Merge tag 'tegra-for-3.10-fixes-for-mmc' of...

Merge tag 'tegra-for-3.10-fixes-for-mmc' of git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra into mmc-next

ARM: tegra: DT-related fixes needed by the MMC tree

In order to convert the Tegra MMC driver to using mmc_of_parse(), some
bugs in the Tegra device-tree content need to be fixed first; it's
currently wrong but unused, and mmc_of_parse() causes that data to be
used for the first time.

Documentation/00-INDEX

@@ -299,6 +299,8 @@ memory-hotplug.txt
 	- Hotpluggable memory support, how to use and current status.
 memory.txt
 	- info on typical Linux memory problems.
+metag/
+	- directory with info about Linux on Meta architecture.
 mips/
 	- directory with info about Linux on MIPS architecture.
 misc-devices/

Documentation/ABI/testing/sysfs-bus-fcoe

-What:		/sys/bus/fcoe/ctlr_X
+What:		/sys/bus/fcoe/
+Date:		August 2012
+KernelVersion:	TBD
+Contact:	Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org
+Description:	The FCoE bus. Attributes in this directory are control interfaces.
+Attributes:
+
+	ctlr_create: 'FCoE Controller' instance creation interface. Writing an
+		     <ifname> to this file will allocate and populate sysfs with a
+		     fcoe_ctlr_device (ctlr_X). The user can then configure any
+		     per-port settings and finally write to the fcoe_ctlr_device's
+		     'start' attribute to begin the kernel's discovery and login
+		     process.
+
+	ctlr_destroy: 'FCoE Controller' instance removal interface. Writing a
+		       fcoe_ctlr_device's sysfs name to this file will log the
+		       fcoe_ctlr_device out of the fabric or otherwise connected
+		       FCoE devices. It will also free all kernel memory allocated
+		       for this fcoe_ctlr_device and any structures associated
+		       with it, this includes the scsi_host.
+
+What:		/sys/bus/fcoe/devices/ctlr_X
 Date:		March 2012
 KernelVersion:	TBD
 Contact:	Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org
-Description:	'FCoE Controller' instances on the fcoe bus
+Description:	'FCoE Controller' instances on the fcoe bus.
+		The FCoE Controller now has a three stage creation process.
+		1) Write interface name to ctlr_create 2) Configure the FCoE
+		Controller (ctlr_X) 3) Enable the FCoE Controller to begin
+		discovery and login. The FCoE Controller is destroyed by
+		writing it's name, i.e. ctlr_X to the ctlr_delete file.
+
 Attributes:
 
 	fcf_dev_loss_tmo: Device loss timeout peroid (see below). Changing
 			  this value will change the dev_loss_tmo for all
 			  FCFs discovered by this controller.
 
+	mode:		  Display or change the FCoE Controller's mode. Possible
+			  modes are 'Fabric' and 'VN2VN'. If a FCoE Controller
+			  is started in 'Fabric' mode then FIP FCF discovery is
+			  initiated and ultimately a fabric login is attempted.
+			  If a FCoE Controller is started in 'VN2VN' mode then
+			  FIP VN2VN discovery and login is performed. A FCoE
+			  Controller only supports one mode at a time.
+
+	enabled:	  Whether an FCoE controller is enabled or disabled.
+			  0 if disabled, 1 if enabled. Writing either 0 or 1
+			  to this file will enable or disable the FCoE controller.
+
 	lesb/link_fail:   Link Error Status Block (LESB) link failure count.
 
 	lesb/vlink_fail:  Link Error Status Block (LESB) virtual link
@@ -26,7 +65,7 @@ Attributes:
 
 Notes: ctlr_X (global increment starting at 0)
 
-What:		/sys/bus/fcoe/fcf_X
+What:		/sys/bus/fcoe/devices/fcf_X
 Date:		March 2012
 KernelVersion:	TBD
 Contact:	Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org

Documentation/ABI/testing/sysfs-platform-msi-laptop

+What:		/sys/devices/platform/msi-laptop-pf/lcd_level
+Date:		Oct 2006
+KernelVersion:	2.6.19
+Contact:	"Lennart Poettering <mzxreary@0pointer.de>"
+Description:
+		Screen brightness: contains a single integer in the range 0..8.
+
+What:		/sys/devices/platform/msi-laptop-pf/auto_brightness
+Date:		Oct 2006
+KernelVersion:	2.6.19
+Contact:	"Lennart Poettering <mzxreary@0pointer.de>"
+Description:
+		Enable automatic brightness control: contains either 0 or 1. If
+		set to 1 the hardware adjusts the screen brightness
+		automatically when the power cord is plugged/unplugged.
+
+What:		/sys/devices/platform/msi-laptop-pf/wlan
+Date:		Oct 2006
+KernelVersion:	2.6.19
+Contact:	"Lennart Poettering <mzxreary@0pointer.de>"
+Description:
+		WLAN subsystem enabled: contains either 0 or 1.
+
+What:		/sys/devices/platform/msi-laptop-pf/bluetooth
+Date:		Oct 2006
+KernelVersion:	2.6.19
+Contact:	"Lennart Poettering <mzxreary@0pointer.de>"
+Description:
+		Bluetooth subsystem enabled: contains either 0 or 1. Please
+		note that this file is constantly 0 if no Bluetooth hardware is
+		available.
+
+What:		/sys/devices/platform/msi-laptop-pf/touchpad
+Date:		Nov 2012
+KernelVersion:	3.8
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Contains either 0 or 1 and indicates if touchpad is turned on.
+		Touchpad state can only be toggled by pressing Fn+F3.
+
+What:		/sys/devices/platform/msi-laptop-pf/turbo_mode
+Date:		Nov 2012
+KernelVersion:	3.8
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Contains either 0 or 1 and indicates if turbo mode is turned
+		on. In turbo mode power LED is orange and processor is
+		overclocked. Turbo mode is available only if charging. It is
+		only possible to toggle turbo mode state by pressing Fn+F10,
+		and there is a few seconds cooldown between subsequent toggles.
+		If user presses Fn+F10 too frequent, turbo mode state is not
+		changed.
+
+What:		/sys/devices/platform/msi-laptop-pf/eco_mode
+Date:		Nov 2012
+KernelVersion:	3.8
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Contains either 0 or 1 and indicates if ECO mode is turned on.
+		In ECO mode power LED is green and userspace should do some
+		powersaving actions. ECO mode is available only on battery
+		power. ECO mode can only be toggled by pressing Fn+F10.
+
+What:		/sys/devices/platform/msi-laptop-pf/turbo_cooldown
+Date:		Nov 2012
+KernelVersion:	3.8
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Contains value in range 0..3:
+			* 0 -> Turbo mode is off
+			* 1 -> Turbo mode is on, cannot be turned off yet
+			* 2 -> Turbo mode is off, cannot be turned on yet
+			* 3 -> Turbo mode is on
+
+What:		/sys/devices/platform/msi-laptop-pf/auto_fan
+Date:		Nov 2012
+KernelVersion:	3.8
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Contains either 0 or 1 and indicates if fan speed is controlled
+		automatically (1) or fan runs at maximal speed (0). Can be
+		toggled in software.
+

Documentation/DMA-API-HOWTO.txt

@@ -488,9 +488,10 @@ will invoke the generic mapping error check interface. Doing so will ensure
 that the mapping code will work correctly on all dma implementations without
 any dependency on the specifics of the underlying implementation. Using the
 returned address without checking for errors could result in failures ranging
-from panics to silent data corruption. Couple of example of incorrect ways to
-check for errors that make assumptions about the underlying dma implementation
-are as follows and these are applicable to dma_map_page() as well.
+from panics to silent data corruption. A couple of examples of incorrect ways
+to check for errors that make assumptions about the underlying dma
+implementation are as follows and these are applicable to dma_map_page() as
+well.
 
 Incorrect example 1:
 	dma_addr_t dma_handle;
@@ -751,7 +752,7 @@ Example 1:
 		dma_unmap_single(dma_handle1);
 	map_error_handling1:
 
-Example 2: (if buffers are allocated a loop, unmap all mapped buffers when
+Example 2: (if buffers are allocated in a loop, unmap all mapped buffers when
 	    mapping error is detected in the middle)
 
 	dma_addr_t dma_addr;

Documentation/IPMI.txt

@@ -348,34 +348,40 @@ You can change this at module load time (for a module) with:
 
   modprobe ipmi_si.o type=<type1>,<type2>....
        ports=<port1>,<port2>... addrs=<addr1>,<addr2>...
-       irqs=<irq1>,<irq2>... trydefaults=[0|1]
+       irqs=<irq1>,<irq2>...
        regspacings=<sp1>,<sp2>,... regsizes=<size1>,<size2>,...
        regshifts=<shift1>,<shift2>,...
        slave_addrs=<addr1>,<addr2>,...
        force_kipmid=<enable1>,<enable2>,...
        kipmid_max_busy_us=<ustime1>,<ustime2>,...
        unload_when_empty=[0|1]
+       trydefaults=[0|1] trydmi=[0|1] tryacpi=[0|1]
+       tryplatform=[0|1] trypci=[0|1]
 
-Each of these except si_trydefaults is a list, the first item for the
+Each of these except try... items is a list, the first item for the
 first interface, second item for the second interface, etc.
 
 The si_type may be either "kcs", "smic", or "bt".  If you leave it blank, it
 defaults to "kcs".
 
-If you specify si_addrs as non-zero for an interface, the driver will
+If you specify addrs as non-zero for an interface, the driver will
 use the memory address given as the address of the device.  This
 overrides si_ports.
 
-If you specify si_ports as non-zero for an interface, the driver will
+If you specify ports as non-zero for an interface, the driver will
 use the I/O port given as the device address.
 
-If you specify si_irqs as non-zero for an interface, the driver will
+If you specify irqs as non-zero for an interface, the driver will
 attempt to use the given interrupt for the device.
 
-si_trydefaults sets whether the standard IPMI interface at 0xca2 and
+trydefaults sets whether the standard IPMI interface at 0xca2 and
 any interfaces specified by ACPE are tried.  By default, the driver
 tries it, set this value to zero to turn this off.
 
+The other try... items disable discovery by their corresponding
+names.  These are all enabled by default, set them to zero to disable
+them.  The tryplatform disables openfirmware.
+
 The next three parameters have to do with register layout.  The
 registers used by the interfaces may not appear at successive
 locations and they may not be in 8-bit registers.  These parameters

Documentation/block/cfq-iosched.txt

@@ -102,6 +102,64 @@ processing of request. Therefore, increasing the value can imporve the
 performace although this can cause the latency of some I/O to increase due
 to more number of requests.
 
+CFQ Group scheduling
+====================
+
+CFQ supports blkio cgroup and has "blkio." prefixed files in each
+blkio cgroup directory. It is weight-based and there are four knobs
+for configuration - weight[_device] and leaf_weight[_device].
+Internal cgroup nodes (the ones with children) can also have tasks in
+them, so the former two configure how much proportion the cgroup as a
+whole is entitled to at its parent's level while the latter two
+configure how much proportion the tasks in the cgroup have compared to
+its direct children.
+
+Another way to think about it is assuming that each internal node has
+an implicit leaf child node which hosts all the tasks whose weight is
+configured by leaf_weight[_device]. Let's assume a blkio hierarchy
+composed of five cgroups - root, A, B, AA and AB - with the following
+weights where the names represent the hierarchy.
+
+        weight leaf_weight
+ root :  125    125
+ A    :  500    750
+ B    :  250    500
+ AA   :  500    500
+ AB   : 1000    500
+
+root never has a parent making its weight is meaningless. For backward
+compatibility, weight is always kept in sync with leaf_weight. B, AA
+and AB have no child and thus its tasks have no children cgroup to
+compete with. They always get 100% of what the cgroup won at the
+parent level. Considering only the weights which matter, the hierarchy
+looks like the following.
+
+          root
+       /    |   \
+      A     B    leaf
+     500   250   125
+   /  |  \
+  AA  AB  leaf
+ 500 1000 750
+
+If all cgroups have active IOs and competing with each other, disk
+time will be distributed like the following.
+
+Distribution below root. The total active weight at this level is
+A:500 + B:250 + C:125 = 875.
+
+ root-leaf :   125 /  875      =~ 14%
+ A         :   500 /  875      =~ 57%
+ B(-leaf)  :   250 /  875      =~ 28%
+
+A has children and further distributes its 57% among the children and
+the implicit leaf node. The total active weight at this level is
+AA:500 + AB:1000 + A-leaf:750 = 2250.
+
+ A-leaf    : ( 750 / 2250) * A =~ 19%
+ AA(-leaf) : ( 500 / 2250) * A =~ 12%
+ AB(-leaf) : (1000 / 2250) * A =~ 25%
+
 CFQ IOPS Mode for group scheduling
 ===================================
 Basic CFQ design is to provide priority based time slices. Higher priority

Documentation/blockdev/nbd.txt

@@ -4,43 +4,13 @@
    can use a remote server as one of its block devices. So every time
    the client computer wants to read, e.g., /dev/nb0, it sends a
    request over TCP to the server, which will reply with the data read.
-   This can be used for stations with low disk space (or even diskless -
-   if you boot from floppy) to borrow disk space from another computer.
-   Unlike NFS, it is possible to put any filesystem on it, etc. It should
-   even be possible to use NBD as a root filesystem (I've never tried),
-   but it requires a user-level program to be in the initrd to start.
-   It also allows you to run block-device in user land (making server
-   and client physically the same computer, communicating using loopback).
-   
-   Current state: It currently works. Network block device is stable.
-   I originally thought that it was impossible to swap over TCP. It
-   turned out not to be true - swapping over TCP now works and seems
-   to be deadlock-free, but it requires heavy patches into Linux's
-   network layer.
-   
+   This can be used for stations with low disk space (or even diskless)
+   to borrow disk space from another computer.
+   Unlike NFS, it is possible to put any filesystem on it, etc.
+
    For more information, or to download the nbd-client and nbd-server
    tools, go to http://nbd.sf.net/.
 
-   Howto: To setup nbd, you can simply do the following:
-
-   First, serve a device or file from a remote server:
-
-   nbd-server <port-number> <device-or-file-to-serve-to-client>
-
-   e.g.,
-	root@server1 # nbd-server 1234 /dev/sdb1
-
-	(serves sdb1 partition on TCP port 1234)
-
-   Then, on the local (client) system:
-
-   nbd-client <server-name-or-IP> <server-port-number> /dev/nb[0-n]
-
-   e.g.,
-	root@client1 # nbd-client server1 1234 /dev/nb0
-
-	(creates the nb0 device on client1)
-
    The nbd kernel module need only be installed on the client
    system, as the nbd-server is completely in userspace. In fact,
    the nbd-server has been successfully ported to other operating

Documentation/cgroups/blkio-controller.txt

@@ -75,7 +75,7 @@ Throttling/Upper Limit policy
         mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
 
 - Specify a bandwidth rate on particular device for root group. The format
-  for policy is "<major>:<minor>  <byes_per_second>".
+  for policy is "<major>:<minor>  <bytes_per_second>".
 
         echo "8:16  1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device
 
@@ -94,13 +94,11 @@ Throttling/Upper Limit policy
 
 Hierarchical Cgroups
 ====================
-- Currently none of the IO control policy supports hierarchical groups. But
-  cgroup interface does allow creation of hierarchical cgroups and internally
-  IO policies treat them as flat hierarchy.
+- Currently only CFQ supports hierarchical groups. For throttling,
+  cgroup interface does allow creation of hierarchical cgroups and
+  internally it treats them as flat hierarchy.
 
-  So this patch will allow creation of cgroup hierarchcy but at the backend
-  everything will be treated as flat. So if somebody created a hierarchy like
-  as follows.
+  If somebody created a hierarchy like as follows.
 
 			root
 			/  \
@@ -108,16 +106,20 @@ Hierarchical Cgroups
 			|
 		     test3
 
-  CFQ and throttling will practically treat all groups at same level.
+  CFQ will handle the hierarchy correctly but and throttling will
+  practically treat all groups at same level. For details on CFQ
+  hierarchy support, refer to Documentation/block/cfq-iosched.txt.
+  Throttling will treat the hierarchy as if it looks like the
+  following.
 
 				pivot
 			     /  /   \  \
 			root  test1 test2  test3
 
-  Down the line we can implement hierarchical accounting/control support
-  and also introduce a new cgroup file "use_hierarchy" which will control
-  whether cgroup hierarchy is viewed as flat or hierarchical by the policy..
-  This is how memory controller also has implemented the things.
+  Nesting cgroups, while allowed, isn't officially supported and blkio
+  genereates warning when cgroups nest. Once throttling implements
+  hierarchy support, hierarchy will be supported and the warning will
+  be removed.
 
 Various user visible config options
 ===================================
@@ -172,6 +174,12 @@ Proportional weight policy files
 	  dev     weight
 	  8:16    300
 
+- blkio.leaf_weight[_device]
+	- Equivalents of blkio.weight[_device] for the purpose of
+          deciding how much weight tasks in the given cgroup has while
+          competing with the cgroup's child cgroups. For details,
+          please refer to Documentation/block/cfq-iosched.txt.
+
 - blkio.time
 	- disk time allocated to cgroup per device in milliseconds. First
 	  two fields specify the major and minor number of the device and
@@ -279,6 +287,11 @@ Proportional weight policy files
 	  and minor number of the device and third field specifies the number
 	  of times a group was dequeued from a particular device.
 
+- blkio.*_recursive
+	- Recursive version of various stats. These files show the
+          same information as their non-recursive counterparts but
+          include stats from all the descendant cgroups.
+
 Throttling/Upper limit policy files
 -----------------------------------
 - blkio.throttle.read_bps_device

Documentation/coccinelle.txt

@@ -87,6 +87,10 @@ As any static code analyzer, Coccinelle produces false
 positives. Thus, reports must be carefully checked, and patches
 reviewed.
 
