Source-Changes-HG archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

[src/trunk]: src/crypto/external/bsd/openssl/lib/libcrypto/arch/arm Update th...



details:   https://anonhg.NetBSD.org/src/rev/dedaadc6687e
branches:  trunk
changeset: 336687:dedaadc6687e
user:      martin <martin%NetBSD.org@localhost>
date:      Tue Mar 10 13:28:47 2015 +0000

description:
Update the ARM asm support code from version 1.0.2 with some local
modifications to make it compile and work on armv4.

diffstat:

 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/aes-armv4.S        |  1178 ++++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/aes.inc            |     4 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/aesv8-armx.S       |   733 ++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/arm_asm.h          |     5 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/armv4-gf2m.S       |   204 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/armv4-mont.S       |   581 ++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/armv4cpuid.S       |   210 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/bsaes-armv7.S      |  2547 +++++++++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/crypto.inc         |    10 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/des.inc            |    12 -
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/ghash-armv4.S      |   524 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/ghashv8-armx.S     |   117 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/modes.inc          |     4 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/sha.inc            |     7 +
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/sha1-armv4-large.S |  1456 +++++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/sha256-armv4.S     |  2696 ++++++++++
 crypto/external/bsd/openssl/lib/libcrypto/arch/arm/sha512-armv4.S     |  1776 ++++++
 17 files changed, 12052 insertions(+), 12 deletions(-)

diffs (truncated from 12132 to 300 lines):

