kernel_optimize_test/arch/powerpc/lib/checksum_64.S
Anton Blanchard fdd374b62c powerpc: Optimise 64bit csum_partial_copy_generic and add csum_and_copy_from_user
We use the same core loop as the new csum_partial, adding in the
stores and exception handling code. To keep things simple we do all the
exception fixup in csum_and_copy_from_user. This wrapper function is
modelled on the generic checksum code and is careful to always calculate
a complete checksum even if we only copied part of the data to userspace.

To test this I forced checksumming on over loopback and ran socklib (a
simple TCP benchmark). On a POWER6 575 throughput improved by 19% with
this patch. If I forced both the sender and receiver onto the same cpu
(with the hope of shifting the benchmark from being cache bandwidth limited
to cpu limited), adding this patch improved performance by 55%

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-09-02 14:07:30 +10:00

458 lines
8.8 KiB
ArmAsm

/*
* This file contains assembly-language implementations
* of IP-style 1's complement checksum routines.
*
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
*/
#include <linux/sys.h>
#include <asm/processor.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
/*
* ip_fast_csum(r3=buf, r4=len) -- Optimized for IP header
* len is in words and is always >= 5.
*
* In practice len == 5, but this is not guaranteed. So this code does not
* attempt to use doubleword instructions.
*/
_GLOBAL(ip_fast_csum)
lwz r0,0(r3)
lwzu r5,4(r3)
addic. r4,r4,-2
addc r0,r0,r5
mtctr r4
blelr-
1: lwzu r4,4(r3)
adde r0,r0,r4
bdnz 1b
addze r0,r0 /* add in final carry */
rldicl r4,r0,32,0 /* fold two 32-bit halves together */
add r0,r0,r4
srdi r0,r0,32
rlwinm r3,r0,16,0,31 /* fold two halves together */
add r3,r0,r3
not r3,r3
srwi r3,r3,16
blr
/*
* Compute checksum of TCP or UDP pseudo-header:
* csum_tcpudp_magic(r3=saddr, r4=daddr, r5=len, r6=proto, r7=sum)
* No real gain trying to do this specially for 64 bit, but
* the 32 bit addition may spill into the upper bits of
* the doubleword so we still must fold it down from 64.
*/
_GLOBAL(csum_tcpudp_magic)
rlwimi r5,r6,16,0,15 /* put proto in upper half of len */
addc r0,r3,r4 /* add 4 32-bit words together */
adde r0,r0,r5
adde r0,r0,r7
rldicl r4,r0,32,0 /* fold 64 bit value */
add r0,r4,r0
srdi r0,r0,32
rlwinm r3,r0,16,0,31 /* fold two halves together */
add r3,r0,r3
not r3,r3
srwi r3,r3,16
blr
#define STACKFRAMESIZE 256
#define STK_REG(i) (112 + ((i)-14)*8)
/*
* Computes the checksum of a memory block at buff, length len,
* and adds in "sum" (32-bit).
*
* csum_partial(r3=buff, r4=len, r5=sum)
*/
_GLOBAL(csum_partial)
addic r0,r5,0 /* clear carry */
srdi. r6,r4,3 /* less than 8 bytes? */
beq .Lcsum_tail_word
/*
* If only halfword aligned, align to a double word. Since odd
* aligned addresses should be rare and they would require more
* work to calculate the correct checksum, we ignore that case
* and take the potential slowdown of unaligned loads.
*/
rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */
beq .Lcsum_aligned
li r7,4
sub r6,r7,r6
mtctr r6
1:
lhz r6,0(r3) /* align to doubleword */
subi r4,r4,2
addi r3,r3,2
adde r0,r0,r6
bdnz 1b
.Lcsum_aligned:
/*
* We unroll the loop such that each iteration is 64 bytes with an
* entry and exit limb of 64 bytes, meaning a minimum size of
* 128 bytes.
*/
srdi. r6,r4,7
beq .Lcsum_tail_doublewords /* len < 128 */
srdi r6,r4,6
subi r6,r6,1
mtctr r6
stdu r1,-STACKFRAMESIZE(r1)
std r14,STK_REG(r14)(r1)
std r15,STK_REG(r15)(r1)
std r16,STK_REG(r16)(r1)
ld r6,0(r3)
ld r9,8(r3)
ld r10,16(r3)
ld r11,24(r3)
/*
* On POWER6 and POWER7 back to back addes take 2 cycles because of
* the XER dependency. This means the fastest this loop can go is
* 16 cycles per iteration. The scheduling of the loop below has
* been shown to hit this on both POWER6 and POWER7.
