linux/arch/arm/lib/copy_template.S
Nicolas Pitre 2239aff6ab [ARM] cache align destination pointer when copying memory for some processors
The implementation for memory copy functions on ARM had a (disabled)
provision for aligning the source pointer before loading registers with
data.  Turns out that aligning the _destination_ pointer is much more
useful, as the read side is already sufficiently helped with the use of
preload.

So this changes the definition of the CALGN() macro to target the
destination pointer instead, and turns it on for Feroceon processors
where the gain is very noticeable.

Signed-off-by: Nicolas Pitre <nico@marvell.com>
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>
2008-06-22 22:44:38 +02:00

248 lines
5.5 KiB
ArmAsm

/*
* linux/arch/arm/lib/copy_template.s
*
* Code template for optimized memory copy functions
*
* Author: Nicolas Pitre
* Created: Sep 28, 2005
* Copyright: MontaVista Software, Inc.
*
* 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.
*/
/*
* Theory of operation
* -------------------
*
* This file provides the core code for a forward memory copy used in
* the implementation of memcopy(), copy_to_user() and copy_from_user().
*
* The including file must define the following accessor macros
* according to the need of the given function:
*
* ldr1w ptr reg abort
*
* This loads one word from 'ptr', stores it in 'reg' and increments
* 'ptr' to the next word. The 'abort' argument is used for fixup tables.
*
* ldr4w ptr reg1 reg2 reg3 reg4 abort
* ldr8w ptr, reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
*
* This loads four or eight words starting from 'ptr', stores them
* in provided registers and increments 'ptr' past those words.
* The'abort' argument is used for fixup tables.
*
* ldr1b ptr reg cond abort
*
* Similar to ldr1w, but it loads a byte and increments 'ptr' one byte.
* It also must apply the condition code if provided, otherwise the
* "al" condition is assumed by default.
*
* str1w ptr reg abort
* str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
* str1b ptr reg cond abort
*
* Same as their ldr* counterparts, but data is stored to 'ptr' location
* rather than being loaded.
*
* enter reg1 reg2
*
* Preserve the provided registers on the stack plus any additional
* data as needed by the implementation including this code. Called
* upon code entry.
*
* exit reg1 reg2
*
* Restore registers with the values previously saved with the
* 'preserv' macro. Called upon code termination.
*/
enter r4, lr
subs r2, r2, #4
blt 8f
ands ip, r0, #3
PLD( pld [r1, #0] )
bne 9f
ands ip, r1, #3
bne 10f
1: subs r2, r2, #(28)
stmfd sp!, {r5 - r8}
blt 5f
CALGN( ands ip, r0, #31 )
CALGN( rsb r3, ip, #32 )
CALGN( sbcnes r4, r3, r2 ) @ C is always set here
CALGN( bcs 2f )
CALGN( adr r4, 6f )
CALGN( subs r2, r2, r3 ) @ C gets set
CALGN( add pc, r4, ip )
PLD( pld [r1, #0] )
2: PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 4f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
3: PLD( pld [r1, #124] )
4: ldr8w r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
subs r2, r2, #32
str8w r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
bge 3b
PLD( cmn r2, #96 )
PLD( bge 4b )
5: ands ip, r2, #28
rsb ip, ip, #32
addne pc, pc, ip @ C is always clear here
b 7f
6: nop
ldr1w r1, r3, abort=20f
ldr1w r1, r4, abort=20f
ldr1w r1, r5, abort=20f
ldr1w r1, r6, abort=20f
ldr1w r1, r7, abort=20f
ldr1w r1, r8, abort=20f
ldr1w r1, lr, abort=20f
add pc, pc, ip
nop
nop
str1w r0, r3, abort=20f
str1w r0, r4, abort=20f
str1w r0, r5, abort=20f
str1w r0, r6, abort=20f
str1w r0, r7, abort=20f
str1w r0, r8, abort=20f
str1w r0, lr, abort=20f
CALGN( bcs 2b )
7: ldmfd sp!, {r5 - r8}
8: movs r2, r2, lsl #31
ldr1b r1, r3, ne, abort=21f
ldr1b r1, r4, cs, abort=21f
ldr1b r1, ip, cs, abort=21f
str1b r0, r3, ne, abort=21f
str1b r0, r4, cs, abort=21f
str1b r0, ip, cs, abort=21f
exit r4, pc
9: rsb ip, ip, #4
cmp ip, #2
ldr1b r1, r3, gt, abort=21f
ldr1b r1, r4, ge, abort=21f
ldr1b r1, lr, abort=21f
str1b r0, r3, gt, abort=21f
str1b r0, r4, ge, abort=21f
subs r2, r2, ip
str1b r0, lr, abort=21f
blt 8b
ands ip, r1, #3
beq 1b
10: bic r1, r1, #3
cmp ip, #2
ldr1w r1, lr, abort=21f
beq 17f
bgt 18f
.macro forward_copy_shift pull push
subs r2, r2, #28
blt 14f
CALGN( ands ip, r0, #31 )
CALGN( rsb ip, ip, #32 )
CALGN( sbcnes r4, ip, r2 ) @ C is always set here
CALGN( subcc r2, r2, ip )
CALGN( bcc 15f )
11: stmfd sp!, {r5 - r9}
PLD( pld [r1, #0] )
PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 13f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
12: PLD( pld [r1, #124] )
13: ldr4w r1, r4, r5, r6, r7, abort=19f
mov r3, lr, pull #\pull
subs r2, r2, #32
ldr4w r1, r8, r9, ip, lr, abort=19f
orr r3, r3, r4, push #\push
mov r4, r4, pull #\pull
orr r4, r4, r5, push #\push
mov r5, r5, pull #\pull
orr r5, r5, r6, push #\push
mov r6, r6, pull #\pull
orr r6, r6, r7, push #\push
mov r7, r7, pull #\pull
orr r7, r7, r8, push #\push
mov r8, r8, pull #\pull
orr r8, r8, r9, push #\push
mov r9, r9, pull #\pull
orr r9, r9, ip, push #\push
mov ip, ip, pull #\pull
orr ip, ip, lr, push #\push
str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
bge 12b
PLD( cmn r2, #96 )
PLD( bge 13b )
ldmfd sp!, {r5 - r9}
14: ands ip, r2, #28
beq 16f
15: mov r3, lr, pull #\pull
ldr1w r1, lr, abort=21f
subs ip, ip, #4
orr r3, r3, lr, push #\push
str1w r0, r3, abort=21f
bgt 15b
CALGN( cmp r2, #0 )
CALGN( bge 11b )
16: sub r1, r1, #(\push / 8)
b 8b
.endm
forward_copy_shift pull=8 push=24
17: forward_copy_shift pull=16 push=16
18: forward_copy_shift pull=24 push=8
/*
* Abort preamble and completion macros.
* If a fixup handler is required then those macros must surround it.
* It is assumed that the fixup code will handle the private part of
* the exit macro.
*/
.macro copy_abort_preamble
19: ldmfd sp!, {r5 - r9}
b 21f
20: ldmfd sp!, {r5 - r8}
21:
.endm
.macro copy_abort_end
ldmfd sp!, {r4, pc}
.endm