diff -r 283f82d06e5d -r dedaadc6687e crypto/external/bsd/openssl/lib/libcrypto/arch/arm/aes-armv4.S
--- /dev/null   Thu Jan 01 00:00:00 1970 +0000
+++ b/crypto/external/bsd/openssl/lib/libcrypto/arch/arm/aes-armv4.S    Tue Mar 10 13:28:47 2015 +0000
@@ -0,0 +1,1178 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro%openssl.org@localhost> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@ ====================================================================
+
+@ AES for ARMv4
+
+@ January 2007.
+@
+@ Code uses single 1K S-box and is >2 times faster than code generated
+@ by gcc-3.4.1. This is thanks to unique feature of ARMv4 ISA, which
+@ allows to merge logical or arithmetic operation with shift or rotate
+@ in one instruction and emit combined result every cycle. The module
+@ is endian-neutral. The performance is ~42 cycles/byte for 128-bit
+@ key [on single-issue Xscale PXA250 core].
+
+@ May 2007.
+@
+@ AES_set_[en|de]crypt_key is added.
+
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 12% improvement on
+@ Cortex A8 core and ~25 cycles per byte processed with 128-bit key.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 16%
+@ improvement on Cortex A8 core and ~21.5 cycles per byte.
+
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# include "arm_asm.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code  32
+#else
+.syntax        unified
+# ifdef __thumb2__
+.thumb
+# else
+.code  32
+# endif
+#endif
+
+.type  AES_Te,%object
+.align 5
+AES_Te:
+.word  0xc66363a5, 0xf87c7c84, 0xee777799, 0xf67b7b8d
+.word  0xfff2f20d, 0xd66b6bbd, 0xde6f6fb1, 0x91c5c554
+.word  0x60303050, 0x02010103, 0xce6767a9, 0x562b2b7d
+.word  0xe7fefe19, 0xb5d7d762, 0x4dababe6, 0xec76769a
+.word  0x8fcaca45, 0x1f82829d, 0x89c9c940, 0xfa7d7d87
+.word  0xeffafa15, 0xb25959eb, 0x8e4747c9, 0xfbf0f00b
+.word  0x41adadec, 0xb3d4d467, 0x5fa2a2fd, 0x45afafea
+.word  0x239c9cbf, 0x53a4a4f7, 0xe4727296, 0x9bc0c05b
+.word  0x75b7b7c2, 0xe1fdfd1c, 0x3d9393ae, 0x4c26266a
+.word  0x6c36365a, 0x7e3f3f41, 0xf5f7f702, 0x83cccc4f
+.word  0x6834345c, 0x51a5a5f4, 0xd1e5e534, 0xf9f1f108
+.word  0xe2717193, 0xabd8d873, 0x62313153, 0x2a15153f
+.word  0x0804040c, 0x95c7c752, 0x46232365, 0x9dc3c35e
+.word  0x30181828, 0x379696a1, 0x0a05050f, 0x2f9a9ab5
+.word  0x0e070709, 0x24121236, 0x1b80809b, 0xdfe2e23d
+.word  0xcdebeb26, 0x4e272769, 0x7fb2b2cd, 0xea75759f
+.word  0x1209091b, 0x1d83839e, 0x582c2c74, 0x341a1a2e
+.word  0x361b1b2d, 0xdc6e6eb2, 0xb45a5aee, 0x5ba0a0fb
+.word  0xa45252f6, 0x763b3b4d, 0xb7d6d661, 0x7db3b3ce
+.word  0x5229297b, 0xdde3e33e, 0x5e2f2f71, 0x13848497
+.word  0xa65353f5, 0xb9d1d168, 0x00000000, 0xc1eded2c
+.word  0x40202060, 0xe3fcfc1f, 0x79b1b1c8, 0xb65b5bed
+.word  0xd46a6abe, 0x8dcbcb46, 0x67bebed9, 0x7239394b
+.word  0x944a4ade, 0x984c4cd4, 0xb05858e8, 0x85cfcf4a
+.word  0xbbd0d06b, 0xc5efef2a, 0x4faaaae5, 0xedfbfb16
+.word  0x864343c5, 0x9a4d4dd7, 0x66333355, 0x11858594
+.word  0x8a4545cf, 0xe9f9f910, 0x04020206, 0xfe7f7f81
+.word  0xa05050f0, 0x783c3c44, 0x259f9fba, 0x4ba8a8e3
+.word  0xa25151f3, 0x5da3a3fe, 0x804040c0, 0x058f8f8a
+.word  0x3f9292ad, 0x219d9dbc, 0x70383848, 0xf1f5f504
+.word  0x63bcbcdf, 0x77b6b6c1, 0xafdada75, 0x42212163
+.word  0x20101030, 0xe5ffff1a, 0xfdf3f30e, 0xbfd2d26d
+.word  0x81cdcd4c, 0x180c0c14, 0x26131335, 0xc3ecec2f
+.word  0xbe5f5fe1, 0x359797a2, 0x884444cc, 0x2e171739
+.word  0x93c4c457, 0x55a7a7f2, 0xfc7e7e82, 0x7a3d3d47
+.word  0xc86464ac, 0xba5d5de7, 0x3219192b, 0xe6737395
+.word  0xc06060a0, 0x19818198, 0x9e4f4fd1, 0xa3dcdc7f
+.word  0x44222266, 0x542a2a7e, 0x3b9090ab, 0x0b888883
+.word  0x8c4646ca, 0xc7eeee29, 0x6bb8b8d3, 0x2814143c
+.word  0xa7dede79, 0xbc5e5ee2, 0x160b0b1d, 0xaddbdb76
+.word  0xdbe0e03b, 0x64323256, 0x743a3a4e, 0x140a0a1e
