diff options
| author | Jason A. Donenfeld <Jason@zx2c4.com> | 2018-09-25 18:54:04 +0200 |
|---|---|---|
| committer | Jason A. Donenfeld <Jason@zx2c4.com> | 2018-09-25 19:35:40 +0200 |
| commit | b2eff7a7fd18afe5f15250ebda36b3e70b5172b1 (patch) | |
| tree | aae4bf69631affab4af49eb5fd66f5868f77050e /src/crypto/zinc | |
| parent | c2aa4b7e7e35974a8740f189c20b767e795bddbe (diff) | |
chacha20-arm,poly1305-arm: fix big-endian aarch64
Suggested-by: Andy Polyakov <appro@openssl.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Diffstat (limited to 'src/crypto/zinc')
| -rw-r--r-- | src/crypto/zinc/chacha20/chacha20-arm64.S | 18 | ||||
| -rw-r--r-- | src/crypto/zinc/poly1305/poly1305-arm64.S | 24 |
2 files changed, 21 insertions, 21 deletions
diff --git a/src/crypto/zinc/chacha20/chacha20-arm64.S b/src/crypto/zinc/chacha20/chacha20-arm64.S index 5037510..1ae11a5 100644 --- a/src/crypto/zinc/chacha20/chacha20-arm64.S +++ b/src/crypto/zinc/chacha20/chacha20-arm64.S @@ -34,7 +34,7 @@ ENTRY(chacha20_arm) ldp x24,x25,[x3] // load key ldp x26,x27,[x3,#16] ldp x28,x30,[x4] // load counter -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ ror x24,x24,#32 ror x25,x25,#32 ror x26,x26,#32 @@ -195,7 +195,7 @@ ENTRY(chacha20_arm) add x20,x20,x21,lsl#32 ldp x19,x21,[x1,#48] add x1,x1,#64 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 @@ -251,7 +251,7 @@ ENTRY(chacha20_arm) add x15,x15,x16,lsl#32 add x17,x17,x19,lsl#32 add x20,x20,x21,lsl#32 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 @@ -316,7 +316,7 @@ ENTRY(chacha20_neon) ldp x28,x30,[x4] // load counter ld1 {v27.4s},[x4] ld1 {v31.4s},[x5] -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev64 v24.4s,v24.4s ror x24,x24,#32 ror x25,x25,#32 @@ -614,7 +614,7 @@ ENTRY(chacha20_neon) add x20,x20,x21,lsl#32 ldp x19,x21,[x1,#48] add x1,x1,#64 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 @@ -693,7 +693,7 @@ ENTRY(chacha20_neon) add x20,x20,x21,lsl#32 ldp x19,x21,[x1,#48] add x1,x1,#64 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 @@ -795,7 +795,7 @@ ENTRY(chacha20_neon) ldp x28,x30,[x4] // load counter ld1 {v27.4s},[x4] ld1 {v31.4s},[x5] -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev64 v24.4s,v24.4s ror x24,x24,#32 ror x25,x25,#32 @@ -1308,7 +1308,7 @@ ENTRY(chacha20_neon) add x20,x20,x21,lsl#32 ldp x19,x21,[x1,#48] add x1,x1,#64 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 @@ -1822,7 +1822,7 @@ ENTRY(chacha20_neon) add x1,x1,#64 add v21.4s,v21.4s,v25.4s -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x5,x5 rev x7,x7 rev x9,x9 diff --git a/src/crypto/zinc/poly1305/poly1305-arm64.S b/src/crypto/zinc/poly1305/poly1305-arm64.S index 84a6544..5f4e7fb 100644 --- a/src/crypto/zinc/poly1305/poly1305-arm64.S +++ b/src/crypto/zinc/poly1305/poly1305-arm64.S @@ -21,7 +21,7 @@ ENTRY(poly1305_init_arm) ldp x7,x8,[x1] // load key mov x9,#0xfffffffc0fffffff movk x9,#0x0fff,lsl#48 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x7,x7 // flip bytes rev x8,x8 #endif @@ -49,7 +49,7 @@ ENTRY(poly1305_blocks_arm) .Loop: ldp x10,x11,[x1],#16 // load input sub x2,x2,#16 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x10,x10 rev x11,x11 #endif @@ -112,13 +112,13 @@ ENTRY(poly1305_emit_arm) csel x4,x4,x12,eq csel x5,x5,x13,eq -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ ror x10,x10,#32 // flip nonce words ror x11,x11,#32 #endif adds x4,x4,x10 // accumulate nonce adc x5,x5,x11 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x4,x4 // flip output bytes rev x5,x5 #endif @@ -232,7 +232,7 @@ ENTRY(poly1305_blocks_neon) adcs x5,x5,xzr adc x6,x6,xzr -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x12,x12 rev x13,x13 #endif @@ -278,7 +278,7 @@ ENTRY(poly1305_blocks_neon) ldp x12,x13,[x1],#16 // load input sub x2,x2,#16 add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x12,x12 rev x13,x13 #endif @@ -363,7 +363,7 @@ ENTRY(poly1305_blocks_neon) lsl x3,x3,#24 add x15,x0,#48 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x8,x8 rev x12,x12 rev x9,x9 @@ -399,7 +399,7 @@ ENTRY(poly1305_blocks_neon) ld1 {v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64 ld1 {v8.4s},[x15] -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x8,x8 rev x12,x12 rev x9,x9 @@ -460,7 +460,7 @@ ENTRY(poly1305_blocks_neon) umull v20.2d,v14.2s,v1.s[2] ldp x9,x13,[x16],#48 umull v19.2d,v14.2s,v0.s[2] -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x8,x8 rev x12,x12 rev x9,x9 @@ -525,7 +525,7 @@ ENTRY(poly1305_blocks_neon) umlal v23.2d,v11.2s,v3.s[0] umlal v20.2d,v11.2s,v8.s[0] umlal v21.2d,v11.2s,v0.s[0] -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x8,x8 rev x12,x12 rev x9,x9 @@ -803,13 +803,13 @@ ENTRY(poly1305_emit_neon) csel x4,x4,x12,eq csel x5,x5,x13,eq -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ ror x10,x10,#32 // flip nonce words ror x11,x11,#32 #endif adds x4,x4,x10 // accumulate nonce adc x5,x5,x11 -#ifdef __ARMEB__ +#ifdef __AARCH64EB__ rev x4,x4 // flip output bytes rev x5,x5 #endif |