priv->fbdev)
+	struct intel_fbdev *ifbdev = dev_priv->fbdev;
+	struct fb_info *info;
+
+	if (!ifbdev)
 		return;
 
-	fb_set_suspend(dev_priv->fbdev->helper.fbdev, state);
+	info = ifbdev->helper.fbdev;
+
+	/* On resume from hibernation: If the object is shmemfs backed, it has
+	 * been restored from swap. If the object is stolen however, it will be
+	 * full of whatever garbage was left in there.
+	 */
+	if (!state && ifbdev->ifb.obj->stolen)
+		memset_io(info->screen_base, 0, info->screen_size);
+
+	fb_set_suspend(info, state);
 }
 
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index de3b0dc..aa01128 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1301,17 +1301,17 @@
 
 	vlv_update_drain_latency(dev);
 
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &valleyview_wm_info, latency_ns,
 			    &valleyview_cursor_wm_info, latency_ns,
 			    &planea_wm, &cursora_wm))
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &valleyview_wm_info, latency_ns,
 			    &valleyview_cursor_wm_info, latency_ns,
 			    &planeb_wm, &cursorb_wm))
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
@@ -1357,17 +1357,17 @@
 	int plane_sr, cursor_sr;
 	unsigned int enabled = 0;
 
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &g4x_wm_info, latency_ns,
 			    &g4x_cursor_wm_info, latency_ns,
 			    &planea_wm, &cursora_wm))
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &g4x_wm_info, latency_ns,
 			    &g4x_cursor_wm_info, latency_ns,
 			    &planeb_wm, &cursorb_wm))
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
@@ -1716,7 +1716,7 @@
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &ironlake_display_wm_info,
 			    ILK_LP0_PLANE_LATENCY,
 			    &ironlake_cursor_wm_info,
@@ -1727,10 +1727,10 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &ironlake_display_wm_info,
 			    ILK_LP0_PLANE_LATENCY,
 			    &ironlake_cursor_wm_info,
@@ -1741,7 +1741,7 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
 	/*
@@ -1801,7 +1801,7 @@
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1812,10 +1812,10 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1826,7 +1826,7 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
 	/*
@@ -1904,7 +1904,7 @@
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1915,10 +1915,10 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1929,10 +1929,10 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
-	if (g4x_compute_wm0(dev, 2,
+	if (g4x_compute_wm0(dev, PIPE_C,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1943,7 +1943,7 @@
 		DRM_DEBUG_KMS("FIFO watermarks For pipe C -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 3;
+		enabled |= 1 << PIPE_C;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index f988965..77b8a45 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -46,29 +46,26 @@
 
 static inline void mga_wait_vsync(struct mga_device *mdev)
 {
-	unsigned int count = 0;
+	unsigned long timeout = jiffies + HZ/10;
 	unsigned int status = 0;
 
 	do {
 		status = RREG32(MGAREG_Status);
-		count++;
-	} while ((status & 0x08) && (count < 250000));
-	count = 0;
+	} while ((status & 0x08) && time_before(jiffies, timeout));
+	timeout = jiffies + HZ/10;
 	status = 0;
 	do {
 		status = RREG32(MGAREG_Status);
-		count++;
-	} while (!(status & 0x08) && (count < 250000));
+	} while (!(status & 0x08) && time_before(jiffies, timeout));
 }
 
 static inline void mga_wait_busy(struct mga_device *mdev)
 {
-	unsigned int count = 0;
+	unsigned long timeout = jiffies + HZ;
 	unsigned int status = 0;
 	do {
 		status = RREG8(MGAREG_Status + 2);
-		count++;
-	} while ((status & 0x01) && (count < 500000));
+	} while ((status & 0x01) && time_before(jiffies, timeout));
 }
 
 /*
@@ -189,12 +186,12 @@
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_REMHEADCTL_CLKDIS;
-		WREG_DAC(MGA1064_REMHEADCTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		/* select PLL Set C */
 		tmp = RREG8(MGAREG_MEM_MISC_READ);
@@ -204,7 +201,7 @@
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN | 0x80;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(500);
 
@@ -212,7 +209,7 @@
 		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~0x04;
-		WREG_DAC(MGA1064_VREF_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(50);
 
@@ -236,13 +233,13 @@
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_REMHEADCTL_CLKSL_MSK;
 		tmp |= MGA1064_REMHEADCTL_CLKSL_PLL;
-		WREG_DAC(MGA1064_REMHEADCTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		/* reset dotclock rate bit */
 		WREG8(MGAREG_SEQ_INDEX, 1);
@@ -253,7 +250,7 @@
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		vcount = RREG8(MGAREG_VCOUNT);
 
@@ -318,7 +315,7 @@
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= 0x3 << 2;
@@ -326,12 +323,12 @@
 
 	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
 	tmp = RREG8(DAC_DATA);
-	WREG_DAC(MGA1064_PIX_PLL_STAT, tmp & ~0x40);
+	WREG8(DAC_DATA, tmp & ~0x40);
 
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG_DAC(MGA1064_EV_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_EV_PIX_PLLC_N, n);
@@ -342,7 +339,7 @@
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	udelay(500);
 
@@ -350,11 +347,11 @@
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 	tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
 	tmp = RREG8(DAC_DATA);
-	WREG_DAC(MGA1064_PIX_PLL_STAT, tmp | 0x40);
+	WREG8(DAC_DATA, tmp | 0x40);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= (0x3 << 2);
@@ -363,7 +360,7 @@
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	return 0;
 }
@@ -416,7 +413,7 @@
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		tmp = RREG8(MGAREG_MEM_MISC_READ);
 		tmp |= 0x3 << 2;
@@ -425,7 +422,7 @@
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(500);
 
@@ -439,13 +436,13 @@
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		vcount = RREG8(MGAREG_VCOUNT);
 
@@ -515,12 +512,12 @@
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_REMHEADCTL_CLKDIS;
-	WREG_DAC(MGA1064_REMHEADCTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= (0x3<<2) | 0xc0;
@@ -530,7 +527,7 @@
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	udelay(500);
 
@@ -657,12 +654,26 @@
 	WREG_DAC(MGA1064_GEN_IO_DATA, tmp);
 }
 
-
+/*
+   This is how the framebuffer base address is stored in g200 cards:
+   * Assume @offset is the gpu_addr variable of the framebuffer object
+   * Then addr is the number of _pixels_ (not bytes) from the start of
+     VRAM to the first pixel we want to display. (divided by 2 for 32bit
+     framebuffers)
+   * addr is stored in the CRTCEXT0, CRTCC and CRTCD registers
+   addr<20> -> CRTCEXT0<6>
+   addr<19-16> -> CRTCEXT0<3-0>
+   addr<15-8> -> CRTCC<7-0>
+   addr<7-0> -> CRTCD<7-0>
+   CRTCEXT0 has to be programmed last to trigger an update and make the
+   new addr variable take effect.
+ */
 void mga_set_start_address(struct drm_crtc *crtc, unsigned offset)
 {
 	struct mga_device *mdev = crtc->dev->dev_private;
 	u32 addr;
 	int count;
+	u8 crtcext0;
 
 	while (RREG8(0x1fda) & 0x08);
 	while (!(RREG8(0x1fda) & 0x08));
@@ -670,10 +681,17 @@
 	count = RREG8(MGAREG_VCOUNT) + 2;
 	while (RREG8(MGAREG_VCOUNT) < count);
 
