Merge branches 'btc', 'dma', 'entry', 'fixes', 'linker-layout', 'misc', 'mmci', 'suspend' and 'vfp' into for-next

CREDITS

@@ -518,7 +518,7 @@ N: Zach Brown
 E: zab@zabbo.net
 D: maestro pci sound
 
-M: David Brownell
+N: David Brownell
 D: Kernel engineer, mentor, and friend.  Maintained USB EHCI and
 D: gadget layers, SPI subsystem, GPIO subsystem, and more than a few
 D: device drivers.  His encouragement also helped many engineers get

Documentation/Changes

@@ -2,13 +2,7 @@ Intro
 =====
 
 This document is designed to provide a list of the minimum levels of
-software necessary to run the 2.6 kernels, as well as provide brief
-instructions regarding any other "Gotchas" users may encounter when
-trying life on the Bleeding Edge.  If upgrading from a pre-2.4.x
-kernel, please consult the Changes file included with 2.4.x kernels for
-additional information; most of that information will not be repeated
-here.  Basically, this document assumes that your system is already
-functional and running at least 2.4.x kernels.
+software necessary to run the 3.0 kernels.
 
 This document is originally based on my "Changes" file for 2.0.x kernels
 and therefore owes credit to the same people as that file (Jared Mauch,
@@ -22,11 +16,10 @@ Upgrade to at *least* these software revisions before thinking you've
 encountered a bug!  If you're unsure what version you're currently
 running, the suggested command should tell you.
 
-Again, keep in mind that this list assumes you are already
-functionally running a Linux 2.4 kernel.  Also, not all tools are
-necessary on all systems; obviously, if you don't have any ISDN
-hardware, for example, you probably needn't concern yourself with
-isdn4k-utils.
+Again, keep in mind that this list assumes you are already functionally
+running a Linux kernel.  Also, not all tools are necessary on all
+systems; obviously, if you don't have any ISDN hardware, for example,
+you probably needn't concern yourself with isdn4k-utils.
 
 o  Gnu C                  3.2                     # gcc --version
 o  Gnu make               3.80                    # make --version
@@ -114,12 +107,12 @@ Ksymoops
 
 If the unthinkable happens and your kernel oopses, you may need the
 ksymoops tool to decode it, but in most cases you don't.
-In the 2.6 kernel it is generally preferred to build the kernel with
-CONFIG_KALLSYMS so that it produces readable dumps that can be used as-is
-(this also produces better output than ksymoops).
-If for some reason your kernel is not build with CONFIG_KALLSYMS and
-you have no way to rebuild and reproduce the Oops with that option, then
-you can still decode that Oops with ksymoops.
+It is generally preferred to build the kernel with CONFIG_KALLSYMS so
+that it produces readable dumps that can be used as-is (this also
+produces better output than ksymoops).  If for some reason your kernel
+is not build with CONFIG_KALLSYMS and you have no way to rebuild and
+reproduce the Oops with that option, then you can still decode that Oops
+with ksymoops.
 
 Module-Init-Tools
 -----------------
@@ -261,8 +254,8 @@ needs to be recompiled or (preferably) upgraded.
 NFS-utils
 ---------
 
-In 2.4 and earlier kernels, the nfs server needed to know about any
-client that expected to be able to access files via NFS.  This
+In ancient (2.4 and earlier) kernels, the nfs server needed to know
+about any client that expected to be able to access files via NFS.  This
 information would be given to the kernel by "mountd" when the client
 mounted the filesystem, or by "exportfs" at system startup.  exportfs
 would take information about active clients from /var/lib/nfs/rmtab.
@@ -272,11 +265,11 @@ which is not always easy, particularly when trying to implement
 fail-over.  Even when the system is working well, rmtab suffers from
 getting lots of old entries that never get removed.
 
-With 2.6 we have the option of having the kernel tell mountd when it
-gets a request from an unknown host, and mountd can give appropriate
-export information to the kernel.  This removes the dependency on
-rmtab and means that the kernel only needs to know about currently
-active clients.
+With modern kernels we have the option of having the kernel tell mountd
+when it gets a request from an unknown host, and mountd can give
+appropriate export information to the kernel.  This removes the
+dependency on rmtab and means that the kernel only needs to know about
+currently active clients.
 
 To enable this new functionality, you need to:
 

Documentation/CodingStyle

@@ -680,8 +680,8 @@ ones already enabled by DEBUG.
 		Chapter 14: Allocating memory
 
 The kernel provides the following general purpose memory allocators:
-kmalloc(), kzalloc(), kcalloc(), and vmalloc().  Please refer to the API
-documentation for further information about them.
+kmalloc(), kzalloc(), kcalloc(), vmalloc(), and vzalloc().  Please refer to
+the API documentation for further information about them.
 
 The preferred form for passing a size of a struct is the following:
 

Documentation/arm/Booting

@@ -164,3 +164,8 @@ In either case, the following conditions must be met:
 - The boot loader is expected to call the kernel image by jumping
   directly to the first instruction of the kernel image.
 
+  On CPUs supporting the ARM instruction set, the entry must be
+  made in ARM state, even for a Thumb-2 kernel.
+
+  On CPUs supporting only the Thumb instruction set such as
+  Cortex-M class CPUs, the entry must be made in Thumb state.

Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt

@@ -0,0 +1,42 @@
+ROM-able zImage boot from eSD
+-----------------------------
+
+An ROM-able zImage compiled with ZBOOT_ROM_SDHI may be written to eSD and
+SuperH Mobile ARM will to boot directly from the SDHI hardware block.
+
+This is achieved by the mask ROM loading the first portion of the image into
+MERAM and then jumping to it. This portion contains loader code which
+copies the entire image to SDRAM and jumps to it. From there the zImage
+boot code proceeds as normal, uncompressing the image into its final
+location and then jumping to it.
+
+This code has been tested on an mackerel board using the developer 1A eSD
+boot mode which is configured using the following jumper settings.
+
+   8 7 6 5 4 3 2 1
+   x|x|x|x| |x|x|
+S4 -+-+-+-+-+-+-+-
+    | | | |x| | |x on
+
+The eSD card needs to be present in SDHI slot 1 (CN7).
+As such S1 and S33 also need to be configured as per
+the notes in arch/arm/mach-shmobile/board-mackerel.c.
+
+A partial zImage must be written to physical partition #1 (boot)
+of the eSD at sector 0 in vrl4 format. A utility vrl4 is supplied to
+accomplish this.
+
+e.g.
+	vrl4 < zImage | dd of=/dev/sdX bs=512 count=17
+
+A full copy of _the same_ zImage should be written to physical partition #1
+(boot) of the eSD at sector 0. This should _not_ be in vrl4 format.
+
+	vrl4 < zImage | dd of=/dev/sdX bs=512
+
+Note: The commands above assume that the physical partition has been
+switched. No such facility currently exists in the Linux Kernel.
+
+Physical partitions are described in the eSD specification.  At the time of
+writing they are not the same as partitions that are typically configured
+using fdisk and visible through /proc/partitions

Documentation/cgroups/blkio-controller.txt

@@ -77,7 +77,7 @@ Throttling/Upper Limit policy
 - Specify a bandwidth rate on particular device for root group. The format
   for policy is "<major>:<minor>  <byes_per_second>".
 
-        echo "8:16  1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device
+        echo "8:16  1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device
 
   Above will put a limit of 1MB/second on reads happening for root group
   on device having major/minor number 8:16.
@@ -90,7 +90,7 @@ Throttling/Upper Limit policy
         1024+0 records out
         4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
 
- Limits for writes can be put using blkio.write_bps_device file.
+ Limits for writes can be put using blkio.throttle.write_bps_device file.
 
 Hierarchical Cgroups
 ====================
@@ -286,28 +286,28 @@ Throttling/Upper limit policy files
 	  specified in bytes per second. Rules are per deivce. Following is
 	  the format.
 
-  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device
 
 - blkio.throttle.write_bps_device
 	- Specifies upper limit on WRITE rate to the device. IO rate is
 	  specified in bytes per second. Rules are per deivce. Following is
 	  the format.
 
-  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device
 
 - blkio.throttle.read_iops_device
 	- Specifies upper limit on READ rate from the device. IO rate is
 	  specified in IO per second. Rules are per deivce. Following is
 	  the format.
 
-  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.read_iops_device
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device
 
 - blkio.throttle.write_iops_device
 	- Specifies upper limit on WRITE rate to the device. IO rate is
 	  specified in io per second. Rules are per deivce. Following is
 	  the format.
 
-  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.write_iops_device
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device
 
 Note: If both BW and IOPS rules are specified for a device, then IO is
       subjectd to both the constraints.

Documentation/devicetree/bindings/arm/pmu.txt

@@ -0,0 +1,21 @@
+* ARM Performance Monitor Units
+
+ARM cores often have a PMU for counting cpu and cache events like cache misses
+and hits. The interface to the PMU is part of the ARM ARM. The ARM PMU
+representation in the device tree should be done as under:-
+
+Required properties:
+
+- compatible : should be one of
+	"arm,cortex-a9-pmu"
+	"arm,cortex-a8-pmu"
+	"arm,arm1176-pmu"
+	"arm,arm1136-pmu"
+- interrupts : 1 combined interrupt or 1 per core.
+
+Example:
+
+pmu {
+        compatible = "arm,cortex-a9-pmu";
+        interrupts = <100 101>;
+};

Documentation/feature-removal-schedule.txt

@@ -583,3 +583,25 @@ Why:	Superseded by the UVCIOC_CTRL_QUERY ioctl.
 Who:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 
 ----------------------------
+
+What:	For VIDIOC_S_FREQUENCY the type field must match the device node's type.
+	If not, return -EINVAL.
+When:	3.2
+Why:	It makes no sense to switch the tuner to radio mode by calling
+	VIDIOC_S_FREQUENCY on a video node, or to switch the tuner to tv mode by
+	calling VIDIOC_S_FREQUENCY on a radio node. This is the first step of a
+	move to more consistent handling of tv and radio tuners.
+Who:	Hans Verkuil <hans.verkuil@cisco.com>
+
+----------------------------
+
+What:	Opening a radio device node will no longer automatically switch the
+	tuner mode from tv to radio.
+When:	3.3
+Why:	Just opening a V4L device should not change the state of the hardware
+	like that. It's very unexpected and against the V4L spec. Instead, you
+	switch to radio mode by calling VIDIOC_S_FREQUENCY. This is the second
+	and last step of the move to consistent handling of tv and radio tuners.
+Who:	Hans Verkuil <hans.verkuil@cisco.com>
+
+----------------------------

Documentation/filesystems/caching/netfs-api.txt

@@ -673,6 +673,22 @@ storage request to complete, or it may attempt to cancel the storage request -
 in which case the page will not be stored in the cache this time.
 
 
+BULK INODE PAGE UNCACHE
+-----------------------
+
+A convenience routine is provided to perform an uncache on all the pages
+attached to an inode.  This assumes that the pages on the inode correspond on a
+1:1 basis with the pages in the cache.
+
+	void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
+					     struct inode *inode);
+
+This takes the netfs cookie that the pages were cached with and the inode that
+the pages are attached to.  This function will wait for pages to finish being
+written to the cache and for the cache to finish with the page generally.  No
+error is returned.
+
+
 ==========================
 INDEX AND DATA FILE UPDATE
 ==========================

Documentation/filesystems/nilfs2.txt

@@ -40,7 +40,6 @@ Features which NILFS2 does not support yet:
 	- POSIX ACLs
 	- quotas
 	- fsck
-	- resize
 	- defragmentation
 
 Mount options

Documentation/filesystems/proc.txt

@@ -843,6 +843,7 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
+     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide

Documentation/hwmon/f71882fg

@@ -22,6 +22,10 @@ Supported chips:
     Prefix: 'f71869'
     Addresses scanned: none, address read from Super I/O config space
     Datasheet: Available from the Fintek website
+  * Fintek F71869A
+    Prefix: 'f71869a'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Not public
   * Fintek F71882FG and F71883FG
     Prefix: 'f71882fg'
     Addresses scanned: none, address read from Super I/O config space

Documentation/hwmon/k10temp

@@ -9,8 +9,8 @@ Supported chips:
   Socket S1G3: Athlon II, Sempron, Turion II
 * AMD Family 11h processors:
   Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
-* AMD Family 12h processors: "Llano"
-* AMD Family 14h processors: "Brazos" (C/E/G-Series)
+* AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
+* AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
 * AMD Family 15h processors: "Bulldozer"
 
   Prefix: 'k10temp'
@@ -20,12 +20,16 @@ Supported chips:
     http://support.amd.com/us/Processor_TechDocs/31116.pdf
   BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors:
     http://support.amd.com/us/Processor_TechDocs/41256.pdf
+  BIOS and Kernel Developer's Guide (BKDG) for AMD Family 12h Processors:
+    http://support.amd.com/us/Processor_TechDocs/41131.pdf
   BIOS and Kernel Developer's Guide (BKDG) for AMD Family 14h Models 00h-0Fh Processors:
     http://support.amd.com/us/Processor_TechDocs/43170.pdf
   Revision Guide for AMD Family 10h Processors:
     http://support.amd.com/us/Processor_TechDocs/41322.pdf
   Revision Guide for AMD Family 11h Processors:
     http://support.amd.com/us/Processor_TechDocs/41788.pdf
+  Revision Guide for AMD Family 12h Processors:
+    http://support.amd.com/us/Processor_TechDocs/44739.pdf
   Revision Guide for AMD Family 14h Models 00h-0Fh Processors:
     http://support.amd.com/us/Processor_TechDocs/47534.pdf
   AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks:

Documentation/kernel-parameters.txt

@@ -2015,6 +2015,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				the default.
 				off: Turn ECRC off
 				on: Turn ECRC on.
+		realloc		reallocate PCI resources if allocations done by BIOS
+				are erroneous.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.

Documentation/laptops/thinkpad-acpi.txt

@@ -534,6 +534,8 @@ Events that are never propagated by the driver:
 0x2404		System is waking up from hibernation to undock
 0x2405		System is waking up from hibernation to eject bay
 0x5010		Brightness level changed/control event
+0x6000		KEYBOARD: Numlock key pressed
+0x6005		KEYBOARD: Fn key pressed (TO BE VERIFIED)
 
 Events that are propagated by the driver to userspace:
 
@@ -545,6 +547,8 @@ Events that are propagated by the driver to userspace:
 0x3006		Bay hotplug request (hint to power up SATA link when
 		the optical drive tray is ejected)
 0x4003		Undocked (see 0x2x04), can sleep again
+0x4010		Docked into hotplug port replicator (non-ACPI dock)
+0x4011		Undocked from hotplug port replicator (non-ACPI dock)
 0x500B		Tablet pen inserted into its storage bay
 0x500C		Tablet pen removed from its storage bay
 0x6011		ALARM: battery is too hot
@@ -552,6 +556,7 @@ Events that are propagated by the driver to userspace:
 0x6021		ALARM: a sensor is too hot
 0x6022		ALARM: a sensor is extremely hot
 0x6030		System thermal table changed
+0x6040		Nvidia Optimus/AC adapter related (TO BE VERIFIED)
 
 Battery nearly empty alarms are a last resort attempt to get the
 operating system to hibernate or shutdown cleanly (0x2313), or shutdown

Documentation/networking/ip-sysctl.txt

@@ -346,7 +346,7 @@ tcp_orphan_retries - INTEGER
 	when RTO retransmissions remain unacknowledged.
 	See tcp_retries2 for more details.
 
-	The default value is 7.
+	The default value is 8.
 	If your machine is a loaded WEB server,
 	you should think about lowering this value, such sockets
 	may consume significant resources. Cf. tcp_max_orphans.

