Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:
	drivers/net/pcmcia/pcnet_cs.c
	net/caif/caif_socket.c

CREDITS

@@ -3554,12 +3554,12 @@ E: cvance@nai.com
 D: portions of the Linux Security Module (LSM) framework and security modules
 
 N: Petr Vandrovec
-E: vandrove@vc.cvut.cz
+E: petr@vandrovec.name
 D: Small contributions to ncpfs
 D: Matrox framebuffer driver
-S: Chudenicka 8
+S: 21513 Conradia Ct
-S: 10200 Prague 10, Hostivar
+S: Cupertino, CA 95014
-S: Czech Republic
+S: USA
 
 N: Thibaut Varene
 E: T-Bone@parisc-linux.org

Documentation/DocBook/device-drivers.tmpl

@@ -46,7 +46,6 @@
 
      <sect1><title>Atomic and pointer manipulation</title>
 !Iarch/x86/include/asm/atomic.h
-!Iarch/x86/include/asm/unaligned.h
      </sect1>
 
      <sect1><title>Delaying, scheduling, and timer routines</title>

Documentation/DocBook/kernel-api.tmpl

@@ -57,7 +57,6 @@
      </para>
 
      <sect1><title>String Conversions</title>
-!Ilib/vsprintf.c
 !Elib/vsprintf.c
      </sect1>
      <sect1><title>String Manipulation</title>

Documentation/DocBook/kernel-locking.tmpl

@@ -1961,6 +1961,12 @@ machines due to caching.
    </sect1>
   </chapter>
 
+  <chapter id="apiref">
+   <title>Mutex API reference</title>
+!Iinclude/linux/mutex.h
+!Ekernel/mutex.c
+  </chapter>
+
   <chapter id="references">
    <title>Further reading</title>
 

Documentation/block/cfq-iosched.txt

@@ -0,0 +1,45 @@
+CFQ ioscheduler tunables
+========================
+
+slice_idle
+----------
+This specifies how long CFQ should idle for next request on certain cfq queues
+(for sequential workloads) and service trees (for random workloads) before
+queue is expired and CFQ selects next queue to dispatch from.
+
+By default slice_idle is a non-zero value. That means by default we idle on
+queues/service trees. This can be very helpful on highly seeky media like
+single spindle SATA/SAS disks where we can cut down on overall number of
+seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues/service tree
+level and one should see an overall improved throughput on faster storage
+devices like multiple SATA/SAS disks in hardware RAID configuration. The down
+side is that isolation provided from WRITES also goes down and notion of
+IO priority becomes weaker.
+
+So depending on storage and workload, it might be useful to set slice_idle=0.
+In general I think for SATA/SAS disks and software RAID of SATA/SAS disks
+keeping slice_idle enabled should be useful. For any configurations where
+there are multiple spindles behind single LUN (Host based hardware RAID
+controller or for storage arrays), setting slice_idle=0 might end up in better
+throughput and acceptable latencies.
+
+CFQ IOPS Mode for group scheduling
+===================================
+Basic CFQ design is to provide priority based time slices. Higher priority
+process gets bigger time slice and lower priority process gets smaller time
+slice. Measuring time becomes harder if storage is fast and supports NCQ and
+it would be better to dispatch multiple requests from multiple cfq queues in
+request queue at a time. In such scenario, it is not possible to measure time
+consumed by single queue accurately.
+
+What is possible though is to measure number of requests dispatched from a
+single queue and also allow dispatch from multiple cfq queue at the same time.
+This effectively becomes the fairness in terms of IOPS (IO operations per
+second).
+
+If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
+to IOPS mode and starts providing fairness in terms of number of requests
+dispatched. Note that this mode switching takes effect only for group
+scheduling. For non-cgroup users nothing should change.

Documentation/cgroups/blkio-controller.txt

@@ -217,6 +217,7 @@ Details of cgroup files
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation
+-----------------------------------------------
 
 If group_isolation=1, it provides stronger isolation between groups at the
 expense of throughput. By default group_isolation is 0. In general that
@@ -243,6 +244,33 @@ By default one should run with group_isolation=0. If that is not sufficient
 and one wants stronger isolation between groups, then set group_isolation=1
 but this will come at cost of reduced throughput.
 
+/sys/block/<disk>/queue/iosched/slice_idle
+------------------------------------------
+On a faster hardware CFQ can be slow, especially with sequential workload.
+This happens because CFQ idles on a single queue and single queue might not
+drive deeper request queue depths to keep the storage busy. In such scenarios
+one can try setting slice_idle=0 and that would switch CFQ to IOPS
+(IO operations per second) mode on NCQ supporting hardware.
+
+That means CFQ will not idle between cfq queues of a cfq group and hence be
+able to driver higher queue depth and achieve better throughput. That also
+means that cfq provides fairness among groups in terms of IOPS and not in
+terms of disk time.
+
+/sys/block/<disk>/queue/iosched/group_idle
+------------------------------------------
+If one disables idling on individual cfq queues and cfq service trees by
+setting slice_idle=0, group_idle kicks in. That means CFQ will still idle
+on the group in an attempt to provide fairness among groups.
+
+By default group_idle is same as slice_idle and does not do anything if
+slice_idle is enabled.
+
+One can experience an overall throughput drop if you have created multiple
+groups and put applications in that group which are not driving enough
+IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
+on individual groups and throughput should improve.
+
 What works
 ==========
 - Currently only sync IO queues are support. All the buffered writes are

Documentation/gpio.txt

@@ -109,17 +109,19 @@ use numbers 2000-2063 to identify GPIOs in a bank of I2C GPIO expanders.
 
 If you want to initialize a structure with an invalid GPIO number, use
 some negative number (perhaps "-EINVAL"); that will never be valid.  To
-test if a number could reference a GPIO, you may use this predicate:
+test if such number from such a structure could reference a GPIO, you
+may use this predicate:
 
 	int gpio_is_valid(int number);
 
 A number that's not valid will be rejected by calls which may request
 or free GPIOs (see below).  Other numbers may also be rejected; for
-example, a number might be valid but unused on a given board.
+example, a number might be valid but temporarily unused on a given board.
-
-Whether a platform supports multiple GPIO controllers is currently a
-platform-specific implementation issue.
 
+Whether a platform supports multiple GPIO controllers is a platform-specific
+implementation issue, as are whether that support can leave "holes" in the space
+of GPIO numbers, and whether new controllers can be added at runtime.  Such issues
+can affect things including whether adjacent GPIO numbers are both valid.
 
 Using GPIOs
 -----------
@@ -480,12 +482,16 @@ To support this framework, a platform's Kconfig will "select" either
 ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
-They may also want to provide a custom value for ARCH_NR_GPIOS.
 
-ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+It may also provide a custom value for ARCH_NR_GPIOS, so that it better
+reflects the number of GPIOs in actual use on that platform, without
+wasting static table space.  (It should count both built-in/SoC GPIOs and
+also ones on GPIO expanders.
+
+ARCH_REQUIRE_GPIOLIB means that the gpiolib code will always get compiled
 into the kernel on that architecture.
 
-ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpiolib code defaults to off and the user
 can enable it and build it into the kernel optionally.
 
 If neither of these options are selected, the platform does not support

Documentation/hwmon/sysfs-interface

@@ -91,12 +91,11 @@ name		The chip name.
 		I2C devices get this attribute created automatically.
 		RO
 
-update_rate	The rate at which the chip will update readings.
+update_interval	The interval at which the chip will update readings.
 		Unit: millisecond
 		RW
-		Some devices have a variable update rate. This attribute
+		Some devices have a variable update rate or interval.
-		can be used to change the update rate to the desired
+		This attribute can be used to change it to the desired value.
-		frequency.
 
 
 ************

Documentation/kernel-doc-nano-HOWTO.txt

@@ -345,5 +345,10 @@ documentation, in <filename>, for the functions listed.
 section titled <section title> from <filename>.
 Spaces are allowed in <section title>; do not quote the <section title>.
 
+!C<filename> is replaced by nothing, but makes the tools check that
+all DOC: sections and documented functions, symbols, etc. are used.
+This makes sense to use when you use !F/!P only and want to verify
+that all documentation is included.
+
 Tim.
 */ <twaugh@redhat.com>

Documentation/mutex-design.txt

@@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler
 mutex semantics are sufficient for your code, then there are a couple
 of advantages of mutexes:
 
- - 'struct mutex' is smaller on most architectures: .e.g on x86,
+ - 'struct mutex' is smaller on most architectures: E.g. on x86,
    'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
    A smaller structure size means less RAM footprint, and better
    CPU-cache utilization.
@@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined:
  void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
  int  mutex_lock_interruptible_nested(struct mutex *lock,
                                       unsigned int subclass);
+ int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);

Documentation/networking/e1000.txt

@@ -1,82 +1,35 @@
 Linux* Base Driver for the Intel(R) PRO/1000 Family of Adapters
 ===============================================================
 
-September 26, 2006
+Intel Gigabit Linux driver.
-
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
-- Building and Installation
 - Command Line Parameters
 - Speed and Duplex Configuration
 - Additional Configurations
-- Known Issues
 - Support
 
-
-In This Release
-===============
-
-This file describes the Linux* Base Driver for the Intel(R) PRO/1000 Family
-of Adapters.  This driver includes support for Itanium(R)2-based systems.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel PRO/1000 adapter. All hardware requirements listed
-apply to use with Linux.
-
-The following features are now available in supported kernels:
- - Native VLANs
- - Channel Bonding (teaming)
- - SNMP
-
-Channel Bonding documentation can be found in the Linux kernel source:
-/Documentation/networking/bonding.txt
-
-The driver information previously displayed in the /proc filesystem is not
-supported in this release.  Alternatively, you can use ethtool (version 1.6
-or later), lspci, and ifconfig to obtain the same information.
-
-Instructions on updating ethtool can be found in the section "Additional
-Configurations" later in this document.
-
-NOTE: The Intel(R) 82562v 10/100 Network Connection only provides 10/100
-support.
-
-
 Identifying Your Adapter
 ========================
 
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/adapter/pro100/21397.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 For the latest Intel network drivers for Linux, refer to the following
 website.  In the search field, enter your adapter name or type, or use the
 networking link on the left to search for your adapter:
 
-    http://downloadfinder.intel.com/scripts-df/support_intel.asp
+    http://support.intel.com/support/go/network/adapter/home.htm
-
 
 Command Line Parameters
 =======================
 
-If the driver is built as a module, the  following optional parameters
-are used by entering them on the command line with the modprobe command
-using this syntax:
-
-     modprobe e1000 [<option>=<VAL1>,<VAL2>,...]
-
-For example, with two PRO/1000 PCI adapters, entering:
-
-     modprobe e1000 TxDescriptors=80,128
-
-loads the e1000 driver with 80 TX descriptors for the first adapter and
-128 TX descriptors for the second adapter.
-
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
@@ -89,10 +42,6 @@ NOTES:  For more information about the AutoNeg, Duplex, and Speed
         parameters, see the application note at:
         http://www.intel.com/design/network/applnots/ap450.htm
 
-        A descriptor describes a data buffer and attributes related to
-        the data buffer.  This information is accessed by the hardware.
-
-
 AutoNeg
 -------
 (Supported only on adapters with copper connections)
@@ -106,7 +55,6 @@ Duplex parameters must not be specified.
 NOTE:  Refer to the Speed and Duplex section of this readme for more
        information on the AutoNeg parameter.
 
-
 Duplex
 ------
 (Supported only on adapters with copper connections)
@@ -119,7 +67,6 @@ set to auto-negotiate, the board auto-detects the correct duplex.  If the
 link partner is forced (either full or half), Duplex defaults to half-
 duplex.
 
-
 FlowControl
 -----------
 Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
@@ -128,16 +75,16 @@ Default Value: Reads flow control settings from the EEPROM
 This parameter controls the automatic generation(Tx) and response(Rx)
 to Ethernet PAUSE frames.
 
-
 InterruptThrottleRate
 ---------------------
 (not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range:   0,1,3,100-100000 (0=off, 1=dynamic, 3=dynamic conservative)
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
 Default Value: 3
 
 The driver can limit the amount of interrupts per second that the adapter
-will generate for incoming packets. It does this by writing a value to the 
+will generate for incoming packets. It does this by writing a value to the
-adapter that is based on the maximum amount of interrupts that the adapter 
+adapter that is based on the maximum amount of interrupts that the adapter
 will generate per second.
 
 Setting InterruptThrottleRate to a value greater or equal to 100
@@ -146,37 +93,43 @@ per second, even if more packets have come in. This reduces interrupt
 load on the system and can lower CPU utilization under heavy load,
 but will increase latency as packets are not processed as quickly.
 
-The default behaviour of the driver previously assumed a static 
+The default behaviour of the driver previously assumed a static
-InterruptThrottleRate value of 8000, providing a good fallback value for 
+InterruptThrottleRate value of 8000, providing a good fallback value for
-all traffic types,but lacking in small packet performance and latency. 
+all traffic types,but lacking in small packet performance and latency.
-The hardware can handle many more small packets per second however, and 
+The hardware can handle many more small packets per second however, and
 for this reason an adaptive interrupt moderation algorithm was implemented.
 
 Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which
-it dynamically adjusts the InterruptThrottleRate value based on the traffic 
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
 that it receives. After determining the type of incoming traffic in the last
-timeframe, it will adjust the InterruptThrottleRate to an appropriate value 
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
 for that traffic.
 
 The algorithm classifies the incoming traffic every interval into
-classes.  Once the class is determined, the InterruptThrottleRate value is 
+classes.  Once the class is determined, the InterruptThrottleRate value is
-adjusted to suit that traffic type the best. There are three classes defined: 
+adjusted to suit that traffic type the best. There are three classes defined:
 "Bulk traffic", for large amounts of packets of normal size; "Low latency",
 for small amounts of traffic and/or a significant percentage of small
-packets; and "Lowest latency", for almost completely small packets or 
+packets; and "Lowest latency", for almost completely small packets or
 minimal traffic.
 
-In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
-for traffic that falls in class "Bulk traffic". If traffic falls in the "Low 
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
-latency" or "Lowest latency" class, the InterruptThrottleRate is increased 
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
 stepwise to 20000. This default mode is suitable for most applications.
 
 For situations where low latency is vital such as cluster or
 grid computing, the algorithm can reduce latency even more when
 InterruptThrottleRate is set to mode 1. In this mode, which operates
-the same as mode 3, the InterruptThrottleRate will be increased stepwise to 
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
 70000 for traffic in class "Lowest latency".
 
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal, the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
 Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 and may improve small packet latency, but is generally not suitable
 for bulk throughput traffic.
@@ -212,8 +165,6 @@ NOTE:  When e1000 is loaded with default settings and multiple adapters
        be platform-specific.  If CPU utilization is not a concern, use
        RX_POLLING (NAPI) and default driver settings.
 
-
-
 RxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -225,15 +176,14 @@ by the driver.  Increasing this value allows the driver to buffer more
 incoming packets, at the expense of increased system memory utilization.
 
 Each descriptor is 16 bytes.  A receive buffer is also allocated for each
-descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending 
+descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
 on the MTU setting. The maximum MTU size is 16110.
 
-NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo 
+NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo
-       Frames.  Depending on the available system resources, the request 
+       Frames.  Depending on the available system resources, the request
-       for a higher number of receive descriptors may be denied.  In this 
+       for a higher number of receive descriptors may be denied.  In this
        case, use a lower number.
 
-
 RxIntDelay
 ----------
 Valid Range:   0-65535 (0=off)
@@ -254,7 +204,6 @@ CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
           restoring the network connection.  To eliminate the potential
           for the hang ensure that RxIntDelay is set to 0.
 
-
 RxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -268,7 +217,6 @@ packet is received within the set amount of time.  Proper tuning,
 along with RxIntDelay, may improve traffic throughput in specific network
 conditions.
 
-
 Speed
 -----
 (This parameter is supported only on adapters with copper connections.)
@@ -280,7 +228,6 @@ Speed forces the line speed to the specified value in megabits per second
 partner is set to auto-negotiate, the board will auto-detect the correct
 speed.  Duplex should also be set when Speed is set to either 10 or 100.
 
-
 TxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -295,6 +242,36 @@ NOTE:  Depending on the available system resources, the request for a
        higher number of transmit descriptors may be denied.  In this case,
        use a lower number.
 
+TxDescriptorStep
+----------------
+Valid Range:    1 (use every Tx Descriptor)
+		4 (use every 4th Tx Descriptor)
+
+Default Value:  1 (use every Tx Descriptor)
+
+On certain non-Intel architectures, it has been observed that intense TX
+traffic bursts of short packets may result in an improper descriptor
+writeback. If this occurs, the driver will report a "TX Timeout" and reset
+the adapter, after which the transmit flow will restart, though data may
+have stalled for as much as 10 seconds before it resumes.
+
+The improper writeback does not occur on the first descriptor in a system
+memory cache-line, which is typically 32 bytes, or 4 descriptors long.
+
+Setting TxDescriptorStep to a value of 4 will ensure that all TX descriptors
+are aligned to the start of a system memory cache line, and so this problem
+will not occur.
+
+NOTES: Setting TxDescriptorStep to 4 effectively reduces the number of
+       TxDescriptors available for transmits to 1/4 of the normal allocation.
+       This has a possible negative performance impact, which may be
+       compensated for by allocating more descriptors using the TxDescriptors
+       module parameter.
+
+       There are other conditions which may result in "TX Timeout", which will
+       not be resolved by the use of the TxDescriptorStep parameter. As the
+       issue addressed by this parameter has never been observed on Intel
+       Architecture platforms, it should not be used on Intel platforms.
 
 TxIntDelay
 ----------
@@ -307,7 +284,6 @@ efficiency if properly tuned for specific network traffic.  If the
 system is reporting dropped transmits, this value may be set too high
 causing the driver to run out of available transmit descriptors.
 
-
 TxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -330,6 +306,35 @@ Default Value: 1
 A value of '1' indicates that the driver should enable IP checksum
 offload for received packets (both UDP and TCP) to the adapter hardware.
 
