linux-stable/arch/arm/common/vlock.S
Nick Desaulniers a2faac3986 ARM: 9263/1: use .arch directives instead of assembler command line flags
Similar to commit a6c30873ee ("ARM: 8989/1: use .fpu assembler
directives instead of assembler arguments").

GCC and GNU binutils support setting the "sub arch" via -march=,
-Wa,-march, target function attribute, and .arch assembler directive.

Clang was missing support for -Wa,-march=, but this was implemented in
clang-13.

The behavior of both GCC and Clang is to
prefer -Wa,-march= over -march= for assembler and assembler-with-cpp
sources, but Clang will warn about the -march= being unused.

clang: warning: argument unused during compilation: '-march=armv6k'
[-Wunused-command-line-argument]

Since most assembler is non-conditionally assembled with one sub arch
(modulo arch/arm/delay-loop.S which conditionally is assembled as armv4
based on CONFIG_ARCH_RPC, and arch/arm/mach-at91/pm-suspend.S which is
conditionally assembled as armv7-a based on CONFIG_CPU_V7), prefer the
.arch assembler directive.

Add a few more instances found in compile testing as found by Arnd and
Nathan.

Link: 1d51c699b9
Link: https://bugs.llvm.org/show_bug.cgi?id=48894
Link: https://github.com/ClangBuiltLinux/linux/issues/1195
Link: https://github.com/ClangBuiltLinux/linux/issues/1315

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2022-11-08 18:36:17 +00:00

101 lines
2.2 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* vlock.S - simple voting lock implementation for ARM
*
* Created by: Dave Martin, 2012-08-16
* Copyright: (C) 2012-2013 Linaro Limited
*
* This algorithm is described in more detail in
* Documentation/arm/vlocks.rst.
*/
#include <linux/linkage.h>
#include "vlock.h"
.arch armv7-a
/* 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)