Merge branch 'hid-suspend' into picolcd

Documentation/ABI/testing/sysfs-bus-usb

@@ -160,7 +160,7 @@ Description:
 		match the driver to the device.  For example:
 		# echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
 
-What:		/sys/bus/usb/device/.../avoid_reset
+What:		/sys/bus/usb/device/.../avoid_reset_quirk
 Date:		December 2009
 Contact:	Oliver Neukum <oliver@neukum.org>
 Description:

Documentation/cgroups/memory.txt

@@ -340,7 +340,7 @@ Note:
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroups' swapiness can't be changed.
+  Following cgroups' swappiness can't be changed.
   - root cgroup (uses /proc/sys/vm/swappiness).
   - a cgroup which uses hierarchy and it has child cgroup.
   - a cgroup which uses hierarchy and not the root of hierarchy.

Documentation/circular-buffers.txt

@@ -0,0 +1,234 @@
+			       ================
+			       CIRCULAR BUFFERS
+			       ================
+
+By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+
+Linux provides a number of features that can be used to implement circular
+buffering.  There are two sets of such features:
+
+ (1) Convenience functions for determining information about power-of-2 sized
+     buffers.
+
+ (2) Memory barriers for when the producer and the consumer of objects in the
+     buffer don't want to share a lock.
+
+To use these facilities, as discussed below, there needs to be just one
+producer and just one consumer.  It is possible to handle multiple producers by
+serialising them, and to handle multiple consumers by serialising them.
+
+
+Contents:
+
+ (*) What is a circular buffer?
+
+ (*) Measuring power-of-2 buffers.
+
+ (*) Using memory barriers with circular buffers.
+     - The producer.
+     - The consumer.
+
+
+==========================
+WHAT IS A CIRCULAR BUFFER?
+==========================
+
+First of all, what is a circular buffer?  A circular buffer is a buffer of
+fixed, finite size into which there are two indices:
+
+ (1) A 'head' index - the point at which the producer inserts items into the
+     buffer.
+
+ (2) A 'tail' index - the point at which the consumer finds the next item in
+     the buffer.
+
+Typically when the tail pointer is equal to the head pointer, the buffer is
+empty; and the buffer is full when the head pointer is one less than the tail
+pointer.
+
+The head index is incremented when items are added, and the tail index when
+items are removed.  The tail index should never jump the head index, and both
+indices should be wrapped to 0 when they reach the end of the buffer, thus
+allowing an infinite amount of data to flow through the buffer.
+
+Typically, items will all be of the same unit size, but this isn't strictly
+required to use the techniques below.  The indices can be increased by more
+than 1 if multiple items or variable-sized items are to be included in the
+buffer, provided that neither index overtakes the other.  The implementer must
+be careful, however, as a region more than one unit in size may wrap the end of
+the buffer and be broken into two segments.
+
+
+============================
+MEASURING POWER-OF-2 BUFFERS
+============================
+
+Calculation of the occupancy or the remaining capacity of an arbitrarily sized
+circular buffer would normally be a slow operation, requiring the use of a
+modulus (divide) instruction.  However, if the buffer is of a power-of-2 size,
+then a much quicker bitwise-AND instruction can be used instead.
+
+Linux provides a set of macros for handling power-of-2 circular buffers.  These
+can be made use of by:
+
+	#include <linux/circ_buf.h>
+
+The macros are:
+
+ (*) Measure the remaining capacity of a buffer:
+
+	CIRC_SPACE(head_index, tail_index, buffer_size);
+
+     This returns the amount of space left in the buffer[1] into which items
+     can be inserted.
+
+
+ (*) Measure the maximum consecutive immediate space in a buffer:
+
+	CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the amount of consecutive space left in the buffer[1] into
+     which items can be immediately inserted without having to wrap back to the
+     beginning of the buffer.
+
+
+ (*) Measure the occupancy of a buffer:
+
+	CIRC_CNT(head_index, tail_index, buffer_size);
+
+     This returns the number of items currently occupying a buffer[2].
+
+
+ (*) Measure the non-wrapping occupancy of a buffer:
+
+	CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the number of consecutive items[2] that can be extracted from
+     the buffer without having to wrap back to the beginning of the buffer.
+
+
+Each of these macros will nominally return a value between 0 and buffer_size-1,
+however:
+
+ [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+     they will return a lower bound as the producer controls the head index,
+     but the consumer may still be depleting the buffer on another CPU and
+     moving the tail index.
+
+     To the consumer it will show an upper bound as the producer may be busy
+     depleting the space.
+
+ [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+     will return a lower bound as the consumer controls the tail index, but the
+     producer may still be filling the buffer on another CPU and moving the
+     head index.
+
+     To the producer it will show an upper bound as the consumer may be busy
+     emptying the buffer.
+
+ [3] To a third party, the order in which the writes to the indices by the
+     producer and consumer become visible cannot be guaranteed as they are
+     independent and may be made on different CPUs - so the result in such a
+     situation will merely be a guess, and may even be negative.
+
+
+===========================================
+USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+===========================================
+
+By using memory barriers in conjunction with circular buffers, you can avoid
+the need to:
+
+ (1) use a single lock to govern access to both ends of the buffer, thus
+     allowing the buffer to be filled and emptied at the same time; and
+
+ (2) use atomic counter operations.
+
+There are two sides to this: the producer that fills the buffer, and the
+consumer that empties it.  Only one thing should be filling a buffer at any one
+time, and only one thing should be emptying a buffer at any one time, but the
+two sides can operate simultaneously.
+
+
+THE PRODUCER
+------------
+
+The producer will look something like this:
+
+	spin_lock(&producer_lock);
+
+	unsigned long head = buffer->head;
+	unsigned long tail = ACCESS_ONCE(buffer->tail);
+
+	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+		/* insert one item into the buffer */
+		struct item *item = buffer[head];
+
+		produce_item(item);
+
+		smp_wmb(); /* commit the item before incrementing the head */
+
+		buffer->head = (head + 1) & (buffer->size - 1);
+
+		/* wake_up() will make sure that the head is committed before
+		 * waking anyone up */
+		wake_up(consumer);
+	}
+
+	spin_unlock(&producer_lock);
+
+This will instruct the CPU that the contents of the new item must be written
+before the head index makes it available to the consumer and then instructs the
+CPU that the revised head index must be written before the consumer is woken.
+
+Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+is used must guarantee a (write) memory barrier between the update of the head
+index and the change of state of the consumer, if a change of state occurs.
+
+
+THE CONSUMER
+------------
+
+The consumer will look something like this:
+
+	spin_lock(&consumer_lock);
+
+	unsigned long head = ACCESS_ONCE(buffer->head);
+	unsigned long tail = buffer->tail;
+
+	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+		/* read index before reading contents at that index */
+		smp_read_barrier_depends();
+
+		/* extract one item from the buffer */
+		struct item *item = buffer[tail];
+
+		consume_item(item);
+
+		smp_mb(); /* finish reading descriptor before incrementing tail */
+
+		buffer->tail = (tail + 1) & (buffer->size - 1);
+	}
+
+	spin_unlock(&consumer_lock);
+
+This will instruct the CPU to make sure the index is up to date before reading
+the new item, and then it shall make sure the CPU has finished reading the item
+before it writes the new tail pointer, which will erase the item.
+
+
+Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+This prevents the compiler from discarding and reloading its cached value -
+which some compilers will do across smp_read_barrier_depends().  This isn't
+strictly needed if you can be sure that the opposition index will _only_ be
+used the once.
+
+
+===============
+FURTHER READING
+===============
+
+See also Documentation/memory-barriers.txt for a description of Linux's memory
+barrier facilities.