Documentation/power/devices.txt

@@ -520,59 +520,20 @@ Support for power domains is provided through the pwr_domain field of struct
 device.  This field is a pointer to an object of type struct dev_power_domain,
 defined in include/linux/pm.h, providing a set of power management callbacks
 analogous to the subsystem-level and device driver callbacks that are executed
-for the given device during all power transitions, in addition to the respective
-subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
-(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
-executed after the analogous subsystem-level callbacks, while the power domain
-"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
-etc.) are executed before the analogous subsystem-level callbacks.  Error codes
-returned by the "suspend" and "resume" power domain callbacks are ignored.
-
-Power domain ->runtime_idle() callback is executed before the subsystem-level
-->runtime_idle() callback and the result returned by it is not ignored.  Namely,
-if it returns error code, the subsystem-level ->runtime_idle() callback will not
-be called and the helper function rpm_idle() executing it will return error
-code.  This mechanism is intended to help platforms where saving device state
-is a time consuming operation and should only be carried out if all devices
-in the power domain are idle, before turning off the shared power resource(s).
-Namely, the power domain ->runtime_idle() callback may return error code until
-the pm_runtime_idle() helper (or its asychronous version) has been called for
-all devices in the power domain (it is recommended that the returned error code
-be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
-callback from being run prematurely.
-
-The support for device power domains is only relevant to platforms needing to
-use the same subsystem-level (e.g. platform bus type) and device driver power
-management callbacks in many different power domain configurations and wanting
-to avoid incorporating the support for power domains into the subsystem-level
-callbacks.  The other platforms need not implement it or take it into account
-in any way.
-
-
-System Devices
---------------
-System devices (sysdevs) follow a slightly different API, which can be found in
-
-	include/linux/sysdev.h
-	drivers/base/sys.c
-
-System devices will be suspended with interrupts disabled, and after all other
-devices have been suspended.  On resume, they will be resumed before any other
-devices, and also with interrupts disabled.  These things occur in special
-"sysdev_driver" phases, which affect only system devices.
-
-Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when
-the non-boot CPUs are all offline and IRQs are disabled on the remaining online
-CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a
-sleep state (or a system image is created).  During resume (or after the image
-has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs
-are enabled on the only online CPU, the non-boot CPUs are enabled, and the
-resume_noirq (or thaw_noirq or restore_noirq) phase begins.
-
-Code to actually enter and exit the system-wide low power state sometimes
-involves hardware details that are only known to the boot firmware, and
-may leave a CPU running software (from SRAM or flash memory) that monitors
-the system and manages its wakeup sequence.
+for the given device during all power transitions, instead of the respective
+subsystem-level callbacks.  Specifically, if a device's pm_domain pointer is
+not NULL, the ->suspend() callback from the object pointed to by it will be
+executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and
+anlogously for all of the remaining callbacks.  In other words, power management
+domain callbacks, if defined for the given device, always take precedence over
+the callbacks provided by the device's subsystem (e.g. bus type).
+
+The support for device power management domains is only relevant to platforms
+needing to use the same device driver power management callbacks in many
+different power domain configurations and wanting to avoid incorporating the
+support for power domains into subsystem-level callbacks, for example by
+modifying the platform bus type.  Other platforms need not implement it or take
+it into account in any way.
 
 
 Device Low Power (suspend) States

Documentation/power/runtime_pm.txt

@@ -501,13 +501,29 @@ helper functions described in Section 4.  In that case, pm_runtime_resume()
 should be used.  Of course, for this purpose the device's run-time PM has to be
 enabled earlier by calling pm_runtime_enable().
 
-If the device bus type's or driver's ->probe() or ->remove() callback runs
+If the device bus type's or driver's ->probe() callback runs
 pm_runtime_suspend() or pm_runtime_idle() or their asynchronous counterparts,
 they will fail returning -EAGAIN, because the device's usage counter is
-incremented by the core before executing ->probe() and ->remove().  Still, it
-may be desirable to suspend the device as soon as ->probe() or ->remove() has
-finished, so the PM core uses pm_runtime_idle_sync() to invoke the
-subsystem-level idle callback for the device at that time.
+incremented by the driver core before executing ->probe().  Still, it may be
+desirable to suspend the device as soon as ->probe() has finished, so the driver
+core uses pm_runtime_put_sync() to invoke the subsystem-level idle callback for
+the device at that time.
+
+Moreover, the driver core prevents runtime PM callbacks from racing with the bus
+notifier callback in __device_release_driver(), which is necessary, because the
+notifier is used by some subsystems to carry out operations affecting the
+runtime PM functionality.  It does so by calling pm_runtime_get_sync() before
+driver_sysfs_remove() and the BUS_NOTIFY_UNBIND_DRIVER notifications.  This
+resumes the device if it's in the suspended state and prevents it from
+being suspended again while those routines are being executed.
+
+To allow bus types and drivers to put devices into the suspended state by
+calling pm_runtime_suspend() from their ->remove() routines, the driver core
+executes pm_runtime_put_sync() after running the BUS_NOTIFY_UNBIND_DRIVER
+notifications in __device_release_driver().  This requires bus types and
+drivers to make their ->remove() callbacks avoid races with runtime PM directly,
+but also it allows of more flexibility in the handling of devices during the
+removal of their drivers.
 
 The user space can effectively disallow the driver of the device to power manage
 it at run time by changing the value of its /sys/devices/.../power/control
@@ -566,11 +582,6 @@ to do this is:
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
-The PM core always increments the run-time usage counter before calling the
-->prepare() callback and decrements it after calling the ->complete() callback.
-Hence disabling run-time PM temporarily like this will not cause any run-time
-suspend callbacks to be lost.
-
 7. Generic subsystem callbacks
 
 Subsystems may wish to conserve code space by using the set of generic power

Documentation/spinlocks.txt

@@ -13,18 +13,8 @@ static DEFINE_SPINLOCK(xxx_lock);
 The above is always safe. It will disable interrupts _locally_, but the
 spinlock itself will guarantee the global lock, so it will guarantee that
 there is only one thread-of-control within the region(s) protected by that
-lock. This works well even under UP. The above sequence under UP
-essentially is just the same as doing
-
-	unsigned long flags;
-
-	save_flags(flags); cli();
-	 ... critical section ...
-	restore_flags(flags);
-
-so the code does _not_ need to worry about UP vs SMP issues: the spinlocks
-work correctly under both (and spinlocks are actually more efficient on
-architectures that allow doing the "save_flags + cli" in one operation).
+lock. This works well even under UP also, so the code does _not_ need to
+worry about UP vs SMP issues: the spinlocks work correctly under both.
 
    NOTE! Implications of spin_locks for memory are further described in:
 
@@ -36,27 +26,7 @@ The above is usually pretty simple (you usually need and want only one
 spinlock for most things - using more than one spinlock can make things a
 lot more complex and even slower and is usually worth it only for
 sequences that you _know_ need to be split up: avoid it at all cost if you
-aren't sure). HOWEVER, it _does_ mean that if you have some code that does
-
-	cli();
-	.. critical section ..
-	sti();
-
-and another sequence that does
-
-	spin_lock_irqsave(flags);
-	.. critical section ..
-	spin_unlock_irqrestore(flags);
-
-then they are NOT mutually exclusive, and the critical regions can happen
-at the same time on two different CPU's. That's fine per se, but the
-critical regions had better be critical for different things (ie they
-can't stomp on each other).
-
-The above is a problem mainly if you end up mixing code - for example the
-routines in ll_rw_block() tend to use cli/sti to protect the atomicity of
-their actions, and if a driver uses spinlocks instead then you should
-think about issues like the above.
+aren't sure).
 
 This is really the only really hard part about spinlocks: once you start
 using spinlocks they tend to expand to areas you might not have noticed
@@ -120,11 +90,10 @@ Lesson 3: spinlocks revisited.
 
 The single spin-lock primitives above are by no means the only ones. They
 are the most safe ones, and the ones that work under all circumstances,
-but partly _because_ they are safe they are also fairly slow. They are
-much faster than a generic global cli/sti pair, but slower than they'd
-need to be, because they do have to disable interrupts (which is just a
-single instruction on a x86, but it's an expensive one - and on other
-architectures it can be worse).
+but partly _because_ they are safe they are also fairly slow. They are slower
+than they'd need to be, because they do have to disable interrupts
+(which is just a single instruction on a x86, but it's an expensive one -
+and on other architectures it can be worse).
 
 If you have a case where you have to protect a data structure across
 several CPU's and you want to use spinlocks you can potentially use

Documentation/usb/error-codes.txt

@@ -76,6 +76,13 @@ A transfer's actual_length may be positive even when an error has been
 reported.  That's because transfers often involve several packets, so that
 one or more packets could finish before an error stops further endpoint I/O.
 
+For isochronous URBs, the urb status value is non-zero only if the URB is
+unlinked, the device is removed, the host controller is disabled, or the total
+transferred length is less than the requested length and the URB_SHORT_NOT_OK
+flag is set.  Completion handlers for isochronous URBs should only see
+urb->status set to zero, -ENOENT, -ECONNRESET, -ESHUTDOWN, or -EREMOTEIO.
+Individual frame descriptor status fields may report more status codes.
+
 
 0			Transfer completed successfully
 
@@ -132,7 +139,7 @@ one or more packets could finish before an error stops further endpoint I/O.
 			device removal events immediately.
 
 -EXDEV			ISO transfer only partially completed
-			look at individual frame status for details
+			(only set in iso_frame_desc[n].status, not urb->status)
 
 -EINVAL			ISO madness, if this happens: Log off and go home
 

Documentation/x86/boot.txt

@@ -674,7 +674,7 @@ Protocol:	2.10+
 
 Field name:	init_size
 Type:		read
-Offset/size:	0x25c/4
+Offset/size:	0x260/4
 
   This field indicates the amount of linear contiguous memory starting
   at the kernel runtime start address that the kernel needs before it

MAINTAINERS

@@ -594,6 +594,16 @@ S:	Maintained
 F:	arch/arm/lib/floppydma.S
 F:	arch/arm/include/asm/floppy.h
 
+ARM PMU PROFILING AND DEBUGGING
+M:	Will Deacon <will.deacon@arm.com>
+S:	Maintained
+F:	arch/arm/kernel/perf_event*
+F:	arch/arm/oprofile/common.c
+F:	arch/arm/kernel/pmu.c
+F:	arch/arm/include/asm/pmu.h
+F:	arch/arm/kernel/hw_breakpoint.c
+F:	arch/arm/include/asm/hw_breakpoint.h
+
 ARM PORT
 M:	Russell King <linux@arm.linux.org.uk>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1345,16 +1355,18 @@ F:	drivers/auxdisplay/
 F:	include/linux/cfag12864b.h
 
 AVR32 ARCHITECTURE
-M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
+M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
+M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
 W:	http://www.atmel.com/products/AVR32/
 W:	http://avr32linux.org/
 W:	http://avrfreaks.net/
-S:	Supported
+S:	Maintained
 F:	arch/avr32/
 
 AVR32/AT32AP MACHINE SUPPORT
-M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
-S:	Supported
+M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
+M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
+S:	Maintained
 F:	arch/avr32/mach-at32ap/
 
 AX.25 NETWORK LAYER
@@ -1390,7 +1402,6 @@ F:	include/linux/backlight.h
 BATMAN ADVANCED
 M:	Marek Lindner <lindner_marek@yahoo.de>
 M:	Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
-M:	Sven Eckelmann <sven@narfation.org>
 L:	b.a.t.m.a.n@lists.open-mesh.org
 W:	http://www.open-mesh.org/
 S:	Maintained
@@ -1423,7 +1434,6 @@ S:	Supported
 F:	arch/blackfin/
 
 BLACKFIN EMAC DRIVER
-M:	Michael Hennerich <michael.hennerich@analog.com>
 L:	uclinux-dist-devel@blackfin.uclinux.org
 W:	http://blackfin.uclinux.org
 S:	Supported
@@ -1639,7 +1649,7 @@ CAN NETWORK LAYER
 M:	Oliver Hartkopp <socketcan@hartkopp.net>
 M:	Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
 M:	Urs Thuermann <urs.thuermann@volkswagen.de>
-L:	socketcan-core@lists.berlios.de
+L:	socketcan-core@lists.berlios.de (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://developer.berlios.de/projects/socketcan/
 S:	Maintained
@@ -1651,7 +1661,7 @@ F:	include/linux/can/raw.h
 
 CAN NETWORK DRIVERS
 M:	Wolfgang Grandegger <wg@grandegger.com>
-L:	socketcan-core@lists.berlios.de
+L:	socketcan-core@lists.berlios.de (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://developer.berlios.de/projects/socketcan/
 S:	Maintained
@@ -2197,7 +2207,7 @@ F:	drivers/acpi/dock.c
 DOCUMENTATION
 M:	Randy Dunlap <rdunlap@xenotime.net>
 L:	linux-doc@vger.kernel.org
-T:	quilt oss.oracle.com/~rdunlap/kernel-doc-patches/current/
+T:	quilt http://userweb.kernel.org/~rdunlap/kernel-doc-patches/current/
 S:	Maintained
 F:	Documentation/
 
@@ -2291,8 +2301,7 @@ F:	drivers/scsi/eata_pio.*
 
 EBTABLES
 M:	Bart De Schuymer <bart.de.schuymer@pandora.be>
-L:	ebtables-user@lists.sourceforge.net
-L:	ebtables-devel@lists.sourceforge.net
+L:	netfilter-devel@vger.kernel.org
 W:	http://ebtables.sourceforge.net/
 S:	Maintained
 F:	include/linux/netfilter_bridge/ebt_*.h
@@ -4983,7 +4992,7 @@ F:	drivers/power/power_supply*
 
 PNP SUPPORT
 M:	Adam Belay <abelay@mit.edu>
-M:	Bjorn Helgaas <bjorn.helgaas@hp.com>
+M:	Bjorn Helgaas <bhelgaas@google.com>
 S:	Maintained
 F:	drivers/pnp/
 
@@ -5182,6 +5191,7 @@ S:	Supported
 F:	drivers/net/qlcnic/
 
 QLOGIC QLGE 10Gb ETHERNET DRIVER
+M:	Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
 M:	Ron Mercer <ron.mercer@qlogic.com>
 M:	linux-driver@qlogic.com
 L:	netdev@vger.kernel.org
@@ -6435,8 +6445,9 @@ S:	Maintained
 F:	drivers/usb/misc/rio500*
 
 USB EHCI DRIVER
+M:	Alan Stern <stern@rowland.harvard.edu>
 L:	linux-usb@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	Documentation/usb/ehci.txt
 F:	drivers/usb/host/ehci*
 
@@ -6463,9 +6474,15 @@ M:	Jiri Kosina <jkosina@suse.cz>
 L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
-F:	Documentation/usb/hiddev.txt
+F:	Documentation/hid/hiddev.txt
 F:	drivers/hid/usbhid/
 
+USB/IP DRIVERS
+M:	Matt Mooney <mfm@muteddisk.com>
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	drivers/staging/usbip/
+
 USB ISP116X DRIVER
 M:	Olav Kongas <ok@artecdesign.ee>
 L:	linux-usb@vger.kernel.org
@@ -6495,8 +6512,9 @@ S:	Maintained
 F:	sound/usb/midi.*
 
 USB OHCI DRIVER
+M:	Alan Stern <stern@rowland.harvard.edu>
 L:	linux-usb@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
@@ -6725,6 +6743,7 @@ F:	fs/fat/
 VIDEOBUF2 FRAMEWORK
 M:	Pawel Osciak <pawel@osciak.com>
 M:	Marek Szyprowski <m.szyprowski@samsung.com>
+M:	Kyungmin Park <kyungmin.park@samsung.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/video/videobuf2-*
@@ -7007,6 +7026,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.
 S:	Maintained
 F:	drivers/platform/x86
 
+X86 MCE INFRASTRUCTURE
+M:	Tony Luck <tony.luck@intel.com>
+M:	Borislav Petkov <bp@amd64.org>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	arch/x86/kernel/cpu/mcheck/*
+
 XEN HYPERVISOR INTERFACE
 M:	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc7
 NAME = Sneaky Weasel
 
 # *DOCUMENTATION*

README

@@ -1,6 +1,6 @@
-	Linux kernel release 2.6.xx <http://kernel.org/>
+	Linux kernel release 3.x <http://kernel.org/>
 
-These are the release notes for Linux version 2.6.  Read them carefully,
+These are the release notes for Linux version 3.  Read them carefully,
 as they tell you what this is all about, explain how to install the
 kernel, and what to do if something goes wrong. 
 
@@ -62,10 +62,10 @@ INSTALLING the kernel source:
    directory where you have permissions (eg. your home directory) and
    unpack it:
 
-		gzip -cd linux-2.6.XX.tar.gz | tar xvf -
+		gzip -cd linux-3.X.tar.gz | tar xvf -
 
    or
-		bzip2 -dc linux-2.6.XX.tar.bz2 | tar xvf -
+		bzip2 -dc linux-3.X.tar.bz2 | tar xvf -
 
 
    Replace "XX" with the version number of the latest kernel.
@@ -75,15 +75,15 @@ INSTALLING the kernel source:
    files.  They should match the library, and not get messed up by
    whatever the kernel-du-jour happens to be.
 
- - You can also upgrade between 2.6.xx releases by patching.  Patches are
+ - You can also upgrade between 3.x releases by patching.  Patches are
    distributed in the traditional gzip and the newer bzip2 format.  To
    install by patching, get all the newer patch files, enter the
-   top level directory of the kernel source (linux-2.6.xx) and execute:
+   top level directory of the kernel source (linux-3.x) and execute:
 
-		gzip -cd ../patch-2.6.xx.gz | patch -p1
+		gzip -cd ../patch-3.x.gz | patch -p1
 
    or
-		bzip2 -dc ../patch-2.6.xx.bz2 | patch -p1
+		bzip2 -dc ../patch-3.x.bz2 | patch -p1
 
    (repeat xx for all versions bigger than the version of your current
    source tree, _in_order_) and you should be ok.  You may want to remove
@@ -91,9 +91,9 @@ INSTALLING the kernel source:
    failed patches (xxx# or xxx.rej). If there are, either you or me has
    made a mistake.
 
-   Unlike patches for the 2.6.x kernels, patches for the 2.6.x.y kernels
+   Unlike patches for the 3.x kernels, patches for the 3.x.y kernels
    (also known as the -stable kernels) are not incremental but instead apply
-   directly to the base 2.6.x kernel.  Please read
+   directly to the base 3.x kernel.  Please read
    Documentation/applying-patches.txt for more information.
 