+.word  0x924949db, 0x0c06060a, 0x4824246c, 0xb85c5ce4
+.word  0x9fc2c25d, 0xbdd3d36e, 0x43acacef, 0xc46262a6
+.word  0x399191a8, 0x319595a4, 0xd3e4e437, 0xf279798b
+.word  0xd5e7e732, 0x8bc8c843, 0x6e373759, 0xda6d6db7
+.word  0x018d8d8c, 0xb1d5d564, 0x9c4e4ed2, 0x49a9a9e0
+.word  0xd86c6cb4, 0xac5656fa, 0xf3f4f407, 0xcfeaea25
+.word  0xca6565af, 0xf47a7a8e, 0x47aeaee9, 0x10080818
+.word  0x6fbabad5, 0xf0787888, 0x4a25256f, 0x5c2e2e72
+.word  0x381c1c24, 0x57a6a6f1, 0x73b4b4c7, 0x97c6c651
+.word  0xcbe8e823, 0xa1dddd7c, 0xe874749c, 0x3e1f1f21
+.word  0x964b4bdd, 0x61bdbddc, 0x0d8b8b86, 0x0f8a8a85
+.word  0xe0707090, 0x7c3e3e42, 0x71b5b5c4, 0xcc6666aa
+.word  0x904848d8, 0x06030305, 0xf7f6f601, 0x1c0e0e12
+.word  0xc26161a3, 0x6a35355f, 0xae5757f9, 0x69b9b9d0
+.word  0x17868691, 0x99c1c158, 0x3a1d1d27, 0x279e9eb9
+.word  0xd9e1e138, 0xebf8f813, 0x2b9898b3, 0x22111133
+.word  0xd26969bb, 0xa9d9d970, 0x078e8e89, 0x339494a7
+.word  0x2d9b9bb6, 0x3c1e1e22, 0x15878792, 0xc9e9e920
+.word  0x87cece49, 0xaa5555ff, 0x50282878, 0xa5dfdf7a
+.word  0x038c8c8f, 0x59a1a1f8, 0x09898980, 0x1a0d0d17
+.word  0x65bfbfda, 0xd7e6e631, 0x844242c6, 0xd06868b8
+.word  0x824141c3, 0x299999b0, 0x5a2d2d77, 0x1e0f0f11
+.word  0x7bb0b0cb, 0xa85454fc, 0x6dbbbbd6, 0x2c16163a
+@ Te4[256]
+.byte  0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+.byte  0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+.byte  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+.byte  0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+.byte  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+.byte  0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+.byte  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+.byte  0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+.byte  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+.byte  0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+.byte  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+.byte  0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+.byte  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+.byte  0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+.byte  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+.byte  0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+.byte  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+.byte  0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+.byte  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+.byte  0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+.byte  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+.byte  0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+.byte  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+.byte  0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+.byte  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+.byte  0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+.byte  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+.byte  0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+.byte  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+.byte  0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+.byte  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+.byte  0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+@ rcon[]
+.word  0x01000000, 0x02000000, 0x04000000, 0x08000000
+.word  0x10000000, 0x20000000, 0x40000000, 0x80000000
+.word  0x1B000000, 0x36000000, 0, 0, 0, 0, 0, 0
+.size  AES_Te,.-AES_Te
+
+@ void AES_encrypt(const unsigned char *in, unsigned char *out,
+@               const AES_KEY *key) {
+.global AES_encrypt
+.type   AES_encrypt,%function
+.align 5
+AES_encrypt:
+#if __ARM_ARCH__<7
+       sub     r3,pc,#8                @ AES_encrypt
+#else
+       adr     r3,AES_encrypt