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+Usage: insmod e1000.ko copybreak=128
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can turn off
+this parameter in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
 
 Speed and Duplex Configuration
 ==============================
@@ -385,40 +390,9 @@ If the link partner is forced to a specific speed and duplex, then this
 parameter should not be used.  Instead, use the Speed and Duplex parameters
 previously mentioned to force the adapter to the same speed and duplex.
 
-
 Additional Configurations
 =========================
 
-  Configuring the Driver on Different Distributions
-  -------------------------------------------------
-  Configuring a network driver to load properly when the system is started
-  is distribution dependent.  Typically, the configuration process involves
-  adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well
-  as editing other system startup scripts and/or configuration files.  Many
-  popular Linux distributions ship with tools to make these changes for you.
-  To learn the proper way to configure a network device for your system,
-  refer to your distribution documentation.  If during this process you are
-  asked for the driver or module name, the name for the Linux Base Driver
-  for the Intel(R) PRO/1000 Family of Adapters is e1000.
-
-  As an example, if you install the e1000 driver for two PRO/1000 adapters
-  (eth0 and eth1) and set the speed and duplex to 10full and 100half, add
-  the following to modules.conf or or modprobe.conf:
-
-       alias eth0 e1000
-       alias eth1 e1000
-       options e1000 Speed=10,100 Duplex=2,1
-
-  Viewing Link Messages
-  ---------------------
-  Link messages will not be displayed to the console if the distribution is
-  restricting system messages.  In order to see network driver link messages
-  on your console, set dmesg to eight by entering the following:
-
-       dmesg -n 8
-
-  NOTE: This setting is not saved across reboots.
-
   Jumbo Frames
   ------------
   Jumbo Frames support is enabled by changing the MTU to a value larger than
@@ -437,9 +411,11 @@ Additional Configurations
    setting in a different location.
 
   Notes:
-
+  Degradation in throughput performance may be observed in some Jumbo frames
-  - To enable Jumbo Frames, increase the MTU size on the interface beyond
+  environments. If this is observed, increasing the application's socket buffer
-    1500.
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
 
   - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
     with the maximum Jumbo Frames size of 16128.
@@ -447,40 +423,11 @@ Additional Configurations
   - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
     loss of link.
 
-  - Some Intel gigabit adapters that support Jumbo Frames have a frame size
-    limit of 9238 bytes, with a corresponding MTU size limit of 9216 bytes.
-    The adapters with this limitation are based on the Intel(R) 82571EB,
-    82572EI, 82573L and 80003ES2LAN controller.  These correspond to the
-    following product names:
-     Intel(R) PRO/1000 PT Server Adapter
-     Intel(R) PRO/1000 PT Desktop Adapter
-     Intel(R) PRO/1000 PT Network Connection
-     Intel(R) PRO/1000 PT Dual Port Server Adapter
-     Intel(R) PRO/1000 PT Dual Port Network Connection
-     Intel(R) PRO/1000 PF Server Adapter
-     Intel(R) PRO/1000 PF Network Connection
-     Intel(R) PRO/1000 PF Dual Port Server Adapter
-     Intel(R) PRO/1000 PB Server Connection
-     Intel(R) PRO/1000 PL Network Connection
-     Intel(R) PRO/1000 EB Network Connection with I/O Acceleration
-     Intel(R) PRO/1000 EB Backplane Connection with I/O Acceleration
-     Intel(R) PRO/1000 PT Quad Port Server Adapter
-
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
     support Jumbo Frames. These correspond to the following product names:
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  - The following adapters do not support Jumbo Frames:
-     Intel(R) 82562V 10/100 Network Connection
-     Intel(R) 82566DM Gigabit Network Connection
-     Intel(R) 82566DC Gigabit Network Connection
-     Intel(R) 82566MM Gigabit Network Connection
-     Intel(R) 82566MC Gigabit Network Connection
-     Intel(R) 82562GT 10/100 Network Connection
-     Intel(R) 82562G 10/100 Network Connection
-
-
   Ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
@@ -490,142 +437,14 @@ Additional Configurations
   The latest release of ethtool can be found from
   http://sourceforge.net/projects/gkernel.
 
-  NOTE: Ethtool 1.6 only supports a limited set of ethtool options.  Support
-  for a more complete ethtool feature set can be enabled by upgrading
-  ethtool to ethtool-1.8.1.
-
   Enabling Wake on LAN* (WoL)
   ---------------------------
-  WoL is configured through the Ethtool* utility.  Ethtool is included with
+  WoL is configured through the Ethtool* utility.
-  all versions of Red Hat after Red Hat 7.2.  For other Linux distributions,
-  download and install Ethtool from the following website:
-  http://sourceforge.net/projects/gkernel.
-
-  For instructions on enabling WoL with Ethtool, refer to the website listed
-  above.
 
   WoL will be enabled on the system during the next shut down or reboot.
   For this driver version, in order to enable WoL, the e1000 driver must be
   loaded when shutting down or rebooting the system.
 
-  Wake On LAN is only supported on port A for the following devices:
-  Intel(R) PRO/1000 PT Dual Port Network Connection
-  Intel(R) PRO/1000 PT Dual Port Server Connection
-  Intel(R) PRO/1000 PT Dual Port Server Adapter
-  Intel(R) PRO/1000 PF Dual Port Server Adapter
-  Intel(R) PRO/1000 PT Quad Port Server Adapter
-
-  NAPI
-  ----
-  NAPI (Rx polling mode) is enabled in the e1000 driver.
-
-  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
-
-
-Known Issues
-============
-
-Dropped Receive Packets on Half-duplex 10/100 Networks
-------------------------------------------------------
-If you have an Intel PCI Express adapter running at 10mbps or 100mbps, half-
-duplex, you may observe occasional dropped receive packets.  There are no
-workarounds for this problem in this network configuration.  The network must
-be updated to operate in full-duplex, and/or 1000mbps only.
-
-Jumbo Frames System Requirement
--------------------------------
-Memory allocation failures have been observed on Linux systems with 64 MB
-of RAM or less that are running Jumbo Frames.  If you are using Jumbo
-Frames, your system may require more than the advertised minimum
-requirement of 64 MB of system memory.
-
-Performance Degradation with Jumbo Frames
------------------------------------------
-Degradation in throughput performance may be observed in some Jumbo frames
-environments.  If this is observed, increasing the application's socket
-buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values
-may help.  See the specific application manual and
-/usr/src/linux*/Documentation/
-networking/ip-sysctl.txt for more details.
-
-Jumbo Frames on Foundry BigIron 8000 switch
--------------------------------------------
-There is a known issue using Jumbo frames when connected to a Foundry
-BigIron 8000 switch.  This is a 3rd party limitation.  If you experience
-loss of packets, lower the MTU size.
-
-Allocating Rx Buffers when Using Jumbo Frames 
----------------------------------------------
-Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if 
-the available memory is heavily fragmented. This issue may be seen with PCI-X 
-adapters or with packet split disabled. This can be reduced or eliminated 
-by changing the amount of available memory for receive buffer allocation, by
-increasing /proc/sys/vm/min_free_kbytes. 
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-Due to the default ARP behavior on Linux, it is not possible to have
-one system on two IP networks in the same Ethernet broadcast domain
-(non-partitioned switch) behave as expected.  All Ethernet interfaces
-will respond to IP traffic for any IP address assigned to the system.
-This results in unbalanced receive traffic.
-
-If you have multiple interfaces in a server, either turn on ARP
-filtering by entering:
-
-    echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-(this only works if your kernel's version is higher than 2.4.5),
-
-NOTE: This setting is not saved across reboots.  The configuration
-change can be made permanent by adding the line:
-    net.ipv4.conf.all.arp_filter = 1
-to the file /etc/sysctl.conf
-
-      or,
-
-install the interfaces in separate broadcast domains (either in
-different switches or in a switch partitioned to VLANs).
-
-82541/82547 can't link or are slow to link with some link partners
------------------------------------------------------------------
-There is a known compatibility issue with 82541/82547 and some
-low-end switches where the link will not be established, or will
-be slow to establish.  In particular, these switches are known to
-be incompatible with 82541/82547:
-
-    Planex FXG-08TE
-    I-O Data ETG-SH8
-
-To workaround this issue, the driver can be compiled with an override
-of the PHY's master/slave setting.  Forcing master or forcing slave
-mode will improve time-to-link.
-
-    # make CFLAGS_EXTRA=-DE1000_MASTER_SLAVE=<n>
-
-Where <n> is:
-
-    0 = Hardware default
-    1 = Master mode
-    2 = Slave mode
-    3 = Auto master/slave
-
-Disable rx flow control with ethtool
-------------------------------------
-In order to disable receive flow control using ethtool, you must turn
-off auto-negotiation on the same command line.
-
-For example:
-
-   ethtool -A eth? autoneg off rx off
-
-Unplugging network cable while ethtool -p is running
-----------------------------------------------------
-In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging
-the network cable while ethtool -p is running will cause the system to
-become unresponsive to keyboard commands, except for control-alt-delete.
-Restarting the system appears to be the only remedy.
-
-
 Support
 =======
 

Documentation/networking/e1000e.txt

@@ -0,0 +1,302 @@
+Linux* Driver for Intel(R) Network Connection
+===============================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Support
+
+Identifying Your Adapter
+========================
+
+The e1000e driver supports all PCI Express Intel(R) Gigabit Network
+Connections, except those that are 82575, 82576 and 82580-based*.
+
+* NOTE: The Intel(R) PRO/1000 P Dual Port Server Adapter is supported by
+  the e1000 driver, not the e1000e driver due to the 82546 part being used
+  behind a PCI Express bridge.
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/go/network/adapter/idguide.htm
+
+For the latest Intel network drivers for Linux, refer to the following
+website.  In the search field, enter your adapter name or type, or use the
+networking link on the left to search for your adapter:
+
+    http://support.intel.com/support/go/network/adapter/home.htm
+
+Command Line Parameters
+=======================
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+NOTES:  For more information about the InterruptThrottleRate,
+        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
+        parameters, see the application note at:
+        http://www.intel.com/design/network/applnots/ap450.htm
+
+InterruptThrottleRate
+---------------------
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
+Default Value: 3
+
+The driver can limit the amount of interrupts per second that the adapter
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
+will generate per second.
+
+Setting InterruptThrottleRate to a value greater or equal to 100
+will program the adapter to send out a maximum of that many interrupts
+per second, even if more packets have come in. This reduces interrupt
+load on the system and can lower CPU utilization under heavy load,
+but will increase latency as packets are not processed as quickly.
+
+The driver has two adaptive modes (setting 1 or 3) in which
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
+that it receives. After determining the type of incoming traffic in the last
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
+for that traffic.
+
+The algorithm classifies the incoming traffic every interval into
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
+"Bulk traffic", for large amounts of packets of normal size; "Low latency",
+for small amounts of traffic and/or a significant percentage of small
+packets; and "Lowest latency", for almost completely small packets or
+minimal traffic.
+
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
+stepwise to 20000. This default mode is suitable for most applications.
+
+For situations where low latency is vital such as cluster or
+grid computing, the algorithm can reduce latency even more when
+InterruptThrottleRate is set to mode 1. In this mode, which operates
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
+70000 for traffic in class "Lowest latency".
+
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
+Setting InterruptThrottleRate to 0 turns off any interrupt moderation
+and may improve small packet latency, but is generally not suitable
+for bulk throughput traffic.
+
+NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+       RxAbsIntDelay parameters.  In other words, minimizing the receive
+       and/or transmit absolute delays does not force the controller to
+       generate more interrupts than what the Interrupt Throttle Rate
+       allows.
+
+NOTE:  When e1000e is loaded with default settings and multiple adapters
+       are in use simultaneously, the CPU utilization may increase non-
+       linearly.  In order to limit the CPU utilization without impacting
+       the overall throughput, we recommend that you load the driver as
+       follows:
+
+           modprobe e1000e InterruptThrottleRate=3000,3000,3000
+
+       This sets the InterruptThrottleRate to 3000 interrupts/sec for
+       the first, second, and third instances of the driver.  The range
+       of 2000 to 3000 interrupts per second works on a majority of
+       systems and is a good starting point, but the optimal value will
+       be platform-specific.  If CPU utilization is not a concern, use
+       RX_POLLING (NAPI) and default driver settings.
+
+RxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 0
+
+This value delays the generation of receive interrupts in units of 1.024
+microseconds.  Receive interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic.  Increasing this value adds
+extra latency to frame reception and can end up decreasing the throughput
+of TCP traffic.  If the system is reporting dropped receives, this value
+may be set too high, causing the driver to run out of available receive
+descriptors.
+
+CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
+          hang (stop transmitting) under certain network conditions.  If
+          this occurs a NETDEV WATCHDOG message is logged in the system
+          event log.  In addition, the controller is automatically reset,
+          restoring the network connection.  To eliminate the potential
+          for the hang ensure that RxIntDelay is set to 0.
+
+RxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is received within the set amount of time.  Proper tuning,
+along with RxIntDelay, may improve traffic throughput in specific network
+conditions.
+
+TxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value delays the generation of transmit interrupts in units of
+1.024 microseconds.  Transmit interrupt reduction can improve CPU
+efficiency if properly tuned for specific network traffic.  If the
+system is reporting dropped transmits, this value may be set too high
+causing the driver to run out of available transmit descriptors.
+
+TxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 32
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is sent on the wire within the set amount of time.  Proper tuning,
+along with TxIntDelay, may improve traffic throughput in specific
+network conditions.
+
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000e/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can set this parameter
+in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
+
+IntMode
+-------
+Valid Range: 0-2 (0=legacy, 1=MSI, 2=MSI-X)
+Default Value: 2
+
+Allows changing the interrupt mode at module load time, without requiring a
+recompile. If the driver load fails to enable a specific interrupt mode, the
+driver will try other interrupt modes, from least to most compatible.  The
+interrupt order is MSI-X, MSI, Legacy.  If specifying MSI (IntMode=1)
+interrupts, only MSI and Legacy will be attempted.
+
+CrcStripping
+------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Strip the CRC from received packets before sending up the network stack.  If
+you have a machine with a BMC enabled but cannot receive IPMI traffic after
+loading or enabling the driver, try disabling this feature.
+
+WriteProtectNVM
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Set the hardware to ignore all write/erase cycles to the GbE region in the
+ICHx NVM (non-volatile memory).  This feature can be disabled by the
+WriteProtectNVM module parameter (enabled by default) only after a hardware
+reset, but the machine must be power cycled before trying to enable writes.
+
+Note: the kernel boot option iomem=relaxed may need to be set if the kernel
+config option CONFIG_STRICT_DEVMEM=y, if the root user wants to write the
+NVM from user space via ethtool.
+
+Additional Configurations
+=========================
+
+  Jumbo Frames
+  ------------
+  Jumbo Frames support is enabled by changing the MTU to a value larger than
+  the default of 1500.  Use the ifconfig command to increase the MTU size.
+  For example:
+
+       ifconfig eth<x> mtu 9000 up
+
+  This setting is not saved across reboots.
+
+  Notes:
+
+  - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
+    with the maximum Jumbo Frames size of 9234 bytes.
+
+  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
+
+  - Some adapters limit Jumbo Frames sized packets to a maximum of
+    4096 bytes and some adapters do not support Jumbo Frames.
+
+
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  We
+  strongly recommend downloading the latest version of Ethtool at:
+
+  http://sourceforge.net/projects/gkernel.
+
+  Speed and Duplex
+  ----------------
+  Speed and Duplex are configured through the Ethtool* utility. For
+  instructions,  refer to the Ethtool man page.
+
+  Enabling Wake on LAN* (WoL)
+  ---------------------------
+  WoL is configured through the Ethtool* utility. For instructions on
+  enabling WoL with Ethtool, refer to the Ethtool man page.
+
+  WoL will be enabled on the system during the next shut down or reboot.
+  For this driver version, in order to enable WoL, the e1000e driver must be
+  loaded when shutting down or rebooting the system.
+
+  In most cases Wake On LAN is only supported on port A for multiple port
+  adapters. To verify if a port supports Wake on LAN run ethtool eth<X>.
+
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net

Documentation/networking/ixgbevf.txt

@@ -1,19 +1,16 @@
 Linux* Base Driver for Intel(R) Network Connection
 ==================================================
 
-November 24, 2009
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
 - Known Issues/Troubleshooting
 - Support
 
-In This Release
-===============
-
 This file describes the ixgbevf Linux* Base Driver for Intel Network
 Connection.
 
@@ -33,7 +30,7 @@ Identifying Your Adapter
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/sb/CS-008441.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 Known Issues/Troubleshooting
 ============================
@@ -57,34 +54,3 @@ or the Intel Wired Networking project hosted by Sourceforge at:
 If an issue is identified with the released source code on the supported
 kernel with a supported adapter, email the specific information related
 to the issue to e1000-devel@lists.sf.net
-
-License
-=======
-
-Intel 10 Gigabit Linux driver.
-Copyright(c) 1999 - 2009 Intel Corporation.
-
-This program is free software; you can redistribute it and/or modify it
-under the terms and conditions of the GNU General Public License,
-version 2, as published by the Free Software Foundation.
-
-This program is distributed in the hope it will be useful, but WITHOUT
-ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-more details.
-
-You should have received a copy of the GNU General Public License along with
-this program; if not, write to the Free Software Foundation, Inc.,
-51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
-The full GNU General Public License is included in this distribution in
-the file called "COPYING".
-
-Trademarks
-==========
-
-Intel, Itanium, and Pentium are trademarks or registered trademarks of
-Intel Corporation or its subsidiaries in the United States and other
-countries.
-
-* Other names and brands may be claimed as the property of others.

Documentation/power/regulator/overview.txt

@@ -13,7 +13,7 @@ regulators (where voltage output is controllable) and current sinks (where
 current limit is controllable).
 