Documentation/connector/cn_test.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <linux/timer.h>
 
 #include <linux/connector.h>

Documentation/filesystems/00-INDEX

@@ -16,6 +16,8 @@ befs.txt
 	- information about the BeOS filesystem for Linux.
 bfs.txt
 	- info for the SCO UnixWare Boot Filesystem (BFS).
+ceph.txt
+	- info for the Ceph Distributed File System
 cifs.txt
 	- description of the CIFS filesystem.
 coda.txt

Documentation/filesystems/9p.txt

@@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9)
 
 	mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
 
+For server running on QEMU host with virtio transport:
+
+	mount -t 9p -o trans=virtio <mount_tag> /mnt/9
+
+where mount_tag is the tag associated by the server to each of the exported
+mount points. Each 9P export is seen by the client as a virtio device with an
+associated "mount_tag" property. Available mount tags can be
+seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
+
 OPTIONS
 =======
 
@@ -47,7 +56,7 @@ OPTIONS
 			fd   	- used passed file descriptors for connection
                                 (see rfdno and wfdno)
 			virtio	- connect to the next virtio channel available
-				(from lguest or KVM with trans_virtio module)
+				(from QEMU with trans_virtio module)
 			rdma	- connect to a specified RDMA channel
 
   uname=name	user name to attempt mount as on the remote server.  The
@@ -85,7 +94,12 @@ OPTIONS
 
   port=n	port to connect to on the remote server
 
-  noextend	force legacy mode (no 9p2000.u semantics)
+  noextend	force legacy mode (no 9p2000.u or 9p2000.L semantics)
+
+  version=name	Select 9P protocol version. Valid options are:
+			9p2000          - Legacy mode (same as noextend)
+			9p2000.u        - Use 9P2000.u protocol
+			9p2000.L        - Use 9P2000.L protocol
 
   dfltuid	attempt to mount as a particular uid
 

Documentation/filesystems/ceph.txt

@@ -0,0 +1,140 @@
+Ceph Distributed File System
+============================
+
+Ceph is a distributed network file system designed to provide good
+performance, reliability, and scalability.
+
+Basic features include:
+
+ * POSIX semantics
+ * Seamless scaling from 1 to many thousands of nodes
+ * High availability and reliability.  No single point of failure.
+ * N-way replication of data across storage nodes
+ * Fast recovery from node failures
+ * Automatic rebalancing of data on node addition/removal
+ * Easy deployment: most FS components are userspace daemons
+
+Also,
+ * Flexible snapshots (on any directory)
+ * Recursive accounting (nested files, directories, bytes)
+
+In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
+on symmetric access by all clients to shared block devices, Ceph
+separates data and metadata management into independent server
+clusters, similar to Lustre.  Unlike Lustre, however, metadata and
+storage nodes run entirely as user space daemons.  Storage nodes
+utilize btrfs to store data objects, leveraging its advanced features
+(checksumming, metadata replication, etc.).  File data is striped
+across storage nodes in large chunks to distribute workload and
+facilitate high throughputs.  When storage nodes fail, data is
+re-replicated in a distributed fashion by the storage nodes themselves
+(with some minimal coordination from a cluster monitor), making the
+system extremely efficient and scalable.
+
+Metadata servers effectively form a large, consistent, distributed
+in-memory cache above the file namespace that is extremely scalable,
+dynamically redistributes metadata in response to workload changes,
+and can tolerate arbitrary (well, non-Byzantine) node failures.  The
+metadata server takes a somewhat unconventional approach to metadata
+storage to significantly improve performance for common workloads.  In
+particular, inodes with only a single link are embedded in
+directories, allowing entire directories of dentries and inodes to be
+loaded into its cache with a single I/O operation.  The contents of
+extremely large directories can be fragmented and managed by
+independent metadata servers, allowing scalable concurrent access.
+
+The system offers automatic data rebalancing/migration when scaling
+from a small cluster of just a few nodes to many hundreds, without
+requiring an administrator carve the data set into static volumes or
+go through the tedious process of migrating data between servers.
+When the file system approaches full, new nodes can be easily added
+and things will "just work."
+
+Ceph includes flexible snapshot mechanism that allows a user to create
+a snapshot on any subdirectory (and its nested contents) in the
+system.  Snapshot creation and deletion are as simple as 'mkdir
+.snap/foo' and 'rmdir .snap/foo'.
+
+Ceph also provides some recursive accounting on directories for nested
+files and bytes.  That is, a 'getfattr -d foo' on any directory in the
+system will reveal the total number of nested regular files and
+subdirectories, and a summation of all nested file sizes.  This makes
+the identification of large disk space consumers relatively quick, as
+no 'du' or similar recursive scan of the file system is required.
+
+
+Mount Syntax
+============
+
+The basic mount syntax is:
+
+ # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+
+You only need to specify a single monitor, as the client will get the
+full list when it connects.  (However, if the monitor you specify
+happens to be down, the mount won't succeed.)  The port can be left
+off if the monitor is using the default.  So if the monitor is at
+1.2.3.4,
+
+ # mount -t ceph 1.2.3.4:/ /mnt/ceph
+
+is sufficient.  If /sbin/mount.ceph is installed, a hostname can be
+used instead of an IP address.
+
+
+
+Mount Options
+=============
+
+  ip=A.B.C.D[:N]
+	Specify the IP and/or port the client should bind to locally.
+	There is normally not much reason to do this.  If the IP is not
+	specified, the client's IP address is determined by looking at the
+	address it's connection to the monitor originates from.
+
+  wsize=X
+	Specify the maximum write size in bytes.  By default there is no
+	maximum.  Ceph will normally size writes based on the file stripe
+	size.
+
+  rsize=X
+	Specify the maximum readahead.
+
+  mount_timeout=X
+	Specify the timeout value for mount (in seconds), in the case
+	of a non-responsive Ceph file system.  The default is 30
+	seconds.
+
+  rbytes
+	When stat() is called on a directory, set st_size to 'rbytes',
+	the summation of file sizes over all files nested beneath that
+	directory.  This is the default.
+
+  norbytes
+	When stat() is called on a directory, set st_size to the
+	number of entries in that directory.
+
+  nocrc
+	Disable CRC32C calculation for data writes.  If set, the storage node
+	must rely on TCP's error correction to detect data corruption
+	in the data payload.
+
+  noasyncreaddir
+	Disable client's use its local cache to satisfy	readdir
+	requests.  (This does not change correctness; the client uses
+	cached metadata only when a lease or capability ensures it is
+	valid.)
+
+
+More Information
+================
+
+For more information on Ceph, see the home page at
+	http://ceph.newdream.net/
+
+The Linux kernel client source tree is available at
+	git://ceph.newdream.net/git/ceph-client.git
+	git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+
+and the source for the full system is at
+	git://ceph.newdream.net/git/ceph.git

Documentation/filesystems/tmpfs.txt

@@ -82,11 +82,13 @@ tmpfs has a mount option to set the NUMA memory allocation policy for
 all files in that instance (if CONFIG_NUMA is enabled) - which can be
 adjusted on the fly via 'mount -o remount ...'
 
