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

Documentation/arm/tcm.txt

+ARM TCM (Tightly-Coupled Memory) handling in Linux
+----
+Written by Linus Walleij <linus.walleij@stericsson.com>
+
+Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory).
+This is usually just a few (4-64) KiB of RAM inside the ARM
+processor.
+
+Due to being embedded inside the CPU The TCM has a
+Harvard-architecture, so there is an ITCM (instruction TCM)
+and a DTCM (data TCM). The DTCM can not contain any
+instructions, but the ITCM can actually contain data.
+The size of DTCM or ITCM is minimum 4KiB so the typical
+minimum configuration is 4KiB ITCM and 4KiB DTCM.
+
+ARM CPU:s have special registers to read out status, physical
+location and size of TCM memories. arch/arm/include/asm/cputype.h
+defines a CPUID_TCM register that you can read out from the
+system control coprocessor. Documentation from ARM can be found
+at http://infocenter.arm.com, search for "TCM Status Register"
+to see documents for all CPUs. Reading this register you can
+determine if ITCM (bit 0) and/or DTCM (bit 16) is present in the
+machine.
+
+There is further a TCM region register (search for "TCM Region
+Registers" at the ARM site) that can report and modify the location
+size of TCM memories at runtime. This is used to read out and modify
+TCM location and size. Notice that this is not a MMU table: you
+actually move the physical location of the TCM around. At the
+place you put it, it will mask any underlying RAM from the
+CPU so it is usually wise not to overlap any physical RAM with
+the TCM. The TCM memory exists totally outside the MMU and will
+override any MMU mappings.
+
+Code executing inside the ITCM does not "see" any MMU mappings
+and e.g. register accesses must be made to physical addresses.
+
+TCM is used for a few things:
+
+- FIQ and other interrupt handlers that need deterministic
+  timing and cannot wait for cache misses.
+
+- Idle loops where all external RAM is set to self-refresh
+  retention mode, so only on-chip RAM is accessible by
+  the CPU and then we hang inside ITCM waiting for an
+  interrupt.
+
+- Other operations which implies shutting off or reconfiguring
+  the external RAM controller.
+
+There is an interface for using TCM on the ARM architecture
+in <asm/tcm.h>. Using this interface it is possible to:
+
+- Define the physical address and size of ITCM and DTCM.
+
+- Tag functions to be compiled into ITCM.
+
+- Tag data and constants to be allocated to DTCM and ITCM.
+
+- Have the remaining TCM RAM added to a special
+  allocation pool with gen_pool_create() and gen_pool_add()
+  and provice tcm_alloc() and tcm_free() for this
+  memory. Such a heap is great for things like saving
+  device state when shutting off device power domains.
+
+A machine that has TCM memory shall select HAVE_TCM in
+arch/arm/Kconfig for itself, and then the
+rest of the functionality will depend on the physical
+location and size of ITCM and DTCM to be defined in
+mach/memory.h for the machine. Code that needs to use
+TCM shall #include <asm/tcm.h> If the TCM is not located
+at the place given in memory.h it will be moved using
+the TCM Region registers.
+
+Functions to go into itcm can be tagged like this:
+int __tcmfunc foo(int bar);
+
+Variables to go into dtcm can be tagged like this:
+int __tcmdata foo;
+
+Constants can be tagged like this:
+int __tcmconst foo;
+
+To put assembler into TCM just use
+.section ".tcm.text" or .section ".tcm.data"
+respectively.
+
+Example code:
+
+#include <asm/tcm.h>
+
+/* Uninitialized data */
+static u32 __tcmdata tcmvar;
+/* Initialized data */
+static u32 __tcmdata tcmassigned = 0x2BADBABEU;
+/* Constant */
+static const u32 __tcmconst tcmconst = 0xCAFEBABEU;
+
+static void __tcmlocalfunc tcm_to_tcm(void)
+{
+	int i;
+	for (i = 0; i < 100; i++)
+		tcmvar ++;
+}
+
+static void __tcmfunc hello_tcm(void)
+{
+	/* Some abstract code that runs in ITCM */
+	int i;
+	for (i = 0; i < 100; i++) {
+		tcmvar ++;
+	}
+	tcm_to_tcm();
+}
+
+static void __init test_tcm(void)
+{
+	u32 *tcmem;
+	int i;
+
+	hello_tcm();
+	printk("Hello TCM executed from ITCM RAM\n");
+
+	printk("TCM variable from testrun: %u @ %p\n", tcmvar, &tcmvar);
+	tcmvar = 0xDEADBEEFU;
+	printk("TCM variable: 0x%x @ %p\n", tcmvar, &tcmvar);
+
+	printk("TCM assigned variable: 0x%x @ %p\n", tcmassigned, &tcmassigned);
+
+	printk("TCM constant: 0x%x @ %p\n", tcmconst, &tcmconst);
+
+	/* Allocate some TCM memory from the pool */
+	tcmem = tcm_alloc(20);
+	if (tcmem) {
+		printk("TCM Allocated 20 bytes of TCM @ %p\n", tcmem);
+		tcmem[0] = 0xDEADBEEFU;
+		tcmem[1] = 0x2BADBABEU;
+		tcmem[2] = 0xCAFEBABEU;
+		tcmem[3] = 0xDEADBEEFU;
+		tcmem[4] = 0x2BADBABEU;
+		for (i = 0; i < 5; i++)
+			printk("TCM tcmem[%d] = %08x\n", i, tcmem[i]);
+		tcm_free(tcmem, 20);
+	}
+}

Documentation/auxdisplay/cfag12864b-example.c

@@ -194,7 +194,6 @@ static void cfag12864b_blit(void)
  */
 
 #include <stdio.h>
-#include <string.h>
 
 #define EXAMPLES	6
 

Documentation/cgroups/cgroups.txt

@@ -408,6 +408,26 @@ You can attach the current shell task by echoing 0:
 
 # echo 0 > tasks
 
+2.3 Mounting hierarchies by name
+--------------------------------
+
+Passing the name=<x> option when mounting a cgroups hierarchy
+associates the given name with the hierarchy.  This can be used when
+mounting a pre-existing hierarchy, in order to refer to it by name
+rather than by its set of active subsystems.  Each hierarchy is either
+nameless, or has a unique name.
+
+The name should match [\w.-]+
+
+When passing a name=<x> option for a new hierarchy, you need to
+specify subsystems manually; the legacy behaviour of mounting all
+subsystems when none are explicitly specified is not supported when
+you give a subsystem a name.
+
+The name of the subsystem appears as part of the hierarchy description
+in /proc/mounts and /proc/<pid>/cgroups.
+
+
 3. Kernel API
 =============
 
@@ -501,7 +521,7 @@ rmdir() will fail with it. From this behavior, pre_destroy() can be
 called multiple times against a cgroup.
 
 int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-	       struct task_struct *task)
+	       struct task_struct *task, bool threadgroup)
 (cgroup_mutex held by caller)
 
 Called prior to moving a task into a cgroup; if the subsystem
@@ -509,14 +529,20 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex.
+remain valid while the caller holds cgroup_mutex. If threadgroup is
+true, then a successful result indicates that all threads in the given
+thread's threadgroup can be moved together.
 
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-	    struct cgroup *old_cgrp, struct task_struct *task)
+	    struct cgroup *old_cgrp, struct task_struct *task,
+	    bool threadgroup)
 (cgroup_mutex held by caller)
 
 Called after the task has been attached to the cgroup, to allow any
 post-attachment activity that requires memory allocations or blocking.
+If threadgroup is true, the subsystem should take care of all threads
+in the specified thread's threadgroup. Currently does not support any
+subsystem that might need the old_cgrp for every thread in the group.
 
 void fork(struct cgroup_subsy *ss, struct task_struct *task)
 

Documentation/cgroups/memory.txt

@@ -179,6 +179,9 @@ The reclaim algorithm has not been modified for cgroups, except that
 pages that are selected for reclaiming come from the per cgroup LRU
 list.
 
+NOTE: Reclaim does not work for the root cgroup, since we cannot set any
+limits on the root cgroup.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -210,6 +213,7 @@ We can alter the memory limit:
 NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
 mega or gigabytes.
 NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
+NOTE: We cannot set limits on the root cgroup any more.
 
 # cat /cgroups/0/memory.limit_in_bytes
 4194304
@@ -375,7 +379,42 @@ cgroups created below it.
 
 NOTE2: This feature can be enabled/disabled per subtree.
 