    Alternatively, the script patch-kernel can be used to automate this
@@ -107,14 +107,14 @@ INSTALLING the kernel source:
    an alternative directory can be specified as the second argument.
 
  - If you are upgrading between releases using the stable series patches
-   (for example, patch-2.6.xx.y), note that these "dot-releases" are
-   not incremental and must be applied to the 2.6.xx base tree. For
-   example, if your base kernel is 2.6.12 and you want to apply the
-   2.6.12.3 patch, you do not and indeed must not first apply the
-   2.6.12.1 and 2.6.12.2 patches. Similarly, if you are running kernel
-   version 2.6.12.2 and want to jump to 2.6.12.3, you must first
-   reverse the 2.6.12.2 patch (that is, patch -R) _before_ applying
-   the 2.6.12.3 patch.
+   (for example, patch-3.x.y), note that these "dot-releases" are
+   not incremental and must be applied to the 3.x base tree. For
+   example, if your base kernel is 3.0 and you want to apply the
+   3.0.3 patch, you do not and indeed must not first apply the
+   3.0.1 and 3.0.2 patches. Similarly, if you are running kernel
+   version 3.0.2 and want to jump to 3.0.3, you must first
+   reverse the 3.0.2 patch (that is, patch -R) _before_ applying
+   the 3.0.3 patch.
    You can read more on this in Documentation/applying-patches.txt
 
  - Make sure you have no stale .o files and dependencies lying around:
@@ -126,7 +126,7 @@ INSTALLING the kernel source:
 
 SOFTWARE REQUIREMENTS
 
-   Compiling and running the 2.6.xx kernels requires up-to-date
+   Compiling and running the 3.x kernels requires up-to-date
    versions of various software packages.  Consult
    Documentation/Changes for the minimum version numbers required
    and how to get updates for these packages.  Beware that using
@@ -142,11 +142,11 @@ BUILD directory for the kernel:
    Using the option "make O=output/dir" allow you to specify an alternate
    place for the output files (including .config).
    Example:
-     kernel source code:	/usr/src/linux-2.6.N
+     kernel source code:	/usr/src/linux-3.N
      build directory:		/home/name/build/kernel
 
    To configure and build the kernel use:
-   cd /usr/src/linux-2.6.N
+   cd /usr/src/linux-3.N
    make O=/home/name/build/kernel menuconfig
    make O=/home/name/build/kernel
    sudo make O=/home/name/build/kernel modules_install install

arch/alpha/include/asm/mmzone.h

@@ -56,7 +56,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
  * Given a kernel address, find the home node of the underlying memory.
  */
 #define kvaddr_to_nid(kaddr)	pa_to_nid(__pa(kaddr))
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 
 /*
  * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory

arch/arm/Kconfig

@@ -37,6 +37,9 @@ config ARM
 	  Europe.  There is an ARM Linux project with a web page at
 	  <http://www.arm.linux.org.uk/>.
 
+config ARM_HAS_SG_CHAIN
+	bool
+
 config HAVE_PWM
 	bool
 
@@ -1346,7 +1349,6 @@ config SMP_ON_UP
 
 config HAVE_ARM_SCU
 	bool
-	depends on SMP
 	help
 	  This option enables support for the ARM system coherency unit
 
@@ -1715,17 +1717,34 @@ config ZBOOT_ROM
 	  Say Y here if you intend to execute your compressed kernel image
 	  (zImage) directly from ROM or flash.  If unsure, say N.
 
+choice
+	prompt "Include SD/MMC loader in zImage (EXPERIMENTAL)"
+	depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
+	default ZBOOT_ROM_NONE
+	help
+	  Include experimental SD/MMC loading code in the ROM-able zImage.
+	  With this enabled it is possible to write the the ROM-able zImage
+	  kernel image to an MMC or SD card and boot the kernel straight
+	  from the reset vector. At reset the processor Mask ROM will load
+	  the first part of the the ROM-able zImage which in turn loads the
+	  rest the kernel image to RAM.
+
+config ZBOOT_ROM_NONE
+	bool "No SD/MMC loader in zImage (EXPERIMENTAL)"
+	help
+	  Do not load image from SD or MMC
+
 config ZBOOT_ROM_MMCIF
 	bool "Include MMCIF loader in zImage (EXPERIMENTAL)"
-	depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
 	help
-	  Say Y here to include experimental MMCIF loading code in the
-	  ROM-able zImage. With this enabled it is possible to write the
-	  the ROM-able zImage kernel image to an MMC card and boot the
-	  kernel straight from the reset vector. At reset the processor
-	  Mask ROM will load the first part of the the ROM-able zImage
-	  which in turn loads the rest the kernel image to RAM using the
-	  MMCIF hardware block.
+	  Load image from MMCIF hardware block.
+
+config ZBOOT_ROM_SH_MOBILE_SDHI
+	bool "Include SuperH Mobile SDHI loader in zImage (EXPERIMENTAL)"
+	help
+	  Load image from SDHI hardware block
+
+endchoice
 
 config CMDLINE
 	string "Default kernel command string"

arch/arm/boot/compressed/Makefile

@@ -6,13 +6,19 @@
 
 OBJS		=
 
-# Ensure that mmcif loader code appears early in the image
+# Ensure that MMCIF loader code appears early in the image
 # to minimise that number of bocks that have to be read in
 # order to load it.
 ifeq ($(CONFIG_ZBOOT_ROM_MMCIF),y)
-ifeq ($(CONFIG_ARCH_SH7372),y)
 OBJS		+= mmcif-sh7372.o
 endif
+
+# Ensure that SDHI loader code appears early in the image
+# to minimise that number of bocks that have to be read in
+# order to load it.
+ifeq ($(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI),y)
+OBJS		+= sdhi-shmobile.o
+OBJS		+= sdhi-sh7372.o
 endif
 
 AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)

arch/arm/boot/compressed/head-shmobile.S

@@ -25,14 +25,14 @@
 	/* load board-specific initialization code */
 #include <mach/zboot.h>
 
-#ifdef CONFIG_ZBOOT_ROM_MMCIF
-	/* Load image from MMC */
-	adr	sp, __tmp_stack + 128
+#if defined(CONFIG_ZBOOT_ROM_MMCIF) || defined(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI)
+	/* Load image from MMC/SD */
+	adr	sp, __tmp_stack + 256
 	ldr	r0, __image_start
 	ldr	r1, __image_end
 	subs	r1, r1, r0
 	ldr	r0, __load_base
-	bl	mmcif_loader
+	bl	mmc_loader
 
 	/* Jump to loaded code */
 	ldr	r0, __loaded
@@ -51,9 +51,9 @@ __loaded:
 	.long	__continue
 	.align
 __tmp_stack:
-	.space	128
+	.space	256
 __continue:
-#endif /* CONFIG_ZBOOT_ROM_MMCIF */
+#endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */
 
 	b	1f
 __atags:@ tag #1

arch/arm/boot/compressed/head.S

@@ -353,7 +353,8 @@ not_relocated:	mov	r0, #0
 		mov	r0, #0			@ must be zero
 		mov	r1, r7			@ restore architecture number
 		mov	r2, r8			@ restore atags pointer
-		mov	pc, r4			@ call kernel
+ ARM(		mov	pc, r4	)		@ call kernel
+ THUMB(		bx	r4	)		@ entry point is always ARM
 
 		.align	2
 		.type	LC0, #object
@@ -597,6 +598,8 @@ __common_mmu_cache_on:
 		sub	pc, lr, r0, lsr #32	@ properly flush pipeline
 #endif
 
+#define PROC_ENTRY_SIZE (4*5)
+
 /*
  * Here follow the relocatable cache support functions for the
  * various processors.  This is a generic hook for locating an
@@ -624,7 +627,7 @@ call_cache_fn:	adr	r12, proc_types
  ARM(		addeq	pc, r12, r3		) @ call cache function
  THUMB(		addeq	r12, r3			)
  THUMB(		moveq	pc, r12			) @ call cache function
-		add	r12, r12, #4*5
+		add	r12, r12, #PROC_ENTRY_SIZE
 		b	1b
 
 /*
@@ -794,6 +797,16 @@ proc_types:
 
 		.size	proc_types, . - proc_types
 
+		/*
+		 * If you get a "non-constant expression in ".if" statement"
+		 * error from the assembler on this line, check that you have
+		 * not accidentally written a "b" instruction where you should
+		 * have written W(b).
+		 */
+		.if (. - proc_types) % PROC_ENTRY_SIZE != 0
+		.error "The size of one or more proc_types entries is wrong."
+		.endif
+
 /*
  * Turn off the Cache and MMU.  ARMv3 does not support
  * reading the control register, but ARMv4 does.

arch/arm/boot/compressed/mmcif-sh7372.c

@@ -40,7 +40,7 @@
  * to an MMC card
  * # dd if=vrl4.out of=/dev/sdx bs=512 seek=1
  */
-asmlinkage void mmcif_loader(unsigned char *buf, unsigned long len)
+asmlinkage void mmc_loader(unsigned char *buf, unsigned long len)
 {
 	mmc_init_progress();
 	mmc_update_progress(MMC_PROGRESS_ENTER);

arch/arm/boot/compressed/sdhi-sh7372.c

@@ -0,0 +1,95 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <mach/mmc.h>
+#include <linux/mmc/boot.h>
+#include <linux/mmc/tmio.h>
+
+#include "sdhi-shmobile.h"
+
+#define PORT179CR       0xe60520b3
+#define PORT180CR       0xe60520b4
+#define PORT181CR       0xe60520b5
+#define PORT182CR       0xe60520b6
+#define PORT183CR       0xe60520b7
+#define PORT184CR       0xe60520b8
+
+#define SMSTPCR3        0xe615013c
+
+#define CR_INPUT_ENABLE 0x10
+#define CR_FUNCTION1    0x01
+
+#define SDHI1_BASE	(void __iomem *)0xe6860000
+#define SDHI_BASE	SDHI1_BASE
+
+/*  SuperH Mobile SDHI loader
+ *
+ * loads the zImage from an SD card starting from block 0
+ * on physical partition 1
+ *
+ * The image must be start with a vrl4 header and
+ * the zImage must start at offset 512 of the image. That is,
+ * at block 1 (=byte 512) of physical partition 1
+ *
+ * Use the following line to write the vrl4 formated zImage
+ * to an SD card
+ * # dd if=vrl4.out of=/dev/sdx bs=512
+ */
+asmlinkage void mmc_loader(unsigned short *buf, unsigned long len)
+{
+	int high_capacity;
+
+	mmc_init_progress();
+
+	mmc_update_progress(MMC_PROGRESS_ENTER);
+        /* Initialise SDHI1 */
+        /* PORT184CR: GPIO_FN_SDHICMD1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT184CR);
+        /* PORT179CR: GPIO_FN_SDHICLK1 Control */
+        __raw_writeb(CR_INPUT_ENABLE|CR_FUNCTION1, PORT179CR);
+        /* PORT181CR: GPIO_FN_SDHID1_3 Control */
+        __raw_writeb(CR_FUNCTION1, PORT183CR);
+        /* PORT182CR: GPIO_FN_SDHID1_2 Control */
+        __raw_writeb(CR_FUNCTION1, PORT182CR);
+        /* PORT183CR: GPIO_FN_SDHID1_1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT181CR);
+        /* PORT180CR: GPIO_FN_SDHID1_0 Control */
+        __raw_writeb(CR_FUNCTION1, PORT180CR);
+
+        /* Enable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 13), SMSTPCR3);
+
+	/* setup SDHI hardware */
+	mmc_update_progress(MMC_PROGRESS_INIT);
+	high_capacity = sdhi_boot_init(SDHI_BASE);
+	if (high_capacity < 0)
+		goto err;
+
+	mmc_update_progress(MMC_PROGRESS_LOAD);
+	/* load kernel */
+	if (sdhi_boot_do_read(SDHI_BASE, high_capacity,
+			      0, /* Kernel is at block 1 */
+			      (len + TMIO_BBS - 1) / TMIO_BBS, buf))
+		goto err;
+
+        /* Disable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3);
+
+	mmc_update_progress(MMC_PROGRESS_DONE);
+
+	return;
+err:
+	for(;;);
+}