-mpol=default             prefers to allocate memory from the local node
+mpol=default             use the process allocation policy
+                         (see set_mempolicy(2))
 mpol=prefer:Node         prefers to allocate memory from the given Node
 mpol=bind:NodeList       allocates memory only from nodes in NodeList
 mpol=interleave          prefers to allocate from each node in turn
 mpol=interleave:NodeList allocates from each node of NodeList in turn
+mpol=local		 prefers to allocate memory from the local node
 
 NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
@@ -134,3 +136,5 @@ Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
    Hugh Dickins, 4 June 2007
+Updated:
+   KOSAKI Motohiro, 16 Mar 2010

Documentation/ioctl/ioctl-number.txt

@@ -291,6 +291,7 @@ Code  Seq#(hex)	Include File		Comments
 0x92	00-0F	drivers/usb/mon/mon_bin.c
 0x93	60-7F	linux/auto_fs.h
 0x94	all	fs/btrfs/ioctl.h
+0x97	00-7F	fs/ceph/ioctl.h		Ceph file system
 0x99	00-0F				537-Addinboard driver
 					<mailto:buk@buks.ipn.de>
 0xA0	all	linux/sdp/sdp.h		Industrial Device Project

Documentation/kobject.txt

@@ -59,37 +59,56 @@ nice to have in other objects.  The C language does not allow for the
 direct expression of inheritance, so other techniques - such as structure
 embedding - must be used.
 
-So, for example, the UIO code has a structure that defines the memory
-region associated with a uio device:
+(As an aside, for those familiar with the kernel linked list implementation,
+this is analogous as to how "list_head" structs are rarely useful on
+their own, but are invariably found embedded in the larger objects of
+interest.)
 
-struct uio_mem {
+So, for example, the UIO code in drivers/uio/uio.c has a structure that
+defines the memory region associated with a uio device:
+
+    struct uio_map {
 	struct kobject kobj;
-	unsigned long addr;
-	unsigned long size;
-	int memtype;
-	void __iomem *internal_addr;
-};
+	struct uio_mem *mem;
+    };
 
-If you have a struct uio_mem structure, finding its embedded kobject is
+If you have a struct uio_map structure, finding its embedded kobject is
 just a matter of using the kobj member.  Code that works with kobjects will
 often have the opposite problem, however: given a struct kobject pointer,
 what is the pointer to the containing structure?  You must avoid tricks
 (such as assuming that the kobject is at the beginning of the structure)
 and, instead, use the container_of() macro, found in <linux/kernel.h>:
 
-	container_of(pointer, type, member)
+    container_of(pointer, type, member)
 
-where pointer is the pointer to the embedded kobject, type is the type of
-the containing structure, and member is the name of the structure field to
-which pointer points.  The return value from container_of() is a pointer to
-the given type. So, for example, a pointer "kp" to a struct kobject
-embedded within a struct uio_mem could be converted to a pointer to the
-containing uio_mem structure with:
+where:
 
-    struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj);
+  * "pointer" is the pointer to the embedded kobject,
+  * "type" is the type of the containing structure, and
+  * "member" is the name of the structure field to which "pointer" points.
 
-Programmers often define a simple macro for "back-casting" kobject pointers
-to the containing type.
+The return value from container_of() is a pointer to the corresponding
+container type. So, for example, a pointer "kp" to a struct kobject
+embedded *within* a struct uio_map could be converted to a pointer to the
+*containing* uio_map structure with:
+
+    struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
+
+For convenience, programmers often define a simple macro for "back-casting"
+kobject pointers to the containing type.  Exactly this happens in the
+earlier drivers/uio/uio.c, as you can see here:
+
+    struct uio_map {
+        struct kobject kobj;
+        struct uio_mem *mem;
+    };
+
+    #define to_map(map) container_of(map, struct uio_map, kobj)
+
+where the macro argument "map" is a pointer to the struct kobject in
+question.  That macro is subsequently invoked with:
+
+    struct uio_map *map = to_map(kobj);
 
 
 Initialization of kobjects
@@ -387,4 +406,5 @@ called, and the objects in the former circle release each other.
 Example code to copy from
 
 For a more complete example of using ksets and kobjects properly, see the
-sample/kobject/kset-example.c code.
+example programs samples/kobject/{kobject-example.c,kset-example.c},
+which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT.

Documentation/memory-barriers.txt

@@ -3,6 +3,7 @@
 			 ============================
 
 By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 Contents:
 
@@ -60,6 +61,10 @@ Contents:
 
      - And then there's the Alpha.
 
+ (*) Example uses.
+
+     - Circular buffers.
+
  (*) References.
 
 
@@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model.
 See the subsection on "Cache Coherency" above.
 
 
+============
+EXAMPLE USES
+============
+
+CIRCULAR BUFFERS
+----------------
+
+Memory barriers can be used to implement circular buffering without the need
+of a lock to serialise the producer with the consumer.  See:
+
+	Documentation/circular-buffers.txt
+
+for details.
+
+
 ==========
 REFERENCES
 ==========

