ARM: mcpm: Add baremetal voting mutexes

This patch adds a simple low-level voting mutex implementation
to be used to arbitrate during first man selection when no load/store
exclusive instructions are usable.

For want of a better name, these are called "vlocks".  (I was
tempted to call them ballot locks, but "block" is way too confusing
an abbreviation...)

There is no function to wait for the lock to be released, and no
vlock_lock() function since we don't need these at the moment.
These could straightforwardly be added if vlocks get used for other
purposes.

For architectural correctness even Strongly-Ordered memory accesses
require barriers in order to guarantee that multiple CPUs have a
coherent view of the ordering of memory accesses.  Whether or not
this matters depends on hardware implementation details of the
memory system.  Since the purpose of this code is to provide a clean,
generic locking mechanism with no platform-specific dependencies the
barriers should be present to avoid unpleasant surprises on future
platforms.

Note:

  * When taking the lock, we don't care about implicit background
    memory operations and other signalling which may be pending,
    because those are not part of the critical section anyway.

    A DMB is sufficient to ensure correctly observed ordering if
    the explicit memory accesses in vlock_trylock.

  * No barrier is required after checking the election result,
    because the result is determined by the store to
    VLOCK_OWNER_OFFSET and is already globally observed due to the
    barriers in voting_end.  This means that global agreement on
    the winner is guaranteed, even before the winner is known
    locally.

Signed-off-by: Dave Martin <dave.martin@linaro.org>
Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>

2 files changed, 137 insertions, 0 deletions

diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S
new file mode 100644
index 00000000000..ff198583f68
--- /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 00000000000..3b441475a59
--- /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 */