diff --git a/Documentation/arm/kernel_user_helpers.txt b/Documentation/arm/kernel_user_helpers.txt
new file mode 100644
index 000000000000..a17df9f91d16
--- /dev/null
+++ b/Documentation/arm/kernel_user_helpers.txt
@@ -0,0 +1,267 @@
+Kernel-provided User Helpers
+============================
+
+These are segment of kernel provided user code reachable from user space
+at a fixed address in kernel memory.  This is used to provide user space
+with some operations which require kernel help because of unimplemented
+native feature and/or instructions in many ARM CPUs. The idea is for this
+code to be executed directly in user mode for best efficiency but which is
+too intimate with the kernel counter part to be left to user libraries.
+In fact this code might even differ from one CPU to another depending on
+the available instruction set, or whether it is a SMP systems. In other
+words, the kernel reserves the right to change this code as needed without
+warning. Only the entry points and their results as documented here are
+guaranteed to be stable.
+
+This is different from (but doesn't preclude) a full blown VDSO
+implementation, however a VDSO would prevent some assembly tricks with
+constants that allows for efficient branching to those code segments. And
+since those code segments only use a few cycles before returning to user
+code, the overhead of a VDSO indirect far call would add a measurable
+overhead to such minimalistic operations.
+
+User space is expected to bypass those helpers and implement those things
+inline (either in the code emitted directly by the compiler, or part of
+the implementation of a library call) when optimizing for a recent enough
+processor that has the necessary native support, but only if resulting
+binaries are already to be incompatible with earlier ARM processors due to
+useage of similar native instructions for other things.  In other words
+don't make binaries unable to run on earlier processors just for the sake
+of not using these kernel helpers if your compiled code is not going to
+use new instructions for other purpose.
+
+New helpers may be added over time, so an older kernel may be missing some
+helpers present in a newer kernel.  For this reason, programs must check
+the value of __kuser_helper_version (see below) before assuming that it is
+safe to call any particular helper.  This check should ideally be
+performed only once at process startup time, and execution aborted early
+if the required helpers are not provided by the kernel version that
+process is running on.
+
+kuser_helper_version
+--------------------
+
+Location:	0xffff0ffc
+
+Reference declaration:
+
+  extern int32_t __kuser_helper_version;
+
+Definition:
+
+  This field contains the number of helpers being implemented by the
+  running kernel.  User space may read this to determine the availability
+  of a particular helper.
+
+Usage example:
+
+#define __kuser_helper_version (*(int32_t *)0xffff0ffc)
+
+void check_kuser_version(void)
+{
+	if (__kuser_helper_version < 2) {
+		fprintf(stderr, "can't do atomic operations, kernel too old\n");
+		abort();
+	}
+}
+
+Notes:
+
+  User space may assume that the value of this field never changes
+  during the lifetime of any single process.  This means that this
+  field can be read once during the initialisation of a library or
+  startup phase of a program.
+
+kuser_get_tls
+-------------
+
+Location:	0xffff0fe0
+
+Reference prototype:
+
+  void * __kuser_get_tls(void);
+
+Input:
+
+  lr = return address
+
+Output:
+
+  r0 = TLS value
+
+Clobbered registers:
+
+  none
+
+Definition:
+
+  Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
+
+Usage example:
+
+typedef void * (__kuser_get_tls_t)(void);
+#define __kuser_get_tls (*(__kuser_get_tls_t *)0xffff0fe0)
+
+void foo()
+{
+	void *tls = __kuser_get_tls();
+	printf("TLS = %p\n", tls);
+}
+
+Notes:
+
+  - Valid only if __kuser_helper_version >= 1 (from kernel version 2.6.12).
+
+kuser_cmpxchg
+-------------
+
+Location:	0xffff0fc0
+
+Reference prototype:
+
+  int __kuser_cmpxchg(int32_t oldval, int32_t newval, volatile int32_t *ptr);
+
+Input:
+
+  r0 = oldval
+  r1 = newval
+  r2 = ptr
+  lr = return address
+
+Output:
+
+  r0 = success code (zero or non-zero)
+  C flag = set if r0 == 0, clear if r0 != 0
+
+Clobbered registers:
+
+  r3, ip, flags
+
+Definition:
+
+  Atomically store newval in *ptr only if *ptr is equal to oldval.
+  Return zero if *ptr was changed or non-zero if no exchange happened.
+  The C flag is also set if *ptr was changed to allow for assembly
+  optimization in the calling code.
+
+Usage example:
+
+typedef int (__kuser_cmpxchg_t)(int oldval, int newval, volatile int *ptr);
+#define __kuser_cmpxchg (*(__kuser_cmpxchg_t *)0xffff0fc0)
+
+int atomic_add(volatile int *ptr, int val)
+{
+	int old, new;
+
+	do {
+		old = *ptr;
+		new = old + val;
+	} while(__kuser_cmpxchg(old, new, ptr));
+
+	return new;
+}
+
+Notes:
+
+  - This routine already includes memory barriers as needed.
+
+  - Valid only if __kuser_helper_version >= 2 (from kernel version 2.6.12).
+
+kuser_memory_barrier
+--------------------
+
+Location:	0xffff0fa0
+
+Reference prototype:
+
+  void __kuser_memory_barrier(void);
+
+Input:
+
+  lr = return address
+
+Output:
+
+  none
+
+Clobbered registers:
+
+  none
+
+Definition:
+
+  Apply any needed memory barrier to preserve consistency with data modified
+  manually and __kuser_cmpxchg usage.
+
+Usage example:
+
+typedef void (__kuser_dmb_t)(void);
+#define __kuser_dmb (*(__kuser_dmb_t *)0xffff0fa0)
+
+Notes:
+
+  - Valid only if __kuser_helper_version >= 3 (from kernel version 2.6.15).
+
+kuser_cmpxchg64
+---------------
+
+Location:	0xffff0f60
+
+Reference prototype:
+
+  int __kuser_cmpxchg64(const int64_t *oldval,
+                        const int64_t *newval,
+                        volatile int64_t *ptr);
+
+Input:
+
+  r0 = pointer to oldval
+  r1 = pointer to newval
+  r2 = pointer to target value
+  lr = return address
+
+Output:
+
+  r0 = success code (zero or non-zero)
+  C flag = set if r0 == 0, clear if r0 != 0
+
+Clobbered registers:
+
+  r3, lr, flags
+
+Definition:
+
+  Atomically store the 64-bit value pointed by *newval in *ptr only if *ptr
+  is equal to the 64-bit value pointed by *oldval.  Return zero if *ptr was
+  changed or non-zero if no exchange happened.
+
+  The C flag is also set if *ptr was changed to allow for assembly
+  optimization in the calling code.
+
+Usage example:
+
+typedef int (__kuser_cmpxchg64_t)(const int64_t *oldval,
+                                  const int64_t *newval,
+                                  volatile int64_t *ptr);
+#define __kuser_cmpxchg64 (*(__kuser_cmpxchg64_t *)0xffff0f60)
+
+int64_t atomic_add64(volatile int64_t *ptr, int64_t val)
+{
+	int64_t old, new;
+
+	do {
+		old = *ptr;
+		new = old + val;
+	} while(__kuser_cmpxchg64(&old, &new, ptr));
+
+	return new;
+}
+
+Notes:
+
+  - This routine already includes memory barriers as needed.
+
+  - Due to the length of this sequence, this spans 2 conventional kuser
+    "slots", therefore 0xffff0f80 is not used as a valid entry point.
+
+  - Valid only if __kuser_helper_version >= 5 (from kernel version 3.1).
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 90c62cd51ca9..8f9ab5c9015b 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -383,7 +383,7 @@ ENDPROC(__pabt_svc)
 	.endm
 