Documentation/networking/stmmac.txt

@@ -0,0 +1,143 @@
+       STMicroelectronics 10/100/1000 Synopsys Ethernet driver
+
+Copyright (C) 2007-2010  STMicroelectronics Ltd
+Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+
+This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
+(Synopsys IP blocks); it has been fully tested on STLinux platforms.
+
+Currently this network device driver is for all STM embedded MAC/GMAC
+(7xxx SoCs).
+
+DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100
+Universal version 4.0 have been used for developing the first code
+implementation.
+
+Please, for more information also visit: www.stlinux.com
+
+1) Kernel Configuration
+The kernel configuration option is STMMAC_ETH:
+ Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
+ STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
+
+2) Driver parameters list:
+	debug: message level (0: no output, 16: all);
+	phyaddr: to manually provide the physical address to the PHY device;
+	dma_rxsize: DMA rx ring size;
+	dma_txsize: DMA tx ring size;
+	buf_sz: DMA buffer size;
+	tc: control the HW FIFO threshold;
+	tx_coe: Enable/Disable Tx Checksum Offload engine;
+	watchdog: transmit timeout (in milliseconds);
+	flow_ctrl: Flow control ability [on/off];
+	pause: Flow Control Pause Time;
+	tmrate: timer period (only if timer optimisation is configured).
+
+3) Command line options
+Driver parameters can be also passed in command line by using:
+	stmmaceth=dma_rxsize:128,dma_txsize:512
+
+4) Driver information and notes
+
+4.1) Transmit process
+The xmit method is invoked when the kernel needs to transmit a packet; it sets
+the descriptors in the ring and informs the DMA engine that there is a packet
+ready to be transmitted.
+Once the controller has finished transmitting the packet, an interrupt is
+triggered; So the driver will be able to release the socket buffers.
+By default, the driver sets the NETIF_F_SG bit in the features field of the
+net_device structure enabling the scatter/gather feature.
+
+4.2) Receive process
+When one or more packets are received, an interrupt happens. The interrupts
+are not queued so the driver has to scan all the descriptors in the ring during
+the receive process.
+This is based on NAPI so the interrupt handler signals only if there is work to be
+done, and it exits.
+Then the poll method will be scheduled at some future point.
+The incoming packets are stored, by the DMA, in a list of pre-allocated socket
+buffers in order to avoid the memcpy (Zero-copy).
+
+4.3) Timer-Driver Interrupt
+Instead of having the device that asynchronously notifies the frame receptions, the
+driver configures a timer to generate an interrupt at regular intervals.
+Based on the granularity of the timer, the frames that are received by the device
+will experience different levels of latency. Some NICs have dedicated timer
+device to perform this task. STMMAC can use either the RTC device or the TMU
+channel 2  on STLinux platforms.
+The timers frequency can be passed to the driver as parameter; when change it,
+take care of both hardware capability and network stability/performance impact.
+Several performance tests on STM platforms showed this optimisation allows to spare
+the CPU while having the maximum throughput.
+
+4.4) WOL
+Wake up on Lan feature through Magic Frame is only supported for the GMAC
+core.
+
+4.5) DMA descriptors
+Driver handles both normal and enhanced descriptors. The latter has been only
+tested on DWC Ether MAC 10/100/1000 Universal version 3.41a.
+
+4.6) Ethtool support
+Ethtool is supported. Driver statistics and internal errors can be taken using:
+ethtool -S ethX command. It is possible to dump registers etc.
+
+4.7) Jumbo and Segmentation Offloading
+Jumbo frames are supported and tested for the GMAC.
+The GSO has been also added but it's performed in software.
+LRO is not supported.
+
+4.8) Physical
+The driver is compatible with PAL to work with PHY and GPHY devices.
+
+4.9) Platform information
+Several information came from the platform; please refer to the
+driver's Header file in include/linux directory.
+
+struct plat_stmmacenet_data {
+        int bus_id;
+        int pbl;
+        int has_gmac;
+        void (*fix_mac_speed)(void *priv, unsigned int speed);
+        void (*bus_setup)(unsigned long ioaddr);
+#ifdef CONFIG_STM_DRIVERS
+        struct stm_pad_config *pad_config;
+#endif
+        void *bsp_priv;
+};
+
+Where:
+- pbl (Programmable Burst Length) is maximum number of
+  beats to be transferred in one DMA transaction.
+  GMAC also enables the 4xPBL by default.
+- fix_mac_speed and bus_setup are used to configure internal target
+  registers (on STM platforms);
+- has_gmac: GMAC core is on board (get it at run-time in the next step);
+- bus_id: bus identifier.
+
+struct plat_stmmacphy_data {
+        int bus_id;
+        int phy_addr;
+        unsigned int phy_mask;
+        int interface;
+        int (*phy_reset)(void *priv);
+        void *priv;
+};
+
+Where:
+- bus_id: bus identifier;
+- phy_addr: physical address used for the attached phy device;
+            set it to -1 to get it at run-time;
+- interface: physical MII interface mode;
+- phy_reset: hook to reset HW function.
+
+TODO:
+- Continue to make the driver more generic and suitable for other Synopsys
+  Ethernet controllers used on other architectures (i.e. ARM).
+- 10G controllers are not supported.
+- MAC uses Normal descriptors and GMAC uses enhanced ones.
+  This is a limit that should be reviewed. MAC could want to
+  use the enhanced structure.
+- Checksumming: Rx/Tx csum is done in HW in case of GMAC only.
+- Review the timer optimisation code to use an embedded device that seems to be
+  available in new chip generations.

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt

@@ -21,6 +21,15 @@ Required properties:
 - fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
   threads.
 
+Optional properties:
+- fsl,firmware-phandle:
+    Usage: required only if there is no fsl,qe-firmware child node
+    Value type: <phandle>
+    Definition: Points to a firmware node (see "QE Firmware Node" below)
+        that contains the firmware that should be uploaded for this QE.
+        The compatible property for the firmware node should say,
+        "fsl,qe-firmware".
+
 Recommended properties
 - brg-frequency : the internal clock source frequency for baud-rate
   generators in Hz.
@@ -59,3 +68,48 @@ Example:
 		reg = <0 c000>;
 	};
      };
+
+* QE Firmware Node
+
+This node defines a firmware binary that is embedded in the device tree, for
+the purpose of passing the firmware from bootloader to the kernel, or from
+the hypervisor to the guest.
+
+The firmware node itself contains the firmware binary contents, a compatible
+property, and any firmware-specific properties.  The node should be placed
+inside a QE node that needs it.  Doing so eliminates the need for a
+fsl,firmware-phandle property.  Other QE nodes that need the same firmware
+should define an fsl,firmware-phandle property that points to the firmware node
+in the first QE node.
+
+The fsl,firmware property can be specified in the DTS (possibly using incbin)
+or can be inserted by the boot loader at boot time.
+
+Required properties:
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: A standard property.  Specify a string that indicates what
+          kind of firmware it is.  For QE, this should be "fsl,qe-firmware".
+
+   - fsl,firmware
+      Usage: required
+      Value type: <prop-encoded-array>, encoded as an array of bytes
+      Definition: A standard property.  This property contains the firmware
+          binary "blob".
+
+Example:
+	qe1@e0080000 {
+		compatible = "fsl,qe";
+		qe_firmware:qe-firmware {
+			compatible = "fsl,qe-firmware";
+			fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...];
+		};
+		...
+	};
+
+	qe2@e0090000 {
+		compatible = "fsl,qe";
+		fsl,firmware-phandle = <&qe_firmware>;
+		...
+	};

Documentation/volatile-considered-harmful.txt

@@ -63,9 +63,9 @@ way to perform a busy wait is:
         cpu_relax();
 
 The cpu_relax() call can lower CPU power consumption or yield to a
-hyperthreaded twin processor; it also happens to serve as a memory barrier,
-so, once again, volatile is unnecessary.  Of course, busy-waiting is
-generally an anti-social act to begin with.
+hyperthreaded twin processor; it also happens to serve as a compiler
+barrier, so, once again, volatile is unnecessary.  Of course, busy-
+waiting is generally an anti-social act to begin with.
 
