diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 00:31:29 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 00:31:29 +0300 |
commit | 0f1d6dfe03ca4e36132221b918499c6f0b0f048d (patch) | |
tree | 0de8e9330610190a23e173ca7d7f3fb74a517aa2 /arch/arm64/crypto/aes-neon.S | |
parent | d05c5f7ba164aed3db02fb188c26d0dd94f5455b (diff) | |
parent | 04b46fbdea5e31ffd745a34fa61269a69ba9f47a (diff) | |
download | linux-0f1d6dfe03ca4e36132221b918499c6f0b0f048d.tar.xz |
Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
Pull crypto updates from Herbert Xu:
"Here is the crypto update for 4.10:
API:
- add skcipher walk interface
- add asynchronous compression (acomp) interface
- fix algif_aed AIO handling of zero buffer
Algorithms:
- fix unaligned access in poly1305
- fix DRBG output to large buffers
Drivers:
- add support for iMX6UL to caam
- fix givenc descriptors (used by IPsec) in caam
- accelerated SHA256/SHA512 for ARM64 from OpenSSL
- add SSE CRCT10DIF and CRC32 to ARM/ARM64
- add AEAD support to Chelsio chcr
- add Armada 8K support to omap-rng"
* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (148 commits)
crypto: testmgr - fix overlap in chunked tests again
crypto: arm/crc32 - accelerated support based on x86 SSE implementation
crypto: arm64/crc32 - accelerated support based on x86 SSE implementation
crypto: arm/crct10dif - port x86 SSE implementation to ARM
crypto: arm64/crct10dif - port x86 SSE implementation to arm64
crypto: testmgr - add/enhance test cases for CRC-T10DIF
crypto: testmgr - avoid overlap in chunked tests
crypto: chcr - checking for IS_ERR() instead of NULL
crypto: caam - check caam_emi_slow instead of re-lookup platform
crypto: algif_aead - fix AIO handling of zero buffer
crypto: aes-ce - Make aes_simd_algs static
crypto: algif_skcipher - set error code when kcalloc fails
crypto: caam - make aamalg_desc a proper module
crypto: caam - pass key buffers with typesafe pointers
crypto: arm64/aes-ce-ccm - Fix AEAD decryption length
MAINTAINERS: add crypto headers to crypto entry
crypt: doc - remove misleading mention of async API
crypto: doc - fix header file name
crypto: api - fix comment typo
crypto: skcipher - Add separate walker for AEAD decryption
..
Diffstat (limited to 'arch/arm64/crypto/aes-neon.S')
-rw-r--r-- | arch/arm64/crypto/aes-neon.S | 25 |
1 files changed, 15 insertions, 10 deletions
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S index b93170e1cc93..85f07ead7c5c 100644 --- a/arch/arm64/crypto/aes-neon.S +++ b/arch/arm64/crypto/aes-neon.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> #define AES_ENTRY(func) ENTRY(neon_ ## func) #define AES_ENDPROC(func) ENDPROC(neon_ ## func) @@ -83,13 +84,13 @@ .endm .macro do_block, enc, in, rounds, rk, rkp, i - ld1 {v15.16b}, [\rk] + ld1 {v15.4s}, [\rk] add \rkp, \rk, #16 mov \i, \rounds 1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */ tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */ sub_bytes \in - ld1 {v15.16b}, [\rkp], #16 + ld1 {v15.4s}, [\rkp], #16 subs \i, \i, #1 beq 2222f .if \enc == 1 @@ -229,7 +230,7 @@ .endm .macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i - ld1 {v15.16b}, [\rk] + ld1 {v15.4s}, [\rk] add \rkp, \rk, #16 mov \i, \rounds 1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ @@ -237,7 +238,7 @@ sub_bytes_2x \in0, \in1 tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */ - ld1 {v15.16b}, [\rkp], #16 + ld1 {v15.4s}, [\rkp], #16 subs \i, \i, #1 beq 2222f .if \enc == 1 @@ -254,7 +255,7 @@ .endm .macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i - ld1 {v15.16b}, [\rk] + ld1 {v15.4s}, [\rk] add \rkp, \rk, #16 mov \i, \rounds 1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ @@ -266,7 +267,7 @@ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */ tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */ tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */ - ld1 {v15.16b}, [\rkp], #16 + ld1 {v15.4s}, [\rkp], #16 subs \i, \i, #1 beq 2222f .if \enc == 1 @@ -306,12 +307,16 @@ .text .align 4 .LForward_ShiftRows: - .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3 - .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb +CPU_LE( .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3 ) +CPU_LE( .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb ) +CPU_BE( .byte 0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8 ) +CPU_BE( .byte 0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0 ) .LReverse_ShiftRows: - .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb - .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3 +CPU_LE( .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb ) +CPU_LE( .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3 ) +CPU_BE( .byte 0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8 ) +CPU_BE( .byte 0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0 ) .LForward_Sbox: .byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5 |