From nobody Mon Nov 16 06:33:20 2026 X-Original-To: dev-commits-src-all@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4jSdNK0ZLRz71JG7 for ; Mon, 16 Nov 2026 06:33:21 +0000 (UTC) (envelope-from git@FreeBSD.org) Received: from mxrelay.nyi.freebsd.org (mxrelay.nyi.freebsd.org [IPv6:2610:1c1:1:606c::19:3]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange x25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id 4jSdNJ5fK3z3N8f for ; Mon, 16 Nov 2026 06:33:20 +0000 (UTC) (envelope-from git@FreeBSD.org) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=freebsd.org; s=dkim; t=1794810800; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=DR1XmIQ8LhCC3uCjGXi5nWHOFdUivJ9q4CmCiMsVyi8=; b=XDdy/qieq6JpGY6Cxbt7GadG2mo9jqvkZYQUxCBjImRDtkHEcdDdgw1I5qH3A0ErdEQKrn ZUoaurpFmIvZCxxiNWnXSXbCBESKlEai126j7DFnhhXL5tk+lG5VnJH9c3+m8VKQ+3Oz+N XKB/tIRPNLIFZ5GDGZ6Xm5TwCLp4bHOXujGSNr30d5Rna6xEWFcYSGeZJAyAetZbuekuWB nF/a+AcUUMJ4BE4FpefoN7HF6vgy0BEk8Xfw/fGgeZlfGdPVsxL/oJHEZgvZJ0ZlXA2OZi XE8fCa1fuil2NfUc0ZiqOaEfwKUVvuaTL7qNqZqMvjCWfNp20dyUs9+ECxrj6A== ARC-Seal: i=1; a=rsa-sha256; d=freebsd.org; s=dkim; cv=none; t=1794810800; b=xIgm0AjJ8rxGIzt6GMSeVCoaR74FipGnzOHhZfVW1FGDI2i4LXM7Rc705b7aqzIHt6Asvw 8RoqB3jJ34Lxej4H4RAB739+rImzl2c5iYw5OBzLA8TvG4GPwkDniAQWZS9knqCtrv/1kq VaWgxq4JwCzWSp1wGSW0dlI12q7AlOJ1EnbFDHjhJB+AHBX8QrUOncqvnftlgLOwU73IAb dq3SAZO6dG2JF6pjzVB5xMncNTEZtmKOe60kZPk8JL1iZ/7f1IdP96Vhh9cRMxVMMJnRv2 IvmKrMG2wm7MZtm6cd9dnvM4rya3Izg7dlcXRn2A0pgYKTlQ+hRoEPpFyou2ww== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=freebsd.org; s=dkim; t=1794810800; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=DR1XmIQ8LhCC3uCjGXi5nWHOFdUivJ9q4CmCiMsVyi8=; b=NTD8KdZv+Yatuu8aihmo80elRx3mRqFy+OwTMJJsCOVCJ8zWL2iByhGB+QwxBtJI7ResoE 3CmVcswpCALOtA2Jf0p2zi/O+qbG8xs95WbP4f9dD8eQfzg3h6sEYwugDH19W13bi6yMvD b9DT8K670VavZ/A6dEc+caPx/Irrfa4pODnyCSQHLQD5603zgFyA8JjVW3ZKSgcwocaXzU +SjLgY/k0VKSlyzT5LB2skIy2oN9NXdvX6KeSKogMf2IC+UW4iCw84WYt+H/gcAkSiZiAZ Ldos8d/AuQkq6r5fsVpAJr/IvnfLpUKRdTfb3m78V1CNjuZkkT9UlGl7e+4EPw== ARC-Authentication-Results: i=1; mx1.freebsd.org; none Received: from gitrepo.freebsd.org (gitrepo.freebsd.org [IPv6:2610:1c1:1:6068::e6a:5]) by mxrelay.nyi.freebsd.org (Postfix) with ESMTP id 4jSdNJ5Jrpzjjj for ; Mon, 16 Nov 2026 06:33:20 +0000 (UTC) (envelope-from git@FreeBSD.org) Received: from git (uid 1279) (envelope-from git@FreeBSD.org) id 12b2d by gitrepo.freebsd.org (DragonFly Mail Agent v0.13+ on gitrepo.freebsd.org); Mon, 16 Nov 2026 06:33:20 +0000 To: src-committers@FreeBSD.org, dev-commits-src-all@FreeBSD.org, dev-commits-src-branches@FreeBSD.org From: Gordon Tetlow Subject: git: 481e348fe751 - stable/15 - openssl: stop generating asm that nothing builds List-Archive: https://lists.freebsd.org/archives/dev-commits-src-all X-BeenThere: dev-commits-src-all@freebsd.org List-Id: Commit messages for all branches of the src repository List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-Git-Committer: gordon X-Git-Repository: src