 There are still a few rare situations where volatile makes sense in the
 kernel:

MAINTAINERS

@@ -797,12 +797,12 @@ M:	Michael Petchkovsky <mkpetch@internode.on.net>
 S:	Maintained
 
 ARM/NOMADIK ARCHITECTURE
-M:     Alessandro Rubini <rubini@unipv.it>
-M:     STEricsson <STEricsson_nomadik_linux@list.st.com>
-L:     linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:     Maintained
-F:     arch/arm/mach-nomadik/
-F:     arch/arm/plat-nomadik/
+M:	Alessandro Rubini <rubini@unipv.it>
+M:	STEricsson <STEricsson_nomadik_linux@list.st.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-nomadik/
+F:	arch/arm/plat-nomadik/
 
 ARM/OPENMOKO NEO FREERUNNER (GTA02) MACHINE SUPPORT
 M:	Nelson Castillo <arhuaco@freaks-unidos.net>
@@ -1441,6 +1441,15 @@ F:	arch/powerpc/include/asm/spu*.h
 F:	arch/powerpc/oprofile/*cell*
 F:	arch/powerpc/platforms/cell/
 
+CEPH DISTRIBUTED FILE SYSTEM CLIENT
+M:	Sage Weil <sage@newdream.net>
+L:	ceph-devel@vger.kernel.org
+W:	http://ceph.newdream.net/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+S:	Supported
+F:	Documentation/filesystems/ceph.txt
+F:	fs/ceph
+
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:	David Vrabel <david.vrabel@csr.com>
 L:	linux-usb@vger.kernel.org
@@ -1917,17 +1926,17 @@ F:	drivers/scsi/dpt*
 F:	drivers/scsi/dpt/
 
 DRBD DRIVER
-P:     Philipp Reisner
-P:     Lars Ellenberg
-M:     drbd-dev@lists.linbit.com
-L:     drbd-user@lists.linbit.com
-W:     http://www.drbd.org
-T:     git git://git.drbd.org/linux-2.6-drbd.git drbd
-T:     git git://git.drbd.org/drbd-8.3.git
-S:     Supported
-F:     drivers/block/drbd/
-F:     lib/lru_cache.c
-F:     Documentation/blockdev/drbd/
+P:	Philipp Reisner
+P:	Lars Ellenberg
+M:	drbd-dev@lists.linbit.com
+L:	drbd-user@lists.linbit.com
+W:	http://www.drbd.org
+T:	git git://git.drbd.org/linux-2.6-drbd.git drbd
+T:	git git://git.drbd.org/drbd-8.3.git
+S:	Supported
+F:	drivers/block/drbd/
+F:	lib/lru_cache.c
+F:	Documentation/blockdev/drbd/
 
 DRIVER CORE, KOBJECTS, AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@suse.de>
@@ -3074,6 +3083,7 @@ F:	include/scsi/*iscsi*
 ISDN SUBSYSTEM
 M:	Karsten Keil <isdn@linux-pingi.de>
 L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
+L:	netdev@vger.kernel.org
 W:	http://www.isdn4linux.de
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kkeil/isdn-2.6.git
 S:	Maintained
@@ -3260,6 +3270,16 @@ S:	Maintained
 F:	include/linux/kexec.h
 F:	kernel/kexec.c
 
+KEYS/KEYRINGS:
+M:	David Howells <dhowells@redhat.com>
+L:	keyrings@linux-nfs.org
+S:	Maintained
+F:	Documentation/keys.txt
+F:	include/linux/key.h
+F:	include/linux/key-type.h
+F:	include/keys/
+F:	security/keys/
+
 KGDB
 M:	Jason Wessel <jason.wessel@windriver.com>
 L:	kgdb-bugreport@lists.sourceforge.net
@@ -3509,8 +3529,8 @@ F:	drivers/scsi/sym53c8xx_2/
 LTP (Linux Test Project)
 M:	Rishikesh K Rajak <risrajak@linux.vnet.ibm.com>
 M:	Garrett Cooper <yanegomi@gmail.com>
-M:     Mike Frysinger <vapier@gentoo.org>
-M:     Subrata Modak <subrata@linux.vnet.ibm.com>
+M:	Mike Frysinger <vapier@gentoo.org>
+M:	Subrata Modak <subrata@linux.vnet.ibm.com>
 L:	ltp-list@lists.sourceforge.net (subscribers-only)
 W:	http://ltp.sourceforge.net/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/galak/ltp.git
@@ -5414,7 +5434,6 @@ S:	Maintained
 F:	sound/soc/codecs/twl4030*
 
 TIPC NETWORK LAYER
-M:	Per Liden <per.liden@ericsson.com>
 M:	Jon Maloy <jon.maloy@ericsson.com>
 M:	Allan Stephens <allan.stephens@windriver.com>
 L:	tipc-discussion@lists.sourceforge.net
@@ -6192,7 +6211,7 @@ F:	arch/x86/
 X86 PLATFORM DRIVERS
 M:	Matthew Garrett <mjg@redhat.com>
 L:	platform-driver-x86@vger.kernel.org
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.git
 S:	Maintained
 F:	drivers/platform/x86
 

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 34
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Man-Eating Seals of Antiquity
 
 # *DOCUMENTATION*

arch/alpha/boot/bootp.c

@@ -8,6 +8,7 @@
  * based significantly on the arch/alpha/boot/main.c of Linus Torvalds
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <generated/utsrelease.h>
 #include <linux/mm.h>

arch/alpha/boot/bootpz.c

@@ -10,6 +10,7 @@
  * and the decompression code from MILO.
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <generated/utsrelease.h>
 #include <linux/mm.h>

arch/alpha/boot/main.c

@@ -6,6 +6,7 @@
  * This file is the bootloader for the Linux/AXP kernel
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <generated/utsrelease.h>
 #include <linux/mm.h>

arch/alpha/boot/misc.c

@@ -19,6 +19,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 

arch/alpha/include/asm/core_marvel.h

@@ -12,7 +12,6 @@
 #define __ALPHA_MARVEL__H__
 
 #include <linux/types.h>
-#include <linux/pci.h>
 #include <linux/spinlock.h>
 
 #include <asm/compiler.h>

arch/alpha/include/asm/core_mcpcia.h

@@ -6,7 +6,6 @@
 #define MCPCIA_ONE_HAE_WINDOW 1
 
 #include <linux/types.h>
-#include <linux/pci.h>
 #include <asm/compiler.h>
 
 /*

arch/alpha/include/asm/core_titan.h

@@ -2,7 +2,6 @@
 #define __ALPHA_TITAN__H__
 
 #include <linux/types.h>
-#include <linux/pci.h>
 #include <asm/compiler.h>
 
 /*

arch/alpha/include/asm/core_tsunami.h

@@ -2,7 +2,6 @@
 #define __ALPHA_TSUNAMI__H__
 
 #include <linux/types.h>
-#include <linux/pci.h>
 #include <asm/compiler.h>
 
 /*

arch/alpha/kernel/irq.c

@@ -18,7 +18,6 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/init.h>
 #include <linux/irq.h>

arch/alpha/kernel/osf_sys.c

@@ -20,7 +20,6 @@
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/utsname.h>
 #include <linux/time.h>
@@ -37,6 +36,7 @@
 #include <linux/uio.h>
 #include <linux/vfs.h>
 #include <linux/rcupdate.h>
+#include <linux/slab.h>
 
