linux_dsm_epyc7002/arch/powerpc/lib/checksum_64.S
Christophe Leroy e9c4943a10 powerpc: Implement csum_ipv6_magic in assembly
The generic csum_ipv6_magic() generates a pretty bad result

00000000 <csum_ipv6_magic>: (PPC32)
   0:	81 23 00 00 	lwz     r9,0(r3)
   4:	81 03 00 04 	lwz     r8,4(r3)
   8:	7c e7 4a 14 	add     r7,r7,r9
   c:	7d 29 38 10 	subfc   r9,r9,r7
  10:	7d 4a 51 10 	subfe   r10,r10,r10
  14:	7d 27 42 14 	add     r9,r7,r8
  18:	7d 2a 48 50 	subf    r9,r10,r9
  1c:	80 e3 00 08 	lwz     r7,8(r3)
  20:	7d 08 48 10 	subfc   r8,r8,r9
  24:	7d 4a 51 10 	subfe   r10,r10,r10
  28:	7d 29 3a 14 	add     r9,r9,r7
  2c:	81 03 00 0c 	lwz     r8,12(r3)
  30:	7d 2a 48 50 	subf    r9,r10,r9
  34:	7c e7 48 10 	subfc   r7,r7,r9
  38:	7d 4a 51 10 	subfe   r10,r10,r10
  3c:	7d 29 42 14 	add     r9,r9,r8
  40:	7d 2a 48 50 	subf    r9,r10,r9
  44:	80 e4 00 00 	lwz     r7,0(r4)
  48:	7d 08 48 10 	subfc   r8,r8,r9
  4c:	7d 4a 51 10 	subfe   r10,r10,r10
  50:	7d 29 3a 14 	add     r9,r9,r7
  54:	7d 2a 48 50 	subf    r9,r10,r9
  58:	81 04 00 04 	lwz     r8,4(r4)
  5c:	7c e7 48 10 	subfc   r7,r7,r9
  60:	7d 4a 51 10 	subfe   r10,r10,r10
  64:	7d 29 42 14 	add     r9,r9,r8
  68:	7d 2a 48 50 	subf    r9,r10,r9
  6c:	80 e4 00 08 	lwz     r7,8(r4)
  70:	7d 08 48 10 	subfc   r8,r8,r9
  74:	7d 4a 51 10 	subfe   r10,r10,r10
  78:	7d 29 3a 14 	add     r9,r9,r7
  7c:	7d 2a 48 50 	subf    r9,r10,r9
  80:	81 04 00 0c 	lwz     r8,12(r4)
  84:	7c e7 48 10 	subfc   r7,r7,r9
  88:	7d 4a 51 10 	subfe   r10,r10,r10
  8c:	7d 29 42 14 	add     r9,r9,r8
  90:	7d 2a 48 50 	subf    r9,r10,r9
  94:	7d 08 48 10 	subfc   r8,r8,r9
  98:	7d 4a 51 10 	subfe   r10,r10,r10
  9c:	7d 29 2a 14 	add     r9,r9,r5
  a0:	7d 2a 48 50 	subf    r9,r10,r9
  a4:	7c a5 48 10 	subfc   r5,r5,r9
  a8:	7c 63 19 10 	subfe   r3,r3,r3
  ac:	7d 29 32 14 	add     r9,r9,r6
  b0:	7d 23 48 50 	subf    r9,r3,r9
  b4:	7c c6 48 10 	subfc   r6,r6,r9
  b8:	7c 63 19 10 	subfe   r3,r3,r3
  bc:	7c 63 48 50 	subf    r3,r3,r9
  c0:	54 6a 80 3e 	rotlwi  r10,r3,16
  c4:	7c 63 52 14 	add     r3,r3,r10
  c8:	7c 63 18 f8 	not     r3,r3
  cc:	54 63 84 3e 	rlwinm  r3,r3,16,16,31
  d0:	4e 80 00 20 	blr