 	.macro	kuser_cmpxchg_check
-#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
@@ -392,7 +392,7 @@ ENDPROC(__pabt_svc)
 	@ perform a quick test inline since it should be false
 	@ 99.9999% of the time.  The rest is done out of line.
 	cmp	r2, #TASK_SIZE
-	blhs	kuser_cmpxchg_fixup
+	blhs	kuser_cmpxchg64_fixup
 #endif
 #endif
 	.endm
@@ -758,31 +758,12 @@ ENDPROC(__switch_to)
 /*
  * User helpers.
  *
- * These are segment of kernel provided user code reachable from user space
- * at a fixed address in kernel memory.  This is used to provide user space
- * with some operations which require kernel help because of unimplemented
- * native feature and/or instructions in many ARM CPUs. The idea is for
- * this code to be executed directly in user mode for best efficiency but
- * which is too intimate with the kernel counter part to be left to user
- * libraries.  In fact this code might even differ from one CPU to another
- * depending on the available  instruction set and restrictions like on
- * SMP systems.  In other words, the kernel reserves the right to change
- * this code as needed without warning. Only the entry points and their
- * results are guaranteed to be stable.
- *
  * Each segment is 32-byte aligned and will be moved to the top of the high
  * vector page.  New segments (if ever needed) must be added in front of
  * existing ones.  This mechanism should be used only for things that are
  * really small and justified, and not be abused freely.
  *
- * User space is expected to implement those things inline when optimizing
- * for a processor that has the necessary native support, but only if such
- * resulting binaries are already to be incompatible with earlier ARM
- * processors due to the use of unsupported instructions other than what
- * is provided here.  In other words don't make binaries unable to run on
- * earlier processors just for the sake of not using these kernel helpers
- * if your compiled code is not going to use the new instructions for other
- * purpose.
+ * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
  THUMB(	.arm	)
 