-	addr = offset >> 2;
+	WREG8(MGAREG_CRTCEXT_INDEX, 0);
+	crtcext0 = RREG8(MGAREG_CRTCEXT_DATA);
+	crtcext0 &= 0xB0;
+	addr = offset / 8;
+	/* Can't store addresses any higher than that...
+	   but we also don't have more than 16MB of memory, so it should be fine. */
+	WARN_ON(addr > 0x1fffff);
+	crtcext0 |= (!!(addr & (1<<20)))<<6;
 	WREG_CRT(0x0d, (u8)(addr & 0xff));
 	WREG_CRT(0x0c, (u8)(addr >> 8) & 0xff);
-	WREG_CRT(0xaf, (u8)(addr >> 16) & 0xf);
+	WREG_ECRT(0x0, ((u8)(addr >> 16) & 0xf) | crtcext0);
 }
 
 
@@ -829,11 +847,7 @@
 
 
 	for (i = 0; i < sizeof(dacvalue); i++) {
-		if ((i <= 0x03) ||
-		    (i == 0x07) ||
-		    (i == 0x0b) ||
-		    (i == 0x0f) ||
-		    ((i >= 0x13) && (i <= 0x17)) ||
+		if ((i <= 0x17) ||
 		    (i == 0x1b) ||
 		    (i == 0x1c) ||
 		    ((i >= 0x1f) && (i <= 0x29)) ||
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index 955af12..a36e64e 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -138,7 +138,6 @@
 		device->oclass[NVDEV_ENGINE_BSP    ] = &nvc0_bsp_oclass;
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
 		device->oclass[NVDEV_ENGINE_COPY0  ] = &nvc0_copy0_oclass;
-		device->oclass[NVDEV_ENGINE_COPY1  ] = &nvc0_copy1_oclass;
 		device->oclass[NVDEV_ENGINE_DISP   ] = &nva3_disp_oclass;
 		break;
 	case 0xce:
@@ -225,7 +224,6 @@
 		device->oclass[NVDEV_ENGINE_BSP    ] = &nvc0_bsp_oclass;
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
 		device->oclass[NVDEV_ENGINE_COPY0  ] = &nvc0_copy0_oclass;
-		device->oclass[NVDEV_ENGINE_COPY1  ] = &nvc0_copy1_oclass;
 		device->oclass[NVDEV_ENGINE_DISP   ] = &nva3_disp_oclass;
 		break;
 	case 0xc8:
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
index ddaeb55..89bf459 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
@@ -47,6 +47,7 @@
 	struct nouveau_gpuobj *cur;
 	int i, p;
 
+	mutex_lock(&nv_subdev(priv)->mutex);
 	cur = priv->playlist[priv->cur_playlist];
 	priv->cur_playlist = !priv->cur_playlist;
 
@@ -60,6 +61,7 @@
 	nv_wr32(priv, 0x0032f4, cur->addr >> 12);
 	nv_wr32(priv, 0x0032ec, p);
 	nv_wr32(priv, 0x002500, 0x00000101);
+	mutex_unlock(&nv_subdev(priv)->mutex);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
index 4d4a6b9..46dfa68 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
@@ -71,6 +71,7 @@
 	struct nouveau_gpuobj *cur;
 	int i, p;
 
+	mutex_lock(&nv_subdev(priv)->mutex);
 	cur = priv->playlist[priv->cur_playlist];
 	priv->cur_playlist = !priv->cur_playlist;
 
@@ -87,6 +88,7 @@
 	nv_wr32(priv, 0x002274, 0x01f00000 | (p >> 3));
 	if (!nv_wait(priv, 0x00227c, 0x00100000, 0x00000000))
 		nv_error(priv, "playlist update failed\n");
+	mutex_unlock(&nv_subdev(priv)->mutex);
 }
 
 static int
@@ -248,9 +250,17 @@
 	struct nvc0_fifo_priv *priv = (void *)object->engine;
 	struct nvc0_fifo_chan *chan = (void *)object;
 	u32 chid = chan->base.chid;
+	u32 mask, engine;
 
 	nv_mask(priv, 0x003004 + (chid * 8), 0x00000001, 0x00000000);
 	nvc0_fifo_playlist_update(priv);
+	mask = nv_rd32(priv, 0x0025a4);
+	for (engine = 0; mask && engine < 16; engine++) {
+		if (!(mask & (1 << engine)))
+			continue;
+		nv_mask(priv, 0x0025a8 + (engine * 4), 0x00000000, 0x00000000);
+		mask &= ~(1 << engine);
+	}
 	nv_wr32(priv, 0x003000 + (chid * 8), 0x00000000);
 
 	return nouveau_fifo_channel_fini(&chan->base, suspend);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
index 9151919..56192a7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
@@ -94,11 +94,13 @@
 	u32 match = (engine << 16) | 0x00000001;
 	int i, p;
 
+	mutex_lock(&nv_subdev(priv)->mutex);
 	cur = engn->playlist[engn->cur_playlist];
 	if (unlikely(cur == NULL)) {
 		int ret = nouveau_gpuobj_new(nv_object(priv), NULL,
 					     0x8000, 0x1000, 0, &cur);
 		if (ret) {
+			mutex_unlock(&nv_subdev(priv)->mutex);
 			nv_error(priv, "playlist alloc failed\n");
 			return;
 		}
@@ -122,6 +124,7 @@
 	nv_wr32(priv, 0x002274, (engine << 20) | (p >> 3));
 	if (!nv_wait(priv, 0x002284 + (engine * 4), 0x00100000, 0x00000000))
 		nv_error(priv, "playlist %d update timeout\n", engine);
+	mutex_unlock(&nv_subdev(priv)->mutex);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index c300b5e..c434d39 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -1940,8 +1940,8 @@
 	trace("ZM_MASK_ADD\tR[0x%06x] &= 0x%08x += 0x%08x\n", addr, mask, add);
 	init->offset += 13;
 
-	data  =  init_rd32(init, addr) & mask;
-	data |= ((data + add) & ~mask);
+	data =  init_rd32(init, addr);
+	data = (data & mask) | ((data + add) & ~mask);
 	init_wr32(init, addr, data);
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
index e4940fb..fb794e9 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltcg/nvc0.c
@@ -29,7 +29,6 @@
 struct nvc0_ltcg_priv {
 	struct nouveau_ltcg base;
 	u32 part_nr;
-	u32 part_mask;
 	u32 subp_nr;
 	struct nouveau_mm tags;
 	u32 num_tags;
@@ -105,8 +104,6 @@
 
