Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
kernel-fxtec-pro1x/arch/powerpc/lib/checksum_64.S
Anton Blanchard 9b83ecb0a3 powerpc: Optimise 64bit csum_partial 
The main loop of csum_partial runs very slowly on recent POWER CPUs. After some
analysis on both POWER6 and POWER7 I came up with routine below. First we get
the source aligned to a double word, ignoring any odd alignment to keep things
simple. Then we do 64 bytes at a time, with an entry and exit limb of a further
64 bytes. On both POWER6 and POWER7 this should be as fast as we can go since
we are limited by the latency of the adde instructions.

To test this I forced checksumming on over loopback and ran socklib (a
simple TCP benchmark). On a POWER6 575 throughput improved by 11% with
this patch.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-09-02 14:07:29 +10:00

342 lines
7.1 KiB
ArmAsm
Raw Blame History

/*
* 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
/*
* 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, and (for an error on
* src) zeroes the rest of dst.
*
* This code needs to be reworked to take advantage of 64 bit sum+copy.
* However, due to tokenring halfword alignment problems this will be very
* tricky. For now we'll leave it until we instrument it somehow.
*
* 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
subi r3,r3,4
subi r4,r4,4
srwi. r6,r5,2
beq 3f /* if we're doing < 4 bytes */
andi. r9,r4,2 /* Align dst to longword boundary */
beq+ 1f
81: lhz r6,4(r3) /* do 2 bytes to get aligned */
addi r3,r3,2
subi r5,r5,2
91: sth r6,4(r4)
addi r4,r4,2
addc r0,r0,r6
srwi. r6,r5,2 /* # words to do */
beq 3f
1: mtctr r6
82: lwzu r6,4(r3) /* the bdnz has zero overhead, so it should */
92: stwu r6,4(r4) /* be unnecessary to unroll this loop */
adde r0,r0,r6
bdnz 82b
andi. r5,r5,3
3: cmpwi 0,r5,2
blt+ 4f
83: lhz r6,4(r3)
addi r3,r3,2
subi r5,r5,2
93: sth r6,4(r4)
addi r4,r4,2
adde r0,r0,r6
4: cmpwi 0,r5,1
bne+ 5f
84: lbz r6,4(r3)
94: stb r6,4(r4)
slwi r6,r6,8 /* Upper byte of word */
adde r0,r0,r6
5: addze r3,r0 /* add in final carry (unlikely with 64-bit regs) */
rldicl r4,r3,32,0 /* fold 64 bit value */
add r3,r4,r3
srdi r3,r3,32
blr
/* These shouldn't go in the fixup section, since that would
cause the ex_table addresses to get out of order. */
.globl src_error_1
src_error_1:
li r6,0
subi r5,r5,2
95: sth r6,4(r4)
addi r4,r4,2
srwi. r6,r5,2
beq 3f
mtctr r6
.globl src_error_2
src_error_2:
li r6,0
96: stwu r6,4(r4)
bdnz 96b
3: andi. r5,r5,3
beq src_error
.globl src_error_3
src_error_3:
li r6,0
mtctr r5
addi r4,r4,3
97: stbu r6,1(r4)
bdnz 97b
.globl src_error
src_error:
cmpdi 0,r7,0
beq 1f
li r6,-EFAULT
stw r6,0(r7)
1: addze r3,r0
blr
.globl dst_error
dst_error:
cmpdi 0,r8,0
beq 1f
li r6,-EFAULT
stw r6,0(r8)
1: addze r3,r0
blr
.section __ex_table,"a"
.align 3
.llong 81b,src_error_1
.llong 91b,dst_error
.llong 82b,src_error_2
.llong 92b,dst_error
.llong 83b,src_error_3
.llong 93b,dst_error
.llong 84b,src_error_3
.llong 94b,dst_error
.llong 95b,dst_error
.llong 96b,dst_error
.llong 97b,dst_error
Reference in a new issue View git blame Copy permalink