-7. TODO
+7. Soft limits
+
+Soft limits allow for greater sharing of memory. The idea behind soft limits
+is to allow control groups to use as much of the memory as needed, provided
+
+a. There is no memory contention
+b. They do not exceed their hard limit
+
+When the system detects memory contention or low memory control groups
+are pushed back to their soft limits. If the soft limit of each control
+group is very high, they are pushed back as much as possible to make
+sure that one control group does not starve the others of memory.
+
+Please note that soft limits is a best effort feature, it comes with
+no guarantees, but it does its best to make sure that when memory is
+heavily contended for, memory is allocated based on the soft limit
+hints/setup. Currently soft limit based reclaim is setup such that
+it gets invoked from balance_pgdat (kswapd).
+
+7.1 Interface
+
+Soft limits can be setup by using the following commands (in this example we
+assume a soft limit of 256 megabytes)
+
+# echo 256M > memory.soft_limit_in_bytes
+
+If we want to change this to 1G, we can at any time use
+
+# echo 1G > memory.soft_limit_in_bytes
+
+NOTE1: Soft limits take effect over a long period of time, since they involve
+       reclaiming memory for balancing between memory cgroups
+NOTE2: It is recommended to set the soft limit always below the hard limit,
+       otherwise the hard limit will take precedence.
+
+8. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first

Documentation/crypto/async-tx-api.txt

@@ -54,20 +54,23 @@ features surfaced as a result:
 
 3.1 General format of the API:
 struct dma_async_tx_descriptor *
-async_<operation>(<op specific parameters>,
-		  enum async_tx_flags flags,
-        	  struct dma_async_tx_descriptor *dependency,
-        	  dma_async_tx_callback callback_routine,
-		  void *callback_parameter);
+async_<operation>(<op specific parameters>, struct async_submit ctl *submit)
 
 3.2 Supported operations:
-memcpy       - memory copy between a source and a destination buffer
-memset       - fill a destination buffer with a byte value
-xor          - xor a series of source buffers and write the result to a
-	       destination buffer
-xor_zero_sum - xor a series of source buffers and set a flag if the
-	       result is zero.  The implementation attempts to prevent
-	       writes to memory
+memcpy  - memory copy between a source and a destination buffer
+memset  - fill a destination buffer with a byte value
+xor     - xor a series of source buffers and write the result to a
+	  destination buffer
+xor_val - xor a series of source buffers and set a flag if the
+	  result is zero.  The implementation attempts to prevent
+	  writes to memory
+pq	- generate the p+q (raid6 syndrome) from a series of source buffers
+pq_val  - validate that a p and or q buffer are in sync with a given series of
+	  sources
+datap	- (raid6_datap_recov) recover a raid6 data block and the p block
+	  from the given sources
+2data	- (raid6_2data_recov) recover 2 raid6 data blocks from the given
+	  sources
 
 3.3 Descriptor management:
 The return value is non-NULL and points to a 'descriptor' when the operation
@@ -80,8 +83,8 @@ acknowledged by the application before the offload engine driver is allowed to
 recycle (or free) the descriptor.  A descriptor can be acked by one of the
 following methods:
 1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted
-2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent
-   descriptor of a new operation.
+2/ submitting an unacknowledged descriptor as a dependency to another
+   async_tx call will implicitly set the acknowledged state.
 3/ calling async_tx_ack() on the descriptor.
 
 3.4 When does the operation execute?
@@ -119,30 +122,42 @@ of an operation.
 Perform a xor->copy->xor operation where each operation depends on the
 result from the previous operation:
 
-void complete_xor_copy_xor(void *param)
+void callback(void *param)
 {
-	printk("complete\n");
+	struct completion *cmp = param;
+
+	complete(cmp);
 }
 
-int run_xor_copy_xor(struct page **xor_srcs,
-		     int xor_src_cnt,
-		     struct page *xor_dest,
-		     size_t xor_len,
-		     struct page *copy_src,
-		     struct page *copy_dest,
-		     size_t copy_len)
+void run_xor_copy_xor(struct page **xor_srcs,
+		      int xor_src_cnt,
+		      struct page *xor_dest,
+		      size_t xor_len,
+		      struct page *copy_src,
+		      struct page *copy_dest,
+		      size_t copy_len)
 {
 	struct dma_async_tx_descriptor *tx;
+	addr_conv_t addr_conv[xor_src_cnt];
+	struct async_submit_ctl submit;
+	addr_conv_t addr_conv[NDISKS];
+	struct completion cmp;
+
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL,
+			  addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit)
 
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL);
-	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len,
-			  ASYNC_TX_DEP_ACK, tx, NULL, NULL);
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK,
-		       tx, complete_xor_copy_xor, NULL);
+	submit->depend_tx = tx;
+	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, &submit);
+
+	init_completion(&cmp);
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx,
+			  callback, &cmp, addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit);
 
 	async_tx_issue_pending_all();
+
+	wait_for_completion(&cmp);
 }
 
 See include/linux/async_tx.h for more information on the flags.  See the

Documentation/filesystems/sharedsubtree.txt

@@ -4,7 +4,7 @@ Shared Subtrees
 Contents:
 	1) Overview
 	2) Features
-	3) smount command
+	3) Setting mount states
 	4) Use-case
 	5) Detailed semantics
 	6) Quiz
@@ -41,14 +41,14 @@ replicas continue to be exactly same.
 
 	Here is an example:
 
-	Lets say /mnt has a mount that is shared.
+	Let's say /mnt has a mount that is shared.
 	mount --make-shared /mnt
 
-	note: mount command does not yet support the --make-shared flag.
-	I have included a small C program which does the same by executing
-	'smount /mnt shared'
+	Note: mount(8) command now supports the --make-shared flag,
+	so the sample 'smount' program is no longer needed and has been
+	removed.
 
-	#mount --bind /mnt /tmp
+	# mount --bind /mnt /tmp
 	The above command replicates the mount at /mnt to the mountpoint /tmp
 	and the contents of both the mounts remain identical.
 
@@ -58,8 +58,8 @@ replicas continue to be exactly same.
 	#ls /tmp
 	a b c
 
-	Now lets say we mount a device at /tmp/a
-	#mount /dev/sd0  /tmp/a
+	Now let's say we mount a device at /tmp/a
+	# mount /dev/sd0  /tmp/a
 
 	#ls /tmp/a
 	t1 t2 t2
@@ -80,21 +80,20 @@ replicas continue to be exactly same.
 
 	Here is an example:
 
-	Lets say /mnt has a mount which is shared.
-	#mount --make-shared /mnt
+	Let's say /mnt has a mount which is shared.
+	# mount --make-shared /mnt
 
-	Lets bind mount /mnt to /tmp
-	#mount --bind /mnt /tmp
+	Let's bind mount /mnt to /tmp
+	# mount --bind /mnt /tmp
 
 	the new mount at /tmp becomes a shared mount and it is a replica of
 	the mount at /mnt.
 
-	Now lets make the mount at /tmp; a slave of /mnt
-	#mount --make-slave /tmp
-	[or smount /tmp slave]
+	Now let's make the mount at /tmp; a slave of /mnt
+	# mount --make-slave /tmp
 
-	lets mount /dev/sd0 on /mnt/a
-	#mount /dev/sd0 /mnt/a
+	let's mount /dev/sd0 on /mnt/a
+	# mount /dev/sd0 /mnt/a
 
 	#ls /mnt/a
 	t1 t2 t3
@@ -104,9 +103,9 @@ replicas continue to be exactly same.
 
 	Note the mount event has propagated to the mount at /tmp
 
-	However lets see what happens if we mount something on the mount at /tmp
+	However let's see what happens if we mount something on the mount at /tmp
 
-	#mount /dev/sd1 /tmp/b
+	# mount /dev/sd1 /tmp/b
 
 	#ls /tmp/b
 	s1 s2 s3
@@ -124,12 +123,11 @@ replicas continue to be exactly same.
 
 2d) A unbindable mount is a unbindable private mount
 
-	lets say we have a mount at /mnt and we make is unbindable
+	let's say we have a mount at /mnt and we make is unbindable
 
-	#mount --make-unbindable /mnt
-	 [ smount /mnt  unbindable ]
+	# mount --make-unbindable /mnt
 
-	 Lets try to bind mount this mount somewhere else.
+	 Let's try to bind mount this mount somewhere else.
 	 # mount --bind /mnt /tmp
 	 mount: wrong fs type, bad option, bad superblock on /mnt,
 	        or too many mounted file systems
@@ -137,149 +135,15 @@ replicas continue to be exactly same.
 	Binding a unbindable mount is a invalid operation.
 
 
-3) smount command
+3) Setting mount states
 
-	Currently the mount command is not aware of shared subtree features.
-	Work is in progress to add the support in mount ( util-linux package ).
-	Till then use the following program.
+	The mount command (util-linux package) can be used to set mount
+	states:
 