arch/arm/boot/compressed/sdhi-shmobile.c

@@ -0,0 +1,449 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/tmio.h>
+#include <mach/sdhi.h>
+
+#define OCR_FASTBOOT		(1<<29)
+#define OCR_HCS			(1<<30)
+#define OCR_BUSY		(1<<31)
+
+#define RESP_CMD12		0x00000030
+
+static inline u16 sd_ctrl_read16(void __iomem *base, int addr)
+{
+        return __raw_readw(base + addr);
+}
+
+static inline u32 sd_ctrl_read32(void __iomem *base, int addr)
+{
+	return __raw_readw(base + addr) |
+	       __raw_readw(base + addr + 2) << 16;
+}
+
+static inline void sd_ctrl_write16(void __iomem *base, int addr, u16 val)
+{
+	__raw_writew(val, base + addr);
+}
+
+static inline void sd_ctrl_write32(void __iomem *base, int addr, u32 val)
+{
+	__raw_writew(val, base + addr);
+	__raw_writew(val >> 16, base + addr + 2);
+}
+
+#define ALL_ERROR (TMIO_STAT_CMD_IDX_ERR | TMIO_STAT_CRCFAIL |		\
+		   TMIO_STAT_STOPBIT_ERR | TMIO_STAT_DATATIMEOUT |	\
+		   TMIO_STAT_RXOVERFLOW | TMIO_STAT_TXUNDERRUN |	\
+		   TMIO_STAT_CMDTIMEOUT | TMIO_STAT_ILL_ACCESS |	\
+		   TMIO_STAT_ILL_FUNC)
+
+static int sdhi_intr(void __iomem *base)
+{
+	unsigned long state = sd_ctrl_read32(base, CTL_STATUS);
+
+	if (state & ALL_ERROR) {
+		sd_ctrl_write32(base, CTL_STATUS, ~ALL_ERROR);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				ALL_ERROR |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return -EINVAL;
+	}
+	if (state & TMIO_STAT_CMDRESPEND) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_CMDRESPEND |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+	if (state & TMIO_STAT_RXRDY) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_RXRDY);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_RXRDY | TMIO_STAT_TXUNDERRUN |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+	if (state & TMIO_STAT_DATAEND) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_DATAEND);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_DATAEND |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+
+	return -EAGAIN;
+}
+
+static int sdhi_boot_wait_resp_end(void __iomem *base)
+{
+	int err = -EAGAIN, timeout = 10000000;
+
+	while (timeout--) {
+		err = sdhi_intr(base);
+		if (err != -EAGAIN)
+			break;
+		udelay(1);
+	}
+
+	return err;
+}
+
+/* SDHI_CLK_CTRL */
+#define CLK_MMC_ENABLE                 (1 << 8)
+#define CLK_MMC_INIT                   (1 << 6)        /* clk / 256 */
+
+static void sdhi_boot_mmc_clk_stop(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, 0x0000);
+	msleep(10);
+	sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, ~CLK_MMC_ENABLE &
+		sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+	msleep(10);
+}
+
+static void sdhi_boot_mmc_clk_start(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, CLK_MMC_ENABLE |
+		sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+	msleep(10);
+	sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, CLK_MMC_ENABLE);
+	msleep(10);
+}
+
+static void sdhi_boot_reset(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_RESET_SD, 0x0000);
+	msleep(10);
+	sd_ctrl_write16(base, CTL_RESET_SD, 0x0001);
+	msleep(10);
+}
+
+/* Set MMC clock / power.
+ * Note: This controller uses a simple divider scheme therefore it cannot
+ * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
+ * MMC wont run that fast, it has to be clocked at 12MHz which is the next
+ * slowest setting.
+ */
+static int sdhi_boot_mmc_set_ios(void __iomem *base, struct mmc_ios *ios)
+{
+	if (sd_ctrl_read32(base, CTL_STATUS) & TMIO_STAT_CMD_BUSY)
+		return -EBUSY;
+
+	if (ios->clock)
+		sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL,
+				ios->clock | CLK_MMC_ENABLE);
+
+	/* Power sequence - OFF -> ON -> UP */
+	switch (ios->power_mode) {
+	case MMC_POWER_OFF: /* power down SD bus */
+		sdhi_boot_mmc_clk_stop(base);
+		break;
+	case MMC_POWER_ON: /* power up SD bus */
+		break;
+	case MMC_POWER_UP: /* start bus clock */
+		sdhi_boot_mmc_clk_start(base);
+		break;
+	}
+
+	switch (ios->bus_width) {
+	case MMC_BUS_WIDTH_1:
+		sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x80e0);
+	break;
+	case MMC_BUS_WIDTH_4:
+		sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x00e0);
+	break;
+	}
+
+	/* Let things settle. delay taken from winCE driver */
+	udelay(140);
+
+	return 0;
+}
+
+/* These are the bitmasks the tmio chip requires to implement the MMC response
+ * types. Note that R1 and R6 are the same in this scheme. */
+#define RESP_NONE      0x0300
+#define RESP_R1        0x0400
+#define RESP_R1B       0x0500
+#define RESP_R2        0x0600
+#define RESP_R3        0x0700
+#define DATA_PRESENT   0x0800
+#define TRANSFER_READ  0x1000
+
+static int sdhi_boot_request(void __iomem *base, struct mmc_command *cmd)
+{
+	int err, c = cmd->opcode;
+
+	switch (mmc_resp_type(cmd)) {
+	case MMC_RSP_NONE: c |= RESP_NONE; break;
+	case MMC_RSP_R1:   c |= RESP_R1;   break;
+	case MMC_RSP_R1B:  c |= RESP_R1B;  break;
+	case MMC_RSP_R2:   c |= RESP_R2;   break;
+	case MMC_RSP_R3:   c |= RESP_R3;   break;
+	default:
+		return -EINVAL;
+	}
+
+	/* No interrupts so this may not be cleared */
+	sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK, TMIO_STAT_CMDRESPEND |
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+	sd_ctrl_write32(base, CTL_ARG_REG, cmd->arg);
+	sd_ctrl_write16(base, CTL_SD_CMD, c);
+
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK,
+			~(TMIO_STAT_CMDRESPEND | ALL_ERROR) &
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	cmd->resp[0] = sd_ctrl_read32(base, CTL_RESPONSE);
+
+	return 0;
+}
+
+static int sdhi_boot_do_read_single(void __iomem *base, int high_capacity,
+				    unsigned long block, unsigned short *buf)
+{
+	int err, i;
+
+	/* CMD17 - Read */
+	{
+		struct mmc_command cmd;
+
+		cmd.opcode = MMC_READ_SINGLE_BLOCK | \
+			     TRANSFER_READ | DATA_PRESENT;
+		if (high_capacity)
+			cmd.arg = block;
+		else
+			cmd.arg = block * TMIO_BBS;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK,
+			~(TMIO_STAT_DATAEND | TMIO_STAT_RXRDY |
+			  TMIO_STAT_TXUNDERRUN) &
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	sd_ctrl_write16(base, CTL_SD_XFER_LEN, TMIO_BBS);
+	for (i = 0; i < TMIO_BBS / sizeof(*buf); i++)
+		*buf++ = sd_ctrl_read16(base, RESP_CMD12);
+
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+		      unsigned long offset, unsigned short count,
+		      unsigned short *buf)
+{
+	unsigned long i;
+	int err = 0;
+
+	for (i = 0; i < count; i++) {
+		err = sdhi_boot_do_read_single(base, high_capacity, offset + i,
+					       buf + (i * TMIO_BBS /
+						      sizeof(*buf)));
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+#define VOLTAGES (MMC_VDD_32_33 | MMC_VDD_33_34)
+
+int sdhi_boot_init(void __iomem *base)
+{
+	bool sd_v2 = false, sd_v1_0 = false;
+	unsigned short cid;
+	int err, high_capacity = 0;
+
+	sdhi_boot_mmc_clk_stop(base);
+	sdhi_boot_reset(base);
+
+	/* mmc0: clock 400000Hz busmode 1 powermode 2 cs 0 Vdd 21 width 0 timing 0 */
+	{
+		struct mmc_ios ios;
+		ios.power_mode = MMC_POWER_ON;
+		ios.bus_width = MMC_BUS_WIDTH_1;
+		ios.clock = CLK_MMC_INIT;
+		err = sdhi_boot_mmc_set_ios(base, &ios);
+		if (err)
+			return err;
+	}
+
+	/* CMD0 */
+	{
+		struct mmc_command cmd;
+		msleep(1);
+		cmd.opcode = MMC_GO_IDLE_STATE;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_NONE;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+		msleep(2);
+	}
+
+	/* CMD8 - Test for SD version 2 */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = SD_SEND_IF_COND;
+		cmd.arg = (VOLTAGES != 0) << 8 | 0xaa;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd); /* Ignore error */
+		if ((cmd.resp[0] & 0xff) == 0xaa)
+			sd_v2 = true;
+	}
+
+	/* CMD55 - Get OCR (SD) */
+	{
+		int timeout = 1000;
+		struct mmc_command cmd;
+
+		cmd.arg = 0;
+
+		do {
+			cmd.opcode = MMC_APP_CMD;
+			cmd.flags = MMC_RSP_R1;
+			cmd.arg = 0;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				break;
+
+			cmd.opcode = SD_APP_OP_COND;
+			cmd.flags = MMC_RSP_R3;
+			cmd.arg = (VOLTAGES & 0xff8000);
+			if (sd_v2)
+				cmd.arg |= OCR_HCS;
+			cmd.arg |= OCR_FASTBOOT;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				break;
+
+			msleep(1);
+		} while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+		if (!err && timeout) {
+			if (!sd_v2)
+				sd_v1_0 = true;
+			high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+		}
+	}
+
+	/* CMD1 - Get OCR (MMC) */
+	if (!sd_v2 && !sd_v1_0) {
+		int timeout = 1000;
+		struct mmc_command cmd;
+
+		do {
+			cmd.opcode = MMC_SEND_OP_COND;
+			cmd.arg = VOLTAGES | OCR_HCS;
+			cmd.flags = MMC_RSP_R3;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				return err;
+
+			msleep(1);
+		} while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+		if (!timeout)
+			return -EAGAIN;
+
+		high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+	}
+
+	/* CMD2 - Get CID */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_ALL_SEND_CID;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_R2;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD3
+	 * MMC: Set the relative address
+	 * SD:  Get the relative address
+	 * Also puts the card into the standby state
+	 */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SET_RELATIVE_ADDR;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+		cid = cmd.resp[0] >> 16;
+	}
+
+	/* CMD9 - Get CSD */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SEND_CSD;
+		cmd.arg = cid << 16;
+		cmd.flags = MMC_RSP_R2;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD7 - Select the card */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SELECT_CARD;
+		//cmd.arg = rca << 16;
+		cmd.arg = cid << 16;
+		//cmd.flags = MMC_RSP_R1B;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD16 - Set the block size */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SET_BLOCKLEN;
+		cmd.arg = TMIO_BBS;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	return high_capacity;
+}

arch/arm/boot/compressed/sdhi-shmobile.h

@@ -0,0 +1,11 @@
+#ifndef SDHI_MOBILE_H
+#define SDHI_MOBILE_H
+
+#include <linux/compiler.h>
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+		      unsigned long offset, unsigned short count,
+		      unsigned short *buf);
+int sdhi_boot_init(void __iomem *base);
+
+#endif

arch/arm/boot/compressed/vmlinux.lds.in

@@ -33,20 +33,24 @@ SECTIONS
     *(.text.*)
     *(.fixup)
     *(.gnu.warning)
+    *(.glue_7t)
+    *(.glue_7)
+  }
+  .rodata : {
     *(.rodata)
     *(.rodata.*)
-    *(.glue_7)
-    *(.glue_7t)
+  }
+  .piggydata : {
     *(.piggydata)
-    . = ALIGN(4);
   }
 
+  . = ALIGN(4);
   _etext = .;
 
+  .got.plt		: { *(.got.plt) }
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
-  .got.plt		: { *(.got.plt) }
   _edata = .;
 
   . = BSS_START;

arch/arm/common/dmabounce.c

@@ -79,6 +79,8 @@ struct dmabounce_device_info {
 	struct dmabounce_pool	large;
 
 	rwlock_t lock;
+
+	int (*needs_bounce)(struct device *, dma_addr_t, size_t);
 };
 
 #ifdef STATS
@@ -210,114 +212,91 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
 	if (!dev || !dev->archdata.dmabounce)
 		return NULL;
 	if (dma_mapping_error(dev, dma_addr)) {
-		if (dev)
-			dev_err(dev, "Trying to %s invalid mapping\n", where);
-		else
-			pr_err("unknown device: Trying to %s invalid mapping\n", where);
+		dev_err(dev, "Trying to %s invalid mapping\n", where);
 		return NULL;
 	}
 	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
 }
 
-static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
+static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	dma_addr_t dma_addr;
-	int needs_bounce = 0;
-
-	if (device_info)
-		DO_STATS ( device_info->map_op_count++ );
-
-	dma_addr = virt_to_dma(dev, ptr);
+	if (!dev || !dev->archdata.dmabounce)
+		return 0;
 
 	if (dev->dma_mask) {
-		unsigned long mask = *dev->dma_mask;
-		unsigned long limit;
+		unsigned long limit, mask = *dev->dma_mask;
 
 		limit = (mask + 1) & ~mask;
 		if (limit && size > limit) {
 			dev_err(dev, "DMA mapping too big (requested %#x "
 				"mask %#Lx)\n", size, *dev->dma_mask);
-			return ~0;
+			return -E2BIG;
 		}
 
-		/*
-		 * Figure out if we need to bounce from the DMA mask.
-		 */
-		needs_bounce = (dma_addr | (dma_addr + size - 1)) & ~mask;
+		/* Figure out if we need to bounce from the DMA mask. */
+		if ((dma_addr | (dma_addr + size - 1)) & ~mask)
+			return 1;
 	}
 
-	if (device_info && (needs_bounce || dma_needs_bounce(dev, dma_addr, size))) {
-		struct safe_buffer *buf;
+	return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
+}
 
-		buf = alloc_safe_buffer(device_info, ptr, size, dir);
-		if (buf == 0) {
-			dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
-			       __func__, ptr);
-			return 0;
-		}
+static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
+	struct safe_buffer *buf;
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	if (device_info)
+		DO_STATS ( device_info->map_op_count++ );
 
-		if ((dir == DMA_TO_DEVICE) ||
-		    (dir == DMA_BIDIRECTIONAL)) {
-			dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
-				__func__, ptr, buf->safe, size);
-			memcpy(buf->safe, ptr, size);
-		}
-		ptr = buf->safe;
+	buf = alloc_safe_buffer(device_info, ptr, size, dir);
+	if (buf == NULL) {
+		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
+		       __func__, ptr);
+		return ~0;
+	}
 
-		dma_addr = buf->safe_dma_addr;
-	} else {
-		/*
-		 * We don't need to sync the DMA buffer since
-		 * it was allocated via the coherent allocators.
-		 */
-		__dma_single_cpu_to_dev(ptr, size, dir);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
+
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
+			__func__, ptr, buf->safe, size);
+		memcpy(buf->safe, ptr, size);
 	}
 
-	return dma_addr;
+	return buf->safe_dma_addr;
 }
 
-static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
+static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
 		size_t size, enum dma_data_direction dir)
 {
-	struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap");
-
-	if (buf) {
-		BUG_ON(buf->size != size);
-		BUG_ON(buf->direction != dir);
+	BUG_ON(buf->size != size);
+	BUG_ON(buf->direction != dir);
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
 
-		DO_STATS(dev->archdata.dmabounce->bounce_count++);
+	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
-			void *ptr = buf->ptr;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		void *ptr = buf->ptr;
 
-			dev_dbg(dev,
-				"%s: copy back safe %p to unsafe %p size %d\n",
-				__func__, buf->safe, ptr, size);
-			memcpy(ptr, buf->safe, size);
+		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
+			__func__, buf->safe, ptr, size);
+		memcpy(ptr, buf->safe, size);
 
-			/*
-			 * Since we may have written to a page cache page,
-			 * we need to ensure that the data will be coherent
-			 * with user mappings.
-			 */
-			__cpuc_flush_dcache_area(ptr, size);
-		}
-		free_safe_buffer(dev->archdata.dmabounce, buf);
-	} else {
-		__dma_single_dev_to_cpu(dma_to_virt(dev, dma_addr), size, dir);
+		/*
+		 * Since we may have written to a page cache page,
+		 * we need to ensure that the data will be coherent
+		 * with user mappings.
+		 */
+		__cpuc_flush_dcache_area(ptr, size);
 	}
+	free_safe_buffer(dev->archdata.dmabounce, buf);
 }
 
 /* ************************************************** */
@@ -328,45 +307,28 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t __dma_map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, ptr, size, dir);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	return map_single(dev, ptr, size, dir);
-}
-EXPORT_SYMBOL(__dma_map_single);
-
-/*
- * see if a mapped address was really a "safe" buffer and if so, copy
- * the data from the safe buffer back to the unsafe buffer and free up
- * the safe buffer.  (basically return things back to the way they
- * should be)
- */
-void __dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
-
-	unmap_single(dev, dma_addr, size, dir);
-}
-EXPORT_SYMBOL(__dma_unmap_single);
-
 dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t dma_addr;
+	int ret;
+
 	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
 		__func__, page, offset, size, dir);
 
-	BUG_ON(!valid_dma_direction(dir));
+	dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;
+
+	ret = needs_bounce(dev, dma_addr, size);
+	if (ret < 0)
+		return ~0;
+
+	if (ret == 0) {
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+		return dma_addr;
+	}
 
 	if (PageHighMem(page)) {
-		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages "
-			     "is not supported\n");
+		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
 		return ~0;
 	}
 
@@ -383,10 +345,19 @@ EXPORT_SYMBOL(__dma_map_page);
 void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 		enum dma_data_direction dir)
 {
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
+	struct safe_buffer *buf;
+
+	dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
+		__func__, dma_addr, size, dir);
+
+	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
+	if (!buf) {
+		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)),
+			dma_addr & ~PAGE_MASK, size, dir);
+		return;
+	}
 
-	unmap_single(dev, dma_addr, size, dir);
+	unmap_single(dev, buf, size, dir);
 }
 EXPORT_SYMBOL(__dma_unmap_page);
 
@@ -461,7 +432,8 @@ static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
 }
 
 int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-		unsigned long large_buffer_size)
+		unsigned long large_buffer_size,
+		int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
 {
 	struct dmabounce_device_info *device_info;
 	int ret;
@@ -497,6 +469,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
 	device_info->dev = dev;
 	INIT_LIST_HEAD(&device_info->safe_buffers);
 	rwlock_init(&device_info->lock);
+	device_info->needs_bounce = needs_bounce_fn;
 
 #ifdef STATS
 	device_info->total_allocs = 0;

arch/arm/common/gic.c

@@ -179,22 +179,21 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
 	unsigned int shift = (d->irq % 4) * 8;
-	unsigned int cpu = cpumask_first(mask_val);
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
 	u32 val, mask, bit;
 
-	if (cpu >= 8)
+	if (cpu >= 8 || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	mask = 0xff << shift;
 	bit = 1 << (cpu + shift);
 
 	spin_lock(&irq_controller_lock);
-	d->node = cpu;
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	spin_unlock(&irq_controller_lock);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 #endif
 

arch/arm/common/it8152.c

@@ -243,6 +243,12 @@ static struct resource it8152_mem = {
  * ITE8152 chip can address up to 64MByte, so all the devices
  * connected to ITE8152 (PCI and USB) should have limited DMA window
  */
+static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+		__func__, dma_addr, size);
+	return (dma_addr + size - PHYS_OFFSET) >= SZ_64M;
+}
 
 /*
  * Setup DMA mask to 64MB on devices connected to ITE8152. Ignore all
@@ -254,7 +260,7 @@ static int it8152_pci_platform_notify(struct device *dev)
 		if (dev->dma_mask)
 			*dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
 		dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
-		dmabounce_register_dev(dev, 2048, 4096);
+		dmabounce_register_dev(dev, 2048, 4096, it8152_needs_bounce);
 	}
 	return 0;
 }
@@ -267,14 +273,6 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
 	return 0;
 }
 
-int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
-		__func__, dma_addr, size);
-	return (dev->bus == &pci_bus_type) &&
-		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
-}
-
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	if (mask >= PHYS_OFFSET + SZ_64M - 1)

arch/arm/common/sa1111.c

@@ -579,7 +579,36 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 
 	sachip->dev->coherent_dma_mask &= sa1111_dma_mask[drac >> 2];
 }
+#endif
 
+#ifdef CONFIG_DMABOUNCE
+/*
+ * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+ * Chip Specification Update" (June 2000), erratum #7, there is a
+ * significant bug in the SA1111 SDRAM shared memory controller.  If
+ * an access to a region of memory above 1MB relative to the bank base,
+ * it is important that address bit 10 _NOT_ be asserted. Depending
+ * on the configuration of the RAM, bit 10 may correspond to one
+ * of several different (processor-relative) address bits.
+ *
+ * This routine only identifies whether or not a given DMA address
+ * is susceptible to the bug.
+ *
+ * This should only get called for sa1111_device types due to the
+ * way we configure our device dma_masks.
+ */
+static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
+{
+	/*
+	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+	 * User's Guide" mentions that jumpers R51 and R52 control the
+	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+	 * SDRAM bank 1 on Neponset). The default configuration selects
+	 * Assabet, so any address in bank 1 is necessarily invalid.
+	 */
+	return (machine_is_assabet() || machine_is_pfs168()) &&
+		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
+}
 #endif
 
 static void sa1111_dev_release(struct device *_dev)
@@ -644,7 +673,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
 		dev->dev.dma_mask = &dev->dma_mask;
 
 		if (dev->dma_mask != 0xffffffffUL) {
-			ret = dmabounce_register_dev(&dev->dev, 1024, 4096);
+			ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
+					sa1111_needs_bounce);
 			if (ret) {
 				dev_err(&dev->dev, "SA1111: Failed to register"
 					" with dmabounce\n");
@@ -818,34 +848,6 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	kfree(sachip);
 }
 