X-Git-Refname: refs/heads/stable/15 X-Git-Reftype: branch X-Git-Commit: 481e348fe751494a3449c3b96a31cd75492fceac Auto-Submitted: auto-generated Date: Mon, 16 Nov 2026 06:33:20 +0000 Message-Id: <6afaa3b0.12b2d.5b923683@gitrepo.freebsd.org> The branch stable/15 has been updated by gordon: URL: https://cgit.FreeBSD.org/src/commit/?id=481e348fe751494a3449c3b96a31cd75492fceac commit 481e348fe751494a3449c3b96a31cd75492fceac Author: Gordon Tetlow AuthorDate: 2026-11-08 19:17:00 +0000 Commit: Gordon Tetlow CommitDate: 2026-11-16 06:22:19 +0000 openssl: stop generating asm that nothing builds Makefile.asm generated eight perlasm outputs that neither libcrypto nor the kernel builds. Additionally, upstream does not build them for these architectures with FreeBSD's configuration: - aarch64: ecp_sm2p256-armv8, sm3-armv8, sm4-armv8, vpsm4-armv8 and vpsm4_ex-armv8. SM2, SM3 and SM4 are disabled (disable-sm2/sm3/sm4). - i386: cast-586 (upstream's x86 configuration uses the C CAST code) and rc5-586 (RC5 is disabled by default). - powerpc: aes-gcm-ppc. Upstream builds it only for 64-bit little-endian; libcrypto and ossl(4) use it only on powerpc64 and powerpc64le, whose copies stay. Remove them from Makefile.asm and delete the generated files, so the next vendor import does not regenerate them. If one of these algorithms is ever enabled, add its script back to Makefile.asm and run "make buildasm". Checked: no file outside crypto/openssl refers to any of them, and libcrypto's source lists did not include them. Built and checked via tinderbox build. Reviewed by: ngie Discussed with: jhb Event: FreeBSD Vendor Summit 2026 Differential Revision: https://reviews.freebsd.org/D61274 (cherry picked from commit ea623d9235e610de16f53990189163f12006f7c6) --- secure/lib/libcrypto/Makefile.asm | 22 +- sys/crypto/openssl/aarch64/ecp_sm2p256-armv8.S | 837 ---- sys/crypto/openssl/aarch64/sm3-armv8.S | 509 --- sys/crypto/openssl/aarch64/sm4-armv8.S | 1093 ------ sys/crypto/openssl/aarch64/vpsm4-armv8.S | 5021 ------------------------ sys/crypto/openssl/aarch64/vpsm4_ex-armv8.S | 4543 --------------------- sys/crypto/openssl/i386/cast-586.S | 2002 ---------- sys/crypto/openssl/i386/rc5-586.S | 1264 ------ sys/crypto/openssl/powerpc/aes-gcm-ppc.S | 988 ----- 9 files changed, 3 insertions(+), 16276 deletions(-) diff --git a/secure/lib/libcrypto/Makefile.asm b/secure/lib/libcrypto/Makefile.asm index 14465c414a61..1162aa7d1a1f 100644 --- a/secure/lib/libcrypto/Makefile.asm +++ b/secure/lib/libcrypto/Makefile.asm @@ -15,9 +15,7 @@ ${LCRYPTO_SRC}/crypto/md5/asm \ ${LCRYPTO_SRC}/crypto/modes/asm \ ${LCRYPTO_SRC}/crypto/poly1305/asm \ - ${LCRYPTO_SRC}/crypto/sha/asm \ - ${LCRYPTO_SRC}/crypto/sm3/asm \ - ${LCRYPTO_SRC}/crypto/sm4/asm + ${LCRYPTO_SRC}/crypto/sha/asm PERLPATH= -I${LCRYPTO_SRC}/crypto/perlasm @@ -34,7 +32,7 @@ SRCS+= armv8-mont.pl SRCS+= chacha-armv8.pl chacha-armv8-sve.pl # ec -SRCS+= ecp_nistz256-armv8.pl ecp_sm2p256-armv8.pl +SRCS+= ecp_nistz256-armv8.pl # md5 SRCS+= md5-aarch64.pl @@ -48,12 +46,6 @@ SRCS+= poly1305-armv8.pl # sha SRCS+= keccak1600-armv8.pl sha1-armv8.pl sha512-armv8.pl -# sm3 -SRCS+= sm3-armv8.pl - -# sm4 -SRCS+= sm4-armv8.pl vpsm4-armv8.pl vpsm4_ex-armv8.pl - ASM= ${SRCS:R:S/$/.S/} sha256-armv8.S all: ${ASM} @@ -218,7 +210,6 @@ CLEANFILES= ${ASM} ${LCRYPTO_SRC}/crypto/bf/asm \ ${LCRYPTO_SRC}/crypto/bn/asm \ ${LCRYPTO_SRC}/crypto/camellia/asm \ - ${LCRYPTO_SRC}/crypto/cast/asm \ ${LCRYPTO_SRC}/crypto/chacha/asm \ ${LCRYPTO_SRC}/crypto/des/asm \ ${LCRYPTO_SRC}/crypto/ec/asm \ @@ -226,7 +217,6 @@ CLEANFILES= ${ASM} ${LCRYPTO_SRC}/crypto/modes/asm \ ${LCRYPTO_SRC}/crypto/poly1305/asm \ ${LCRYPTO_SRC}/crypto/rc4/asm \ - ${LCRYPTO_SRC}/crypto/rc5/asm \ ${LCRYPTO_SRC}/crypto/ripemd/asm \ ${LCRYPTO_SRC}/crypto/sha/asm \ ${LCRYPTO_SRC}/crypto/whrlpool/asm \ @@ -250,9 +240,6 @@ SRCS+= bn-586.pl co-586.pl x86-gf2m.pl x86-mont.pl # camellia SRCS+= cmll-x86.pl -# cast -SRCS+= cast-586.pl - # chacha SRCS+= chacha-x86.pl @@ -274,9 +261,6 @@ SRCS+= poly1305-x86.pl # rc4 SRCS+= rc4-586.pl -# rc5 -SRCS+= rc5-586.pl - # ripemd SRCS+= rmd-586.pl @@ -329,7 +313,7 @@ SRCS+= aes-ppc.pl vpaes-ppc.pl aesp8-ppc.pl SRCS+= sha1-ppc.pl sha512-ppc.pl sha512p8-ppc.pl #modes -SRCS+= aes-gcm-ppc.pl ghashp8-ppc.pl +SRCS+= ghashp8-ppc.pl #chacha SRCS+= chacha-ppc.pl chachap10-ppc.pl diff --git a/sys/crypto/openssl/aarch64/ecp_sm2p256-armv8.S b/sys/crypto/openssl/aarch64/ecp_sm2p256-armv8.S deleted file mode 100644 index c9d925a7bc77..000000000000 --- a/sys/crypto/openssl/aarch64/ecp_sm2p256-armv8.S +++ /dev/null @@ -1,837 +0,0 @@ -/* Do not modify. This file is auto-generated from ecp_sm2p256-armv8.pl. */ -#include "arm_arch.h" -.arch armv8-a -.section .rodata - -.align 5 -// The polynomial p -.Lpoly: -.quad 0xffffffffffffffff,0xffffffff00000000,0xffffffffffffffff,0xfffffffeffffffff -// The order of polynomial n -.Lord: -.quad 0x53bbf40939d54123,0x7203df6b21c6052b,0xffffffffffffffff,0xfffffffeffffffff -// (p + 1) / 2 -.Lpoly_div_2: -.quad 0x8000000000000000,0xffffffff80000000,0xffffffffffffffff,0x7fffffff7fffffff -// (n + 1) / 2 -.Lord_div_2: -.quad 0xa9ddfa049ceaa092,0xb901efb590e30295,0xffffffffffffffff,0x7fffffff7fffffff - -.text - -// void bn_rshift1(BN_ULONG *a); -.globl bn_rshift1 -.type bn_rshift1,%function -.align 5 -bn_rshift1: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x0] - ldp x9,x10,[x0,#16] - - // Right shift - extr x7,x8,x7,#1 - extr x8,x9,x8,#1 - extr x9,x10,x9,#1 - lsr x10,x10,#1 - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - - ret -.size bn_rshift1,.-bn_rshift1 - -// void bn_sub(BN_ULONG *r, const BN_ULONG *a, const BN_ULONG *b); -.globl bn_sub -.type bn_sub,%function -.align 5 -bn_sub: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Subtraction - subs x7,x7,x11 - sbcs x8,x8,x12 - sbcs x9,x9,x13 - sbc x10,x10,x14 - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - - ret -.size bn_sub,.