 (C) 2008  Wolfson Microelectronics PLC.
-Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Author: Liam Girdwood <lrg@slimlogic.co.uk>
 
 
 Nomenclature

Documentation/sound/alsa/HD-Audio-Models.txt

@@ -296,6 +296,7 @@ Conexant 5051
 Conexant 5066
 =============
   laptop	Basic Laptop config (default)
+  hp-laptop	HP laptops, e g G60
   dell-laptop	Dell laptops
   dell-vostro	Dell Vostro
   olpc-xo-1_5	OLPC XO 1.5

Documentation/workqueue.txt

@@ -0,0 +1,380 @@
+
+Concurrency Managed Workqueue (cmwq)
+
+September, 2010		Tejun Heo <tj@kernel.org>
+			Florian Mickler <florian@mickler.org>
+
+CONTENTS
+
+1. Introduction
+2. Why cmwq?
+3. The Design
+4. Application Programming Interface (API)
+5. Example Execution Scenarios
+6. Guidelines
+
+
+1. Introduction
+
+There are many cases where an asynchronous process execution context
+is needed and the workqueue (wq) API is the most commonly used
+mechanism for such cases.
+
+When such an asynchronous execution context is needed, a work item
+describing which function to execute is put on a queue.  An
+independent thread serves as the asynchronous execution context.  The
+queue is called workqueue and the thread is called worker.
+
+While there are work items on the workqueue the worker executes the
+functions associated with the work items one after the other.  When
+there is no work item left on the workqueue the worker becomes idle.
+When a new work item gets queued, the worker begins executing again.
+
+
+2. Why cmwq?
+
+In the original wq implementation, a multi threaded (MT) wq had one
+worker thread per CPU and a single threaded (ST) wq had one worker
+thread system-wide.  A single MT wq needed to keep around the same
+number of workers as the number of CPUs.  The kernel grew a lot of MT
+wq users over the years and with the number of CPU cores continuously
+rising, some systems saturated the default 32k PID space just booting
+up.
+
+Although MT wq wasted a lot of resource, the level of concurrency
+provided was unsatisfactory.  The limitation was common to both ST and
+MT wq albeit less severe on MT.  Each wq maintained its own separate
+worker pool.  A MT wq could provide only one execution context per CPU
+while a ST wq one for the whole system.  Work items had to compete for
+those very limited execution contexts leading to various problems
+including proneness to deadlocks around the single execution context.
+
+The tension between the provided level of concurrency and resource
+usage also forced its users to make unnecessary tradeoffs like libata
+choosing to use ST wq for polling PIOs and accepting an unnecessary
+limitation that no two polling PIOs can progress at the same time.  As
+MT wq don't provide much better concurrency, users which require
+higher level of concurrency, like async or fscache, had to implement
+their own thread pool.
+
+Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with
+focus on the following goals.
+
+* Maintain compatibility with the original workqueue API.
+
+* Use per-CPU unified worker pools shared by all wq to provide
+  flexible level of concurrency on demand without wasting a lot of
+  resource.
+
+* Automatically regulate worker pool and level of concurrency so that
+  the API users don't need to worry about such details.
+
+
+3. The Design
+
+In order to ease the asynchronous execution of functions a new
+abstraction, the work item, is introduced.
+
+A work item is a simple struct that holds a pointer to the function
+that is to be executed asynchronously.  Whenever a driver or subsystem
+wants a function to be executed asynchronously it has to set up a work
+item pointing to that function and queue that work item on a
+workqueue.
+
+Special purpose threads, called worker threads, execute the functions
+off of the queue, one after the other.  If no work is queued, the
+worker threads become idle.  These worker threads are managed in so
+called thread-pools.
+
+The cmwq design differentiates between the user-facing workqueues that
+subsystems and drivers queue work items on and the backend mechanism
+which manages thread-pool and processes the queued work items.
+
+The backend is called gcwq.  There is one gcwq for each possible CPU
+and one gcwq to serve work items queued on unbound workqueues.
+
+Subsystems and drivers can create and queue work items through special
+workqueue API functions as they see fit. They can influence some
+aspects of the way the work items are executed by setting flags on the
+workqueue they are putting the work item on. These flags include
+things like CPU locality, reentrancy, concurrency limits and more. To
+get a detailed overview refer to the API description of
+alloc_workqueue() below.
+
+When a work item is queued to a workqueue, the target gcwq is
+determined according to the queue parameters and workqueue attributes
+and appended on the shared worklist of the gcwq.  For example, unless
+specifically overridden, a work item of a bound workqueue will be
+queued on the worklist of exactly that gcwq that is associated to the
+CPU the issuer is running on.
+
+For any worker pool implementation, managing the concurrency level
+(how many execution contexts are active) is an important issue.  cmwq
+tries to keep the concurrency at a minimal but sufficient level.
+Minimal to save resources and sufficient in that the system is used at
+its full capacity.
+
+Each gcwq bound to an actual CPU implements concurrency management by
+hooking into the scheduler.  The gcwq is notified whenever an active
+worker wakes up or sleeps and keeps track of the number of the
+currently runnable workers.  Generally, work items are not expected to
+hog a CPU and consume many cycles.  That means maintaining just enough
+concurrency to prevent work processing from stalling should be
+optimal.  As long as there are one or more runnable workers on the
+CPU, the gcwq doesn't start execution of a new work, but, when the
+last running worker goes to sleep, it immediately schedules a new
+worker so that the CPU doesn't sit idle while there are pending work
+items.  This allows using a minimal number of workers without losing
+execution bandwidth.
+
+Keeping idle workers around doesn't cost other than the memory space
+for kthreads, so cmwq holds onto idle ones for a while before killing
+them.
+
+For an unbound wq, the above concurrency management doesn't apply and
+the gcwq for the pseudo unbound CPU tries to start executing all work
+items as soon as possible.  The responsibility of regulating
+concurrency level is on the users.  There is also a flag to mark a
+bound wq to ignore the concurrency management.  Please refer to the
+API section for details.
+
+Forward progress guarantee relies on that workers can be created when
+more execution contexts are necessary, which in turn is guaranteed
+through the use of rescue workers.  All work items which might be used
+on code paths that handle memory reclaim are required to be queued on
+wq's that have a rescue-worker reserved for execution under memory
+pressure.  Else it is possible that the thread-pool deadlocks waiting
+for execution contexts to free up.
+
+
+4. Application Programming Interface (API)
+
+alloc_workqueue() allocates a wq.  The original create_*workqueue()
+functions are deprecated and scheduled for removal.  alloc_workqueue()
+takes three arguments - @name, @flags and @max_active.  @name is the
+name of the wq and also used as the name of the rescuer thread if
+there is one.
+
+A wq no longer manages execution resources but serves as a domain for
+forward progress guarantee, flush and work item attributes.  @flags
+and @max_active control how work items are assigned execution
+resources, scheduled and executed.
+
+@flags:
+
+  WQ_NON_REENTRANT
+
+	By default, a wq guarantees non-reentrance only on the same
+	CPU.  A work item may not be executed concurrently on the same
+	CPU by multiple workers but is allowed to be executed
+	concurrently on multiple CPUs.  This flag makes sure
+	non-reentrance is enforced across all CPUs.  Work items queued
+	to a non-reentrant wq are guaranteed to be executed by at most
+	one worker system-wide at any given time.
+
+  WQ_UNBOUND
+
+	Work items queued to an unbound wq are served by a special
+	gcwq which hosts workers which are not bound to any specific
+	CPU.  This makes the wq behave as a simple execution context
+	provider without concurrency management.  The unbound gcwq
+	tries to start execution of work items as soon as possible.
+	Unbound wq sacrifices locality but is useful for the following
+	cases.
+
+	* Wide fluctuation in the concurrency level requirement is
+	  expected and using bound wq may end up creating large number
+	  of mostly unused workers across different CPUs as the issuer
+	  hops through different CPUs.
+
+	* Long running CPU intensive workloads which can be better
+	  managed by the system scheduler.
+
+  WQ_FREEZEABLE
+
+	A freezeable wq participates in the freeze phase of the system
+	suspend operations.  Work items on the wq are drained and no
+	new work item starts execution until thawed.
+
+  WQ_RESCUER
+
+	All wq which might be used in the memory reclaim paths _MUST_
+	have this flag set.  This reserves one worker exclusively for
+	the execution of this wq under memory pressure.
+
+  WQ_HIGHPRI
+
+	Work items of a highpri wq are queued at the head of the
+	worklist of the target gcwq and start execution regardless of
+	the current concurrency level.  In other words, highpri work
+	items will always start execution as soon as execution
+	resource is available.
+
+	Ordering among highpri work items is preserved - a highpri
+	work item queued after another highpri work item will start
+	execution after the earlier highpri work item starts.
+
+	Although highpri work items are not held back by other
+	runnable work items, they still contribute to the concurrency
+	level.  Highpri work items in runnable state will prevent
+	non-highpri work items from starting execution.
+
+	This flag is meaningless for unbound wq.
+
+  WQ_CPU_INTENSIVE
+
+	Work items of a CPU intensive wq do not contribute to the
+	concurrency level.  In other words, runnable CPU intensive
+	work items will not prevent other work items from starting
+	execution.  This is useful for bound work items which are
+	expected to hog CPU cycles so that their execution is
+	regulated by the system scheduler.
+
+	Although CPU intensive work items don't contribute to the
+	concurrency level, start of their executions is still
+	regulated by the concurrency management and runnable
+	non-CPU-intensive work items can delay execution of CPU
+	intensive work items.
+
+	This flag is meaningless for unbound wq.
+
+  WQ_HIGHPRI | WQ_CPU_INTENSIVE
+
+	This combination makes the wq avoid interaction with
+	concurrency management completely and behave as a simple
+	per-CPU execution context provider.  Work items queued on a
+	highpri CPU-intensive wq start execution as soon as resources
+	are available and don't affect execution of other work items.
+
+@max_active:
+
+@max_active determines the maximum number of execution contexts per
+CPU which can be assigned to the work items of a wq.  For example,
+with @max_active of 16, at most 16 work items of the wq can be
+executing at the same time per CPU.
+
+Currently, for a bound wq, the maximum limit for @max_active is 512
+and the default value used when 0 is specified is 256.  For an unbound
+wq, the limit is higher of 512 and 4 * num_possible_cpus().  These
+values are chosen sufficiently high such that they are not the
+limiting factor while providing protection in runaway cases.
+
+The number of active work items of a wq is usually regulated by the
+users of the wq, more specifically, by how many work items the users
+may queue at the same time.  Unless there is a specific need for
+throttling the number of active work items, specifying '0' is
+recommended.
+
+Some users depend on the strict execution ordering of ST wq.  The
+combination of @max_active of 1 and WQ_UNBOUND is used to achieve this
+behavior.  Work items on such wq are always queued to the unbound gcwq
+and only one work item can be active at any given time thus achieving
+the same ordering property as ST wq.
+
+
+5. Example Execution Scenarios
+
+The following example execution scenarios try to illustrate how cmwq
+behave under different configurations.
+
+ Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU.
+ w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms
+ again before finishing.  w1 and w2 burn CPU for 5ms then sleep for
+ 10ms.
+
+Ignoring all other tasks, works and processing overhead, and assuming
+simple FIFO scheduling, the following is one highly simplified version
+of possible sequences of events with the original wq.
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 starts and burns CPU
+ 25		w1 sleeps
+ 35		w1 wakes up and finishes
+ 35		w2 starts and burns CPU
+ 40		w2 sleeps
+ 50		w2 wakes up and finishes
+
+And with cmwq with @max_active >= 3,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 starts and burns CPU
+ 10		w1 sleeps
+ 10		w2 starts and burns CPU
+ 15		w2 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 25		w2 wakes up and finishes
+
+If @max_active == 2,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 starts and burns CPU
+ 10		w1 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 20		w2 starts and burns CPU
+ 25		w2 sleeps
+ 35		w2 wakes up and finishes
+
+Now, let's assume w1 and w2 are queued to a different wq q1 which has
+WQ_HIGHPRI set,
+
+ TIME IN MSECS	EVENT
+ 0		w1 and w2 start and burn CPU
+ 5		w1 sleeps
+ 10		w2 sleeps
+ 10		w0 starts and burns CPU
+ 15		w0 sleeps
+ 15		w1 wakes up and finishes
+ 20		w2 wakes up and finishes
+ 25		w0 wakes up and burns CPU
+ 30		w0 finishes
+
+If q1 has WQ_CPU_INTENSIVE set,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 and w2 start and burn CPU
+ 10		w1 sleeps
+ 15		w2 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 25		w2 wakes up and finishes
+
+
+6. Guidelines
+
+* Do not forget to use WQ_RESCUER if a wq may process work items which
+  are used during memory reclaim.  Each wq with WQ_RESCUER set has one
+  rescuer thread reserved for it.  If there is dependency among
+  multiple work items used during memory reclaim, they should be
+  queued to separate wq each with WQ_RESCUER.
+
+* Unless strict ordering is required, there is no need to use ST wq.
+
+* Unless there is a specific need, using 0 for @max_active is
+  recommended.  In most use cases, concurrency level usually stays
+  well under the default limit.
+
+* A wq serves as a domain for forward progress guarantee (WQ_RESCUER),
+  flush and work item attributes.  Work items which are not involved
+  in memory reclaim and don't need to be flushed as a part of a group
+  of work items, and don't require any special attribute, can use one
+  of the system wq.  There is no difference in execution
+  characteristics between using a dedicated wq and a system wq.
+
+* Unless work items are expected to consume a huge amount of CPU
+  cycles, using a bound wq is usually beneficial due to the increased
+  level of locality in wq operations and work item execution.

MAINTAINERS

@@ -962,6 +962,13 @@ W:	http://www.fluff.org/ben/linux/
 S:	Maintained
 F:	arch/arm/mach-s3c6410/
 
+ARM/S5P ARM ARCHITECTURES
+M:	Kukjin Kim <kgene.kim@samsung.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-s5p*/
+
 ARM/SHMOBILE ARM ARCHITECTURE
 M:	Paul Mundt <lethal@linux-sh.org>
 M:	Magnus Damm <magnus.damm@gmail.com>
@@ -1227,7 +1234,7 @@ F:	drivers/auxdisplay/
 F:	include/linux/cfag12864b.h
 
 AVR32 ARCHITECTURE
-M:	Haavard Skinnemoen <hskinnemoen@atmel.com>
+M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
 W:	http://www.atmel.com/products/AVR32/
 W:	http://avr32linux.org/
 W:	http://avrfreaks.net/
@@ -1235,7 +1242,7 @@ S:	Supported
 F:	arch/avr32/
 
 AVR32/AT32AP MACHINE SUPPORT
-M:	Haavard Skinnemoen <hskinnemoen@atmel.com>
+M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
 S:	Supported
 F:	arch/avr32/mach-at32ap/
 
@@ -2213,6 +2220,12 @@ W:	http://acpi4asus.sf.net
 S:	Maintained
 F:	drivers/platform/x86/eeepc-laptop.c
 
+EFIFB FRAMEBUFFER DRIVER
+L:	linux-fbdev@vger.kernel.org
+M:	Peter Jones <pjones@redhat.com>
+S:	Maintained
+F:	drivers/video/efifb.c
+
 EFS FILESYSTEM
 W:	http://aeschi.ch.eu.org/efs/
 S:	Orphan
@@ -2671,9 +2684,14 @@ S:	Maintained
 F:	drivers/media/video/gspca/
 
 HARDWARE MONITORING
+M:	Jean Delvare <khali@linux-fr.org>
+M:	Guenter Roeck <guenter.roeck@ericsson.com>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
-S:	Orphan
+T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
+T:	quilt kernel.org/pub/linux/kernel/people/groeck/linux-staging/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
+S:	Maintained
 F:	Documentation/hwmon/
 F:	drivers/hwmon/
 F:	include/linux/hwmon*.h
@@ -2811,11 +2829,6 @@ S:	Maintained
 F:	arch/x86/kernel/hpet.c
 F:	arch/x86/include/asm/hpet.h
 
-HPET:	ACPI
-M:	Bob Picco <bob.picco@hp.com>
-S:	Maintained
-F:	drivers/char/hpet.c
-
 HPFS FILESYSTEM
 M:	Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
 W:	http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi
@@ -3070,16 +3083,27 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ixp2000/
 
-INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe)
+INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf)
 M:	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
 M:	Jesse Brandeburg <jesse.brandeburg@intel.com>
 M:	Bruce Allan <bruce.w.allan@intel.com>
-M:	Alex Duyck <alexander.h.duyck@intel.com>
+M:	Carolyn Wyborny <carolyn.wyborny@intel.com>
+M:	Don Skidmore <donald.c.skidmore@intel.com>
+M:	Greg Rose <gregory.v.rose@intel.com>
 M:	PJ Waskiewicz <peter.p.waskiewicz.jr@intel.com>
+M:	Alex Duyck <alexander.h.duyck@intel.com>
 M:	John Ronciak <john.ronciak@intel.com>
 L:	e1000-devel@lists.sourceforge.net
 W:	http://e1000.sourceforge.net/
 S:	Supported
+F:	Documentation/networking/e100.txt
+F:	Documentation/networking/e1000.txt
+F:	Documentation/networking/e1000e.txt
+F:	Documentation/networking/igb.txt
+F:	Documentation/networking/igbvf.txt
+F:	Documentation/networking/ixgb.txt
+F:	Documentation/networking/ixgbe.txt
+F:	Documentation/networking/ixgbevf.txt
 F:	drivers/net/e100.c
 F:	drivers/net/e1000/
 F:	drivers/net/e1000e/
@@ -3087,6 +3111,7 @@ F:	drivers/net/igb/
 F:	drivers/net/igbvf/
 F:	drivers/net/ixgb/
 F:	drivers/net/ixgbe/
+F:	drivers/net/ixgbevf/
 
 INTEL PRO/WIRELESS 2100 NETWORK CONNECTION SUPPORT
 L:	linux-wireless@vger.kernel.org
@@ -3434,7 +3459,7 @@ F:	drivers/s390/kvm/
 
 KEXEC
 M:	Eric Biederman <ebiederm@xmission.com>
-W:	http://ftp.kernel.org/pub/linux/kernel/people/horms/kexec-tools/
+W:	http://kernel.org/pub/linux/utils/kernel/kexec/
 L:	kexec@lists.infradead.org
 S:	Maintained
 F:	include/linux/kexec.h
@@ -3795,9 +3820,8 @@ W:	http://www.syskonnect.com
 S:	Supported
 
 MATROX FRAMEBUFFER DRIVER
-M:	Petr Vandrovec <vandrove@vc.cvut.cz>
 L:	linux-fbdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/video/matrox/matroxfb_*
 F:	include/linux/matroxfb.h
 