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-int dma_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-	/*
-	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-	 * User's Guide" mentions that jumpers R51 and R52 control the
-	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-	 * SDRAM bank 1 on Neponset). The default configuration selects
-	 * Assabet, so any address in bank 1 is necessarily invalid.
-	 */
-	return ((machine_is_assabet() || machine_is_pfs168()) &&
-		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000));
-}
-
 struct sa1111_save_data {
 	unsigned int	skcr;
 	unsigned int	skpcr;

arch/arm/include/asm/assembler.h

@@ -13,6 +13,9 @@
  *  Do not include any C declarations in this file - it is included by
  *  assembler source.
  */
+#ifndef __ASM_ASSEMBLER_H__
+#define __ASM_ASSEMBLER_H__
+
 #ifndef __ASSEMBLY__
 #error "Only include this from assembly code"
 #endif
@@ -290,3 +293,4 @@
 	.macro	ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
 	usracc	ldr, \reg, \ptr, \inc, \cond, \rept, \abort
 	.endm
+#endif /* __ASM_ASSEMBLER_H__ */

arch/arm/include/asm/bitops.h

@@ -26,8 +26,8 @@
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-#define smp_mb__before_clear_bit()	mb()
-#define smp_mb__after_clear_bit()	mb()
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
 
 /*
  * These functions are the basis of our bit ops.

arch/arm/include/asm/dma-mapping.h

@@ -115,39 +115,8 @@ static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 		___dma_page_dev_to_cpu(page, off, size, dir);
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- *
- * FIXME: This should really be a platform specific issue - we should
- * return false if GFP_DMA allocations may not satisfy the supplied 'mask'.
- */
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	if (mask < ISA_DMA_THRESHOLD)
-		return 0;
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_DMABOUNCE
-	if (dev->archdata.dmabounce) {
-		if (dma_mask >= ISA_DMA_THRESHOLD)
-			return 0;
-		else
-			return -EIO;
-	}
-#endif
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
+extern int dma_supported(struct device *, u64);
+extern int dma_set_mask(struct device *, u64);
 
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
@@ -256,14 +225,14 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
  * @dev: valid struct device pointer
  * @small_buf_size: size of buffers to use with small buffer pool
  * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ * @needs_bounce_fn: called to determine whether buffer needs bouncing
  *
  * This function should be called by low-level platform code to register
  * a device as requireing DMA buffer bouncing. The function will allocate
  * appropriate DMA pools for the device.
- *
  */
 extern int dmabounce_register_dev(struct device *, unsigned long,
-		unsigned long);
+		unsigned long, int (*)(struct device *, dma_addr_t, size_t));
 
 /**
  * dmabounce_unregister_dev
@@ -277,31 +246,9 @@ extern int dmabounce_register_dev(struct device *, unsigned long,
  */
 extern void dmabounce_unregister_dev(struct device *);
 
-/**
- * dma_needs_bounce
- *
- * @dev: valid struct device pointer
- * @dma_handle: dma_handle of unbounced buffer
- * @size: size of region being mapped
- *
- * Platforms that utilize the dmabounce mechanism must implement
- * this function.
- *
- * The dmabounce routines call this function whenever a dma-mapping
- * is requested to determine whether a given buffer needs to be bounced
- * or not. The function must return 0 if the buffer is OK for
- * DMA access and 1 if the buffer needs to be bounced.
- *
- */
-extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.
  */
-extern dma_addr_t __dma_map_single(struct device *, void *, size_t,
-		enum dma_data_direction);
-extern void __dma_unmap_single(struct device *, dma_addr_t, size_t,
-		enum dma_data_direction);
 extern dma_addr_t __dma_map_page(struct device *, struct page *,
 		unsigned long, size_t, enum dma_data_direction);
 extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
@@ -328,13 +275,6 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 }
 
 
-static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_single_cpu_to_dev(cpu_addr, size, dir);
-	return virt_to_dma(dev, cpu_addr);
-}
-
 static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir)
 {
@@ -342,12 +282,6 @@ static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
 }
 
-static inline void __dma_unmap_single(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
-}
-
 static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
@@ -373,14 +307,18 @@ static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 		size_t size, enum dma_data_direction dir)
 {
+	unsigned long offset;
+	struct page *page;
 	dma_addr_t addr;
 
+	BUG_ON(!virt_addr_valid(cpu_addr));
+	BUG_ON(!virt_addr_valid(cpu_addr + size - 1));
 	BUG_ON(!valid_dma_direction(dir));
 
-	addr = __dma_map_single(dev, cpu_addr, size, dir);
-	debug_dma_map_page(dev, virt_to_page(cpu_addr),
-			(unsigned long)cpu_addr & ~PAGE_MASK, size,
-			dir, addr, true);
+	page = virt_to_page(cpu_addr);
+	offset = (unsigned long)cpu_addr & ~PAGE_MASK;
+	addr = __dma_map_page(dev, page, offset, size, dir);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, true);
 
 	return addr;
 }
@@ -430,7 +368,7 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
 	debug_dma_unmap_page(dev, handle, size, dir, true);
-	__dma_unmap_single(dev, handle, size, dir);
+	__dma_unmap_page(dev, handle, size, dir);
 }
 
 /**

arch/arm/include/asm/entry-macro-multi.S

@@ -1,9 +1,11 @@
+#include <asm/assembler.h>
+
 /*
  * Interrupt handling.  Preserves r7, r8, r9
  */
 	.macro	arch_irq_handler_default
-	get_irqnr_preamble r5, lr
-1:	get_irqnr_and_base r0, r6, r5, lr
+	get_irqnr_preamble r6, lr
+1:	get_irqnr_and_base r0, r2, r6, lr
 	movne	r1, sp
 	@
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
@@ -15,17 +17,17 @@
 	/*
 	 * XXX
 	 *
-	 * this macro assumes that irqstat (r6) and base (r5) are
+	 * this macro assumes that irqstat (r2) and base (r6) are
 	 * preserved from get_irqnr_and_base above
 	 */
-	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_SMP(test_for_ipi r0, r2, r6, lr)
 	ALT_UP_B(9997f)
 	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
 
 #ifdef CONFIG_LOCAL_TIMERS
-	test_for_ltirq r0, r6, r5, lr
+	test_for_ltirq r0, r2, r6, lr
 	movne	r0, sp
 	adrne	lr, BSYM(1b)
 	bne	do_local_timer
@@ -38,7 +40,7 @@
 	.align	5
 	.global \symbol_name
 \symbol_name:
-	mov	r4, lr
+	mov	r8, lr
 	arch_irq_handler_default
-	mov     pc, r4
+	mov     pc, r8
 	.endm

arch/arm/include/asm/memory.h

@@ -203,18 +203,6 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #define PHYS_OFFSET	PLAT_PHYS_OFFSET
 #endif
 
-/*
- * The DMA mask corresponding to the maximum bus address allocatable
- * using GFP_DMA.  The default here places no restriction on DMA
- * allocations.  This must be the smallest DMA mask in the system,
- * so a successful GFP_DMA allocation will always satisfy this.
- */
-#ifndef ARM_DMA_ZONE_SIZE
-#define ISA_DMA_THRESHOLD	(0xffffffffULL)
-#else
-#define ISA_DMA_THRESHOLD	(PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1)
-#endif
-
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.

arch/arm/include/asm/pmu.h

@@ -52,7 +52,7 @@ reserve_pmu(enum arm_pmu_type device);
  * a cookie.
  */
 extern int
-release_pmu(struct platform_device *pdev);
+release_pmu(enum arm_pmu_type type);
 
 /**
  * init_pmu() - Initialise the PMU.

arch/arm/include/asm/proc-fns.h

@@ -82,13 +82,13 @@ extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #else
-#define cpu_proc_init()			processor._proc_init()
-#define cpu_proc_fin()			processor._proc_fin()
-#define cpu_reset(addr)			processor.reset(addr)
-#define cpu_do_idle()			processor._do_idle()
-#define cpu_dcache_clean_area(addr,sz)	processor.dcache_clean_area(addr,sz)
-#define cpu_set_pte_ext(ptep,pte,ext)	processor.set_pte_ext(ptep,pte,ext)
-#define cpu_do_switch_mm(pgd,mm)	processor.switch_mm(pgd,mm)
+#define cpu_proc_init			processor._proc_init
+#define cpu_proc_fin			processor._proc_fin
+#define cpu_reset			processor.reset
+#define cpu_do_idle			processor._do_idle
+#define cpu_dcache_clean_area		processor.dcache_clean_area
+#define cpu_set_pte_ext			processor.set_pte_ext
+#define cpu_do_switch_mm		processor.switch_mm
 #endif
 
 extern void cpu_resume(void);

arch/arm/include/asm/scatterlist.h

@@ -1,6 +1,10 @@
 #ifndef _ASMARM_SCATTERLIST_H
 #define _ASMARM_SCATTERLIST_H
 
+#ifdef CONFIG_ARM_HAS_SG_CHAIN
+#define ARCH_HAS_SG_CHAIN
+#endif
+
 #include <asm/memory.h>
 #include <asm/types.h>
 #include <asm-generic/scatterlist.h>

arch/arm/include/asm/setup.h

@@ -187,12 +187,16 @@ struct tagtable {
 
 #define __tag __used __attribute__((__section__(".taglist.init")))
 #define __tagtable(tag, fn) \
-static struct tagtable __tagtable_##fn __tag = { tag, fn }
+static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
 /*
  * Memory map description
  */
-#define NR_BANKS 8
+#ifdef CONFIG_ARCH_EP93XX
+# define NR_BANKS 16
+#else
+# define NR_BANKS 8
+#endif
 
 struct membank {
 	phys_addr_t start;

arch/arm/include/asm/suspend.h

@@ -0,0 +1,22 @@
+#ifndef __ASM_ARM_SUSPEND_H
+#define __ASM_ARM_SUSPEND_H
+
+#include <asm/memory.h>
+#include <asm/tlbflush.h>
+
+extern void cpu_resume(void);
+
+/*
+ * Hide the first two arguments to __cpu_suspend - these are an implementation
+ * detail which platform code shouldn't have to know about.
+ */
+static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	extern int __cpu_suspend(int, long, unsigned long,
+				 int (*)(unsigned long));
+	int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn);
+	flush_tlb_all();
+	return ret;
+}
+
+#endif

arch/arm/include/asm/tcm.h

@@ -27,5 +27,7 @@
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
+bool tcm_dtcm_present(void);
+bool tcm_itcm_present(void);
 
 #endif

arch/arm/include/asm/traps.h

@@ -3,6 +3,9 @@
 
 #include <linux/list.h>
 
+struct pt_regs;
+struct task_struct;
+
 struct undef_hook {
 	struct list_head node;
 	u32 instr_mask;

arch/arm/kernel/asm-offsets.c

@@ -59,6 +59,9 @@ int main(void)
   DEFINE(TI_TP_VALUE,		offsetof(struct thread_info, tp_value));
   DEFINE(TI_FPSTATE,		offsetof(struct thread_info, fpstate));
   DEFINE(TI_VFPSTATE,		offsetof(struct thread_info, vfpstate));
+#ifdef CONFIG_SMP
+  DEFINE(VFP_CPU,		offsetof(union vfp_state, hard.cpu));
+#endif
 #ifdef CONFIG_ARM_THUMBEE
   DEFINE(TI_THUMBEE_STATE,	offsetof(struct thread_info, thumbee_state));
 #endif

arch/arm/kernel/entry-armv.S

@@ -29,21 +29,53 @@
 #include <asm/entry-macro-multi.S>
 
 /*
- * Interrupt handling.  Preserves r7, r8, r9
+ * Interrupt handling.
  */
 	.macro	irq_handler
 #ifdef CONFIG_MULTI_IRQ_HANDLER
-	ldr	r5, =handle_arch_irq
+	ldr	r1, =handle_arch_irq
 	mov	r0, sp
-	ldr	r5, [r5]
+	ldr	r1, [r1]
 	adr	lr, BSYM(9997f)
-	teq	r5, #0
-	movne	pc, r5
+	teq	r1, #0
+	movne	pc, r1
 #endif
 	arch_irq_handler_default
 9997:
 	.endm
 
+	.macro	pabt_helper
+	@ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5
+#ifdef MULTI_PABORT
+	ldr	ip, .LCprocfns
+	mov	lr, pc
+	ldr	pc, [ip, #PROCESSOR_PABT_FUNC]
+#else
+	bl	CPU_PABORT_HANDLER
+#endif
+	.endm
+
+	.macro	dabt_helper
+
+	@
+	@ Call the processor-specific abort handler:
+	@
+	@  r2 - pt_regs
+	@  r4 - aborted context pc
+	@  r5 - aborted context psr
+	@
+	@ The abort handler must return the aborted address in r0, and
+	@ the fault status register in r1.  r9 must be preserved.
+	@
+#ifdef MULTI_DABORT
+	ldr	ip, .LCprocfns
+	mov	lr, pc
+	ldr	pc, [ip, #PROCESSOR_DABT_FUNC]
+#else
+	bl	CPU_DABORT_HANDLER
+#endif
+	.endm
+
 #ifdef CONFIG_KPROBES
 	.section	.kprobes.text,"ax",%progbits
 #else
@@ -126,106 +158,74 @@ ENDPROC(__und_invalid)
  SPFIX(	subeq	sp, sp, #4	)
 	stmia	sp, {r1 - r12}
 
-	ldmia	r0, {r1 - r3}
-	add	r5, sp, #S_SP - 4	@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""      ""       ""
-	add	r0, sp, #(S_FRAME_SIZE + \stack_hole - 4)
- SPFIX(	addeq	r0, r0, #4	)
-	str	r1, [sp, #-4]!		@ save the "real" r0 copied
+	ldmia	r0, {r3 - r5}
+	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
+	mov	r6, #-1			@  ""  ""      ""       ""
+	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ SPFIX(	addeq	r2, r2, #4	)
+	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
 
-	mov	r1, lr
+	mov	r3, lr
 
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
-	@  r0 - sp_svc
-	@  r1 - lr_svc
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - spsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+	@  r2 - sp_svc
+	@  r3 - lr_svc
+	@  r4 - lr_<exception>, already fixed up for correct return/restart
+	@  r5 - spsr_<exception>
+	@  r6 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
-	stmia	r5, {r0 - r4}
+	stmia	r7, {r2 - r6}
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	.endm
 
 	.align	5
 __dabt_svc:
 	svc_entry
-
-	@
-	@ get ready to re-enable interrupts if appropriate
-	@
-	mrs	r9, cpsr
-	tst	r3, #PSR_I_BIT
-	biceq	r9, r9, #PSR_I_BIT
-
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context cpsr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.  r9 must be preserved.
-	@
-#ifdef MULTI_DABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-	bl	CPU_DABORT_HANDLER
-#endif
-
-	@
-	@ set desired IRQ state, then call main handler
-	@
-	debug_entry r1
-	msr	cpsr_c, r9
 	mov	r2, sp
-	bl	do_DataAbort
+	dabt_helper
 
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
 	disable_irq_notrace
 
-	@
-	@ restore SPSR and restart the instruction
-	@
-	ldr	r2, [sp, #S_PSR]
-	svc_exit r2				@ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
 
 	.align	5
 __irq_svc:
 	svc_entry
+	irq_handler
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	add	r7, r8, #1			@ increment it
-	str	r7, [tsk, #TI_PREEMPT]
-#endif
-
-	irq_handler
-#ifdef CONFIG_PREEMPT
-	str	r8, [tsk, #TI_PREEMPT]		@ restore preempt count
 	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
 	movne	r0, #0				@ force flags to 0
 	tst	r0, #_TIF_NEED_RESCHED
 	blne	svc_preempt
 #endif
-	ldr	r4, [sp, #S_PSR]		@ irqs are already disabled
+
 #ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r4, #PSR_I_BIT
-	bleq	trace_hardirqs_on
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
 #endif
-	svc_exit r4				@ return from exception
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__irq_svc)
 
@@ -251,7 +251,6 @@ __und_svc:
 #else
 	svc_entry
 #endif
-
 	@
 	@ call emulation code, which returns using r9 if it has emulated
 	@ the instruction, or the more conventional lr if we are to treat
@@ -260,15 +259,16 @@ __und_svc:
 	@  r0 - instruction
 	@
 #ifndef	CONFIG_THUMB2_KERNEL
-	ldr	r0, [r2, #-4]
+	ldr	r0, [r4, #-4]
 #else
-	ldrh	r0, [r2, #-2]			@ Thumb instruction at LR - 2
+	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
 	and	r9, r0, #0xf800
 	cmp	r9, #0xe800			@ 32-bit instruction if xx >= 0
-	ldrhhs	r9, [r2]			@ bottom 16 bits
+	ldrhhs	r9, [r4]			@ bottom 16 bits
 	orrhs	r0, r9, r0, lsl #16
 #endif
 	adr	r9, BSYM(1f)
+	mov	r2, r4
 	bl	call_fpe
 
 	mov	r0, sp				@ struct pt_regs *regs
@@ -282,45 +282,35 @@ __und_svc:
 	@
 	@ restore SPSR and restart the instruction
 	@
-	ldr	r2, [sp, #S_PSR]		@ Get SVC cpsr
-	svc_exit r2				@ return from exception
+	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__und_svc)
 