-	------------------------------------------------------------------------
-	//
-	//this code was developed my Miklos Szeredi <miklos@szeredi.hu>
-	//and modified by Ram Pai <linuxram@us.ibm.com>
-	// sample usage:
-	//              smount /tmp shared
-	//
-	#include <stdio.h>
-	#include <stdlib.h>
-	#include <unistd.h>
-	#include <string.h>
-	#include <sys/mount.h>
-	#include <sys/fsuid.h>
-
-	#ifndef MS_REC
-	#define MS_REC		0x4000	/* 16384: Recursive loopback */
-	#endif
-
-	#ifndef MS_SHARED
-	#define MS_SHARED		1<<20	/* Shared */
-	#endif
-
-	#ifndef MS_PRIVATE
-	#define MS_PRIVATE		1<<18	/* Private */
-	#endif
-
-	#ifndef MS_SLAVE
-	#define MS_SLAVE		1<<19	/* Slave */
-	#endif
-
-	#ifndef MS_UNBINDABLE
-	#define MS_UNBINDABLE		1<<17	/* Unbindable */
-	#endif
-
-	int main(int argc, char *argv[])
-	{
-		int type;
-		if(argc != 3) {
-			fprintf(stderr, "usage: %s dir "
-			"<rshared|rslave|rprivate|runbindable|shared|slave"
-			"|private|unbindable>\n" , argv[0]);
-			return 1;
-		}
-
-		fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]);
-
-		if (strcmp(argv[2],"rshared")==0)
-			type=(MS_SHARED|MS_REC);
-		else if (strcmp(argv[2],"rslave")==0)
-			type=(MS_SLAVE|MS_REC);
-		else if (strcmp(argv[2],"rprivate")==0)
-			type=(MS_PRIVATE|MS_REC);
-		else if (strcmp(argv[2],"runbindable")==0)
-			type=(MS_UNBINDABLE|MS_REC);
-		else if (strcmp(argv[2],"shared")==0)
-			type=MS_SHARED;
-		else if (strcmp(argv[2],"slave")==0)
-			type=MS_SLAVE;
-		else if (strcmp(argv[2],"private")==0)
-			type=MS_PRIVATE;
-		else if (strcmp(argv[2],"unbindable")==0)
-			type=MS_UNBINDABLE;
-		else {
-			fprintf(stderr, "invalid operation: %s\n", argv[2]);
-			return 1;
-		}
-		setfsuid(getuid());
-
-		if(mount("", argv[1], "dontcare", type, "") == -1) {
-			perror("mount");
-			return 1;
-		}
-		return 0;
-	}
-	-----------------------------------------------------------------------
-
-	Copy the above code snippet into smount.c
-	gcc -o smount smount.c
-
-
-	(i) To mark all the mounts under /mnt as shared execute the following
-	command:
-
-	 	smount /mnt rshared
-		the corresponding syntax planned for mount command is
-		mount --make-rshared /mnt
-
-	    just to mark a mount /mnt as shared, execute the following
-	    command:
-	 	smount /mnt shared
-		the corresponding syntax planned for mount command is
-		mount --make-shared /mnt
-
-	(ii) To mark all the shared mounts under /mnt as slave execute the
-	following
-
-	     command:
-		smount /mnt rslave
-		the corresponding syntax planned for mount command is
-		mount --make-rslave /mnt
-
-	    just to mark a mount /mnt as slave, execute the following
-	    command:
-	 	smount /mnt slave
-		the corresponding syntax planned for mount command is
-		mount --make-slave /mnt
-
-	(iii) To mark all the mounts under /mnt as private execute the
-	following command:
-
-		smount /mnt rprivate
-		the corresponding syntax planned for mount command is
-		mount --make-rprivate /mnt
-
-	    just to mark a mount /mnt as private, execute the following
-	    command:
-	 	smount /mnt private
-		the corresponding syntax planned for mount command is
-		mount --make-private /mnt
-
-	      NOTE: by default all the mounts are created as private. But if
-	      you want to change some shared/slave/unbindable  mount as
-	      private at a later point in time, this command can help.
-
-	(iv) To mark all the mounts under /mnt as unbindable execute the
-	following
-
-	     command:
-		smount /mnt runbindable
-		the corresponding syntax planned for mount command is
-		mount --make-runbindable /mnt
-
-	    just to mark a mount /mnt as unbindable, execute the following
-	    command:
-	 	smount /mnt unbindable
-		the corresponding syntax planned for mount command is
-		mount --make-unbindable /mnt
+	mount --make-shared mountpoint
+	mount --make-slave mountpoint
+	mount --make-private mountpoint
+	mount --make-unbindable mountpoint
 
 
 4) Use cases
@@ -350,7 +214,7 @@ replicas continue to be exactly same.
 		mount --rbind / /view/v3
 		mount --rbind / /view/v4
 
-		and if /usr has a versioning filesystem mounted, than that
+		and if /usr has a versioning filesystem mounted, then that
 		mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and
 		/view/v4/usr too
 
@@ -390,7 +254,7 @@ replicas continue to be exactly same.
 
 		For example:
 			mount --make-shared /mnt
-			mount --bin /mnt /tmp
+			mount --bind /mnt /tmp
 
 		The mount at /mnt and that at /tmp are both shared and belong
 		to the same peer group. Anything mounted or unmounted under
@@ -558,7 +422,7 @@ replicas continue to be exactly same.
 	then the subtree under the unbindable mount is pruned in the new
 	location.
 
-	eg: lets say we have the following mount tree.
+	eg: let's say we have the following mount tree.
 
 		A
 	      /   \
@@ -566,7 +430,7 @@ replicas continue to be exactly same.
 	     / \ / \
 	     D E F G
 
-	     Lets say all the mount except the mount C in the tree are
+	     Let's say all the mount except the mount C in the tree are
 	     of a type other than unbindable.
 
 	     If this tree is rbound to say Z
@@ -683,13 +547,13 @@ replicas continue to be exactly same.
 	'b' on mounts that receive propagation from mount 'B' and does not have
 	sub-mounts within them are unmounted.
 
-	Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to
+	Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to
 	each other.
 
-	lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
+	let's say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
 	'B1', 'B2' and 'B3' respectively.
 
-	lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
+	let's say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
 	mount 'B1', 'B2' and 'B3' respectively.
 
 	if 'C1' is unmounted, all the mounts that are most-recently-mounted on
@@ -710,7 +574,7 @@ replicas continue to be exactly same.
 	A cloned namespace contains all the mounts as that of the parent
 	namespace.
 
-	Lets say 'A' and 'B' are the corresponding mounts in the parent and the
+	Let's say 'A' and 'B' are the corresponding mounts in the parent and the
 	child namespace.
 
 	If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to
@@ -759,11 +623,11 @@ replicas continue to be exactly same.
 		mount --make-slave /mnt
 
 		At this point we have the first mount at /tmp and
-		its root dentry is 1. Lets call this mount 'A'
+		its root dentry is 1. Let's call this mount 'A'
 		And then we have a second mount at /tmp1 with root
-		dentry 2. Lets call this mount 'B'
+		dentry 2. Let's call this mount 'B'
 		Next we have a third mount at /mnt with root dentry
-		mnt. Lets call this mount 'C'
+		mnt. Let's call this mount 'C'
 
 		'B' is the slave of 'A' and 'C' is a slave of 'B'
 		A -> B -> C
@@ -794,7 +658,7 @@ replicas continue to be exactly same.
 
 	Q3 Why is unbindable mount needed?
 
-		Lets say we want to replicate the mount tree at multiple
+		Let's say we want to replicate the mount tree at multiple
 		locations within the same subtree.
 
 		if one rbind mounts a tree within the same subtree 'n' times
@@ -803,7 +667,7 @@ replicas continue to be exactly same.
 		mounts. Here is a example.
 
 		step 1:
-		   lets say the root tree has just two directories with
+		   let's say the root tree has just two directories with
 		   one vfsmount.
 				    root
 				   /    \
@@ -875,7 +739,7 @@ replicas continue to be exactly same.
 		Unclonable mounts come in handy here.
 
 		step 1:
-		   lets say the root tree has just two directories with
+		   let's say the root tree has just two directories with
 		   one vfsmount.
 				    root
 				   /    \

Documentation/filesystems/vfs.txt

@@ -536,6 +536,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
+	int (*error_remove_page) (struct mapping *mapping, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations {
   	prevent redirtying the page, it is kept locked during the whole
 	operation.
 
+  error_remove_page: normally set to generic_error_remove_page if truncation
+	is ok for this address space. Used for memory failure handling.
+	Setting this implies you deal with pages going away under you,
+	unless you have them locked or reference counts increased.
+
+
 The File Object
 ===============
 

Documentation/ioctl/ioctl-number.txt

@@ -135,6 +135,7 @@ Code	Seq#	Include File		Comments
 					<http://mikonos.dia.unisa.it/tcfs>
 'l'	40-7F	linux/udf_fs_i.h	in development:
 					<http://sourceforge.net/projects/linux-udf/>
+'m'	00-09	linux/mmtimer.h
 'm'	all	linux/mtio.h		conflict!
 'm'	all	linux/soundcard.h	conflict!
 'm'	all	linux/synclink.h	conflict!

Documentation/sysctl/fs.txt

@@ -96,13 +96,16 @@ handles that the Linux kernel will allocate. When you get lots
 of error messages about running out of file handles, you might
 want to increase this limit.
 
-The three values in file-nr denote the number of allocated
-file handles, the number of unused file handles and the maximum
-number of file handles. When the allocated file handles come
-close to the maximum, but the number of unused file handles is
-significantly greater than 0, you've encountered a peak in your 
-usage of file handles and you don't need to increase the maximum.
-
+Historically, the three values in file-nr denoted the number of
+allocated file handles, the number of allocated but unused file
+handles, and the maximum number of file handles. Linux 2.6 always
+reports 0 as the number of free file handles -- this is not an
+error, it just means that the number of allocated file handles
+exactly matches the number of used file handles.
+
+Attempts to allocate more file descriptors than file-max are
+reported with printk, look for "VFS: file-max limit <number>
+reached".
 ==============================================================
 
 nr_open:

Documentation/sysctl/kernel.txt

@@ -22,6 +22,7 @@ show up in /proc/sys/kernel:
 - callhome		     [ S390 only ]
 - auto_msgmni
 - core_pattern
+- core_pipe_limit
 - core_uses_pid
 - ctrl-alt-del
 - dentry-state
@@ -135,6 +136,27 @@ core_pattern is used to specify a core dumpfile pattern name.
 
 ==============================================================
 
+core_pipe_limit:
+
+This sysctl is only applicable when core_pattern is configured to pipe core
+files to user space helper a (when the first character of core_pattern is a '|',
+see above).  When collecting cores via a pipe to an application, it is
+occasionally usefull for the collecting application to gather data about the
+crashing process from its /proc/pid directory.  In order to do this safely, the
+kernel must wait for the collecting process to exit, so as not to remove the
+crashing processes proc files prematurely.  This in turn creates the possibility
+that a misbehaving userspace collecting process can block the reaping of a
+crashed process simply by never exiting.  This sysctl defends against that.  It
+defines how many concurrent crashing processes may be piped to user space
+applications in parallel.  If this value is exceeded, then those crashing
+processes above that value are noted via the kernel log and their cores are
+skipped.  0 is a special value, indicating that unlimited processes may be
+captured in parallel, but that no waiting will take place (i.e. the collecting
+process is not guaranteed access to /proc/<crahing pid>/).  This value defaults
+to 0.
+
+==============================================================
+
 core_uses_pid:
 
 The default coredump filename is "core".  By setting

Documentation/sysctl/vm.txt

@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm:
 - legacy_va_layout
 - lowmem_reserve_ratio
 - max_map_count
+- memory_failure_early_kill
+- memory_failure_recovery
 - min_free_kbytes
 - min_slab_ratio
 - min_unmapped_ratio
@@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm:
 - vfs_cache_pressure
 - zone_reclaim_mode
 
-
 ==============================================================
 
 block_dump
@@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation.
 