@@ -799,97 +780,104 @@ ENDPROC(__switch_to)
 __kuser_helper_start:
 
 /*
- * Reference prototype:
- *
- *	void __kernel_memory_barrier(void)
- *
- * Input:
- *
- *	lr = return address
- *
- * Output:
- *
- *	none
- *
- * Clobbered:
- *
- *	none
- *
- * Definition and user space usage example:
- *
- *	typedef void (__kernel_dmb_t)(void);
- *	#define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0)
- *
- * Apply any needed memory barrier to preserve consistency with data modified
- * manually and __kuser_cmpxchg usage.
- *
- * This could be used as follows:
- *
- * #define __kernel_dmb() \
- *         asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \
- *	        : : : "r0", "lr","cc" )
+ * Due to the length of some sequences, __kuser_cmpxchg64 spans 2 regular
+ * kuser "slots", therefore 0xffff0f80 is not used as a valid entry point.
  */
 
+__kuser_cmpxchg64:				@ 0xffff0f60
+
+#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+
+	/*
+	 * Poor you.  No fast solution possible...
+	 * The kernel itself must perform the operation.
+	 * A special ghost syscall is used for that (see traps.c).
+	 */
+	stmfd	sp!, {r7, lr}
+	ldr	r7, 1f			@ it's 20 bits
+	swi	__ARM_NR_cmpxchg64
+	ldmfd	sp!, {r7, pc}
+1:	.word	__ARM_NR_cmpxchg64
+
+#elif defined(CONFIG_CPU_32v6K)
+
+	stmfd	sp!, {r4, r5, r6, r7}
+	ldrd	r4, r5, [r0]			@ load old val
+	ldrd	r6, r7, [r1]			@ load new val
+	smp_dmb	arm
+1:	ldrexd	r0, r1, [r2]			@ load current val
+	eors	r3, r0, r4			@ compare with oldval (1)
+	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	strexdeq r3, r6, r7, [r2]		@ store newval if eq
+	teqeq	r3, #1				@ success?
+	beq	1b				@ if no then retry
+	smp_dmb	arm
+	rsbs	r0, r3, #0			@ set returned val and C flag
+	ldmfd	sp!, {r4, r5, r6, r7}
+	bx	lr
+
+#elif !defined(CONFIG_SMP)
+
+#ifdef CONFIG_MMU
+
+	/*
+	 * The only thing that can break atomicity in this cmpxchg64
+	 * implementation is either an IRQ or a data abort exception
+	 * causing another process/thread to be scheduled in the middle of
+	 * the critical sequence.  The same strategy as for cmpxchg is used.
+	 */
+	stmfd	sp!, {r4, r5, r6, lr}
+	ldmia	r0, {r4, r5}			@ load old val
+	ldmia	r1, {r6, lr}			@ load new val
+1:	ldmia	r2, {r0, r1}			@ load current val
+	eors	r3, r0, r4			@ compare with oldval (1)
+	eoreqs	r3, r1, r5			@ compare with oldval (2)
+2:	stmeqia	r2, {r6, lr}			@ store newval if eq
+	rsbs	r0, r3, #0			@ set return val and C flag
+	ldmfd	sp!, {r4, r5, r6, pc}
+
+	.text
+kuser_cmpxchg64_fixup:
+	@ Called from kuser_cmpxchg_fixup.
+	@ r2 = address of interrupted insn (must be preserved).
+	@ sp = saved regs. r7 and r8 are clobbered.
+	@ 1b = first critical insn, 2b = last critical insn.
+	@ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b.
+	mov	r7, #0xffff0fff
+	sub	r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64)))
+	subs	r8, r2, r7
+	rsbcss	r8, r8, #(2b - 1b)
+	strcs	r7, [sp, #S_PC]
+#if __LINUX_ARM_ARCH__ < 6
+	bcc	kuser_cmpxchg32_fixup
+#endif
+	mov	pc, lr
+	.previous
+
+#else
+#warning "NPTL on non MMU needs fixing"
+	mov	r0, #-1
+	adds	r0, r0, #0
+	usr_ret	lr
+#endif
+
+#else
+#error "incoherent kernel configuration"
+#endif
+
+	/* pad to next slot */
+	.rept	(16 - (. - __kuser_cmpxchg64)/4)
+	.word	0
+	.endr
+
+	.align	5
+
 __kuser_memory_barrier:				@ 0xffff0fa0
 	smp_dmb	arm
 	usr_ret	lr
 