@@ -3921,10 +3945,8 @@ F:	Documentation/serial/moxa-smartio
 F:	drivers/char/mxser.*
 
 MSI LAPTOP SUPPORT
-M:	Lennart Poettering <mzxreary@0pointer.de>
+M:	Lee, Chun-Yi <jlee@novell.com>
 L:	platform-driver-x86@vger.kernel.org
-W:	https://tango.0pointer.de/mailman/listinfo/s270-linux
-W:	http://0pointer.de/lennart/tchibo.html
 S:	Maintained
 F:	drivers/platform/x86/msi-laptop.c
 
@@ -3941,8 +3963,10 @@ S:	Supported
 F:	drivers/mfd/
 
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
-S:	Orphan
+M:	Chris Ball <cjb@laptop.org>
 L:	linux-mmc@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git
+S:	Maintained
 F:	drivers/mmc/
 F:	include/linux/mmc/
 
@@ -3964,7 +3988,7 @@ F:	drivers/char/isicom.c
 F:	include/linux/isicom.h
 
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 L:	linux-usb@vger.kernel.org
 T:	git git://gitorious.org/usb/usb.git
 S:	Maintained
@@ -3984,8 +4008,8 @@ S:	Maintained
 F:	drivers/net/natsemi.c
 
 NCP FILESYSTEM
-M:	Petr Vandrovec <vandrove@vc.cvut.cz>
+M:	Petr Vandrovec <petr@vandrovec.name>
-S:	Maintained
+S:	Odd Fixes
 F:	fs/ncpfs/
 
 NCR DUAL 700 SCSI DRIVER (MICROCHANNEL)
@@ -4262,7 +4286,7 @@ S:	Maintained
 F:	drivers/char/hw_random/omap-rng.c
 
 OMAP USB SUPPORT
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
@@ -4839,6 +4863,7 @@ RCUTORTURE MODULE
 M:	Josh Triplett <josh@freedesktop.org>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/rcutorture.c
 
@@ -4863,6 +4888,7 @@ M:	Dipankar Sarma <dipankar@in.ibm.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 W:	http://www.rdrop.com/users/paulmck/rclock/
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/
 F:	include/linux/rcu*
 F:	include/linux/srcu*
@@ -4870,12 +4896,10 @@ F:	kernel/rcu*
 F:	kernel/srcu*
 X:	kernel/rcutorture.c
 
-REAL TIME CLOCK DRIVER
+REAL TIME CLOCK DRIVER (LEGACY)
 M:	Paul Gortmaker <p_gortmaker@yahoo.com>
 S:	Maintained
-F:	Documentation/rtc.txt
+F:	drivers/char/rtc.c
-F:	drivers/rtc/
-F:	include/linux/rtc.h
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
@@ -5112,8 +5136,10 @@ S:	Maintained
 F:	drivers/mmc/host/sdricoh_cs.c
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER
-S:	Orphan
+M:	Chris Ball <cjb@laptop.org>
 L:	linux-mmc@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git
+S:	Maintained
 F:	drivers/mmc/host/sdhci.*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 36
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc7
 NAME = Sheep on Meth
 
 # *DOCUMENTATION*

arch/Kconfig

@@ -32,8 +32,9 @@ config HAVE_OPROFILE
 
 config KPROBES
 	bool "Kprobes"
-	depends on KALLSYMS && MODULES
+	depends on MODULES
 	depends on HAVE_KPROBES
+	select KALLSYMS
 	help
 	  Kprobes allows you to trap at almost any kernel address and
 	  execute a callback function.  register_kprobe() establishes
@@ -45,7 +46,6 @@ config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	select KALLSYMS_ALL
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool

arch/alpha/include/asm/cacheflush.h

@@ -43,6 +43,8 @@ extern void smp_imb(void);
 /* ??? Ought to use this in arch/alpha/kernel/signal.c too.  */
 
 #ifndef CONFIG_SMP
+#include <linux/sched.h>
+
 extern void __load_new_mm_context(struct mm_struct *);
 static inline void
 flush_icache_user_range(struct vm_area_struct *vma, struct page *page,

arch/alpha/include/asm/unistd.h

@@ -449,10 +449,13 @@
 #define __NR_pwritev			491
 #define __NR_rt_tgsigqueueinfo		492
 #define __NR_perf_event_open		493
+#define __NR_fanotify_init		494
+#define __NR_fanotify_mark		495
+#define __NR_prlimit64			496
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			494
+#define NR_SYSCALLS			497
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
@@ -463,6 +466,7 @@
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
 
 /* "Conditional" syscalls.  What we want is
 

arch/alpha/kernel/entry.S

@@ -73,8 +73,6 @@
 	ldq	$20, HAE_REG($19);	\
 	stq	$21, HAE_CACHE($19);	\
 	stq	$21, 0($20);		\
-	ldq	$0, 0($sp);		\
-	ldq	$1, 8($sp);		\
 99:;					\
 	ldq	$19, 72($sp);		\
 	ldq	$20, 80($sp);		\
@@ -316,19 +314,24 @@ ret_from_sys_call:
 	cmovne	$26, 0, $19		/* $19 = 0 => non-restartable */
 	ldq	$0, SP_OFF($sp)
 	and	$0, 8, $0
-	beq	$0, restore_all
+	beq	$0, ret_to_kernel
-ret_from_reschedule:
+ret_to_user:
 	/* Make sure need_resched and sigpending don't change between
 		sampling and the rti.  */
 	lda	$16, 7
 	call_pal PAL_swpipl
 	ldl	$5, TI_FLAGS($8)
 	and	$5, _TIF_WORK_MASK, $2
-	bne	$5, work_pending
+	bne	$2, work_pending
 restore_all:
 	RESTORE_ALL
 	call_pal PAL_rti
 
+ret_to_kernel:
+	lda	$16, 7
+	call_pal PAL_swpipl
+	br restore_all
+
 	.align 3
 $syscall_error:
 	/*
@@ -363,7 +366,7 @@ $ret_success:
  *       $8: current.
  *      $19: The old syscall number, or zero if this is not a return
  *           from a syscall that errored and is possibly restartable.
- *      $20: Error indication.
+ *      $20: The old a3 value
  */
 
 	.align	4
@@ -392,12 +395,18 @@ $work_resched:
 
 $work_notifysig:
 	mov	$sp, $16
-	br	$1, do_switch_stack
+	bsr	$1, do_switch_stack
 	mov	$sp, $17
 	mov	$5, $18
+	mov	$19, $9		/* save old syscall number */
+	mov	$20, $10	/* save old a3 */
+	and	$5, _TIF_SIGPENDING, $2
+	cmovne	$2, 0, $9	/* we don't want double syscall restarts */
 	jsr	$26, do_notify_resume
+	mov	$9, $19
+	mov	$10, $20
 	bsr	$1, undo_switch_stack
-	br	restore_all
+	br	ret_to_user
 .end work_pending
 
 /*
@@ -430,6 +439,7 @@ strace:
 	beq	$1, 1f
 	ldq	$27, 0($2)
 1:	jsr	$26, ($27), sys_gettimeofday
+ret_from_straced:
 	ldgp	$gp, 0($26)
 
 	/* check return.. */
@@ -650,7 +660,7 @@ kernel_thread:
 	/* We don't actually care for a3 success widgetry in the kernel.
 	   Not for positive errno values.  */
 	stq	$0, 0($sp)		/* $0 */
-	br	restore_all
+	br	ret_to_kernel
 .end kernel_thread
 
 /*
@@ -757,11 +767,15 @@ sys_vfork:
 	.ent	sys_sigreturn
 sys_sigreturn:
 	.prologue 0
+	lda	$9, ret_from_straced
+	cmpult	$26, $9, $9
 	mov	$sp, $17
 	lda	$18, -SWITCH_STACK_SIZE($sp)
 	lda	$sp, -SWITCH_STACK_SIZE($sp)
 	jsr	$26, do_sigreturn
-	br	$1, undo_switch_stack
+	bne	$9, 1f
+	jsr	$26, syscall_trace
+1:	br	$1, undo_switch_stack
 	br	ret_from_sys_call
 .end sys_sigreturn
 
@@ -770,46 +784,18 @@ sys_sigreturn:
 	.ent	sys_rt_sigreturn
 sys_rt_sigreturn:
 	.prologue 0
+	lda	$9, ret_from_straced
+	cmpult	$26, $9, $9
 	mov	$sp, $17
 	lda	$18, -SWITCH_STACK_SIZE($sp)
 	lda	$sp, -SWITCH_STACK_SIZE($sp)
 	jsr	$26, do_rt_sigreturn
-	br	$1, undo_switch_stack
+	bne	$9, 1f
+	jsr	$26, syscall_trace
+1:	br	$1, undo_switch_stack
 	br	ret_from_sys_call
 .end sys_rt_sigreturn
 
-	.align	4
-	.globl	sys_sigsuspend
-	.ent	sys_sigsuspend
-sys_sigsuspend:
-	.prologue 0
-	mov	$sp, $17
-	br	$1, do_switch_stack
-	mov	$sp, $18
-	subq	$sp, 16, $sp
-	stq	$26, 0($sp)
-	jsr	$26, do_sigsuspend
-	ldq	$26, 0($sp)
-	lda	$sp, SWITCH_STACK_SIZE+16($sp)
-	ret
-.end sys_sigsuspend
-
-	.align	4
-	.globl	sys_rt_sigsuspend
-	.ent	sys_rt_sigsuspend
-sys_rt_sigsuspend:
-	.prologue 0
-	mov	$sp, $18
-	br	$1, do_switch_stack
-	mov	$sp, $19
-	subq	$sp, 16, $sp
-	stq	$26, 0($sp)
-	jsr	$26, do_rt_sigsuspend
-	ldq	$26, 0($sp)
-	lda	$sp, SWITCH_STACK_SIZE+16($sp)
-	ret
-.end sys_rt_sigsuspend
-
 	.align	4
 	.globl	sys_sethae
 	.ent	sys_sethae
@@ -928,15 +914,6 @@ sys_execve:
 	jmp	$31, do_sys_execve
 .end sys_execve
 
-	.align	4
-	.globl	osf_sigprocmask
-	.ent	osf_sigprocmask
-osf_sigprocmask:
-	.prologue 0
-	mov	$sp, $18
-	jmp	$31, sys_osf_sigprocmask
-.end osf_sigprocmask
-
 	.align	4
 	.globl	alpha_ni_syscall
 	.ent	alpha_ni_syscall

arch/alpha/kernel/err_ev6.c

@@ -90,11 +90,13 @@ static int
 ev6_parse_cbox(u64 c_addr, u64 c1_syn, u64 c2_syn, 
 	       u64 c_stat, u64 c_sts, int print)
 {
-	char *sourcename[] = { "UNKNOWN", "UNKNOWN", "UNKNOWN",
+	static const char * const sourcename[] = {
-			       "MEMORY", "BCACHE", "DCACHE", 
+		"UNKNOWN", "UNKNOWN", "UNKNOWN",
-			       "BCACHE PROBE", "BCACHE PROBE" };
+		"MEMORY", "BCACHE", "DCACHE",
-	char *streamname[] = { "D", "I" };
+		"BCACHE PROBE", "BCACHE PROBE"
-	char *bitsname[] = { "SINGLE", "DOUBLE" };
+	};
+	static const char * const streamname[] = { "D", "I" };
+	static const char * const bitsname[] = { "SINGLE", "DOUBLE" };
 	int status = MCHK_DISPOSITION_REPORT;
 	int source = -1, stream = -1, bits = -1;
 

arch/alpha/kernel/err_marvel.c

@@ -589,22 +589,23 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt)
 static void
 marvel_print_pox_trans_sum(u64 trans_sum)
 {
-	char *pcix_cmd[] = { "Interrupt Acknowledge",
+	static const char * const pcix_cmd[] = {
-			     "Special Cycle",
+		"Interrupt Acknowledge",
-			     "I/O Read",
+		"Special Cycle",
-			     "I/O Write",
+		"I/O Read",
-			     "Reserved",
+		"I/O Write",
-			     "Reserved / Device ID Message",
+		"Reserved",
-			     "Memory Read",
+		"Reserved / Device ID Message",
-			     "Memory Write",
+		"Memory Read",
-			     "Reserved / Alias to Memory Read Block",
+		"Memory Write",
-			     "Reserved / Alias to Memory Write Block",
+		"Reserved / Alias to Memory Read Block",
-			     "Configuration Read",
+		"Reserved / Alias to Memory Write Block",
-			     "Configuration Write",
+		"Configuration Read",
-			     "Memory Read Multiple / Split Completion",
+		"Configuration Write",
-			     "Dual Address Cycle",
+		"Memory Read Multiple / Split Completion",
-			     "Memory Read Line / Memory Read Block",
+		"Dual Address Cycle",
-			     "Memory Write and Invalidate / Memory Write Block"
+		"Memory Read Line / Memory Read Block",
+		"Memory Write and Invalidate / Memory Write Block"
 	};
 
 #define IO7__POX_TRANSUM__PCI_ADDR__S		(0)

arch/alpha/kernel/err_titan.c

@@ -75,8 +75,12 @@ titan_parse_p_serror(int which, u64 serror, int print)
 	int status = MCHK_DISPOSITION_REPORT;
 
 #ifdef CONFIG_VERBOSE_MCHECK
-	char *serror_src[] = {"GPCI", "APCI", "AGP HP", "AGP LP"};
+	static const char * const serror_src[] = {
-	char *serror_cmd[] = {"DMA Read", "DMA RMW", "SGTE Read", "Reserved"};
+		"GPCI", "APCI", "AGP HP", "AGP LP"
+	};
+	static const char * const serror_cmd[] = {
+		"DMA Read", "DMA RMW", "SGTE Read", "Reserved"
+	};
 #endif /* CONFIG_VERBOSE_MCHECK */
 
 #define TITAN__PCHIP_SERROR__LOST_UECC	(1UL << 0)
@@ -140,14 +144,15 @@ titan_parse_p_perror(int which, int port, u64 perror, int print)
 	int status = MCHK_DISPOSITION_REPORT;
 
 #ifdef CONFIG_VERBOSE_MCHECK
-	char *perror_cmd[] = { "Interrupt Acknowledge", "Special Cycle",
+	static const char * const perror_cmd[] = {
-			       "I/O Read",	       	"I/O Write",
+		"Interrupt Acknowledge", "Special Cycle",
-			       "Reserved",	       	"Reserved",
+		"I/O Read",		"I/O Write",
-			       "Memory Read",		"Memory Write",
+		"Reserved",		"Reserved",
-			       "Reserved",		"Reserved",
+		"Memory Read",		"Memory Write",
-			       "Configuration Read",	"Configuration Write",
+		"Reserved",		"Reserved",
-			       "Memory Read Multiple",	"Dual Address Cycle",
+		"Configuration Read",	"Configuration Write",
-			       "Memory Read Line","Memory Write and Invalidate"
+		"Memory Read Multiple",	"Dual Address Cycle",
+		"Memory Read Line",	"Memory Write and Invalidate"
 	};
 #endif /* CONFIG_VERBOSE_MCHECK */
 
@@ -273,11 +278,11 @@ titan_parse_p_agperror(int which, u64 agperror, int print)
 	int cmd, len;
 	unsigned long addr;
 
-	char *agperror_cmd[] = { "Read (low-priority)",	"Read (high-priority)",
+	static const char * const agperror_cmd[] = {
-				 "Write (low-priority)",
+		"Read (low-priority)",	"Read (high-priority)",
-				 "Write (high-priority)",
+		"Write (low-priority)",	"Write (high-priority)",
-				 "Reserved",		"Reserved",
+		"Reserved",		"Reserved",
-				 "Flush",		"Fence"
+		"Flush",		"Fence"
 	};
 #endif /* CONFIG_VERBOSE_MCHECK */
 

arch/alpha/kernel/osf_sys.c

@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
@@ -69,7 +68,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start,
 {
 	struct mm_struct *mm;
 
-	lock_kernel();
 	mm = current->mm;
 	mm->end_code = bss_start + bss_len;
 	mm->start_brk = bss_start + bss_len;
@@ -78,7 +76,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start,
 	printk("set_program_attributes(%lx %lx %lx %lx)\n",
 		text_start, text_len, bss_start, bss_len);
 #endif
-	unlock_kernel();
 	return 0;
 }
 
@@ -517,7 +514,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code,
 	long error;
 	int __user *min_buf_size_ptr;
 
-	lock_kernel();
 	switch (code) {
 	case PL_SET:
 		if (get_user(error, &args->set.nbytes))
@@ -547,7 +543,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code,
 		error = -EOPNOTSUPP;
 		break;
 	};
-	unlock_kernel();
 	return error;
 }
 
@@ -594,7 +589,7 @@ SYSCALL_DEFINE2(osf_sigstack, struct sigstack __user *, uss,
 
 SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count)
 {
-	char *sysinfo_table[] = {
+	const char *sysinfo_table[] = {
 		utsname()->sysname,
 		utsname()->nodename,
 		utsname()->release,
@@ -606,7 +601,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count)
 		"dummy",	/* secure RPC domain */
 	};
 	unsigned long offset;
-	char *res;
+	const char *res;
 	long len, err = -EINVAL;
 
 	offset = command-1;

arch/alpha/kernel/pci-sysfs.c

@@ -66,7 +66,7 @@ static int pci_mmap_resource(struct kobject *kobj,
 {
 	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
 						       struct device, kobj));
-	struct resource *res = (struct resource *)attr->private;
+	struct resource *res = attr->private;
 	enum pci_mmap_state mmap_type;
 	struct pci_bus_region bar;
 	int i;

arch/alpha/kernel/process.c

@@ -356,7 +356,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti)
 	dest[27] = pt->r27;
 	dest[28] = pt->r28;
 	dest[29] = pt->gp;
-	dest[30] = rdusp();
+	dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp;
 	dest[31] = pt->pc;
 