 The default value is 65536.
 
+=============================================================
+
+memory_failure_early_kill:
+
+Control how to kill processes when uncorrected memory error (typically
+a 2bit error in a memory module) is detected in the background by hardware
+that cannot be handled by the kernel. In some cases (like the page
+still having a valid copy on disk) the kernel will handle the failure
+transparently without affecting any applications. But if there is
+no other uptodate copy of the data it will kill to prevent any data
+corruptions from propagating.
+
+1: Kill all processes that have the corrupted and not reloadable page mapped
+as soon as the corruption is detected.  Note this is not supported
+for a few types of pages, like kernel internally allocated data or
+the swap cache, but works for the majority of user pages.
+
+0: Only unmap the corrupted page from all processes and only kill a process
+who tries to access it.
+
+The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can
+handle this if they want to.
+
+This is only active on architectures/platforms with advanced machine
+check handling and depends on the hardware capabilities.
+
+Applications can override this setting individually with the PR_MCE_KILL prctl
+
+==============================================================
+
+memory_failure_recovery
+
+Enable memory failure recovery (when supported by the platform)
+
+1: Attempt recovery.
+
+0: Always panic on a memory failure.
+
 ==============================================================
 
 min_free_kbytes:

Documentation/vm/.gitignore

+page-types
 slabinfo

Documentation/vm/locking

@@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the
 mm start up ... this is a loose form of stability on mm_users. For
 example, it is used in copy_mm to protect against a racing tlb_gather_mmu
 single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might 
+truncate) does not lose sending ipi's to cloned threads that might
 be spawned underneath it and go to user mode to drag in pte's into tlbs.
 
 swap_lock

Documentation/vm/page-types.c

@@ -5,6 +5,7 @@
  * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
  */
 
+#define _LARGEFILE64_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -13,11 +14,32 @@
 #include <string.h>
 #include <getopt.h>
 #include <limits.h>
+#include <assert.h>
 #include <sys/types.h>
 #include <sys/errno.h>
 #include <sys/fcntl.h>
 
 
+/*
+ * pagemap kernel ABI bits
+ */
+
+#define PM_ENTRY_BYTES      sizeof(uint64_t)
+#define PM_STATUS_BITS      3
+#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS      6
+#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+
+
 /*
  * kernel page flags
  */
@@ -126,6 +148,14 @@ static int		nr_addr_ranges;
 static unsigned long	opt_offset[MAX_ADDR_RANGES];
 static unsigned long	opt_size[MAX_ADDR_RANGES];
 
+#define MAX_VMAS	10240
+static int		nr_vmas;
+static unsigned long	pg_start[MAX_VMAS];
+static unsigned long	pg_end[MAX_VMAS];
+static unsigned long	voffset;
+
+static int		pagemap_fd;
+
 #define MAX_BIT_FILTERS	64
 static int		nr_bit_filters;
 static uint64_t		opt_mask[MAX_BIT_FILTERS];
@@ -135,7 +165,6 @@ static int		page_size;
 
 #define PAGES_BATCH	(64 << 10)	/* 64k pages */
 static int		kpageflags_fd;
-static uint64_t		kpageflags_buf[KPF_BYTES * PAGES_BATCH];
 
 #define HASH_SHIFT	13
 #define HASH_SIZE	(1 << HASH_SHIFT)
@@ -158,6 +187,11 @@ static uint64_t 	page_flags[HASH_SIZE];
 	type __min2 = (y);			\
 	__min1 < __min2 ? __min1 : __min2; })
 
+#define max_t(type, x, y) ({			\
+	type __max1 = (x);			\
+	type __max2 = (y);			\
+	__max1 > __max2 ? __max1 : __max2; })
+
 static unsigned long pages2mb(unsigned long pages)
 {
 	return (pages * page_size) >> 20;
@@ -224,26 +258,34 @@ static char *page_flag_longname(uint64_t flags)
 static void show_page_range(unsigned long offset, uint64_t flags)
 {
 	static uint64_t      flags0;
+	static unsigned long voff;
 	static unsigned long index;
 	static unsigned long count;
 
-	if (flags == flags0 && offset == index + count) {
+	if (flags == flags0 && offset == index + count &&
+	    (!opt_pid || voffset == voff + count)) {
 		count++;
 		return;
 	}
 
-	if (count)
-		printf("%lu\t%lu\t%s\n",
+	if (count) {
+		if (opt_pid)
+			printf("%lx\t", voff);
+		printf("%lx\t%lx\t%s\n",
 				index, count, page_flag_name(flags0));
+	}
 
 	flags0 = flags;
 	index  = offset;
+	voff   = voffset;
 	count  = 1;
 }
 
 static void show_page(unsigned long offset, uint64_t flags)
 {
-	printf("%lu\t%s\n", offset, page_flag_name(flags));
+	if (opt_pid)
+		printf("%lx\t", voffset);
+	printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
 static void show_summary(void)
@@ -383,6 +425,8 @@ static void walk_pfn(unsigned long index, unsigned long count)
 	lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
 
 	while (count) {
+		uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH];
+
 		batch = min_t(unsigned long, count, PAGES_BATCH);
 		n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
 		if (n == 0)
@@ -404,6 +448,81 @@ static void walk_pfn(unsigned long index, unsigned long count)
 	}
 }
 
+
+#define PAGEMAP_BATCH	4096
+static unsigned long task_pfn(unsigned long pgoff)
+{
+	static uint64_t buf[PAGEMAP_BATCH];
+	static unsigned long start;
+	static long count;
+	uint64_t pfn;
+
+	if (pgoff < start || pgoff >= start + count) {
+		if (lseek64(pagemap_fd,
+			    (uint64_t)pgoff * PM_ENTRY_BYTES,
+			    SEEK_SET) < 0) {
+			perror("pagemap seek");
+			exit(EXIT_FAILURE);
+		}
+		count = read(pagemap_fd, buf, sizeof(buf));
+		if (count == 0)
+			return 0;
+		if (count < 0) {
+			perror("pagemap read");
+			exit(EXIT_FAILURE);
+		}
+		if (count % PM_ENTRY_BYTES) {
+			fatal("pagemap read not aligned.\n");
+			exit(EXIT_FAILURE);
+		}
+		count /= PM_ENTRY_BYTES;
+		start = pgoff;
+	}
+
+	pfn = buf[pgoff - start];
+	if (pfn & PM_PRESENT)
+		pfn = PM_PFRAME(pfn);
+	else
+		pfn = 0;
+
+	return pfn;
+}
+
+static void walk_task(unsigned long index, unsigned long count)
+{
+	int i = 0;
+	const unsigned long end = index + count;
+
+	while (index < end) {
+
+		while (pg_end[i] <= index)
+			if (++i >= nr_vmas)
+				return;
+		if (pg_start[i] >= end)
+			return;
+
+		voffset = max_t(unsigned long, pg_start[i], index);
+		index   = min_t(unsigned long, pg_end[i], end);
+
+		assert(voffset < index);
+		for (; voffset < index; voffset++) {
+			unsigned long pfn = task_pfn(voffset);
+			if (pfn)
+				walk_pfn(pfn, 1);
+		}
+	}
+}
+
+static void add_addr_range(unsigned long offset, unsigned long size)
+{
+	if (nr_addr_ranges >= MAX_ADDR_RANGES)
+		fatal("too many addr ranges\n");
+
+	opt_offset[nr_addr_ranges] = offset;
+	opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset);
+	nr_addr_ranges++;
+}
+
 static void walk_addr_ranges(void)
 {
 	int i;
@@ -415,10 +534,13 @@ static void walk_addr_ranges(void)
 	}
 
 	if (!nr_addr_ranges)
-		walk_pfn(0, ULONG_MAX);
+		add_addr_range(0, ULONG_MAX);
 
 	for (i = 0; i < nr_addr_ranges; i++)
-		walk_pfn(opt_offset[i], opt_size[i]);
+		if (!opt_pid)
+			walk_pfn(opt_offset[i], opt_size[i]);
+		else
+			walk_task(opt_offset[i], opt_size[i]);
 
 	close(kpageflags_fd);
 }
@@ -446,8 +568,8 @@ static void usage(void)
 "            -r|--raw                  Raw mode, for kernel developers\n"
 "            -a|--addr    addr-spec    Walk a range of pages\n"
 "            -b|--bits    bits-spec    Walk pages with specified bits\n"
-#if 0 /* planned features */
 "            -p|--pid     pid          Walk process address space\n"
+#if 0 /* planned features */
 "            -f|--file    filename     Walk file address space\n"
 #endif
 "            -l|--list                 Show page details in ranges\n"
@@ -459,7 +581,7 @@ static void usage(void)
 "            N+M                       pages range from N to N+M-1\n"
 "            N,M                       pages range from N to M-1\n"
 "            N,                        pages range from N to end\n"
-"            ,M                        pages range from 0 to M\n"
+"            ,M                        pages range from 0 to M-1\n"
 "bits-spec:\n"
 "            bit1,bit2                 (flags & (bit1|bit2)) != 0\n"
 "            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1\n"
@@ -496,21 +618,57 @@ static unsigned long long parse_number(const char *str)
 
 static void parse_pid(const char *str)
 {
+	FILE *file;
+	char buf[5000];
+
 	opt_pid = parse_number(str);
-}
 