 #include <asm/fpu.h>
 #include <asm/io.h>

arch/alpha/kernel/pci-noop.c

@@ -7,6 +7,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/gfp.h>
 #include <linux/capability.h>
 #include <linux/mm.h>
 #include <linux/errno.h>

arch/alpha/kernel/pci-sysfs.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
 
 static int hose_mmap_page_range(struct pci_controller *hose,

arch/alpha/kernel/pci_iommu.c

@@ -5,7 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
-#include <linux/slab.h>
+#include <linux/gfp.h>
 #include <linux/bootmem.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>

arch/alpha/kernel/process.c

@@ -17,7 +17,6 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/time.h>
 #include <linux/major.h>
@@ -28,6 +27,7 @@
 #include <linux/reboot.h>
 #include <linux/tty.h>
 #include <linux/console.h>
+#include <linux/slab.h>
 
 #include <asm/reg.h>
 #include <asm/uaccess.h>

arch/alpha/kernel/ptrace.c

@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
-#include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/signal.h>
 

arch/alpha/kernel/smc37c669.c

@@ -3,7 +3,6 @@
  */
 #include <linux/kernel.h>
 
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/delay.h>

arch/alpha/kernel/smc37c93x.c

@@ -4,7 +4,6 @@
 
 #include <linux/kernel.h>
 
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/delay.h>

arch/alpha/kernel/srm_env.c

@@ -30,6 +30,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/gfp.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/proc_fs.h>

arch/alpha/kernel/sys_dp264.c

@@ -224,7 +224,7 @@ static void
 dp264_device_interrupt(unsigned long vector)
 {
 #if 1
-	printk("dp264_device_interrupt: NOT IMPLEMENTED YET!! \n");
+	printk("dp264_device_interrupt: NOT IMPLEMENTED YET!!\n");
 #else
 	unsigned long pld;
 	unsigned int i;

arch/alpha/kernel/sys_titan.c

@@ -171,7 +171,7 @@ titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 static void
 titan_device_interrupt(unsigned long vector)
 {
-	printk("titan_device_interrupt: NOT IMPLEMENTED YET!! \n");
+	printk("titan_device_interrupt: NOT IMPLEMENTED YET!!\n");
 }
 
 static void 

arch/alpha/kernel/traps.c

@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
+#include <linux/ratelimit.h>
 
 #include <asm/gentrap.h>
 #include <asm/uaccess.h>
@@ -771,8 +772,7 @@ asmlinkage void
 do_entUnaUser(void __user * va, unsigned long opcode,
 	      unsigned long reg, struct pt_regs *regs)
 {
-	static int cnt = 0;
-	static unsigned long last_time;
+	static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 5);
 
 	unsigned long tmp1, tmp2, tmp3, tmp4;
 	unsigned long fake_reg, *reg_addr = &fake_reg;
@@ -783,15 +783,11 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 	   with the unaliged access.  */
 
 	if (!test_thread_flag (TIF_UAC_NOPRINT)) {
-		if (cnt >= 5 && time_after(jiffies, last_time + 5 * HZ)) {
-			cnt = 0;
-		}
-		if (++cnt < 5) {
+		if (__ratelimit(&ratelimit)) {
 			printk("%s(%d): unaligned trap at %016lx: %p %lx %ld\n",
 			       current->comm, task_pid_nr(current),
 			       regs->pc - 4, va, opcode, reg);
 		}
-		last_time = jiffies;
 	}
 	if (test_thread_flag (TIF_UAC_SIGBUS))
 		goto give_sigbus;

arch/alpha/mm/init.c

@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/bootmem.h> /* max_low_pfn */
 #include <linux/vmalloc.h>
+#include <linux/gfp.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>

arch/arm/common/clkdev.c

@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/mutex.h>
 #include <linux/clk.h>
+#include <linux/slab.h>
 
 #include <asm/clkdev.h>
 #include <mach/clkdev.h>

arch/arm/common/it8152.c

@@ -21,7 +21,6 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/irq.h>

arch/arm/common/locomo.c

@@ -290,7 +290,7 @@ static int locomo_suspend(struct platform_device *dev, pm_message_t state)
 	save->LCM_GPO     = locomo_readl(lchip->base + LOCOMO_GPO);	/* GPIO */
 	locomo_writel(0x00, lchip->base + LOCOMO_GPO);
 	save->LCM_SPICT   = locomo_readl(lchip->base + LOCOMO_SPI + LOCOMO_SPICT);	/* SPI */
-	locomo_writel(0x40, lchip->base + LOCOMO_SPICT);
+	locomo_writel(0x40, lchip->base + LOCOMO_SPI + LOCOMO_SPICT);
 	save->LCM_GPE     = locomo_readl(lchip->base + LOCOMO_GPE);	/* GPIO */
 	locomo_writel(0x00, lchip->base + LOCOMO_GPE);
 	save->LCM_ASD     = locomo_readl(lchip->base + LOCOMO_ASD);	/* ADSTART */
@@ -418,7 +418,7 @@ __locomo_probe(struct device *me, struct resource *mem, int irq)
 	/* Longtime timer */
 	locomo_writel(0, lchip->base + LOCOMO_LTINT);
 	/* SPI */
-	locomo_writel(0, lchip->base + LOCOMO_SPIIE);
+	locomo_writel(0, lchip->base + LOCOMO_SPI + LOCOMO_SPIIE);
 
 	locomo_writel(6 + 8 + 320 + 30 - 10, lchip->base + LOCOMO_ASD);
 	r = locomo_readl(lchip->base + LOCOMO_ASD);
@@ -707,7 +707,7 @@ void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int
 	udelay(DAC_SCL_HIGH_HOLD_TIME);	/* 4.7 usec */
 	if (locomo_readl(mapbase + LOCOMO_DAC) & LOCOMO_DAC_SDAOEB) {	/* High is error */
 		printk(KERN_WARNING "locomo: m62332_senddata Error 1\n");
-		return;
+		goto out;
 	}
 
 	/* Send Sub address (LSB is channel select) */
@@ -735,7 +735,7 @@ void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int
 	udelay(DAC_SCL_HIGH_HOLD_TIME);	/* 4.7 usec */
 	if (locomo_readl(mapbase + LOCOMO_DAC) & LOCOMO_DAC_SDAOEB) {	/* High is error */
 		printk(KERN_WARNING "locomo: m62332_senddata Error 2\n");
-		return;
+		goto out;
 	}
 
 	/* Send DAC data */
@@ -760,9 +760,9 @@ void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int
 	udelay(DAC_SCL_HIGH_HOLD_TIME);	/* 4.7 usec */
 	if (locomo_readl(mapbase + LOCOMO_DAC) & LOCOMO_DAC_SDAOEB) {	/* High is error */
 		printk(KERN_WARNING "locomo: m62332_senddata Error 3\n");
-		return;
 	}
 
+out:
 	/* stop */
 	r = locomo_readl(mapbase + LOCOMO_DAC);
 	r &=  ~(LOCOMO_DAC_SCLOEB);

arch/arm/include/asm/cacheflush.h

@@ -15,6 +15,7 @@
 #include <asm/glue.h>
 #include <asm/shmparam.h>
 #include <asm/cachetype.h>
+#include <asm/outercache.h>
 
 #define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
 
@@ -219,12 +220,6 @@ struct cpu_cache_fns {
 	void (*dma_flush_range)(const void *, const void *);
 };
 