+To enable verbose messages set the V= variable, for example:
+
+   make coccicheck MODE=report V=1
+
 
  Using Coccinelle with a single semantic patch
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Documentation/device-mapper/cache-policies.txt

+Guidance for writing policies
+=============================
+
+Try to keep transactionality out of it.  The core is careful to
+avoid asking about anything that is migrating.  This is a pain, but
+makes it easier to write the policies.
+
+Mappings are loaded into the policy at construction time.
+
+Every bio that is mapped by the target is referred to the policy.
+The policy can return a simple HIT or MISS or issue a migration.
+
+Currently there's no way for the policy to issue background work,
+e.g. to start writing back dirty blocks that are going to be evicte
+soon.
+
+Because we map bios, rather than requests it's easy for the policy
+to get fooled by many small bios.  For this reason the core target
+issues periodic ticks to the policy.  It's suggested that the policy
+doesn't update states (eg, hit counts) for a block more than once
+for each tick.  The core ticks by watching bios complete, and so
+trying to see when the io scheduler has let the ios run.
+
+
+Overview of supplied cache replacement policies
+===============================================
+
+multiqueue
+----------
+
+This policy is the default.
+
+The multiqueue policy has two sets of 16 queues: one set for entries
+waiting for the cache and another one for those in the cache.
+Cache entries in the queues are aged based on logical time. Entry into
+the cache is based on variable thresholds and queue selection is based
+on hit count on entry. The policy aims to take different cache miss
+costs into account and to adjust to varying load patterns automatically.
+
+Message and constructor argument pairs are:
+	'sequential_threshold <#nr_sequential_ios>' and
+	'random_threshold <#nr_random_ios>'.
+
+The sequential threshold indicates the number of contiguous I/Os
+required before a stream is treated as sequential.  The random threshold
+is the number of intervening non-contiguous I/Os that must be seen
+before the stream is treated as random again.
+
+The sequential and random thresholds default to 512 and 4 respectively.
+
+Large, sequential ios are probably better left on the origin device
+since spindles tend to have good bandwidth. The io_tracker counts
+contiguous I/Os to try to spot when the io is in one of these sequential
+modes.
+
+cleaner
+-------
+
+The cleaner writes back all dirty blocks in a cache to decommission it.
+
+Examples
+========
+
+The syntax for a table is:
+	cache <metadata dev> <cache dev> <origin dev> <block size>
+	<#feature_args> [<feature arg>]*
+	<policy> <#policy_args> [<policy arg>]*
+
+The syntax to send a message using the dmsetup command is:
+	dmsetup message <mapped device> 0 sequential_threshold 1024
+	dmsetup message <mapped device> 0 random_threshold 8
+
+Using dmsetup:
+	dmsetup create blah --table "0 268435456 cache /dev/sdb /dev/sdc \
+	    /dev/sdd 512 0 mq 4 sequential_threshold 1024 random_threshold 8"
+	creates a 128GB large mapped device named 'blah' with the
+	sequential threshold set to 1024 and the random_threshold set to 8.

Documentation/device-mapper/cache.txt

+Introduction
+============
+
+dm-cache is a device mapper target written by Joe Thornber, Heinz
+Mauelshagen, and Mike Snitzer.
+
+It aims to improve performance of a block device (eg, a spindle) by
+dynamically migrating some of its data to a faster, smaller device
+(eg, an SSD).
+
+This device-mapper solution allows us to insert this caching at
+different levels of the dm stack, for instance above the data device for
+a thin-provisioning pool.  Caching solutions that are integrated more
+closely with the virtual memory system should give better performance.
+
+The target reuses the metadata library used in the thin-provisioning
+library.
+
+The decision as to what data to migrate and when is left to a plug-in
+policy module.  Several of these have been written as we experiment,
+and we hope other people will contribute others for specific io
+scenarios (eg. a vm image server).
+
+Glossary
+========
+
+  Migration -  Movement of the primary copy of a logical block from one
+	       device to the other.
+  Promotion -  Migration from slow device to fast device.
+  Demotion  -  Migration from fast device to slow device.
+
+The origin device always contains a copy of the logical block, which
+may be out of date or kept in sync with the copy on the cache device
+(depending on policy).
+
+Design
+======
+
+Sub-devices
+-----------
+
+The target is constructed by passing three devices to it (along with
+other parameters detailed later):
+
+1. An origin device - the big, slow one.
+
+2. A cache device - the small, fast one.
+
+3. A small metadata device - records which blocks are in the cache,
+   which are dirty, and extra hints for use by the policy object.
+   This information could be put on the cache device, but having it
+   separate allows the volume manager to configure it differently,
+   e.g. as a mirror for extra robustness.
+
+Fixed block size
+----------------
+
+The origin is divided up into blocks of a fixed size.  This block size
+is configurable when you first create the cache.  Typically we've been
+using block sizes of 256k - 1024k.
+
+Having a fixed block size simplifies the target a lot.  But it is
+something of a compromise.  For instance, a small part of a block may be
+getting hit a lot, yet the whole block will be promoted to the cache.
+So large block sizes are bad because they waste cache space.  And small
+block sizes are bad because they increase the amount of metadata (both
+in core and on disk).
+
+Writeback/writethrough
+----------------------
+
+The cache has two modes, writeback and writethrough.
+
+If writeback, the default, is selected then a write to a block that is
+cached will go only to the cache and the block will be marked dirty in
+the metadata.
+
+If writethrough is selected then a write to a cached block will not
+complete until it has hit both the origin and cache devices.  Clean
+blocks should remain clean.
+
+A simple cleaner policy is provided, which will clean (write back) all
+dirty blocks in a cache.  Useful for decommissioning a cache.
+
+Migration throttling
+--------------------
+
+Migrating data between the origin and cache device uses bandwidth.
+The user can set a throttle to prevent more than a certain amount of
+migration occuring at any one time.  Currently we're not taking any
+account of normal io traffic going to the devices.  More work needs
+doing here to avoid migrating during those peak io moments.
+
+For the time being, a message "migration_threshold <#sectors>"
+can be used to set the maximum number of sectors being migrated,
+the default being 204800 sectors (or 100MB).
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
+written.  If no such requests are made then commits will occur every
+second.  This means the cache behaves like a physical disk that has a
+write cache (the same is true of the thin-provisioning target).  If
+power is lost you may lose some recent writes.  The metadata should
+always be consistent in spite of any crash.
+
+The 'dirty' state for a cache block changes far too frequently for us
+to keep updating it on the fly.  So we treat it as a hint.  In normal
+operation it will be written when the dm device is suspended.  If the
+system crashes all cache blocks will be assumed dirty when restarted.
+
+Per-block policy hints
+----------------------
+
+Policy plug-ins can store a chunk of data per cache block.  It's up to
+the policy how big this chunk is, but it should be kept small.  Like the
+dirty flags this data is lost if there's a crash so a safe fallback
+value should always be possible.
+
+For instance, the 'mq' policy, which is currently the default policy,
+uses this facility to store the hit count of the cache blocks.  If
+there's a crash this information will be lost, which means the cache
+may be less efficient until those hit counts are regenerated.
+
+Policy hints affect performance, not correctness.
+
+Policy messaging
+----------------
+
+Policies will have different tunables, specific to each one, so we
+need a generic way of getting and setting these.  Device-mapper
+messages are used.  Refer to cache-policies.txt.
+
+Discard bitset resolution
+-------------------------
+
+We can avoid copying data during migration if we know the block has
+been discarded.  A prime example of this is when mkfs discards the
+whole block device.  We store a bitset tracking the discard state of
+blocks.  However, we allow this bitset to have a different block size
+from the cache blocks.  This is because we need to track the discard
+state for all of the origin device (compare with the dirty bitset
+which is just for the smaller cache device).
+
+Target interface
+================
+
+Constructor
+-----------
+
+ cache <metadata dev> <cache dev> <origin dev> <block size>
+       <#feature args> [<feature arg>]*
+       <policy> <#policy args> [policy args]*
+
+ metadata dev    : fast device holding the persistent metadata
+ cache dev	 : fast device holding cached data blocks
+ origin dev	 : slow device holding original data blocks
+ block size      : cache unit size in sectors
+
+ #feature args   : number of feature arguments passed
+ feature args    : writethrough.  (The default is writeback.)
+
+ policy          : the replacement policy to use
+ #policy args    : an even number of arguments corresponding to
+                   key/value pairs passed to the policy
+ policy args     : key/value pairs passed to the policy
+		   E.g. 'sequential_threshold 1024'
+		   See cache-policies.txt for details.
+
+Optional feature arguments are:
+   writethrough  : write through caching that prohibits cache block
+		   content from being different from origin block content.
+		   Without this argument, the default behaviour is to write
+		   back cache block contents later for performance reasons,
+		   so they may differ from the corresponding origin blocks.
+
+A policy called 'default' is always registered.  This is an alias for
+the policy we currently think is giving best all round performance.
+
+As the default policy could vary between kernels, if you are relying on
+the characteristics of a specific policy, always request it by name.
+
+Status
+------
+
+<#used metadata blocks>/<#total metadata blocks> <#read hits> <#read misses>
+<#write hits> <#write misses> <#demotions> <#promotions> <#blocks in cache>
+<#dirty> <#features> <features>* <#core args> <core args>* <#policy args>
+<policy args>*
+
+#used metadata blocks    : Number of metadata blocks used
+#total metadata blocks   : Total number of metadata blocks
+#read hits               : Number of times a READ bio has been mapped
+			     to the cache
+#read misses             : Number of times a READ bio has been mapped
+			     to the origin
+#write hits              : Number of times a WRITE bio has been mapped
+			     to the cache
+#write misses            : Number of times a WRITE bio has been
+			     mapped to the origin
+#demotions               : Number of times a block has been removed
+			     from the cache
+#promotions              : Number of times a block has been moved to
+			     the cache
+#blocks in cache         : Number of blocks resident in the cache
+#dirty                   : Number of blocks in the cache that differ
+			     from the origin
+#feature args            : Number of feature args to follow
+feature args             : 'writethrough' (optional)
+#core args               : Number of core arguments (must be even)
+core args                : Key/value pairs for tuning the core
+			     e.g. migration_threshold
+#policy args             : Number of policy arguments to follow (must be even)
+policy args              : Key/value pairs
+			     e.g. 'sequential_threshold 1024
+
+Messages
+--------
+
+Policies will have different tunables, specific to each one, so we
+need a generic way of getting and setting these.  Device-mapper
+messages are used.  (A sysfs interface would also be possible.)
+
+The message format is:
+
+   <key> <value>
+
+E.g.
+   dmsetup message my_cache 0 sequential_threshold 1024
+
+Examples
+========
+
+The test suite can be found here:
+
+https://github.com/jthornber/thinp-test-suite
+
+dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \
+	/dev/mapper/ssd /dev/mapper/origin 512 1 writeback default 0'
+dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \
+	/dev/mapper/ssd /dev/mapper/origin 1024 1 writeback \
+	mq 4 sequential_threshold 1024 random_threshold 8'

Documentation/devicetree/bindings/arc/interrupts.txt

+* ARC700 incore Interrupt Controller
+
+  The core interrupt controller provides 32 prioritised interrupts (2 levels)
+  to ARC700 core.
+
+Properties:
+
+- compatible: "snps,arc700-intc"
+- interrupt-controller: This is an interrupt controller.
+- #interrupt-cells: Must be <1>.
+
+  Single Cell "interrupts" property of a device specifies the IRQ number
+  between 0 to 31
+
+  intc accessed via the special ARC AUX register interface, hence "reg" property
+  is not specified.
+
+Example:
+
+	intc: interrupt-controller {
+		compatible = "snps,arc700-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};

Documentation/devicetree/bindings/arm/armadeus.txt

+Armadeus i.MX Platforms Device Tree Bindings
+-----------------------------------------------
+
+APF51: i.MX51 based module.
+Required root node properties:
+    - compatible = "armadeus,imx51-apf51", "fsl,imx51";

Documentation/devicetree/bindings/arm/fsl.txt

@@ -5,6 +5,14 @@ i.MX23 Evaluation Kit
 Required root node properties:
     - compatible = "fsl,imx23-evk", "fsl,imx23";
 
+i.MX25 Product Development Kit
+Required root node properties:
+    - compatible = "fsl,imx25-pdk", "fsl,imx25";
+
+i.MX27 Product Development Kit
+Required root node properties:
+    - compatible = "fsl,imx27-pdk", "fsl,imx27";
+
 i.MX28 Evaluation Kit
 Required root node properties:
     - compatible = "fsl,imx28-evk", "fsl,imx28";

Documentation/devicetree/bindings/clock/imx5-clock.txt

@@ -171,6 +171,7 @@ clocks and IDs.
 	can_sel			156
 	can1_serial_gate	157
 	can1_ipg_gate		158
+	owire_gate		159
 
 Examples (for mx53):
 

Documentation/devicetree/bindings/clock/imx6q-clock.txt

@@ -203,6 +203,8 @@ clocks and IDs.
 	pcie_ref		188
 	pcie_ref_125m		189
 	enet_ref		190
+	usbphy1_gate		191
+	usbphy2_gate		192
 
 Examples:
 

Documentation/devicetree/bindings/dma/snps-dma.txt

@@ -3,59 +3,61 @@
 Required properties:
 - compatible: "snps,dma-spear1340"
 - reg: Address range of the DMAC registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the DMAC interrupt number
-- nr_channels: Number of channels supported by hardware
-- is_private: The device channels should be marked as private and not for by the
-  general purpose DMA channel allocator. False if not passed.
+- dma-channels: Number of channels supported by hardware
+- dma-requests: Number of DMA request lines supported, up to 16
+- dma-masters: Number of AHB masters supported by the controller
+- #dma-cells: must be <3>
 - chan_allocation_order: order of allocation of channel, 0 (default): ascending,
   1: descending
 - chan_priority: priority of channels. 0 (default): increase from chan 0->n, 1:
   increase from chan n->0
 - block_size: Maximum block size supported by the controller
-- nr_masters: Number of AHB masters supported by the controller
 - data_width: Maximum data width supported by hardware per AHB master
   (0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
-- slave_info:
-	- bus_id: name of this device channel, not just a device name since
-	  devices may have more than one channel e.g. "foo_tx". For using the
-	  dw_generic_filter(), slave drivers must pass exactly this string as
-	  param to filter function.
-	- cfg_hi: Platform-specific initializer for the CFG_HI register
-	- cfg_lo: Platform-specific initializer for the CFG_LO register
-	- src_master: src master for transfers on allocated channel.
-	- dst_master: dest master for transfers on allocated channel.
+
+
+Optional properties:
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- is_private: The device channels should be marked as private and not for by the
+  general purpose DMA channel allocator. False if not passed.
 
 Example:
 
-	dma@fc000000 {
+	dmahost: dma@fc000000 {
 		compatible = "snps,dma-spear1340";
 		reg = <0xfc000000 0x1000>;
 		interrupt-parent = <&vic1>;
 		interrupts = <12>;
 
-		nr_channels = <8>;
+		dma-channels = <8>;
+		dma-requests = <16>;
+		dma-masters = <2>;
+		#dma-cells = <3>;
 		chan_allocation_order = <1>;
 		chan_priority = <1>;
 		block_size = <0xfff>;
-		nr_masters = <2>;
 		data_width = <3 3 0 0>;
+	};
 
-		slave_info {
-			uart0-tx {
-				bus_id = "uart0-tx";
-				cfg_hi = <0x4000>;	/* 0x8 << 11 */
-				cfg_lo = <0>;
-				src_master = <0>;
-				dst_master = <1>;
-			};
-			spi0-tx {
-				bus_id = "spi0-tx";
-				cfg_hi = <0x2000>;	/* 0x4 << 11 */
-				cfg_lo = <0>;
-				src_master = <0>;
-				dst_master = <0>;
-			};
-		};
+DMA clients connected to the Designware DMA controller must use the format
+described in the dma.txt file, using a four-cell specifier for each channel.
+The four cells in order are:
+
+1. A phandle pointing to the DMA controller
+2. The DMA request line number
+3. Source master for transfers on allocated channel
+4. Destination master for transfers on allocated channel
+
+Example:
+	
+	serial@e0000000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0xe0000000 0x1000>;
+		interrupts = <0 35 0x4>;
+		status = "disabled";
+		dmas = <&dmahost 12 0 1>,
+			<&dmahost 13 0 1 0>;
+		dma-names = "rx", "rx";
 	};

Documentation/devicetree/bindings/metag/meta-intc.txt

+* Meta External Trigger Controller Binding
+
+This binding specifies what properties must be available in the device tree
+representation of a Meta external trigger controller.
+
+Required properties:
+
+    - compatible: Specifies the compatibility list for the interrupt controller.
+      The type shall be <string> and the value shall include "img,meta-intc".
+
+    - num-banks: Specifies the number of interrupt banks (each of which can
+      handle 32 interrupt sources).
+
+    - interrupt-controller: The presence of this property identifies the node
+      as an interupt controller. No property value shall be defined.
+
+    - #interrupt-cells: Specifies the number of cells needed to encode an
+      interrupt source. The type shall be a <u32> and the value shall be 2.
+
+    - #address-cells: Specifies the number of cells needed to encode an
+      address. The type shall be <u32> and the value shall be 0. As such,
+      'interrupt-map' nodes do not have to specify a parent unit address.
+
+Optional properties:
+
+    - no-mask: The controller doesn't have any mask registers.
+
+* Interrupt Specifier Definition
+
+  Interrupt specifiers consists of 2 cells encoded as follows:
+
+    - <1st-cell>: The interrupt-number that identifies the interrupt source.
+
+    - <2nd-cell>: The Linux interrupt flags containing level-sense information,
+                  encoded as follows:
+                    1 = edge triggered
+                    4 = level-sensitive
+
+* Examples
+
+Example 1:
+
+	/*
+	 * Meta external trigger block
+	 */
+	intc: intc {
+		// This is an interrupt controller node.
+		interrupt-controller;
+
+		// No address cells so that 'interrupt-map' nodes which
+		// reference this interrupt controller node do not need a parent
+		// address specifier.
+		#address-cells = <0>;
+
+		// Two cells to encode interrupt sources.
+		#interrupt-cells = <2>;
+
+		// Number of interrupt banks
+		num-banks = <2>;
+
+		// No HWMASKEXT is available (specify on Chorus2 and Comet ES1)
+		no-mask;
+
+		// Compatible with Meta hardware trigger block.
+		compatible = "img,meta-intc";
+	};
+
+Example 2:
+
+	/*
+	 * An interrupt generating device that is wired to a Meta external
+	 * trigger block.
+	 */
+	uart1: uart@0x02004c00 {
+		// Interrupt source '5' that is level-sensitive.
+		// Note that there are only two cells as specified in the
+		// interrupt parent's '#interrupt-cells' property.
+		interrupts = <5 4 /* level */>;
+
+		// The interrupt controller that this device is wired to.
+		interrupt-parent = <&intc>;
+	};

Documentation/devicetree/bindings/mips/cpu_irq.txt

+MIPS CPU interrupt controller
+
+On MIPS the mips_cpu_intc_init() helper can be used to initialize the 8 CPU
+IRQs from a devicetree file and create a irq_domain for IRQ controller.
+
+With the irq_domain in place we can describe how the 8 IRQs are wired to the
+platforms internal interrupt controller cascade.
+
+Below is an example of a platform describing the cascade inside the devicetree
+and the code used to load it inside arch_init_irq().
+
+Required properties:
+- compatible : Should be "mti,cpu-interrupt-controller"
+
+Example devicetree:
+	cpu-irq: cpu-irq@0 {
+		#address-cells = <0>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		compatible = "mti,cpu-interrupt-controller";
+	};
+
+	intc: intc@200 {
+		compatible = "ralink,rt2880-intc";
+		reg = <0x200 0x100>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		interrupt-parent = <&cpu-irq>;
+		interrupts = <2>;
+	};
+
+
+Example platform irq.c:
+static struct of_device_id __initdata of_irq_ids[] = {
+	{ .compatible = "mti,cpu-interrupt-controller", .data = mips_cpu_intc_init },
+	{ .compatible = "ralink,rt2880-intc", .data = intc_of_init },
+	{},
+};
+
+void __init arch_init_irq(void)
+{
+	of_irq_init(of_irq_ids);
+}

Documentation/devicetree/bindings/mtd/elm.txt

+Error location module
+
+Required properties:
+- compatible: Must be "ti,am33xx-elm"
+- reg: physical base address and size of the registers map.
+- interrupts: Interrupt number for the elm.
+
+Optional properties:
+- ti,hwmods: Name of the hwmod associated to the elm
+
+Example:
+elm: elm@0 {
+	compatible = "ti,am3352-elm";
+	reg = <0x48080000 0x2000>;
+	interrupts = <4>;
+};

Documentation/devicetree/bindings/mtd/mtd-physmap.txt

@@ -26,6 +26,9 @@ file systems on embedded devices.
  - linux,mtd-name: allow to specify the mtd name for retro capability with
    physmap-flash drivers as boot loader pass the mtd partition via the old
    device name physmap-flash.
+ - use-advanced-sector-protection: boolean to enable support for the
+   advanced sector protection (Spansion: PPB - Persistent Protection
+   Bits) locking.
 