-bn_sub - -// void ecp_sm2p256_div_by_2(BN_ULONG *r,const BN_ULONG *a); -.globl ecp_sm2p256_div_by_2 -.type ecp_sm2p256_div_by_2,%function -.align 5 -ecp_sm2p256_div_by_2: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - - // Save the least significant bit - mov x3,x7 - - // Right shift 1 - extr x7,x8,x7,#1 - extr x8,x9,x8,#1 - extr x9,x10,x9,#1 - lsr x10,x10,#1 - - // Load mod - adrp x2,.Lpoly_div_2 - add x2,x2,#:lo12:.Lpoly_div_2 - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Parity check - tst x3,#1 - csel x11,xzr,x11,eq - csel x12,xzr,x12,eq - csel x13,xzr,x13,eq - csel x14,xzr,x14,eq - - // Add - adds x7,x7,x11 - adcs x8,x8,x12 - adcs x9,x9,x13 - adc x10,x10,x14 - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - ret -.size ecp_sm2p256_div_by_2,.-ecp_sm2p256_div_by_2 - -// void ecp_sm2p256_div_by_2_mod_ord(BN_ULONG *r,const BN_ULONG *a); -.globl ecp_sm2p256_div_by_2_mod_ord -.type ecp_sm2p256_div_by_2_mod_ord,%function -.align 5 -ecp_sm2p256_div_by_2_mod_ord: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - - // Save the least significant bit - mov x3,x7 - - // Right shift 1 - extr x7,x8,x7,#1 - extr x8,x9,x8,#1 - extr x9,x10,x9,#1 - lsr x10,x10,#1 - - // Load mod - adrp x2,.Lord_div_2 - add x2,x2,#:lo12:.Lord_div_2 - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Parity check - tst x3,#1 - csel x11,xzr,x11,eq - csel x12,xzr,x12,eq - csel x13,xzr,x13,eq - csel x14,xzr,x14,eq - - // Add - adds x7,x7,x11 - adcs x8,x8,x12 - adcs x9,x9,x13 - adc x10,x10,x14 - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - ret -.size ecp_sm2p256_div_by_2_mod_ord,.-ecp_sm2p256_div_by_2_mod_ord - -// void ecp_sm2p256_mul_by_3(BN_ULONG *r,const BN_ULONG *a); -.globl ecp_sm2p256_mul_by_3 -.type ecp_sm2p256_mul_by_3,%function -.align 5 -ecp_sm2p256_mul_by_3: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - - // 2*a - adds x7,x7,x7 - adcs x8,x8,x8 - adcs x9,x9,x9 - adcs x10,x10,x10 - adcs x15,xzr,xzr - - mov x3,x7 - mov x4,x8 - mov x5,x9 - mov x6,x10 - - // Sub polynomial - adrp x2,.Lpoly - add x2,x2,#:lo12:.Lpoly - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - subs x7,x7,x11 - sbcs x8,x8,x12 - sbcs x9,x9,x13 - sbcs x10,x10,x14 - sbcs x15,x15,xzr - - csel x7,x7,x3,cs - csel x8,x8,x4,cs - csel x9,x9,x5,cs - csel x10,x10,x6,cs - eor x15,x15,x15 - - // 3*a - ldp x11,x12,[x1] - ldp x13,x14,[x1,#16] - adds x7,x7,x11 - adcs x8,x8,x12 - adcs x9,x9,x13 - adcs x10,x10,x14 - adcs x15,xzr,xzr - - mov x3,x7 - mov x4,x8 - mov x5,x9 - mov x6,x10 - - // Sub polynomial - adrp x2,.Lpoly - add x2,x2,#:lo12:.Lpoly - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - subs x7,x7,x11 - sbcs x8,x8,x12 - sbcs x9,x9,x13 - sbcs x10,x10,x14 - sbcs x15,x15,xzr - - csel x7,x7,x3,cs - csel x8,x8,x4,cs - csel x9,x9,x5,cs - csel x10,x10,x6,cs - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - - ret -.size ecp_sm2p256_mul_by_3,.