-struct outer_cache_fns {
-	void (*inv_range)(unsigned long, unsigned long);
-	void (*clean_range)(unsigned long, unsigned long);
-	void (*flush_range)(unsigned long, unsigned long);
-};
-
 /*
  * Select the calling method
  */
@@ -281,37 +276,6 @@ extern void dmac_flush_range(const void *, const void *);
 
 #endif
 
-#ifdef CONFIG_OUTER_CACHE
-
-extern struct outer_cache_fns outer_cache;
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.inv_range)
-		outer_cache.inv_range(start, end);
-}
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.clean_range)
-		outer_cache.clean_range(start, end);
-}
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{
-	if (outer_cache.flush_range)
-		outer_cache.flush_range(start, end);
-}
-
-#else
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{ }
-
-#endif
-
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user

arch/arm/include/asm/clkdev.h

@@ -13,6 +13,7 @@
 #define __ASM_CLKDEV_H
 
 struct clk;
+struct device;
 
 struct clk_lookup {
 	struct list_head	node;

arch/arm/include/asm/irq.h

@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 struct irqaction;
+struct pt_regs;
 extern void migrate_irqs(void);
 
 extern void asm_do_IRQ(unsigned int, struct pt_regs *);

arch/arm/include/asm/outercache.h

@@ -0,0 +1,75 @@
+/*
+ * arch/arm/include/asm/outercache.h
+ *
+ * Copyright (C) 2010 ARM Ltd.
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_OUTERCACHE_H
+#define __ASM_OUTERCACHE_H
+
+struct outer_cache_fns {
+	void (*inv_range)(unsigned long, unsigned long);
+	void (*clean_range)(unsigned long, unsigned long);
+	void (*flush_range)(unsigned long, unsigned long);
+#ifdef CONFIG_OUTER_CACHE_SYNC
+	void (*sync)(void);
+#endif
+};
+
+#ifdef CONFIG_OUTER_CACHE
+
+extern struct outer_cache_fns outer_cache;
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.inv_range)
+		outer_cache.inv_range(start, end);
+}
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.clean_range)
+		outer_cache.clean_range(start, end);
+}
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{
+	if (outer_cache.flush_range)
+		outer_cache.flush_range(start, end);
+}
+
+#else
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{ }
+
+#endif
+
+#ifdef CONFIG_OUTER_CACHE_SYNC
+static inline void outer_sync(void)
+{
+	if (outer_cache.sync)
+		outer_cache.sync();
+}
+#else
+static inline void outer_sync(void)
+{ }
+#endif
+
+#endif	/* __ASM_OUTERCACHE_H */

arch/arm/include/asm/system.h

@@ -60,6 +60,8 @@
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 
+#include <asm/outercache.h>
+
 #define __exception	__attribute__((section(".exception.text")))
 
 struct thread_info;
@@ -137,10 +139,12 @@ extern unsigned int user_debug;
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 #endif
 
-#if __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
-#define mb()		dmb()
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
+#define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dmb()
-#define wmb()		dmb()
+#define wmb()		mb()
 #else
 #define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
@@ -152,9 +156,9 @@ extern unsigned int user_debug;
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #else
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
+#define smp_mb()	dmb()
+#define smp_rmb()	dmb()
+#define smp_wmb()	dmb()
 #endif
 
 #define read_barrier_depends()		do { } while(0)

arch/arm/kernel/irq.c

@@ -27,7 +27,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/smp.h>
 #include <linux/init.h>

arch/arm/kernel/kprobes.c

@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
@@ -393,6 +394,14 @@ void __kprobes jprobe_return(void)
 		/*
 		 * Setup an empty pt_regs. Fill SP and PC fields as
 		 * they're needed by longjmp_break_handler.
+		 *
+		 * We allocate some slack between the original SP and start of
+		 * our fabricated regs. To be precise we want to have worst case
+		 * covered which is STMFD with all 16 regs so we allocate 2 *
+		 * sizeof(struct_pt_regs)).
+		 *
+		 * This is to prevent any simulated instruction from writing
+		 * over the regs when they are accessing the stack.
 		 */
 		"sub    sp, %0, %1		\n\t"
 		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
@@ -410,7 +419,7 @@ void __kprobes jprobe_return(void)
 		"ldmia	sp, {r0 - pc}		\n\t"
 		:
 		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs)),
+		  "I" (sizeof(struct pt_regs) * 2),
 		  "J" (offsetof(struct pt_regs, ARM_sp)),
 		  "J" (offsetof(struct pt_regs, ARM_pc)),
 		  "J" (offsetof(struct pt_regs, ARM_cpsr))

arch/arm/kernel/module.c

@@ -16,9 +16,9 @@
 #include <linux/mm.h>
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/string.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/sections.h>

arch/arm/kernel/process.c

@@ -16,7 +16,6 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>

arch/arm/kernel/sys_arm.c

@@ -15,7 +15,6 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
@@ -27,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/ipc.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 
 /* Fork a new task - this creates a new program thread.
  * This is called indirectly via a small wrapper

arch/arm/lib/memmove.S

@@ -74,7 +74,7 @@ ENTRY(memmove)
 		rsb	ip, ip, #32
 		addne	pc, pc, ip		@ C is always clear here
 		b	7f
-6:		nop
+6:		W(nop)
 		W(ldr)	r3, [r1, #-4]!
 		W(ldr)	r4, [r1, #-4]!
 		W(ldr)	r5, [r1, #-4]!
@@ -85,7 +85,7 @@ ENTRY(memmove)
 
 		add	pc, pc, ip
 		nop
-		nop
+		W(nop)
 		W(str)	r3, [r0, #-4]!
 		W(str)	r4, [r0, #-4]!
 		W(str)	r5, [r0, #-4]!

arch/arm/lib/uaccess_with_memcpy.c

@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/hardirq.h> /* for in_atomic() */
+#include <linux/gfp.h>
 #include <asm/current.h>
 #include <asm/page.h>
 

arch/arm/mach-aaec2000/core.c

@@ -20,6 +20,7 @@
 #include <linux/timex.h>
 #include <linux/signal.h>
 #include <linux/clk.h>
+#include <linux/gfp.h>
 
 #include <mach/hardware.h>
 #include <asm/irq.h>

arch/arm/mach-bcmring/dma.c

@@ -28,6 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqreturn.h>
 #include <linux/proc_fs.h>
+#include <linux/slab.h>
 
 #include <mach/timer.h>
 

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

@@ -22,6 +22,7 @@
 #include <linux/leds.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
+#include <linux/slab.h>
 #include <linux/mtd/nand.h>
 #include <linux/input.h>
 #include <linux/spi/spi.h>

arch/arm/mach-davinci/dma.c

@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 #include <mach/edma.h>
 

arch/arm/mach-h720x/common.c

@@ -14,7 +14,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mman.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>

arch/arm/mach-integrator/cpu.c

@@ -13,7 +13,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/init.h>

arch/arm/mach-integrator/impd1.c

@@ -21,6 +21,7 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 #include <asm/clkdev.h>
 #include <mach/clkdev.h>

arch/arm/mach-integrator/integrator_cp.c

@@ -13,7 +13,6 @@
 #include <linux/list.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sysdev.h>
 #include <linux/amba/bus.h>
@@ -21,6 +20,7 @@
 #include <linux/amba/clcd.h>
 #include <linux/amba/mmci.h>
 #include <linux/io.h>
+#include <linux/gfp.h>
 