+#endif
+       stmdb   sp!,{r1,r4-r12,lr}
+       mov     r12,r0          @ inp
+       mov     r11,r2
+       sub     r10,r3,#AES_encrypt-AES_Te      @ Te
+#if __ARM_ARCH__<7
+       ldrb    r0,[r12,#3]     @ load input data in endian-neutral
+       ldrb    r4,[r12,#2]     @ manner...
+       ldrb    r5,[r12,#1]
+       ldrb    r6,[r12,#0]
+       orr     r0,r0,r4,lsl#8
+       ldrb    r1,[r12,#7]
+       orr     r0,r0,r5,lsl#16
+       ldrb    r4,[r12,#6]
+       orr     r0,r0,r6,lsl#24
+       ldrb    r5,[r12,#5]
+       ldrb    r6,[r12,#4]
+       orr     r1,r1,r4,lsl#8
+       ldrb    r2,[r12,#11]
+       orr     r1,r1,r5,lsl#16
+       ldrb    r4,[r12,#10]
+       orr     r1,r1,r6,lsl#24
+       ldrb    r5,[r12,#9]
+       ldrb    r6,[r12,#8]
+       orr     r2,r2,r4,lsl#8
+       ldrb    r3,[r12,#15]
+       orr     r2,r2,r5,lsl#16
+       ldrb    r4,[r12,#14]
+       orr     r2,r2,r6,lsl#24
+       ldrb    r5,[r12,#13]
+       ldrb    r6,[r12,#12]
+       orr     r3,r3,r4,lsl#8
+       orr     r3,r3,r5,lsl#16
+       orr     r3,r3,r6,lsl#24
+#else
+       ldr     r0,[r12,#0]
+       ldr     r1,[r12,#4]
+       ldr     r2,[r12,#8]
+       ldr     r3,[r12,#12]
+#ifdef __ARMEL__
+       rev     r0,r0
+       rev     r1,r1
+       rev     r2,r2
+       rev     r3,r3
+#endif
+#endif
+       bl      _armv4_AES_encrypt
+
+       ldr     r12,[sp],#4             @ pop out
+#if __ARM_ARCH__>=7
+#ifdef __ARMEL__
+       rev     r0,r0
+       rev     r1,r1
+       rev     r2,r2
+       rev     r3,r3
+#endif
+       str     r0,[r12,#0]
+       str     r1,[r12,#4]
+       str     r2,[r12,#8]
+       str     r3,[r12,#12]
+#else
+       mov     r4,r0,lsr#24            @ write output in endian-neutral
+       mov     r5,r0,lsr#16            @ manner...
+       mov     r6,r0,lsr#8
+       strb    r4,[r12,#0]
+       strb    r5,[r12,#1]
+       mov     r4,r1,lsr#24
+       strb    r6,[r12,#2]
+       mov     r5,r1,lsr#16
+       strb    r0,[r12,#3]
+       mov     r6,r1,lsr#8
+       strb    r4,[r12,#4]
+       strb    r5,[r12,#5]
+       mov     r4,r2,lsr#24
+       strb    r6,[r12,#6]
+       mov     r5,r2,lsr#16
+       strb    r1,[r12,#7]
+       mov     r6,r2,lsr#8
+       strb    r4,[r12,#8]
+       strb    r5,[r12,#9]
+       mov     r4,r3,lsr#24
+       strb    r6,[r12,#10]
+       mov     r5,r3,lsr#16
+       strb    r2,[r12,#11]
+       mov     r6,r3,lsr#8
+       strb    r4,[r12,#12]
+       strb    r5,[r12,#13]
+       strb    r6,[r12,#14]
+       strb    r3,[r12,#15]
+#endif
+#if __ARM_ARCH__>=5
+       ldmia   sp!,{r4-r12,pc}
+#else
+       ldmia   sp!,{r4-r12,lr}
+       tst     lr,#1
+       moveq   pc,lr                   @ be binary compatible with V4, yet
+       .word   0xe12fff1e                      @ interoperable with Thumb ISA:-)
+#endif
+.size  AES_encrypt,.-AES_encrypt
+
+.type   _armv4_AES_encrypt,%function
+.align 2
+_armv4_AES_encrypt:
+       str     lr,[sp,#-4]!            @ push lr
+       ldmia   r11!,{r4-r7}
+       eor     r0,r0,r4
+       ldr     r12,[r11,#240-16]
+       eor     r1,r1,r5
+       eor     r2,r2,r6
+       eor     r3,r3,r7
+       sub     r12,r12,#1
+       mov     lr,#255
+
+       and     r7,lr,r0
+       and     r8,lr,r0,lsr#8
+       and     r9,lr,r0,lsr#16
+       mov     r0,r0,lsr#24
+.Lenc_loop:
+       ldr     r4,[r10,r7,lsl#2]       @ Te3[s0>>0]
+       and     r7,lr,r1,lsr#16 @ i0
+       ldr     r5,[r10,r8,lsl#2]       @ Te2[s0>>8]
+       and     r8,lr,r1
+       ldr     r6,[r10,r9,lsl#2]       @ Te1[s0>>16]
+       and     r9,lr,r1,lsr#8
+       ldr     r0,[r10,r0,lsl#2]       @ Te0[s0>>24]
+       mov     r1,r1,lsr#24
+
+       ldr     r7,[r10,r7,lsl#2]       @ Te1[s1>>16]



Home | Main Index | Thread Index | Old Index