-ecp_sm2p256_mul_by_3 - -// void ecp_sm2p256_add(BN_ULONG *r,const BN_ULONG *a,const BN_ULONG *b); -.globl ecp_sm2p256_add -.type ecp_sm2p256_add,%function -.align 5 -ecp_sm2p256_add: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Addition - adds x7,x7,x11 - adcs x8,x8,x12 - adcs x9,x9,x13 - adcs x10,x10,x14 - adc x15,xzr,xzr - - // Load polynomial - adrp x2,.Lpoly - add x2,x2,#:lo12:.Lpoly - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Backup Addition - mov x3,x7 - mov x4,x8 - mov x5,x9 - mov x6,x10 - - // Sub polynomial - subs x3,x3,x11 - sbcs x4,x4,x12 - sbcs x5,x5,x13 - sbcs x6,x6,x14 - sbcs x15,x15,xzr - - // Select based on carry - csel x7,x7,x3,cc - csel x8,x8,x4,cc - csel x9,x9,x5,cc - csel x10,x10,x6,cc - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - ret -.size ecp_sm2p256_add,.-ecp_sm2p256_add - -// void ecp_sm2p256_sub(BN_ULONG *r,const BN_ULONG *a,const BN_ULONG *b); -.globl ecp_sm2p256_sub -.type ecp_sm2p256_sub,%function -.align 5 -ecp_sm2p256_sub: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Subtraction - subs x7,x7,x11 - sbcs x8,x8,x12 - sbcs x9,x9,x13 - sbcs x10,x10,x14 - sbc x15,xzr,xzr - - // Load polynomial - adrp x2,.Lpoly - add x2,x2,#:lo12:.Lpoly - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Backup subtraction - mov x3,x7 - mov x4,x8 - mov x5,x9 - mov x6,x10 - - // Add polynomial - adds x3,x3,x11 - adcs x4,x4,x12 - adcs x5,x5,x13 - adcs x6,x6,x14 - tst x15,x15 - - // Select based on carry - csel x7,x7,x3,eq - csel x8,x8,x4,eq - csel x9,x9,x5,eq - csel x10,x10,x6,eq - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - ret -.size ecp_sm2p256_sub,.-ecp_sm2p256_sub - -// void ecp_sm2p256_sub_mod_ord(BN_ULONG *r,const BN_ULONG *a,const BN_ULONG *b); -.globl ecp_sm2p256_sub_mod_ord -.type ecp_sm2p256_sub_mod_ord,%function -.align 5 -ecp_sm2p256_sub_mod_ord: - AARCH64_VALID_CALL_TARGET - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Subtraction - subs x7,x7,x11 - sbcs x8,x8,x12 - sbcs x9,x9,x13 - sbcs x10,x10,x14 - sbc x15,xzr,xzr - - // Load polynomial - adrp x2,.Lord - add x2,x2,#:lo12:.Lord - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - - // Backup subtraction - mov x3,x7 - mov x4,x8 - mov x5,x9 - mov x6,x10 - - // Add polynomial - adds x3,x3,x11 - adcs x4,x4,x12 - adcs x5,x5,x13 - adcs x6,x6,x14 - tst x15,x15 - - // Select based on carry - csel x7,x7,x3,eq - csel x8,x8,x4,eq - csel x9,x9,x5,eq - csel x10,x10,x6,eq - - // Store results - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - ret -.size ecp_sm2p256_sub_mod_ord,.-ecp_sm2p256_sub_mod_ord - -.macro RDC - // a = | s7 | ... | s0 |, where si are 64-bit quantities - // = |a15|a14| ... |a1|a0|, where ai are 32-bit quantities - // | s7 | s6 | s5 | s4 | - // | a15 | a14 | a13 | a12 | a11 | a10 | a9 | a8 | - // | s3 | s2 | s1 | s0 | - // | a7 | a6 | a5 | a4 | a3 | a2 | a1 | a0 | - // ================================================= - // | a8 | a11 | a10 | a9 | a8 | 0 | s4 | (+) - // | a9 | a15 | s6 | a11 | 0 | a10 | a9 | (+) - // | a10 | 0 | a14 | a13 | a12 | 0 | s5 | (+) - // | a11 | 0 | s7 | a13 | 0 | a12 | a11 | (+) - // | a12 | 0 | s7 | a13 | 0 | s6 | (+) - // | a12 | 0 | 0 | a15 | a14 | 0 | a14 | a13 | (+) - // | a13 | 0 | 0 | 0 | a15 | 0 | a14 | a13 | (+) - // | a13 | 0 | 0 | 0 | 0 | 0 | s7 | (+) - // | a14 | 0 | 0 | 0 | 0 | 0 | s7 | (+) - // | a14 | 0 | 0 | 0 | 0 | 0 | 0 | a15 | (+) - // | a15 | 0 | 0 | 0 | 0 | 0 | 0 | a15 | (+) - // | a15 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | (+) - // | s7 | 0 | 0 | 0 | 0 | 0 | 0 | (+) - // | 0 | 0 | 0 | 0 | 0 | a8 | 0 | 0 | (-) - // | 0 | 0 | 0 | 0 | 0 | a9 | 0 | 0 | (-) - // | 0 | 0 | 0 | 0 | 0 | a13 | 0 | 0 | (-) - // | 0 | 0 | 0 | 0 | 0 | a14 | 0 | 0 | (-) - // | U[7]| U[6]| U[5]| U[4]| U[3]| U[2]| U[1]| U[0]| - // | V[3] | V[2] | V[1] | V[0] | - - // 1. 64-bit addition - // t2=s6+s7+s7 - adds x5,x13,x14 - adcs x4,xzr,xzr - adds x5,x5,x14 - adcs x4,x4,xzr - // t3=s4+s5+t2 - adds x6,x11,x5 - adcs x15,x4,xzr - adds x6,x6,x12 - adcs x15,x15,xzr - // sum - adds x7,x7,x6 - adcs x8,x8,x15 - adcs x9,x9,x5 - adcs x10,x10,x14 - adcs x3,xzr,xzr - adds x10,x10,x4 - adcs x3,x3,xzr - - stp x7,x8,[sp,#32] - stp x9,x10,[sp,#48] - - // 2. 64-bit to 32-bit spread - mov x4,#0xffffffff - mov x7,x11 - mov x8,x12 - mov x9,x13 - mov x10,x14 - and x7,x7,x4 // a8 - and x8,x8,x4 // a10 - and x9,x9,x4 // a12 - and x10,x10,x4 // a14 - lsr x11,x11,#32 // a9 - lsr x12,x12,#32 // a11 - lsr x13,x13,#32 // a13 - lsr x14,x14,#32 // a15 - - // 3. 32-bit addition - add x4,x10,x9 // t1 <- a12 + a14 - add x5,x14,x13 // t2 <- a13 + a15 - add x6,x7,x11 // t3 <- a8 + a9 - add x15,x10,x8 // t4 <- a10 + a14 - add x14,x14,x12 // a15 <- a11 + a15 - add x9,x5,x4 // a12 <- a12 + a13 + a14 + a15 - add x8,x8,x9 // a10 <- a10 + a12 + a13 + a14 + a15 - add x8,x8,x9 // a10 <- a10 + 2*(a12 + a13 + a14 + a15) - add x8,x8,x6 // a10 <- a8 + a9 + a10 + 2*(a12 + a13 + a14 + a15) - add x8,x8,x12 // a10 <- a8 + a9 + a10 + a11 + 2*(a12 + a13 + a14 + a15) - add x9,x9,x13 // a12 <- a12 + 2*a13 + a14 + a15 - add x9,x9,x12 // a12 <- a11 + a12 + 2*a13 + a14 + a15 - add x9,x9,x7 // a12 <- a8 + a11 + a12 + 2*a13 + a14 + a15 - add x6,x6,x10 // t3 <- a8 + a9 + a14 - add x6,x6,x13 // t3 <- a8 + a9 + a13 + a14 - add x11,x11,x5 // a9 <- a9 + a13 + a15 - add x12,x12,x11 // a11 <- a9 + a11 + a13 + a15 - add x12,x12,x5 // a11 <- a9 + a11 + 2*(a13 + a15) - add x4,x4,x15 // t1 <- a10 + a12 + 2*a14 - - // U[0] s5 a9 + a11 + 2*(a13 + a15) - // U[1] t1 a10 + a12 + 2*a14 - // U[2] -t3 a8 + a9 + a13 + a14 - // U[3] s2 a8 + a11 + a12 + 2*a13 + a14 + a15 - // U[4] s4 a9 + a13 + a15 - // U[5] t4 a10 + a14 - // U[6] s7 a11 + a15 - // U[7] s1 a8 + a9 + a10 + a11 + 2*(a12 + a13 + a14 + a15) - - // 4. 32-bit to 64-bit - lsl x7,x4,#32 - extr x4,x9,x4,#32 - extr x9,x15,x9,#32 - extr x15,x8,x15,#32 - lsr x8,x8,#32 - - // 5. 