 	.align	5
 __pabt_svc:
 	svc_entry
-
-	@
-	@ re-enable interrupts if appropriate
-	@
-	mrs	r9, cpsr
-	tst	r3, #PSR_I_BIT
-	biceq	r9, r9, #PSR_I_BIT
-
-	mov	r0, r2			@ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-	bl	CPU_PABORT_HANDLER
-#endif
-	debug_entry r1
-	msr	cpsr_c, r9			@ Maybe enable interrupts
 	mov	r2, sp				@ regs
-	bl	do_PrefetchAbort		@ call abort handler
+	pabt_helper
 
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
 	disable_irq_notrace
 
-	@
-	@ restore SPSR and restart the instruction
-	@
-	ldr	r2, [sp, #S_PSR]
-	svc_exit r2				@ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__pabt_svc)
 
@@ -351,23 +341,23 @@ ENDPROC(__pabt_svc)
  ARM(	stmib	sp, {r1 - r12}	)
  THUMB(	stmia	sp, {r0 - r12}	)
 
-	ldmia	r0, {r1 - r3}
+	ldmia	r0, {r3 - r5}
 	add	r0, sp, #S_PC		@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""     ""        ""
+	mov	r6, #-1			@  ""  ""     ""        ""
 
-	str	r1, [sp]		@ save the "real" r0 copied
+	str	r3, [sp]		@ save the "real" r0 copied
 					@ from the exception stack
 
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - spsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+	@  r4 - lr_<exception>, already fixed up for correct return/restart
+	@  r5 - spsr_<exception>
+	@  r6 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
 	@ Also, separately save sp_usr and lr_usr
 	@
-	stmia	r0, {r2 - r4}
+	stmia	r0, {r4 - r6}
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
@@ -380,6 +370,10 @@ ENDPROC(__pabt_svc)
 	@ Clear FP to mark the first stack frame
 	@
 	zero_fp
+
+#ifdef CONFIG_IRQSOFF_TRACER
+	bl	trace_hardirqs_off
+#endif
 	.endm
 
 	.macro	kuser_cmpxchg_check
@@ -391,7 +385,7 @@ ENDPROC(__pabt_svc)
 	@ if it was interrupted in a critical region.  Here we
 	@ perform a quick test inline since it should be false
 	@ 99.9999% of the time.  The rest is done out of line.
-	cmp	r2, #TASK_SIZE
+	cmp	r4, #TASK_SIZE
 	blhs	kuser_cmpxchg_fixup
 #endif
 #endif
@@ -401,32 +395,9 @@ ENDPROC(__pabt_svc)
 __dabt_usr:
 	usr_entry
 	kuser_cmpxchg_check
-
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context cpsr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.
-	@
-#ifdef MULTI_DABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-	bl	CPU_DABORT_HANDLER
-#endif
-
-	@
-	@ IRQs on, then call the main handler
-	@
-	debug_entry r1
-	enable_irq
 	mov	r2, sp
-	adr	lr, BSYM(ret_from_exception)
-	b	do_DataAbort
+	dabt_helper
+	b	ret_from_exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_usr)
 
@@ -434,28 +405,8 @@ ENDPROC(__dabt_usr)
 __irq_usr:
 	usr_entry
 	kuser_cmpxchg_check
-
-#ifdef CONFIG_IRQSOFF_TRACER
-	bl	trace_hardirqs_off
-#endif
-
-	get_thread_info tsk
-#ifdef CONFIG_PREEMPT
-	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	add	r7, r8, #1			@ increment it
-	str	r7, [tsk, #TI_PREEMPT]
-#endif
-
 	irq_handler
-#ifdef CONFIG_PREEMPT
-	ldr	r0, [tsk, #TI_PREEMPT]
-	str	r8, [tsk, #TI_PREEMPT]
-	teq	r0, r7
- ARM(	strne	r0, [r0, -r0]	)
- THUMB(	movne	r0, #0		)
- THUMB(	strne	r0, [r0]	)
-#endif
-
+	get_thread_info tsk
 	mov	why, #0
 	b	ret_to_user_from_irq
  UNWIND(.fnend		)
@@ -467,6 +418,9 @@ ENDPROC(__irq_usr)
 __und_usr:
 	usr_entry
 
+	mov	r2, r4
+	mov	r3, r5
+
 	@
 	@ fall through to the emulation code, which returns using r9 if
 	@ it has emulated the instruction, or the more conventional lr
@@ -682,19 +636,8 @@ ENDPROC(__und_usr_unknown)
 	.align	5
 __pabt_usr:
 	usr_entry
-
-	mov	r0, r2			@ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-	bl	CPU_PABORT_HANDLER
-#endif
-	debug_entry r1
-	enable_irq				@ Enable interrupts
 	mov	r2, sp				@ regs
-	bl	do_PrefetchAbort		@ call abort handler
+	pabt_helper
  UNWIND(.fnend		)
 	/* fall through */
 /*
@@ -927,13 +870,13 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 	.text
 kuser_cmpxchg_fixup:
 	@ Called from kuser_cmpxchg_check macro.
-	@ r2 = address of interrupted insn (must be preserved).
+	@ r4 = address of interrupted insn (must be preserved).
 	@ sp = saved regs. r7 and r8 are clobbered.
 	@ 1b = first critical insn, 2b = last critical insn.
-	@ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b.
+	@ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b.
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
-	subs	r8, r2, r7
+	subs	r8, r4, r7
 	rsbcss	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 	mov	pc, lr

arch/arm/kernel/entry-header.S

@@ -165,25 +165,6 @@
 	.endm
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
-	@
-	@ Debug exceptions are taken as prefetch or data aborts.
-	@ We must disable preemption during the handler so that
-	@ we can access the debug registers safely.
-	@
-	.macro	debug_entry, fsr
-#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT)
-	ldr	r4, =0x40f		@ mask out fsr.fs
-	and	r5, r4, \fsr
-	cmp	r5, #2			@ debug exception
-	bne	1f
-	get_thread_info r10
-	ldr	r6, [r10, #TI_PREEMPT]	@ get preempt count
-	add	r11, r6, #1		@ increment it
-	str	r11, [r10, #TI_PREEMPT]
-1:
-#endif
-	.endm
-
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.

arch/arm/kernel/head-nommu.S

@@ -32,8 +32,16 @@
  * numbers for r1.
  *
  */
+	.arm
+
 	__HEAD
 ENTRY(stext)
+
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 #ifndef CONFIG_CPU_CP15

arch/arm/kernel/head.S

@@ -71,8 +71,16 @@
  * crap here - that's what the boot loader (or in extreme, well justified
  * circumstances, zImage) is for.
  */
+	.arm
+
 	__HEAD
 ENTRY(stext)
+
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 	mrc	p15, 0, r9, c0, c0		@ get processor id

arch/arm/kernel/hw_breakpoint.c

@@ -796,7 +796,7 @@ unlock:
 
 /*
  * Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint] with preemption disabled.
+ * Prefetch Abort Handler [breakpoint] with interrupts disabled.
  */
 static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 				 struct pt_regs *regs)
@@ -804,8 +804,10 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	int ret = 0;
 	u32 dscr;
 
-	/* We must be called with preemption disabled. */
-	WARN_ON(preemptible());
+	preempt_disable();
+
+	if (interrupts_enabled(regs))
+		local_irq_enable();
 
 	/* We only handle watchpoints and hardware breakpoints. */
 	ARM_DBG_READ(c1, 0, dscr);
@@ -824,10 +826,6 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		ret = 1; /* Unhandled fault. */
 	}
 
-	/*
-	 * Re-enable preemption after it was disabled in the
-	 * low-level exception handling code.
-	 */
 	preempt_enable();
 
 	return ret;

arch/arm/kernel/irq.c

@@ -131,54 +131,63 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool migrate_one_irq(struct irq_data *d)
+static bool migrate_one_irq(struct irq_desc *desc)
 {
-	unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask);
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	const struct cpumask *affinity = d->affinity;
+	struct irq_chip *c;
 	bool ret = false;
 
-	if (cpu >= nr_cpu_ids) {
-		cpu = cpumask_any(cpu_online_mask);
+	/*
+	 * If this is a per-CPU interrupt, or the affinity does not
+	 * include this CPU, then we have nothing to do.
+	 */
+	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+		return false;
+
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
 		ret = true;
 	}
 
-	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu);
-
-	d->chip->irq_set_affinity(d, cpumask_of(cpu), true);
+	c = irq_data_get_irq_chip(d);
+	if (c->irq_set_affinity)
+		c->irq_set_affinity(d, affinity, true);
+	else
+		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 
 	return ret;
 }
 
 /*
- * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
- * the affinity settings do not allow other CPUs, force them onto any
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
  * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
  */
 void migrate_irqs(void)
 {
-	unsigned int i, cpu = smp_processor_id();
+	unsigned int i;
 	struct irq_desc *desc;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		struct irq_data *d = &desc->irq_data;
 		bool affinity_broken = false;
 
-		raw_spin_lock(&desc->lock);
-		do {
-			if (desc->action == NULL)
-				break;
-
-			if (d->node != cpu)
-				break;
+		if (!desc)
+			continue;
 
-			affinity_broken = migrate_one_irq(d);
-		} while (0);
+		raw_spin_lock(&desc->lock);
+		affinity_broken = migrate_one_irq(desc);
 		raw_spin_unlock(&desc->lock);
 
 		if (affinity_broken && printk_ratelimit())
-			pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
+			pr_warning("IRQ%u no longer affine to CPU%u\n", i,
+				smp_processor_id());
 	}
 
 	local_irq_restore(flags);

arch/arm/kernel/module.c

@@ -193,8 +193,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x02000000;
 			offset += sym->st_value - loc;
 
-			/* only Thumb addresses allowed (no interworking) */
-			if (!(offset & 1) ||
+			/*
+			 * For function symbols, only Thumb addresses are
+			 * allowed (no interworking).
+			 *
+			 * For non-function symbols, the destination
+			 * has no specific ARM/Thumb disposition, so
+			 * the branch is resolved under the assumption
+			 * that interworking is not required.
+			 */
+			if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
+				!(offset & 1)) ||
 			    offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",

arch/arm/kernel/perf_event.c

@@ -435,7 +435,7 @@ armpmu_reserve_hardware(void)
 			if (irq >= 0)
 				free_irq(irq, NULL);
 		}
-		release_pmu(pmu_device);
+		release_pmu(ARM_PMU_DEVICE_CPU);
 		pmu_device = NULL;
 	}
 
@@ -454,7 +454,7 @@ armpmu_release_hardware(void)
 	}
 	armpmu->stop();
 
-	release_pmu(pmu_device);
+	release_pmu(ARM_PMU_DEVICE_CPU);
 	pmu_device = NULL;
 }
 
@@ -583,7 +583,7 @@ static int armpmu_event_init(struct perf_event *event)
 static void armpmu_enable(struct pmu *pmu)
 {
 	/* Enable all of the perf events on hardware. */
-	int idx;
+	int idx, enabled = 0;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	if (!armpmu)
@@ -596,9 +596,11 @@ static void armpmu_enable(struct pmu *pmu)
 			continue;
 
 		armpmu->enable(&event->hw, idx);
+		enabled = 1;
 	}
 
-	armpmu->start();
+	if (enabled)
+		armpmu->start();
 }
 
 static void armpmu_disable(struct pmu *pmu)

arch/arm/kernel/pmu.c

@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #include <asm/pmu.h>
@@ -25,36 +26,88 @@ static volatile long pmu_lock;
 
 static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
 
-static int __devinit pmu_device_probe(struct platform_device *pdev)
+static int __devinit pmu_register(struct platform_device *pdev,
+					enum arm_pmu_type type)
 {
-
-	if (pdev->id < 0 || pdev->id >= ARM_NUM_PMU_DEVICES) {
+	if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
 		pr_warning("received registration request for unknown "
-				"device %d\n", pdev->id);
+				"device %d\n", type);
 		return -EINVAL;
 	}
 
-	if (pmu_devices[pdev->id])
-		pr_warning("registering new PMU device type %d overwrites "
-				"previous registration!\n", pdev->id);
-	else
-		pr_info("registered new PMU device of type %d\n",
-				pdev->id);
+	if (pmu_devices[type]) {
+		pr_warning("rejecting duplicate registration of PMU device "
+			"type %d.", type);
+		return -ENOSPC;
+	}
 
-	pmu_devices[pdev->id] = pdev;
+	pr_info("registered new PMU device of type %d\n", type);
+	pmu_devices[type] = pdev;
 	return 0;
 }
 
-static struct platform_driver pmu_driver = {
+#define OF_MATCH_PMU(_name, _type) {	\
+	.compatible = _name,		\
+	.data = (void *)_type,		\
+}
+
+#define OF_MATCH_CPU(name)	OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU)
+
+static struct of_device_id armpmu_of_device_ids[] = {
+	OF_MATCH_CPU("arm,cortex-a9-pmu"),
+	OF_MATCH_CPU("arm,cortex-a8-pmu"),
+	OF_MATCH_CPU("arm,arm1136-pmu"),
+	OF_MATCH_CPU("arm,arm1176-pmu"),
+	{},
+};
+
+#define PLAT_MATCH_PMU(_name, _type) {	\
+	.name		= _name,	\
+	.driver_data	= _type,	\
+}
+
+#define PLAT_MATCH_CPU(_name)	PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU)
+
+static struct platform_device_id armpmu_plat_device_ids[] = {
+	PLAT_MATCH_CPU("arm-pmu"),
+	{},
+};
+
+enum arm_pmu_type armpmu_device_type(struct platform_device *pdev)
+{
+	const struct of_device_id	*of_id;
+	const struct platform_device_id *pdev_id;
+
+	/* provided by of_device_id table */
+	if (pdev->dev.of_node) {
+		of_id = of_match_device(armpmu_of_device_ids, &pdev->dev);
+		BUG_ON(!of_id);
+		return (enum arm_pmu_type)of_id->data;
+	}
+
+	/* Provided by platform_device_id table */
+	pdev_id = platform_get_device_id(pdev);
+	BUG_ON(!pdev_id);
+	return pdev_id->driver_data;
+}
+
+static int __devinit armpmu_device_probe(struct platform_device *pdev)
+{
+	return pmu_register(pdev, armpmu_device_type(pdev));
+}
+
+static struct platform_driver armpmu_driver = {
 	.driver		= {
 		.name	= "arm-pmu",
+		.of_match_table = armpmu_of_device_ids,
 	},
-	.probe		= pmu_device_probe,
+	.probe		= armpmu_device_probe,
+	.id_table	= armpmu_plat_device_ids,
 };
 
 static int __init register_pmu_driver(void)
 {
-	return platform_driver_register(&pmu_driver);
+	return platform_driver_register(&armpmu_driver);
 }
 device_initcall(register_pmu_driver);
 
@@ -77,11 +130,11 @@ reserve_pmu(enum arm_pmu_type device)
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
 int
-release_pmu(struct platform_device *pdev)
+release_pmu(enum arm_pmu_type device)
 {
-	if (WARN_ON(pdev != pmu_devices[pdev->id]))
+	if (WARN_ON(!pmu_devices[device]))
 		return -EINVAL;
-	clear_bit_unlock(pdev->id, &pmu_lock);
+	clear_bit_unlock(device, &pmu_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(release_pmu);

arch/arm/kernel/setup.c

@@ -73,6 +73,7 @@ __setup("fpe=", fpe_setup);
 #endif
 
 extern void paging_init(struct machine_desc *desc);
+extern void sanity_check_meminfo(void);
 extern void reboot_setup(char *str);
 
 unsigned int processor_id;
@@ -342,54 +343,6 @@ static void __init feat_v6_fixup(void)
 		elf_hwcap &= ~HWCAP_TLS;
 }
 
-static void __init setup_processor(void)
-{
-	struct proc_info_list *list;
-
-	/*
-	 * locate processor in the list of supported processor
-	 * types.  The linker builds this table for us from the
-	 * entries in arch/arm/mm/proc-*.S
-	 */
-	list = lookup_processor_type(read_cpuid_id());
-	if (!list) {
-		printk("CPU configuration botched (ID %08x), unable "
-		       "to continue.\n", read_cpuid_id());
-		while (1);
-	}
-
-	cpu_name = list->cpu_name;
-
-#ifdef MULTI_CPU
-	processor = *list->proc;
-#endif
-#ifdef MULTI_TLB
-	cpu_tlb = *list->tlb;
-#endif
-#ifdef MULTI_USER
-	cpu_user = *list->user;
-#endif
-#ifdef MULTI_CACHE
-	cpu_cache = *list->cache;
-#endif
-
-	printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
-	       proc_arch[cpu_architecture()], cr_alignment);
-
-	sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
-	sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
-	elf_hwcap = list->elf_hwcap;
-#ifndef CONFIG_ARM_THUMB
-	elf_hwcap &= ~HWCAP_THUMB;
-#endif
-
-	feat_v6_fixup();
-
-	cacheid_init();
-	cpu_proc_init();
-}
-
 /*
  * cpu_init - initialise one CPU.
  *
@@ -405,6 +358,8 @@ void cpu_init(void)
 		BUG();
 	}
 