0000000000000000 <.csum_ipv6_magic>: (PPC64)
   0:	81 23 00 00 	lwz     r9,0(r3)
   4:	80 03 00 04 	lwz     r0,4(r3)
   8:	81 63 00 08 	lwz     r11,8(r3)
   c:	7c e7 4a 14 	add     r7,r7,r9
  10:	7f 89 38 40 	cmplw   cr7,r9,r7
  14:	7d 47 02 14 	add     r10,r7,r0
  18:	7d 30 10 26 	mfocrf  r9,1
  1c:	55 29 f7 fe 	rlwinm  r9,r9,30,31,31
  20:	7d 4a 4a 14 	add     r10,r10,r9
  24:	7f 80 50 40 	cmplw   cr7,r0,r10
  28:	7d 2a 5a 14 	add     r9,r10,r11
  2c:	80 03 00 0c 	lwz     r0,12(r3)
  30:	81 44 00 00 	lwz     r10,0(r4)
  34:	7d 10 10 26 	mfocrf  r8,1
  38:	55 08 f7 fe 	rlwinm  r8,r8,30,31,31
  3c:	7d 29 42 14 	add     r9,r9,r8
  40:	81 04 00 04 	lwz     r8,4(r4)
  44:	7f 8b 48 40 	cmplw   cr7,r11,r9
  48:	7d 29 02 14 	add     r9,r9,r0
  4c:	7d 70 10 26 	mfocrf  r11,1
  50:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  54:	7d 29 5a 14 	add     r9,r9,r11
  58:	7f 80 48 40 	cmplw   cr7,r0,r9
  5c:	7d 29 52 14 	add     r9,r9,r10
  60:	7c 10 10 26 	mfocrf  r0,1
  64:	54 00 f7 fe 	rlwinm  r0,r0,30,31,31
  68:	7d 69 02 14 	add     r11,r9,r0
  6c:	7f 8a 58 40 	cmplw   cr7,r10,r11
  70:	7c 0b 42 14 	add     r0,r11,r8
  74:	81 44 00 08 	lwz     r10,8(r4)
  78:	7c f0 10 26 	mfocrf  r7,1
  7c:	54 e7 f7 fe 	rlwinm  r7,r7,30,31,31
  80:	7c 00 3a 14 	add     r0,r0,r7
  84:	7f 88 00 40 	cmplw   cr7,r8,r0
  88:	7d 20 52 14 	add     r9,r0,r10
  8c:	80 04 00 0c 	lwz     r0,12(r4)
  90:	7d 70 10 26 	mfocrf  r11,1
  94:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  98:	7d 29 5a 14 	add     r9,r9,r11
  9c:	7f 8a 48 40 	cmplw   cr7,r10,r9
  a0:	7d 29 02 14 	add     r9,r9,r0
  a4:	7d 70 10 26 	mfocrf  r11,1
  a8:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  ac:	7d 29 5a 14 	add     r9,r9,r11
  b0:	7f 80 48 40 	cmplw   cr7,r0,r9
  b4:	7d 29 2a 14 	add     r9,r9,r5
  b8:	7c 10 10 26 	mfocrf  r0,1
  bc:	54 00 f7 fe 	rlwinm  r0,r0,30,31,31
  c0:	7d 29 02 14 	add     r9,r9,r0
  c4:	7f 85 48 40 	cmplw   cr7,r5,r9
  c8:	7c 09 32 14 	add     r0,r9,r6
  cc:	7d 50 10 26 	mfocrf  r10,1
  d0:	55 4a f7 fe 	rlwinm  r10,r10,30,31,31
  d4:	7c 00 52 14 	add     r0,r0,r10
  d8:	7f 80 30 40 	cmplw   cr7,r0,r6
  dc:	7d 30 10 26 	mfocrf  r9,1
  e0:	55 29 ef fe 	rlwinm  r9,r9,29,31,31
  e4:	7c 09 02 14 	add     r0,r9,r0
  e8:	54 03 80 3e 	rotlwi  r3,r0,16
  ec:	7c 03 02 14 	add     r0,r3,r0
  f0:	7c 03 00 f8 	not     r3,r0
  f4:	78 63 84 22 	rldicl  r3,r3,48,48
  f8:	4e 80 00 20 	blr

This patch implements it in assembly for both PPC32 and PPC64

Link: https://github.com/linuxppc/linux/issues/9
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04 00:39:19 +10:00

460 lines
8.5 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>
#include <asm/export.h>
/*
* 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 >> 1) & 0x3 */
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 adde instructions 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)
#ifdef __BIG_ENDIAN__
sldi r9,r6,8 /* Pad the byte out to 16 bits */
adde r0,r0,r9
#else
adde r0,r0,r6
#endif
.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
EXPORT_SYMBOL(__csum_partial)
.macro srcnr
100:
EX_TABLE(100b,.Lsrc_error_nr)
.endm
.macro source
150:
EX_TABLE(150b,.Lsrc_error)
.endm
.macro dstnr
200:
EX_TABLE(200b,.Ldest_error_nr)
.endm
.macro dest
250:
EX_TABLE(250b,.Ldest_error)
.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 >> 1) & 0x3 */
beq .Lcopy_aligned
li r9,4
sub r6,r9,r6
mtctr r6
1:
srcnr; lhz r6,0(r3) /* align to doubleword */
subi r5,r5,2
addi r3,r3,2
adde r0,r0,r6
dstnr; 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 adde instructions 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:
srcnr; ld r6,0(r3)
addi r3,r3,8
adde r0,r0,r6
dstnr; 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
srcnr; lwz r6,0(r3)
addi r3,r3,4
adde r0,r0,r6
dstnr; 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
srcnr; lhz r6,0(r3)
addi r3,r3,2
adde r0,r0,r6
dstnr; 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
srcnr; lbz r6,0(r3)
#ifdef __BIG_ENDIAN__
sldi r9,r6,8 /* Pad the byte out to 16 bits */
adde r0,r0,r9
#else
adde r0,r0,r6
#endif
dstnr; 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:
ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
addi r1,r1,STACKFRAMESIZE
.Lsrc_error_nr:
cmpdi 0,r7,0
beqlr
li r6,-EFAULT
stw r6,0(r7)
blr
.Ldest_error:
ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
addi r1,r1,STACKFRAMESIZE
.Ldest_error_nr:
cmpdi 0,r8,0
beqlr
li r6,-EFAULT
stw r6,0(r8)
blr
EXPORT_SYMBOL(csum_partial_copy_generic)
/*
* __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
* const struct in6_addr *daddr,
* __u32 len, __u8 proto, __wsum sum)
*/
_GLOBAL(csum_ipv6_magic)
ld r8, 0(r3)
ld r9, 8(r3)
add r5, r5, r6
addc r0, r8, r9
ld r10, 0(r4)
ld r11, 8(r4)
adde r0, r0, r10
add r5, r5, r7
adde r0, r0, r11
adde r0, r0, r5
addze r0, r0
rotldi r3, r0, 32 /* fold two 32 bit halves together */
add r3, r0, r3
srdi r0, r3, 32
rotlwi r3, r0, 16 /* fold two 16 bit halves together */
add r3, r0, r3
not r3, r3
rlwinm r3, r3, 16, 16, 31
blr
EXPORT_SYMBOL(csum_ipv6_magic)