/* SPDX-License-Identifier: BSD-2-Clause */ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * * Copyright (C) 2014 - 2017 Linaro Ltd. */ #include #include #define CPU_LE(x...) x SHASH .req q0 T1 .req q1 XL .req q2 XM .req q3 XH .req q4 IN1 .req q4 SHASH_L .req d0 SHASH_H .req d1 T1_L .req d2 T1_H .req d3 XL_L .req d4 XL_H .req d5 XM_L .req d6 XM_H .req d7 XH_L .req d8 t0l .req d10 t0h .req d11 t1l .req d12 t1h .req d13 t2l .req d14 t2h .req d15 t3l .req d16 t3h .req d17 t4l .req d18 t4h .req d19 t0q .req q5 t1q .req q6 t2q .req q7 t3q .req q8 t4q .req q9 T2 .req q9 s1l .req d20 s1h .req d21 s2l .req d22 s2h .req d23 s3l .req d24 s3h .req d25 s4l .req d26 s4h .req d27 MASK .req d28 SHASH2_p8 .req d28 k16 .req d29 k32 .req d30 k48 .req d31 SHASH2_p64 .req d31 .text .fpu crypto-neon-fp-armv8 .macro __pmull_p64, rd, rn, rm, b1, b2, b3, b4 vmull.p64 \rd, \rn, \rm .endm /* * This implementation of 64x64 -> 128 bit polynomial multiplication * using vmull.p8 instructions (8x8 -> 16) is taken from the paper * "Fast Software Polynomial Multiplication on ARM Processors Using * the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and * Ricardo Dahab (https://hal.inria.fr/hal-01506572) * * It has been slightly tweaked for in-order performance, and to allow * 'rq' to overlap with 'ad' or 'bd'. */ .macro __pmull_p8, rq, ad, bd, b1=t4l, b2=t3l, b3=t4l, b4=t3l vext.8 t0l, \ad, \ad, #1 @ A1 .ifc \b1, t4l vext.8 t4l, \bd, \bd, #1 @ B1 .endif vmull.p8 t0q, t0l, \bd @ F = A1*B vext.8 t1l, \ad, \ad, #2 @ A2 vmull.p8 t4q, \ad, \b1 @ E = A*B1 .ifc \b2, t3l vext.8 t3l, \bd, \bd, #2 @ B2 .endif vmull.p8 t1q, t1l, \bd @ H = A2*B vext.8 t2l, \ad, \ad, #3 @ A3 vmull.p8 t3q, \ad, \b2 @ G = A*B2 veor t0q, t0q, t4q @ L = E + F .ifc \b3, t4l vext.8 t4l, \bd, \bd, #3 @ B3 .endif vmull.p8 t2q, t2l, \bd @ J = A3*B veor t0l, t0l, t0h @ t0 = (L) (P0 + P1) << 8 veor t1q, t1q, t3q @ M = G + H .ifc \b4, t3l vext.8 t3l, \bd, \bd, #4 @ B4 .endif vmull.p8 t4q, \ad, \b3 @ I = A*B3 veor t1l, t1l, t1h @ t1 = (M) (P2 + P3) << 16 vmull.p8 t3q, \ad, \b4 @ K = A*B4 vand t0h, t0h, k48 vand t1h, t1h, k32 veor t2q, t2q, t4q @ N = I + J veor t0l, t0l, t0h veor t1l, t1l, t1h veor t2l, t2l, t2h @ t2 = (N) (P4 + P5) << 24 vand t2h, t2h, k16 veor t3l, t3l, t3h @ t3 = (K) (P6 + P7) << 32 vmov.i64 t3h, #0 vext.8 t0q, t0q, t0q, #15 veor t2l, t2l, t2h vext.8 t1q, t1q, t1q, #14 vmull.p8 \rq, \ad, \bd @ D = A*B vext.8 t2q, t2q, t2q, #13 vext.8 t3q, t3q, t3q, #12 veor t0q, t0q, t1q veor t2q, t2q, t3q veor \rq, \rq, t0q veor \rq, \rq, t2q .endm // // PMULL (64x64->128) based reduction for CPUs that can do // it in a single instruction. // .macro __pmull_reduce_p64 vmull.p64 T1, XL_L, MASK veor XH_L, XH_L, XM_H vext.8 T1, T1, T1, #8 veor XL_H, XL_H, XM_L veor T1, T1, XL vmull.p64 XL, T1_H, MASK .endm // // Alternative reduction for CPUs that lack support for the // 64x64->128 PMULL instruction // .macro __pmull_reduce_p8 veor XL_H, XL_H, XM_L veor XH_L, XH_L, XM_H vshl.i64 T1, XL, #57 vshl.i64 T2, XL, #62 veor T1, T1, T2 vshl.i64 T2, XL, #63 veor T1, T1, T2 veor XL_H, XL_H, T1_L veor XH_L, XH_L, T1_H vshr.u64 T1, XL, #1 veor XH, XH, XL veor XL, XL, T1 vshr.u64 T1, T1, #6 vshr.u64 XL, XL, #1 .endm .macro ghash_update, pn vld1.64 {XL}, [r1] /* do the head block first, if supplied */ ldr ip, [sp] teq ip, #0 beq 0f vld1.8 {T1}, [ip] teq r0, #0 b 1f 0: vld1.8 {T1}, [r2]! subs r0, r0, #1 1: /* multiply XL by SHASH in GF(2^128) */ #ifndef CONFIG_CPU_BIG_ENDIAN vrev64.8 T1, T1 #endif vext.8 IN1, T1, T1, #8 veor T1_L, T1_L, XL_H veor XL, XL, IN1 __pmull_\pn XH, XL_H, SHASH_H, s1h, s2h, s3h, s4h @ a1 * b1 veor T1, T1, XL __pmull_\pn XL, XL_L, SHASH_L, s1l, s2l, s3l, s4l @ a0 * b0 __pmull_\pn XM, T1_L, SHASH2_\pn @ (a1+a0)(b1+b0) veor T1, XL, XH veor XM, XM, T1 __pmull_reduce_\pn veor T1, T1, XH veor XL, XL, T1 bne 0b vst1.64 {XL}, [r1] bx lr .endm /* * void pmull_ghash_update(int blocks, u64 dg[], const char *src, * struct ghash_key const *k, const char *head) */ FUNC pmull_ghash_update_p64 , : vld1.64 {SHASH}, [r3] veor SHASH2_p64, SHASH_L, SHASH_H vmov.i8 MASK, #0xe1 vshl.u64 MASK, MASK, #57 ghash_update p64 END_FUNC pmull_ghash_update_p64 FUNC pmull_ghash_update_p8 , : vld1.64 {SHASH}, [r3] veor SHASH2_p8, SHASH_L, SHASH_H vext.8 s1l, SHASH_L, SHASH_L, #1 vext.8 s2l, SHASH_L, SHASH_L, #2 vext.8 s3l, SHASH_L, SHASH_L, #3 vext.8 s4l, SHASH_L, SHASH_L, #4 vext.8 s1h, SHASH_H, SHASH_H, #1 vext.8 s2h, SHASH_H, SHASH_H, #2 vext.8 s3h, SHASH_H, SHASH_H, #3 vext.8 s4h, SHASH_H, SHASH_H, #4 vmov.i64 k16, #0xffff vmov.i64 k32, #0xffffffff vmov.i64 k48, #0xffffffffffff ghash_update p8 END_FUNC pmull_ghash_update_p8