*/
.align 5
2:
adde r0,r0,r6
ld r12,32(r3)
ld r14,40(r3)
adde r0,r0,r9
ld r15,48(r3)
ld r16,56(r3)
addi r3,r3,64
adde r0,r0,r10
adde r0,r0,r11
adde r0,r0,r12
adde r0,r0,r14
adde r0,r0,r15
ld r6,0(r3)
ld r9,8(r3)
adde r0,r0,r16
ld r10,16(r3)
ld r11,24(r3)
bdnz 2b
adde r0,r0,r6
ld r12,32(r3)
ld r14,40(r3)
adde r0,r0,r9
ld r15,48(r3)
ld r16,56(r3)
addi r3,r3,64
adde r0,r0,r10
adde r0,r0,r11
adde r0,r0,r12
adde r0,r0,r14
adde r0,r0,r15
adde r0,r0,r16
ld r14,STK_REG(r14)(r1)
ld r15,STK_REG(r15)(r1)
ld r16,STK_REG(r16)(r1)
addi r1,r1,STACKFRAMESIZE
andi. r4,r4,63
.Lcsum_tail_doublewords: /* Up to 127 bytes to go */
srdi. r6,r4,3
beq .Lcsum_tail_word
mtctr r6
3:
ld r6,0(r3)
addi r3,r3,8
adde r0,r0,r6
bdnz 3b
andi. r4,r4,7
.Lcsum_tail_word: /* Up to 7 bytes to go */
srdi. r6,r4,2
beq .Lcsum_tail_halfword
lwz r6,0(r3)
addi r3,r3,4
adde r0,r0,r6
subi r4,r4,4
.Lcsum_tail_halfword: /* Up to 3 bytes to go */
srdi. r6,r4,1
beq .Lcsum_tail_byte
lhz r6,0(r3)
addi r3,r3,2
adde r0,r0,r6
subi r4,r4,2
.Lcsum_tail_byte: /* Up to 1 byte to go */
andi. r6,r4,1
beq .Lcsum_finish
lbz r6,0(r3)
sldi r9,r6,8 /* Pad the byte out to 16 bits */
adde r0,r0,r9
.Lcsum_finish:
addze r0,r0 /* add in final carry */
rldicl r4,r0,32,0 /* fold two 32 bit halves together */
add r3,r4,r0
srdi r3,r3,32
blr
.macro source
100:
.section __ex_table,"a"
.align 3
.llong 100b,.Lsrc_error
.previous
.endm
.macro dest
200:
.section __ex_table,"a"
.align 3
.llong 200b,.Ldest_error
.previous
.endm
/*
* Computes the checksum of a memory block at src, length len,
* and adds in "sum" (32-bit), while copying the block to dst.
* If an access exception occurs on src or dst, it stores -EFAULT
* to *src_err or *dst_err respectively. The caller must take any action
* required in this case (zeroing memory, recalculating partial checksum etc).
*
* csum_partial_copy_generic(r3=src, r4=dst, r5=len, r6=sum, r7=src_err, r8=dst_err)
*/
_GLOBAL(csum_partial_copy_generic)
addic r0,r6,0 /* clear carry */
srdi. r6,r5,3 /* less than 8 bytes? */
beq .Lcopy_tail_word
/*
* If only halfword aligned, align to a double word. Since odd
* aligned addresses should be rare and they would require more
* work to calculate the correct checksum, we ignore that case
* and take the potential slowdown of unaligned loads.
*
* If the source and destination are relatively unaligned we only
* align the source. This keeps things simple.
*/
rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */
beq .Lcopy_aligned
li r7,4
sub r6,r7,r6
mtctr r6
1:
source; lhz r6,0(r3) /* align to doubleword */
subi r5,r5,2
addi r3,r3,2
adde r0,r0,r6
dest; sth r6,0(r4)
addi r4,r4,2
bdnz 1b
.Lcopy_aligned:
/*
* We unroll the loop such that each iteration is 64 bytes with an
* entry and exit limb of 64 bytes, meaning a minimum size of
* 128 bytes.