 For JEDEC compatible devices, the following additional properties
 are defined:

Documentation/devicetree/bindings/serial/lantiq_asc.txt

+Lantiq SoC ASC serial controller
+
+Required properties:
+- compatible : Should be "lantiq,asc"
+- reg : Address and length of the register set for the device
+- interrupts: the 3 (tx rx err) interrupt numbers. The interrupt specifier
+  depends on the interrupt-parent interrupt controller.
+
+Example:
+
+asc1: serial@E100C00 {
+	compatible = "lantiq,asc";
+	reg = <0xE100C00 0x400>;
+	interrupt-parent = <&icu0>;
+	interrupts = <112 113 114>;
+};

Documentation/devicetree/bindings/thermal/dove-thermal.txt

+* Dove Thermal
+
+This driver is for Dove SoCs which contain a thermal sensor.
+
+Required properties:
+- compatible : "marvell,dove-thermal"
+- reg : Address range of the thermal registers
+
+The reg properties should contain two ranges. The first is for the
+three Thermal Manager registers, while the second range contains the
+Thermal Diode Control Registers.
+
+Example:
+
+	thermal@10078 {
+		compatible = "marvell,dove-thermal";
+		reg = <0xd001c 0x0c>, <0xd005c 0x08>;
+	};

Documentation/devicetree/bindings/thermal/kirkwood-thermal.txt

+* Kirkwood Thermal
+
+This version is for Kirkwood 88F8262 & 88F6283 SoCs. Other kirkwoods
+don't contain a thermal sensor.
+
+Required properties:
+- compatible : "marvell,kirkwood-thermal"
+- reg : Address range of the thermal registers
+
+Example:
+
+	thermal@10078 {
+		compatible = "marvell,kirkwood-thermal";
+		reg = <0x10078 0x4>;
+	};

Documentation/devicetree/bindings/thermal/rcar-thermal.txt

+* Renesas R-Car Thermal
+
+Required properties:
+- compatible		: "renesas,rcar-thermal"
+- reg			: Address range of the thermal registers.
+			  The 1st reg will be recognized as common register
+			  if it has "interrupts".
+
+Option properties:
+
+- interrupts		: use interrupt
+
+Example (non interrupt support):
+
+thermal@e61f0100 {
+	compatible = "renesas,rcar-thermal";
+	reg = <0xe61f0100 0x38>;
+};
+
+Example (interrupt support):
+
+thermal@e61f0000 {
+	compatible = "renesas,rcar-thermal";
+	reg = <0xe61f0000 0x14
+		0xe61f0100 0x38
+		0xe61f0200 0x38
+		0xe61f0300 0x38>;
+	interrupts = <0 69 4>;
+};

Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt → Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt

-Marvell Armada 370 and Armada XP Global Timers
-----------------------------------------------
+Marvell Armada 370 and Armada XP Timers
+---------------------------------------
 
 Required properties:
 - compatible: Should be "marvell,armada-370-xp-timer"
-- interrupts: Should contain the list of Global Timer interrupts
-- reg: Should contain the base address of the Global Timer registers
+- interrupts: Should contain the list of Global Timer interrupts and
+  then local timer interrupts
+- reg: Should contain location and length for timers register. First
+  pair for the Global Timer registers, second pair for the
+  local/private timers.
 - clocks: clock driving the timer hardware
 
 Optional properties:

Documentation/devicetree/bindings/w1/fsl-imx-owire.txt

+* Freescale i.MX One wire bus master controller
+
+Required properties:
+- compatible : should be "fsl,imx21-owire"
+- reg : Address and length of the register set for the device
+
+Optional properties:
+- clocks : phandle of clock that supplies the module (required if platform
+		clock bindings use device tree)
+
+Example:
+
+- From imx53.dtsi:
+owire: owire@63fa4000 {
+	compatible = "fsl,imx53-owire", "fsl,imx21-owire";
+	reg = <0x63fa4000 0x4000>;
+	clocks = <&clks 159>;
+	status = "disabled";
+};

Documentation/devicetree/bindings/watchdog/atmel-at91rm9200-wdt.txt

+Atmel AT91RM9200 System Timer Watchdog
+
+Required properties:
+- compatible: must be "atmel,at91sam9260-wdt".
+
+Example:
+	watchdog@fffffd00 {
+		compatible = "atmel,at91rm9200-wdt";
+	};

Documentation/devicetree/bindings/watchdog/atmel-wdt.txt

@@ -7,9 +7,13 @@ Required properties:
 - reg: physical base address of the controller and length of memory mapped
   region.
 
+Optional properties:
+- timeout-sec: contains the watchdog timeout in seconds.
+
 Example:
 
 	watchdog@fffffd40 {
 		compatible = "atmel,at91sam9260-wdt";
 		reg = <0xfffffd40 0x10>;
+		timeout-sec = <10>;
 	};

Documentation/devicetree/bindings/watchdog/marvel.txt

@@ -5,10 +5,15 @@ Required Properties:
 - Compatibility : "marvell,orion-wdt"
 - reg		: Address of the timer registers
 
+Optional properties:
+
+- timeout-sec	: Contains the watchdog timeout in seconds
+
 Example:
 
 	wdt@20300 {
 		compatible = "marvell,orion-wdt";
 		reg = <0x20300 0x28>;
+		timeout-sec = <10>;
 		status = "okay";
 	};

Documentation/devicetree/bindings/watchdog/pnx4008-wdt.txt

@@ -5,9 +5,13 @@ Required properties:
 - reg: physical base address of the controller and length of memory mapped
   region.
 
+Optional properties:
+- timeout-sec: contains the watchdog timeout in seconds.
+
 Example:
 
 	watchdog@4003C000 {
 		compatible = "nxp,pnx4008-wdt";
 		reg = <0x4003C000 0x1000>;
+		timeout-sec = <10>;
 	};

Documentation/devicetree/bindings/watchdog/qca-ar7130-wdt.txt

+* Qualcomm Atheros AR7130 Watchdog Timer (WDT) Controller
+
+Required properties:
+- compatible: must be "qca,ar7130-wdt"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+
+Example:
+
+wdt@18060008 {
+	compatible = "qca,ar9330-wdt", "qca,ar7130-wdt";
+	reg = <0x18060008 0x8>;
+};

Documentation/devicetree/bindings/watchdog/samsung-wdt.txt

@@ -9,3 +9,6 @@ Required properties:
 - reg : base physical address of the controller and length of memory mapped
 	region.
 - interrupts : interrupt number to the cpu.
+
+Optional properties:
+- timeout-sec : contains the watchdog timeout in seconds.

Documentation/dma-buf-sharing.txt

@@ -302,7 +302,11 @@ Access to a dma_buf from the kernel context involves three steps:
       void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
 
    The vmap call can fail if there is no vmap support in the exporter, or if it
-   runs out of vmalloc space. Fallback to kmap should be implemented.
+   runs out of vmalloc space. Fallback to kmap should be implemented. Note that
+   the dma-buf layer keeps a reference count for all vmap access and calls down
+   into the exporter's vmap function only when no vmapping exists, and only
+   unmaps it once. Protection against concurrent vmap/vunmap calls is provided
+   by taking the dma_buf->lock mutex.
 
 3. Finish access
 

Documentation/kbuild/kconfig-language.txt

@@ -388,26 +388,3 @@ config FOO
 	depends on BAR && m
 
 limits FOO to module (=m) or disabled (=n).
-
-Kconfig symbol existence
-~~~~~~~~~~~~~~~~~~~~~~~~
-The following two methods produce the same kconfig symbol dependencies
-but differ greatly in kconfig symbol existence (production) in the
-generated config file.
-
-case 1:
-
-config FOO
-	tristate "about foo"
-	depends on BAR
-
-vs. case 2:
-
-if BAR
-config FOO
-	tristate "about foo"
-endif
-
-In case 1, the symbol FOO will always exist in the config file (given
-no other dependencies).  In case 2, the symbol FOO will only exist in
-the config file if BAR is enabled.

Documentation/kbuild/kconfig.txt

@@ -46,6 +46,12 @@ KCONFIG_OVERWRITECONFIG
 If you set KCONFIG_OVERWRITECONFIG in the environment, Kconfig will not
 break symlinks when .config is a symlink to somewhere else.
 
+CONFIG_
+--------------------------------------------------
+If you set CONFIG_ in the environment, Kconfig will prefix all symbols
+with its value when saving the configuration, instead of using the default,
+"CONFIG_".
+
 ______________________________________________________________________
 Environment variables for '{allyes/allmod/allno/rand}config'
 

Documentation/kernel-parameters.txt

@@ -564,6 +564,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			UART at the specified I/O port or MMIO address,
 			switching to the matching ttyS device later.  The
 			options are the same as for ttyS, above.
+		hvc<n>	Use the hypervisor console device <n>. This is for
+			both Xen and PowerPC hypervisors.
 
                 If the device connected to the port is not a TTY but a braille
                 device, prepend "brl," before the device type, for instance
@@ -757,6 +759,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	earlyprintk=	[X86,SH,BLACKFIN]
 			earlyprintk=vga
+			earlyprintk=xen
 			earlyprintk=serial[,ttySn[,baudrate]]
 			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
@@ -774,6 +777,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The VGA output is eventually overwritten by the real
 			console.
 
+			The xen output can only be used by Xen PV guests.
+
 	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
 			ekgdboc=kbd
 
@@ -973,6 +978,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			       If specified, z/VM IUCV HVC accepts connections
 			       from listed z/VM user IDs only.
 
+	hwthread_map=	[METAG] Comma-separated list of Linux cpu id to
+			        hardware thread id mappings.
+				Format: <cpu>:<hwthread>
+
 	keep_bootcon	[KNL]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window
@@ -1640,42 +1649,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			that the amount of memory usable for all allocations
 			is not too small.
 
-	movablemem_map=acpi
-			[KNL,X86,IA-64,PPC] This parameter is similar to
-			memmap except it specifies the memory map of
-			ZONE_MOVABLE.
-			This option inform the kernel to use Hot Pluggable bit
-			in flags from SRAT from ACPI BIOS to determine which
-			memory devices could be hotplugged. The corresponding
-			memory ranges will be set as ZONE_MOVABLE.
-			NOTE: Whatever node the kernel resides in will always
-			      be un-hotpluggable.
-
-	movablemem_map=nn[KMG]@ss[KMG]
-			[KNL,X86,IA-64,PPC] This parameter is similar to
-			memmap except it specifies the memory map of
-			ZONE_MOVABLE.
-			If user specifies memory ranges, the info in SRAT will
-			be ingored. And it works like the following:
-			- If more ranges are all within one node, then from
-			  lowest ss to the end of the node will be ZONE_MOVABLE.
-			- If a range is within a node, then from ss to the end
-			  of the node will be ZONE_MOVABLE.
-			- If a range covers two or more nodes, then from ss to
-			  the end of the 1st node will be ZONE_MOVABLE, and all
-			  the rest nodes will only have ZONE_MOVABLE.
-			If memmap is specified at the same time, the
-			movablemem_map will be limited within the memmap
-			areas. If kernelcore or movablecore is also specified,
-			movablemem_map will have higher priority to be
-			satisfied. So the administrator should be careful that
-			the amount of movablemem_map areas are not too large.
-			Otherwise kernel won't have enough memory to start.
-			NOTE: We don't stop users specifying the node the
-			      kernel resides in as hotpluggable so that this
-			      option can be used as a workaround of firmware
-                              bugs.
-
 	MTD_Partition=	[MTD]
 			Format: <name>,<region-number>,<size>,<offset>
 

Documentation/metag/00-INDEX

+00-INDEX
+	- this file
+kernel-ABI.txt
+	- Documents metag ABI details

Documentation/metag/kernel-ABI.txt

+			==========================
+			KERNEL ABIS FOR METAG ARCH
+			==========================
+
+This document describes the Linux ABIs for the metag architecture, and has the
+following sections:
+
+ (*) Outline of registers
+ (*) Userland registers
+ (*) Kernel registers
+ (*) System call ABI
+ (*) Calling conventions
+
+
+====================
+OUTLINE OF REGISTERS
+====================
+
+The main Meta core registers are arranged in units:
+
+	UNIT	Type	DESCRIPTION	GP	EXT	PRIV	GLOBAL
+	=======	=======	===============	=======	=======	=======	=======
+	CT	Special	Control unit
+	D0	General	Data unit 0	0-7	8-15	16-31	16-31
+	D1	General	Data unit 1	0-7	8-15	16-31	16-31
+	A0	General	Address unit 0	0-3	4-7	 8-15	 8-15
+	A1	General	Address unit 1	0-3	4-7	 8-15	 8-15
+	PC	Special	PC unit		0		 1
+	PORT	Special	Ports
+	TR	Special	Trigger unit			 0-7
+	TT	Special	Trace unit			 0-5
+	FX	General	FP unit			0-15
+
+GP registers form part of the main context.
+
+Extended context registers (EXT) may not be present on all hardware threads and
+can be context switched if support is enabled and the appropriate bits are set
+in e.g. the D0.8 register to indicate what extended state to preserve.
+
+Global registers are shared between threads and are privilege protected.
+
+See arch/metag/include/asm/metag_regs.h for definitions relating to core
+registers and the fields and bits they contain. See the TRMs for further details
+about special registers.
+
+Several special registers are preserved in the main context, these are the
+interesting ones:
+
+	REG	(ALIAS)		PURPOSE
+	=======================	===============================================
+	CT.1	(TXMODE)	Processor mode bits (particularly for DSP)
+	CT.2	(TXSTATUS)	Condition flags and LSM_STEP (MGET/MSET step)
+	CT.3	(TXRPT)		Branch repeat counter
+	PC.0	(PC)		Program counter
+
+Some of the general registers have special purposes in the ABI and therefore
+have aliases:
+
+	D0 REG	(ALIAS)	PURPOSE		D1 REG	(ALIAS)	PURPOSE
+	===============	===============	===============	=======================
+	D0.0	(D0Re0)	32bit result	D1.0	(D1Re0)	Top half of 64bit result
+	D0.1	(D0Ar6)	Argument 6	D1.1	(D1Ar5)	Argument 5
+	D0.2	(D0Ar4)	Argument 4	D1.2	(D1Ar3)	Argument 3
+	D0.3	(D0Ar2)	Argument 2	D1.3	(D1Ar1)	Argument 1
+	D0.4	(D0FrT)	Frame temp	D1.4	(D1RtP)	Return pointer
+	D0.5		Call preserved	D1.5		Call preserved
+	D0.6		Call preserved	D1.6		Call preserved
+	D0.7		Call preserved	D1.7		Call preserved
+
+	A0 REG	(ALIAS)	PURPOSE		A1 REG	(ALIAS)	PURPOSE
+	===============	===============	===============	=======================
+	A0.0	(A0StP)	Stack pointer	A1.0	(A1GbP)	Global base pointer
+	A0.1	(A0FrP)	Frame pointer	A1.1	(A1LbP)	Local base pointer
+	A0.2				A1.2
+	A0.3				A1.3
+
+
+==================
+USERLAND REGISTERS
+==================
+
+All the general purpose D0, D1, A0, A1 registers are preserved when entering the
+kernel (including asynchronous events such as interrupts and timer ticks) except
+the following which have special purposes in the ABI:
+
+	REGISTERS	WHEN	STATUS		PURPOSE
+	===============	=======	===============	===============================
+	D0.8		DSP	Preserved	ECH, determines what extended
+						DSP state to preserve.
+	A0.0	(A0StP)	ALWAYS	Preserved	Stack >= A0StP may be clobbered
+						at any time by the creation of a
+						signal frame.
+	A1.0	(A1GbP)	SMP	Clobbered	Used as temporary for loading
+						kernel stack pointer and saving
+						core context.
+	A0.15		!SMP	Protected	Stores kernel stack pointer.
+	A1.15		ALWAYS	Protected	Stores kernel base pointer.
+
+On UP A0.15 is used to store the kernel stack pointer for storing the userland
+context. A0.15 is global between hardware threads though which means it cannot
+be used on SMP for this purpose. Since no protected local registers are
+available A1GbP is reserved for use as a temporary to allow a percpu stack
+pointer to be loaded for storing the rest of the context.
+
+
+================
+KERNEL REGISTERS
+================
+
+When in the kernel the following registers have special purposes in the ABI:
+
+	REGISTERS	WHEN	STATUS		PURPOSE
+	===============	=======	===============	===============================
+	A0.0	(A0StP)	ALWAYS	Preserved	Stack >= A0StP may be clobbered
+						at any time by the creation of
+						an irq signal frame.
+	A1.0	(A1GbP)	ALWAYS	Preserved	Reserved (kernel base pointer).
+
+
+===============
+SYSTEM CALL ABI
+===============
+
+When a system call is made, the following registers are effective:
+
+	REGISTERS	CALL			RETURN
+	===============	=======================	===============================
+	D0.0	(D0Re0)				Return value (or -errno)
+	D1.0	(D1Re0)	System call number	Clobbered
+	D0.1	(D0Ar6)	Syscall arg #6		Preserved
+	D1.1	(D1Ar5)	Syscall arg #5		Preserved
+	D0.2	(D0Ar4)	Syscall arg #4		Preserved
+	D1.2	(D1Ar3)	Syscall arg #3		Preserved
+	D0.3	(D0Ar2)	Syscall arg #2		Preserved
+	D1.3	(D1Ar1)	Syscall arg #1		Preserved
+
+Due to the limited number of argument registers and some system calls with badly
+aligned 64-bit arguments, 64-bit values are always packed in consecutive
+arguments, even if this is contrary to the normal calling conventions (where the
+two halves would go in a matching pair of data registers).
+
+For example fadvise64_64 usually has the signature:
+
+	long sys_fadvise64_64(i32 fd, i64 offs, i64 len, i32 advice);
+
+But for metag fadvise64_64 is wrapped so that the 64-bit arguments are packed:
+
+	long sys_fadvise64_64_metag(i32 fd,      i32 offs_lo,
+				    i32 offs_hi, i32 len_lo,
+				    i32 len_hi,  i32 advice)
+
+So the arguments are packed in the registers like this:
+
+	D0 REG	(ALIAS)	VALUE		D1 REG	(ALIAS)	VALUE
+	===============	===============	===============	=======================
+	D0.1	(D0Ar6)	advice		D1.1	(D1Ar5)	hi(len)
+	D0.2	(D0Ar4)	lo(len)		D1.2	(D1Ar3)	hi(offs)
+	D0.3	(D0Ar2)	lo(offs)	D1.3	(D1Ar1)	fd
+
+
+===================
+CALLING CONVENTIONS
+===================
+
+These calling conventions apply to both user and kernel code. The stack grows
+from low addresses to high addresses in the metag ABI. The stack pointer (A0StP)
+should always point to the next free address on the stack and should at all
+times be 64-bit aligned. The following registers are effective at the point of a
+call:
+
+	REGISTERS	CALL			RETURN
+	===============	=======================	===============================
+	D0.0	(D0Re0)				32bit return value
+	D1.0	(D1Re0)				Upper half of 64bit return value
+	D0.1	(D0Ar6)	32bit argument #6	Clobbered
+	D1.1	(D1Ar5)	32bit argument #5	Clobbered
+	D0.2	(D0Ar4)	32bit argument #4	Clobbered
+	D1.2	(D1Ar3)	32bit argument #3	Clobbered
+	D0.3	(D0Ar2)	32bit argument #2	Clobbered
+	D1.3	(D1Ar1)	32bit argument #1	Clobbered
+	D0.4	(D0FrT)				Clobbered
+	D1.4	(D1RtP)	Return pointer		Clobbered
+	D{0-1}.{5-7}				Preserved
+	A0.0	(A0StP)	Stack pointer		Preserved
+	A1.0	(A0GbP)				Preserved
+	A0.1	(A0FrP)	Frame pointer		Preserved
+	A1.1	(A0LbP)				Preserved
+	A{0-1},{2-3}				Clobbered
+
+64-bit arguments are placed in matching pairs of registers (i.e. the same
+register number in both D0 and D1 units), with the least significant half in D0
+and the most significant half in D1, leaving a gap where necessary. Futher
+arguments are stored on the stack in reverse order (earlier arguments at higher
+addresses):
+
+	ADDRESS		0     1     2     3	4     5     6     7
+	===============	===== ===== ===== =====	===== ===== ===== =====
+	A0StP       -->
+	A0StP-0x08	32bit argument #8	32bit argument #7
+	A0StP-0x10	32bit argument #10	32bit argument #9
+
+Function prologues tend to look a bit like this:
+
+	/* If frame pointer in use, move it to frame temp register so it can be
+	   easily pushed onto stack */
+	MOV	D0FrT,A0FrP
+
+	/* If frame pointer in use, set it to stack pointer */
+	ADD	A0FrP,A0StP,#0
+
+	/* Preserve D0FrT, D1RtP, D{0-1}.{5-7} on stack, incrementing A0StP */
+	MSETL	[A0StP++],D0FrT,D0.5,D0.6,D0.7
+
+	/* Allocate some stack space for local variables */
+	ADD	A0StP,A0StP,#0x10
+
+At this point the stack would look like this:
+
+	ADDRESS		0     1     2     3	4     5     6     7
+	===============	===== ===== ===== =====	===== ===== ===== =====
+	A0StP       -->
+	A0StP-0x08
+	A0StP-0x10
+	A0StP-0x18	Old D0.7		Old D1.7
+	A0StP-0x20	Old D0.6		Old D1.6
+	A0StP-0x28	Old D0.5		Old D1.5
+	A0FrP       -->	Old A0FrP (frame ptr)	Old D1RtP (return ptr)
+	A0FrP-0x08	32bit argument #8	32bit argument #7
+	A0FrP-0x10	32bit argument #10	32bit argument #9
+
+Function epilogues tend to differ depending on the use of a frame pointer. An
+example of a frame pointer epilogue:
+
+	/* Restore D0FrT, D1RtP, D{0-1}.{5-7} from stack, incrementing A0FrP */
+	MGETL	D0FrT,D0.5,D0.6,D0.7,[A0FrP++]
+	/* Restore stack pointer to where frame pointer was before increment */
+	SUB	A0StP,A0FrP,#0x20
+	/* Restore frame pointer from frame temp */
+	MOV	A0FrP,D0FrT
+	/* Return to caller via restored return pointer */
+	MOV	PC,D1RtP
+
+If the function hasn't touched the frame pointer, MGETL cannot be safely used
+with A0StP as it always increments and that would expose the stack to clobbering
+by interrupts (kernel) or signals (user). Therefore it's common to see the MGETL
+split into separate GETL instructions:
+
+	/* Restore D0FrT, D1RtP, D{0-1}.{5-7} from stack */
+	GETL	D0FrT,D1RtP,[A0StP+#-0x30]
+	GETL	D0.5,D1.5,[A0StP+#-0x28]
+	GETL	D0.6,D1.6,[A0StP+#-0x20]
+	GETL	D0.7,D1.7,[A0StP+#-0x18]
+	/* Restore stack pointer */
+	SUB	A0StP,A0StP,#0x30
+	/* Return to caller via restored return pointer */
+	MOV	PC,D1RtP

