From: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Date: Thu, 26 Jan 2023 13:58:30 +0000 (+0100)
Subject: riscv: sha256: Provide a Zvknha-based implementation
X-Git-Tag: openssl-3.3.0-alpha1~755
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=17073066520dbbf1ef3ce4856c570d61e9548083;p=thirdparty%2Fopenssl.git

riscv: sha256: Provide a Zvknha-based implementation

The upcoming RISC-V vector crypto extensions feature
a Zvknha extension, that provides sha256-specific instructions.
This patch provides an implementation that utilizes this
extension if available.

Tested on QEMU and no regressions observed.

Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>

Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Hugo Landau <hlandau@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/21923)
---

diff --git a/crypto/perlasm/riscv.pm b/crypto/perlasm/riscv.pm
index 057109f18b6..661b5ad80de 100644
--- a/crypto/perlasm/riscv.pm
+++ b/crypto/perlasm/riscv.pm
@@ -281,6 +281,22 @@ sub rev8 {
 
 # Vector instructions
 
+sub vadd_vv {
+    # vadd.vv vd, vs2, vs1
+    my $template = 0b0000001_00000_00000_000_00000_1010111;
+    my $vd = read_vreg shift;
+    my $vs2 = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    return ".word ".($template | ($vs2 << 20) | ($vs1 << 15) | ($vd << 7));
+}
+
+sub vid_v {
+    # vid.v vd
+    my $template = 0b0101001_00000_10001_010_00000_1010111;
+    my $vd = read_vreg shift;
+    return ".word ".($template | ($vd << 7));
+}
+
 sub vle32_v {
     # vle32.v vd, (rs1)
     my $template = 0b0000001_00000_00000_110_00000_0000111;
@@ -297,6 +313,15 @@ sub vle64_v {
     return ".word ".($template | ($rs1 << 15) | ($vd << 7));
 }
 
+sub vlse32_v {
+    # vlse32.v vd, (rs1), rs2
+    my $template = 0b0000101_00000_00000_110_00000_0000111;
+    my $vd = read_vreg shift;
+    my $rs1 = read_reg shift;
+    my $rs2 = read_reg shift;
+    return ".word ".($template | ($rs2 << 20) | ($rs1 << 15) | ($vd << 7));
+}
+
 sub vlse64_v {
     # vlse64.v vd, (rs1), rs2
     my $template = 0b0000101_00000_00000_111_00000_0000111;
@@ -315,6 +340,24 @@ sub vmerge_vim {
     return ".word ".($template | ($vs2 << 20) | ($imm << 15) | ($vd << 7));
 }
 
+sub vmerge_vvm {
+    # vmerge.vvm vd vs2 vs1
+    my $template = 0b0101110_00000_00000_000_00000_1010111;
+    my $vd = read_vreg shift;
+    my $vs2 = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    return ".word ".($template | ($vs2 << 20) | ($vs1 <<   15) | ($vd << 7))
+}
+
+sub vmseq_vi {
+    # vmseq vd vs1, imm
+    my $template = 0b0110001_00000_00000_011_00000_1010111;
+    my $vd = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    my $imm = shift;
+    return ".word ".($template | ($vs1 << 20) | ($imm <<   15) | ($vd << 7))
+}
+
 sub vmv_v_i {
     # vmv.v.i vd, imm
     my $template = 0b0101111_00000_00000_011_00000_1010111;
@@ -411,6 +454,15 @@ sub vsrl_vx {
     return ".word ".($template | ($vs2 << 20) | ($rs1 << 15) | ($vd << 7));
 }
 
+sub vsse32_v {
+    # vse32.v vs3, (rs1), rs2
+    my $template = 0b0000101_00000_00000_110_00000_0100111;
+    my $vs3 = read_vreg shift;
+    my $rs1 = read_reg shift;
+    my $rs2 = read_reg shift;
+    return ".word ".($template | ($rs2 << 20) | ($rs1 << 15) | ($vs3 << 7));
+}
+
 sub vsse64_v {
     # vsse64.v vs3, (rs1), rs2
     my $template = 0b0000101_00000_00000_111_00000_0100111;
@@ -558,4 +610,33 @@ sub vaesz_vs {
     return ".word ".($template | ($vs2 << 20) | ($vd << 7));
 }
 