*/
srdi. r6,r5,7
beq .Lcopy_tail_doublewords /* len < 128 */
srdi r6,r5,6
subi r6,r6,1
mtctr r6
stdu r1,-STACKFRAMESIZE(r1)
std r14,STK_REG(r14)(r1)
std r15,STK_REG(r15)(r1)
std r16,STK_REG(r16)(r1)
source; ld r6,0(r3)
source; ld r9,8(r3)
source; ld r10,16(r3)
source; ld r11,24(r3)
/*
* On POWER6 and POWER7 back to back addes take 2 cycles because of
* the XER dependency. This means the fastest this loop can go is
* 16 cycles per iteration. The scheduling of the loop below has
* been shown to hit this on both POWER6 and POWER7.
*/
.align 5
2:
adde r0,r0,r6
source; ld r12,32(r3)
source; ld r14,40(r3)
adde r0,r0,r9
source; ld r15,48(r3)
source; ld r16,56(r3)
addi r3,r3,64
adde r0,r0,r10
dest; std r6,0(r4)
dest; std r9,8(r4)
adde r0,r0,r11
dest; std r10,16(r4)
dest; std r11,24(r4)
adde r0,r0,r12
dest; std r12,32(r4)
dest; std r14,40(r4)
adde r0,r0,r14
dest; std r15,48(r4)
dest; std r16,56(r4)
addi r4,r4,64
adde r0,r0,r15
source; ld r6,0(r3)
source; ld r9,8(r3)
adde r0,r0,r16
source; ld r10,16(r3)
source; ld r11,24(r3)
bdnz 2b
adde r0,r0,r6
source; ld r12,32(r3)
source; ld r14,40(r3)
adde r0,r0,r9
source; ld r15,48(r3)
source; ld r16,56(r3)
addi r3,r3,64
adde r0,r0,r10
dest; std r6,0(r4)
dest; std r9,8(r4)
adde r0,r0,r11
dest; std r10,16(r4)
dest; std r11,24(r4)
adde r0,r0,r12
dest; std r12,32(r4)
dest; std r14,40(r4)
adde r0,r0,r14
dest; std r15,48(r4)
dest; std r16,56(r4)
addi r4,r4,64
adde r0,r0,r15
adde r0,r0,r16
ld r14,STK_REG(r14)(r1)
ld r15,STK_REG(r15)(r1)
ld r16,STK_REG(r16)(r1)
addi r1,r1,STACKFRAMESIZE
andi. r5,r5,63
.Lcopy_tail_doublewords: /* Up to 127 bytes to go */
srdi. r6,r5,3
beq .Lcopy_tail_word
mtctr r6
3:
source; ld r6,0(r3)
addi r3,r3,8
adde r0,r0,r6
dest; std r6,0(r4)
addi r4,r4,8
bdnz 3b
andi. r5,r5,7
.Lcopy_tail_word: /* Up to 7 bytes to go */
srdi. r6,r5,2
beq .Lcopy_tail_halfword
source; lwz r6,0(r3)
addi r3,r3,4
adde r0,r0,r6
dest; stw r6,0(r4)
addi r4,r4,4
subi r5,r5,4
.Lcopy_tail_halfword: /* Up to 3 bytes to go */
srdi. r6,r5,1
beq .Lcopy_tail_byte
source; lhz r6,0(r3)
addi r3,r3,2
adde r0,r0,r6
dest; sth r6,0(r4)
addi r4,r4,2
subi r5,r5,2
.Lcopy_tail_byte: /* Up to 1 byte to go */
andi. r6,r5,1
beq .Lcopy_finish
source; lbz r6,0(r3)
sldi r9,r6,8 /* Pad the byte out to 16 bits */
adde r0,r0,r9
dest; stb r6,0(r4)
.Lcopy_finish:
addze r0,r0 /* add in final carry */
rldicl r4,r0,32,0 /* fold two 32 bit halves together */
add r3,r4,r0
srdi r3,r3,32
blr
.Lsrc_error:
cmpdi 0,r7,0
beqlr
li r6,-EFAULT
stw r6,0(r7)
blr
.Ldest_error:
cmpdi 0,r8,0
beqlr
li r6,-EFAULT
stw r6,0(r8)
blr