 	/* wait until it's finished with clearing */
 	for (p = 0; p < priv->part_nr; ++p) {
-		if (!(priv->part_mask & (1 << p)))
-			continue;
 		for (i = 0; i < priv->subp_nr; ++i)
 			nv_wait(priv, 0x1410c8 + p * 0x2000 + i * 0x400, ~0, 0);
 	}
@@ -121,6 +118,8 @@
 	int ret;
 
 	nv_wr32(priv, 0x17e8d8, priv->part_nr);
+	if (nv_device(pfb)->card_type >= NV_E0)
+		nv_wr32(priv, 0x17e000, priv->part_nr);
 
 	/* tags for 1/4 of VRAM should be enough (8192/4 per GiB of VRAM) */
 	priv->num_tags = (pfb->ram.size >> 17) / 4;
@@ -167,16 +166,20 @@
 {
 	struct nvc0_ltcg_priv *priv;
 	struct nouveau_fb *pfb = nouveau_fb(parent);
-	int ret;
+	u32 parts, mask;
+	int ret, i;
 
 	ret = nouveau_ltcg_create(parent, engine, oclass, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	priv->part_nr = nv_rd32(priv, 0x022438);
-	priv->part_mask = nv_rd32(priv, 0x022554);
-
+	parts = nv_rd32(priv, 0x022438);
+	mask = nv_rd32(priv, 0x022554);
+	for (i = 0; i < parts; i++) {
+		if (!(mask & (1 << i)))
+			priv->part_nr++;
+	}
 	priv->subp_nr = nv_rd32(priv, 0x17e8dc) >> 28;
 
 	nv_mask(priv, 0x17e820, 0x00100000, 0x00000000); /* INTR_EN &= ~0x10 */
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 46c152f..383f4e6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -453,18 +453,32 @@
 	NV_INFO(drm, "evicting buffers...\n");
 	ttm_bo_evict_mm(&drm->ttm.bdev, TTM_PL_VRAM);
 
+	NV_INFO(drm, "waiting for kernel channels to go idle...\n");
+	if (drm->cechan) {
+		ret = nouveau_channel_idle(drm->cechan);
+		if (ret)
+			return ret;
+	}
+
+	if (drm->channel) {
+		ret = nouveau_channel_idle(drm->channel);
+		if (ret)
+			return ret;
+	}
+
+	NV_INFO(drm, "suspending client object trees...\n");
 	if (drm->fence && nouveau_fence(drm)->suspend) {
 		if (!nouveau_fence(drm)->suspend(drm))
 			return -ENOMEM;
 	}
 
-	NV_INFO(drm, "suspending client object trees...\n");
 	list_for_each_entry(cli, &drm->clients, head) {
 		ret = nouveau_client_fini(&cli->base, true);
 		if (ret)
 			goto fail_client;
 	}
 
+	NV_INFO(drm, "suspending kernel object tree...\n");
 	ret = nouveau_client_fini(&drm->client.base, true);
 	if (ret)
 		goto fail_client;
@@ -514,17 +528,18 @@
 
 	nouveau_agp_reset(drm);
 
-	NV_INFO(drm, "resuming client object trees...\n");
+	NV_INFO(drm, "resuming kernel object tree...\n");
 	nouveau_client_init(&drm->client.base);
 	nouveau_agp_init(drm);
 
+	NV_INFO(drm, "resuming client object trees...\n");
+	if (drm->fence && nouveau_fence(drm)->resume)
+		nouveau_fence(drm)->resume(drm);
+
 	list_for_each_entry(cli, &drm->clients, head) {
 		nouveau_client_init(&cli->base);
 	}
 
-	if (drm->fence && nouveau_fence(drm)->resume)
-		nouveau_fence(drm)->resume(drm);
-
 	nouveau_run_vbios_init(dev);
 	nouveau_pm_resume(dev);
 
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 08b0823..f867714 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -277,7 +277,7 @@
 	return 0;
 }
 
-static int wait_for_io_cmd_user(struct qxl_device *qdev, uint8_t val, long port)
+static int wait_for_io_cmd_user(struct qxl_device *qdev, uint8_t val, long port, bool intr)
 {
 	int irq_num;
 	long addr = qdev->io_base + port;
@@ -285,20 +285,29 @@
 
 	mutex_lock(&qdev->async_io_mutex);
 	irq_num = atomic_read(&qdev->irq_received_io_cmd);
-
-
 	if (qdev->last_sent_io_cmd > irq_num) {
-		ret = wait_event_interruptible(qdev->io_cmd_event,
-					       atomic_read(&qdev->irq_received_io_cmd) > irq_num);
-		if (ret)
+		if (intr)
+			ret = wait_event_interruptible_timeout(qdev->io_cmd_event,
+							       atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+		else
+			ret = wait_event_timeout(qdev->io_cmd_event,
+						 atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+		/* 0 is timeout, just bail the "hw" has gone away */
+		if (ret <= 0)
 			goto out;
 		irq_num = atomic_read(&qdev->irq_received_io_cmd);
 	}
 	outb(val, addr);
 	qdev->last_sent_io_cmd = irq_num + 1;
-	ret = wait_event_interruptible(qdev->io_cmd_event,
-				       atomic_read(&qdev->irq_received_io_cmd) > irq_num);
+	if (intr)
+		ret = wait_event_interruptible_timeout(qdev->io_cmd_event,
+						       atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+	else
+		ret = wait_event_timeout(qdev->io_cmd_event,
+					 atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
 out:
+	if (ret > 0)
+		ret = 0;
 	mutex_unlock(&qdev->async_io_mutex);
 	return ret;
 }
@@ -308,7 +317,7 @@
 	int ret;
 
 restart:
-	ret = wait_for_io_cmd_user(qdev, val, port);
+	ret = wait_for_io_cmd_user(qdev, val, port, false);
 	if (ret == -ERESTARTSYS)
 		goto restart;
 }
@@ -340,7 +349,7 @@
 	mutex_lock(&qdev->update_area_mutex);
 	qdev->ram_header->update_area = *area;
 	qdev->ram_header->update_surface = surface_id;
-	ret = wait_for_io_cmd_user(qdev, 0, QXL_IO_UPDATE_AREA_ASYNC);
+	ret = wait_for_io_cmd_user(qdev, 0, QXL_IO_UPDATE_AREA_ASYNC, true);
 	mutex_unlock(&qdev->update_area_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index fcfd443..823d29e 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -428,10 +428,10 @@
 	int inc = 1;
 
 	qobj = gem_to_qxl_bo(qxl_fb->obj);
-	if (qxl_fb != qdev->active_user_framebuffer) {
-		DRM_INFO("%s: qxl_fb 0x%p != qdev->active_user_framebuffer 0x%p\n",
-			__func__, qxl_fb, qdev->active_user_framebuffer);
-	}
+	/* if we aren't primary surface ignore this */
+	if (!qobj->is_primary)
+		return 0;
+
 	if (!num_clips) {
 		num_clips = 1;
 		clips = &norect;
@@ -604,7 +604,6 @@
 					       mode->hdisplay,
 					       mode->vdisplay);
 	}
-	qdev->mode_set = true;
 	return 0;
 }
 