+## Zvknha instructions
+
+sub vsha2ms_vv {
+    # vsha2ms.vv vd, vs2, vs1
+    my $template = 0b1011011_00000_00000_010_00000_1110111;
+    my $vd = read_vreg shift;
+    my $vs2 = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    return ".word ".($template | ($vs2 << 20)| ($vs1 << 15 )| ($vd << 7));
+}
+
+sub vsha2ch_vv {
+    # vsha2ch.vv vd, vs2, vs1
+    my $template = 0b101110_10000_00000_001_00000_01110111;
+    my $vd = read_vreg shift;
+    my $vs2 = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    return ".word ".($template | ($vs2 << 20)| ($vs1 << 15 )| ($vd << 7));
+}
+
+sub vsha2cl_vv {
+    # vsha2cl.vv vd, vs2, vs1
+    my $template = 0b101111_10000_00000_001_00000_01110111;
+    my $vd = read_vreg shift;
+    my $vs2 = read_vreg shift;
+    my $vs1 = read_vreg shift;
+    return ".word ".($template | ($vs2 << 20)| ($vs1 << 15 )| ($vd << 7));
+}
+
 1;
diff --git a/crypto/sha/asm/sha256-riscv64-zvbb-zvknha.pl b/crypto/sha/asm/sha256-riscv64-zvbb-zvknha.pl
new file mode 100644
index 00000000000..f98f39ce15f
--- /dev/null
+++ b/crypto/sha/asm/sha256-riscv64-zvbb-zvknha.pl
@@ -0,0 +1,312 @@
+#! /usr/bin/env perl
+# This file is dual-licensed, meaning that you can use it under your
+# choice of either of the following two licenses:
+#
+# Copyright 2023 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the Apache License 2.0 (the "License"). You can obtain
+# a copy in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+#
+# or
+#
+# Copyright (c) 2023, Christoph Müllner <christoph.muellner@vrull.eu>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+# The generated code of this file depends on the following RISC-V extensions:
+# - RV64I
+# - RISC-V vector ('V') with VLEN >= 128
+# - Vector Bit-manipulation used in Cryptography ('Zvbb')
+# - Vector SHA-2 Secure Hash ('Zvknha')
+
+use strict;
+use warnings;
+
+use FindBin qw($Bin);
+use lib "$Bin";
+use lib "$Bin/../../perlasm";
+use riscv;
+
+# $output is the last argument if it looks like a file (it has an extension)
+# $flavour is the first argument if it doesn't look like a file
+my $output = $#ARGV >= 0 && $ARGV[$#ARGV] =~ m|\.\w+$| ? pop : undef;
+my $flavour = $#ARGV >= 0 && $ARGV[0] !~ m|\.| ? shift : undef;
+
+$output and open STDOUT,">$output";
+
+my $code=<<___;
+.text
+___
+
+my ($V0, $V10, $V11, $V12, $V13, $V14, $V15, $V16, $V17) = ("v0", "v10", "v11", "v12", "v13", "v14","v15", "v16", "v17");
+my ($V26, $V27) = ("v26", "v27");
+
+my $K256 = "K256";
+
+# Function arguments
+my ($H, $INP, $LEN, $KT, $STRIDE) = ("a0", "a1", "a2", "a3", "t3");
+
+################################################################################
+# void sha256_block_data_order_zvbb_zvknha(void *c, const void *p, size_t len)
+$code .= <<___;
+.p2align 2
+.globl sha256_block_data_order_zvbb_zvknha
+.type   sha256_block_data_order_zvbb_zvknha,\@function
+sha256_block_data_order_zvbb_zvknha:
+    @{[vsetivli__x0_4_e32_m1_tu_mu]}
+
+    # H is stored as {a,b,c,d},{e,f,g,h}, but we need {f,e,b,a},{h,g,d,c}
+    # We achieve this by reading with a negative stride followed by
+    # element sliding.
+    li $STRIDE, -4
+    addi $H, $H, 12
+    @{[vlse32_v $V16, $H, $STRIDE]} # {d,c,b,a}
+    addi $H, $H, 16
+    @{[vlse32_v $V17, $H, $STRIDE]} # {h,g,f,e}
+    # Keep H advanced by 12
+    addi $H, $H, -16
+
+    @{[vmv_v_v $V27, $V16]} # {d,c,b,a}
+    @{[vslidedown_vi $V26, $V16, 2]} # {b,a,0,0}