+	cpu_proc_init();
+
 	/*
 	 * Define the placement constraint for the inline asm directive below.
 	 * In Thumb-2, msr with an immediate value is not allowed.
@@ -441,6 +396,54 @@ void cpu_init(void)
 	    : "r14");
 }
 
+static void __init setup_processor(void)
+{
+	struct proc_info_list *list;
+
+	/*
+	 * locate processor in the list of supported processor
+	 * types.  The linker builds this table for us from the
+	 * entries in arch/arm/mm/proc-*.S
+	 */
+	list = lookup_processor_type(read_cpuid_id());
+	if (!list) {
+		printk("CPU configuration botched (ID %08x), unable "
+		       "to continue.\n", read_cpuid_id());
+		while (1);
+	}
+
+	cpu_name = list->cpu_name;
+
+#ifdef MULTI_CPU
+	processor = *list->proc;
+#endif
+#ifdef MULTI_TLB
+	cpu_tlb = *list->tlb;
+#endif
+#ifdef MULTI_USER
+	cpu_user = *list->user;
+#endif
+#ifdef MULTI_CACHE
+	cpu_cache = *list->cache;
+#endif
+
+	printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
+	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+	       proc_arch[cpu_architecture()], cr_alignment);
+
+	sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
+	sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
+	elf_hwcap = list->elf_hwcap;
+#ifndef CONFIG_ARM_THUMB
+	elf_hwcap &= ~HWCAP_THUMB;
+#endif
+
+	feat_v6_fixup();
+
+	cacheid_init();
+	cpu_init();
+}
+
 void __init dump_machine_table(void)
 {
 	struct machine_desc *p;
@@ -900,6 +903,7 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	sanity_check_meminfo();
 	arm_memblock_init(&meminfo, mdesc);
 
 	paging_init(mdesc);
@@ -913,7 +917,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	reserve_crashkernel();
 
-	cpu_init();
 	tcm_init();
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER

arch/arm/kernel/sleep.S

@@ -10,64 +10,61 @@
 /*
  * Save CPU state for a suspend
  *  r1 = v:p offset
- *  r3 = virtual return function
- * Note: sp is decremented to allocate space for CPU state on stack
- * r0-r3,r9,r10,lr corrupted
+ *  r2 = suspend function arg0
+ *  r3 = suspend function
  */
-ENTRY(cpu_suspend)
-	mov	r9, lr
+ENTRY(__cpu_suspend)
+	stmfd	sp!, {r4 - r11, lr}
 #ifdef MULTI_CPU
 	ldr	r10, =processor
-	mov	r2, sp			@ current virtual SP
-	ldr	r0, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
+	ldr	r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
 	ldr	ip, [r10, #CPU_DO_RESUME] @ virtual resume function
-	sub	sp, sp, r0		@ allocate CPU state on stack
-	mov	r0, sp			@ save pointer
+#else
+	ldr	r5, =cpu_suspend_size
+	ldr	ip, =cpu_do_resume
+#endif
+	mov	r6, sp			@ current virtual SP
+	sub	sp, sp, r5		@ allocate CPU state on stack
+	mov	r0, sp			@ save pointer to CPU save block
 	add	ip, ip, r1		@ convert resume fn to phys
-	stmfd	sp!, {r1, r2, r3, ip}	@ save v:p, virt SP, retfn, phys resume fn
-	ldr	r3, =sleep_save_sp
-	add	r2, sp, r1		@ convert SP to phys
+	stmfd	sp!, {r1, r6, ip}	@ save v:p, virt SP, phys resume fn
+	ldr	r5, =sleep_save_sp
+	add	r6, sp, r1		@ convert SP to phys
+	stmfd	sp!, {r2, r3}		@ save suspend func arg and pointer
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
 	ALT_UP(mov lr, #0)
 	and	lr, lr, #15
-	str	r2, [r3, lr, lsl #2]	@ save phys SP
+	str	r6, [r5, lr, lsl #2]	@ save phys SP
 #else
-	str	r2, [r3]		@ save phys SP
+	str	r6, [r5]		@ save phys SP
 #endif
+#ifdef MULTI_CPU
 	mov	lr, pc
 	ldr	pc, [r10, #CPU_DO_SUSPEND] @ save CPU state
 #else
-	mov	r2, sp			@ current virtual SP
-	ldr	r0, =cpu_suspend_size
-	sub	sp, sp, r0		@ allocate CPU state on stack
-	mov	r0, sp			@ save pointer
-	stmfd	sp!, {r1, r2, r3}	@ save v:p, virt SP, return fn
-	ldr	r3, =sleep_save_sp
-	add	r2, sp, r1		@ convert SP to phys
-#ifdef CONFIG_SMP
-	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
-	ALT_UP(mov lr, #0)
-	and	lr, lr, #15
-	str	r2, [r3, lr, lsl #2]	@ save phys SP
-#else
-	str	r2, [r3]		@ save phys SP
-#endif
 	bl	cpu_do_suspend
 #endif
 
 	@ flush data cache
 #ifdef MULTI_CACHE
 	ldr	r10, =cpu_cache
-	mov	lr, r9
+	mov	lr, pc
 	ldr	pc, [r10, #CACHE_FLUSH_KERN_ALL]
 #else
-	mov	lr, r9
-	b	__cpuc_flush_kern_all
+	bl	__cpuc_flush_kern_all
 #endif
-ENDPROC(cpu_suspend)
+	adr	lr, BSYM(cpu_suspend_abort)
+	ldmfd	sp!, {r0, pc}		@ call suspend fn
+ENDPROC(__cpu_suspend)
 	.ltorg
 
+cpu_suspend_abort:
+	ldmia	sp!, {r1 - r3}		@ pop v:p, virt SP, phys resume fn
+	mov	sp, r2
+	ldmfd	sp!, {r4 - r11, pc}
+ENDPROC(cpu_suspend_abort)
+
 /*
  * r0 = control register value
  * r1 = v:p offset (preserved by cpu_do_resume)
@@ -97,7 +94,9 @@ ENDPROC(cpu_resume_turn_mmu_on)
 cpu_resume_after_mmu:
 	str	r5, [r2, r4, lsl #2]	@ restore old mapping
 	mcr	p15, 0, r0, c1, c0, 0	@ turn on D-cache
-	mov	pc, lr
+	bl	cpu_init		@ restore the und/abt/irq banked regs
+	mov	r0, #0			@ return zero on success
+	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_resume_after_mmu)
 
 /*
@@ -120,20 +119,11 @@ ENTRY(cpu_resume)
 	ldr	r0, sleep_save_sp	@ stack phys addr
 #endif
 	setmode	PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
-#ifdef MULTI_CPU
-	@ load v:p, stack, return fn, resume fn
-  ARM(	ldmia	r0!, {r1, sp, lr, pc}	)
-THUMB(	ldmia	r0!, {r1, r2, r3, r4}	)
+	@ load v:p, stack, resume fn
+  ARM(	ldmia	r0!, {r1, sp, pc}	)
+THUMB(	ldmia	r0!, {r1, r2, r3}	)
 THUMB(	mov	sp, r2			)
-THUMB(	mov	lr, r3			)
-THUMB(	bx	r4			)
-#else
-	@ load v:p, stack, return fn
-  ARM(	ldmia	r0!, {r1, sp, lr}	)
-THUMB(	ldmia	r0!, {r1, r2, lr}	)
-THUMB(	mov	sp, r2			)
-	b	cpu_do_resume
-#endif
+THUMB(	bx	r3			)
 ENDPROC(cpu_resume)
 
 sleep_save_sp:

arch/arm/kernel/smp.c

@@ -318,9 +318,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	smp_store_cpu_info(cpu);
 
 	/*
-	 * OK, now it's safe to let the boot CPU continue
+	 * OK, now it's safe to let the boot CPU continue.  Wait for
+	 * the CPU migration code to notice that the CPU is online
+	 * before we continue.
 	 */
 	set_cpu_online(cpu, true);
+	while (!cpu_active(cpu))
+		cpu_relax();
 
 	/*
 	 * OK, it's off to the idle thread for us
@@ -361,14 +365,21 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	 */
 	if (max_cpus > ncores)
 		max_cpus = ncores;
-
-	if (max_cpus > 1) {
+	if (ncores > 1 && max_cpus) {
 		/*
 		 * Enable the local timer or broadcast device for the
 		 * boot CPU, but only if we have more than one CPU.
 		 */
 		percpu_timer_setup();
 
+		/*
+		 * Initialise the present map, which describes the set of CPUs
+		 * actually populated at the present time. A platform should
+		 * re-initialize the map in platform_smp_prepare_cpus() if
+		 * present != possible (e.g. physical hotplug).
+		 */
+		init_cpu_present(&cpu_possible_map);
+
 		/*
 		 * Initialise the SCU if there are more than one CPU
 		 * and let them know where to start.

arch/arm/kernel/smp_scu.c

@@ -20,6 +20,7 @@
 #define SCU_INVALIDATE		0x0c
 #define SCU_FPGA_REVISION	0x10
 
+#ifdef CONFIG_SMP
 /*
  * Get the number of CPU cores from the SCU configuration
  */
@@ -50,6 +51,7 @@ void __init scu_enable(void __iomem *scu_base)
 	 */
 	flush_cache_all();
 }
+#endif
 
 /*
  * Set the executing CPUs power mode as defined.  This will be in

arch/arm/kernel/smp_twd.c

@@ -115,7 +115,7 @@ static void __cpuinit twd_calibrate_rate(void)
 		twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
 
 		printk("%lu.%02luMHz.\n", twd_timer_rate / 1000000,
-			(twd_timer_rate / 1000000) % 100);
+			(twd_timer_rate / 10000) % 100);
 	}
 }
 

arch/arm/kernel/tcm.c

@@ -19,6 +19,8 @@
 #include "tcm.h"
 
 static struct gen_pool *tcm_pool;
+static bool dtcm_present;
+static bool itcm_present;
 
 /* TCM section definitions from the linker */
 extern char __itcm_start, __sitcm_text, __eitcm_text;
@@ -90,6 +92,18 @@ void tcm_free(void *addr, size_t len)
 }
 EXPORT_SYMBOL(tcm_free);
 
+bool tcm_dtcm_present(void)
+{
+	return dtcm_present;
+}
+EXPORT_SYMBOL(tcm_dtcm_present);
+
+bool tcm_itcm_present(void)
+{
+	return itcm_present;
+}
+EXPORT_SYMBOL(tcm_itcm_present);
+
 static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
 				  u32 *offset)
 {
@@ -134,6 +148,10 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
 			(tcm_region & 1) ? "" : "not ");
 	}
 
+	/* Not much fun you can do with a size 0 bank */
+	if (tcm_size == 0)
+		return 0;
+
 	/* Force move the TCM bank to where we want it, enable */
 	tcm_region = *offset | (tcm_region & 0x00000ffeU) | 1;
 
@@ -165,12 +183,20 @@ void __init tcm_init(void)
 	u32 tcm_status = read_cpuid_tcmstatus();
 	u8 dtcm_banks = (tcm_status >> 16) & 0x03;
 	u8 itcm_banks = (tcm_status & 0x03);
+	size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data;
+	size_t itcm_code_sz = &__eitcm_text - &__sitcm_text;
 	char *start;
 	char *end;
 	char *ram;
 	int ret;
 	int i;
 
+	/* Values greater than 2 for D/ITCM banks are "reserved" */
+	if (dtcm_banks > 2)
+		dtcm_banks = 0;
+	if (itcm_banks > 2)
+		itcm_banks = 0;
+
 	/* Setup DTCM if present */
 	if (dtcm_banks > 0) {
 		for (i = 0; i < dtcm_banks; i++) {
@@ -178,6 +204,13 @@ void __init tcm_init(void)
 			if (ret)
 				return;
 		}
+		/* This means you compiled more code than fits into DTCM */
+		if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) {
+			pr_info("CPU DTCM: %u bytes of code compiled to "
+				"DTCM but only %lu bytes of DTCM present\n",
+				dtcm_code_sz, (dtcm_end - DTCM_OFFSET));
+			goto no_dtcm;
+		}
 		dtcm_res.end = dtcm_end - 1;
 		request_resource(&iomem_resource, &dtcm_res);
 		dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET;
@@ -186,12 +219,16 @@ void __init tcm_init(void)
 		start = &__sdtcm_data;
 		end   = &__edtcm_data;
 		ram   = &__dtcm_start;
-		/* This means you compiled more code than fits into DTCM */
-		BUG_ON((end - start) > (dtcm_end - DTCM_OFFSET));
-		memcpy(start, ram, (end-start));
-		pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+		memcpy(start, ram, dtcm_code_sz);
+		pr_debug("CPU DTCM: copied data from %p - %p\n",
+			 start, end);
+		dtcm_present = true;
+	} else if (dtcm_code_sz) {
+		pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no "
+			"DTCM banks present in CPU\n", dtcm_code_sz);
 	}
 
+no_dtcm:
 	/* Setup ITCM if present */
 	if (itcm_banks > 0) {
 		for (i = 0; i < itcm_banks; i++) {
@@ -199,6 +236,13 @@ void __init tcm_init(void)
 			if (ret)
 				return;
 		}
+		/* This means you compiled more code than fits into ITCM */
+		if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) {
+			pr_info("CPU ITCM: %u bytes of code compiled to "
+				"ITCM but only %lu bytes of ITCM present\n",
+				itcm_code_sz, (itcm_end - ITCM_OFFSET));
+			return;
+		}
 		itcm_res.end = itcm_end - 1;
 		request_resource(&iomem_resource, &itcm_res);
 		itcm_iomap[0].length = itcm_end - ITCM_OFFSET;
@@ -207,10 +251,13 @@ void __init tcm_init(void)
 		start = &__sitcm_text;
 		end   = &__eitcm_text;
 		ram   = &__itcm_start;
-		/* This means you compiled more code than fits into ITCM */
-		BUG_ON((end - start) > (itcm_end - ITCM_OFFSET));
-		memcpy(start, ram, (end-start));
-		pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+		memcpy(start, ram, itcm_code_sz);
+		pr_debug("CPU ITCM: copied code from %p - %p\n",
+			 start, end);
+		itcm_present = true;
+	} else if (itcm_code_sz) {
+		pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no "
+			"ITCM banks present in CPU\n", itcm_code_sz);
 	}
 }
 
@@ -221,7 +268,6 @@ void __init tcm_init(void)
  */
 static int __init setup_tcm_pool(void)
 {
-	u32 tcm_status = read_cpuid_tcmstatus();
 	u32 dtcm_pool_start = (u32) &__edtcm_data;
 	u32 itcm_pool_start = (u32) &__eitcm_text;
 	int ret;
@@ -236,7 +282,7 @@ static int __init setup_tcm_pool(void)
 	pr_debug("Setting up TCM memory pool\n");
 
 	/* Add the rest of DTCM to the TCM pool */
-	if (tcm_status & (0x03 << 16)) {
+	if (dtcm_present) {
 		if (dtcm_pool_start < dtcm_end) {
 			ret = gen_pool_add(tcm_pool, dtcm_pool_start,
 					   dtcm_end - dtcm_pool_start, -1);
@@ -253,7 +299,7 @@ static int __init setup_tcm_pool(void)
 	}
 
 	/* Add the rest of ITCM to the TCM pool */
-	if (tcm_status & 0x03) {
+	if (itcm_present) {
 		if (itcm_pool_start < itcm_end) {
 			ret = gen_pool_add(tcm_pool, itcm_pool_start,
 					   itcm_end - itcm_pool_start, -1);

arch/arm/kernel/vmlinux.lds.S

@@ -38,57 +38,6 @@ jiffies = jiffies_64 + 4;
 
 SECTIONS
 {
-#ifdef CONFIG_XIP_KERNEL
-	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
-#else
-	. = PAGE_OFFSET + TEXT_OFFSET;
-#endif
-
-	.init : {			/* Init code and data		*/
-		_stext = .;
-		_sinittext = .;
-			HEAD_TEXT
-			INIT_TEXT
-			ARM_EXIT_KEEP(EXIT_TEXT)
-		_einittext = .;
-		ARM_CPU_DISCARD(PROC_INFO)
-		__arch_info_begin = .;
-			*(.arch.info.init)
-		__arch_info_end = .;
-		__tagtable_begin = .;
-			*(.taglist.init)
-		__tagtable_end = .;
-#ifdef CONFIG_SMP_ON_UP
-		__smpalt_begin = .;
-			*(.alt.smp.init)
-		__smpalt_end = .;
-#endif
-
-		__pv_table_begin = .;
-			*(.pv_table)
-		__pv_table_end = .;
-
-		INIT_SETUP(16)
-
-		INIT_CALLS
-		CON_INITCALL
-		SECURITY_INITCALL
-		INIT_RAM_FS
-
-#ifndef CONFIG_XIP_KERNEL
-		__init_begin = _stext;
-		INIT_DATA
-		ARM_EXIT_KEEP(EXIT_DATA)
-#endif
-	}
-
-	PERCPU_SECTION(32)
-
-#ifndef CONFIG_XIP_KERNEL
-	. = ALIGN(PAGE_SIZE);
-	__init_end = .;
-#endif
-
 	/*
 	 * unwind exit sections must be discarded before the rest of the
 	 * unwind sections get included.
@@ -105,11 +54,23 @@ SECTIONS
 #ifndef CONFIG_MMU
 		*(.fixup)
 		*(__ex_table)
+#endif
+#ifndef CONFIG_SMP_ON_UP
+		*(.alt.smp.init)
 #endif
 	}
 