@@ -893,7 +892,6 @@
 {
 	struct drm_gem_object *obj;
 	struct qxl_framebuffer *qxl_fb;
-	struct qxl_device *qdev = dev->dev_private;
 	int ret;
 
 	obj = drm_gem_object_lookup(dev, file_priv, mode_cmd->handles[0]);
@@ -909,13 +907,6 @@
 		return NULL;
 	}
 
-	if (qdev->active_user_framebuffer) {
-		DRM_INFO("%s: active_user_framebuffer %p -> %p\n",
-			 __func__,
-			 qdev->active_user_framebuffer, qxl_fb);
-	}
-	qdev->active_user_framebuffer = qxl_fb;
-
 	return &qxl_fb->base;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 52b582c..43d06ab 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -255,12 +255,6 @@
 	struct qxl_gem		gem;
 	struct qxl_mode_info mode_info;
 
-	/*
-	 * last created framebuffer with fb_create
-	 * only used by debugfs dumbppm
-	 */
-	struct qxl_framebuffer *active_user_framebuffer;
-
 	struct fb_info			*fbdev_info;
 	struct qxl_framebuffer	*fbdev_qfb;
 	void *ram_physical;
@@ -270,7 +264,6 @@
 	struct qxl_ring *cursor_ring;
 
 	struct qxl_ram_header *ram_header;
-	bool mode_set;
 
 	bool primary_created;
 
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 04b64f9..6db7370 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -294,6 +294,7 @@
 		goto out;
 
 	if (!qobj->pin_count) {
+		qxl_ttm_placement_from_domain(qobj, qobj->type);
 		ret = ttm_bo_validate(&qobj->tbo, &qobj->placement,
 				      true, false);
 		if (unlikely(ret))
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 6d6fdb3..d5df8fd 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1811,12 +1811,9 @@
 
 static void atombios_crtc_prepare(struct drm_crtc *crtc)
 {
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
 
-	radeon_crtc->in_mode_set = true;
-
 	/* disable crtc pair power gating before programming */
 	if (ASIC_IS_DCE6(rdev))
 		atombios_powergate_crtc(crtc, ATOM_DISABLE);
@@ -1827,11 +1824,8 @@
 
 static void atombios_crtc_commit(struct drm_crtc *crtc)
 {
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 	atombios_lock_crtc(crtc, ATOM_DISABLE);
-	radeon_crtc->in_mode_set = false;
 }
 
 static void atombios_crtc_disable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 105bafb..8f9e2d3 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2343,11 +2343,13 @@
 	u32 crtc_enabled, tmp, frame_count, blackout;
 	int i, j;
 
-	save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
-	save->vga_hdp_control = RREG32(VGA_HDP_CONTROL);
+	if (!ASIC_IS_NODCE(rdev)) {
+		save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
+		save->vga_hdp_control = RREG32(VGA_HDP_CONTROL);
 
-	/* disable VGA render */
-	WREG32(VGA_RENDER_CONTROL, 0);
+		/* disable VGA render */
+		WREG32(VGA_RENDER_CONTROL, 0);
+	}
 	/* blank the display controllers */
 	for (i = 0; i < rdev->num_crtc; i++) {
 		crtc_enabled = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]) & EVERGREEN_CRTC_MASTER_EN;
@@ -2438,8 +2440,11 @@
 		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + crtc_offsets[i],
 		       (u32)rdev->mc.vram_start);
 	}
-	WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS_HIGH, upper_32_bits(rdev->mc.vram_start));
-	WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS, (u32)rdev->mc.vram_start);
+
+	if (!ASIC_IS_NODCE(rdev)) {
+		WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS_HIGH, upper_32_bits(rdev->mc.vram_start));
+		WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS, (u32)rdev->mc.vram_start);
+	}
 
 	/* unlock regs and wait for update */
 	for (i = 0; i < rdev->num_crtc; i++) {
@@ -2499,10 +2504,12 @@
 			}
 		}
 	}
-	/* Unlock vga access */
-	WREG32(VGA_HDP_CONTROL, save->vga_hdp_control);
-	mdelay(1);
-	WREG32(VGA_RENDER_CONTROL, save->vga_render_control);
+	if (!ASIC_IS_NODCE(rdev)) {
+		/* Unlock vga access */
+		WREG32(VGA_HDP_CONTROL, save->vga_hdp_control);
+		mdelay(1);
+		WREG32(VGA_RENDER_CONTROL, save->vga_render_control);
+	}
 }
 
 void evergreen_mc_program(struct radeon_device *rdev)
@@ -3405,8 +3412,8 @@
 		rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
 	} else {
 		/* size in MB on evergreen/cayman/tn */
-		rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
-		rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
+		rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+		rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	}
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	r700_vram_gtt_location(rdev, &rdev->mc);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index b4ab8ce..ed7c8a7 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -154,19 +154,18 @@
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
-	u32 base_rate = 48000;
+	u32 base_rate = 24000;
 
 	if (!dig || !dig->afmt)
 		return;
 
-	/* XXX: properly calculate this */
 	/* XXX two dtos; generally use dto0 for hdmi */
 	/* Express [24MHz / target pixel clock] as an exact rational
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	WREG32(DCCG_AUDIO_DTO0_PHASE, (base_rate*50) & 0xffffff);
-	WREG32(DCCG_AUDIO_DTO0_MODULE, (clock*100) & 0xffffff);
+	WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+	WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
 	WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id));
 }
 
diff --git a/drivers/gpu/drm/radeon/r300_cmdbuf.c b/drivers/gpu/drm/radeon/r300_cmdbuf.c
index 865e2c9..60170ea 100644
--- a/drivers/gpu/drm/radeon/r300_cmdbuf.c
+++ b/drivers/gpu/drm/radeon/r300_cmdbuf.c
@@ -75,7 +75,7 @@
 		OUT_RING(CP_PACKET0(R300_RE_CLIPRECT_TL_0, nr * 2 - 1));
 
 		for (i = 0; i < nr; ++i) {
-			if (DRM_COPY_FROM_USER_UNCHECKED
+			if (DRM_COPY_FROM_USER
 			    (&box, &cmdbuf->boxes[n + i], sizeof(box))) {
 				DRM_ERROR("copy cliprect faulted\n");
 				return -EFAULT;
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 47f180a..456750a 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -232,7 +232,7 @@
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 base_rate = 48000;
+	u32 base_rate = 24000;
 