+    @{[vslidedown_vi $V16, $V17, 2]} # {f,e,0,0}
+    @{[vslideup_vi $V16, $V26, 2]} # {f,e,b,a}
+    @{[vslideup_vi $V17, $V27, 2]} # {h,g,d,c}
+
+    # Keep the old state as we need it later: H' = H+{a',b',c',...,h'}.
+    @{[vmv_v_v $V26, $V16]}
+    @{[vmv_v_v $V27, $V17]}
+
+L_round_loop:
+    la $KT, $K256 # Load round constants K256
+
+    # Load the 512-bits of the message block in v10-v13 and perform
+    # an endian swap on each 4 bytes element.
+    @{[vle32_v $V10, $INP]}
+    @{[vrev8_v $V10, $V10]}
+    add $INP, $INP, 16
+    @{[vle32_v $V11, $INP]}
+    @{[vrev8_v $V11, $V11]}
+    add $INP, $INP, 16
+    @{[vle32_v $V12, $INP]}
+    @{[vrev8_v $V12, $V12]}
+    add $INP, $INP, 16
+    @{[vle32_v $V13, $INP]}
+    @{[vrev8_v $V13, $V13]}
+    add $INP, $INP, 16
+
+    # Decrement length by 1
+    add $LEN, $LEN, -1
+
+    # Set v0 up for the vmerge that replaces the first word (idx==0)
+    @{[vid_v $V0]}
+    @{[vmseq_vi $V0, $V0, 0x0]}    # v0.mask[i] = (i == 0 ? 1 : 0)
+
+    # Quad-round 0 (+0, Wt from oldest to newest in v10->v11->v12->v13)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V10]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V12, $V11, $V0]}
+    @{[vsha2ms_vv $V10, $V14, $V13]}  # Generate W[19:16]
+
+    # Quad-round 1 (+1, v11->v12->v13->v10)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V11]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V13, $V12, $V0]}
+    @{[vsha2ms_vv $V11, $V14, $V10]}  # Generate W[23:20]
+
+    # Quad-round 2 (+2, v12->v13->v10->v11)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V12]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V10, $V13, $V0]}
+    @{[vsha2ms_vv $V12, $V14, $V11]}  # Generate W[27:24]
+
+    # Quad-round 3 (+3, v13->v10->v11->v12)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V13]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V11, $V10, $V0]}
+    @{[vsha2ms_vv $V13, $V14, $V12]}  # Generate W[31:28]
+
+    # Quad-round 4 (+0, v10->v11->v12->v13)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V10]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V12, $V11, $V0]}
+    @{[vsha2ms_vv $V10, $V14, $V13]}  # Generate W[35:32]
+
+    # Quad-round 5 (+1, v11->v12->v13->v10)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V11]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V13, $V12, $V0]}
+    @{[vsha2ms_vv $V11, $V14, $V10]}  # Generate W[39:36]
+
+    # Quad-round 6 (+2, v12->v13->v10->v11)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V12]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V10, $V13, $V0]}
+    @{[vsha2ms_vv $V12, $V14, $V11]}  # Generate W[43:40]
+
+    # Quad-round 7 (+3, v13->v10->v11->v12)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V13]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V11, $V10, $V0]}
+    @{[vsha2ms_vv $V13, $V14, $V12]}  # Generate W[47:44]
+
+    # Quad-round 8 (+0, v10->v11->v12->v13)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V10]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V12, $V11, $V0]}
+    @{[vsha2ms_vv $V10, $V14, $V13]}  # Generate W[51:48]
+
+    # Quad-round 9 (+1, v11->v12->v13->v10)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V11]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V13, $V12, $V0]}
+    @{[vsha2ms_vv $V11, $V14, $V10]}  # Generate W[55:52]
+
+    # Quad-round 10 (+2, v12->v13->v10->v11)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V12]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V10, $V13, $V0]}