-static void parse_file(const char *name)
-{
+	sprintf(buf, "/proc/%d/pagemap", opt_pid);
+	pagemap_fd = open(buf, O_RDONLY);
+	if (pagemap_fd < 0) {
+		perror(buf);
+		exit(EXIT_FAILURE);
+	}
+
+	sprintf(buf, "/proc/%d/maps", opt_pid);
+	file = fopen(buf, "r");
+	if (!file) {
+		perror(buf);
+		exit(EXIT_FAILURE);
+	}
+
+	while (fgets(buf, sizeof(buf), file) != NULL) {
+		unsigned long vm_start;
+		unsigned long vm_end;
+		unsigned long long pgoff;
+		int major, minor;
+		char r, w, x, s;
+		unsigned long ino;
+		int n;
+
+		n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu",
+			   &vm_start,
+			   &vm_end,
+			   &r, &w, &x, &s,
+			   &pgoff,
+			   &major, &minor,
+			   &ino);
+		if (n < 10) {
+			fprintf(stderr, "unexpected line: %s\n", buf);
+			continue;
+		}
+		pg_start[nr_vmas] = vm_start / page_size;
+		pg_end[nr_vmas] = vm_end / page_size;
+		if (++nr_vmas >= MAX_VMAS) {
+			fprintf(stderr, "too many VMAs\n");
+			break;
+		}
+	}
+	fclose(file);
 }
 
-static void add_addr_range(unsigned long offset, unsigned long size)
+static void parse_file(const char *name)
 {
-	if (nr_addr_ranges >= MAX_ADDR_RANGES)
-		fatal("too much addr ranges\n");
-
-	opt_offset[nr_addr_ranges] = offset;
-	opt_size[nr_addr_ranges] = size;
-	nr_addr_ranges++;
 }
 
 static void parse_addr_range(const char *optarg)
@@ -676,8 +834,10 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (opt_list && opt_pid)
+		printf("voffset\t");
 	if (opt_list == 1)
-		printf("offset\tcount\tflags\n");
+		printf("offset\tlen\tflags\n");
 	if (opt_list == 2)
 		printf("offset\tflags\n");
 

MAINTAINERS

@@ -257,12 +257,6 @@ W:	http://www.lesswatts.org/projects/acpi/
 S:	Supported
 F:	drivers/acpi/fan.c
 
-ACPI PCI HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
-L:	linux-pci@vger.kernel.org
-S:	Supported
-F:	drivers/pci/hotplug/acpi*
-
 ACPI THERMAL DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
@@ -689,7 +683,7 @@ S:	Maintained
 ARM/INTEL IXP4XX ARM ARCHITECTURE
 M:	Imre Kaloz <kaloz@openwrt.org>
 M:	Krzysztof Halasa <khc@pm.waw.pl>
-L:	linux-arm-kernel@lists.infradead.org
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-ixp4xx/
 
@@ -746,18 +740,22 @@ M:	Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
 M:	Dirk Opfer <dirk@opfer-online.de>
 S:	Maintained
 
-ARM/PALMTX,PALMT5,PALMLD,PALMTE2 SUPPORT
-M:	Marek Vasut <marek.vasut@gmail.com>
+ARM/PALMTX,PALMT5,PALMLD,PALMTE2,PALMTC SUPPORT
+P:	Marek Vasut
+M:	marek.vasut@gmail.com
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
 
 ARM/PALM TREO 680 SUPPORT
 M:	Tomas Cech <sleep_walker@suse.cz>
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
 
 ARM/PALMZ72 SUPPORT
 M:	Sergey Lapin <slapin@ossfans.org>
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
 
@@ -2331,7 +2329,9 @@ S:	Orphan
 F:	drivers/hwmon/
 
 HARDWARE RANDOM NUMBER GENERATOR CORE
-S:	Orphan
+M:	Matt Mackall <mpm@selenic.com>
+M:	Herbert Xu <herbert@gondor.apana.org.au>
+S:	Odd fixes
 F:	Documentation/hw_random.txt
 F:	drivers/char/hw_random/
 F:	include/linux/hw_random.h
@@ -4003,11 +4003,11 @@ F:	Documentation/PCI/
 F:	drivers/pci/
 F:	include/linux/pci*
 
-PCIE HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
+PCI HOTPLUG
+M:	Jesse Barnes <jbarnes@virtuousgeek.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
-F:	drivers/pci/pcie/
+F:	drivers/pci/hotplug
 
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
@@ -4670,12 +4670,6 @@ F:	drivers/serial/serial_lh7a40x.c
 F:	drivers/usb/gadget/lh7a40*
 F:	drivers/usb/host/ohci-lh7a40*
 
-SHPC HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
-L:	linux-pci@vger.kernel.org
-S:	Supported
-F:	drivers/pci/hotplug/shpchp*
-
 SIMPLE FIRMWARE INTERFACE (SFI)
 P:	Len Brown
 M:	lenb@kernel.org
@@ -4687,7 +4681,6 @@ F:	arch/x86/kernel/*sfi*
 F:	drivers/sfi/
 F:	include/linux/sfi*.h
 
-
 SIMTEC EB110ATX (Chalice CATS)
 P:	Ben Dooks
 M:	Vincent Sanders <support@simtec.co.uk>

arch/alpha/include/asm/fcntl.h

@@ -26,6 +26,8 @@
 #define F_GETOWN	6	/*  for sockets. */
 #define F_SETSIG	10	/*  for sockets. */
 #define F_GETSIG	11	/*  for sockets. */
+#define F_SETOWN_EX	12
+#define F_GETOWN_EX	13
 
 /* for posix fcntl() and lockf() */
 #define F_RDLCK		1

arch/alpha/kernel/core_marvel.c

@@ -1016,7 +1016,7 @@ marvel_agp_bind_memory(alpha_agp_info *agp, off_t pg_start, struct agp_memory *m
 {
 	struct marvel_agp_aperture *aper = agp->aperture.sysdata;
 	return iommu_bind(aper->arena, aper->pg_start + pg_start, 
-			  mem->page_count, mem->memory);
+			  mem->page_count, mem->pages);
 }
 
 static int 

arch/alpha/kernel/core_titan.c

@@ -680,7 +680,7 @@ titan_agp_bind_memory(alpha_agp_info *agp, off_t pg_start, struct agp_memory *me
 {
 	struct titan_agp_aperture *aper = agp->aperture.sysdata;
 	return iommu_bind(aper->arena, aper->pg_start + pg_start, 
-			  mem->page_count, mem->memory);
+			  mem->page_count, mem->pages);
 }
 
 static int 

arch/alpha/kernel/init_task.c

@@ -13,6 +13,5 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct task_struct init_task = INIT_TASK(init_task);
 EXPORT_SYMBOL(init_task);
 
-union thread_union init_thread_union
-	__attribute__((section(".data.init_thread")))
-	= { INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union __init_task_data =
+	{ INIT_THREAD_INFO(init_task) };

arch/alpha/kernel/pci_impl.h

@@ -198,7 +198,7 @@ extern unsigned long size_for_memory(unsigned long max);
 
 extern int iommu_reserve(struct pci_iommu_arena *, long, long);
 extern int iommu_release(struct pci_iommu_arena *, long, long);
-extern int iommu_bind(struct pci_iommu_arena *, long, long, unsigned long *);
+extern int iommu_bind(struct pci_iommu_arena *, long, long, struct page **);
 extern int iommu_unbind(struct pci_iommu_arena *, long, long);
 
 

arch/alpha/kernel/pci_iommu.c

@@ -876,7 +876,7 @@ iommu_release(struct pci_iommu_arena *arena, long pg_start, long pg_count)
 
 int
 iommu_bind(struct pci_iommu_arena *arena, long pg_start, long pg_count, 
-	   unsigned long *physaddrs)
+	   struct page **pages)
 {
 	unsigned long flags;
 	unsigned long *ptes;
@@ -896,7 +896,7 @@ iommu_bind(struct pci_iommu_arena *arena, long pg_start, long pg_count,
 	}
 		
 	for(i = 0, j = pg_start; i < pg_count; i++, j++)
-		ptes[j] = mk_iommu_pte(physaddrs[i]);
+		ptes[j] = mk_iommu_pte(page_to_phys(pages[i]));
 
 	spin_unlock_irqrestore(&arena->lock, flags);
 

arch/alpha/kernel/vmlinux.lds.S

 #include <asm-generic/vmlinux.lds.h>
 #include <asm/page.h>
+#include <asm/thread_info.h>
 
 OUTPUT_FORMAT("elf64-alpha")
 OUTPUT_ARCH(alpha)
@@ -31,88 +32,21 @@ SECTIONS
 	} :kernel
 
 	RODATA
-
-	/* Exception table */
-	. = ALIGN(16);
-	__ex_table : {
-		__start___ex_table = .;
-		*(__ex_table)
-		__stop___ex_table = .;
-	}
+	EXCEPTION_TABLE(16)
 
