455bd4c430
Recent GCC versions (e.g. GCC-4.7.2) perform optimizations based on
assumptions about the implementation of memset and similar functions.
The current ARM optimized memset code does not return the value of
its first argument, as is usually expected from standard implementations.
For instance in the following function:
void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
{
memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter));
waiter->magic = waiter;
INIT_LIST_HEAD(&waiter->list);
}
compiled as:
800554d0 <debug_mutex_lock_common>:
800554d0: e92d4008 push {r3, lr}
800554d4: e1a00001 mov r0, r1
800554d8: e3a02010 mov r2, #16 ; 0x10
800554dc: e3a01011 mov r1, #17 ; 0x11
800554e0: eb04426e bl 80165ea0 <memset>
800554e4: e1a03000 mov r3, r0
800554e8: e583000c str r0, [r3, #12]
800554ec: e5830000 str r0, [r3]
800554f0: e5830004 str r0, [r3, #4]
800554f4: e8bd8008 pop {r3, pc}
GCC assumes memset returns the value of pointer 'waiter' in register r0; causing
register/memory corruptions.
This patch fixes the return value of the assembly version of memset.
It adds a 'mov' instruction and merges an additional load+store into
existing load/store instructions.
For ease of review, here is a breakdown of the patch into 4 simple steps:
Step 1
======
Perform the following substitutions:
ip -> r8, then
r0 -> ip,
and insert 'mov ip, r0' as the first statement of the function.
At this point, we have a memset() implementation returning the proper result,
but corrupting r8 on some paths (the ones that were using ip).
Step 2
======
Make sure r8 is saved and restored when (! CALGN(1)+0) == 1:
save r8:
- str lr, [sp, #-4]!
+ stmfd sp!, {r8, lr}
and restore r8 on both exit paths:
- ldmeqfd sp!, {pc} @ Now <64 bytes to go.
+ ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go.
(...)
tst r2, #16
stmneia ip!, {r1, r3, r8, lr}
- ldr lr, [sp], #4
+ ldmfd sp!, {r8, lr}
Step 3
======
Make sure r8 is saved and restored when (! CALGN(1)+0) == 0:
save r8:
- stmfd sp!, {r4-r7, lr}
+ stmfd sp!, {r4-r8, lr}
and restore r8 on both exit paths:
bgt 3b
- ldmeqfd sp!, {r4-r7, pc}
+ ldmeqfd sp!, {r4-r8, pc}
(...)
tst r2, #16
stmneia ip!, {r4-r7}
- ldmfd sp!, {r4-r7, lr}
+ ldmfd sp!, {r4-r8, lr}
Step 4
======
Rewrite register list "r4-r7, r8" as "r4-r8".
Signed-off-by: Ivan Djelic <ivan.djelic@parrot.com>
Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Dirk Behme <dirk.behme@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
130 lines
2.5 KiB
ArmAsm
130 lines
2.5 KiB
ArmAsm
/*
|
|
* linux/arch/arm/lib/memset.S
|
|
*
|
|
* Copyright (C) 1995-2000 Russell King
|
|
*
|
|
* 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.
|
|
*
|
|
* ASM optimised string functions
|
|
*/
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
|
|
.text
|
|
.align 5
|
|
.word 0
|
|
|
|
1: subs r2, r2, #4 @ 1 do we have enough
|
|
blt 5f @ 1 bytes to align with?
|
|
cmp r3, #2 @ 1
|
|
strltb r1, [ip], #1 @ 1
|
|
strleb r1, [ip], #1 @ 1
|
|
strb r1, [ip], #1 @ 1
|
|
add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3))
|
|
/*
|
|
* The pointer is now aligned and the length is adjusted. Try doing the
|
|
* memset again.
|
|
*/
|
|
|
|
ENTRY(memset)
|
|
/*
|
|
* Preserve the contents of r0 for the return value.
|
|
*/
|
|
mov ip, r0
|
|
ands r3, ip, #3 @ 1 unaligned?
|
|
bne 1b @ 1
|
|
/*
|
|
* we know that the pointer in ip is aligned to a word boundary.
|
|
*/
|
|
orr r1, r1, r1, lsl #8
|
|
orr r1, r1, r1, lsl #16
|
|
mov r3, r1
|
|
cmp r2, #16
|
|
blt 4f
|
|
|
|
#if ! CALGN(1)+0
|
|
|
|
/*
|
|
* We need 2 extra registers for this loop - use r8 and the LR
|
|
*/
|
|
stmfd sp!, {r8, lr}
|
|
mov r8, r1
|
|
mov lr, r1
|
|
|
|
2: subs r2, r2, #64
|
|
stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time.
|
|
stmgeia ip!, {r1, r3, r8, lr}
|
|
stmgeia ip!, {r1, r3, r8, lr}
|
|
stmgeia ip!, {r1, r3, r8, lr}
|
|
bgt 2b
|
|
ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go.
|
|
/*
|
|
* No need to correct the count; we're only testing bits from now on
|
|
*/
|
|
tst r2, #32
|
|
stmneia ip!, {r1, r3, r8, lr}
|
|
stmneia ip!, {r1, r3, r8, lr}
|
|
tst r2, #16
|
|
stmneia ip!, {r1, r3, r8, lr}
|
|
ldmfd sp!, {r8, lr}
|
|
|
|
#else
|
|
|
|
/*
|
|
* This version aligns the destination pointer in order to write
|
|
* whole cache lines at once.
|
|
*/
|
|
|
|
stmfd sp!, {r4-r8, lr}
|
|
mov r4, r1
|
|
mov r5, r1
|
|
mov r6, r1
|
|
mov r7, r1
|
|
mov r8, r1
|
|
mov lr, r1
|
|
|
|
cmp r2, #96
|
|
tstgt ip, #31
|
|
ble 3f
|
|
|
|
and r8, ip, #31
|
|
rsb r8, r8, #32
|
|
sub r2, r2, r8
|
|
movs r8, r8, lsl #(32 - 4)
|
|
stmcsia ip!, {r4, r5, r6, r7}
|
|
stmmiia ip!, {r4, r5}
|
|
tst r8, #(1 << 30)
|
|
mov r8, r1
|
|
strne r1, [ip], #4
|
|
|
|
3: subs r2, r2, #64
|
|
stmgeia ip!, {r1, r3-r8, lr}
|
|
stmgeia ip!, {r1, r3-r8, lr}
|
|
bgt 3b
|
|
ldmeqfd sp!, {r4-r8, pc}
|
|
|
|
tst r2, #32
|
|
stmneia ip!, {r1, r3-r8, lr}
|
|
tst r2, #16
|
|
stmneia ip!, {r4-r7}
|
|
ldmfd sp!, {r4-r8, lr}
|
|
|
|
#endif
|
|
|
|
4: tst r2, #8
|
|
stmneia ip!, {r1, r3}
|
|
tst r2, #4
|
|
strne r1, [ip], #4
|
|
/*
|
|
* When we get here, we've got less than 4 bytes to zero. We
|
|
* may have an unaligned pointer as well.
|
|
*/
|
|
5: tst r2, #2
|
|
strneb r1, [ip], #1
|
|
strneb r1, [ip], #1
|
|
tst r2, #1
|
|
strneb r1, [ip], #1
|
|
mov pc, lr
|
|
ENDPROC(memset)
|