diff --git a/Documentation/arm/vlocks.txt b/Documentation/arm/vlocks.txt
new file mode 100644
index 0000000000000000000000000000000000000000..415960a9bab0e4da6f65e8bf712337a06ea03773
--- /dev/null
+++ b/Documentation/arm/vlocks.txt
@@ -0,0 +1,211 @@
+vlocks for Bare-Metal Mutual Exclusion
+======================================
+
+Voting Locks, or "vlocks" provide a simple low-level mutual exclusion
+mechanism, with reasonable but minimal requirements on the memory
+system.
+
+These are intended to be used to coordinate critical activity among CPUs
+which are otherwise non-coherent, in situations where the hardware
+provides no other mechanism to support this and ordinary spinlocks
+cannot be used.
+
+
+vlocks make use of the atomicity provided by the memory system for
+writes to a single memory location. To arbitrate, every CPU "votes for
+itself", by storing a unique number to a common memory location. The
+final value seen in that memory location when all the votes have been
+cast identifies the winner.
+
+In order to make sure that the election produces an unambiguous result
+in finite time, a CPU will only enter the election in the first place if
+no winner has been chosen and the election does not appear to have
+started yet.
+
+
+Algorithm
+---------
+
+The easiest way to explain the vlocks algorithm is with some pseudo-code:
+
+
+ int currently_voting[NR_CPUS] = { 0, };
+ int last_vote = -1; /* no votes yet */
+
+ bool vlock_trylock(int this_cpu)
+ {
+ /* signal our desire to vote */
+ currently_voting[this_cpu] = 1;
+ if (last_vote != -1) {
+ /* someone already volunteered himself */
+ currently_voting[this_cpu] = 0;
+ return false; /* not ourself */
+ }
+
+ /* let's suggest ourself */
+ last_vote = this_cpu;
+ currently_voting[this_cpu] = 0;
+
+ /* then wait until everyone else is done voting */
+ for_each_cpu(i) {
+ while (currently_voting[i] != 0)
+ /* wait */;
+ }
+
+ /* result */
+ if (last_vote == this_cpu)
+ return true; /* we won */
+ return false;
+ }
+
+ bool vlock_unlock(void)
+ {
+ last_vote = -1;
+ }
+
+
+The currently_voting[] array provides a way for the CPUs to determine
+whether an election is in progress, and plays a role analogous to the
+"entering" array in Lamport's bakery algorithm [1].
+
+However, once the election has started, the underlying memory system
+atomicity is used to pick the winner. This avoids the need for a static
+priority rule to act as a tie-breaker, or any counters which could
+overflow.
+
+As long as the last_vote variable is globally visible to all CPUs, it
+will contain only one value that won't change once every CPU has cleared
+its currently_voting flag.
+
+
+Features and limitations
+------------------------
+
+ * vlocks are not intended to be fair. In the contended case, it is the
+ _last_ CPU which attempts to get the lock which will be most likely
+ to win.
+
+ vlocks are therefore best suited to situations where it is necessary
+ to pick a unique winner, but it does not matter which CPU actually
+ wins.
+
+ * Like other similar mechanisms, vlocks will not scale well to a large
+ number of CPUs.
+
+ vlocks can be cascaded in a voting hierarchy to permit better scaling
+ if necessary, as in the following hypothetical example for 4096 CPUs:
+
+ /* first level: local election */
+ my_town = towns[(this_cpu >> 4) & 0xf];
+ I_won = vlock_trylock(my_town, this_cpu & 0xf);
+ if (I_won) {
+ /* we won the town election, let's go for the state */
+ my_state = states[(this_cpu >> 8) & 0xf];
+ I_won = vlock_lock(my_state, this_cpu & 0xf));
+ if (I_won) {
+ /* and so on */
+ I_won = vlock_lock(the_whole_country, this_cpu & 0xf];
+ if (I_won) {
+ /* ... */
+ }
+ vlock_unlock(the_whole_country);
+ }
+ vlock_unlock(my_state);
+ }
+ vlock_unlock(my_town);
+
+
+ARM implementation
+------------------
+
+The current ARM implementation [2] contains some optimisations beyond
+the basic algorithm:
+
+ * By packing the members of the currently_voting array close together,
+ we can read the whole array in one transaction (providing the number
+ of CPUs potentially contending the lock is small enough). This
+ reduces the number of round-trips required to external memory.