 	/* Will be freed after init */
-	. = ALIGN(PAGE_SIZE);
-	/* Init code and data */
-	__init_begin = .;
-	.init.text : {
-		_sinittext = .;
-		INIT_TEXT
-		_einittext = .;
-	}
-	.init.data : {
-		INIT_DATA
-	}
-
-	. = ALIGN(16);
-	.init.setup : {
-		__setup_start = .;
-		*(.init.setup)
-		__setup_end = .;
-	}
-
-	. = ALIGN(8);
-	.initcall.init : {
-		__initcall_start = .;
-		INITCALLS
-		__initcall_end = .;
-	}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
-	.init.ramfs : {
-		__initramfs_start = .;
-		*(.init.ramfs)
-		__initramfs_end = .;
-	}
-#endif
-
-	. = ALIGN(8);
-	.con_initcall.init : {
-		__con_initcall_start = .;
-		*(.con_initcall.init)
-		__con_initcall_end = .;
-	}
-
-	. = ALIGN(8);
-	SECURITY_INIT
-
+	__init_begin = ALIGN(PAGE_SIZE);
+	INIT_TEXT_SECTION(PAGE_SIZE)
+	INIT_DATA_SECTION(16)
 	PERCPU(PAGE_SIZE)
-
-	. = ALIGN(2 * PAGE_SIZE);
+	/* Align to THREAD_SIZE rather than PAGE_SIZE here so any padding page
+	   needed for the THREAD_SIZE aligned init_task gets freed after init */
+	. = ALIGN(THREAD_SIZE);
 	__init_end = .;
 	/* Freed after init ends here */
 
-	/* Note 2 page alignment above.  */
-	.data.init_thread : {
-		*(.data.init_thread)
-	}
-
-	. = ALIGN(PAGE_SIZE);
-	.data.page_aligned : {
-		*(.data.page_aligned)
-	}
-
-	. = ALIGN(64);
-	.data.cacheline_aligned : {
-		*(.data.cacheline_aligned)
-	}
-
 	_data = .;
-	/* Data */
-	.data : {
-		DATA_DATA
-		CONSTRUCTORS
-	}
+	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
 
 	.got : {
 		*(.got)
@@ -122,16 +56,7 @@ SECTIONS
 	}
 	_edata = .;	/* End of data section */
 
-	__bss_start = .;
-	.sbss : {
-		*(.sbss)
-		*(.scommon)
-	}
-	.bss : {
-		*(.bss)
-		*(COMMON)
-	}
-	__bss_stop = .;
+	BSS_SECTION(0, 0, 0)
 	_end = .;
 
 	.mdebug 0 : {

arch/arm/Kconfig

@@ -46,6 +46,10 @@ config GENERIC_CLOCKEVENTS_BROADCAST
 	depends on GENERIC_CLOCKEVENTS
 	default y if SMP && !LOCAL_TIMERS
 
+config HAVE_TCM
+	bool
+	select GENERIC_ALLOCATOR
+
 config NO_IOPORT
 	bool
 
@@ -649,6 +653,7 @@ config ARCH_U300
 	bool "ST-Ericsson U300 Series"
 	depends on MMU
 	select CPU_ARM926T
+	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_VIC
 	select GENERIC_TIME

arch/arm/common/locomo.c

@@ -865,6 +865,7 @@ void locomo_gpio_set_dir(struct device *dev, unsigned int bits, unsigned int dir
 
 	spin_unlock_irqrestore(&lchip->lock, flags);
 }
+EXPORT_SYMBOL(locomo_gpio_set_dir);
 
 int locomo_gpio_read_level(struct device *dev, unsigned int bits)
 {
@@ -882,6 +883,7 @@ int locomo_gpio_read_level(struct device *dev, unsigned int bits)
 	ret &= bits;
 	return ret;
 }
+EXPORT_SYMBOL(locomo_gpio_read_level);
 
 int locomo_gpio_read_output(struct device *dev, unsigned int bits)
 {
@@ -899,6 +901,7 @@ int locomo_gpio_read_output(struct device *dev, unsigned int bits)
 	ret &= bits;
 	return ret;
 }
+EXPORT_SYMBOL(locomo_gpio_read_output);
 
 void locomo_gpio_write(struct device *dev, unsigned int bits, unsigned int set)
 {
@@ -920,6 +923,7 @@ void locomo_gpio_write(struct device *dev, unsigned int bits, unsigned int set)
 
 	spin_unlock_irqrestore(&lchip->lock, flags);
 }
+EXPORT_SYMBOL(locomo_gpio_write);
 
 static void locomo_m62332_sendbit(void *mapbase, int bit)
 {
@@ -1084,13 +1088,12 @@ void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int
 
 	spin_unlock_irqrestore(&lchip->lock, flags);
 }
+EXPORT_SYMBOL(locomo_m62332_senddata);
 
 /*
  *	Frontlight control
  */
 
-static struct locomo *locomo_chip_driver(struct locomo_dev *ldev);
-
 void locomo_frontlight_set(struct locomo_dev *dev, int duty, int vr, int bpwf)
 {
 	unsigned long flags;
@@ -1182,11 +1185,13 @@ int locomo_driver_register(struct locomo_driver *driver)
 	driver->drv.bus = &locomo_bus_type;
 	return driver_register(&driver->drv);
 }
+EXPORT_SYMBOL(locomo_driver_register);
 
 void locomo_driver_unregister(struct locomo_driver *driver)
 {
 	driver_unregister(&driver->drv);
 }
+EXPORT_SYMBOL(locomo_driver_unregister);
 
 static int __init locomo_init(void)
 {
@@ -1208,11 +1213,3 @@ module_exit(locomo_exit);
 MODULE_DESCRIPTION("Sharp LoCoMo core driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("John Lenz <lenz@cs.wisc.edu>");
-
-EXPORT_SYMBOL(locomo_driver_register);
-EXPORT_SYMBOL(locomo_driver_unregister);
-EXPORT_SYMBOL(locomo_gpio_set_dir);
-EXPORT_SYMBOL(locomo_gpio_read_level);
-EXPORT_SYMBOL(locomo_gpio_read_output);
-EXPORT_SYMBOL(locomo_gpio_write);
-EXPORT_SYMBOL(locomo_m62332_senddata);

arch/arm/common/vic.c

@@ -22,6 +22,7 @@
 #include <linux/list.h>
 #include <linux/io.h>
 #include <linux/sysdev.h>
+#include <linux/device.h>
 #include <linux/amba/bus.h>
 
 #include <asm/mach/irq.h>

arch/arm/include/asm/atomic.h

@@ -19,31 +19,21 @@
 
 #ifdef __KERNEL__
 
+/*
+ * On ARM, ordinary assignment (str instruction) doesn't clear the local
+ * strex/ldrex monitor on some implementations. The reason we can use it for
+ * atomic_set() is the clrex or dummy strex done on every exception return.
+ */
 #define atomic_read(v)	((v)->counter)
+#define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
 
 /*
  * ARMv6 UP and SMP safe atomic ops.  We use load exclusive and
  * store exclusive to ensure that these are atomic.  We may loop
- * to ensure that the update happens.  Writing to 'v->counter'
- * without using the following operations WILL break the atomic
- * nature of these ops.
+ * to ensure that the update happens.
  */
-static inline void atomic_set(atomic_t *v, int i)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__("@ atomic_set\n"
-"1:	ldrex	%0, [%1]\n"
-"	strex	%0, %2, [%1]\n"
-"	teq	%0, #0\n"
-"	bne	1b"
-	: "=&r" (tmp)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	unsigned long tmp;
@@ -163,8 +153,6 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-#define atomic_set(v,i)	(((v)->counter) = (i))
-
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long flags;

arch/arm/include/asm/cache.h

@@ -4,7 +4,7 @@
 #ifndef __ASMARM_CACHE_H
 #define __ASMARM_CACHE_H
 
-#define L1_CACHE_SHIFT		5
+#define L1_CACHE_SHIFT		CONFIG_ARM_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
 /*

arch/arm/include/asm/cputype.h

@@ -63,6 +63,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CPUID_CACHETYPE);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
+{
+	return read_cpuid(CPUID_TCM);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For
@@ -73,7 +78,10 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 #else
 static inline int cpu_is_xsc3(void)
 {
-	if ((read_cpuid_id() & 0xffffe000) == 0x69056000)
+	unsigned int id;
+	id = read_cpuid_id() & 0xffffe000;
+	/* It covers both Intel ID and Marvell ID */
+	if ((id == 0x69056000) || (id == 0x56056000))
 		return 1;
 
 	return 0;

arch/arm/include/asm/hardware/iop3xx-adma.h

@@ -187,11 +187,74 @@ union iop3xx_desc {
 	void *ptr;
 };
 
+/* No support for p+q operations */
+static inline int
+iop_chan_pq_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
+			 dma_addr_t addr, unsigned char coef)
+{
+	BUG();
+}
+
+static inline int
+iop_chan_pq_zero_sum_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+			  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
+{
+	BUG();
+}
+
+#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
+
+static inline void
+iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
+			      dma_addr_t *src)
+{
+	BUG();
+}
+
 static inline int iop_adma_get_max_xor(void)
 {
 	return 32;
 }
 
+static inline int iop_adma_get_max_pq(void)
+{
+	BUG();
+	return 0;
+}
+
 static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
 {
 	int id = chan->device->id;
@@ -332,6 +395,11 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
 	return slot_cnt;
 }
 
+static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
+{
+	return 0;
+}
+
 static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -349,6 +417,14 @@ static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 	return 0;
 }
 
+
+static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
+					  struct iop_adma_chan *chan)
+{
+	BUG();
+	return 0;
+}
+
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -756,13 +832,14 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
 	hw_desc->src[0] = val;
 }
 