+    @{[vsha2ms_vv $V12, $V14, $V11]}  # Generate W[59:56]
+
+    # Quad-round 11 (+3, v13->v10->v11->v12)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V13]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+    @{[vmerge_vvm $V14, $V11, $V10, $V0]}
+    @{[vsha2ms_vv $V13, $V14, $V12]}  # Generate W[63:60]
+
+    # Quad-round 12 (+0, v10->v11->v12->v13)
+    # Note that we stop generating new message schedule words (Wt, v10-13)
+    # as we already generated all the words we end up consuming (i.e., W[63:60]).
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V10]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+
+    # Quad-round 13 (+1, v11->v12->v13->v10)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V11]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+
+    # Quad-round 14 (+2, v12->v13->v10->v11)
+    @{[vle32_v $V15, $KT]}
+    addi $KT, $KT, 16
+    @{[vadd_vv $V14, $V15, $V12]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+
+    # Quad-round 15 (+3, v13->v10->v11->v12)
+    @{[vle32_v $V15, $KT]}
+    # No kt increment needed.
+    @{[vadd_vv $V14, $V15, $V13]}
+    @{[vsha2cl_vv $V17, $V16, $V14]}
+    @{[vsha2ch_vv $V16, $V17, $V14]}
+
+    # H' = H+{a',b',c',...,h'}
+    @{[vadd_vv $V16, $V26, $V16]}
+    @{[vadd_vv $V17, $V27, $V17]}
+    @{[vmv_v_v $V26, $V16]}
+    @{[vmv_v_v $V27, $V17]}
+    bnez $LEN, L_round_loop
+
+    # v26 = v16 = {f,e,b,a}
+    # v27 = v17 = {h,g,d,c}
+    # Let's do the opposit transformation like on entry.
+
+    @{[vslideup_vi $V17, $V16, 2]} # {h,g,f,e}
+
+    @{[vslidedown_vi $V16, $V27, 2]} # {d,c,0,0}
+    @{[vslidedown_vi $V26, $V26, 2]} # {b,a,0,0}
+    @{[vslideup_vi $V16, $V26, 2]} # {d,c,b,a}
+
+    # H is already advanced by 12
+    @{[vsse32_v $V16, $H, $STRIDE]} # {a,b,c,d}
+    addi $H, $H, 16
+    @{[vsse32_v $V17, $H, $STRIDE]} # {e,f,g,h}
+
+    ret
+.size sha256_block_data_order_zvbb_zvknha,.-sha256_block_data_order_zvbb_zvknha
+
+.p2align 2
+.type $K256,\@object
+$K256:
+    .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+    .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+    .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+    .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+    .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+    .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+    .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+    .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+    .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+    .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+    .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+    .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+    .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+    .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+    .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+    .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+.size $K256,.-$K256
+___
+
+print $code;
+
+close STDOUT or die "error closing STDOUT: $!";
diff --git a/crypto/sha/build.info b/crypto/sha/build.info
index 556a658d8b5..4eb9a312129 100644
--- a/crypto/sha/build.info
+++ b/crypto/sha/build.info
@@ -46,6 +46,9 @@ IF[{- !$disabled{asm} -}]
   $SHA1ASM_c64xplus=sha1-c64xplus.s sha256-c64xplus.s sha512-c64xplus.s
   $SHA1DEF_c64xplus=SHA1_ASM SHA256_ASM SHA512_ASM
 