+
+ In the ARM implementation, this means that we can use a single load
+ and comparison:
+
+ LDR Rt, [Rn]
+ CMP Rt, #0
+
+ ...in place of code equivalent to:
+
+ LDRB Rt, [Rn]
+ CMP Rt, #0
+ LDRBEQ Rt, [Rn, #1]
+ CMPEQ Rt, #0
+ LDRBEQ Rt, [Rn, #2]
+ CMPEQ Rt, #0
+ LDRBEQ Rt, [Rn, #3]
+ CMPEQ Rt, #0
+
+ This cuts down on the fast-path latency, as well as potentially
+ reducing bus contention in contended cases.
+
+ The optimisation relies on the fact that the ARM memory system
+ guarantees coherency between overlapping memory accesses of
+ different sizes, similarly to many other architectures. Note that
+ we do not care which element of currently_voting appears in which
+ bits of Rt, so there is no need to worry about endianness in this
+ optimisation.
+
+ If there are too many CPUs to read the currently_voting array in
+ one transaction then multiple transations are still required. The
+ implementation uses a simple loop of word-sized loads for this
+ case. The number of transactions is still fewer than would be
+ required if bytes were loaded individually.
+
+
+ In principle, we could aggregate further by using LDRD or LDM, but
+ to keep the code simple this was not attempted in the initial
+ implementation.
+
+
+ * vlocks are currently only used to coordinate between CPUs which are
+ unable to enable their caches yet. This means that the
+ implementation removes many of the barriers which would be required
+ when executing the algorithm in cached memory.
+
+ packing of the currently_voting array does not work with cached
+ memory unless all CPUs contending the lock are cache-coherent, due
+ to cache writebacks from one CPU clobbering values written by other
+ CPUs. (Though if all the CPUs are cache-coherent, you should be
+ probably be using proper spinlocks instead anyway).
+
+
+ * The "no votes yet" value used for the last_vote variable is 0 (not
+ -1 as in the pseudocode). This allows statically-allocated vlocks
+ to be implicitly initialised to an unlocked state simply by putting
+ them in .bss.
+
+ An offset is added to each CPU's ID for the purpose of setting this
+ variable, so that no CPU uses the value 0 for its ID.
+
+
+Colophon
+--------
+
+Originally created and documented by Dave Martin for Linaro Limited, for
+use in ARM-based big.LITTLE platforms, with review and input gratefully
+received from Nicolas Pitre and Achin Gupta. Thanks to Nicolas for
+grabbing most of this text out of the relevant mail thread and writing
+up the pseudocode.
+
+Copyright (C) 2012-2013 Linaro Limited
+Distributed under the terms of Version 2 of the GNU General Public
+License, as defined in linux/COPYING.
+
+
+References
+----------
+
+[1] Lamport, L. "A New Solution of Dijkstra's Concurrent Programming
+ Problem", Communications of the ACM 17, 8 (August 1974), 453-455.
+
+ http://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm
+
+[2] linux/arch/arm/common/vlock.S, www.kernel.org.
diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S
new file mode 100644
index 0000000000000000000000000000000000000000..ff198583f683930951e93a4503ed651e76c7d939
--- /dev/null
+++ b/arch/arm/common/vlock.S
@@ -0,0 +1,108 @@
+/*
+ * vlock.S - simple voting lock implementation for ARM
+ *
+ * Created by: Dave Martin, 2012-08-16
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * 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.
+ *
+ *
+ * This algorithm is described in more detail in
+ * Documentation/arm/vlocks.txt.