-static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
+static inline enum sum_check_flags
+iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
 {
 	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
 	struct iop3xx_aau_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
 
 	iop_paranoia(!(desc_ctrl.tx_complete && desc_ctrl.zero_result_en));
-	return desc_ctrl.zero_result_err;
+	return desc_ctrl.zero_result_err << SUM_CHECK_P;
 }
 
 static inline void iop_chan_append(struct iop_adma_chan *chan)

arch/arm/include/asm/hardware/iop_adma.h

@@ -86,6 +86,7 @@ struct iop_adma_chan {
  * @idx: pool index
  * @unmap_src_cnt: number of xor sources
  * @unmap_len: transaction bytecount
+ * @tx_list: list of descriptors that are associated with one operation
  * @async_tx: support for the async_tx api
  * @group_list: list of slots that make up a multi-descriptor transaction
  *	for example transfer lengths larger than the supported hw max
@@ -102,10 +103,12 @@ struct iop_adma_desc_slot {
 	u16 idx;
 	u16 unmap_src_cnt;
 	size_t unmap_len;
+	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	union {
 		u32 *xor_check_result;
 		u32 *crc32_result;
+		u32 *pq_check_result;
 	};
 };
 

arch/arm/include/asm/tcm.h

+/*
+ *
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ *
+ */
+#ifndef __ASMARM_TCM_H
+#define __ASMARM_TCM_H
+
+#ifndef CONFIG_HAVE_TCM
+#error "You should not be including tcm.h unless you have a TCM!"
+#endif
+
+#include <linux/compiler.h>
+
+/* Tag variables with this */
+#define __tcmdata __section(.tcm.data)
+/* Tag constants with this */
+#define __tcmconst __section(.tcm.rodata)
+/* Tag functions inside TCM called from outside TCM with this */
+#define __tcmfunc __attribute__((long_call)) __section(.tcm.text) noinline
+/* Tag function inside TCM called from inside TCM  with this */
+#define __tcmlocalfunc __section(.tcm.text)
+
+void *tcm_alloc(size_t len);
+void tcm_free(void *addr, size_t len);
+
+#endif

arch/arm/include/asm/unified.h

@@ -35,7 +35,9 @@
 
 #define ARM(x...)
 #define THUMB(x...)	x
+#ifdef __ASSEMBLY__
 #define W(instr)	instr.w
+#endif
 #define BSYM(sym)	sym + 1
 
 #else	/* !CONFIG_THUMB2_KERNEL */
@@ -45,7 +47,9 @@
 
 #define ARM(x...)	x
 #define THUMB(x...)
+#ifdef __ASSEMBLY__
 #define W(instr)	instr
+#endif
 #define BSYM(sym)	sym
 
 #endif	/* CONFIG_THUMB2_KERNEL */

arch/arm/kernel/Makefile

@@ -35,6 +35,7 @@ obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
+obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312

arch/arm/kernel/entry-armv.S

@@ -272,7 +272,15 @@ __und_svc:
 	@
 	@  r0 - instruction
 	@
+#ifndef	CONFIG_THUMB2_KERNEL
 	ldr	r0, [r2, #-4]
+#else
+	ldrh	r0, [r2, #-2]			@ Thumb instruction at LR - 2
+	and	r9, r0, #0xf800
+	cmp	r9, #0xe800			@ 32-bit instruction if xx >= 0
+	ldrhhs	r9, [r2]			@ bottom 16 bits
+	orrhs	r0, r9, r0, lsl #16
+#endif
 	adr	r9, BSYM(1f)
 	bl	call_fpe
 
@@ -678,7 +686,9 @@ ENTRY(fp_enter)
 	.word	no_fp
 	.previous
 
-no_fp:	mov	pc, lr
+ENTRY(no_fp)
+	mov	pc, lr
+ENDPROC(no_fp)
 
 __und_usr_unknown:
 	enable_irq
@@ -734,13 +744,6 @@ ENTRY(__switch_to)
 #ifdef CONFIG_MMU
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-#if __LINUX_ARM_ARCH__ >= 6
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
-	strex	r5, r4, [ip]			@ Clear exclusive monitor
-#endif
-#endif
 #if defined(CONFIG_HAS_TLS_REG)
 	mcr	p15, 0, r3, c13, c0, 3		@ set TLS register
 #elif !defined(CONFIG_TLS_REG_EMUL)

arch/arm/kernel/entry-header.S

@@ -76,13 +76,25 @@
 #ifndef CONFIG_THUMB2_KERNEL
 	.macro	svc_exit, rpsr
 	msr	spsr_cxsf, \rpsr
+#if defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#elif defined (CONFIG_CPU_V6)
+	ldr	r0, [sp]
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+	ldmib	sp, {r1 - pc}^			@ load r1 - pc, cpsr
+#endif
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
+#if defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
+#elif defined (CONFIG_CPU_V6)
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+#endif
 	.if	\fast
 	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
 	.else
@@ -98,6 +110,7 @@
 	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
 	.macro	svc_exit, rpsr
+	clrex					@ clear the exclusive monitor
 	ldr	r0, [sp, #S_SP]			@ top of the stack
 	ldr	r1, [sp, #S_PC]			@ return address
 	tst	r0, #4				@ orig stack 8-byte aligned?
@@ -110,6 +123,7 @@
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
+	clrex					@ clear the exclusive monitor
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr

arch/arm/kernel/kprobes.c

@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
@@ -83,10 +84,24 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
 	flush_insns(p->addr, 1);
 }
 
+/*
+ * The actual disarming is done here on each CPU and synchronized using
+ * stop_machine. This synchronization is necessary on SMP to avoid removing
+ * a probe between the moment the 'Undefined Instruction' exception is raised
+ * and the moment the exception handler reads the faulting instruction from
+ * memory.
+ */
+int __kprobes __arch_disarm_kprobe(void *p)
+{
+	struct kprobe *kp = p;
+	*kp->addr = kp->opcode;
+	flush_insns(kp->addr, 1);
+	return 0;
+}
+
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	*p->addr = p->opcode;
-	flush_insns(p->addr, 1);
+	stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)

arch/arm/kernel/setup.c

@@ -45,6 +45,7 @@
 
 #include "compat.h"
 #include "atags.h"
+#include "tcm.h"
 
 #ifndef MEM_SIZE
 #define MEM_SIZE	(16*1024*1024)
@@ -749,6 +750,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	cpu_init();
+	tcm_init();
 
 	/*
 	 * Set up various architecture-specific pointers

arch/arm/kernel/tcm.c

+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/ioport.h>
+#include <linux/genalloc.h>
+#include <linux/string.h> /* memcpy */
+#include <asm/page.h> /* PAGE_SHIFT */
+#include <asm/cputype.h>
+#include <asm/mach/map.h>
+#include <mach/memory.h>
+#include "tcm.h"
+
+/* Scream and warn about misuse */
+#if !defined(ITCM_OFFSET) || !defined(ITCM_END) || \
+    !defined(DTCM_OFFSET) || !defined(DTCM_END)
+#error "TCM support selected but offsets not defined!"
+#endif
+
+static struct gen_pool *tcm_pool;
+
+/* TCM section definitions from the linker */
+extern char __itcm_start, __sitcm_text, __eitcm_text;
+extern char __dtcm_start, __sdtcm_data, __edtcm_data;
+
+/*
+ * TCM memory resources
+ */
+static struct resource dtcm_res = {
+	.name = "DTCM RAM",
+	.start = DTCM_OFFSET,
+	.end = DTCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct resource itcm_res = {
+	.name = "ITCM RAM",
+	.start = ITCM_OFFSET,
+	.end = ITCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct map_desc dtcm_iomap[] __initdata = {
+	{
+		.virtual	= DTCM_OFFSET,
+		.pfn		= __phys_to_pfn(DTCM_OFFSET),
+		.length		= (DTCM_END - DTCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+static struct map_desc itcm_iomap[] __initdata = {
+	{
+		.virtual	= ITCM_OFFSET,
+		.pfn		= __phys_to_pfn(ITCM_OFFSET),
+		.length		= (ITCM_END - ITCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+/*
+ * Allocate a chunk of TCM memory
+ */
+void *tcm_alloc(size_t len)
+{
+	unsigned long vaddr;
+
+	if (!tcm_pool)
+		return NULL;
+
+	vaddr = gen_pool_alloc(tcm_pool, len);
+	if (!vaddr)
+		return NULL;
+
+	return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+/*
+ * Free a chunk of TCM memory
+ */
+void tcm_free(void *addr, size_t len)
+{
+	gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+
+static void __init setup_tcm_bank(u8 type, u32 offset, u32 expected_size)
+{
+	const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128,
+				    256, 512, 1024, -1, -1, -1, -1 };
+	u32 tcm_region;
+	int tcm_size;
+
+	/* Read the special TCM region register c9, 0 */
+	if (!type)
+		asm("mrc	p15, 0, %0, c9, c1, 0"
+		    : "=r" (tcm_region));
+	else
+		asm("mrc	p15, 0, %0, c9, c1, 1"
+		    : "=r" (tcm_region));
+
+	tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f];
+	if (tcm_size < 0) {
+		pr_err("CPU: %sTCM of unknown size!\n",
+			type ? "I" : "D");
+	} else {
+		pr_info("CPU: found %sTCM %dk @ %08x, %senabled\n",
+			type ? "I" : "D",
+			tcm_size,
+			(tcm_region & 0xfffff000U),
+			(tcm_region & 1) ? "" : "not ");
+	}
+
+	if (tcm_size != expected_size) {
+		pr_crit("CPU: %sTCM was detected %dk but expected %dk!\n",
+		       type ? "I" : "D",
+		       tcm_size,
+		       expected_size);
+		/* Adjust to the expected size? what can we do... */
+	}
+
+	/* Force move the TCM bank to where we want it, enable */
+	tcm_region = offset | (tcm_region & 0x00000ffeU) | 1;
+
+	if (!type)
+		asm("mcr	p15, 0, %0, c9, c1, 0"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+	else
+		asm("mcr	p15, 0, %0, c9, c1, 1"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+
+	pr_debug("CPU: moved %sTCM %dk to %08x, enabled\n",
+		 type ? "I" : "D",
+		 tcm_size,
+		 (tcm_region & 0xfffff000U));
+}
+
+/*
+ * This initializes the TCM memory
+ */
+void __init tcm_init(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	char *start;
+	char *end;
+	char *ram;
+
+	/* Setup DTCM if present */
+	if (tcm_status & (1 << 16)) {
+		setup_tcm_bank(0, DTCM_OFFSET,
+			       (DTCM_END - DTCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &dtcm_res);
+		iotable_init(dtcm_iomap, 1);
+		/* Copy data from RAM to DTCM */
+		start = &__sdtcm_data;
+		end   = &__edtcm_data;
+		ram   = &__dtcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+	}
+
+	/* Setup ITCM if present */
+	if (tcm_status & 1) {
+		setup_tcm_bank(1, ITCM_OFFSET,
+			       (ITCM_END - ITCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &itcm_res);
+		iotable_init(itcm_iomap, 1);
+		/* Copy code from RAM to ITCM */
+		start = &__sitcm_text;
+		end   = &__eitcm_text;
+		ram   = &__itcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+	}
+}
+
+/*
+ * This creates the TCM memory pool and has to be done later,
+ * during the core_initicalls, since the allocator is not yet
+ * up and running when the first initialization runs.
+ */
+static int __init setup_tcm_pool(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	u32 dtcm_pool_start = (u32) &__edtcm_data;
+	u32 itcm_pool_start = (u32) &__eitcm_text;
+	int ret;
+
+	/*
+	 * Set up malloc pool, 2^2 = 4 bytes granularity since
+	 * the TCM is sometimes just 4 KiB. NB: pages and cache
+	 * line alignments does not matter in TCM!
+	 */
+	tcm_pool = gen_pool_create(2, -1);
+
+	pr_debug("Setting up TCM memory pool\n");
+
+	/* Add the rest of DTCM to the TCM pool */
+	if (tcm_status & (1 << 16)) {
+		if (dtcm_pool_start < DTCM_END) {
+			ret = gen_pool_add(tcm_pool, dtcm_pool_start,
+					   DTCM_END - dtcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU DTCM: could not add DTCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 DTCM_END - dtcm_pool_start + 1,
+				 dtcm_pool_start);
+		}
+	}
+
+	/* Add the rest of ITCM to the TCM pool */
+	if (tcm_status & 1) {
+		if (itcm_pool_start < ITCM_END) {
+			ret = gen_pool_add(tcm_pool, itcm_pool_start,
+					   ITCM_END - itcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU ITCM: could not add ITCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 ITCM_END - itcm_pool_start + 1,
+				 itcm_pool_start);
+		}
+	}
+	return 0;
+}
+
+core_initcall(setup_tcm_pool);

