kernel_optimize_test/arch/arm/common/vlock.S
Will Deacon 40a5c0b415 ARM: mcpm: use -st dsb option prior to sev instructions
In a similar manner to our spinlock implementation, mcpm uses sev to
wake up cores waiting on a lock when the lock is unlocked. In order to
ensure that the final write unlocking the lock is visible, a dsb
instruction is executed immediately prior to the sev.

This patch changes these dsbs to use the -st option, since we only
require that the store unlocking the lock is made visible.

Acked-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2013-08-12 12:25:45 +01:00

109 lines
2.6 KiB
ArmAsm

/*
* 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 st
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 st
sev
bx lr
ENDPROC(vlock_unlock)