+  $SHA1ASM_riscv64=sha_riscv.c sha256-riscv64-zvbb-zvknha.S
+  $SHA1DEF_riscv64=SHA256_ASM INCLUDE_C_SHA256
+
   # Now that we have defined all the arch specific variables, use the
   # appropriate one, and define the appropriate macros
   IF[$SHA1ASM_{- $target{asm_arch} -}]
@@ -168,6 +171,8 @@ GENERATE[sha256-c64xplus.S]=asm/sha256-c64xplus.pl
 GENERATE[sha512-c64xplus.S]=asm/sha512-c64xplus.pl
 GENERATE[keccak1600-c64x.S]=asm/keccak1600-c64x.pl
 
+GENERATE[sha256-riscv64-zvbb-zvknha.S]=asm/sha256-riscv64-zvbb-zvknha.pl
+
 # These are not yet used
 GENERATE[keccak1600-avx2.S]=asm/keccak1600-avx2.pl
 GENERATE[keccak1600-avx512.S]=asm/keccak1600-avx512.pl
diff --git a/crypto/sha/sha_riscv.c b/crypto/sha/sha_riscv.c
new file mode 100644
index 00000000000..04a6752f4cc
--- /dev/null
+++ b/crypto/sha/sha_riscv.c
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2023 The OpenSSL Project Authors. All Rights Reserved.
+ *
+ * Licensed under the Apache License 2.0 (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ */
+
+#include <stdlib.h>
+#include <string.h>
+
+#include <openssl/opensslconf.h>
+#include <openssl/sha.h>
+#include "crypto/riscv_arch.h"
+
+void sha256_block_data_order_zvbb_zvknha(void *ctx, const void *in, size_t num);
+void sha256_block_data_order_c(void *ctx, const void *in, size_t num);
+void sha256_block_data_order(SHA256_CTX *ctx, const void *in, size_t num);
+
+void sha256_block_data_order(SHA256_CTX *ctx, const void *in, size_t num)
+{
+    if (RISCV_HAS_ZVBB_AND_ZVKNHA() && riscv_vlen() >= 128) {
+        sha256_block_data_order_zvbb_zvknha(ctx, in, num);
+    } else {
+        sha256_block_data_order_c(ctx, in, num);
+    }
+}
diff --git a/include/crypto/riscv_arch.def b/include/crypto/riscv_arch.def
index d727ef7824c..6462d30156d 100644
--- a/include/crypto/riscv_arch.def
+++ b/include/crypto/riscv_arch.def
@@ -37,6 +37,7 @@ RISCV_DEFINE_CAP(ZVBB, 0, 15)
 RISCV_DEFINE_CAP(ZVBC, 0, 16)
 RISCV_DEFINE_CAP(ZVKG, 0, 17)
 RISCV_DEFINE_CAP(ZVKNED, 0, 18)
+RISCV_DEFINE_CAP(ZVKNHA, 0, 19)
 
 /*
  * In the future ...
diff --git a/include/crypto/riscv_arch.h b/include/crypto/riscv_arch.h
index 8bd281ad807..54a790d5a6c 100644
--- a/include/crypto/riscv_arch.h
+++ b/include/crypto/riscv_arch.h
@@ -60,6 +60,7 @@ static const size_t kRISCVNumCaps =
 #define RISCV_HAS_ZBB_AND_ZBC() (RISCV_HAS_ZBB() && RISCV_HAS_ZBC())
 #define RISCV_HAS_ZBKB_AND_ZKND_AND_ZKNE() (RISCV_HAS_ZBKB() && RISCV_HAS_ZKND() && RISCV_HAS_ZKNE())
 #define RISCV_HAS_ZKND_AND_ZKNE() (RISCV_HAS_ZKND() && RISCV_HAS_ZKNE())
+#define RISCV_HAS_ZVBB_AND_ZVKNHA() (RISCV_HAS_ZVBB() && RISCV_HAS_ZVKNHA())
 
 /*
  * Get the size of a vector register in bits (VLEN).