arch/arm/kernel/tcm.h

+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+
+#ifdef CONFIG_HAVE_TCM
+void __init tcm_init(void);
+#else
+/* No TCM support, just blank inlines to be optimized out */
+inline void tcm_init(void)
+{
+}
+#endif

arch/arm/kernel/vmlinux.lds.S

@@ -199,6 +199,63 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
+#ifdef CONFIG_HAVE_TCM
+        /*
+	 * We align everything to a page boundary so we can
+	 * free it after init has commenced and TCM contents have
+	 * been copied to its destination.
+	 */
+	.tcm_start : {
+		. = ALIGN(PAGE_SIZE);
+		__tcm_start = .;
+		__itcm_start = .;
+	}
+
+	/*
+	 * Link these to the ITCM RAM
+	 * Put VMA to the TCM address and LMA to the common RAM
+	 * and we'll upload the contents from RAM to TCM and free
+	 * the used RAM after that.
+	 */
+	.text_itcm ITCM_OFFSET : AT(__itcm_start)
+	{
+		__sitcm_text = .;
+		*(.tcm.text)
+		*(.tcm.rodata)
+		. = ALIGN(4);
+		__eitcm_text = .;
+	}
+
+	/*
+	 * Reset the dot pointer, this is needed to create the
+	 * relative __dtcm_start below (to be used as extern in code).
+	 */
+	. = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm);
+
+	.dtcm_start : {
+		__dtcm_start = .;
+	}
+
+	/* TODO: add remainder of ITCM as well, that can be used for data! */
+	.data_dtcm DTCM_OFFSET : AT(__dtcm_start)
+	{
+		. = ALIGN(4);
+		__sdtcm_data = .;
+		*(.tcm.data)
+		. = ALIGN(4);
+		__edtcm_data = .;
+	}
+
+	/* Reset the dot pointer or the linker gets confused */
+	. = ADDR(.dtcm_start) + SIZEOF(.data_dtcm);
+
+	/* End marker for freeing TCM copy in linked object */
+	.tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){
+		. = ALIGN(PAGE_SIZE);
+		__tcm_end = .;
+	}
+#endif
+
 	.bss : {
 		__bss_start = .;	/* BSS				*/
 		*(.bss)

arch/arm/lib/copy_page.S

@@ -12,8 +12,9 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 
-#define COPY_COUNT (PAGE_SZ/64 PLD( -1 ))
+#define COPY_COUNT (PAGE_SZ / (2 * L1_CACHE_BYTES) PLD( -1 ))
 
 		.text
 		.align	5
@@ -26,17 +27,16 @@
 ENTRY(copy_page)
 		stmfd	sp!, {r4, lr}			@	2
 	PLD(	pld	[r1, #0]		)
-	PLD(	pld	[r1, #32]		)
+	PLD(	pld	[r1, #L1_CACHE_BYTES]		)
 		mov	r2, #COPY_COUNT			@	1
 		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-1:	PLD(	pld	[r1, #64]		)
-	PLD(	pld	[r1, #96]		)
-2:		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
+1:	PLD(	pld	[r1, #2 * L1_CACHE_BYTES])
+	PLD(	pld	[r1, #3 * L1_CACHE_BYTES])
+2:
+	.rept	(2 * L1_CACHE_BYTES / 16 - 1)
 		stmia	r0!, {r3, r4, ip, lr}		@	4
 		ldmia	r1!, {r3, r4, ip, lr}		@	4
+	.endr
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
 		ldmgtia	r1!, {r3, r4, ip, lr}		@	4

arch/arm/mach-at91/at91cap9_devices.c

@@ -771,9 +771,9 @@ void __init at91_add_device_pwm(u32 mask) {}
  *  AC97
  * -------------------------------------------------------------------- */
 
-#if defined(CONFIG_SND_AT91_AC97) || defined(CONFIG_SND_AT91_AC97_MODULE)
+#if defined(CONFIG_SND_ATMEL_AC97C) || defined(CONFIG_SND_ATMEL_AC97C_MODULE)
 static u64 ac97_dmamask = DMA_BIT_MASK(32);
-static struct atmel_ac97_data ac97_data;
+static struct ac97c_platform_data ac97_data;
 
 static struct resource ac97_resources[] = {
 	[0] = {
@@ -789,7 +789,7 @@ static struct resource ac97_resources[] = {
 };
 
 static struct platform_device at91cap9_ac97_device = {
-	.name		= "ac97c",
+	.name		= "atmel_ac97c",
 	.id		= 1,
 	.dev		= {
 				.dma_mask		= &ac97_dmamask,
@@ -800,7 +800,7 @@ static struct platform_device at91cap9_ac97_device = {
 	.num_resources	= ARRAY_SIZE(ac97_resources),
 };
 
-void __init at91_add_device_ac97(struct atmel_ac97_data *data)
+void __init at91_add_device_ac97(struct ac97c_platform_data *data)
 {
 	if (!data)
 		return;
@@ -818,7 +818,7 @@ void __init at91_add_device_ac97(struct atmel_ac97_data *data)
 	platform_device_register(&at91cap9_ac97_device);
 }
 #else
-void __init at91_add_device_ac97(struct atmel_ac97_data *data) {}
+void __init at91_add_device_ac97(struct ac97c_platform_data *data) {}
 #endif
 
 

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

@@ -364,7 +364,7 @@ static struct atmel_lcdfb_info __initdata cap9adk_lcdc_data;
 /*
  * AC97
  */
-static struct atmel_ac97_data cap9adk_ac97_data = {
+static struct ac97c_platform_data cap9adk_ac97_data = {
 //	.reset_pin	= ... not connected
 };
 

arch/arm/mach-at91/board-neocore926.c

@@ -340,7 +340,7 @@ static void __init neocore926_add_device_buttons(void) {}
 /*
  * AC97
  */
-static struct atmel_ac97_data neocore926_ac97_data = {
+static struct ac97c_platform_data neocore926_ac97_data = {
 	.reset_pin	= AT91_PIN_PA13,
 };
 

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

@@ -310,6 +310,14 @@ static void __init ek_add_device_buttons(void) {}
 #endif
 
 
+/*
+ * AC97
+ * reset_pin is not connected: NRST
+ */
+static struct ac97c_platform_data ek_ac97_data = {
+};
+
+
 /*
  * LEDs ... these could all be PWM-driven, for variable brightness
  */
@@ -372,6 +380,8 @@ static void __init ek_board_init(void)
 	at91_add_device_lcdc(&ek_lcdc_data);
 	/* Push Buttons */
 	ek_add_device_buttons();
+	/* AC97 */
+	at91_add_device_ac97(&ek_ac97_data);
 	/* LEDs */
 	at91_gpio_leds(ek_leds, ARRAY_SIZE(ek_leds));
 	at91_pwm_leds(ek_pwm_led, ARRAY_SIZE(ek_pwm_led));