hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 

Pull more crypto fixes from Herbert Xu:
 "This fixes a couple of issues in arm64/chacha that was introduced in
  5.0"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
  crypto: arm64/chacha - fix hchacha_block_neon() for big endian
  crypto: arm64/chacha - fix chacha_4block_xor_neon() for big endian
This commit is contained in:
Linus Torvalds 2019-03-02 08:32:02 -08:00
parent a215ce8f0e f86d17e9ef
commit fa3294c58c
1 changed files with 18 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
arch/arm64/crypto/chacha-neon-core.S
View File

@ -158,8 +158,8 @@ ENTRY(hchacha_block_neon)
mov w3, w2 mov w3, w2
bl chacha_permute bl chacha_permute
st1 {v0.16b}, [x1], #16 st1 {v0.4s}, [x1], #16
st1 {v3.16b}, [x1] st1 {v3.4s}, [x1]
ldp x29, x30, [sp], #16 ldp x29, x30, [sp], #16
ret ret
@ -532,6 +532,10 @@ ENTRY(chacha_4block_xor_neon)
add v3.4s, v3.4s, v19.4s add v3.4s, v3.4s, v19.4s
add a2, a2, w8 add a2, a2, w8
add a3, a3, w9 add a3, a3, w9
CPU_BE( rev a0, a0 )
CPU_BE( rev a1, a1 )
CPU_BE( rev a2, a2 )
CPU_BE( rev a3, a3 )
ld4r {v24.4s-v27.4s}, [x0], #16 ld4r {v24.4s-v27.4s}, [x0], #16
ld4r {v28.4s-v31.4s}, [x0] ld4r {v28.4s-v31.4s}, [x0]
@ -552,6 +556,10 @@ ENTRY(chacha_4block_xor_neon)
add v7.4s, v7.4s, v23.4s add v7.4s, v7.4s, v23.4s
add a6, a6, w8 add a6, a6, w8
add a7, a7, w9 add a7, a7, w9
CPU_BE( rev a4, a4 )
CPU_BE( rev a5, a5 )
CPU_BE( rev a6, a6 )
CPU_BE( rev a7, a7 )
// x8[0-3] += s2[0] // x8[0-3] += s2[0]
// x9[0-3] += s2[1] // x9[0-3] += s2[1]
@ -569,6 +577,10 @@ ENTRY(chacha_4block_xor_neon)
add v11.4s, v11.4s, v27.4s add v11.4s, v11.4s, v27.4s
add a10, a10, w8 add a10, a10, w8
add a11, a11, w9 add a11, a11, w9
CPU_BE( rev a8, a8 )
CPU_BE( rev a9, a9 )
CPU_BE( rev a10, a10 )
CPU_BE( rev a11, a11 )
// x12[0-3] += s3[0] // x12[0-3] += s3[0]
// x13[0-3] += s3[1] // x13[0-3] += s3[1]
@ -586,6 +598,10 @@ ENTRY(chacha_4block_xor_neon)
add v15.4s, v15.4s, v31.4s add v15.4s, v15.4s, v31.4s
add a14, a14, w8 add a14, a14, w8
add a15, a15, w9 add a15, a15, w9
CPU_BE( rev a12, a12 )
CPU_BE( rev a13, a13 )
CPU_BE( rev a14, a14 )
CPU_BE( rev a15, a15 )
// interleave 32-bit words in state n, n+1 // interleave 32-bit words in state n, n+1
ldp w6, w7, [x2], #64 ldp w6, w7, [x2], #64