64-bit addition - adds x12,x12,x7 - adcs x4,x4,xzr - adcs x11,x11,x9 - adcs x14,x14,x15 - adcs x3,x3,x8 - - // V[0] s5 - // V[1] t1 - // V[2] s4 - // V[3] s7 - // carry t0 - // sub t3 - - // 5. Process s0-s3 - ldp x7,x8,[sp,#32] - ldp x9,x10,[sp,#48] - // add with V0-V3 - adds x7,x7,x12 - adcs x8,x8,x4 - adcs x9,x9,x11 - adcs x10,x10,x14 - adcs x3,x3,xzr - // sub with t3 - subs x8,x8,x6 - sbcs x9,x9,xzr - sbcs x10,x10,xzr - sbcs x3,x3,xzr - - // 6. MOD - // First Mod - lsl x4,x3,#32 - subs x5,x4,x3 - - adds x7,x7,x3 - adcs x8,x8,x5 - adcs x9,x9,xzr - adcs x10,x10,x4 - - // Last Mod - // return y - p if y > p else y - mov x11,x7 - mov x12,x8 - mov x13,x9 - mov x14,x10 - - adrp x3,.Lpoly - add x3,x3,#:lo12:.Lpoly - ldp x4,x5,[x3] - ldp x6,x15,[x3,#16] - - adcs x16,xzr,xzr - - subs x7,x7,x4 - sbcs x8,x8,x5 - sbcs x9,x9,x6 - sbcs x10,x10,x15 - sbcs x16,x16,xzr - - csel x7,x7,x11,cs - csel x8,x8,x12,cs - csel x9,x9,x13,cs - csel x10,x10,x14,cs - -.endm - -// void ecp_sm2p256_mul(BN_ULONG *r, const BN_ULONG *a, const BN_ULONG *b); -.globl ecp_sm2p256_mul -.type ecp_sm2p256_mul,%function -.align 5 -ecp_sm2p256_mul: - AARCH64_SIGN_LINK_REGISTER - // Store scalar registers - stp x29,x30,[sp,#-80]! - add x29,sp,#0 - stp x16,x17,[sp,#16] - stp x19,x20,[sp,#64] - - // Load inputs - ldp x7,x8,[x1] - ldp x9,x10,[x1,#16] - ldp x11,x12,[x2] - ldp x13,x14,[x2,#16] - -// ### multiplication ### - // ======================== - // s3 s2 s1 s0 - // * s7 s6 s5 s4 - // ------------------------ - // + s0 s0 s0 s0 - // * * * * - // s7 s6 s5 s4 - // s1 s1 s1 s1 - // * * * * - // s7 s6 s5 s4 - // s2 s2 s2 s2 - // * * * * - // s7 s6 s5 s4 - // s3 s3 s3 s3 - // * * * * - // s7 s6 s5 s4 - // ------------------------ - // s7 s6 s5 s4 s3 s2 s1 s0 - // ======================== - -// ### s0*s4 ### - mul x16,x7,x11 - umulh x5,x7,x11 - -// ### s1*s4 + s0*s5 ### - mul x3,x8,x11 - umulh x4,x8,x11 - adds x5,x5,x3 - adcs x6,x4,xzr - - mul x3,x7,x12 - umulh x4,x7,x12 - adds x5,x5,x3 - adcs x6,x6,x4 - adcs x15,xzr,xzr - -// ### s2*s4 + s1*s5 + s0*s6 ### - mul x3,x9,x11 - umulh x4,x9,x11 - adds x6,x6,x3 - adcs x15,x15,x4 - - mul x3,x8,x12 - umulh x4,x8,x12 - adds x6,x6,x3 - adcs x15,x15,x4 - adcs x17,xzr,xzr - - mul x3,x7,x13 - umulh x4,x7,x13 - adds x6,x6,x3 - adcs x15,x15,x4 - adcs x17,x17,xzr - -// ### s3*s4 + s2*s5 + s1*s6 + s0*s7 ### - mul x3,x10,x11 - umulh x4,x10,x11 - adds x15,x15,x3 - adcs x17,x17,x4 - adcs x19,xzr,xzr - - mul x3,x9,x12 - umulh x4,x9,x12 - adds x15,x15,x3 - adcs x17,x17,x4 - adcs x19,x19,xzr - - mul x3,x8,x13 - umulh x4,x8,x13 - adds x15,x15,x3 - adcs x17,x17,x4 - adcs x19,x19,xzr - - mul x3,x7,x14 - umulh x4,x7,x14 - adds x15,x15,x3 - adcs x17,x17,x4 - adcs x19,x19,xzr - -// ### s3*s5 + s2*s6 + s1*s7 ### - mul x3,x10,x12 - umulh x4,x10,x12 - adds x17,x17,x3 - adcs x19,x19,x4 - adcs x20,xzr,xzr - - mul x3,x9,x13 - umulh x4,x9,x13 - adds x17,x17,x3 - adcs x19,x19,x4 - adcs x20,x20,xzr - - mul x3,x8,x14 - umulh x4,x8,x14 - adds x11,x17,x3 - adcs x19,x19,x4 - adcs x20,x20,xzr - -// ### s3*s6 + s2*s7 ### - mul x3,x10,x13 - umulh x4,x10,x13 - adds x19,x19,x3 - adcs x20,x20,x4 - adcs x17,xzr,xzr - - mul x3,x9,x14 - umulh x4,x9,x14 - adds x12,x19,x3 - adcs x20,x20,x4 - adcs x17,x17,xzr - -// ### s3*s7 ### - mul x3,x10,x14 - umulh x4,x10,x14 - adds x13,x20,x3 - adcs x14,x17,x4 - - mov x7,x16 - mov x8,x5 - mov x9,x6 - mov x10,x15 - - // result of mul: s7 s6 s5 s4 s3 s2 s1 s0 - -// ### Reduction ### - RDC - - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - - // Restore scalar registers - ldp x16,x17,[sp,#16] - ldp x19,x20,[sp,#64] - ldp x29,x30,[sp],#80 - - AARCH64_VALIDATE_LINK_REGISTER - ret -.size ecp_sm2p256_mul,.