 	/* Once upon a time this was the PS value.  Which is stupid

arch/alpha/kernel/signal.c

@@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *,
 /*
  * The OSF/1 sigprocmask calling sequence is different from the
  * C sigprocmask() sequence..
- *
- * how:
- * 1 - SIG_BLOCK
- * 2 - SIG_UNBLOCK
- * 3 - SIG_SETMASK
- *
- * We change the range to -1 .. 1 in order to let gcc easily
- * use the conditional move instructions.
- *
- * Note that we don't need to acquire the kernel lock for SMP
- * operation, as all of this is local to this thread.
  */
-SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask,
+SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask)
-		struct pt_regs *, regs)
 {
-	unsigned long oldmask = -EINVAL;
+	sigset_t oldmask;
+	sigset_t mask;
+	unsigned long res;
 
-	if ((unsigned long)how-1 <= 2) {
+	siginitset(&mask, newmask & _BLOCKABLE);
-		long sign = how-2;		/* -1 .. 1 */
+	res = sigprocmask(how, &mask, &oldmask);
-		unsigned long block, unblock;
+	if (!res) {
-
+		force_successful_syscall_return();
-		newmask &= _BLOCKABLE;
+		res = oldmask.sig[0];
-		spin_lock_irq(&current->sighand->siglock);
-		oldmask = current->blocked.sig[0];
-
-		unblock = oldmask & ~newmask;
-		block = oldmask | newmask;
-		if (!sign)
-			block = unblock;
-		if (sign <= 0)
-			newmask = block;
-		if (_NSIG_WORDS > 1 && sign > 0)
-			sigemptyset(&current->blocked);
-		current->blocked.sig[0] = newmask;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-
-		regs->r0 = 0;		/* special no error return */
 	}
-	return oldmask;
+	return res;
 }
 
 SYSCALL_DEFINE3(osf_sigaction, int, sig,
@@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 		old_sigset_t mask;
 		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
 		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-		    __get_user(new_ka.sa.sa_flags, &act->sa_flags))
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(mask, &act->sa_mask))
 			return -EFAULT;
-		__get_user(mask, &act->sa_mask);
 		siginitset(&new_ka.sa.sa_mask, mask);
 		new_ka.ka_restorer = NULL;
 	}
@@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 	if (!ret && oact) {
 		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
 		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags))
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
 			return -EFAULT;
-		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
 	}
 
 	return ret;
@@ -144,8 +118,7 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act,
 /*
  * Atomically swap in the new signal mask, and wait for a signal.
  */
-asmlinkage int
+SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask)
-do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw)
 {
 	mask &= _BLOCKABLE;
 	spin_lock_irq(&current->sighand->siglock);
@@ -154,41 +127,6 @@ do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	/* Indicate EINTR on return from any possible signal handler,
-	   which will not come back through here, but via sigreturn.  */
-	regs->r0 = EINTR;
-	regs->r19 = 1;
-
-	current->state = TASK_INTERRUPTIBLE;
-	schedule();
-	set_thread_flag(TIF_RESTORE_SIGMASK);
-	return -ERESTARTNOHAND;
-}
-
-asmlinkage int
-do_rt_sigsuspend(sigset_t __user *uset, size_t sigsetsize,
-		 struct pt_regs *regs, struct switch_stack *sw)
-{
-	sigset_t set;
-
-	/* XXX: Don't preclude handling different sized sigset_t's.  */
-	if (sigsetsize != sizeof(sigset_t))
-		return -EINVAL;
-	if (copy_from_user(&set, uset, sizeof(set)))
-		return -EFAULT;
-
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->saved_sigmask = current->blocked;
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	/* Indicate EINTR on return from any possible signal handler,
-	   which will not come back through here, but via sigreturn.  */
-	regs->r0 = EINTR;
-	regs->r19 = 1;
-
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
 	set_thread_flag(TIF_RESTORE_SIGMASK);
@@ -239,6 +177,8 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	unsigned long usp;
 	long i, err = __get_user(regs->pc, &sc->sc_pc);
 
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
 	sw->r26 = (unsigned long) ret_from_sys_call;
 
 	err |= __get_user(regs->r0, sc->sc_regs+0);
@@ -591,7 +531,6 @@ syscall_restart(unsigned long r0, unsigned long r19,
 		regs->pc -= 4;
 		break;
 	case ERESTART_RESTARTBLOCK:
-		current_thread_info()->restart_block.fn = do_no_restart_syscall;
 		regs->r0 = EINTR;
 		break;
 	}

arch/alpha/kernel/srm_env.c

@@ -87,7 +87,7 @@ static int srm_env_proc_show(struct seq_file *m, void *v)
 	srm_env_t	*entry;
 	char		*page;
 
-	entry = (srm_env_t *)m->private;
+	entry = m->private;
 	page = (char *)__get_free_page(GFP_USER);
 	if (!page)
 		return -ENOMEM;

arch/alpha/kernel/systbls.S

@@ -58,7 +58,7 @@ sys_call_table:
 	.quad sys_open				/* 45 */
 	.quad alpha_ni_syscall
 	.quad sys_getxgid
-	.quad osf_sigprocmask
+	.quad sys_osf_sigprocmask
 	.quad alpha_ni_syscall
 	.quad alpha_ni_syscall			/* 50 */
 	.quad sys_acct
@@ -512,6 +512,9 @@ sys_call_table:
 	.quad sys_pwritev
 	.quad sys_rt_tgsigqueueinfo
 	.quad sys_perf_event_open
+	.quad sys_fanotify_init
+	.quad sys_fanotify_mark				/* 495 */
+	.quad sys_prlimit64
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object

arch/alpha/kernel/time.c

@@ -191,16 +191,16 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 
 	write_sequnlock(&xtime_lock);
 
-#ifndef CONFIG_SMP
-	while (nticks--)
-		update_process_times(user_mode(get_irq_regs()));
-#endif
-
 	if (test_perf_event_pending()) {
 		clear_perf_event_pending();
 		perf_event_do_pending();
 	}
 
+#ifndef CONFIG_SMP
+	while (nticks--)
+		update_process_times(user_mode(get_irq_regs()));
+#endif
+
 	return IRQ_HANDLED;
 }
 

arch/alpha/kernel/traps.c

@@ -13,7 +13,6 @@
 #include <linux/sched.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
-#include <linux/smp_lock.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
@@ -623,7 +622,6 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 		return;
 	}
 
-	lock_kernel();
 	printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n",
 		pc, va, opcode, reg);
 	do_exit(SIGSEGV);
@@ -646,7 +644,6 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 	 * Yikes!  No one to forward the exception to.
 	 * Since the registers are in a weird format, dump them ourselves.
  	 */
-	lock_kernel();
 
 	printk("%s(%d): unhandled unaligned exception\n",
 	       current->comm, task_pid_nr(current));

arch/arm/Kconfig

@@ -271,7 +271,6 @@ config ARCH_AT91
 	bool "Atmel AT91"
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
-	select ARCH_USES_GETTIMEOFFSET
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -1051,6 +1050,32 @@ config ARM_ERRATA_460075
 	  ACTLR register. Note that setting specific bits in the ACTLR register
 	  may not be available in non-secure mode.
 
+config ARM_ERRATA_742230
+	bool "ARM errata: DMB operation may be faulty"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742230 Cortex-A9
+	  (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction
+	  between two write operations may not ensure the correct visibility
+	  ordering of the two writes. This workaround sets a specific bit in
+	  the diagnostic register of the Cortex-A9 which causes the DMB
+	  instruction to behave as a DSB, ensuring the correct behaviour of
+	  the two writes.
+
+config ARM_ERRATA_742231
+	bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742231 Cortex-A9
+	  (r2p0..r2p2) erratum. Under certain conditions, specific to the
+	  Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode,
+	  accessing some data located in the same cache line, may get corrupted
+	  data due to bad handling of the address hazard when the line gets
+	  replaced from one of the CPUs at the same time as another CPU is
+	  accessing it. This workaround sets specific bits in the diagnostic
+	  register of the Cortex-A9 which reduces the linefill issuing
+	  capabilities of the processor.
+
 config PL310_ERRATA_588369
 	bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
 	depends on CACHE_L2X0 && ARCH_OMAP4
@@ -1576,97 +1601,6 @@ config AUTO_ZRELADDR
 	  0xf8000000. This assumes the zImage being placed in the first 128MB
 	  from start of memory.
 
-config ZRELADDR
-	hex "Physical address of the decompressed kernel image"
-	depends on !AUTO_ZRELADDR
-	default 0x00008000 if ARCH_BCMRING ||\
-		ARCH_CNS3XXX ||\
-		ARCH_DOVE ||\
-		ARCH_EBSA110 ||\
-		ARCH_FOOTBRIDGE ||\
-		ARCH_INTEGRATOR ||\
-		ARCH_IOP13XX ||\
-		ARCH_IOP33X ||\
-		ARCH_IXP2000 ||\
-		ARCH_IXP23XX ||\
-		ARCH_IXP4XX ||\
-		ARCH_KIRKWOOD ||\
-		ARCH_KS8695 ||\
-		ARCH_LOKI ||\
-		ARCH_MMP ||\
-		ARCH_MV78XX0 ||\
-		ARCH_NOMADIK ||\
-		ARCH_NUC93X ||\
-		ARCH_NS9XXX ||\
-		ARCH_ORION5X ||\
-		ARCH_SPEAR3XX ||\
-		ARCH_SPEAR6XX ||\
-		ARCH_TEGRA ||\
-		ARCH_U8500 ||\
-		ARCH_VERSATILE ||\
-		ARCH_W90X900
-	default 0x08008000 if ARCH_MX1 ||\
-		ARCH_SHARK
-	default 0x10008000 if ARCH_MSM ||\
-		ARCH_OMAP1 ||\
-		ARCH_RPC
-	default 0x20008000 if ARCH_S5P6440 ||\
-		ARCH_S5P6442 ||\
-		ARCH_S5PC100 ||\
-		ARCH_S5PV210
-	default 0x30008000 if ARCH_S3C2410 ||\
-		ARCH_S3C2400 ||\
-		ARCH_S3C2412 ||\
-		ARCH_S3C2416 ||\
-		ARCH_S3C2440 ||\
-		ARCH_S3C2443
-	default 0x40008000 if ARCH_STMP378X ||\
-		ARCH_STMP37XX ||\
-		ARCH_SH7372 ||\
-		ARCH_SH7377 ||\
-		ARCH_S5PV310
-	default 0x50008000 if ARCH_S3C64XX ||\
-		ARCH_SH7367
-	default 0x60008000 if ARCH_VEXPRESS
-	default 0x80008000 if ARCH_MX25 ||\
-		ARCH_MX3 ||\
-		ARCH_NETX ||\
-		ARCH_OMAP2PLUS ||\
-		ARCH_PNX4008
-	default 0x90008000 if ARCH_MX5 ||\
-		ARCH_MX91231
-	default 0xa0008000 if ARCH_IOP32X ||\
-		ARCH_PXA ||\
-		MACH_MX27
-	default 0xc0008000 if ARCH_LH7A40X ||\
-		MACH_MX21
-	default 0xf0008000 if ARCH_AAEC2000 ||\
-		ARCH_L7200
-	default 0xc0028000 if ARCH_CLPS711X
-	default 0x70008000 if ARCH_AT91 && (ARCH_AT91CAP9 || ARCH_AT91SAM9G45)
-	default 0x20008000 if ARCH_AT91 && !(ARCH_AT91CAP9 || ARCH_AT91SAM9G45)
-	default 0xc0008000 if ARCH_DAVINCI && ARCH_DAVINCI_DA8XX
-	default 0x80008000 if ARCH_DAVINCI && !ARCH_DAVINCI_DA8XX
-	default 0x00008000 if ARCH_EP93XX && EP93XX_SDCE3_SYNC_PHYS_OFFSET
-	default 0xc0008000 if ARCH_EP93XX && EP93XX_SDCE0_PHYS_OFFSET
-	default 0xd0008000 if ARCH_EP93XX && EP93XX_SDCE1_PHYS_OFFSET
-	default 0xe0008000 if ARCH_EP93XX && EP93XX_SDCE2_PHYS_OFFSET
-	default 0xf0008000 if ARCH_EP93XX && EP93XX_SDCE3_ASYNC_PHYS_OFFSET
-	default 0x00008000 if ARCH_GEMINI && GEMINI_MEM_SWAP
-	default 0x10008000 if ARCH_GEMINI && !GEMINI_MEM_SWAP
-	default 0x70008000 if ARCH_REALVIEW && REALVIEW_HIGH_PHYS_OFFSET
-	default 0x00008000 if ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET
-	default 0xc0208000 if ARCH_SA1100 && SA1111
-	default 0xc0008000 if ARCH_SA1100 && !SA1111
-	default 0x30108000 if ARCH_S3C2410 && PM_H1940
-	default 0x28E08000 if ARCH_U300 && MACH_U300_SINGLE_RAM
-	default 0x48008000 if ARCH_U300 && !MACH_U300_SINGLE_RAM
-	help
-	  ZRELADDR is the physical address where the decompressed kernel
-	  image will be placed. ZRELADDR has to be specified when the
-	  assumption of AUTO_ZRELADDR is not valid, or when ZBOOT_ROM is
-	  selected.
-
 endmenu
 
 menu "CPU Power Management"

arch/arm/boot/Makefile

@@ -14,16 +14,18 @@
 MKIMAGE         := $(srctree)/scripts/mkuboot.sh
 
 ifneq ($(MACHINE),)
--include $(srctree)/$(MACHINE)/Makefile.boot
+include $(srctree)/$(MACHINE)/Makefile.boot
 endif
 
 # Note: the following conditions must always be true:
+#   ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET)
 #   PARAMS_PHYS must be within 4MB of ZRELADDR
 #   INITRD_PHYS must be in RAM
+ZRELADDR    := $(zreladdr-y)
 PARAMS_PHYS := $(params_phys-y)
 INITRD_PHYS := $(initrd_phys-y)
 
-export INITRD_PHYS PARAMS_PHYS
+export ZRELADDR INITRD_PHYS PARAMS_PHYS
 
 targets := Image zImage xipImage bootpImage uImage
 
@@ -65,7 +67,7 @@ quiet_cmd_uimage = UIMAGE  $@
 ifeq ($(CONFIG_ZBOOT_ROM),y)
 $(obj)/uImage: LOADADDR=$(CONFIG_ZBOOT_ROM_TEXT)
 else
-$(obj)/uImage: LOADADDR=$(CONFIG_ZRELADDR)
+$(obj)/uImage: LOADADDR=$(ZRELADDR)
 endif
 
 ifeq ($(CONFIG_THUMB2_KERNEL),y)

arch/arm/boot/compressed/Makefile

@@ -79,6 +79,10 @@ endif
 EXTRA_CFLAGS  := -fpic -fno-builtin
 EXTRA_AFLAGS  := -Wa,-march=all
 
+# Supply ZRELADDR to the decompressor via a linker symbol.
+ifneq ($(CONFIG_AUTO_ZRELADDR),y)
+LDFLAGS_vmlinux := --defsym zreladdr=$(ZRELADDR)
+endif
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux += --be8
 endif
@@ -112,5 +116,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config
+$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
 	@sed "$(SEDFLAGS)" < $< > $@

arch/arm/boot/compressed/head.S

@@ -177,7 +177,7 @@ not_angel:
 		and	r4, pc, #0xf8000000
 		add	r4, r4, #TEXT_OFFSET
 #else
-		ldr	r4, =CONFIG_ZRELADDR
+		ldr	r4, =zreladdr
 #endif
 		subs	r0, r0, r1		@ calculate the delta offset
 

arch/arm/common/it8152.c

@@ -263,6 +263,22 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
 	return 0;
 }
 
+int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+		__func__, dma_addr, size);
+	return (dev->bus == &pci_bus_type) &&
+		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
+}
+
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= PHYS_OFFSET + SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 int __init it8152_pci_setup(int nr, struct pci_sys_data *sys)
 {
 	it8152_io.start = IT8152_IO_BASE + 0x12000;

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

@@ -288,15 +288,7 @@ extern void dmabounce_unregister_dev(struct device *);
  * DMA access and 1 if the buffer needs to be bounced.
  *
  */
-#ifdef CONFIG_SA1111
 extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-#else
-static inline int dma_needs_bounce(struct device *dev, dma_addr_t addr,
-				   size_t size)
-{
-	return 0;
-}
-#endif
 
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.

arch/arm/include/asm/perf_event.h

@@ -17,7 +17,7 @@
  * counter interrupts are regular interrupts and not an NMI. This
  * means that when we receive the interrupt we can call
  * perf_event_do_pending() that handles all of the work with
- * interrupts enabled.
+ * interrupts disabled.
  */
 static inline void
 set_perf_event_pending(void)

arch/arm/include/asm/pgtable.h

@@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)

arch/arm/include/asm/unistd.h

@@ -393,6 +393,9 @@
 #define __NR_perf_event_open		(__NR_SYSCALL_BASE+364)
 #define __NR_recvmmsg			(__NR_SYSCALL_BASE+365)
 #define __NR_accept4			(__NR_SYSCALL_BASE+366)
+#define __NR_fanotify_init		(__NR_SYSCALL_BASE+367)
+#define __NR_fanotify_mark		(__NR_SYSCALL_BASE+368)
+#define __NR_prlimit64			(__NR_SYSCALL_BASE+369)
 
 /*
  * The following SWIs are ARM private.

arch/arm/kernel/calls.S

@@ -376,6 +376,9 @@
 		CALL(sys_perf_event_open)
 /* 365 */	CALL(sys_recvmmsg)
 		CALL(sys_accept4)
+		CALL(sys_fanotify_init)
+		CALL(sys_fanotify_mark)
+		CALL(sys_prlimit64)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/arm/kernel/entry-common.S

@@ -48,6 +48,8 @@ work_pending:
 	beq	no_work_pending
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
+	tst	r1, #_TIF_SIGPENDING		@ delivering a signal?
+	movne	why, #0				@ prevent further restarts
 	bl	do_notify_resume
 	b	ret_slow_syscall		@ Check work again
 
@@ -418,11 +420,13 @@ ENDPROC(sys_clone_wrapper)
 
 sys_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
+		mov	why, #0		@ prevent syscall restart handling
 		b	sys_sigreturn
 ENDPROC(sys_sigreturn_wrapper)
 
 sys_rt_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
+		mov	why, #0		@ prevent syscall restart handling
 		b	sys_rt_sigreturn
 ENDPROC(sys_rt_sigreturn_wrapper)
 

arch/arm/kernel/perf_event.c

@@ -319,8 +319,8 @@ validate_event(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event fake_event = event->hw;
 