Documentation/scsi/ChangeLog.megaraid_sas

+Release Date    : Sat. Feb 9, 2013 17:00:00 PST 2013 -
+			(emaild-id:megaraidlinux@lsi.com)
+			Adam Radford
+Current Version : 06.506.00.00-rc1
+Old Version     : 06.504.01.00-rc1
+    1. Add 4k FastPath DIF support.
+    2. Dont load DevHandle unless FastPath enabled.
+    3. Version and Changelog update.
+-------------------------------------------------------------------------------
 Release Date    : Mon. Oct 1, 2012 17:00:00 PST 2012 -
 			(emaild-id:megaraidlinux@lsi.com)
 			Adam Radford

Documentation/thermal/exynos_thermal_emulation

+EXYNOS EMULATION MODE
+========================
+
+Copyright (C) 2012 Samsung Electronics
+
+Written by Jonghwa Lee <jonghwa3.lee@samsung.com>
+
+Description
+-----------
+
+Exynos 4x12 (4212, 4412) and 5 series provide emulation mode for thermal management unit.
+Thermal emulation mode supports software debug for TMU's operation. User can set temperature
+manually with software code and TMU will read current temperature from user value not from
+sensor's value.
+
+Enabling CONFIG_EXYNOS_THERMAL_EMUL option will make this support in available.
+When it's enabled, sysfs node will be created under
+/sys/bus/platform/devices/'exynos device name'/ with name of 'emulation'.
+
+The sysfs node, 'emulation', will contain value 0 for the initial state. When you input any
+temperature you want to update to sysfs node, it automatically enable emulation mode and
+current temperature will be changed into it.
+(Exynos also supports user changable delay time which would be used to delay of
+ changing temperature. However, this node only uses same delay of real sensing time, 938us.)
+
+Exynos emulation mode requires synchronous of value changing and enabling. It means when you
+want to update the any value of delay or next temperature, then you have to enable emulation
+mode at the same time. (Or you have to keep the mode enabling.) If you don't, it fails to
+change the value to updated one and just use last succeessful value repeatedly. That's why
+this node gives users the right to change termerpature only. Just one interface makes it more
+simply to use.
+
+Disabling emulation mode only requires writing value 0 to sysfs node.
+
+
+TEMP	120 |
+	    |
+	100 |
+	    |
+	 80 |
+	    |		     	 	 +-----------
+	 60 |      		     	 |	    |
+	    |	           +-------------|          |
+	 40 |              |         	 |          |
+	    |		   |	     	 |          |
+	 20 |		   |	     	 |          +----------
+	    |	 	   |	     	 |          |          |
+	  0 |______________|_____________|__________|__________|_________
+		   A	    	 A	    A	   	       A     TIME
+		   |<----->|	 |<----->|  |<----->|	       |
+		   | 938us |  	 |	 |  |       |          |
+emulation    :  0  50	   |  	 70      |  20      |          0
+current temp :   sensor   50		 70         20	      sensor

Documentation/thermal/intel_powerclamp.txt

+			 =======================
+			 INTEL POWERCLAMP DRIVER
+			 =======================
+By: Arjan van de Ven <arjan@linux.intel.com>
+    Jacob Pan <jacob.jun.pan@linux.intel.com>
+
+Contents:
+	(*) Introduction
+	    - Goals and Objectives
+
+	(*) Theory of Operation
+	    - Idle Injection
+	    - Calibration
+
+	(*) Performance Analysis
+	    - Effectiveness and Limitations
+	    - Power vs Performance
+	    - Scalability
+	    - Calibration
+	    - Comparison with Alternative Techniques
+
+	(*) Usage and Interfaces
+	    - Generic Thermal Layer (sysfs)
+	    - Kernel APIs (TBD)
+
+============
+INTRODUCTION
+============
+
+Consider the situation where a system’s power consumption must be
+reduced at runtime, due to power budget, thermal constraint, or noise
+level, and where active cooling is not preferred. Software managed
+passive power reduction must be performed to prevent the hardware
+actions that are designed for catastrophic scenarios.
+
+Currently, P-states, T-states (clock modulation), and CPU offlining
+are used for CPU throttling.
+
+On Intel CPUs, C-states provide effective power reduction, but so far
+they’re only used opportunistically, based on workload. With the
+development of intel_powerclamp driver, the method of synchronizing
+idle injection across all online CPU threads was introduced. The goal
+is to achieve forced and controllable C-state residency.
+
+Test/Analysis has been made in the areas of power, performance,
+scalability, and user experience. In many cases, clear advantage is
+shown over taking the CPU offline or modulating the CPU clock.
+
+
+===================
+THEORY OF OPERATION
+===================
+
+Idle Injection
+--------------
+
+On modern Intel processors (Nehalem or later), package level C-state
+residency is available in MSRs, thus also available to the kernel.
+
+These MSRs are:
+      #define MSR_PKG_C2_RESIDENCY	0x60D
+      #define MSR_PKG_C3_RESIDENCY	0x3F8
+      #define MSR_PKG_C6_RESIDENCY	0x3F9
+      #define MSR_PKG_C7_RESIDENCY	0x3FA
+
+If the kernel can also inject idle time to the system, then a
+closed-loop control system can be established that manages package
+level C-state. The intel_powerclamp driver is conceived as such a
+control system, where the target set point is a user-selected idle
+ratio (based on power reduction), and the error is the difference
+between the actual package level C-state residency ratio and the target idle
+ratio.
+
+Injection is controlled by high priority kernel threads, spawned for
+each online CPU.
+
+These kernel threads, with SCHED_FIFO class, are created to perform
+clamping actions of controlled duty ratio and duration. Each per-CPU
+thread synchronizes its idle time and duration, based on the rounding
+of jiffies, so accumulated errors can be prevented to avoid a jittery
+effect. Threads are also bound to the CPU such that they cannot be
+migrated, unless the CPU is taken offline. In this case, threads
+belong to the offlined CPUs will be terminated immediately.
+
+Running as SCHED_FIFO and relatively high priority, also allows such
+scheme to work for both preemptable and non-preemptable kernels.
+Alignment of idle time around jiffies ensures scalability for HZ
+values. This effect can be better visualized using a Perf timechart.
+The following diagram shows the behavior of kernel thread
+kidle_inject/cpu. During idle injection, it runs monitor/mwait idle
+for a given "duration", then relinquishes the CPU to other tasks,
+until the next time interval.
+
+The NOHZ schedule tick is disabled during idle time, but interrupts
+are not masked. Tests show that the extra wakeups from scheduler tick
+have a dramatic impact on the effectiveness of the powerclamp driver
+on large scale systems (Westmere system with 80 processors).
+
+CPU0
+		  ____________          ____________
+kidle_inject/0   |   sleep    |  mwait |  sleep     |
+	_________|            |________|            |_______
+			       duration
+CPU1
+		  ____________          ____________
+kidle_inject/1   |   sleep    |  mwait |  sleep     |
+	_________|            |________|            |_______
+			      ^
+			      |
+			      |
+			      roundup(jiffies, interval)
+
+Only one CPU is allowed to collect statistics and update global
+control parameters. This CPU is referred to as the controlling CPU in
+this document. The controlling CPU is elected at runtime, with a
+policy that favors BSP, taking into account the possibility of a CPU
+hot-plug.
+
+In terms of dynamics of the idle control system, package level idle
+time is considered largely as a non-causal system where its behavior
+cannot be based on the past or current input. Therefore, the
+intel_powerclamp driver attempts to enforce the desired idle time
+instantly as given input (target idle ratio). After injection,
+powerclamp moniors the actual idle for a given time window and adjust
+the next injection accordingly to avoid over/under correction.
+
+When used in a causal control system, such as a temperature control,
+it is up to the user of this driver to implement algorithms where
+past samples and outputs are included in the feedback. For example, a
+PID-based thermal controller can use the powerclamp driver to
+maintain a desired target temperature, based on integral and
+derivative gains of the past samples.
+
+
+
+Calibration
+-----------
+During scalability testing, it is observed that synchronized actions
+among CPUs become challenging as the number of cores grows. This is
+also true for the ability of a system to enter package level C-states.
+
+To make sure the intel_powerclamp driver scales well, online
+calibration is implemented. The goals for doing such a calibration
+are:
+
+a) determine the effective range of idle injection ratio
+b) determine the amount of compensation needed at each target ratio
+
+Compensation to each target ratio consists of two parts:
+
+        a) steady state error compensation
+	This is to offset the error occurring when the system can
+	enter idle without extra wakeups (such as external interrupts).
+
+	b) dynamic error compensation
+	When an excessive amount of wakeups occurs during idle, an
+	additional idle ratio can be added to quiet interrupts, by
+	slowing down CPU activities.
+
+A debugfs file is provided for the user to examine compensation
+progress and results, such as on a Westmere system.
+[jacob@nex01 ~]$ cat
+/sys/kernel/debug/intel_powerclamp/powerclamp_calib
+controlling cpu: 0
+pct confidence steady dynamic (compensation)
+0	0	0	0
+1	1	0	0
+2	1	1	0
+3	3	1	0
+4	3	1	0
+5	3	1	0
+6	3	1	0
+7	3	1	0
+8	3	1	0
+...
+30	3	2	0
+31	3	2	0
+32	3	1	0
+33	3	2	0
+34	3	1	0
+35	3	2	0
+36	3	1	0
+37	3	2	0
+38	3	1	0
+39	3	2	0
+40	3	3	0
+41	3	1	0
+42	3	2	0
+43	3	1	0
+44	3	1	0
+45	3	2	0
+46	3	3	0
+47	3	0	0
+48	3	2	0
+49	3	3	0
+
+Calibration occurs during runtime. No offline method is available.
+Steady state compensation is used only when confidence levels of all
+adjacent ratios have reached satisfactory level. A confidence level
+is accumulated based on clean data collected at runtime. Data
+collected during a period without extra interrupts is considered
+clean.
+
+To compensate for excessive amounts of wakeup during idle, additional
+idle time is injected when such a condition is detected. Currently,
+we have a simple algorithm to double the injection ratio. A possible
+enhancement might be to throttle the offending IRQ, such as delaying
+EOI for level triggered interrupts. But it is a challenge to be
+non-intrusive to the scheduler or the IRQ core code.
+
+
+CPU Online/Offline
+------------------
+Per-CPU kernel threads are started/stopped upon receiving
+notifications of CPU hotplug activities. The intel_powerclamp driver
+keeps track of clamping kernel threads, even after they are migrated
+to other CPUs, after a CPU offline event.
+
+
+=====================
+Performance Analysis
+=====================
+This section describes the general performance data collected on
+multiple systems, including Westmere (80P) and Ivy Bridge (4P, 8P).
+
+Effectiveness and Limitations
+-----------------------------
+The maximum range that idle injection is allowed is capped at 50
+percent. As mentioned earlier, since interrupts are allowed during
+forced idle time, excessive interrupts could result in less
+effectiveness. The extreme case would be doing a ping -f to generated
+flooded network interrupts without much CPU acknowledgement. In this
+case, little can be done from the idle injection threads. In most
+normal cases, such as scp a large file, applications can be throttled
+by the powerclamp driver, since slowing down the CPU also slows down
+network protocol processing, which in turn reduces interrupts.
+
+When control parameters change at runtime by the controlling CPU, it
+may take an additional period for the rest of the CPUs to catch up
+with the changes. During this time, idle injection is out of sync,
+thus not able to enter package C- states at the expected ratio. But
+this effect is minor, in that in most cases change to the target
+ratio is updated much less frequently than the idle injection
+frequency.
+
+Scalability
+-----------
+Tests also show a minor, but measurable, difference between the 4P/8P
+Ivy Bridge system and the 80P Westmere server under 50% idle ratio.
+More compensation is needed on Westmere for the same amount of
+target idle ratio. The compensation also increases as the idle ratio
+gets larger. The above reason constitutes the need for the
+calibration code.
+
+On the IVB 8P system, compared to an offline CPU, powerclamp can
+achieve up to 40% better performance per watt. (measured by a spin
+counter summed over per CPU counting threads spawned for all running
+CPUs).
+
+====================
+Usage and Interfaces
+====================
+The powerclamp driver is registered to the generic thermal layer as a
+cooling device. Currently, it’s not bound to any thermal zones.
+
+jacob@chromoly:/sys/class/thermal/cooling_device14$ grep . *
+cur_state:0
+max_state:50
+type:intel_powerclamp
+
+Example usage:
+- To inject 25% idle time
+$ sudo sh -c "echo 25 > /sys/class/thermal/cooling_device80/cur_state
+"
+
+If the system is not busy and has more than 25% idle time already,
+then the powerclamp driver will not start idle injection. Using Top
+will not show idle injection kernel threads.
+
+If the system is busy (spin test below) and has less than 25% natural
+idle time, powerclamp kernel threads will do idle injection, which
+appear running to the scheduler. But the overall system idle is still
+reflected. In this example, 24.1% idle is shown. This helps the
+system admin or user determine the cause of slowdown, when a
+powerclamp driver is in action.
+
+
+Tasks: 197 total,   1 running, 196 sleeping,   0 stopped,   0 zombie
+Cpu(s): 71.2%us,  4.7%sy,  0.0%ni, 24.1%id,  0.0%wa,  0.0%hi,  0.0%si,  0.0%st
+Mem:   3943228k total,  1689632k used,  2253596k free,    74960k buffers
+Swap:  4087804k total,        0k used,  4087804k free,   945336k cached
+
+  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
+ 3352 jacob     20   0  262m  644  428 S  286  0.0   0:17.16 spin
+ 3341 root     -51   0     0    0    0 D   25  0.0   0:01.62 kidle_inject/0
+ 3344 root     -51   0     0    0    0 D   25  0.0   0:01.60 kidle_inject/3
+ 3342 root     -51   0     0    0    0 D   25  0.0   0:01.61 kidle_inject/1
+ 3343 root     -51   0     0    0    0 D   25  0.0   0:01.60 kidle_inject/2
+ 2935 jacob     20   0  696m 125m  35m S    5  3.3   0:31.11 firefox
+ 1546 root      20   0  158m  20m 6640 S    3  0.5   0:26.97 Xorg
+ 2100 jacob     20   0 1223m  88m  30m S    3  2.3   0:23.68 compiz
+
+Tests have shown that by using the powerclamp driver as a cooling
+device, a PID based userspace thermal controller can manage to
+control CPU temperature effectively, when no other thermal influence
+is added. For example, a UltraBook user can compile the kernel under
+certain temperature (below most active trip points).