-ecp_sm2p256_mul - -// void ecp_sm2p256_sqr(BN_ULONG *r, const BN_ULONG *a); -.globl ecp_sm2p256_sqr -.type ecp_sm2p256_sqr,%function -.align 5 - -ecp_sm2p256_sqr: - AARCH64_SIGN_LINK_REGISTER - // Store scalar registers - stp x29,x30,[sp,#-80]! - add x29,sp,#0 - stp x16,x17,[sp,#16] - stp x19,x20,[sp,#64] - - // Load inputs - ldp x11,x12,[x1] - ldp x13,x14,[x1,#16] - -// ### square ### - // ======================== - // s7 s6 s5 s4 - // * s7 s6 s5 s4 - // ------------------------ - // + s4 s4 s4 s4 - // * * * * - // s7 s6 s5 s4 - // s5 s5 s5 s5 - // * * * * - // s7 s6 s5 s4 - // s6 s6 s6 s6 - // * * * * - // s7 s6 s5 s4 - // s7 s7 s7 s7 - // * * * * - // s7 s6 s5 s4 - // ------------------------ - // s7 s6 s5 s4 s3 s2 s1 s0 - // ======================== - -// ### s4*s5 ### - mul x8,x11,x12 - umulh x9,x11,x12 - -// ### s4*s6 ### - mul x3,x13,x11 - umulh x10,x13,x11 - adds x9,x9,x3 - adcs x10,x10,xzr - -// ### s4*s7 + s5*s6 ### - mul x3,x14,x11 - umulh x4,x14,x11 - adds x10,x10,x3 - adcs x7,x4,xzr - - mul x3,x13,x12 - umulh x4,x13,x12 - adds x10,x10,x3 - adcs x7,x7,x4 - adcs x5,xzr,xzr - -// ### s5*s7 ### - mul x3,x14,x12 - umulh x4,x14,x12 - adds x7,x7,x3 - adcs x5,x5,x4 - -// ### s6*s7 ### - mul x3,x14,x13 - umulh x4,x14,x13 - adds x5,x5,x3 - adcs x6,x4,xzr - -// ### 2*(t3,t2,s0,s3,s2,s1) ### - adds x8,x8,x8 - adcs x9,x9,x9 - adcs x10,x10,x10 - adcs x7,x7,x7 - adcs x5,x5,x5 - adcs x6,x6,x6 - adcs x15,xzr,xzr - -// ### s4*s4 ### - mul x16,x11,x11 - umulh x17,x11,x11 - -// ### s5*s5 ### - mul x11,x12,x12 - umulh x12,x12,x12 - -// ### s6*s6 ### - mul x3,x13,x13 - umulh x4,x13,x13 - -// ### s7*s7 ### - mul x19,x14,x14 - umulh x20,x14,x14 - - adds x8,x8,x17 - adcs x9,x9,x11 - adcs x10,x10,x12 - adcs x7,x7,x3 - adcs x5,x5,x4 - adcs x6,x6,x19 - adcs x15,x15,x20 - - mov x11,x7 - mov x7,x16 - mov x12,x5 - mov x13,x6 - mov x14,x15 - - // result of mul: s7 s6 s5 s4 s3 s2 s1 s0 - -// ### Reduction ### - RDC - - stp x7,x8,[x0] - stp x9,x10,[x0,#16] - - // Restore scalar registers - ldp x16,x17,[sp,#16] - ldp x19,x20,[sp,#64] - ldp x29,x30,[sp],#80 - - AARCH64_VALIDATE_LINK_REGISTER - ret -.size ecp_sm2p256_sqr,.-ecp_sm2p256_sqr diff --git a/sys/crypto/openssl/aarch64/sm3-armv8.S b/sys/crypto/openssl/aarch64/sm3-armv8.S deleted file mode 100644 index 08785cae9e16..000000000000 --- a/sys/crypto/openssl/aarch64/sm3-armv8.S +++ /dev/null @@ -1,509 +0,0 @@ -/* Do not modify. This file is auto-generated from sm3-armv8.pl. */ -// Copyright 2021-2025 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 *** 15451 LINES SKIPPED ***