 	if (!dig || !dig->afmt)
 		return;
@@ -240,7 +240,6 @@
 	/* there are two DTOs selected by DCCG_AUDIO_DTO_SELECT.
 	 * doesn't matter which one you use.  Just use the first one.
 	 */
-	/* XXX: properly calculate this */
 	/* XXX two dtos; generally use dto0 for hdmi */
 	/* Express [24MHz / target pixel clock] as an exact rational
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
@@ -250,13 +249,13 @@
 		/* according to the reg specs, this should DCE3.2 only, but in
 		 * practice it seems to cover DCE3.0 as well.
 		 */
-		WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 50);
+		WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
 		WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
 		WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
 	} else {
 		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
-		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate * 50) |
-		       AUDIO_DTO_MODULE(clock * 100));
+		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
+		       AUDIO_DTO_MODULE(clock / 10));
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 1442ce7..142ce6c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1694,6 +1694,7 @@
 	int num_crtc; /* number of crtcs */
 	struct mutex dc_hw_i2c_mutex; /* display controller hw i2c mutex */
 	bool audio_enabled;
+	bool has_uvd;
 	struct r600_audio audio_status; /* audio stuff */
 	struct notifier_block acpi_nb;
 	/* only one userspace can use Hyperz features or CMASK at a time */
@@ -1838,6 +1839,7 @@
 #define ASIC_IS_DCE61(rdev) ((rdev->family >= CHIP_ARUBA) && \
 			     (rdev->flags & RADEON_IS_IGP))
 #define ASIC_IS_DCE64(rdev) ((rdev->family == CHIP_OLAND))
+#define ASIC_IS_NODCE(rdev) ((rdev->family == CHIP_HAINAN))
 
 /*
  * BIOS helpers.
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 6417132..06b8c19 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1935,6 +1935,8 @@
 	else
 		rdev->num_crtc = 2;
 
+	rdev->has_uvd = false;
+
 	switch (rdev->family) {
 	case CHIP_R100:
 	case CHIP_RV100:
@@ -1999,16 +2001,22 @@
 	case CHIP_RV635:
 	case CHIP_RV670:
 		rdev->asic = &r600_asic;
+		if (rdev->family == CHIP_R600)
+			rdev->has_uvd = false;
+		else
+			rdev->has_uvd = true;
 		break;
 	case CHIP_RS780:
 	case CHIP_RS880:
 		rdev->asic = &rs780_asic;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_RV770:
 	case CHIP_RV730:
 	case CHIP_RV710:
 	case CHIP_RV740:
 		rdev->asic = &rv770_asic;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_CEDAR:
 	case CHIP_REDWOOD:
@@ -2021,11 +2029,13 @@
 		else
 			rdev->num_crtc = 6;
 		rdev->asic = &evergreen_asic;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_PALM:
 	case CHIP_SUMO:
 	case CHIP_SUMO2:
 		rdev->asic = &sumo_asic;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_BARTS:
 	case CHIP_TURKS:
@@ -2036,27 +2046,37 @@
 		else
 			rdev->num_crtc = 6;
 		rdev->asic = &btc_asic;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_CAYMAN:
 		rdev->asic = &cayman_asic;
 		/* set num crtcs */
 		rdev->num_crtc = 6;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_ARUBA:
 		rdev->asic = &trinity_asic;
 		/* set num crtcs */
 		rdev->num_crtc = 4;
+		rdev->has_uvd = true;
 		break;
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
+	case CHIP_HAINAN:
 		rdev->asic = &si_asic;
 		/* set num crtcs */
-		if (rdev->family == CHIP_OLAND)
+		if (rdev->family == CHIP_HAINAN)
+			rdev->num_crtc = 0;
+		else if (rdev->family == CHIP_OLAND)
 			rdev->num_crtc = 2;
 		else
 			rdev->num_crtc = 6;
+		if (rdev->family == CHIP_HAINAN)
+			rdev->has_uvd = false;
+		else
+			rdev->has_uvd = true;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index fa3c56f..061b227 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -244,24 +244,28 @@
 
 	/* enable the rom */
 	WREG32(R600_BUS_CNTL, (bus_cntl & ~R600_BIOS_ROM_DIS));
-	/* Disable VGA mode */
-	WREG32(AVIVO_D1VGA_CONTROL,
-	       (d1vga_control & ~(AVIVO_DVGA_CONTROL_MODE_ENABLE |
-		AVIVO_DVGA_CONTROL_TIMING_SELECT)));
-	WREG32(AVIVO_D2VGA_CONTROL,
-	       (d2vga_control & ~(AVIVO_DVGA_CONTROL_MODE_ENABLE |
-		AVIVO_DVGA_CONTROL_TIMING_SELECT)));
-	WREG32(AVIVO_VGA_RENDER_CONTROL,
-	       (vga_render_control & ~AVIVO_VGA_VSTATUS_CNTL_MASK));
+	if (!ASIC_IS_NODCE(rdev)) {
+		/* Disable VGA mode */
+		WREG32(AVIVO_D1VGA_CONTROL,
+		       (d1vga_control & ~(AVIVO_DVGA_CONTROL_MODE_ENABLE |
+					  AVIVO_DVGA_CONTROL_TIMING_SELECT)));
+		WREG32(AVIVO_D2VGA_CONTROL,
+		       (d2vga_control & ~(AVIVO_DVGA_CONTROL_MODE_ENABLE |
+					  AVIVO_DVGA_CONTROL_TIMING_SELECT)));
+		WREG32(AVIVO_VGA_RENDER_CONTROL,
+		       (vga_render_control & ~AVIVO_VGA_VSTATUS_CNTL_MASK));
+	}
 	WREG32(R600_ROM_CNTL, rom_cntl | R600_SCK_OVERWRITE);
 
 	r = radeon_read_bios(rdev);
 
 	/* restore regs */
 	WREG32(R600_BUS_CNTL, bus_cntl);
-	WREG32(AVIVO_D1VGA_CONTROL, d1vga_control);
-	WREG32(AVIVO_D2VGA_CONTROL, d2vga_control);
-	WREG32(AVIVO_VGA_RENDER_CONTROL, vga_render_control);
+	if (!ASIC_IS_NODCE(rdev)) {
+		WREG32(AVIVO_D1VGA_CONTROL, d1vga_control);
+		WREG32(AVIVO_D2VGA_CONTROL, d2vga_control);
+		WREG32(AVIVO_VGA_RENDER_CONTROL, vga_render_control);
+	}
 	WREG32(R600_ROM_CNTL, rom_cntl);
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index a8f6089..c2c59fb 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -94,6 +94,7 @@
 	"PITCAIRN",
 	"VERDE",
 	"OLAND",
+	"HAINAN",
 	"LAST",
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d33f484..094e7e5 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -147,7 +147,7 @@
 #endif
 
 int radeon_no_wb;
-int radeon_modeset = 1;
+int radeon_modeset = -1;
 int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
 int radeon_agpmode = 0;
@@ -456,6 +456,16 @@
 
 static int __init radeon_init(void)
 {
+#ifdef CONFIG_VGA_CONSOLE
+	if (vgacon_text_force() && radeon_modeset == -1) {
+		DRM_INFO("VGACON disable radeon kernel modesetting.\n");
+		radeon_modeset = 0;
+	}
+#endif
+	/* set to modesetting by default if not nomodeset */
+	if (radeon_modeset == -1)
+		radeon_modeset = 1;
+
 	if (radeon_modeset == 1) {
 		DRM_INFO("radeon kernel modesetting enabled.\n");
 		driver = &kms_driver;
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 2d91123..36e9803 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -92,6 +92,7 @@
 	CHIP_PITCAIRN,
 	CHIP_VERDE,
 	CHIP_OLAND,
+	CHIP_HAINAN,
 	CHIP_LAST,
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 6857cb4..7cb178a 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -1031,11 +1031,9 @@
 