Documentation/thermal/sysfs-api.txt

@@ -55,6 +55,8 @@ temperature) and throttle appropriate devices.
 	.get_trip_type: get the type of certain trip point.
 	.get_trip_temp: get the temperature above which the certain trip point
 			will be fired.
+	.set_emul_temp: set the emulation temperature which helps in debugging
+			different threshold temperature points.
 
 1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
@@ -153,6 +155,7 @@ Thermal zone device sys I/F, created once it's registered:
     |---trip_point_[0-*]_temp:	Trip point temperature
     |---trip_point_[0-*]_type:	Trip point type
     |---trip_point_[0-*]_hyst:	Hysteresis value for this trip point
+    |---emul_temp:		Emulated temperature set node
 
 Thermal cooling device sys I/F, created once it's registered:
 /sys/class/thermal/cooling_device[0-*]:
@@ -252,6 +255,16 @@ passive
 	Valid values: 0 (disabled) or greater than 1000
 	RW, Optional
 
+emul_temp
+	Interface to set the emulated temperature method in thermal zone
+	(sensor). After setting this temperature, the thermal zone may pass
+	this temperature to platform emulation function if registered or
+	cache it locally. This is useful in debugging different temperature
+	threshold and its associated cooling action. This is write only node
+	and writing 0 on this node should disable emulation.
+	Unit: millidegree Celsius
+	WO, Optional
+
 *****************************
 * Cooling device attributes *
 *****************************
@@ -329,8 +342,9 @@ The framework includes a simple notification mechanism, in the form of a
 netlink event. Netlink socket initialization is done during the _init_
 of the framework. Drivers which intend to use the notification mechanism
 just need to call thermal_generate_netlink_event() with two arguments viz
-(originator, event). Typically the originator will be an integer assigned
-to a thermal_zone_device when it registers itself with the framework. The
+(originator, event). The originator is a pointer to struct thermal_zone_device
+from where the event has been originated. An integer which represents the
+thermal zone device will be used in the message to identify the zone. The
 event will be one of:{THERMAL_AUX0, THERMAL_AUX1, THERMAL_CRITICAL,
 THERMAL_DEV_FAULT}. Notification can be sent when the current temperature
 crosses any of the configured thresholds.

Documentation/watchdog/watchdog-kernel-api.txt

 The Linux WatchDog Timer Driver Core kernel API.
 ===============================================
-Last reviewed: 22-May-2012
+Last reviewed: 12-Feb-2013
 
 Wim Van Sebroeck <wim@iguana.be>
 
@@ -212,3 +212,15 @@ driver specific data to and a pointer to the data itself.
 The watchdog_get_drvdata function allows you to retrieve driver specific data.
 The argument of this function is the watchdog device where you want to retrieve
 data from. The function returns the pointer to the driver specific data.
+
+To initialize the timeout field, the following function can be used:
+
+extern int watchdog_init_timeout(struct watchdog_device *wdd,
+                                  unsigned int timeout_parm, struct device *dev);
+
+The watchdog_init_timeout function allows you to initialize the timeout field
+using the module timeout parameter or by retrieving the timeout-sec property from
+the device tree (if the module timeout parameter is invalid). Best practice is
+to set the default timeout value as timeout value in the watchdog_device and
+then use this function to set the user "preferred" timeout value.
+This routine returns zero on success and a negative errno code for failure.

MAINTAINERS

@@ -97,12 +97,13 @@ Descriptions of section entries:
 	   X:	net/ipv6/
 	   matches all files in and below net excluding net/ipv6/
 	K: Keyword perl extended regex pattern to match content in a
-	   patch or file.  For instance:
+	   patch or file, or an affected filename.  For instance:
 	   K: of_get_profile
-	      matches patches or files that contain "of_get_profile"
+	      matches patch or file content, or filenames, that contain
+	      "of_get_profile"
 	   K: \b(printk|pr_(info|err))\b
-	      matches patches or files that contain one or more of the words
-	      printk, pr_info or pr_err
+	      matches patch or file content, or filenames, that contain one or
+	      more of the words printk, pr_info or pr_err
 	   One regex pattern per line.  Multiple K: lines acceptable.
 
 Note: For the hard of thinking, this list is meant to remain in alphabetical
@@ -1799,7 +1800,8 @@ F:	drivers/bcma/
 F:	include/linux/bcma/
 
 BROCADE BFA FC SCSI DRIVER
-M:	Krishna C Gudipati <kgudipat@brocade.com>
+M:	Anil Gurumurthy <agurumur@brocade.com>
+M:	Vijaya Mohan Guvva <vmohan@brocade.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/bfa/
@@ -2073,8 +2075,8 @@ S:	Maintained
 F:	include/linux/clk.h
 
 CISCO FCOE HBA DRIVER
-M:	Abhijeet Joglekar <abjoglek@cisco.com>
-M:	Venkata Siva Vijayendra Bhamidipati <vbhamidi@cisco.com>
+M:	Hiral Patel <hiralpat@cisco.com>
+M:	Suma Ramars <sramars@cisco.com>
 M:	Brian Uchino <buchino@cisco.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported
@@ -2902,6 +2904,13 @@ W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/e7xxx_edac.c
 
+EDAC-GHES
+M:	Mauro Carvalho Chehab <mchehab@redhat.com>
+L:	linux-edac@vger.kernel.org
+W:	bluesmoke.sourceforge.net
+S:	Maintained
+F:	drivers/edac/ghes-edac.c
+
 EDAC-I82443BXGX
 M:	Tim Small <tim@buttersideup.com>
 L:	linux-edac@vger.kernel.org
@@ -5195,6 +5204,18 @@ F:	drivers/mtd/
 F:	include/linux/mtd/
 F:	include/uapi/mtd/
 
+METAG ARCHITECTURE
+M:	James Hogan <james.hogan@imgtec.com>
+S:	Supported
+F:	arch/metag/
+F:	Documentation/metag/
+F:	Documentation/devicetree/bindings/metag/
+F:	drivers/clocksource/metag_generic.c
+F:	drivers/irqchip/irq-metag.c
+F:	drivers/irqchip/irq-metag-ext.c
+F:	drivers/tty/metag_da.c
+F:	fs/imgdafs/
+
 MICROBLAZE ARCHITECTURE
 M:	Michal Simek <monstr@monstr.eu>
 L:	microblaze-uclinux@itee.uq.edu.au (moderated for non-subscribers)
@@ -5437,6 +5458,7 @@ F:	net/netrom/
 NETWORK BLOCK DEVICE (NBD)
 M:	Paul Clements <Paul.Clements@steeleye.com>
 S:	Maintained
+L:	nbd-general@lists.sourceforge.net
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/linux/nbd.h
@@ -6512,6 +6534,12 @@ S:	Maintained
 F:	Documentation/blockdev/ramdisk.txt
 F:	drivers/block/brd.c
 
+RAMSAM DRIVER (IBM RamSan 70/80 PCI SSD Flash Card)
+M:	Joshua Morris <josh.h.morris@us.ibm.com>
+M:	Philip Kelleher <pjk1939@linux.vnet.ibm.com>
+S:	Maintained
+F:	drivers/block/rsxx/
+
 RANDOM NUMBER DRIVER
 M:	Theodore Ts'o" <tytso@mit.edu>
 S:	Maintained
@@ -7539,6 +7567,7 @@ STAGING - NVIDIA COMPLIANT EMBEDDED CONTROLLER INTERFACE (nvec)
 M:	Julian Andres Klode <jak@jak-linux.org>
 M:	Marc Dietrich <marvin24@gmx.de>
 L:	ac100@lists.launchpad.net (moderated for non-subscribers)
+L:	linux-tegra@vger.kernel.org
 S:	Maintained
 F:	drivers/staging/nvec/
 
@@ -7665,6 +7694,12 @@ F:	lib/swiotlb.c
 F:	arch/*/kernel/pci-swiotlb.c
 F:	include/linux/swiotlb.h
 
+SYNOPSYS ARC ARCHITECTURE
+M:	Vineet Gupta <vgupta@synopsys.com>
+L:	linux-snps-arc@vger.kernel.org
+S:	Supported
+F:	arch/arc/
+
 SYSV FILESYSTEM
 M:	Christoph Hellwig <hch@infradead.org>
 S:	Maintained
@@ -7831,9 +7866,7 @@ L:	linux-tegra@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/linux-tegra/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra.git
 S:	Supported
-F:	arch/arm/mach-tegra
-F:	arch/arm/boot/dts/tegra*
-F:	arch/arm/configs/tegra_defconfig
+K:	(?i)[^a-z]tegra
 
 TEHUTI ETHERNET DRIVER
 M:	Andy Gospodarek <andy@greyhouse.net>

Makefile

 VERSION = 3
-PATCHLEVEL = 8
+PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
@@ -192,7 +192,6 @@ SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
 # "make" in the configured kernel build directory always uses that.
 # Default value for CROSS_COMPILE is not to prefix executables
 # Note: Some architectures assign CROSS_COMPILE in their arch/*/Makefile
-export KBUILD_BUILDHOST := $(SUBARCH)
 ARCH		?= $(SUBARCH)
 CROSS_COMPILE	?= $(CONFIG_CROSS_COMPILE:"%"=%)
 
@@ -620,7 +619,8 @@ KBUILD_AFLAGS	+= -gdwarf-2
 endif
 
 ifdef CONFIG_DEBUG_INFO_REDUCED
-KBUILD_CFLAGS 	+= $(call cc-option, -femit-struct-debug-baseonly)
+KBUILD_CFLAGS 	+= $(call cc-option, -femit-struct-debug-baseonly) \
+		   $(call cc-option,-fno-var-tracking)
 endif
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -1398,7 +1398,7 @@ quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN   $(wildcard $(rm-files))
 # Run depmod only if we have System.map and depmod is executable
 quiet_cmd_depmod = DEPMOD  $(KERNELRELEASE)
       cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \
-                   $(KERNELRELEASE)
+                   $(KERNELRELEASE) "$(patsubst "%",%,$(CONFIG_SYMBOL_PREFIX))"
 
 # Create temporary dir for module support files
 # clean it up only when building all modules

arch/Kconfig

@@ -103,6 +103,22 @@ config UPROBES
 
 	  If in doubt, say "N".
 
+config HAVE_64BIT_ALIGNED_ACCESS
+	def_bool 64BIT && !HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  Some architectures require 64 bit accesses to be 64 bit
+	  aligned, which also requires structs containing 64 bit values
+	  to be 64 bit aligned too. This includes some 32 bit
+	  architectures which can do 64 bit accesses, as well as 64 bit
+	  architectures without unaligned access.
+
+	  This symbol should be selected by an architecture if 64 bit
+	  accesses are required to be 64 bit aligned in this way even
+	  though it is not a 64 bit architecture.
+
+	  See Documentation/unaligned-memory-access.txt for more
+	  information on the topic of unaligned memory accesses.
+
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
 	help
@@ -303,6 +319,13 @@ config ARCH_WANT_OLD_COMPAT_IPC
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
+config HAVE_VIRT_TO_BUS
+	bool
+	help
+	  An architecture should select this if it implements the
+	  deprecated interface virt_to_bus().  All new architectures
+	  should probably not select this.
+
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help

arch/alpha/Kconfig

@@ -9,6 +9,7 @@ config ALPHA
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
 	select HAVE_GENERIC_HARDIRQS
+	select HAVE_VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select AUTO_IRQ_AFFINITY if SMP
 	select GENERIC_IRQ_SHOW