-	if (event->pmu && event->pmu != &pmu)
+	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
-		return 0;
+		return 1;
 
 	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
 }
@@ -1041,8 +1041,8 @@ armv6pmu_handle_irq(int irq_num,
 	/*
 	 * Handle the pending perf events.
 	 *
-	 * Note: this call *must* be run with interrupts enabled. For
+	 * Note: this call *must* be run with interrupts disabled. For
-	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
 	perf_event_do_pending();
@@ -2017,8 +2017,8 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	/*
 	 * Handle the pending perf events.
 	 *
-	 * Note: this call *must* be run with interrupts enabled. For
+	 * Note: this call *must* be run with interrupts disabled. For
-	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
 	perf_event_do_pending();

arch/arm/mach-at91/at91sam9g45.c

@@ -121,8 +121,8 @@ static struct clk ssc1_clk = {
 	.pmc_mask	= 1 << AT91SAM9G45_ID_SSC1,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
-static struct clk tcb_clk = {
+static struct clk tcb0_clk = {
-	.name		= "tcb_clk",
+	.name		= "tcb0_clk",
 	.pmc_mask	= 1 << AT91SAM9G45_ID_TCB,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
@@ -192,6 +192,14 @@ static struct clk ohci_clk = {
 	.parent		= &uhphs_clk,
 };
 
+/* One additional fake clock for second TC block */
+static struct clk tcb1_clk = {
+	.name		= "tcb1_clk",
+	.pmc_mask	= 0,
+	.type		= CLK_TYPE_PERIPHERAL,
+	.parent		= &tcb0_clk,
+};
+
 static struct clk *periph_clocks[] __initdata = {
 	&pioA_clk,
 	&pioB_clk,
@@ -208,7 +216,7 @@ static struct clk *periph_clocks[] __initdata = {
 	&spi1_clk,
 	&ssc0_clk,
 	&ssc1_clk,
-	&tcb_clk,
+	&tcb0_clk,
 	&pwm_clk,
 	&tsc_clk,
 	&dma_clk,
@@ -221,6 +229,7 @@ static struct clk *periph_clocks[] __initdata = {
 	&mmc1_clk,
 	// irq0
 	&ohci_clk,
+	&tcb1_clk,
 };
 
 /*

arch/arm/mach-at91/at91sam9g45_devices.c

@@ -46,7 +46,7 @@ static struct resource hdmac_resources[] = {
 		.end	= AT91_BASE_SYS + AT91_DMA + SZ_512 - 1,
 		.flags	= IORESOURCE_MEM,
 	},
-	[2] = {
+	[1] = {
 		.start	= AT91SAM9G45_ID_DMA,
 		.end	= AT91SAM9G45_ID_DMA,
 		.flags	= IORESOURCE_IRQ,
@@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PA21,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi0_device = {
@@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PB11,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi1_device = {
@@ -835,9 +835,9 @@ static struct platform_device at91sam9g45_tcb1_device = {
 static void __init at91_add_device_tc(void)
 {
 	/* this chip has one clock and irq for all six TC channels */
-	at91_clock_associate("tcb_clk", &at91sam9g45_tcb0_device.dev, "t0_clk");
+	at91_clock_associate("tcb0_clk", &at91sam9g45_tcb0_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb0_device);
-	at91_clock_associate("tcb_clk", &at91sam9g45_tcb1_device.dev, "t0_clk");
+	at91_clock_associate("tcb1_clk", &at91sam9g45_tcb1_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb1_device);
 }
 #else

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

@@ -93,11 +93,12 @@ static struct resource dm9000_resource[] = {
 		.start	= AT91_PIN_PC11,
 		.end	= AT91_PIN_PC11,
 		.flags	= IORESOURCE_IRQ
+			| IORESOURCE_IRQ_LOWEDGE | IORESOURCE_IRQ_HIGHEDGE,
 	}
 };
 
 static struct dm9000_plat_data dm9000_platdata = {
-	.flags		= DM9000_PLATF_16BITONLY,
+	.flags		= DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM,
 };
 
 static struct platform_device dm9000_device = {
@@ -167,17 +168,6 @@ static struct at91_udc_data __initdata ek_udc_data = {
 };
 
 
-/*
- * MCI (SD/MMC)
- */
-static struct at91_mmc_data __initdata ek_mmc_data = {
-	.wire4		= 1,
-//	.det_pin	= ... not connected
-//	.wp_pin		= ... not connected
-//	.vcc_pin	= ... not connected
-};
-
-
 /*
  * NAND flash
  */
@@ -246,6 +236,10 @@ static void __init ek_add_device_nand(void)
 	at91_add_device_nand(&ek_nand_data);
 }
 
+/*
+ * SPI related devices
+ */
+#if defined(CONFIG_SPI_ATMEL) || defined(CONFIG_SPI_ATMEL_MODULE)
 
 /*
  * ADS7846 Touchscreen
@@ -356,6 +350,19 @@ static struct spi_board_info ek_spi_devices[] = {
 #endif
 };
 
+#else /* CONFIG_SPI_ATMEL_* */
+/* spi0 and mmc/sd share the same PIO pins: cannot be used at the same time */
+
+/*
+ * MCI (SD/MMC)
+ * det_pin, wp_pin and vcc_pin are not connected
+ */
+static struct at91_mmc_data __initdata ek_mmc_data = {
+	.wire4		= 1,
+};
+
+#endif /* CONFIG_SPI_ATMEL_* */
+
 
 /*
  * LCD Controller

arch/arm/mach-at91/clock.c

@@ -501,7 +501,8 @@ postcore_initcall(at91_clk_debugfs_init);
 int __init clk_register(struct clk *clk)
 {
 	if (clk_is_peripheral(clk)) {
-		clk->parent = &mck;
+		if (!clk->parent)
+			clk->parent = &mck;
 		clk->mode = pmc_periph_mode;
 		list_add_tail(&clk->node, &clocks);
 	}

arch/arm/mach-davinci/dm355.c

@@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
+		.type		= MT_MEMORY_NONCACHED,
-		.type		= MT_DEVICE,
 	},
 };
 

arch/arm/mach-davinci/dm365.c

@@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
+		.type		= MT_MEMORY_NONCACHED,
-		.type		= MT_DEVICE,
 	},
 };
 

arch/arm/mach-davinci/dm644x.c

@@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00008000),
 		.length		= SZ_16K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
+		.type		= MT_MEMORY_NONCACHED,
-		.type		= MT_DEVICE,
 	},
 };
 

arch/arm/mach-davinci/dm646x.c

@@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
+		.type		= MT_MEMORY_NONCACHED,
-		.type		= MT_DEVICE,
 	},
 };
 

arch/arm/mach-dove/include/mach/io.h

@@ -13,8 +13,8 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 
-#define __io(a)  ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\
+#define __io(a)  	((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
-				   DOVE_PCIE0_IO_VIRT_BASE))
+						 DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)		(a)
+#define __mem_pci(a)	(a)
 
 #endif

arch/arm/mach-ep93xx/clock.c

@@ -560,4 +560,4 @@ static int __init ep93xx_clock_init(void)
 	clkdev_add_table(clocks, ARRAY_SIZE(clocks));
 	return 0;
 }
-arch_initcall(ep93xx_clock_init);
+postcore_initcall(ep93xx_clock_init);

arch/arm/mach-ixp4xx/common-pci.c

@@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys)
 	return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys);
 }
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 EXPORT_SYMBOL(ixp4xx_pci_read);
 EXPORT_SYMBOL(ixp4xx_pci_write);
 

arch/arm/mach-ixp4xx/include/mach/hardware.h

@@ -26,6 +26,8 @@
 #define PCIBIOS_MAX_MEM		0x4BFFFFFF
 #endif
 
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
+
 #define pcibios_assign_all_busses()	1
 
 /* Register locations and bits */

arch/arm/mach-kirkwood/include/mach/kirkwood.h

@@ -38,7 +38,7 @@
 
 #define KIRKWOOD_PCIE1_IO_PHYS_BASE	0xf3000000
 #define KIRKWOOD_PCIE1_IO_VIRT_BASE	0xfef00000
-#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00000000
+#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00100000
 #define KIRKWOOD_PCIE1_IO_SIZE		SZ_1M
 
 #define KIRKWOOD_PCIE_IO_PHYS_BASE	0xf2000000

arch/arm/mach-kirkwood/pcie.c

@@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 0 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 
@@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 1 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 

arch/arm/mach-mmp/include/mach/system.h

@@ -9,6 +9,8 @@
 #ifndef __ASM_MACH_SYSTEM_H
 #define __ASM_MACH_SYSTEM_H
 
+#include <mach/cputype.h>
+
 static inline void arch_idle(void)
 {
 	cpu_do_idle();
@@ -16,6 +18,9 @@ static inline void arch_idle(void)
 
 static inline void arch_reset(char mode, const char *cmd)
 {
-	cpu_reset(0);
+	if (cpu_is_pxa168())
+		cpu_reset(0xffff0000);
+	else
+		cpu_reset(0);
 }
 #endif /* __ASM_MACH_SYSTEM_H */

arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c

@@ -215,7 +215,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
  * Add platform devices present on this baseboard and init
  * them from CPU side as far as required to use them later on
  */
-void __init eukrea_mbimxsd_baseboard_init(void)
+void __init eukrea_mbimxsd25_baseboard_init(void)
 {
 	if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads,
 			ARRAY_SIZE(eukrea_mbimxsd_pads)))

arch/arm/mach-mx25/mach-cpuimx25.c

@@ -147,8 +147,8 @@ static void __init eukrea_cpuimx25_init(void)
 	if (!otg_mode_host)
 		mxc_register_device(&otg_udc_device, &otg_device_pdata);
 
-#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD
+#ifdef CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD
-	eukrea_mbimxsd_baseboard_init();
+	eukrea_mbimxsd25_baseboard_init();
 #endif
 }
 

arch/arm/mach-mx3/clock-imx35.c

@@ -155,7 +155,7 @@ static unsigned long get_rate_arm(void)
 
 	aad = &clk_consumer[(pdr0 >> 16) & 0xf];
 	if (aad->sel)
-		fref = fref * 2 / 3;
+		fref = fref * 3 / 4;
 
 	return fref / aad->arm;
 }
@@ -164,7 +164,7 @@ static unsigned long get_rate_ahb(struct clk *clk)
 {
 	unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0);
 	struct arm_ahb_div *aad;
-	unsigned long fref = get_rate_mpll();
+	unsigned long fref = get_rate_arm();
 
 	aad = &clk_consumer[(pdr0 >> 16) & 0xf];
 
@@ -176,16 +176,11 @@ static unsigned long get_rate_ipg(struct clk *clk)
 	return get_rate_ahb(NULL) >> 1;
 }
 
-static unsigned long get_3_3_div(unsigned long in)
-{
-	return (((in >> 3) & 0x7) + 1) * ((in & 0x7) + 1);
-}
-
 static unsigned long get_rate_uart(struct clk *clk)
 {
 	unsigned long pdr3 = __raw_readl(CCM_BASE + CCM_PDR3);
 	unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4);
-	unsigned long div = get_3_3_div(pdr4 >> 10);
+	unsigned long div = ((pdr4 >> 10) & 0x3f) + 1;
 
 	if (pdr3 & (1 << 14))
 		return get_rate_arm() / div;
@@ -216,7 +211,7 @@ static unsigned long get_rate_sdhc(struct clk *clk)
 		break;
 	}
 
-	return rate / get_3_3_div(div);
+	return rate / (div + 1);
 }
 
 static unsigned long get_rate_mshc(struct clk *clk)
@@ -270,7 +265,7 @@ static unsigned long get_rate_csi(struct clk *clk)
 	else
 		rate = get_rate_ppll();
 
-	return rate / get_3_3_div((pdr2 >> 16) & 0x3f);
+	return rate / (((pdr2 >> 16) & 0x3f) + 1);
 }
 
 static unsigned long get_rate_otg(struct clk *clk)
@@ -283,25 +278,51 @@ static unsigned long get_rate_otg(struct clk *clk)
 	else
 		rate = get_rate_ppll();
 
-	return rate / get_3_3_div((pdr4 >> 22) & 0x3f);
+	return rate / (((pdr4 >> 22) & 0x3f) + 1);
 }
 
 static unsigned long get_rate_ipg_per(struct clk *clk)
 {
 	unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0);
 	unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4);
-	unsigned long div1, div2;
+	unsigned long div;
 
 	if (pdr0 & (1 << 26)) {
-		div1 = (pdr4 >> 19) & 0x7;
+		div = (pdr4 >> 16) & 0x3f;
-		div2 = (pdr4 >> 16) & 0x7;
+		return get_rate_arm() / (div + 1);
-		return get_rate_arm() / ((div1 + 1) * (div2 + 1));
 	} else {
-		div1 = (pdr0 >> 12) & 0x7;
+		div = (pdr0 >> 12) & 0x7;
-		return get_rate_ahb(NULL) / div1;
+		return get_rate_ahb(NULL) / (div + 1);
 	}
 }
 
+static unsigned long get_rate_hsp(struct clk *clk)
+{
+	unsigned long hsp_podf = (__raw_readl(CCM_BASE + CCM_PDR0) >> 20) & 0x03;
+	unsigned long fref = get_rate_mpll();
+
+	if (fref > 400 * 1000 * 1000) {
+		switch (hsp_podf) {
+		case 0:
+			return fref >> 2;
+		case 1:
+			return fref >> 3;
+		case 2:
+			return fref / 3;
+		}
+	} else {
+		switch (hsp_podf) {
+		case 0:
+		case 2:
+			return fref / 3;
+		case 1:
+			return fref / 6;
+		}
+	}
+
+	return 0;
+}
+
 static int clk_cgr_enable(struct clk *clk)
 {
 	u32 reg;
@@ -359,7 +380,7 @@ DEFINE_CLOCK(i2c1_clk,   0, CCM_CGR1, 10, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(i2c2_clk,   1, CCM_CGR1, 12, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(i2c3_clk,   2, CCM_CGR1, 14, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(iomuxc_clk, 0, CCM_CGR1, 16, NULL, NULL);
-DEFINE_CLOCK(ipu_clk,    0, CCM_CGR1, 18, get_rate_ahb, NULL);
+DEFINE_CLOCK(ipu_clk,    0, CCM_CGR1, 18, get_rate_hsp, NULL);
 DEFINE_CLOCK(kpp_clk,    0, CCM_CGR1, 20, get_rate_ipg, NULL);
 DEFINE_CLOCK(mlb_clk,    0, CCM_CGR1, 22, get_rate_ahb, NULL);
 DEFINE_CLOCK(mshc_clk,   0, CCM_CGR1, 24, get_rate_mshc, NULL);
@@ -485,10 +506,10 @@ static struct clk_lookup lookups[] = {
 
 int __init mx35_clocks_init()
 {
-	unsigned int ll = 0;
+	unsigned int cgr2 = 3 << 26, cgr3 = 0;
 
 #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC)
-	ll = (3 << 16);
+	cgr2 |= 3 << 16;
 #endif
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
@@ -499,8 +520,20 @@ int __init mx35_clocks_init()
 	__raw_writel((3 << 18), CCM_BASE + CCM_CGR0);
 	__raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16),
 			CCM_BASE + CCM_CGR1);
-	__raw_writel((3 << 26) | ll, CCM_BASE + CCM_CGR2);
+
-	__raw_writel(0, CCM_BASE + CCM_CGR3);
+	/*
+	 * Check if we came up in internal boot mode. If yes, we need some
+	 * extra clocks turned on, otherwise the MX35 boot ROM code will
+	 * hang after a watchdog reset.
+	 */
+	if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) {
+		/* Additionally turn on UART1, SCC, and IIM clocks */
+		cgr2 |= 3 << 16 | 3 << 4;
+		cgr3 |= 3 << 2;
+	}
+
+	__raw_writel(cgr2, CCM_BASE + CCM_CGR2);
+	__raw_writel(cgr3, CCM_BASE + CCM_CGR3);
 
 	mxc_timer_init(&gpt_clk,
 			MX35_IO_ADDRESS(MX35_GPT1_BASE_ADDR), MX35_INT_GPT);

arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c

@@ -216,7 +216,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
  * Add platform devices present on this baseboard and init
  * them from CPU side as far as required to use them later on
  */
-void __init eukrea_mbimxsd_baseboard_init(void)
+void __init eukrea_mbimxsd35_baseboard_init(void)
 {
 	if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads,
 			ARRAY_SIZE(eukrea_mbimxsd_pads)))

arch/arm/mach-mx3/mach-cpuimx35.c

@@ -201,8 +201,8 @@ static void __init mxc_board_init(void)
 	if (!otg_mode_host)
 		mxc_register_device(&mxc_otg_udc_device, &otg_device_pdata);
 
-#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD
+#ifdef CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD
-	eukrea_mbimxsd_baseboard_init();
+	eukrea_mbimxsd35_baseboard_init();
 #endif
 }
 

arch/arm/mach-mx5/clock-mx51.c

@@ -56,7 +56,7 @@ static void _clk_ccgr_disable(struct clk *clk)
 {
 	u32 reg;
 	reg = __raw_readl(clk->enable_reg);
-	reg &= ~(MXC_CCM_CCGRx_MOD_OFF << clk->enable_shift);
+	reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift);
 	__raw_writel(reg, clk->enable_reg);
 
 }

arch/arm/mach-pxa/cpufreq-pxa2xx.c

@@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	freqs.cpu = policy->cpu;
 
 	if (freq_debug)
-		pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, "
+		pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n",
-			 "(SDRAM %d Mhz)\n",
 			 freqs.new / 1000, (pxa_freq_settings[idx].div2) ?
 			 (new_freq_mem / 2000) : (new_freq_mem / 1000));
 
@@ -398,7 +397,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	return 0;
 }
 
-static __init int pxa_cpufreq_init(struct cpufreq_policy *policy)
+static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int i;
 	unsigned int freq;

arch/arm/mach-pxa/cpufreq-pxa3xx.c

@@ -204,7 +204,7 @@ static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy,
 	return 0;
 }
 