+ */
+
+#include <linux/linkage.h>
+#include "vlock.h"
+
+/* Select different code if voting flags can fit in a single word. */
+#if VLOCK_VOTING_SIZE > 4
+#define FEW(x...)
+#define MANY(x...) x
+#else
+#define FEW(x...) x
+#define MANY(x...)
+#endif
+
+@ voting lock for first-man coordination
+
+.macro voting_begin rbase:req, rcpu:req, rscratch:req
+ mov \rscratch, #1
+ strb \rscratch, [\rbase, \rcpu]
+ dmb
+.endm
+
+.macro voting_end rbase:req, rcpu:req, rscratch:req
+ dmb
+ mov \rscratch, #0
+ strb \rscratch, [\rbase, \rcpu]
+ dsb
+ sev
+.endm
+
+/*
+ * The vlock structure must reside in Strongly-Ordered or Device memory.
+ * This implementation deliberately eliminates most of the barriers which
+ * would be required for other memory types, and assumes that independent
+ * writes to neighbouring locations within a cacheline do not interfere
+ * with one another.
+ */
+
+@ r0: lock structure base
+@ r1: CPU ID (0-based index within cluster)
+ENTRY(vlock_trylock)
+ add r1, r1, #VLOCK_VOTING_OFFSET
+
+ voting_begin r0, r1, r2
+
+ ldrb r2, [r0, #VLOCK_OWNER_OFFSET] @ check whether lock is held
+ cmp r2, #VLOCK_OWNER_NONE
+ bne trylock_fail @ fail if so
+
+ @ Control dependency implies strb not observable before previous ldrb.
+
+ strb r1, [r0, #VLOCK_OWNER_OFFSET] @ submit my vote
+
+ voting_end r0, r1, r2 @ implies DMB
+
+ @ Wait for the current round of voting to finish:
+
+ MANY( mov r3, #VLOCK_VOTING_OFFSET )
+0:
+ MANY( ldr r2, [r0, r3] )
+ FEW( ldr r2, [r0, #VLOCK_VOTING_OFFSET] )
+ cmp r2, #0
+ wfene
+ bne 0b
+ MANY( add r3, r3, #4 )
+ MANY( cmp r3, #VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE )
+ MANY( bne 0b )
+
+ @ Check who won:
+
+ dmb
+ ldrb r2, [r0, #VLOCK_OWNER_OFFSET]
+ eor r0, r1, r2 @ zero if I won, else nonzero
+ bx lr
+
+trylock_fail:
+ voting_end r0, r1, r2
+ mov r0, #1 @ nonzero indicates that I lost
+ bx lr
+ENDPROC(vlock_trylock)
+
+@ r0: lock structure base
+ENTRY(vlock_unlock)
+ dmb
+ mov r1, #VLOCK_OWNER_NONE
+ strb r1, [r0, #VLOCK_OWNER_OFFSET]
+ dsb
+ sev
+ bx lr
+ENDPROC(vlock_unlock)
diff --git a/arch/arm/common/vlock.h b/arch/arm/common/vlock.h
new file mode 100644
index 0000000000000000000000000000000000000000..3b441475a59b3831b69d22357d8ad81579f097af
--- /dev/null
+++ b/arch/arm/common/vlock.h
@@ -0,0 +1,29 @@
+/*
+ * vlock.h - simple voting lock implementation
+ *
+ * Created by: Dave Martin, 2012-08-16
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * 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.
+ */
+
+#ifndef __VLOCK_H
+#define __VLOCK_H
+
+#include <asm/mcpm.h>
+
+/* Offsets and sizes are rounded to a word (4 bytes) */
+#define VLOCK_OWNER_OFFSET 0
+#define VLOCK_VOTING_OFFSET 4
+#define VLOCK_VOTING_SIZE ((MAX_CPUS_PER_CLUSTER + 3) / 4 * 4)
+#define VLOCK_SIZE (VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE)
+#define VLOCK_OWNER_NONE 0
+
+#endif /* ! __VLOCK_H */