 #include <asm/clkdev.h>
 #include <mach/clkdev.h>

arch/arm/mach-integrator/pci_v3.c

@@ -22,7 +22,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/pci.h>
-#include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>

arch/arm/mach-iop13xx/pci.c

@@ -18,6 +18,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/jiffies.h>
 #include <asm/irq.h>

arch/arm/mach-iop32x/glantank.c

@@ -19,7 +19,6 @@
 #include <linux/pci.h>
 #include <linux/pm.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-iop32x/iq31244.c

@@ -21,7 +21,6 @@
 #include <linux/pci.h>
 #include <linux/pm.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-iop32x/iq80321.c

@@ -18,7 +18,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-iop32x/n2100.c

@@ -23,7 +23,6 @@
 #include <linux/pci.h>
 #include <linux/pm.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-iop33x/iq80331.c

@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-iop33x/iq80332.c

@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
 #include <linux/mtd/physmap.h>

arch/arm/mach-ixp2000/enp2611.c

@@ -26,7 +26,6 @@
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/serial.h>
 #include <linux/tty.h>

arch/arm/mach-ixp2000/ixdp2400.c

@@ -23,7 +23,6 @@
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 

arch/arm/mach-ixp2000/ixdp2800.c

@@ -23,7 +23,6 @@
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 

arch/arm/mach-ixp2000/ixdp2x00.c

@@ -23,7 +23,6 @@
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 

arch/arm/mach-ixp2000/ixdp2x01.c

@@ -23,7 +23,6 @@
 #include <linux/bitops.h>
 #include <linux/pci.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/serial.h>
 #include <linux/tty.h>

arch/arm/mach-ixp2000/pci.c

@@ -22,7 +22,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 

arch/arm/mach-ixp23xx/include/mach/memory.h

@@ -19,7 +19,7 @@
  */
 #define PHYS_OFFSET		(0x00000000)
 
-#define IXP23XX_PCI_SDRAM_OFFSET (*((volatile int *)IXP23XX_PCI_SDRAM_BAR) & 0xfffffff0))
+#define IXP23XX_PCI_SDRAM_OFFSET (*((volatile int *)IXP23XX_PCI_SDRAM_BAR) & 0xfffffff0)
 
 #define __phys_to_bus(x)	((x) + (IXP23XX_PCI_SDRAM_OFFSET - PHYS_OFFSET))
 #define __bus_to_phys(x)	((x) - (IXP23XX_PCI_SDRAM_OFFSET - PHYS_OFFSET))

arch/arm/mach-ixp23xx/pci.c

@@ -23,7 +23,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 

arch/arm/mach-ixp4xx/avila-setup.c

@@ -17,7 +17,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 #include <linux/i2c-gpio.h>
 #include <asm/types.h>
 #include <asm/setup.h>

arch/arm/mach-ixp4xx/coyote-setup.c

@@ -14,7 +14,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>

arch/arm/mach-ixp4xx/gateway7001-setup.c

@@ -17,7 +17,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>

arch/arm/mach-ixp4xx/gtwx5715-setup.c

@@ -27,7 +27,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 #include <asm/types.h>
 #include <asm/setup.h>
 #include <asm/memory.h>

arch/arm/mach-ixp4xx/ixdp425-setup.c

@@ -14,7 +14,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 #include <linux/i2c-gpio.h>
 #include <linux/io.h>
 #include <linux/mtd/mtd.h>

arch/arm/mach-ixp4xx/ixp4xx_npe.c

@@ -20,7 +20,6 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <mach/npe.h>
 
 #define DEBUG_MSG			0

arch/arm/mach-ixp4xx/wg302v2-setup.c

@@ -18,7 +18,6 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_8250.h>
-#include <linux/slab.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>

arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c

@@ -74,9 +74,9 @@ static struct gpio_keys_button mv88f6281gtw_ge_button_pins[] = {
 		.desc		= "SWR Button",
 		.active_low	= 1,
 	}, {
-		.code		= KEY_F1,
+		.code		= KEY_WPS_BUTTON,
 		.gpio		= 46,
-		.desc		= "WPS Button(F1)",
+		.desc		= "WPS Button",
 		.active_low	= 1,
 	},
 };

arch/arm/mach-kirkwood/pcie.c

@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/mbus.h>
 #include <asm/irq.h>
 #include <asm/mach/pci.h>

arch/arm/mach-lh7a40x/clcd.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/sysdev.h>

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

@@ -14,7 +14,7 @@
 #define UART2_BASE	(APB_PHYS_BASE + 0x17000)
 #define UART3_BASE	(APB_PHYS_BASE + 0x18000)
 
-static volatile unsigned long *UART = (unsigned long *)UART2_BASE;
+static volatile unsigned long *UART;
 
 static inline void putc(char c)
 {
@@ -37,6 +37,9 @@ static inline void flush(void)
 
 static inline void arch_decomp_setup(void)
 {
+	/* default to UART2 */
+	UART = (unsigned long *)UART2_BASE;
+
 	if (machine_is_avengers_lite())
 		UART = (unsigned long *)UART3_BASE;
 }

arch/arm/mach-mx3/mach-mx31moboard.c

@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/fsl_devices.h>
+#include <linux/gfp.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>

arch/arm/mach-mx3/mach-pcm037.c

@@ -36,6 +36,7 @@
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 #include <linux/fsl_devices.h>
+#include <linux/gfp.h>
 
 #include <media/soc_camera.h>
 

arch/arm/mach-mx3/mx31moboard-devboard.c

@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #include <linux/usb/otg.h>

arch/arm/mach-mx3/mx31moboard-marxbot.c

@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
+#include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
 

arch/arm/mach-netx/fb.c

@@ -23,6 +23,7 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
 #include <linux/err.h>
+#include <linux/gfp.h>
 
 #include <asm/irq.h>
 

arch/arm/mach-netx/xc.c

@@ -21,6 +21,7 @@
 #include <linux/device.h>
 #include <linux/firmware.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/io.h>
 
 #include <mach/hardware.h>

arch/arm/mach-nomadik/gpio.c

@@ -19,6 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/slab.h>
 
 #include <mach/hardware.h>
 #include <mach/gpio.h>

arch/arm/mach-ns9xxx/plat-serial8250.c

@@ -10,6 +10,7 @@
  */
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
+#include <linux/slab.h>
 
 #include <mach/regs-board-a9m9750dev.h>
 #include <mach/board.h>

arch/arm/mach-ns9xxx/processor-ns9360.c

@@ -10,7 +10,6 @@
  */
 #include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/slab.h>
 
 #include <asm/page.h>
 #include <asm/mach/map.h>

arch/arm/mach-omap1/mcbsp.c

@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <mach/irqs.h>
 #include <plat/dma.h>

arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c

@@ -31,6 +31,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/cpufreq.h>
+#include <linux/slab.h>
 
 #include <plat/clock.h>
 #include <plat/sram.h>