 static void radeon_crtc_prepare(struct drm_crtc *crtc)
 {
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
-	radeon_crtc->in_mode_set = true;
 	/*
 	* The hardware wedges sometimes if you reconfigure one CRTC
 	* whilst another is running (see fdo bug #24611).
@@ -1046,7 +1044,6 @@
 
 static void radeon_crtc_commit(struct drm_crtc *crtc)
 {
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
@@ -1057,7 +1054,6 @@
 		if (crtci->enabled)
 			radeon_crtc_dpms(crtci, DRM_MODE_DPMS_ON);
 	}
-	radeon_crtc->in_mode_set = false;
 }
 
 static const struct drm_crtc_helper_funcs legacy_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 44e579e..69ad4fe 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -302,7 +302,6 @@
 	u16 lut_r[256], lut_g[256], lut_b[256];
 	bool enabled;
 	bool can_tile;
-	bool in_mode_set;
 	uint32_t crtc_offset;
 	struct drm_gem_object *cursor_bo;
 	uint64_t cursor_addr;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 93f760e..6c0ce89 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -726,7 +726,7 @@
 		return r;
 	}
 	DRM_INFO("radeon: %uM of VRAM memory ready\n",
-		 (unsigned)rdev->mc.real_vram_size / (1024 * 1024));
+		 (unsigned) (rdev->mc.real_vram_size / (1024 * 1024)));
 	r = ttm_bo_init_mm(&rdev->mman.bdev, TTM_PL_TT,
 				rdev->mc.gtt_size >> PAGE_SHIFT);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index f0b6c2f..5ffade6 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -60,6 +60,11 @@
 MODULE_FIRMWARE("radeon/OLAND_ce.bin");
 MODULE_FIRMWARE("radeon/OLAND_mc.bin");
 MODULE_FIRMWARE("radeon/OLAND_rlc.bin");
+MODULE_FIRMWARE("radeon/HAINAN_pfp.bin");
+MODULE_FIRMWARE("radeon/HAINAN_me.bin");
+MODULE_FIRMWARE("radeon/HAINAN_ce.bin");
+MODULE_FIRMWARE("radeon/HAINAN_mc.bin");
+MODULE_FIRMWARE("radeon/HAINAN_rlc.bin");
 
 extern int r600_ih_ring_alloc(struct radeon_device *rdev);
 extern void r600_ih_ring_fini(struct radeon_device *rdev);
@@ -265,6 +270,40 @@
 	0x15c0, 0x000c0fc0, 0x000c0400
 };
 
+static const u32 hainan_golden_registers[] =
+{
+	0x9a10, 0x00010000, 0x00018208,
+	0x9830, 0xffffffff, 0x00000000,
+	0x9834, 0xf00fffff, 0x00000400,
+	0x9838, 0x0002021c, 0x00020200,
+	0xd0c0, 0xff000fff, 0x00000100,
+	0xd030, 0x000300c0, 0x00800040,
+	0xd8c0, 0xff000fff, 0x00000100,
+	0xd830, 0x000300c0, 0x00800040,
+	0x2ae4, 0x00073ffe, 0x000022a2,
+	0x240c, 0x000007ff, 0x00000000,
+	0x8a14, 0xf000001f, 0x00000007,
+	0x8b24, 0xffffffff, 0x00ffffff,
+	0x8b10, 0x0000ff0f, 0x00000000,
+	0x28a4c, 0x07ffffff, 0x4e000000,
+	0x28350, 0x3f3f3fff, 0x00000000,
+	0x30, 0x000000ff, 0x0040,
+	0x34, 0x00000040, 0x00004040,
+	0x9100, 0x03e00000, 0x03600000,
+	0x9060, 0x0000007f, 0x00000020,
+	0x9508, 0x00010000, 0x00010000,
+	0xac14, 0x000003ff, 0x000000f1,
+	0xac10, 0xffffffff, 0x00000000,
+	0xac0c, 0xffffffff, 0x00003210,
+	0x88d4, 0x0000001f, 0x00000010,
+	0x15c0, 0x000c0fc0, 0x000c0400
+};
+
+static const u32 hainan_golden_registers2[] =
+{
+	0x98f8, 0xffffffff, 0x02010001
+};
+
 static const u32 tahiti_mgcg_cgcg_init[] =
 {
 	0xc400, 0xffffffff, 0xfffffffc,
@@ -673,6 +712,83 @@
 	0xd8c0, 0xfffffff0, 0x00000100
 };
 
