crypto/internal/fips140/aes: actually use the VTBL instruction on arm64

Support for the VTBL instruction was added in CL 110015 - use it
directly, rather than using WORD encodings. Note that one of the
WORD encodings does not actually match the instruction in the
comment - use the instruction that matches the existing encoding
instead.

Change-Id: I1933162f8144a6b86b38e8b550d36907131b1dd4
Reviewed-on: https://go-review.googlesource.com/c/go/+/666795
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: David Chase <drchase@google.com>
Reviewed-by: Filippo Valsorda <filippo@golang.org>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

diff --git a/src/crypto/internal/fips140/aes/aes_arm64.s b/src/crypto/internal/fips140/aes/aes_arm64.s
index 192d0df8965ba9db97a95870941f0430586d19c9..1e885595404ed374962a7a8ca4d1470293c5e7af 100644 (file)
--- a/src/crypto/internal/fips140/aes/aes_arm64.s
+++ b/src/crypto/internal/fips140/aes/aes_arm64.s
@@ -134,7 +134,7 @@ TEXT ·expandKeyAsm(SB),NOSPLIT,$0
        MOVW    $0x1b, R14
 ks128Loop:
                VMOV    R7, V2.S[0]
-               WORD    $0x4E030042       // TBL V3.B16, [V2.B16], V2.B16
+               VTBL    V3.B16, [V2.B16], V2.B16
                AESE    V0.B16, V2.B16    // Use AES to compute the SBOX
                EORW    R13, R4
                LSLW    $1, R13           // Compute next Rcon
@@ -180,7 +180,7 @@ ks192:
 ks192Loop:
                STPW.P  (R6, R7), 8(R10)
                VMOV    R7, V2.S[0]
-               WORD    $0x4E030042 //TBL       V3.B16, [V2.B16], V2.B16
+               VTBL    V3.B16, [V2.B16], V2.B16
                AESE    V0.B16, V2.B16
                EORW    R13, R2
                LSLW    $1, R13
@@ -233,7 +233,7 @@ ks256Loop:
                STPW.P  (R4, R5), 8(R10)
                STPW.P  (R6, R7), 8(R10)
                VMOV    R7, V2.S[0]
-               WORD    $0x4E030042 //TBL       V3.B16, [V2.B16], V2.B16
+               VTBL    V3.B16, [V2.B16], V2.B16
                AESE    V0.B16, V2.B16
                EORW    R13, R0
                LSLW    $1, R13
@@ -244,7 +244,7 @@ ks256Loop:
                EORW    R1, R2
                EORW    R2, R3
                VMOV    R3, V2.S[0]
-               WORD    $0x4E040042 //TBL       V3.B16, [V2.B16], V2.B16
+               VTBL    V4.B16, [V2.B16], V2.B16
                AESE    V0.B16, V2.B16
                VMOV    V2.S[0], R9
                EORW    R9, R4