linux/arch/powerpc/include/asm/checksum.h

235 lines
6 KiB

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>
2018-05-24 11:33:18 +00:00
powerpc: Force inlining of csum_add() Commit 328e7e487a46 ("powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10") inlined csum_partial(). Now that csum_partial() is inlined, GCC outlines csum_add() when called by csum_partial(). c064fb28 <csum_add>: c064fb28: 7c 63 20 14 addc r3,r3,r4 c064fb2c: 7c 63 01 94 addze r3,r3 c064fb30: 4e 80 00 20 blr c0665fb8 <csum_add>: c0665fb8: 7c 63 20 14 addc r3,r3,r4 c0665fbc: 7c 63 01 94 addze r3,r3 c0665fc0: 4e 80 00 20 blr c066719c: 7c 9a c0 2e lwzx r4,r26,r24 c06671a0: 38 60 00 00 li r3,0 c06671a4: 7f 1a c2 14 add r24,r26,r24 c06671a8: 4b ff ee 11 bl c0665fb8 <csum_add> c06671ac: 80 98 00 04 lwz r4,4(r24) c06671b0: 4b ff ee 09 bl c0665fb8 <csum_add> c06671b4: 80 98 00 08 lwz r4,8(r24) c06671b8: 4b ff ee 01 bl c0665fb8 <csum_add> c06671bc: a0 98 00 0c lhz r4,12(r24) c06671c0: 4b ff ed f9 bl c0665fb8 <csum_add> c06671c4: 7c 63 18 f8 not r3,r3 c06671c8: 81 3f 00 68 lwz r9,104(r31) c06671cc: 81 5f 00 a0 lwz r10,160(r31) c06671d0: 7d 29 18 14 addc r9,r9,r3 c06671d4: 7d 29 01 94 addze r9,r9 c06671d8: 91 3f 00 68 stw r9,104(r31) c06671dc: 7d 1a 50 50 subf r8,r26,r10 c06671e0: 83 01 00 10 lwz r24,16(r1) c06671e4: 83 41 00 18 lwz r26,24(r1) The sum with 0 is useless, should have been skipped. And there is even one completely unused instance of csum_add(). In file included from ./include/net/checksum.h:22, from ./include/linux/skbuff.h:28, from ./include/linux/icmp.h:16, from net/ipv6/ip6_tunnel.c:23: ./arch/powerpc/include/asm/checksum.h: In function '__ip6_tnl_rcv': ./arch/powerpc/include/asm/checksum.h:94:22: warning: inlining failed in call to 'csum_add': call is unlikely and code size would grow [-Winline] 94 | static inline __wsum csum_add(__wsum csum, __wsum addend) | ^~~~~~~~ ./arch/powerpc/include/asm/checksum.h:172:31: note: called from here 172 | sum = csum_add(sum, (__force __wsum)*(const u32 *)buff); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./arch/powerpc/include/asm/checksum.h:94:22: warning: inlining failed in call to 'csum_add': call is unlikely and code size would grow [-Winline] 94 | static inline __wsum csum_add(__wsum csum, __wsum addend) | ^~~~~~~~ ./arch/powerpc/include/asm/checksum.h:177:31: note: called from here 177 | sum = csum_add(sum, (__force __wsum) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 178 | *(const u32 *)(buff + 4)); | ~~~~~~~~~~~~~~~~~~~~~~~~~ ./arch/powerpc/include/asm/checksum.h:94:22: warning: inlining failed in call to 'csum_add': call is unlikely and code size would grow [-Winline] 94 | static inline __wsum csum_add(__wsum csum, __wsum addend) | ^~~~~~~~ ./arch/powerpc/include/asm/checksum.h:183:31: note: called from here 183 | sum = csum_add(sum, (__force __wsum) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 184 | *(const u32 *)(buff + 8)); | ~~~~~~~~~~~~~~~~~~~~~~~~~ ./arch/powerpc/include/asm/checksum.h:94:22: warning: inlining failed in call to 'csum_add': call is unlikely and code size would grow [-Winline] 94 | static inline __wsum csum_add(__wsum csum, __wsum addend) | ^~~~~~~~ ./arch/powerpc/include/asm/checksum.h:186:31: note: called from here 186 | sum = csum_add(sum, (__force __wsum) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 187 | *(const u16 *)(buff + 12)); | ~~~~~~~~~~~~~~~~~~~~~~~~~~ Force inlining of csum_add(). 