+static const u32 hainan_mgcg_cgcg_init[] =
+{
+	0xc400, 0xffffffff, 0xfffffffc,
+	0x802c, 0xffffffff, 0xe0000000,
+	0x9a60, 0xffffffff, 0x00000100,
+	0x92a4, 0xffffffff, 0x00000100,
+	0xc164, 0xffffffff, 0x00000100,
+	0x9774, 0xffffffff, 0x00000100,
+	0x8984, 0xffffffff, 0x06000100,
+	0x8a18, 0xffffffff, 0x00000100,
+	0x92a0, 0xffffffff, 0x00000100,
+	0xc380, 0xffffffff, 0x00000100,
+	0x8b28, 0xffffffff, 0x00000100,
+	0x9144, 0xffffffff, 0x00000100,
+	0x8d88, 0xffffffff, 0x00000100,
+	0x8d8c, 0xffffffff, 0x00000100,
+	0x9030, 0xffffffff, 0x00000100,
+	0x9034, 0xffffffff, 0x00000100,
+	0x9038, 0xffffffff, 0x00000100,
+	0x903c, 0xffffffff, 0x00000100,
+	0xad80, 0xffffffff, 0x00000100,
+	0xac54, 0xffffffff, 0x00000100,
+	0x897c, 0xffffffff, 0x06000100,
+	0x9868, 0xffffffff, 0x00000100,
+	0x9510, 0xffffffff, 0x00000100,
+	0xaf04, 0xffffffff, 0x00000100,
+	0xae04, 0xffffffff, 0x00000100,
+	0x949c, 0xffffffff, 0x00000100,
+	0x802c, 0xffffffff, 0xe0000000,
+	0x9160, 0xffffffff, 0x00010000,
+	0x9164, 0xffffffff, 0x00030002,
+	0x9168, 0xffffffff, 0x00040007,
+	0x916c, 0xffffffff, 0x00060005,
+	0x9170, 0xffffffff, 0x00090008,
+	0x9174, 0xffffffff, 0x00020001,
+	0x9178, 0xffffffff, 0x00040003,
+	0x917c, 0xffffffff, 0x00000007,
+	0x9180, 0xffffffff, 0x00060005,
+	0x9184, 0xffffffff, 0x00090008,
+	0x9188, 0xffffffff, 0x00030002,
+	0x918c, 0xffffffff, 0x00050004,
+	0x9190, 0xffffffff, 0x00000008,
+	0x9194, 0xffffffff, 0x00070006,
+	0x9198, 0xffffffff, 0x000a0009,
+	0x919c, 0xffffffff, 0x00040003,
+	0x91a0, 0xffffffff, 0x00060005,
+	0x91a4, 0xffffffff, 0x00000009,
+	0x91a8, 0xffffffff, 0x00080007,
+	0x91ac, 0xffffffff, 0x000b000a,
+	0x91b0, 0xffffffff, 0x00050004,
+	0x91b4, 0xffffffff, 0x00070006,
+	0x91b8, 0xffffffff, 0x0008000b,
+	0x91bc, 0xffffffff, 0x000a0009,
+	0x91c0, 0xffffffff, 0x000d000c,
+	0x91c4, 0xffffffff, 0x00060005,
+	0x91c8, 0xffffffff, 0x00080007,
+	0x91cc, 0xffffffff, 0x0000000b,
+	0x91d0, 0xffffffff, 0x000a0009,
+	0x91d4, 0xffffffff, 0x000d000c,
+	0x9150, 0xffffffff, 0x96940200,
+	0x8708, 0xffffffff, 0x00900100,
+	0xc478, 0xffffffff, 0x00000080,
+	0xc404, 0xffffffff, 0x0020003f,
+	0x30, 0xffffffff, 0x0000001c,
+	0x34, 0x000f0000, 0x000f0000,
+	0x160c, 0xffffffff, 0x00000100,
+	0x1024, 0xffffffff, 0x00000100,
+	0x20a8, 0xffffffff, 0x00000104,
+	0x264c, 0x000c0000, 0x000c0000,
+	0x2648, 0x000c0000, 0x000c0000,
+	0x2f50, 0x00000001, 0x00000001,
+	0x30cc, 0xc0000fff, 0x00000104,
+	0xc1e4, 0x00000001, 0x00000001,
+	0xd0c0, 0xfffffff0, 0x00000100,
+	0xd8c0, 0xfffffff0, 0x00000100
+};
+
 static u32 verde_pg_init[] =
 {
 	0x353c, 0xffffffff, 0x40000,
@@ -853,6 +969,17 @@
 						 oland_mgcg_cgcg_init,
 						 (const u32)ARRAY_SIZE(oland_mgcg_cgcg_init));
 		break;
+	case CHIP_HAINAN:
+		radeon_program_register_sequence(rdev,
+						 hainan_golden_registers,
+						 (const u32)ARRAY_SIZE(hainan_golden_registers));
+		radeon_program_register_sequence(rdev,
+						 hainan_golden_registers2,
+						 (const u32)ARRAY_SIZE(hainan_golden_registers2));
+		radeon_program_register_sequence(rdev,
+						 hainan_mgcg_cgcg_init,
+						 (const u32)ARRAY_SIZE(hainan_mgcg_cgcg_init));
+		break;
 	default:
 		break;
 	}
@@ -1062,6 +1189,45 @@
 	{0x0000009f, 0x00a17730}
 };
 
+static const u32 hainan_io_mc_regs[TAHITI_IO_MC_REGS_SIZE][2] = {
+	{0x0000006f, 0x03044000},
+	{0x00000070, 0x0480c018},
+	{0x00000071, 0x00000040},
+	{0x00000072, 0x01000000},
+	{0x00000074, 0x000000ff},
+	{0x00000075, 0x00143400},
+	{0x00000076, 0x08ec0800},
+	{0x00000077, 0x040000cc},
+	{0x00000079, 0x00000000},
+	{0x0000007a, 0x21000409},
+	{0x0000007c, 0x00000000},
+	{0x0000007d, 0xe8000000},
+	{0x0000007e, 0x044408a8},
+	{0x0000007f, 0x00000003},
+	{0x00000080, 0x00000000},
+	{0x00000081, 0x01000000},
+	{0x00000082, 0x02000000},
+	{0x00000083, 0x00000000},
+	{0x00000084, 0xe3f3e4f4},
+	{0x00000085, 0x00052024},
+	{0x00000087, 0x00000000},
+	{0x00000088, 0x66036603},
+	{0x00000089, 0x01000000},
+	{0x0000008b, 0x1c0a0000},
+	{0x0000008c, 0xff010000},
+	{0x0000008e, 0xffffefff},
+	{0x0000008f, 0xfff3efff},
+	{0x00000090, 0xfff3efbf},
+	{0x00000094, 0x00101101},
+	{0x00000095, 0x00000fff},
+	{0x00000096, 0x00116fff},
+	{0x00000097, 0x60010000},
+	{0x00000098, 0x10010000},
+	{0x00000099, 0x00006000},
+	{0x0000009a, 0x00001000},
+	{0x0000009f, 0x00a07730}
+};
+
 /* ucode loading */
 static int si_mc_load_microcode(struct radeon_device *rdev)
 {
@@ -1095,6 +1261,11 @@
 		ucode_size = OLAND_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
+	case CHIP_HAINAN:
+		io_mc_regs = (u32 *)&hainan_io_mc_regs;
+		ucode_size = OLAND_MC_UCODE_SIZE;
+		regs_size = TAHITI_IO_MC_REGS_SIZE;
+		break;
 	}
 
 	running = RREG32(MC_SEQ_SUP_CNTL) & RUN_MASK;
@@ -1198,6 +1369,15 @@
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
 		break;
+	case CHIP_HAINAN:
+		chip_name = "HAINAN";
+		rlc_chip_name = "HAINAN";
+		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
+		me_req_size = SI_PM4_UCODE_SIZE * 4;
+		ce_req_size = SI_CE_UCODE_SIZE * 4;
+		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
+		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		break;
 	default: BUG();
 	}
 
@@ -2003,7 +2183,8 @@
 			WREG32(GB_TILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if ((rdev->family == CHIP_VERDE) ||
-		   (rdev->family == CHIP_OLAND)) {
+		   (rdev->family == CHIP_OLAND) ||
+		   (rdev->family == CHIP_HAINAN)) {
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
 			case 0:  /* non-AA compressed depth or any compressed stencil */
@@ -2466,6 +2647,23 @@
 		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
 		gb_addr_config = VERDE_GB_ADDR_CONFIG_GOLDEN;
 		break;
+	case CHIP_HAINAN:
+		rdev->config.si.max_shader_engines = 1;
+		rdev->config.si.max_tile_pipes = 4;
+		rdev->config.si.max_cu_per_sh = 5;
+		rdev->config.si.max_sh_per_se = 1;
+		rdev->config.si.max_backends_per_se = 1;
+		rdev->config.si.max_texture_channel_caches = 2;
+		rdev->config.si.max_gprs = 256;
+		rdev->config.si.max_gs_threads = 16;
+		rdev->config.si.max_hw_contexts = 8;
+
+		rdev->config.si.sc_prim_fifo_size_frontend = 0x20;
+		rdev->config.si.sc_prim_fifo_size_backend = 0x40;
+		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = HAINAN_GB_ADDR_CONFIG_GOLDEN;
+		break;
 	}
 