-static __init int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
+static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret = -EINVAL;
 

arch/arm/mach-pxa/include/mach/hardware.h

@@ -264,23 +264,35 @@
  * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
  * == 0x3 for pxa300/pxa310/pxa320
  */
+#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
 #define __cpu_is_pxa2xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id <= 0x2;				\
 	 })
+#else
+#define __cpu_is_pxa2xx(id)	(0)
+#endif
 
+#ifdef CONFIG_PXA3xx
 #define __cpu_is_pxa3xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id == 0x3;				\
 	 })
+#else
+#define __cpu_is_pxa3xx(id)	(0)
+#endif
 
+#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
 #define __cpu_is_pxa93x(id)				\
 	({						\
 		unsigned int _id = (id) >> 4 & 0xfff;	\
 		_id == 0x683 || _id == 0x693;		\
 	 })
+#else
+#define __cpu_is_pxa93x(id)	(0)
+#endif
 
 #define cpu_is_pxa2xx()					\
 	({						\
@@ -309,7 +321,7 @@ extern unsigned long get_clock_tick_rate(void);
 #define PCIBIOS_MIN_IO		0
 #define PCIBIOS_MIN_MEM		0
 #define pcibios_assign_all_busses()	1
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
 #endif
 
-
 #endif  /* _ASM_ARCH_HARDWARE_H */

arch/arm/mach-pxa/include/mach/io.h

@@ -6,6 +6,8 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
+#include <mach/hardware.h>
+
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*

arch/arm/mach-pxa/include/mach/mfp-pxa300.h

@@ -71,10 +71,10 @@
 #define GPIO46_CI_DD_7		MFP_CFG_DRV(GPIO46, AF0, DS04X)
 #define GPIO47_CI_DD_8		MFP_CFG_DRV(GPIO47, AF1, DS04X)
 #define GPIO48_CI_DD_9		MFP_CFG_DRV(GPIO48, AF1, DS04X)
-#define GPIO52_CI_HSYNC		MFP_CFG_DRV(GPIO52, AF0, DS04X)
-#define GPIO51_CI_VSYNC		MFP_CFG_DRV(GPIO51, AF0, DS04X)
 #define GPIO49_CI_MCLK		MFP_CFG_DRV(GPIO49, AF0, DS04X)
 #define GPIO50_CI_PCLK		MFP_CFG_DRV(GPIO50, AF0, DS04X)
+#define GPIO51_CI_HSYNC		MFP_CFG_DRV(GPIO51, AF0, DS04X)
+#define GPIO52_CI_VSYNC		MFP_CFG_DRV(GPIO52, AF0, DS04X)
 
 /* KEYPAD */
 #define GPIO3_KP_DKIN_6		MFP_CFG_LPM(GPIO3,   AF2, FLOAT)

arch/arm/mach-pxa/palm27x.c

@@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = {
 	},
 };
 
+static struct i2c_pxa_platform_data palm27x_i2c_power_info = {
+	.use_pio	= 1,
+};
+
 void __init palm27x_pmic_init(void)
 {
 	i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info));
-	pxa27x_set_i2c_power_info(NULL);
+	pxa27x_set_i2c_power_info(&palm27x_i2c_power_info);
 }
 #endif

arch/arm/mach-pxa/vpac270.c

@@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {}
 #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE)
 static struct pxamci_platform_data vpac270_mci_platform_data = {
 	.ocr_mask		= MMC_VDD_32_33 | MMC_VDD_33_34,
+	.gpio_power		= -1,
 	.gpio_card_detect	= GPIO53_VPAC270_SD_DETECT_N,
 	.gpio_card_ro		= GPIO52_VPAC270_SD_READONLY,
 	.detect_delay_ms	= 200,

arch/arm/mach-s3c64xx/dev-spi.c

@@ -18,10 +18,11 @@
 #include <mach/map.h>
 #include <mach/gpio-bank-c.h>
 #include <mach/spi-clocks.h>
+#include <mach/irqs.h>
 
 #include <plat/s3c64xx-spi.h>
 #include <plat/gpio-cfg.h>
-#include <plat/irqs.h>
+#include <plat/devs.h>
 
 static char *spi_src_clks[] = {
 	[S3C64XX_SPI_SRCCLK_PCLK] = "pclk",

arch/arm/mach-s3c64xx/mach-real6410.c

@@ -30,73 +30,73 @@
 #include <plat/devs.h>
 #include <plat/regs-serial.h>
 
-#define UCON S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK
+#define UCON (S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK)
-#define ULCON S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB
+#define ULCON (S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB)
-#define UFCON S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE
+#define UFCON (S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE)
 
 static struct s3c2410_uartcfg real6410_uartcfgs[] __initdata = {
 	[0] = {
-		.hwport	     = 0,
+		.hwport	= 0,
-		.flags	     = 0,
+		.flags	= 0,
-		.ucon	     = UCON,
+		.ucon	= UCON,
-		.ulcon	     = ULCON,
+		.ulcon	= ULCON,
-		.ufcon	     = UFCON,
+		.ufcon	= UFCON,
 	},
 	[1] = {
-		.hwport	     = 1,
+		.hwport	= 1,
-		.flags	     = 0,
+		.flags	= 0,
-		.ucon	     = UCON,
+		.ucon	= UCON,
-		.ulcon	     = ULCON,
+		.ulcon	= ULCON,
-		.ufcon	     = UFCON,
+		.ufcon	= UFCON,
 	},
 	[2] = {
-		.hwport	     = 2,
+		.hwport	= 2,
-		.flags	     = 0,
+		.flags	= 0,
-		.ucon	     = UCON,
+		.ucon	= UCON,
-		.ulcon	     = ULCON,
+		.ulcon	= ULCON,
-		.ufcon	     = UFCON,
+		.ufcon	= UFCON,
 	},
 	[3] = {
-		.hwport	     = 3,
+		.hwport	= 3,
-		.flags	     = 0,
+		.flags	= 0,
-		.ucon	     = UCON,
+		.ucon	= UCON,
-		.ulcon	     = ULCON,
+		.ulcon	= ULCON,
-		.ufcon	     = UFCON,
+		.ufcon	= UFCON,
 	},
 };
 
 /* DM9000AEP 10/100 ethernet controller */
 
 static struct resource real6410_dm9k_resource[] = {
-        [0] = {
+	[0] = {
-                .start = S3C64XX_PA_XM0CSN1,
+		.start	= S3C64XX_PA_XM0CSN1,
-                .end   = S3C64XX_PA_XM0CSN1 + 1,
+		.end	= S3C64XX_PA_XM0CSN1 + 1,
-                .flags = IORESOURCE_MEM
+		.flags	= IORESOURCE_MEM
-        },
+	},
-        [1] = {
+	[1] = {
-                .start = S3C64XX_PA_XM0CSN1 + 4,
+		.start	= S3C64XX_PA_XM0CSN1 + 4,
-                .end   = S3C64XX_PA_XM0CSN1 + 5,
+		.end	= S3C64XX_PA_XM0CSN1 + 5,
-                .flags = IORESOURCE_MEM
+		.flags	= IORESOURCE_MEM
-        },
+	},
-        [2] = {
+	[2] = {
-                .start = S3C_EINT(7),
+		.start	= S3C_EINT(7),
-                .end   = S3C_EINT(7),
+		.end	= S3C_EINT(7),
-                .flags = IORESOURCE_IRQ,
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL
-        }
+	}
 };
 
 static struct dm9000_plat_data real6410_dm9k_pdata = {
-        .flags          = (DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM),
+	.flags		= (DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM),
 };
 
 static struct platform_device real6410_device_eth = {
-        .name           = "dm9000",
+	.name		= "dm9000",
-        .id             = -1,
+	.id		= -1,
-        .num_resources  = ARRAY_SIZE(real6410_dm9k_resource),
+	.num_resources	= ARRAY_SIZE(real6410_dm9k_resource),
-        .resource       = real6410_dm9k_resource,
+	.resource	= real6410_dm9k_resource,
-        .dev            = {
+	.dev		= {
-                .platform_data  = &real6410_dm9k_pdata,
+		.platform_data	= &real6410_dm9k_pdata,
-        },
+	},
 };
 
 static struct platform_device *real6410_devices[] __initdata = {
@@ -129,12 +129,12 @@ static void __init real6410_machine_init(void)
 	/* set timing for nCS1 suitable for ethernet chip */
 
 	__raw_writel((0 << S3C64XX_SROM_BCX__PMC__SHIFT) |
-			(6 << S3C64XX_SROM_BCX__TACP__SHIFT) |
+		(6 << S3C64XX_SROM_BCX__TACP__SHIFT) |
-			(4 << S3C64XX_SROM_BCX__TCAH__SHIFT) |
+		(4 << S3C64XX_SROM_BCX__TCAH__SHIFT) |
-			(1 << S3C64XX_SROM_BCX__TCOH__SHIFT) |
+		(1 << S3C64XX_SROM_BCX__TCOH__SHIFT) |
-			(13 << S3C64XX_SROM_BCX__TACC__SHIFT) |
+		(13 << S3C64XX_SROM_BCX__TACC__SHIFT) |
-			(4 << S3C64XX_SROM_BCX__TCOS__SHIFT) |
+		(4 << S3C64XX_SROM_BCX__TCOS__SHIFT) |
-			(0 << S3C64XX_SROM_BCX__TACS__SHIFT), S3C64XX_SROM_BC1);
+		(0 << S3C64XX_SROM_BCX__TACS__SHIFT), S3C64XX_SROM_BC1);
 
 	platform_add_devices(real6410_devices, ARRAY_SIZE(real6410_devices));
 }

arch/arm/mach-s5pv210/clock.c

@@ -280,6 +280,24 @@ static struct clk init_clocks_disable[] = {
 		.parent		= &clk_hclk_dsys.clk,
 		.enable		= s5pv210_clk_ip0_ctrl,
 		.ctrlbit	= (1<<29),
+	}, {
+		.name		= "fimc",
+		.id		= 0,
+		.parent		= &clk_hclk_dsys.clk,
+		.enable		= s5pv210_clk_ip0_ctrl,
+		.ctrlbit	= (1 << 24),
+	}, {
+		.name		= "fimc",
+		.id		= 1,
+		.parent		= &clk_hclk_dsys.clk,
+		.enable		= s5pv210_clk_ip0_ctrl,
+		.ctrlbit	= (1 << 25),
+	}, {
+		.name		= "fimc",
+		.id		= 2,
+		.parent		= &clk_hclk_dsys.clk,
+		.enable		= s5pv210_clk_ip0_ctrl,
+		.ctrlbit	= (1 << 26),
 	}, {
 		.name		= "otg",
 		.id		= -1,
@@ -357,7 +375,7 @@ static struct clk init_clocks_disable[] = {
 		.id		= 1,
 		.parent		= &clk_pclk_psys.clk,
 		.enable		= s5pv210_clk_ip3_ctrl,
-		.ctrlbit	= (1<<8),
+		.ctrlbit	= (1 << 10),
 	}, {
 		.name		= "i2c",
 		.id		= 2,

arch/arm/mach-s5pv210/cpu.c

@@ -47,7 +47,7 @@ static struct map_desc s5pv210_iodesc[] __initdata = {
 	{
 		.virtual	= (unsigned long)S5P_VA_SYSTIMER,
 		.pfn		= __phys_to_pfn(S5PV210_PA_SYSTIMER),
-		.length		= SZ_1M,
+		.length		= SZ_4K,
 		.type		= MT_DEVICE,
 	}, {
 		.virtual	= (unsigned long)VA_VIC2,

arch/arm/mach-shmobile/Makefile

@@ -3,7 +3,7 @@
 #
 
 # Common objects
-obj-y				:= timer.o console.o clock.o
+obj-y				:= timer.o console.o clock.o pm_runtime.o
 
 # CPU objects
 obj-$(CONFIG_ARCH_SH7367)	+= setup-sh7367.o clock-sh7367.o intc-sh7367.o

arch/arm/mach-shmobile/board-ap4evb.c

@@ -25,6 +25,7 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/mfd/sh_mobile_sdhi.h>
+#include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -39,6 +40,7 @@
 #include <linux/sh_clk.h>
 #include <linux/gpio.h>
 #include <linux/input.h>
+#include <linux/leds.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/usb/r8a66597.h>
 
@@ -307,6 +309,7 @@ static struct sh_mobile_sdhi_info sdhi1_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
 	.tmio_ocr_mask	= MMC_VDD_165_195,
+	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE,
 };
 
 static struct resource sdhi1_resources[] = {
@@ -558,7 +561,7 @@ static struct resource fsi_resources[] = {
 
 static struct platform_device fsi_device = {
 	.name		= "sh_fsi2",
-	.id		= 0,
+	.id		= -1,
 	.num_resources	= ARRAY_SIZE(fsi_resources),
 	.resource	= fsi_resources,
 	.dev	= {
@@ -650,7 +653,44 @@ static struct platform_device hdmi_device = {
 	},
 };
 
+static struct gpio_led ap4evb_leds[] = {
+	{
+		.name			= "led4",
+		.gpio			= GPIO_PORT185,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led2",
+		.gpio			= GPIO_PORT186,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led3",
+		.gpio			= GPIO_PORT187,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led1",
+		.gpio			= GPIO_PORT188,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	}
+};
+
+static struct gpio_led_platform_data ap4evb_leds_pdata = {
+	.num_leds = ARRAY_SIZE(ap4evb_leds),
+	.leds = ap4evb_leds,
+};
+
+static struct platform_device leds_device = {
+	.name = "leds-gpio",
+	.id = 0,
+	.dev = {
+		.platform_data  = &ap4evb_leds_pdata,
+	},
+};
+
 static struct platform_device *ap4evb_devices[] __initdata = {
+	&leds_device,
 	&nor_flash_device,
 	&smc911x_device,
 	&sdhi0_device,
@@ -840,20 +880,6 @@ static void __init ap4evb_init(void)
 	gpio_request(GPIO_FN_CS5A,	NULL);
 	gpio_request(GPIO_FN_IRQ6_39,	NULL);
 
-	/* enable LED 1 - 4 */
-	gpio_request(GPIO_PORT185, NULL);
-	gpio_request(GPIO_PORT186, NULL);
-	gpio_request(GPIO_PORT187, NULL);
-	gpio_request(GPIO_PORT188, NULL);
-	gpio_direction_output(GPIO_PORT185, 1);
-	gpio_direction_output(GPIO_PORT186, 1);
-	gpio_direction_output(GPIO_PORT187, 1);
-	gpio_direction_output(GPIO_PORT188, 1);
-	gpio_export(GPIO_PORT185, 0);
-	gpio_export(GPIO_PORT186, 0);
-	gpio_export(GPIO_PORT187, 0);
-	gpio_export(GPIO_PORT188, 0);
-
 	/* enable Debug switch (S6) */
 	gpio_request(GPIO_PORT32, NULL);
 	gpio_request(GPIO_PORT33, NULL);

arch/arm/mach-shmobile/clock-sh7372.c

@@ -286,7 +286,6 @@ static struct clk_ops pllc2_clk_ops = {
 
 struct clk pllc2_clk = {
 	.ops		= &pllc2_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
 	.parent		= &extal1_div2_clk,
 	.freq_table	= pllc2_freq_table,
 	.parent_table	= pllc2_parent,
@@ -395,7 +394,7 @@ static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = {
 
 enum { MSTP001,
        MSTP131, MSTP130,
-       MSTP129, MSTP128,
+       MSTP129, MSTP128, MSTP127, MSTP126,
        MSTP118, MSTP117, MSTP116,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
@@ -413,6 +412,8 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */
 	[MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */
 	[MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* VEU0 */
+	[MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU */
+	[MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2 */
 	[MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX */
 	[MSTP117] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 17, 0), /* LCDC1 */
 	[MSTP116] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 16, 0), /* IIC0 */
@@ -428,7 +429,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */
 	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
 	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
-	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, CLK_ENABLE_ON_INIT), /* FSIA */
+	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSIA */
 	[MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */
 	[MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */
 	[MSTP314] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 14, 0), /* SDHI0 */
@@ -498,6 +499,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.1", &mstp_clks[MSTP128]), /* VEU0 */
+	CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU */
+	CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2 */
 	CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1", &mstp_clks[MSTP117]), /* LCDC1 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* IIC0 */

arch/arm/mach-shmobile/clock.c

@@ -1,8 +1,10 @@
 /*
- * SH-Mobile Timer
+ * SH-Mobile Clock Framework
  *
  * Copyright (C) 2010  Magnus Damm
  *
+ * Used together with arch/arm/common/clkdev.c and drivers/sh/clk.c.
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; version 2 of the License.