+#ifdef CONFIG_XIP_KERNEL
+	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
+#else
+	. = PAGE_OFFSET + TEXT_OFFSET;
+#endif
+	.head.text : {
+		_text = .;
+		HEAD_TEXT
+	}
 	.text : {			/* Real text segment		*/
-		_text = .;		/* Text and read-only data	*/
+		_stext = .;		/* Text and read-only data	*/
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;
@@ -122,8 +83,6 @@ SECTIONS
 			*(.fixup)
 #endif
 			*(.gnu.warning)
-			*(.rodata)
-			*(.rodata.*)
 			*(.glue_7)
 			*(.glue_7t)
 		. = ALIGN(4);
@@ -152,10 +111,63 @@ SECTIONS
 
 	_etext = .;			/* End of text and rodata section */
 
+#ifndef CONFIG_XIP_KERNEL
+	. = ALIGN(PAGE_SIZE);
+	__init_begin = .;
+#endif
+
+	INIT_TEXT_SECTION(8)
+	.exit.text : {
+		ARM_EXIT_KEEP(EXIT_TEXT)
+	}
+	.init.proc.info : {
+		ARM_CPU_DISCARD(PROC_INFO)
+	}
+	.init.arch.info : {
+		__arch_info_begin = .;
+		*(.arch.info.init)
+		__arch_info_end = .;
+	}
+	.init.tagtable : {
+		__tagtable_begin = .;
+		*(.taglist.init)
+		__tagtable_end = .;
+	}
+#ifdef CONFIG_SMP_ON_UP
+	.init.smpalt : {
+		__smpalt_begin = .;
+		*(.alt.smp.init)
+		__smpalt_end = .;
+	}
+#endif
+	.init.pv_table : {
+		__pv_table_begin = .;
+		*(.pv_table)
+		__pv_table_end = .;
+	}
+	.init.data : {
+#ifndef CONFIG_XIP_KERNEL
+		INIT_DATA
+#endif
+		INIT_SETUP(16)
+		INIT_CALLS
+		CON_INITCALL
+		SECURITY_INITCALL
+		INIT_RAM_FS
+	}
+#ifndef CONFIG_XIP_KERNEL
+	.exit.data : {
+		ARM_EXIT_KEEP(EXIT_DATA)
+	}
+#endif
+
+	PERCPU_SECTION(32)
+
 #ifdef CONFIG_XIP_KERNEL
 	__data_loc = ALIGN(4);		/* location in binary */
 	. = PAGE_OFFSET + TEXT_OFFSET;
 #else
+	__init_end = .;
 	. = ALIGN(THREAD_SIZE);
 	__data_loc = .;
 #endif
@@ -270,12 +282,6 @@ SECTIONS
 
 	/* Default discards */
 	DISCARDS
-
-#ifndef CONFIG_SMP_ON_UP
-	/DISCARD/ : {
-		*(.alt.smp.init)
-	}
-#endif
 }
 
 /*

arch/arm/mach-at91/at91cap9.c

@@ -223,15 +223,15 @@ static struct clk *periph_clocks[] __initdata = {
 };
 
 static struct clk_lookup periph_clocks_lookups[] = {
-	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb_clk),
-	CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 };
 
 static struct clk_lookup usart_clocks_lookups[] = {

arch/arm/mach-at91/at91cap9_devices.c

@@ -1220,7 +1220,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91cap9_set_console_clock(portnr);
+		at91cap9_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91rm9200.c

@@ -199,9 +199,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
-	CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
-	CLKDEV_CON_DEV_ID("ssc", "ssc.2", &ssc2_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
 };
 
 static struct clk_lookup usart_clocks_lookups[] = {

arch/arm/mach-at91/at91rm9200_devices.c

@@ -1135,7 +1135,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91rm9200_set_console_clock(portnr);
+		at91rm9200_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91sam9260_devices.c

@@ -1173,7 +1173,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91sam9260_set_console_clock(portnr);
+		at91sam9260_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91sam9261_devices.c

@@ -1013,7 +1013,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91sam9261_set_console_clock(portnr);
+		at91sam9261_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91sam9263_devices.c

@@ -1395,7 +1395,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91sam9263_set_console_clock(portnr);
+		at91sam9263_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91sam9g45.c

@@ -217,11 +217,11 @@ static struct clk *periph_clocks[] __initdata = {
 static struct clk_lookup periph_clocks_lookups[] = {
 	/* One additional fake clock for ohci */
 	CLKDEV_CON_ID("ohci_clk", &uhphs_clk),
-	CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci.0", &uhphs_clk),
-	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
-	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
-	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
+	CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci", &uhphs_clk),
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.0", &mmc0_clk),
+	CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.1", &mmc1_clk),
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb0_clk),

arch/arm/mach-at91/at91sam9g45_devices.c

@@ -1550,7 +1550,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91sam9g45_set_console_clock(portnr);
+		at91sam9g45_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/at91sam9rl.c

@@ -191,8 +191,8 @@ static struct clk *periph_clocks[] __initdata = {
 };
 
 static struct clk_lookup periph_clocks_lookups[] = {
-	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),

arch/arm/mach-at91/at91sam9rl_devices.c

@@ -1168,7 +1168,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
 	if (portnr < ATMEL_MAX_UART) {
 		atmel_default_console_device = at91_uarts[portnr];
-		at91sam9rl_set_console_clock(portnr);
+		at91sam9rl_set_console_clock(at91_uarts[portnr]->id);
 	}
 }
 

arch/arm/mach-at91/board-cap9adk.c

@@ -215,7 +215,7 @@ static void __init cap9adk_add_device_nand(void)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
 
-	cap9adk_nand_data.bus_width_16 = !board_have_nand_8bit();
+	cap9adk_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (cap9adk_nand_data.bus_width_16)
 		cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/board-sam9260ek.c

@@ -214,7 +214,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+	ek_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/board-sam9261ek.c

@@ -220,7 +220,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+	ek_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/board-sam9263ek.c

@@ -221,7 +221,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+	ek_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/board-sam9g20ek.c

@@ -198,7 +198,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+	ek_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/board-sam9m10g45ek.c

@@ -178,7 +178,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-	ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+	ek_nand_data.bus_width_16 = board_have_nand_16bit();
 	/* setup bus-width (8 or 16) */
 	if (ek_nand_data.bus_width_16)
 		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;

arch/arm/mach-at91/include/mach/system_rev.h

@@ -13,13 +13,13 @@
  * the 16-31 bit are reserved for at91 generic information
  *
  * bit 31:
- *	0 => nand 16 bit
- *	1 => nand 8 bit
+ *	0 => nand 8 bit
+ *	1 => nand 16 bit
  */
-#define BOARD_HAVE_NAND_8BIT	(1 << 31)
-static int inline board_have_nand_8bit(void)
+#define BOARD_HAVE_NAND_16BIT	(1 << 31)
+static inline int board_have_nand_16bit(void)
 {
-	return system_rev & BOARD_HAVE_NAND_8BIT;
+	return system_rev & BOARD_HAVE_NAND_16BIT;
 }
 
 #endif /* __ARCH_SYSTEM_REV_H__ */

arch/arm/mach-bcmring/include/mach/entry-macro.S

@@ -80,7 +80,3 @@
 
 		.macro  arch_ret_to_user, tmp1, tmp2
 		.endm
-
-		.macro	irq_prio_table
-		.endm
-

arch/arm/mach-davinci/board-dm365-evm.c

@@ -520,7 +520,7 @@ fail:
 	 */
 	if (have_imager()) {
 		label = "HD imager";
-		mux |= 1;
+		mux |= 2;
 
 		/* externally mux MMC1/ENET/AIC33 to imager */
 		mux |= BIT(6) | BIT(5) | BIT(3);
@@ -540,7 +540,7 @@ fail:
 		resets &= ~BIT(1);
 
 		if (have_tvp7002()) {
-			mux |= 2;
+			mux |= 1;
 			resets &= ~BIT(2);
 			label = "tvp7002 HD";
 		} else {

arch/arm/mach-davinci/gpio.c

@@ -254,8 +254,10 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 {
 	struct davinci_gpio_regs __iomem *g;
 	u32 mask = 0xffff;
+	struct davinci_gpio_controller *d;
 
-	g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc);
+	d = (struct davinci_gpio_controller *)irq_desc_get_handler_data(desc);
+	g = (struct davinci_gpio_regs __iomem *)d->regs;
 
 	/* we only care about one bank */
 	if (irq & 1)
@@ -274,11 +276,14 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 		if (!status)
 			break;
 		__raw_writel(status, &g->intstat);
-		if (irq & 1)
-			status >>= 16;
 
 		/* now demux them to the right lowlevel handler */
-		n = (int)irq_get_handler_data(irq);
+		n = d->irq_base;
+		if (irq & 1) {
+			n += 16;
+			status >>= 16;
+		}
+
 		while (status) {
 			res = ffs(status);
 			n += res;
@@ -424,7 +429,13 @@ static int __init davinci_gpio_irq_setup(void)
 
 		/* set up all irqs in this bank */
 		irq_set_chained_handler(bank_irq, gpio_irq_handler);
-		irq_set_handler_data(bank_irq, (__force void *)g);
+
+		/*
+		 * Each chip handles 32 gpios, and each irq bank consists of 16
+		 * gpio irqs. Pass the irq bank's corresponding controller to
+		 * the chained irq handler.
+		 */
+		irq_set_handler_data(bank_irq, &chips[gpio / 32]);
 
 		for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) {
 			irq_set_chip(irq, &gpio_irqchip);

arch/arm/mach-davinci/include/mach/entry-macro.S

@@ -46,6 +46,3 @@
 #endif
 1002:
 		.endm
-
-		.macro	irq_prio_table
-		.endm

arch/arm/mach-davinci/irq.c

@@ -52,8 +52,14 @@ davinci_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num)
 	struct irq_chip_type *ct;
 
 	gc = irq_alloc_generic_chip("AINTC", 1, irq_start, base, handle_edge_irq);
+	if (!gc) {
+		pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n",
+		       __func__, irq_start);
+		return;
+	}
+
 	ct = gc->chip_types;
-	ct->chip.irq_ack = irq_gc_ack;
+	ct->chip.irq_ack = irq_gc_ack_set_bit;
 	ct->chip.irq_mask = irq_gc_mask_clr_bit;
 	ct->chip.irq_unmask = irq_gc_mask_set_bit;
 

arch/arm/mach-ep93xx/core.c

@@ -251,9 +251,9 @@ static void ep93xx_uart_set_mctrl(struct amba_device *dev,
 	unsigned int mcr;
 
 	mcr = 0;
-	if (!(mctrl & TIOCM_RTS))
+	if (mctrl & TIOCM_RTS)
 		mcr |= 2;
-	if (!(mctrl & TIOCM_DTR))
+	if (mctrl & TIOCM_DTR)
 		mcr |= 1;
 
 	__raw_writel(mcr, base + EP93XX_UART_MCR_OFFSET);

arch/arm/mach-exynos4/cpu.c

@@ -23,6 +23,7 @@
 #include <plat/sdhci.h>
 #include <plat/devs.h>
 #include <plat/fimc-core.h>
+#include <plat/iic-core.h>
 
 #include <mach/regs-irq.h>
 
@@ -132,6 +133,11 @@ void __init exynos4_map_io(void)
 	s3c_fimc_setname(1, "exynos4-fimc");
 	s3c_fimc_setname(2, "exynos4-fimc");
 	s3c_fimc_setname(3, "exynos4-fimc");
+
+	/* The I2C bus controllers are directly compatible with s3c2440 */
+	s3c_i2c0_setname("s3c2440-i2c");
+	s3c_i2c1_setname("s3c2440-i2c");
+	s3c_i2c2_setname("s3c2440-i2c");
 }
 
 void __init exynos4_init_clocks(int xtal)

arch/arm/mach-exynos4/dev-audio.c

@@ -330,7 +330,7 @@ struct platform_device exynos4_device_ac97 = {
 
 static int exynos4_spdif_cfg_gpio(struct platform_device *pdev)
 {
-	s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(3));
+	s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(4));
 
 	return 0;
 }

arch/arm/mach-exynos4/headsmp.S

@@ -13,7 +13,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-	__INIT
+	__CPUINIT
 
 /*
  * exynos4 specific entry point for secondary CPUs.  This provides

arch/arm/mach-exynos4/init.c

@@ -35,6 +35,7 @@ void __init exynos4_common_init_uarts(struct s3c2410_uartcfg *cfg, int no)
 			tcfg->clocks = exynos4_serial_clocks;
 			tcfg->clocks_size = ARRAY_SIZE(exynos4_serial_clocks);
 		}
+		tcfg->flags |= NO_NEED_CHECK_CLKSRC;
 	}
 
 	s3c24xx_init_uartdevs("s5pv210-uart", s5p_uart_resources, cfg, no);

arch/arm/mach-exynos4/mach-smdkv310.c

@@ -78,9 +78,7 @@ static struct s3c2410_uartcfg smdkv310_uartcfgs[] __initdata = {
 };
 
 static struct s3c_sdhci_platdata smdkv310_hsmmc0_pdata __initdata = {
-	.cd_type		= S3C_SDHCI_CD_GPIO,
-	.ext_cd_gpio		= EXYNOS4_GPK0(2),
-	.ext_cd_gpio_invert	= 1,
+	.cd_type		= S3C_SDHCI_CD_INTERNAL,
 	.clk_type		= S3C_SDHCI_CLK_DIV_EXTERNAL,
 #ifdef CONFIG_EXYNOS4_SDHCI_CH0_8BIT
 	.max_width		= 8,
@@ -96,9 +94,7 @@ static struct s3c_sdhci_platdata smdkv310_hsmmc1_pdata __initdata = {
 };
 
 static struct s3c_sdhci_platdata smdkv310_hsmmc2_pdata __initdata = {
-	.cd_type		= S3C_SDHCI_CD_GPIO,
-	.ext_cd_gpio		= EXYNOS4_GPK2(2),
-	.ext_cd_gpio_invert	= 1,
+	.cd_type		= S3C_SDHCI_CD_INTERNAL,
 	.clk_type		= S3C_SDHCI_CLK_DIV_EXTERNAL,
 #ifdef CONFIG_EXYNOS4_SDHCI_CH2_8BIT
 	.max_width		= 8,

arch/arm/mach-exynos4/platsmp.c

@@ -154,14 +154,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-	int i;
-
-	/*
-	 * Initialise the present map, which describes the set of CPUs
-	 * actually populated at the present time.
-	 */
-	for (i = 0; i < max_cpus; i++)
-		set_cpu_present(i, true);
 
 	scu_enable(scu_base_addr());
 

arch/arm/mach-exynos4/pm.c

@@ -280,7 +280,7 @@ static struct sleep_save exynos4_l2cc_save[] = {
 	SAVE_ITEM(S5P_VA_L2CC + L2X0_AUX_CTRL),
 };
 
-void exynos4_cpu_suspend(void)
+static int exynos4_cpu_suspend(unsigned long arg)
 {
 	unsigned long tmp;
 	unsigned long mask = 0xFFFFFFFF;

arch/arm/mach-exynos4/sleep.S

@@ -32,28 +32,6 @@
 
 	.text
 
-	/*
-	 * s3c_cpu_save
-	 *
-	 * entry:
-	 *	r1 = v:p offset
-	 */
-
-ENTRY(s3c_cpu_save)
-
-	stmfd	sp!, { r3 - r12, lr }
-	ldr	r3, =resume_with_mmu
-	bl	cpu_suspend
-
-	ldr	r0, =pm_cpu_sleep
-	ldr	r0, [ r0 ]
-	mov	pc, r0
-
-resume_with_mmu:
-	ldmfd	sp!, { r3 - r12, pc }
-
-	.ltorg
-
 	/*
 	 * sleep magic, to allow the bootloader to check for an valid
 	 * image to resume to. Must be the first word before the

arch/arm/mach-h720x/Kconfig

@@ -6,12 +6,14 @@ config ARCH_H7201
 	bool "gms30c7201"
 	depends on ARCH_H720X
 	select CPU_H7201
+	select ZONE_DMA
 	help
 	  Say Y here if you are using the Hynix GMS30C7201 Reference Board
 
 config ARCH_H7202
 	bool "hms30c7202"
 	select CPU_H7202
+	select ZONE_DMA
 	depends on ARCH_H720X
 	help
 	  Say Y here if you are using the Hynix HMS30C7202 Reference Board