arch/arc/Kbuild

+obj-y += kernel/
+obj-y += mm/

arch/arc/Kconfig

+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+config ARC
+	def_bool y
+	select CLONE_BACKWARDS
+	# ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev
+	select DEVTMPFS if !INITRAMFS_SOURCE=""
+	select GENERIC_ATOMIC64
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_FIND_FIRST_BIT
+	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_SHOW
+	select GENERIC_KERNEL_EXECVE
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_PENDING_IRQ if SMP
+	select GENERIC_SMP_IDLE_THREAD
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_IOREMAP_PROT
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_MEMBLOCK
+	select HAVE_MOD_ARCH_SPECIFIC if ARC_DW2_UNWIND
+	select HAVE_OPROFILE
+	select HAVE_PERF_EVENTS
+	select IRQ_DOMAIN
+	select MODULES_USE_ELF_RELA
+	select NO_BOOTMEM
+	select OF
+	select OF_EARLY_FLATTREE
+	select PERF_USE_VMALLOC
+
+config SCHED_OMIT_FRAME_POINTER
+	def_bool y
+
+config GENERIC_CSUM
+	def_bool y
+
+config RWSEM_GENERIC_SPINLOCK
+	def_bool y
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config MMU
+	def_bool y
+
+config NO_IOPORT
+	def_bool y
+
+config GENERIC_CALIBRATE_DELAY
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config BINFMT_ELF
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+	select STACKTRACE
+
+config HAVE_LATENCYTOP_SUPPORT
+	def_bool y
+
+config NO_DMA
+	def_bool n
+
+source "init/Kconfig"
+source "kernel/Kconfig.freezer"
+
+menu "ARC Architecture Configuration"
+
+menu "ARC Platform/SoC/Board"
+
+source "arch/arc/plat-arcfpga/Kconfig"
+#New platform adds here
+
+endmenu
+
+menu "ARC CPU Configuration"
+
+choice
+	prompt "ARC Core"
+	default ARC_CPU_770
+
+config ARC_CPU_750D
+	bool "ARC750D"
+	help
+	  Support for ARC750 core
+
+config ARC_CPU_770
+	bool "ARC770"
+	select ARC_CPU_REL_4_10
+	help
+	  Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
+	  This core has a bunch of cool new features:
+	  -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4)
+                   Shared Address Spaces (for sharing TLB entires in MMU)
+	  -Caches: New Prog Model, Region Flush
+	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
+
+endchoice
+
+config CPU_BIG_ENDIAN
+	bool "Enable Big Endian Mode"
+	default n
+	help
+	  Build kernel for Big Endian Mode of ARC CPU
+
+# If a platform can't work with 0x8000_0000 based dma_addr_t
+config ARC_PLAT_NEEDS_CPU_TO_DMA
+	bool
+
+config SMP
+	bool "Symmetric Multi-Processing (Incomplete)"
+	default n
+	select USE_GENERIC_SMP_HELPERS
+	help
+	  This enables support for systems with more than one CPU. If you have
+	  a system with only one CPU, like most personal computers, say N. If
+	  you have a system with more than one CPU, say Y.
+
+if SMP
+
+config ARC_HAS_COH_CACHES
+	def_bool n
+
+config ARC_HAS_COH_LLSC
+	def_bool n
+
+config ARC_HAS_COH_RTSC
+	def_bool n
+
+config ARC_HAS_REENTRANT_IRQ_LV2
+	def_bool n
+
+endif
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-32)"
+	range 2 32
+	depends on SMP
+	default "2"
+
+menuconfig ARC_CACHE
+	bool "Enable Cache Support"
+	default y
+	# if SMP, cache enabled ONLY if ARC implementation has cache coherency
+	depends on !SMP || ARC_HAS_COH_CACHES
+
+if ARC_CACHE
+
+config ARC_CACHE_LINE_SHIFT
+	int "Cache Line Length (as power of 2)"
+	range 5 7
+	default "6"
+	help
+	  Starting with ARC700 4.9, Cache line length is configurable,
+	  This option specifies "N", with Line-len = 2 power N
+	  So line lengths of 32, 64, 128 are specified by 5,6,7, respectively
+	  Linux only supports same line lengths for I and D caches.
+
+config ARC_HAS_ICACHE
+	bool "Use Instruction Cache"
+	default y
+
+config ARC_HAS_DCACHE
+	bool "Use Data Cache"
+	default y
+
+config ARC_CACHE_PAGES
+	bool "Per Page Cache Control"
+	default y
+	depends on ARC_HAS_ICACHE || ARC_HAS_DCACHE
+	help
+	  This can be used to over-ride the global I/D Cache Enable on a
+	  per-page basis (but only for pages accessed via MMU such as
+	  Kernel Virtual address or User Virtual Address)
+	  TLB entries have a per-page Cache Enable Bit.
+	  Note that Global I/D ENABLE + Per Page DISABLE works but corollary
+	  Global DISABLE + Per Page ENABLE won't work
+
+endif	#ARC_CACHE
+
+config ARC_HAS_ICCM
+	bool "Use ICCM"
+	help
+	  Single Cycle RAMS to store Fast Path Code
+	default n
+
+config ARC_ICCM_SZ
+	int "ICCM Size in KB"
+	default "64"
+	depends on ARC_HAS_ICCM
+
+config ARC_HAS_DCCM
+	bool "Use DCCM"
+	help
+	  Single Cycle RAMS to store Fast Path Data
+	default n
+
+config ARC_DCCM_SZ
+	int "DCCM Size in KB"
+	default "64"
+	depends on ARC_HAS_DCCM
+
+config ARC_DCCM_BASE
+	hex "DCCM map address"
+	default "0xA0000000"
+	depends on ARC_HAS_DCCM
+
+config ARC_HAS_HW_MPY
+	bool "Use Hardware Multiplier (Normal or Faster XMAC)"
+	default y
+	help
+	  Influences how gcc generates code for MPY operations.
+	  If enabled, MPYxx insns are generated, provided by Standard/XMAC
+	  Multipler. Otherwise software multipy lib is used
+
+choice
+	prompt "ARC700 MMU Version"
+	default ARC_MMU_V3 if ARC_CPU_770
+	default ARC_MMU_V2 if ARC_CPU_750D
+
+config ARC_MMU_V1
+	bool "MMU v1"
+	help
+	  Orig ARC700 MMU
+
+config ARC_MMU_V2
+	bool "MMU v2"
+	help
+	  Fixed the deficiency of v1 - possible thrashing in memcpy sceanrio
+	  when 2 D-TLB and 1 I-TLB entries index into same 2way set.
+
+config ARC_MMU_V3
+	bool "MMU v3"
+	depends on ARC_CPU_770
+	help
+	  Introduced with ARC700 4.10: New Features
+	  Variable Page size (1k-16k), var JTLB size 128 x (2 or 4)
+	  Shared Address Spaces (SASID)
+
+endchoice
+
+
+choice
+	prompt "MMU Page Size"
+	default ARC_PAGE_SIZE_8K
+
+config ARC_PAGE_SIZE_8K
+	bool "8KB"
+	help
+	  Choose between 8k vs 16k
+
+config ARC_PAGE_SIZE_16K
+	bool "16KB"
+	depends on ARC_MMU_V3
+
+config ARC_PAGE_SIZE_4K
+	bool "4KB"
+	depends on ARC_MMU_V3
+
+endchoice
+
+config ARC_COMPACT_IRQ_LEVELS
+	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+	default n
+	# Timer HAS to be high priority, for any other high priority config
+	select ARC_IRQ3_LV2
+	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
+	depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
+
+if ARC_COMPACT_IRQ_LEVELS
+
+config ARC_IRQ3_LV2
+	bool
+
+config ARC_IRQ5_LV2
+	bool
+
+config ARC_IRQ6_LV2
+	bool
+
+endif
+
+config ARC_FPU_SAVE_RESTORE
+	bool "Enable FPU state persistence across context switch"
+	default n
+	help
+	  Double Precision Floating Point unit had dedictaed regs which
+	  need to be saved/restored across context-switch.
+	  Note that ARC FPU is overly simplistic, unlike say x86, which has
+	  hardware pieces to allow software to conditionally save/restore,
+	  based on actual usage of FPU by a task. Thus our implemn does
+	  this for all tasks in system.
+
+menuconfig ARC_CPU_REL_4_10
+	bool "Enable support for Rel 4.10 features"
+	default n
+	help
+	  -ARC770 (and dependent features) enabled
+	  -ARC750 also shares some of the new features with 770
+
+config ARC_HAS_LLSC
+	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
+	default y
+	depends on ARC_CPU_770
+	# if SMP, enable LLSC ONLY if ARC implementation has coherent atomics
+	depends on !SMP || ARC_HAS_COH_LLSC
+
+config ARC_HAS_SWAPE
+	bool "Insn: SWAPE (endian-swap)"
+	default y
+	depends on ARC_CPU_REL_4_10
+
+config ARC_HAS_RTSC
+	bool "Insn: RTSC (64-bit r/o cycle counter)"
+	default y
+	depends on ARC_CPU_REL_4_10
+	# if SMP, enable RTSC only if counter is coherent across cores
+	depends on !SMP || ARC_HAS_COH_RTSC
+
+endmenu   # "ARC CPU Configuration"
+
+config LINUX_LINK_BASE
+	hex "Linux Link Address"
+	default "0x80000000"
+	help
+	  ARC700 divides the 32 bit phy address space into two equal halves
+	  -Lower 2G (0 - 0x7FFF_FFFF ) is user virtual, translated by MMU
+	  -Upper 2G (0x8000_0000 onwards) is untranslated, for kernel
+	  Typically Linux kernel is linked at the start of untransalted addr,
+	  hence the default value of 0x8zs.
+	  However some customers have peripherals mapped at this addr, so
+	  Linux needs to be scooted a bit.
+	  If you don't know what the above means, leave this setting alone.
+
+config ARC_CURR_IN_REG
+	bool "Dedicate Register r25 for current_task pointer"
+	default y
+	help
+	  This reserved Register R25 to point to Current Task in
+	  kernel mode. This saves memory access for each such access
+
+
+config ARC_MISALIGN_ACCESS
+	bool "Emulate unaligned memory access (userspace only)"
+	default N
+	select SYSCTL_ARCH_UNALIGN_NO_WARN
+	select SYSCTL_ARCH_UNALIGN_ALLOW
+	help
+	  This enables misaligned 16 & 32 bit memory access from user space.
+	  Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide
+	  potential bugs in code
+
+config ARC_STACK_NONEXEC
+	bool "Make stack non-executable"
+	default n
+	help
+	  To disable the execute permissions of stack/heap of processes
+	  which are enabled by default.
+
+config HZ
+	int "Timer Frequency"
+	default 100
+
+config ARC_METAWARE_HLINK
+	bool "Support for Metaware debugger assisted Host access"
+	default n
+	help
+	  This options allows a Linux userland apps to directly access
+	  host file system (open/creat/read/write etc) with help from
+	  Metaware Debugger. This can come in handy for Linux-host communication
+	  when there is no real usable peripheral such as EMAC.
+
+menuconfig ARC_DBG
+	bool "ARC debugging"
+	default y
+
+config ARC_DW2_UNWIND
+	bool "Enable DWARF specific kernel stack unwind"
+	depends on ARC_DBG
+	default y
+	select KALLSYMS
+	help
+	  Compiles the kernel with DWARF unwind information and can be used
+	  to get stack backtraces.
+
+	  If you say Y here the resulting kernel image will be slightly larger
+	  but not slower, and it will give very useful debugging information.
+	  If you don't debug the kernel, you can say N, but we may not be able
+	  to solve problems without frame unwind information
+
+config ARC_DBG_TLB_PARANOIA
+	bool "Paranoia Checks in Low Level TLB Handlers"
+	depends on ARC_DBG
+	default n
+
+config ARC_DBG_TLB_MISS_COUNT
+	bool "Profile TLB Misses"
+	default n
+	select DEBUG_FS
+	depends on ARC_DBG
+	help
+	  Counts number of I and D TLB Misses and exports them via Debugfs
+	  The counters can be cleared via Debugfs as well
+
+config CMDLINE
+	string "Kernel command line to built-in"
+	default "print-fatal-signals=1"
+	help
+	  The default command line which will be appended to the optional
+	  u-boot provided command line (see below)
+
+config CMDLINE_UBOOT
+	bool "Support U-boot kernel command line passing"
+	default n
+	help
+	  If you are using U-boot (www.denx.de) and wish to pass the kernel
+	  command line from the U-boot environment to the Linux kernel then
+	  switch this option on.
+	  ARC U-boot will setup the cmdline in RAM/flash and set r2 to point
+	  to it. kernel startup code will copy the string into cmdline buffer
+	  and also append CONFIG_CMDLINE.
+
+config ARC_BUILTIN_DTB_NAME
+	string "Built in DTB"
+	help
+	  Set the name of the DTB to embed in the vmlinux binary
+	  Leaving it blank selects the minimal "skeleton" dtb
+
+source "kernel/Kconfig.preempt"
+
+endmenu	 # "ARC Architecture Configuration"
+
+source "mm/Kconfig"
+source "net/Kconfig"
+source "drivers/Kconfig"
+source "fs/Kconfig"
+source "arch/arc/Kconfig.debug"
+source "security/Kconfig"
+source "crypto/Kconfig"
+source "lib/Kconfig"

arch/arc/Kconfig.debug

+menu "Kernel hacking"
+
+source "lib/Kconfig.debug"
+
+config EARLY_PRINTK
+	bool "Early printk" if EMBEDDED
+	default y
+	help
+	  Write kernel log output directly into the VGA buffer or to a serial
+	  port.
+
+	  This is useful for kernel debugging when your machine crashes very
+	  early before the console code is initialized. For normal operation
+	  it is not recommended because it looks ugly and doesn't cooperate
+	  with klogd/syslogd or the X server. You should normally N here,
+	  unless you want to debug such a crash.
+
+config DEBUG_STACKOVERFLOW
+	bool "Check for stack overflows"
+	depends on DEBUG_KERNEL
+	help
+	  This option will cause messages to be printed if free stack space
+	  drops below a certain limit.
+
+config 16KSTACKS
+	bool "Use 16Kb for kernel stacks instead of 8Kb"
+	help
+	  If you say Y here the kernel will use a  16Kb stacksize for the
+	  kernel stack attached to each process/thread. The default is 8K.
+	  This increases the resident kernel footprint and will cause less
+	  threads to run on the system and also increase the pressure
+	  on the VM subsystem for higher order allocations.
+
+endmenu

arch/arc/Makefile

+#
+# Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+UTS_MACHINE := arc
+
+KBUILD_DEFCONFIG := fpga_defconfig
+
+cflags-y	+= -mA7 -fno-common -pipe -fno-builtin -D__linux__
+
+LINUXINCLUDE	+=  -include ${src}/arch/arc/include/asm/defines.h
+
+ifdef CONFIG_ARC_CURR_IN_REG
+# For a global register defintion, make sure it gets passed to every file
+# We had a customer reported bug where some code built in kernel was NOT using
+# any kernel headers, and missing the r25 global register
+# Can't do unconditionally (like above) because of recursive include issues
+# due to <linux/thread_info.h>
+LINUXINCLUDE	+=  -include ${src}/arch/arc/include/asm/current.h
+endif
+
+atleast_gcc44 :=  $(call cc-ifversion, -gt, 0402, y)
+cflags-$(atleast_gcc44)			+= -fsection-anchors
+
+cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
+cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
+cflags-$(CONFIG_ARC_HAS_RTSC)		+= -mrtsc
+cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
+
+ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+# Generic build system uses -O2, we want -O3
+cflags-y  += -O3
+endif
+
+# small data is default for elf32 tool-chain. If not usable, disable it
+# This also allows repurposing GP as scratch reg to gcc reg allocator
+disable_small_data := y
+cflags-$(disable_small_data)		+= -mno-sdata -fcall-used-gp
+
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mbig-endian
+ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
+
+# STAR 9000518362:
+# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept
+# --build-id w/o "-marclinux".
+# Default arc-elf32-ld is OK
+ldflags-y				+= -marclinux
+
+ARC_LIBGCC				:= -mA7
+cflags-$(CONFIG_ARC_HAS_HW_MPY)		+= -multcost=16
+
+ifndef CONFIG_ARC_HAS_HW_MPY
+	cflags-y	+= -mno-mpy
+
+# newlib for ARC700 assumes MPY to be always present, which is generally true
+# However, if someone really doesn't want MPY, we need to use the 600 ver
+# which coupled with -mno-mpy will use mpy emulation
+# With gcc 4.4.7, -mno-mpy is enough to make any other related adjustments,
+# e.g. increased cost of MPY. With gcc 4.2.1 this had to be explicitly hinted
+
+	ARC_LIBGCC		:= -marc600
+	ifneq ($(atleast_gcc44),y)
+		cflags-y	+= -multcost=30
+	endif
+endif
+
+LIBGCC	:= $(shell $(CC) $(ARC_LIBGCC) $(cflags-y) --print-libgcc-file-name)
+
+# Modules with short calls might break for calls into builtin-kernel
+KBUILD_CFLAGS_MODULE	+= -mlong-calls
+
+# Finally dump eveything into kernel build system
+KBUILD_CFLAGS	+= $(cflags-y)
+KBUILD_AFLAGS	+= $(KBUILD_CFLAGS)
+LDFLAGS		+= $(ldflags-y)
+
+head-y		:= arch/arc/kernel/head.o
+
+# See arch/arc/Kbuild for content of core part of the kernel
+core-y		+= arch/arc/
+
+# w/o this dtb won't embed into kernel binary
+core-y		+= arch/arc/boot/dts/
+
+core-$(CONFIG_ARC_PLAT_FPGA_LEGACY)	+= arch/arc/plat-arcfpga/
+
+drivers-$(CONFIG_OPROFILE)	+= arch/arc/oprofile/
+
+libs-y		+= arch/arc/lib/ $(LIBGCC)
+
+#default target for make without any arguements.
+KBUILD_IMAGE := bootpImage
+
+all:	$(KBUILD_IMAGE)
+boot	:= arch/arc/boot
+
+bootpImage: vmlinux
+
+uImage: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+%.dtb %.dtb.S %.dtb.o: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@
+
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+
+archclean:
+	$(Q)$(MAKE) $(clean)=$(boot)
+
+# Hacks to enable final link due to absence of link-time branch relexation
+# and gcc choosing optimal(shorter) branches at -O3
+#
+# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
+# However lib/decompress_inflate.o (.init.text) calls
+# zlib_inflate_workspacesize (.text) causing relocation errors.
+# Thus forcing all exten calls in this file to be long calls
+export CFLAGS_decompress_inflate.o = -mmedium-calls
+export CFLAGS_initramfs.o = -mmedium-calls
+ifdef CONFIG_SMP
+export CFLAGS_core.o = -mmedium-calls
+endif

arch/arc/boot/Makefile

+targets := vmlinux.bin vmlinux.bin.gz uImage
+
+# uImage build relies on mkimage being availble on your host for ARC target
+# You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
+# and make sure it's reacable from your PATH
+MKIMAGE := $(srctree)/scripts/mkuboot.sh
+
+OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S
+
+LINUX_START_TEXT = $$(readelf -h vmlinux | \
+			grep "Entry point address" | grep -o 0x.*)
+
+UIMAGE_LOADADDR    = $(CONFIG_LINUX_LINK_BASE)
+UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
+UIMAGE_COMPRESSION = gzip
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+$(obj)/uImage: $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,uimage)
+
+PHONY += FORCE

arch/arc/boot/dts/Makefile

+# Built-in dtb
+builtindtb-y		:= angel4
+
+ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),"")
+	builtindtb-y	:= $(patsubst "%",%,$(CONFIG_ARC_BUILTIN_DTB_NAME))
+endif
+
+obj-y   += $(builtindtb-y).dtb.o
+targets += $(builtindtb-y).dtb
+
+dtbs:  $(addprefix  $(obj)/, $(builtindtb-y).dtb)
+
+clean-files := *.dtb

arch/arc/boot/dts/angel4.dts

+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,arc-angel4";
+	clock-frequency = <80000000>;	/* 80 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&intc>;
+
+	chosen {
+		bootargs = "console=ttyARC0,115200n8";
+	};
+
+	aliases {
+		serial0 = &arcuart0;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;	/* 256M */
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		intc: interrupt-controller {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		arcuart0: serial@c0fc1000 {
+			compatible = "snps,arc-uart";
+			reg = <0xc0fc1000 0x100>;
+			interrupts = <5>;
+			clock-frequency = <80000000>;
+			current-speed = <115200>;
+			status = "okay";
+		};
+	};
+};

arch/arc/boot/dts/skeleton.dts

+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"

arch/arc/boot/dts/skeleton.dtsi

+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Skeleton device tree; the bare minimum needed to boot; just include and
+ * add a compatible value.
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <80000000>;	/* 80 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "snps,arc770d";
+			reg = <0>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;	/* 256M */
+	};
+};

arch/arc/configs/fpga_defconfig

+CONFIG_CROSS_COMPILE="arc-elf32-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs"
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_FPGA_LEGACY=y
+CONFIG_ARC_BOARD_ML509=y
+# CONFIG_ARC_HAS_RTSC is not set
+CONFIG_ARC_BUILTIN_DTB_NAME="angel4"
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_ARC=y
+CONFIG_SERIAL_ARC_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_XZ_DEC=y

arch/arc/include/asm/Kbuild

+generic-y += auxvec.h
+generic-y += bugs.h
+generic-y += bitsperlong.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += fb.h
+generic-y += ftrace.h
+generic-y += hardirq.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += pci.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += siginfo.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += types.h
+generic-y += ucontext.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += xor.h