 	/* Initialize HDP */
@@ -2559,9 +2757,11 @@
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 	WREG32(DMA_TILING_CONFIG + DMA0_REGISTER_OFFSET, gb_addr_config);
 	WREG32(DMA_TILING_CONFIG + DMA1_REGISTER_OFFSET, gb_addr_config);
-	WREG32(UVD_UDEC_ADDR_CONFIG, gb_addr_config);
-	WREG32(UVD_UDEC_DB_ADDR_CONFIG, gb_addr_config);
-	WREG32(UVD_UDEC_DBW_ADDR_CONFIG, gb_addr_config);
+	if (rdev->has_uvd) {
+		WREG32(UVD_UDEC_ADDR_CONFIG, gb_addr_config);
+		WREG32(UVD_UDEC_DB_ADDR_CONFIG, gb_addr_config);
+		WREG32(UVD_UDEC_DBW_ADDR_CONFIG, gb_addr_config);
+	}
 
 	si_tiling_mode_table_init(rdev);
 
@@ -3304,8 +3504,9 @@
 	if (radeon_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
-	/* Lockout access through VGA aperture*/
-	WREG32(VGA_HDP_CONTROL, VGA_MEMORY_DISABLE);
+	if (!ASIC_IS_NODCE(rdev))
+		/* Lockout access through VGA aperture*/
+		WREG32(VGA_HDP_CONTROL, VGA_MEMORY_DISABLE);
 	/* Update configuration */
 	WREG32(MC_VM_SYSTEM_APERTURE_LOW_ADDR,
 	       rdev->mc.vram_start >> 12);
@@ -3327,9 +3528,11 @@
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 	evergreen_mc_resume(rdev, &save);
-	/* we need to own VRAM, so turn off the VGA renderer here
-	 * to stop it overwriting our objects */
-	rv515_vga_render_disable(rdev);
+	if (!ASIC_IS_NODCE(rdev)) {
+		/* we need to own VRAM, so turn off the VGA renderer here
+		 * to stop it overwriting our objects */
+		rv515_vga_render_disable(rdev);
+	}
 }
 
 static void si_vram_gtt_location(struct radeon_device *rdev,
@@ -3397,8 +3600,8 @@
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	/* size in MB on si */
-	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
-	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
+	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	si_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
@@ -4251,8 +4454,10 @@
 	tmp = RREG32(DMA_CNTL + DMA1_REGISTER_OFFSET) & ~TRAP_ENABLE;
 	WREG32(DMA_CNTL + DMA1_REGISTER_OFFSET, tmp);
 	WREG32(GRBM_INT_CNTL, 0);
-	WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	if (rdev->num_crtc >= 2) {
+		WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
+		WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	}
 	if (rdev->num_crtc >= 4) {
 		WREG32(INT_MASK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
 		WREG32(INT_MASK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
@@ -4262,8 +4467,10 @@
 		WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
 
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	}
 	if (rdev->num_crtc >= 4) {
 		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
 		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
@@ -4273,21 +4480,22 @@
 		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
 
-	WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
+	if (!ASIC_IS_NODCE(rdev)) {
+		WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
 
-	tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD1_INT_CONTROL, tmp);
-	tmp = RREG32(DC_HPD2_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD2_INT_CONTROL, tmp);
-	tmp = RREG32(DC_HPD3_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD3_INT_CONTROL, tmp);
-	tmp = RREG32(DC_HPD4_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD4_INT_CONTROL, tmp);
-	tmp = RREG32(DC_HPD5_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD5_INT_CONTROL, tmp);
-	tmp = RREG32(DC_HPD6_INT_CONTROL) & DC_HPDx_INT_POLARITY;
-	WREG32(DC_HPD6_INT_CONTROL, tmp);
-
+		tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD1_INT_CONTROL, tmp);
+		tmp = RREG32(DC_HPD2_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD2_INT_CONTROL, tmp);
+		tmp = RREG32(DC_HPD3_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD3_INT_CONTROL, tmp);
+		tmp = RREG32(DC_HPD4_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD4_INT_CONTROL, tmp);
+		tmp = RREG32(DC_HPD5_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD5_INT_CONTROL, tmp);
+		tmp = RREG32(DC_HPD6_INT_CONTROL) & DC_HPDx_INT_POLARITY;
+		WREG32(DC_HPD6_INT_CONTROL, tmp);
+	}
 }
 
 static int si_irq_init(struct radeon_device *rdev)
@@ -4366,7 +4574,7 @@
 	u32 cp_int_cntl = CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE;
 	u32 cp_int_cntl1 = 0, cp_int_cntl2 = 0;
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
-	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
+	u32 hpd1 = 0, hpd2 = 0, hpd3 = 0, hpd4 = 0, hpd5 = 0, hpd6 = 0;
 	u32 grbm_int_cntl = 0;
 	u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0;
 	u32 dma_cntl, dma_cntl1;
@@ -4383,12 +4591,14 @@
 		return 0;
 	}
 
-	hpd1 = RREG32(DC_HPD1_INT_CONTROL) & ~DC_HPDx_INT_EN;
-	hpd2 = RREG32(DC_HPD2_INT_CONTROL) & ~DC_HPDx_INT_EN;
-	hpd3 = RREG32(DC_HPD3_INT_CONTROL) & ~DC_HPDx_INT_EN;
-	hpd4 = RREG32(DC_HPD4_INT_CONTROL) & ~DC_HPDx_INT_EN;
-	hpd5 = RREG32(DC_HPD5_INT_CONTROL) & ~DC_HPDx_INT_EN;
-	hpd6 = RREG32(DC_HPD6_INT_CONTROL) & ~DC_HPDx_INT_EN;
+	if (!ASIC_IS_NODCE(rdev)) {
+		hpd1 = RREG32(DC_HPD1_INT_CONTROL) & ~DC_HPDx_INT_EN;
+		hpd2 = RREG32(DC_HPD2_INT_CONTROL) & ~DC_HPDx_INT_EN;
+		hpd3 = RREG32(DC_HPD3_INT_CONTROL) & ~DC_HPDx_INT_EN;
+		hpd4 = RREG32(DC_HPD4_INT_CONTROL) & ~DC_HPDx_INT_EN;
+		hpd5 = RREG32(DC_HPD5_INT_CONTROL) & ~DC_HPDx_INT_EN;
+		hpd6 = RREG32(DC_HPD6_INT_CONTROL) & ~DC_HPDx_INT_EN;
+	}
 
 	dma_cntl = RREG32(DMA_CNTL + DMA0_REGISTER_OFFSET) & ~TRAP_ENABLE;
 	dma_cntl1 = RREG32(DMA_CNTL + DMA1_REGISTER_OFFSET) & ~TRAP_ENABLE;
@@ -4479,8 +4689,10 @@
 
 	WREG32(GRBM_INT_CNTL, grbm_int_cntl);
 
-	WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, crtc1);
-	WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, crtc2);
+	if (rdev->num_crtc >= 2) {
+		WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, crtc1);
+		WREG32(INT_M