arch/arm/mach-shmobile/pm_runtime.c

@@ -0,0 +1,169 @@
+/*
+ * arch/arm/mach-shmobile/pm_runtime.c
+ *
+ * Runtime PM support code for SuperH Mobile ARM
+ *
+ *  Copyright (C) 2009-2010 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/sh_clk.h>
+#include <linux/bitmap.h>
+
+#ifdef CONFIG_PM_RUNTIME
+#define BIT_ONCE 0
+#define BIT_ACTIVE 1
+#define BIT_CLK_ENABLED 2
+
+struct pm_runtime_data {
+	unsigned long flags;
+	struct clk *clk;
+};
+
+static void __devres_release(struct device *dev, void *res)
+{
+	struct pm_runtime_data *prd = res;
+
+	dev_dbg(dev, "__devres_release()\n");
+
+	if (test_bit(BIT_CLK_ENABLED, &prd->flags))
+		clk_disable(prd->clk);
+
+	if (test_bit(BIT_ACTIVE, &prd->flags))
+		clk_put(prd->clk);
+}
+
+static struct pm_runtime_data *__to_prd(struct device *dev)
+{
+	return devres_find(dev, __devres_release, NULL, NULL);
+}
+
+static void platform_pm_runtime_init(struct device *dev,
+				     struct pm_runtime_data *prd)
+{
+	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) {
+		prd->clk = clk_get(dev, NULL);
+		if (!IS_ERR(prd->clk)) {
+			set_bit(BIT_ACTIVE, &prd->flags);
+			dev_info(dev, "clocks managed by runtime pm\n");
+		}
+	}
+}
+
+static void platform_pm_runtime_bug(struct device *dev,
+				    struct pm_runtime_data *prd)
+{
+	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags))
+		dev_err(dev, "runtime pm suspend before resume\n");
+}
+
+int platform_pm_runtime_suspend(struct device *dev)
+{
+	struct pm_runtime_data *prd = __to_prd(dev);
+
+	dev_dbg(dev, "platform_pm_runtime_suspend()\n");
+
+	platform_pm_runtime_bug(dev, prd);
+
+	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
+		clk_disable(prd->clk);
+		clear_bit(BIT_CLK_ENABLED, &prd->flags);
+	}
+
+	return 0;
+}
+
+int platform_pm_runtime_resume(struct device *dev)
+{
+	struct pm_runtime_data *prd = __to_prd(dev);
+
+	dev_dbg(dev, "platform_pm_runtime_resume()\n");
+
+	platform_pm_runtime_init(dev, prd);
+
+	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
+		clk_enable(prd->clk);
+		set_bit(BIT_CLK_ENABLED, &prd->flags);
+	}
+
+	return 0;
+}
+
+int platform_pm_runtime_idle(struct device *dev)
+{
+	/* suspend synchronously to disable clocks immediately */
+	return pm_runtime_suspend(dev);
+}
+
+static int platform_bus_notify(struct notifier_block *nb,
+			       unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct pm_runtime_data *prd;
+
+	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
+
+	if (action == BUS_NOTIFY_BIND_DRIVER) {
+		prd = devres_alloc(__devres_release, sizeof(*prd), GFP_KERNEL);
+		if (prd)
+			devres_add(dev, prd);
+		else
+			dev_err(dev, "unable to alloc memory for runtime pm\n");
+	}
+
+	return 0;
+}
+
+#else /* CONFIG_PM_RUNTIME */
+
+static int platform_bus_notify(struct notifier_block *nb,
+			       unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct clk *clk;
+
+	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
+
+	switch (action) {
+	case BUS_NOTIFY_BIND_DRIVER:
+		clk = clk_get(dev, NULL);
+		if (!IS_ERR(clk)) {
+			clk_enable(clk);
+			clk_put(clk);
+			dev_info(dev, "runtime pm disabled, clock forced on\n");
+		}
+		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		clk = clk_get(dev, NULL);
+		if (!IS_ERR(clk)) {
+			clk_disable(clk);
+			clk_put(clk);
+			dev_info(dev, "runtime pm disabled, clock forced off\n");
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_PM_RUNTIME */
+
+static struct notifier_block platform_bus_notifier = {
+	.notifier_call = platform_bus_notify
+};
+
+static int __init sh_pm_runtime_init(void)
+{
+	bus_register_notifier(&platform_bus_type, &platform_bus_notifier);
+	return 0;
+}
+core_initcall(sh_pm_runtime_init);

arch/arm/mach-u300/include/mach/gpio.h

@@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value);
 extern int gpio_get_value(unsigned gpio);
 extern void gpio_set_value(unsigned gpio, int value);
 
+#define gpio_get_value_cansleep gpio_get_value
+#define gpio_set_value_cansleep gpio_set_value
+
 /* wrappers to sleep-enable the previous two functions */
 static inline unsigned gpio_to_irq(unsigned gpio)
 {

arch/arm/mach-vexpress/ct-ca9x4.c

@@ -227,7 +227,13 @@ static void ct_ca9x4_init(void)
 	int i;
 
 #ifdef CONFIG_CACHE_L2X0
-	l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff);
+	void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC);
+
+	/* set RAM latencies to 1 cycle for this core tile. */
+	writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
+	writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
 #endif
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));

arch/arm/mm/Kconfig

@@ -398,7 +398,7 @@ config CPU_V6
 # ARMv6k
 config CPU_32v6K
 	bool "Support ARM V6K processor extensions" if !SMP
-	depends on CPU_V6
+	depends on CPU_V6 || CPU_V7
 	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
 	help
 	  Say Y here if your ARMv6 processor supports the 'K' extension.

arch/arm/mm/alignment.c

@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (ai_usermode & UM_SIGNAL)
 		force_sig(SIGBUS, current);
-	else
+	else {
-		set_cr(cr_no_alignment);
+		/*
+		 * We're about to disable the alignment trap and return to
+		 * user space.  But if an interrupt occurs before actually
+		 * reaching user space, then the IRQ vector entry code will
+		 * notice that we were still in kernel space and therefore
+		 * the alignment trap won't be re-enabled in that case as it
+		 * is presumed to be always on from kernel space.
+		 * Let's prevent that race by disabling interrupts here (they
+		 * are disabled on the way back to user space anyway in
+		 * entry-common.S) and disable the alignment trap only if
+		 * there is no work pending for this thread.
+		 */
+		raw_local_irq_disable();
+		if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+			set_cr(cr_no_alignment);
+	}
 
 	return 0;
 }

arch/arm/mm/dma-mapping.c

@@ -229,6 +229,8 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 			}
 		} while (size -= PAGE_SIZE);
 
+		dsb();
+
 		return (void *)c->vm_start;
 	}
 	return NULL;

arch/arm/mm/mmu.c

@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_USER,
 	},
 	[MT_MEMORY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_USER | L_PTE_EXEC,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_NONCACHED] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_USER | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -411,9 +418,12 @@ static void __init build_mem_type_table(void)
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
-	if (arch_is_coherent() && cpu_is_xsc3())
+	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+	}
 	/*
 	 * ARMv6 and above have extended page tables.
 	 */
@@ -438,7 +448,9 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 #endif
 	}
 
@@ -475,6 +487,8 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
 	switch (cp->pmd) {
@@ -498,6 +512,19 @@ static void __init build_mem_type_table(void)
 	}
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+			      unsigned long size, pgprot_t vma_prot)
+{
+	if (!pfn_valid(pfn))
+		return pgprot_noncached(vma_prot);
+	else if (file->f_flags & O_SYNC)
+		return pgprot_writecombine(vma_prot);
+	return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)

arch/arm/mm/proc-v7.S

@@ -186,13 +186,14 @@ cpu_v7_name:
  *	It is assumed that:
  *	- cache type register is implemented
  */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
 	mrc	p15, 0, r0, c1, c0, 1
 	tst	r0, #(1 << 6)			@ SMP/nAMP mode enabled?
 	orreq	r0, r0, #(1 << 6) | (1 << 0)	@ Enable SMP/nAMP mode and
 	mcreq	p15, 0, r0, c1, c0, 1		@ TLB ops broadcasting
 #endif
+__v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
 	bl	v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
 	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
 	and	r10, r0, #0xff000000		@ ARM?
 	teq	r10, #0x41000000
-	bne	2f
+	bne	3f
 	and	r5, r0, #0x00f00000		@ variant
 	and	r6, r0, #0x0000000f		@ revision
-	orr	r0, r6, r5, lsr #20-4		@ combine variant and revision
+	orr	r6, r6, r5, lsr #20-4		@ combine variant and revision
+	ubfx	r0, r0, #4, #12			@ primary part number
 
+	/* Cortex-A8 Errata */
+	ldr	r10, =0x00000c08		@ Cortex-A8 primary part number
+	teq	r0, r10
+	bne	2f
 #ifdef CONFIG_ARM_ERRATA_430973
 	teq	r5, #0x00100000			@ only present in r1p*
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
@@ -213,21 +219,42 @@ __v7_setup:
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
 	orreq	r10, r10, #(1 << 5)		@ set L1NEON to 1
 	orreq	r10, r10, #(1 << 9)		@ set PLDNOP to 1
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
 	tsteq	r10, #1 << 22
 	orreq	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
 	mcreq	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
 #endif
+	b	3f
 
-2:	mov	r10, #0
+	/* Cortex-A9 Errata */
+2:	ldr	r10, =0x00000c09		@ Cortex-A9 primary part number
+	teq	r0, r10
+	bne	3f
+#ifdef CONFIG_ARM_ERRATA_742230
+	cmp	r6, #0x22			@ only present up to r2p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 4		@ set bit #4
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+	teq	r6, #0x20			@ present in r2p0
+	teqne	r6, #0x21			@ present in r2p1
+	teqne	r6, #0x22			@ present in r2p2
+	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orreq	r10, r10, #1 << 12		@ set bit #12
+	orreq	r10, r10, #1 << 22		@ set bit #22
+	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+
+3:	mov	r10, #0
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 #endif
@@ -323,6 +350,29 @@ cpu_elf_name:
 
 	.section ".proc.info.init", #alloc, #execinstr
 
+	.type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+	.long	0x410fc090		@ Required ID value
+	.long	0xff0ffff0		@ Mask for ID
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_XN | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__v7_ca9mp_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	cpu_v7_name
+	.long	v7_processor_functions
+	.long	v7wbi_tlb_fns
+	.long	v6_user_fns
+	.long	v7_cache_fns
+	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
 	/*
 	 * Match any ARMv7 processor core.
 	 */

arch/arm/oprofile/common.c

@@ -102,6 +102,7 @@ static int op_create_counter(int cpu, int event)
 	if (IS_ERR(pevent)) {
 		ret = PTR_ERR(pevent);
 	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		perf_event_release_kernel(pevent);
 		pr_warning("oprofile: failed to enable event %d "
 				"on CPU %d\n", event, cpu);
 		ret = -EBUSY;
@@ -365,6 +366,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ret = init_driverfs();
 	if (ret) {
 		kfree(counter_config);
+		counter_config = NULL;
 		return ret;
 	}
 
@@ -402,7 +404,6 @@ void oprofile_arch_exit(void)
 	struct perf_event *event;
 
 	if (*perf_events) {
-		exit_driverfs();
 		for_each_possible_cpu(cpu) {
 			for (id = 0; id < perf_num_counters; ++id) {
 				event = perf_events[cpu][id];
@@ -413,8 +414,10 @@ void oprofile_arch_exit(void)
 		}
 	}
 
-	if (counter_config)
+	if (counter_config) {
 		kfree(counter_config);
+		exit_driverfs();
+	}
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)

arch/arm/plat-mxc/Kconfig

@@ -43,6 +43,7 @@ config ARCH_MXC91231
 config ARCH_MX5
 	bool "MX5-based"
 	select CPU_V7
+	select ARM_L1_CACHE_SHIFT_6
 	help
 	  This enables support for systems based on the Freescale i.MX51 family
 

arch/arm/plat-mxc/include/mach/eukrea-baseboards.h

@@ -37,9 +37,9 @@
  * mach-mx5/eukrea_mbimx51-baseboard.c for cpuimx51
  */
 
-extern void eukrea_mbimx25_baseboard_init(void);
+extern void eukrea_mbimxsd25_baseboard_init(void);
 extern void eukrea_mbimx27_baseboard_init(void);
-extern void eukrea_mbimx35_baseboard_init(void);
+extern void eukrea_mbimxsd35_baseboard_init(void);
 extern void eukrea_mbimx51_baseboard_init(void);
 
 #endif

arch/arm/plat-mxc/tzic.c

@@ -164,8 +164,9 @@ int tzic_enable_wake(int is_idle)
 		return -EAGAIN;
 
 	for (i = 0; i < 4; i++) {
-		v = is_idle ? __raw_readl(TZIC_ENSET0(i)) : wakeup_intr[i];
+		v = is_idle ? __raw_readl(tzic_base + TZIC_ENSET0(i)) :
-		__raw_writel(v, TZIC_WAKEUP0(i));
+			wakeup_intr[i];
+		__raw_writel(v, tzic_base + TZIC_WAKEUP0(i));
 	}
 
 	return 0;

arch/arm/plat-nomadik/timer.c

@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/mach-nomadik/timer.c
+ *  linux/arch/arm/plat-nomadik/timer.c
  *
  * Copyright (C) 2008 STMicroelectronics
  * Copyright (C) 2010 Alessandro Rubini
@@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode,
 		cr = readl(mtu_base + MTU_CR(1));
 		writel(0, mtu_base + MTU_LR(1));
 		writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1));
-		writel(0x2, mtu_base + MTU_IMSC);
+		writel(1 << 1, mtu_base + MTU_IMSC);
 		break;
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	case CLOCK_EVT_MODE_UNUSED:
@@ -131,25 +131,23 @@ void __init nmdk_timer_init(void)
 {
 	unsigned long rate;
 	struct clk *clk0;
-	struct clk *clk1;
+	u32 cr = MTU_CRn_32BITS;
-	u32 cr;
 
 	clk0 = clk_get_sys("mtu0", NULL);
 	BUG_ON(IS_ERR(clk0));
 
-	clk1 = clk_get_sys("mtu1", NULL);
-	BUG_ON(IS_ERR(clk1));
-
 	clk_enable(clk0);
-	clk_enable(clk1);
 
 	/*
-	 * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500:
+	 * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
-	 * use a divide-by-16 counter if it's more than 16MHz
+	 * for ux500.
+	 * Use a divide-by-16 counter if the tick rate is more than 32MHz.
+	 * At 32 MHz, the timer (with 32 bit counter) can be programmed
+	 * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
+	 * with 16 gives too low timer resolution.
 	 */
-	cr = MTU_CRn_32BITS;;
 	rate = clk_get_rate(clk0);
-	if (rate > 16 << 20) {
+	if (rate > 32000000) {
 		rate /= 16;
 		cr |= MTU_CRn_PRESCALE_16;
 	} else {
@@ -170,15 +168,8 @@ void __init nmdk_timer_init(void)
 		pr_err("timer: failed to initialize clock source %s\n",
 		       nmdk_clksrc.name);
 
-	/* Timer 1 is used for events, fix according to rate */
+	/* Timer 1 is used for events */
-	cr = MTU_CRn_32BITS;
+
-	rate = clk_get_rate(clk1);
-	if (rate > 16 << 20) {
-		rate /= 16;
-		cr |= MTU_CRn_PRESCALE_16;
-	} else {
-		cr |= MTU_CRn_PRESCALE_1;
-	}
 	clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE);
 
 	writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */

arch/arm/plat-omap/Kconfig

@@ -33,7 +33,7 @@ config OMAP_DEBUG_DEVICES
 config OMAP_DEBUG_LEDS
 	bool
 	depends on OMAP_DEBUG_DEVICES
-	default y if LEDS
+	default y if LEDS_CLASS
 
 config OMAP_RESET_CLOCKS
 	bool "Reset unused clocks during boot"

arch/arm/plat-omap/mcbsp.c

@@ -156,7 +156,7 @@ static irqreturn_t omap_mcbsp_rx_irq_handler(int irq, void *dev_id)
 		/* Writing zero to RSYNC_ERR clears the IRQ */
 		MCBSP_WRITE(mcbsp_rx, SPCR1, MCBSP_READ_CACHE(mcbsp_rx, SPCR1));
 	} else {
-		complete(&mcbsp_rx->tx_irq_completion);
+		complete(&mcbsp_rx->rx_irq_completion);
 	}
 
 	return IRQ_HANDLED;

arch/arm/plat-omap/sram.c

@@ -220,20 +220,7 @@ void __init omap_map_sram(void)
 	if (omap_sram_size == 0)
 		return;
 
-	if (cpu_is_omap24xx()) {
-		omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA;
-
-		base = OMAP2_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-	}
-
 	if (cpu_is_omap34xx()) {
-		omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA;
-		base = OMAP3_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-
 		/*
 		 * SRAM must be marked as non-cached on OMAP3 since the
 		 * CORE DPLL M2 divider change code (in SRAM) runs with the
@@ -244,13 +231,11 @@ void __init omap_map_sram(void)
 		omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED;
 	}
 
-	if (cpu_is_omap44xx()) {
+	omap_sram_io_desc[0].virtual = omap_sram_base;
-		omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA;
+	base = omap_sram_start;
-		base = OMAP4_SRAM_PA;
+	base = ROUND_DOWN(base, PAGE_SIZE);
-		base = ROUND_DOWN(base, PAGE_SIZE);
+	omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
+	omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
-	}
-	omap_sram_io_desc[0].length = 1024 * 1024;	/* Use section desc */
 	iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
 
 	printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",

arch/arm/plat-pxa/pwm.c

@@ -176,7 +176,7 @@ static inline void __add_pwm(struct pwm_device *pwm)
 
 static int __devinit pwm_probe(struct platform_device *pdev)
 {
-	struct platform_device_id *id = platform_get_device_id(pdev);
+	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct pwm_device *pwm, *secondary = NULL;
 	struct resource *r;
 	int ret = 0;

arch/arm/plat-s5p/dev-fimc0.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
@@ -18,7 +19,7 @@
 static struct resource s5p_fimc0_resource[] = {
 	[0] = {
 		.start	= S5P_PA_FIMC0,
-		.end	= S5P_PA_FIMC0 + SZ_1M - 1,
+		.end	= S5P_PA_FIMC0 + SZ_4K - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
@@ -28,9 +29,15 @@ static struct resource s5p_fimc0_resource[] = {
 	},
 };
 
+static u64 s5p_fimc0_dma_mask = DMA_BIT_MASK(32);
+
 struct platform_device s5p_device_fimc0 = {
 	.name		= "s5p-fimc",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(s5p_fimc0_resource),
 	.resource	= s5p_fimc0_resource,
+	.dev		= {
+		.dma_mask		= &s5p_fimc0_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
 };

arch/arm/plat-s5p/dev-fimc1.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
@@ -18,7 +19,7 @@
 static struct resource s5p_fimc1_resource[] = {
 	[0] = {
 		.start	= S5P_PA_FIMC1,
-		.end	= S5P_PA_FIMC1 + SZ_1M - 1,
+		.end	= S5P_PA_FIMC1 + SZ_4K - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
@@ -28,9 +29,15 @@ static struct resource s5p_fimc1_resource[] = {
 	},
 };
 
+static u64 s5p_fimc1_dma_mask = DMA_BIT_MASK(32);
+
 struct platform_device s5p_device_fimc1 = {
 	.name		= "s5p-fimc",
 	.id		= 1,
 	.num_resources	= ARRAY_SIZE(s5p_fimc1_resource),
 	.resource	= s5p_fimc1_resource,
+	.dev		= {
+		.dma_mask		= &s5p_fimc1_dma_mask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
 };