94c: 80 df 00 a0 lwz r6,160(r31) 950: 7d 28 50 2e lwzx r9,r8,r10 954: 7d 48 52 14 add r10,r8,r10 958: 80 aa 00 04 lwz r5,4(r10) 95c: 80 ff 00 68 lwz r7,104(r31) 960: 7d 29 28 14 addc r9,r9,r5 964: 7d 29 01 94 addze r9,r9 968: 7d 08 30 50 subf r8,r8,r6 96c: 80 aa 00 08 lwz r5,8(r10) 970: a1 4a 00 0c lhz r10,12(r10) 974: 7d 29 28 14 addc r9,r9,r5 978: 7d 29 01 94 addze r9,r9 97c: 7d 29 50 14 addc r9,r9,r10 980: 7d 29 01 94 addze r9,r9 984: 7d 29 48 f8 not r9,r9 988: 7c e7 48 14 addc r7,r7,r9 98c: 7c e7 01 94 addze r7,r7 990: 90 ff 00 68 stw r7,104(r31) In the non-inlined version, the first sum with 0 was performed. Here it is skipped. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/f7f4d4e364de6e473da874468b903da6e5d97adc.1620713272.git.christophe.leroy@csgroup.eu
2021-05-11 06:08:06 +00:00
powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10 ppc-linux-objdump -d vmlinux | grep -e "<csum_partial>" -e "<__csum_partial>" With gcc9 I get: c0017ef8 <__csum_partial>: c00182fc: 4b ff fb fd bl c0017ef8 <__csum_partial> c0018478: 4b ff fa 80 b c0017ef8 <__csum_partial> c03e8458: 4b c2 fa a0 b c0017ef8 <__csum_partial> c03e8518: 4b c2 f9 e1 bl c0017ef8 <__csum_partial> c03ef410: 4b c2 8a e9 bl c0017ef8 <__csum_partial> c03f0b24: 4b c2 73 d5 bl c0017ef8 <__csum_partial> c04279a4: 4b bf 05 55 bl c0017ef8 <__csum_partial> c0429820: 4b be e6 d9 bl c0017ef8 <__csum_partial> c0429944: 4b be e5 b5 bl c0017ef8 <__csum_partial> c042b478: 4b be ca 81 bl c0017ef8 <__csum_partial> c042b554: 4b be c9 a5 bl c0017ef8 <__csum_partial> c045f15c: 4b bb 8d 9d bl c0017ef8 <__csum_partial> c0492190: 4b b8 5d 69 bl c0017ef8 <__csum_partial> c0492310: 4b b8 5b e9 bl c0017ef8 <__csum_partial> c0495594: 4b b8 29 65 bl c0017ef8 <__csum_partial> c049c420: 4b b7 ba d9 bl c0017ef8 <__csum_partial> c049c870: 4b b7 b6 89 bl c0017ef8 <__csum_partial> c049c930: 4b b7 b5 c9 bl c0017ef8 <__csum_partial> c04a9ca0: 4b b6 e2 59 bl c0017ef8 <__csum_partial> c04bdde4: 4b b5 a1 15 bl c0017ef8 <__csum_partial> c04be480: 4b b5 9a 79 bl c0017ef8 <__csum_partial> c04be710: 4b b5 97 e9 bl c0017ef8 <__csum_partial> c04c969c: 4b b4 e8 5d bl c0017ef8 <__csum_partial> c04ca2fc: 4b b4 db fd bl c0017ef8 <__csum_partial> c04cf5bc: 4b b4 89 3d bl c0017ef8 <__csum_partial> c04d0440: 4b b4 7a b9 bl c0017ef8 <__csum_partial> With gcc10 I get: c0018d08 <__csum_partial>: c0019020 <csum_partial>: c0019020: 4b ff fc e8 b c0018d08 <__csum_partial> c001914c: 4b ff fe d4 b c0019020 <csum_partial> c0019250: 4b ff fd d1 bl c0019020 <csum_partial> c03e404c <csum_partial>: c03e404c: 4b c3 4c bc b c0018d08 <__csum_partial> c03e4050: 4b ff ff fc b c03e404c <csum_partial> c03e40fc: 4b ff ff 51 bl c03e404c <csum_partial> c03e6680: 4b ff d9 cd bl c03e404c <csum_partial> c03e68c4: 4b ff d7 89 bl c03e404c <csum_partial> c03e7934: 4b ff c7 19 bl c03e404c <csum_partial> c03e7bf8: 4b ff c4 55 bl c03e404c <csum_partial> c03eb148: 4b ff 8f 05 bl c03e404c <csum_partial> c03ecf68: 4b c2 bd a1 bl c0018d08 <__csum_partial> c04275b8 <csum_partial>: c04275b8: 4b bf 17 50 b c0018d08 <__csum_partial> c0427884: 4b ff fd 35 bl c04275b8 <csum_partial> c0427b18: 4b ff fa a1 bl c04275b8 <csum_partial> c0427bd8: 4b ff f9 e1 bl c04275b8 <csum_partial> c0427cd4: 4b ff f8 e5 bl c04275b8 <csum_partial> c0427e34: 4b ff f7 85 bl c04275b8 <csum_partial> c045a1c0: 4b bb eb 49 bl c0018d08 <__csum_partial> c0489464 <csum_partial>: c0489464: 4b b8 f8 a4 b c0018d08 <__csum_partial> c04896b0: 4b ff fd b5 bl c0489464 <csum_partial> c048982c: 4b ff fc 39 bl c0489464 <csum_partial> c0490158: 4b b8 8b b1 bl c0018d08 <__csum_partial> c0492f0c <csum_partial>: c0492f0c: 4b b8 5d fc b c0018d08 <__csum_partial> c049326c: 4b ff fc a1 bl c0492f0c <csum_partial> c049333c: 4b ff fb d1 bl c0492f0c <csum_partial> c0493b18: 4b ff f3 f5 bl c0492f0c <csum_partial> c0493f50: 4b ff ef bd bl c0492f0c <csum_partial> c0493ffc: 4b ff ef 11 bl c0492f0c <csum_partial> c04a0f78: 4b b7 7d 91 bl c0018d08 <__csum_partial> c04b3e3c: 4b b6 4e cd bl c0018d08 <__csum_partial> c04b40d0 <csum_partial>: c04b40d0: 4b b6 4c 38 b c0018d08 <__csum_partial> c04b4448: 4b ff fc 89 bl c04b40d0 <csum_partial> c04b46f4: 4b ff f9 dd bl c04b40d0 <csum_partial> c04bf448: 4b b5 98 c0 b c0018d08 <__csum_partial> c04c5264: 4b b5 3a a5 bl c0018d08 <__csum_partial> c04c61e4: 4b b5 2b 25 bl c0018d08 <__csum_partial> gcc10 defines multiple versions of csum_partial() which are just an unconditionnal branch to __csum_partial(). To enforce inlining of that branch to __csum_partial(), mark csum_partial() as __always_inline. With this patch with gcc10: c0018d08 <__csum_partial>: c0019148: 4b ff fb c0 b c0018d08 <__csum_partial> c001924c: 4b ff fa bd bl c0018d08 <__csum_partial> c03e40ec: 4b c3 4c 1d bl c0018d08 <__csum_partial> c03e4120: 4b c3 4b e8 b c0018d08 <__csum_partial> c03eb004: 4b c2 dd 05 bl c0018d08 <__csum_partial> c03ecef4: 4b c2 be 15 bl c0018d08 <__csum_partial> c0427558: 4b bf 17 b1 bl c0018d08 <__csum_partial> c04286e4: 4b bf 06 25 bl c0018d08 <__csum_partial> c0428cd8: 4b bf 00 31 bl c0018d08 <__csum_partial> c0428d84: 4b be ff 85 bl c0018d08 <__csum_partial> c045a17c: 4b bb eb 8d bl c0018d08 <__csum_partial> c0489450: 4b b8 f8 b9 bl c0018d08 <__csum_partial> c0491860: 4b b8 74 a9 bl c0018d08 <__csum_partial> c0492eec: 4b b8 5e 1d bl c0018d08 <__csum_partial> c04a0eac: 4b b7 7e 5d bl c0018d08 <__csum_partial> c04b3e34: 4b b6 4e d5 bl c0018d08 <__csum_partial> c04b426c: 4b b6 4a 9d bl c0018d08 <__csum_partial> c04b463c: 4b b6 46 cd bl c0018d08 <__csum_partial> c04c004c: 4b b5 8c bd bl c0018d08 <__csum_partial> c04c0368: 4b b5 89 a1 bl c0018d08 <__csum_partial> c04c5254: 4b b5 3a b5 bl c0018d08 <__csum_partial> c04c60d4: 4b b5 2c 35 bl c0018d08 <__csum_partial> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/a1d31f84ddb0926813b17fcd5cc7f3fa7b4deac2.1602759123.git.christophe.leroy@csgroup.eu
2020-10-15 10:52:20 +00:00
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>
2018-05-24 11:33:18 +00:00