 	.align	5
 
-/*
- * Reference prototype:
- *
- *	int __kernel_cmpxchg(int oldval, int newval, int *ptr)
- *
- * Input:
- *
- *	r0 = oldval
- *	r1 = newval
- *	r2 = ptr
- *	lr = return address
- *
- * Output:
- *
- *	r0 = returned value (zero or non-zero)
- *	C flag = set if r0 == 0, clear if r0 != 0
- *
- * Clobbered:
- *
- *	r3, ip, flags
- *
- * Definition and user space usage example:
- *
- *	typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr);
- *	#define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0)
- *
- * Atomically store newval in *ptr if *ptr is equal to oldval for user space.
- * Return zero if *ptr was changed or non-zero if no exchange happened.
- * The C flag is also set if *ptr was changed to allow for assembly
- * optimization in the calling code.
- *
- * Notes:
- *
- *    - This routine already includes memory barriers as needed.
- *
- * For example, a user space atomic_add implementation could look like this:
- *
- * #define atomic_add(ptr, val) \
- *	({ register unsigned int *__ptr asm("r2") = (ptr); \
- *	   register unsigned int __result asm("r1"); \
- *	   asm volatile ( \
- *	       "1: @ atomic_add\n\t" \
- *	       "ldr	r0, [r2]\n\t" \
- *	       "mov	r3, #0xffff0fff\n\t" \
- *	       "add	lr, pc, #4\n\t" \
- *	       "add	r1, r0, %2\n\t" \
- *	       "add	pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \
- *	       "bcc	1b" \
- *	       : "=&r" (__result) \
- *	       : "r" (__ptr), "rIL" (val) \
- *	       : "r0","r3","ip","lr","cc","memory" ); \
- *	   __result; })
- */
-
 __kuser_cmpxchg:				@ 0xffff0fc0
 
 #if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
@@ -925,7 +913,7 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 	usr_ret	lr
 
 	.text
-kuser_cmpxchg_fixup:
+kuser_cmpxchg32_fixup:
 	@ Called from kuser_cmpxchg_check macro.
 	@ r2 = address of interrupted insn (must be preserved).
 	@ sp = saved regs. r7 and r8 are clobbered.
@@ -963,39 +951,6 @@ kuser_cmpxchg_fixup:
 
 	.align	5
 
-/*
- * Reference prototype:
- *
- *	int __kernel_get_tls(void)
- *
- * Input:
- *
- *	lr = return address
- *
- * Output:
- *
- *	r0 = TLS value
- *
- * Clobbered:
- *
- *	none
- *
- * Definition and user space usage example:
- *
- *	typedef int (__kernel_get_tls_t)(void);
- *	#define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0)
- *
- * Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
- *
- * This could be used as follows:
- *
- * #define __kernel_get_tls() \
- *	({ register unsigned int __val asm("r0"); \
- *         asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \
- *	        : "=r" (__val) : : "lr","cc" ); \
- *	   __val; })
- */
-
 __kuser_get_tls:				@ 0xffff0fe0
 	ldr	r0, [pc, #(16 - 8)]	@ read TLS, set in kuser_get_tls_init
 	usr_ret	lr
@@ -1004,19 +959,6 @@ __kuser_get_tls:				@ 0xffff0fe0
 	.word	0			@ 0xffff0ff0 software TLS value, then
 	.endr				@ pad up to __kuser_helper_version
 
-/*
- * Reference declaration:
- *
- *	extern unsigned int __kernel_helper_version;
- *
- * Definition and user space usage example:
- *
- *	#define __kernel_helper_version (*(unsigned int *)0xffff0ffc)
- *
- * User space may read this to determine the curent number of helpers
- * available.
- */
-
 __kuser_helper_version:				@ 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)