arch/arc/include/asm/arcregs.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_ARCREGS_H
+#define _ASM_ARC_ARCREGS_H
+
+#ifdef __KERNEL__
+
+/* Build Configuration Registers */
+#define ARC_REG_DCCMBASE_BCR	0x61	/* DCCM Base Addr */
+#define ARC_REG_CRC_BCR		0x62
+#define ARC_REG_DVFB_BCR	0x64
+#define ARC_REG_EXTARITH_BCR	0x65
+#define ARC_REG_VECBASE_BCR	0x68
+#define ARC_REG_PERIBASE_BCR	0x69
+#define ARC_REG_FP_BCR		0x6B	/* Single-Precision FPU */
+#define ARC_REG_DPFP_BCR	0x6C	/* Dbl Precision FPU */
+#define ARC_REG_MMU_BCR		0x6f
+#define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
+#define ARC_REG_TIMERS_BCR	0x75
+#define ARC_REG_ICCM_BCR	0x78
+#define ARC_REG_XY_MEM_BCR	0x79
+#define ARC_REG_MAC_BCR		0x7a
+#define ARC_REG_MUL_BCR		0x7b
+#define ARC_REG_SWAP_BCR	0x7c
+#define ARC_REG_NORM_BCR	0x7d
+#define ARC_REG_MIXMAX_BCR	0x7e
+#define ARC_REG_BARREL_BCR	0x7f
+#define ARC_REG_D_UNCACH_BCR	0x6A
+
+/* status32 Bits Positions */
+#define STATUS_H_BIT		0	/* CPU Halted */
+#define STATUS_E1_BIT		1	/* Int 1 enable */
+#define STATUS_E2_BIT		2	/* Int 2 enable */
+#define STATUS_A1_BIT		3	/* Int 1 active */
+#define STATUS_A2_BIT		4	/* Int 2 active */
+#define STATUS_AE_BIT		5	/* Exception active */
+#define STATUS_DE_BIT		6	/* PC is in delay slot */
+#define STATUS_U_BIT		7	/* User/Kernel mode */
+#define STATUS_L_BIT		12	/* Loop inhibit */
+
+/* These masks correspond to the status word(STATUS_32) bits */
+#define STATUS_H_MASK		(1<<STATUS_H_BIT)
+#define STATUS_E1_MASK		(1<<STATUS_E1_BIT)
+#define STATUS_E2_MASK		(1<<STATUS_E2_BIT)
+#define STATUS_A1_MASK		(1<<STATUS_A1_BIT)
+#define STATUS_A2_MASK		(1<<STATUS_A2_BIT)
+#define STATUS_AE_MASK		(1<<STATUS_AE_BIT)
+#define STATUS_DE_MASK		(1<<STATUS_DE_BIT)
+#define STATUS_U_MASK		(1<<STATUS_U_BIT)
+#define STATUS_L_MASK		(1<<STATUS_L_BIT)
+
+/*
+ * ECR: Exception Cause Reg bits-n-pieces
+ * [23:16] = Exception Vector
+ * [15: 8] = Exception Cause Code
+ * [ 7: 0] = Exception Parameters (for certain types only)
+ */
+#define ECR_VEC_MASK			0xff0000
+#define ECR_CODE_MASK			0x00ff00
+#define ECR_PARAM_MASK			0x0000ff
+
+/* Exception Cause Vector Values */
+#define ECR_V_INSN_ERR			0x02
+#define ECR_V_MACH_CHK			0x20
+#define ECR_V_ITLB_MISS			0x21
+#define ECR_V_DTLB_MISS			0x22
+#define ECR_V_PROTV			0x23
+
+/* Protection Violation Exception Cause Code Values */
+#define ECR_C_PROTV_INST_FETCH		0x00
+#define ECR_C_PROTV_LOAD		0x01
+#define ECR_C_PROTV_STORE		0x02
+#define ECR_C_PROTV_XCHG		0x03
+#define ECR_C_PROTV_MISALIG_DATA	0x04
+
+/* DTLB Miss Exception Cause Code Values */
+#define ECR_C_BIT_DTLB_LD_MISS		8
+#define ECR_C_BIT_DTLB_ST_MISS		9
+
+
+/* Auxiliary registers */
+#define AUX_IDENTITY		4
+#define AUX_INTR_VEC_BASE	0x25
+#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_LV12		0x43	/* interrupt level register */
+
+#define AUX_IENABLE		0x40c
+#define AUX_ITRIGGER		0x40d
+#define AUX_IPULSE		0x415
+
+/* Timer related Aux registers */
+#define ARC_REG_TIMER0_LIMIT	0x23	/* timer 0 limit */
+#define ARC_REG_TIMER0_CTRL	0x22	/* timer 0 control */
+#define ARC_REG_TIMER0_CNT	0x21	/* timer 0 count */
+#define ARC_REG_TIMER1_LIMIT	0x102	/* timer 1 limit */
+#define ARC_REG_TIMER1_CTRL	0x101	/* timer 1 control */
+#define ARC_REG_TIMER1_CNT	0x100	/* timer 1 count */
+
+#define TIMER_CTRL_IE		(1 << 0) /* Interupt when Count reachs limit */
+#define TIMER_CTRL_NH		(1 << 1) /* Count only when CPU NOT halted */
+
+/* MMU Management regs */
+#define ARC_REG_TLBPD0		0x405
+#define ARC_REG_TLBPD1		0x406
+#define ARC_REG_TLBINDEX	0x407
+#define ARC_REG_TLBCOMMAND	0x408
+#define ARC_REG_PID		0x409
+#define ARC_REG_SCRATCH_DATA0	0x418
+
+/* Bits in MMU PID register */
+#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+
+/* Error code if probe fails */
+#define TLB_LKUP_ERR		0x80000000
+
+/* TLB Commands */
+#define TLBWrite    0x1
+#define TLBRead     0x2
+#define TLBGetIndex 0x3
+#define TLBProbe    0x4
+
+#if (CONFIG_ARC_MMU_VER >= 2)
+#define TLBWriteNI  0x5		/* write JTLB without inv uTLBs */
+#define TLBIVUTLB   0x6		/* explicitly inv uTLBs */
+#else
+#undef TLBWriteNI		/* These cmds don't exist on older MMU */
+#undef TLBIVUTLB
+#endif
+
+/* Instruction cache related Auxiliary registers */
+#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
+#define ARC_REG_IC_IVIC		0x10
+#define ARC_REG_IC_CTRL		0x11
+#define ARC_REG_IC_IVIL		0x19
+#if (CONFIG_ARC_MMU_VER > 2)
+#define ARC_REG_IC_PTAG		0x1E
+#endif
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_CACHE_DISABLE   0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR		0x72
+#define ARC_REG_DC_IVDC		0x47
+#define ARC_REG_DC_CTRL		0x48
+#define ARC_REG_DC_IVDL		0x4A
+#define ARC_REG_DC_FLSH		0x4B
+#define ARC_REG_DC_FLDL		0x4C
+#if (CONFIG_ARC_MMU_VER > 2)
+#define ARC_REG_DC_PTAG		0x5C
+#endif
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_INV_MODE_FLUSH  0x40
+#define DC_CTRL_FLUSH_STATUS    0x100
+
+/* MMU Management regs */
+#define ARC_REG_PID		0x409
+#define ARC_REG_SCRATCH_DATA0	0x418
+
+/* Bits in MMU PID register */
+#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+
+/*
+ * Floating Pt Registers
+ * Status regs are read-only (build-time) so need not be saved/restored
+ */
+#define ARC_AUX_FP_STAT         0x300
+#define ARC_AUX_DPFP_1L         0x301
+#define ARC_AUX_DPFP_1H         0x302
+#define ARC_AUX_DPFP_2L         0x303
+#define ARC_AUX_DPFP_2H         0x304
+#define ARC_AUX_DPFP_STAT       0x305
+
+#ifndef __ASSEMBLY__
+
+/*
+ ******************************************************************
+ *      Inline ASM macros to read/write AUX Regs
+ *      Essentially invocation of lr/sr insns from "C"
+ */
+
+#if 1
+
+#define read_aux_reg(reg)	__builtin_arc_lr(reg)
+
+/* gcc builtin sr needs reg param to be long immediate */
+#define write_aux_reg(reg_immed, val)		\
+		__builtin_arc_sr((unsigned int)val, reg_immed)
+
+#else
+
+#define read_aux_reg(reg)		\
+({					\
+	unsigned int __ret;		\
+	__asm__ __volatile__(		\
+	"	lr    %0, [%1]"		\
+	: "=r"(__ret)			\
+	: "i"(reg));			\
+	__ret;				\
+})
+
+/*
+ * Aux Reg address is specified as long immediate by caller
+ * e.g.
+ *    write_aux_reg(0x69, some_val);
+ * This generates tightest code.
+ */
+#define write_aux_reg(reg_imm, val)	\
+({					\
+	__asm__ __volatile__(		\
+	"	sr   %0, [%1]	\n"	\
+	:				\
+	: "ir"(val), "i"(reg_imm));	\
+})
+
+/*
+ * Aux Reg address is specified in a variable
+ *  * e.g.
+ *      reg_num = 0x69
+ *      write_aux_reg2(reg_num, some_val);
+ * This has to generate glue code to load the reg num from
+ *  memory to a reg hence not recommended.
+ */
+#define write_aux_reg2(reg_in_var, val)		\
+({						\
+	unsigned int tmp;			\
+						\
+	__asm__ __volatile__(			\
+	"	ld   %0, [%2]	\n\t"		\
+	"	sr   %1, [%0]	\n\t"		\
+	: "=&r"(tmp)				\
+	: "r"(val), "memory"(&reg_in_var));	\
+})
+
+#endif
+
+#define READ_BCR(reg, into)				\
+{							\
+	unsigned int tmp;				\
+	tmp = read_aux_reg(reg);			\
+	if (sizeof(tmp) == sizeof(into)) {		\
+		into = *((typeof(into) *)&tmp);		\
+	} else {					\
+		extern void bogus_undefined(void);	\
+		bogus_undefined();			\
+	}						\
+}
+
+#define WRITE_BCR(reg, into)				\
+{							\
+	unsigned int tmp;				\
+	if (sizeof(tmp) == sizeof(into)) {		\
+		tmp = (*(unsigned int *)(into));	\
+		write_aux_reg(reg, tmp);		\
+	} else  {					\
+		extern void bogus_undefined(void);	\
+		bogus_undefined();			\
+	}						\
+}
+
+/* Helpers */
+#define TO_KB(bytes)		((bytes) >> 10)
+#define TO_MB(bytes)		(TO_KB(bytes) >> 10)
+#define PAGES_TO_KB(n_pages)	((n_pages) << (PAGE_SHIFT - 10))
+#define PAGES_TO_MB(n_pages)	(PAGES_TO_KB(n_pages) >> 10)
+
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+/* These DPFP regs need to be saved/restored across ctx-sw */
+struct arc_fpu {
+	struct {
+		unsigned int l, h;
+	} aux_dpfp[2];
+};
+#endif
+
+/*
+ ***************************************************************
+ * Build Configuration Registers, with encoded hardware config
+ */
+struct bcr_identity {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int chip_id:16, cpu_id:8, family:8;
+#else
+	unsigned int family:8, cpu_id:8, chip_id:16;
+#endif
+};
+
+struct bcr_mmu_1_2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8;
+#else
+	unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8;
+#endif
+};
+
+struct bcr_mmu_3 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, pg_sz:4,
+		     u_itlb:4, u_dtlb:4;
+#else
+	unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, reserv:3, osm:1, sets:4,
+		     ways:4, ver:8;
+#endif
+};
+
+#define EXTN_SWAP_VALID     0x1
+#define EXTN_NORM_VALID     0x2
+#define EXTN_MINMAX_VALID   0x2
+#define EXTN_BARREL_VALID   0x2
+
+struct bcr_extn {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:20, crc:1, ext_arith:2, mul:2, barrel:2, minmax:2,
+		     norm:2, swap:1;
+#else
+	unsigned int swap:1, norm:2, minmax:2, barrel:2, mul:2, ext_arith:2,
+		     crc:1, pad:20;
+#endif
+};
+
+/* DSP Options Ref Manual */
+struct bcr_extn_mac_mul {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:16, type:8, ver:8;
+#else
+	unsigned int ver:8, type:8, pad:16;
+#endif
+};
+
+struct bcr_extn_xymem {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ram_org:2, num_banks:4, bank_sz:4, ver:8;
+#else
+	unsigned int ver:8, bank_sz:4, num_banks:4, ram_org:2;
+#endif
+};
+
+struct bcr_cache {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:12, line_len:4, sz:4, config:4, ver:8;
+#else
+	unsigned int ver:8, config:4, sz:4, line_len:4, pad:12;
+#endif
+};
+
+struct bcr_perip {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int start:8, pad2:8, sz:8, pad:8;
+#else
+	unsigned int pad:8, sz:8, pad2:8, start:8;
+#endif
+};
+struct bcr_iccm {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int base:16, pad:5, sz:3, ver:8;
+#else
+	unsigned int ver:8, sz:3, pad:5, base:16;
+#endif
+};
+
+/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */
+struct bcr_dccm_base {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int addr:24, ver:8;
+#else
+	unsigned int ver:8, addr:24;
+#endif
+};
+
+/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */
+struct bcr_dccm {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int res:21, sz:3, ver:8;
+#else
+	unsigned int ver:8, sz:3, res:21;
+#endif
+};
+
+/* Both SP and DP FPU BCRs have same format */
+struct bcr_fp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int fast:1, ver:8;
+#else
+	unsigned int ver:8, fast:1;
+#endif
+};
+
+/*
+ *******************************************************************
+ * Generic structures to hold build configuration used at runtime
+ */
+
+struct cpuinfo_arc_mmu {
+	unsigned int ver, pg_sz, sets, ways, u_dtlb, u_itlb, num_tlb;
+};
+
+struct cpuinfo_arc_cache {
+	unsigned int has_aliasing, sz, line_len, assoc, ver;
+};
+
+struct cpuinfo_arc_ccm {
+	unsigned int base_addr, sz;
+};
+
+struct cpuinfo_arc {
+	struct cpuinfo_arc_cache icache, dcache;
+	struct cpuinfo_arc_mmu mmu;
+	struct bcr_identity core;
+	unsigned int timers;
+	unsigned int vec_base;
+	unsigned int uncached_base;
+	struct cpuinfo_arc_ccm iccm, dccm;
+	struct bcr_extn extn;
+	struct bcr_extn_xymem extn_xymem;
+	struct bcr_extn_mac_mul extn_mac_mul;
+	struct bcr_fp fp, dpfp;
+};
+
+extern struct cpuinfo_arc cpuinfo_arc700[];
+
+#endif /* __ASEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_ARC_ARCREGS_H */

arch/arc/include/asm/asm-offsets.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <generated/asm-offsets.h>

arch/arc/include/asm/atomic.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_ATOMIC_H
+#define _ASM_ARC_ATOMIC_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+#include <asm/smp.h>
+
+#define atomic_read(v)  ((v)->counter)
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define atomic_set(v, i) (((v)->counter) = (i))
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	add     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	sub     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+}
+
+/* add and also return the new value */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	add     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	sub     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(&v->counter), "ir"(i)
+	: "cc");
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned int temp;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bic     %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(addr), "ir"(mask)
+	: "cc");
+}
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#ifndef CONFIG_SMP
+
+ /* violating atomic_xxx API locking protocol in UP for optimization sake */
+#define atomic_set(v, i) (((v)->counter) = (i))
+
+#else
+
+static inline void atomic_set(atomic_t *v, int i)
+{
+	/*
+	 * Independent of hardware support, all of the atomic_xxx() APIs need
+	 * to follow the same locking rules to make sure that a "hardware"
+	 * atomic insn (e.g. LD) doesn't clobber an "emulated" atomic insn
+	 * sequence
+	 *
+	 * Thus atomic_set() despite being 1 insn (and seemingly atomic)
+	 * requires the locking.
+	 */
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter = i;
+	atomic_ops_unlock(flags);
+}
+#endif
+
+/*
+ * Non hardware assisted Atomic-R-M-W
+ * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
+ */
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter += i;
+	atomic_ops_unlock(flags);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	v->counter -= i;
+	atomic_ops_unlock(flags);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	unsigned long temp;
+
+	atomic_ops_lock(flags);
+	temp = v->counter;
+	temp += i;
+	v->counter = temp;
+	atomic_ops_unlock(flags);
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	unsigned long temp;
+
+	atomic_ops_lock(flags);
+	temp = v->counter;
+	temp -= i;
+	v->counter = temp;
+	atomic_ops_unlock(flags);
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned long flags;
+
+	atomic_ops_lock(flags);
+	*addr &= ~mask;
+	atomic_ops_unlock(flags);
+}
+
+#endif /* !CONFIG_ARC_HAS_LLSC */
+
+/**
+ * __atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v
+ */
+#define __atomic_add_unless(v, a, u)					\
+({									\
+	int c, old;							\
+	c = atomic_read(v);						\
+	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
+		c = old;						\
+	c;								\
+})
+
+#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
+
+#define atomic_inc(v)			atomic_add(1, v)
+#define atomic_dec(v)			atomic_sub(1, v)
+
+#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
+#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
+
+#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
+
+#define ATOMIC_INIT(i)			{ (i) }
+
+#include <asm-generic/atomic64.h>
+
+#endif
+
+#endif
+
+#endif

arch/arc/include/asm/barrier.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */
+#define mb() __asm__ __volatile__ ("" : : : "memory")
+#define rmb() mb()
+#define wmb() mb()
+#define set_mb(var, value)  do { var = value; mb(); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+#define read_barrier_depends()  mb()
+
+/* TODO-vineetg verify the correctness of macros here */
+#ifdef CONFIG_SMP
+#define smp_mb()        mb()
+#define smp_rmb()       rmb()
+#define smp_wmb()       wmb()
+#else
+#define smp_mb()        barrier()
+#define smp_rmb()       barrier()
+#define smp_wmb()       barrier()
+#endif
+
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+#define smp_read_barrier_depends()      do { } while (0)
+
+#endif
+
+#endif

arch/arc/include/asm/bitops.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_BITOPS_H
+#define _ASM_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+/*
+ * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns.
+ * The Kconfig glue ensures that in SMP, this is only set if the container
+ * SoC/platform has cross-core coherent LLOCK/SCOND
+ */
+#if defined(CONFIG_ARC_HAS_LLSC)
+
+static inline void set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bset    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b	\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bclr    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b	\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+static inline void change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	bxor    %0, %0, %2	\n"
+	"	scond   %0, [%1]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+}
+
+/*
+ * Semantically:
+ *    Test the bit
+ *    if clear
+ *        set it and return 0 (old value)
+ *    else
+ *        return 1 (old value).
+ *
+ * Since ARC lacks a equivalent h/w primitive, the bit is set unconditionally
+ * and the old value of bit is returned
+ */
+static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bset    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bclr    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned int old, temp;
+
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%2]	\n"
+	"	bxor    %1, %0, %3	\n"
+	"	scond   %1, [%2]	\n"
+	"	bnz     1b		\n"
+	: "=&r"(old), "=&r"(temp)
+	: "r"(m), "ir"(nr)
+	: "cc");
+
+	return (old & (1 << nr)) != 0;
+}
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#include <asm/smp.h>
+
+/*
+ * Non hardware assisted Atomic-R-M-W
+ * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
+ *
+ * There's "significant" micro-optimization in writing our own variants of
+ * bitops (over generic variants)
+ *
+ * (1) The generic APIs have "signed" @nr while we have it "unsigned"
+ *     This avoids extra code to be generated for pointer arithmatic, since
+ *     is "not sure" that index is NOT -ve
+ * (2) Utilize the fact that ARCompact bit fidding insn (BSET/BCLR/ASL) etc
+ *     only consider bottom 5 bits of @nr, so NO need to mask them off.
+ *     (GCC Quirk: however for constant @nr we still need to do the masking
+ *             at compile time)
+ */
+
+static inline void set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp | (1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp & ~(1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline void change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	temp = *m;
+	*m = temp ^ (1UL << nr);
+
+	bitops_unlock(flags);
+}
+
+static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old | (1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old & ~(1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old, flags;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	bitops_lock(flags);
+
+	old = *m;
+	*m = old ^ (1 << nr);
+
+	bitops_unlock(flags);
+
+	return (old & (1 << nr)) != 0;
+}
+
+#endif /* CONFIG_ARC_HAS_LLSC */
+
+/***************************************
+ * Non atomic variants
+ **************************************/
+
+static inline void __set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp | (1UL << nr);
+}
+
+static inline void __clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp & ~(1UL << nr);
+}
+
+static inline void __change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long temp;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	temp = *m;
+	*m = temp ^ (1UL << nr);
+}
+
+static inline int
+__test_and_set_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old | (1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+__test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old & ~(1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+static inline int
+__test_and_change_bit(unsigned long nr, volatile unsigned long *m)
+{
+	unsigned long old;
+	m += nr >> 5;
+
+	if (__builtin_constant_p(nr))
+		nr &= 0x1f;
+
+	old = *m;
+	*m = old ^ (1 << nr);
+
+	return (old & (1 << nr)) != 0;
+}
+
+/*
+ * This routine doesn't need to be atomic.
+ */
+static inline int
+__constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+{
+	return ((1UL << (nr & 31)) &
+		(((const volatile unsigned int *)addr)[nr >> 5])) != 0;
+}
+
+static inline int
+__test_bit(unsigned int nr, const volatile unsigned long *addr)
+{
+	unsigned long mask;
+
+	addr += nr >> 5;
+
+	/* ARC700 only considers 5 bits in bit-fiddling insn */
+	mask = 1 << nr;
+
+	return ((mask & *addr) != 0);
+}
+
+#define test_bit(nr, addr)	(__builtin_constant_p(nr) ? \
+					__constant_test_bit((nr), (addr)) : \
+					__test_bit((nr), (addr)))
+
+/*
+ * Count the number of zeros, starting from MSB
+ * Helper for fls( ) friends
+ * This is a pure count, so (1-32) or (0-31) doesn't apply
+ * It could be 0 to 32, based on num of 0's in there
+ * clz(0x8000_0000) = 0, clz(0xFFFF_FFFF)=0, clz(0) = 32, clz(1) = 31
+ */
+static inline __attribute__ ((const)) int clz(unsigned int x)
+{
+	unsigned int res;
+
+	__asm__ __volatile__(
+	"	norm.f  %0, %1		\n"
+	"	mov.n   %0, 0		\n"
+	"	add.p   %0, %0, 1	\n"
+	: "=r"(res)
+	: "r"(x)
+	: "cc");
+
+	return res;
+}
+
+static inline int constant_fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+/*
+ * fls = Find Last Set in word
+ * @result: [1-32]
+ * fls(1) = 1, fls(0x80000000) = 32, fls(0) = 0
+ */
+static inline __attribute__ ((const)) int fls(unsigned long x)
+{
+	if (__builtin_constant_p(x))
+	       return constant_fls(x);
+
+	return 32 - clz(x);
+}
+
+/*
+ * __fls: Similar to fls, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __fls(unsigned long x)
+{
+	if (!x)
+		return 0;
+	else
+		return fls(x) - 1;
+}
+
+/*
+ * ffs = Find First Set in word (LSB to MSB)
+ * @result: [1-32], 0 if all 0's
+ */
+#define ffs(x)	({ unsigned long __t = (x); fls(__t & -__t); })
+
+/*
+ * __ffs: Similar to ffs, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __ffs(unsigned long word)
+{
+	if (!word)
+		return word;
+
+	return ffs(word) - 1;
+}
+
+/*
+ * ffz = Find First Zero in word.
+ * @return:[0-31], 32 if all 1's
+ */
+#define ffz(x)	__ffs(~(x))
+
+/* TODO does this affect uni-processor code */
+#define smp_mb__before_clear_bit()  barrier()
+#define smp_mb__after_clear_bit()   barrier()
+
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/lock.h>
+
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif

arch/arc/include/asm/bug.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_BUG_H
+#define _ASM_ARC_BUG_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/ptrace.h>
+
+struct task_struct;
+
+void show_regs(struct pt_regs *regs);
+void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs);
+void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
+			    unsigned long address, unsigned long cause_reg);
+void die(const char *str, struct pt_regs *regs, unsigned long address,
+	 unsigned long cause_reg);
+
+#define BUG()	do {				\
+	dump_stack();					\
+	pr_warn("Kernel BUG in %s: %s: %d!\n",	\
+		__FILE__, __func__,  __LINE__);	\
+} while (0)
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#endif	/* !__ASSEMBLY__ */
+
+#endif

arch/arc/include/asm/cache.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_CACHE_H
+#define __ARC_ASM_CACHE_H
+
+/* In case $$ not config, setup a dummy number for rest of kernel */
+#ifndef CONFIG_ARC_CACHE_LINE_SHIFT
+#define L1_CACHE_SHIFT		6
+#else
+#define L1_CACHE_SHIFT		CONFIG_ARC_CACHE_LINE_SHIFT
+#endif
+
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define ARC_ICACHE_WAYS	2
+#define ARC_DCACHE_WAYS	4
+
+/* Helpers */
+#define ARC_ICACHE_LINE_LEN	L1_CACHE_BYTES
+#define ARC_DCACHE_LINE_LEN	L1_CACHE_BYTES
+
+#define ICACHE_LINE_MASK	(~(ARC_ICACHE_LINE_LEN - 1))
+#define DCACHE_LINE_MASK	(~(ARC_DCACHE_LINE_LEN - 1))
+
+#if ARC_ICACHE_LINE_LEN != ARC_DCACHE_LINE_LEN
+#error "Need to fix some code as I/D cache lines not same"
+#else
+#define is_not_cache_aligned(p)	((unsigned long)p & (~DCACHE_LINE_MASK))
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* Uncached access macros */
+#define arc_read_uncached_32(ptr)	\
+({					\
+	unsigned int __ret;		\
+	__asm__ __volatile__(		\
+	"	ld.di %0, [%1]	\n"	\
+	: "=r"(__ret)			\
+	: "r"(ptr));			\
+	__ret;				\
+})
+
+#define arc_write_uncached_32(ptr, data)\
+({					\
+	__asm__ __volatile__(		\
+	"	st.di %0, [%1]	\n"	\
+	:				\
+	: "r"(data), "r"(ptr));		\
+})
+
+/* used to give SHMLBA a value to avoid Cache Aliasing */
+extern unsigned int ARC_shmlba;
+
+#define ARCH_DMA_MINALIGN      L1_CACHE_BYTES
+
+/*
+ * ARC700 doesn't cache any access in top 256M.
+ * Ideal for wiring memory mapped peripherals as we don't need to do
+ * explicit uncached accesses (LD.di/ST.di) hence more portable drivers
+ */
+#define ARC_UNCACHED_ADDR_SPACE	0xc0000000
+
+extern void arc_cache_init(void);
+extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
+extern void __init read_decode_cache_bcr(void);
+#endif
+
+#endif /* _ASM_CACHE_H */

arch/arc/include/asm/cacheflush.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  vineetg: May 2011: for Non-aliasing VIPT D-cache following can be NOPs
+ *   -flush_cache_dup_mm (fork)
+ *   -likewise for flush_cache_mm (exit/execve)
+ *   -likewise for flush_cache_{range,page} (munmap, exit, COW-break)
+ *
+ *  vineetg: April 2008
+ *   -Added a critical CacheLine flush to copy_to_user_page( ) which
+ *     was causing gdbserver to not setup breakpoints consistently
+ */
+
+#ifndef _ASM_CACHEFLUSH_H
+#define _ASM_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+void flush_cache_all(void);
+
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
+void flush_icache_range_vaddr(unsigned long paddr, unsigned long u_vaddr,
+				     int len);
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+
+void flush_dcache_page(struct page *page);
+
+void dma_cache_wback_inv(unsigned long start, unsigned long sz);
+void dma_cache_inv(unsigned long start, unsigned long sz);
+void dma_cache_wback(unsigned long start, unsigned long sz);
+
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+
+/* TBD: optimize this */
+#define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vunmap(start, end)		flush_cache_all()
+
+/*
+ * VM callbacks when entire/range of user-space V-P mappings are
+ * torn-down/get-invalidated
+ *
+ * Currently we don't support D$ aliasing configs for our VIPT caches
+ * NOPS for VIPT Cache with non-aliasing D$ configurations only
+ */
+#define flush_cache_dup_mm(mm)			/* called on fork */
+#define flush_cache_mm(mm)			/* called on munmap/exit */
+#define flush_cache_range(mm, u_vstart, u_vend)
+#define flush_cache_page(vma, u_vaddr, pfn)	/* PF handling/COW-break */
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
+do {									\
+	memcpy(dst, src, len);						\
+	if (vma->vm_flags & VM_EXEC)					\
+		flush_icache_range_vaddr((unsigned long)(dst), vaddr, len);\
+} while (0)
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)		\
+	memcpy(dst, src, len);						\
+
+#endif

arch/arc/include/asm/checksum.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Joern Rennecke  <joern.rennecke@embecosm.com>: Jan 2012
+ *  -Insn Scheduling improvements to csum core routines.
+ *      = csum_fold( ) largely derived from ARM version.
+ *      = ip_fast_cum( ) to have module scheduling
+ *  -gcc 4.4.x broke networking. Alias analysis needed to be primed.
+ *   worked around by adding memory clobber to ip_fast_csum( )
+ *
+ * vineetg: May 2010
+ *  -Rewrote ip_fast_cscum( ) and csum_fold( ) with fast inline asm
+ */
+
+#ifndef _ASM_ARC_CHECKSUM_H
+#define _ASM_ARC_CHECKSUM_H
+
+/*
+ *	Fold a partial checksum
+ *
+ *  The 2 swords comprising the 32bit sum are added, any carry to 16th bit
+ *  added back and final sword result inverted.
+ */
+static inline __sum16 csum_fold(__wsum s)
+{
+	unsigned r = s << 16 | s >> 16;	/* ror */
+	s = ~s;
+	s -= r;
+	return s >> 16;
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ */
+static inline __sum16
+ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	const void *ptr = iph;
+	unsigned int tmp, tmp2, sum;
+
+	__asm__(
+	"	ld.ab  %0, [%3, 4]		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"	sub    %1, %4, 2		\n"
+	"	lsr.f  lp_count, %1, 1		\n"
+	"	bcc    0f			\n"
+	"	add.f  %0, %0, %2		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"0:	lp     1f			\n"
+	"	ld.ab  %1, [%3, 4]		\n"
+	"	adc.f  %0, %0, %2		\n"
+	"	ld.ab  %2, [%3, 4]		\n"
+	"	adc.f  %0, %0, %1		\n"
+	"1:	adc.f  %0, %0, %2		\n"
+	"	add.cs %0,%0,1			\n"
+	: "=&r"(sum), "=r"(tmp), "=&r"(tmp2), "+&r" (ptr)
+	: "r"(ihl)
+	: "cc", "lp_count", "memory");
+
+	return csum_fold(sum);
+}
+
+/*
+ * TCP pseudo Header is 12 bytes:
+ * SA [4], DA [4], zeroes [1], Proto[1], TCP Seg(hdr+data) Len [2]
+ */
+static inline __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+		   unsigned short proto, __wsum sum)
+{
+	__asm__ __volatile__(
+	"	add.f %0, %0, %1	\n"
+	"	adc.f %0, %0, %2	\n"
+	"	adc.f %0, %0, %3	\n"
+	"	adc.f %0, %0, %4	\n"
+	"	adc   %0, %0, 0		\n"
+	: "+&r"(sum)
+	: "r"(saddr), "r"(daddr),
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	  "r"(len),
+#else
+	  "r"(len << 8),
+#endif
+	  "r"(htons(proto))
+	: "cc");
+
+	return sum;
+}
+
+#define csum_fold csum_fold
+#define ip_fast_csum ip_fast_csum
+#define csum_tcpudp_nofold csum_tcpudp_nofold
+
+#include <asm-generic/checksum.h>
+
+#endif /* _ASM_ARC_CHECKSUM_H */

arch/arc/include/asm/clk.h

+/*
+ * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_CLK_H
+#define _ASM_ARC_CLK_H
+
+/* Although we can't really hide core_freq, the accessor is still better way */
+extern unsigned long core_freq;
+
+static inline unsigned long arc_get_core_freq(void)
+{
+	return core_freq;
+}
+
+extern int arc_set_core_freq(unsigned long);
+
+#endif

arch/arc/include/asm/cmpxchg.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_CMPXCHG_H
+#define __ASM_ARC_CMPXCHG_H
+
+#include <linux/types.h>
+#include <asm/smp.h>
+
+#ifdef CONFIG_ARC_HAS_LLSC
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	"1:	llock   %0, [%1]	\n"
+	"	brne    %0, %2, 2f	\n"
+	"	scond   %3, [%1]	\n"
+	"	bnz     1b		\n"
+	"2:				\n"
+	: "=&r"(prev)
+	: "r"(ptr), "ir"(expected),
+	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
+	: "cc");
+
+	return prev;
+}
+
+#else
+
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
+{
+	unsigned long flags;
+	int prev;
+	volatile unsigned long *p = ptr;
+
+	atomic_ops_lock(flags);
+	prev = *p;
+	if (prev == expected)
+		*p = new;
+	atomic_ops_unlock(flags);
+	return prev;
+}
+
+#endif /* CONFIG_ARC_HAS_LLSC */
+
+#define cmpxchg(ptr, o, n) ((typeof(*(ptr)))__cmpxchg((ptr), \
+				(unsigned long)(o), (unsigned long)(n)))
+
+/*
+ * Since not supported natively, ARC cmpxchg() uses atomic_ops_lock (UP/SMP)
+ * just to gaurantee semantics.
+ * atomic_cmpxchg() needs to use the same locks as it's other atomic siblings
+ * which also happens to be atomic_ops_lock.
+ *
+ * Thus despite semantically being different, implementation of atomic_cmpxchg()
+ * is same as cmpxchg().
+ */
+#define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
+
+
+/*
+ * xchg (reg with memory) based on "Native atomic" EX insn
+ */
+static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
+				   int size)
+{
+	extern unsigned long __xchg_bad_pointer(void);
+
+	switch (size) {
+	case 4:
+		__asm__ __volatile__(
+		"	ex  %0, [%1]	\n"
+		: "+r"(val)
+		: "r"(ptr)
+		: "memory");
+
+		return val;
+	}
+	return __xchg_bad_pointer();
+}
+
+#define _xchg(ptr, with) ((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), \
+						 sizeof(*(ptr))))
+
+/*
+ * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need
+ * not require any locking. However there's a quirk.
+ * ARC lacks native CMPXCHG, thus emulated (see above), using external locking -
+ * incidently it "reuses" the same atomic_ops_lock used by atomic APIs.
+ * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to
+ * abide by same serializing rules, thus ends up using atomic_ops_lock as well.
+ *
+ * This however is only relevant if SMP and/or ARC lacks LLSC
+ *   if (UP or LLSC)
+ *      xchg doesn't need serialization
+ *   else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC)
+ *      xchg needs serialization
+ */
+
+#if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP)
+
+#define xchg(ptr, with)			\
+({					\
+	unsigned long flags;		\
+	typeof(*(ptr)) old_val;		\
+					\
+	atomic_ops_lock(flags);		\
+	old_val = _xchg(ptr, with);	\
+	atomic_ops_unlock(flags);	\
+	old_val;			\
+})
+
+#else
+
+#define xchg(ptr, with)  _xchg(ptr, with)
+
+#endif
+
+/*
+ * "atomic" variant of xchg()
+ * REQ: It needs to follow the same serialization rules as other atomic_xxx()
+ * Since xchg() doesn't always do that, it would seem that following defintion
+ * is incorrect. But here's the rationale:
+ *   SMP : Even xchg() takes the atomic_ops_lock, so OK.
+ *   LLSC: atomic_ops_lock are not relevent at all (even if SMP, since LLSC
+ *         is natively "SMP safe", no serialization required).
+ *   UP  : other atomics disable IRQ, so no way a difft ctxt atomic_xchg()
+ *         could clobber them. atomic_xchg() itself would be 1 insn, so it
+ *         can't be clobbered by others. Thus no serialization required when
+ *         atomic_xchg is involved.
+ */
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+#endif

arch/arc/include/asm/current.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: May 16th, 2008
+ *  - Current macro is now implemented as "global register" r25
+ */
+
+#ifndef _ASM_ARC_CURRENT_H
+#define _ASM_ARC_CURRENT_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+register struct task_struct *curr_arc asm("r25");
+#define current (curr_arc)
+
+#else
+#include <asm-generic/current.h>
+#endif /* ! CONFIG_ARC_CURR_IN_REG */
+
+#endif /* ! __ASSEMBLY__ */
+
+#endif	/* __KERNEL__ */
+
+#endif /* _ASM_ARC_CURRENT_H */

arch/arc/include/asm/defines.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_DEFINES_H__
+#define __ARC_ASM_DEFINES_H__
+
+#if defined(CONFIG_ARC_MMU_V1)
+#define CONFIG_ARC_MMU_VER 1
+#elif defined(CONFIG_ARC_MMU_V2)
+#define CONFIG_ARC_MMU_VER 2
+#elif defined(CONFIG_ARC_MMU_V3)
+#define CONFIG_ARC_MMU_VER 3
+#endif
+
+#ifdef CONFIG_ARC_HAS_LLSC
+#define __CONFIG_ARC_HAS_LLSC_VAL 1
+#else
+#define __CONFIG_ARC_HAS_LLSC_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_SWAPE
+#define __CONFIG_ARC_HAS_SWAPE_VAL 1
+#else
+#define __CONFIG_ARC_HAS_SWAPE_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_RTSC
+#define __CONFIG_ARC_HAS_RTSC_VAL 1
+#else
+#define __CONFIG_ARC_HAS_RTSC_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_MMU_SASID
+#define __CONFIG_ARC_MMU_SASID_VAL 1
+#else
+#define __CONFIG_ARC_MMU_SASID_VAL 0
+#endif
+
+#ifdef CONFIG_ARC_HAS_ICACHE
+#define __CONFIG_ARC_HAS_ICACHE	1
+#else
+#define __CONFIG_ARC_HAS_ICACHE	0
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+#define __CONFIG_ARC_HAS_DCACHE	1
+#else
+#define __CONFIG_ARC_HAS_DCACHE	0
+#endif
+
+#endif /* __ARC_ASM_DEFINES_H__ */

arch/arc/include/asm/delay.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Delay routines using pre computed loops_per_jiffy value.
+ *
+ * vineetg: Feb 2012
+ *  -Rewrote in "C" to avoid dealing with availability of H/w MPY
+ *  -Also reduced the num of MPY operations from 3 to 2
+ *
+ * Amit Bhor: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_UDELAY_H
+#define __ASM_ARC_UDELAY_H
+
+#include <asm/param.h>		/* HZ */
+
+static inline void __delay(unsigned long loops)
+{
+	__asm__ __volatile__(
+	"1:	sub.f %0, %0, 1	\n"
+	"	jpnz 1b		\n"
+	: "+r"(loops)
+	:
+	: "cc");
+}
+
+extern void __bad_udelay(void);
+
+/*
+ * Normal Math for computing loops in "N" usecs
+ *  -we have precomputed @loops_per_jiffy
+ *  -1 sec has HZ jiffies
+ * loops per "N" usecs = ((loops_per_jiffy * HZ / 1000000) * N)
+ *
+ * Approximate Division by multiplication:
+ *  -Mathematically if we multiply and divide a number by same value the
+ *   result remains unchanged:  In this case, we use 2^32
+ *  -> (loops_per_N_usec * 2^32 ) / 2^32
+ *  -> (((loops_per_jiffy * HZ / 1000000) * N) * 2^32) / 2^32
+ *  -> (loops_per_jiffy * HZ * N * 4295) / 2^32
+ *
+ *  -Divide by 2^32 is very simply right shift by 32
+ *  -We simply need to ensure that the multiply per above eqn happens in
+ *   64-bit precision (if CPU doesn't support it - gcc can emaulate it)
+ */
+
+static inline void __udelay(unsigned long usecs)
+{
+	unsigned long loops;
+
+	/* (long long) cast ensures 64 bit MPY - real or emulated
+	 * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
+	 */
+	loops = ((long long)(usecs * 4295 * HZ) *
+		 (long long)(loops_per_jiffy)) >> 32;
+
+	__delay(loops);
+}
+
+#define udelay(n) (__builtin_constant_p(n) ? ((n) > 20000 ? __bad_udelay() \
+				: __udelay(n)) : __udelay(n))
+
+#endif /* __ASM_ARC_UDELAY_H */

arch/arc/include/asm/dma.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_ARC_DMA_H
+#define ASM_ARC_DMA_H
+
+#define MAX_DMA_ADDRESS 0xC0000000
+
+#endif

arch/arc/include/asm/exec.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_EXEC_H
+#define __ASM_ARC_EXEC_H
+
+/* Align to 16b */
+#define arch_align_stack(p) ((unsigned long)(p) & ~0xf)
+
+#endif

arch/arc/include/asm/irq.h

+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARC_IRQ_H
+#define __ASM_ARC_IRQ_H
+
+#define NR_IRQS		32
+
+/* Platform Independent IRQs */
+#define TIMER0_IRQ      3
+#define TIMER1_IRQ      4
+
+#include <asm-generic/irq.h>
+
+extern void __init arc_init_IRQ(void);
+extern int __init get_hw_config_num_irq(void);
+
+void __cpuinit arc_local_timer_setup(unsigned int cpu);
+
+#endif