Engage ARMv8 AES support.

5 files changed, 82 insertions, 10 deletions

diff --git a/Configure b/Configure
index 8e79dd4df0..b997052377 100755
--- a/Configure
+++ b/Configure
@@ -136,8 +136,8 @@ my $alpha_asm="alphacpuid.o:bn_asm.o alpha-mont.o:::::sha1-alpha.o:::::::ghash-a
 my $mips64_asm=":bn-mips.o mips-mont.o::aes_cbc.o aes-mips.o:::sha1-mips.o sha256-mips.o sha512-mips.o::::::::";
 my $mips32_asm=$mips64_asm; $mips32_asm =~ s/\s*sha512\-mips\.o//;
 my $s390x_asm="s390xcap.o s390xcpuid.o:bn-s390x.o s390x-mont.o s390x-gf2m.o::aes-s390x.o aes-ctr.o aes-xts.o:::sha1-s390x.o sha256-s390x.o sha512-s390x.o::rc4-s390x.o:::::ghash-s390x.o:";
-my $armv4_asm="armcap.o armv4cpuid.o:bn_asm.o armv4-mont.o armv4-gf2m.o::aes_cbc.o aes-armv4.o bsaes-armv7.o:::sha1-armv4-large.o sha256-armv4.o sha512-armv4.o:::::::ghash-armv4.o::void";
-my $aarch64_asm="armcap.o arm64cpuid.o mem_clr.o::::::sha1-armv8.o sha256-armv8.o sha512-armv8.o::::::::";
+my $armv4_asm="armcap.o armv4cpuid.o:bn_asm.o armv4-mont.o armv4-gf2m.o::aes_cbc.o aes-armv4.o bsaes-armv7.o aesv8-armx.o:::sha1-armv4-large.o sha256-armv4.o sha512-armv4.o:::::::ghash-armv4.o::void";
+my $aarch64_asm="armcap.o arm64cpuid.o mem_clr.o:::aes_core.o aes_cbc.o aesv8-armx.o:::sha1-armv8.o sha256-armv8.o sha512-armv8.o::::::::";
 my $parisc11_asm="pariscid.o:bn_asm.o parisc-mont.o::aes_core.o aes_cbc.o aes-parisc.o:::sha1-parisc.o sha256-parisc.o sha512-parisc.o::rc4-parisc.o:::::ghash-parisc.o::32";
 my $parisc20_asm="pariscid.o:pa-risc2W.o parisc-mont.o::aes_core.o aes_cbc.o aes-parisc.o:::sha1-parisc.o sha256-parisc.o sha512-parisc.o::rc4-parisc.o:::::ghash-parisc.o::64";
 my $ppc64_asm="ppccpuid.o ppccap.o:bn-ppc.o ppc-mont.o ppc64-mont.o::aes_core.o aes_cbc.o aes-ppc.o vpaes-ppc.o:::sha1-ppc.o sha256-ppc.o sha512-ppc.o::::::::";
diff --git a/TABLE b/TABLE
index e730da9bda..9a8df35dea 100644
--- a/TABLE
+++ b/TABLE
@@ -1100,7 +1100,7 @@ $bn_ops       = BN_LLONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR
 $cpuid_obj    = armcap.o armv4cpuid.o
 $bn_obj       = bn_asm.o armv4-mont.o armv4-gf2m.o
 $des_obj      = 
-$aes_obj      = aes_cbc.o aes-armv4.o bsaes-armv7.o
+$aes_obj      = aes_cbc.o aes-armv4.o bsaes-armv7.o aesv8-armx.o
 $bf_obj       = 
 $md5_obj      = 
 $sha1_obj     = sha1-armv4-large.o sha256-armv4.o sha512-armv4.o
@@ -4004,7 +4004,7 @@ $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR
 $cpuid_obj    = armcap.o arm64cpuid.o mem_clr.o
 $bn_obj       = 
 $des_obj      = 
-$aes_obj      = 
+$aes_obj      = aes_core.o aes_cbc.o aesv8-armx.o
 $bf_obj       = 
 $md5_obj      = 
 $sha1_obj     = sha1-armv8.o sha256-armv8.o sha512-armv8.o
@@ -4202,7 +4202,7 @@ $bn_ops       = BN_LLONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR
 $cpuid_obj    = armcap.o armv4cpuid.o
 $bn_obj       = bn_asm.o armv4-mont.o armv4-gf2m.o
 $des_obj      = 
-$aes_obj      = aes_cbc.o aes-armv4.o bsaes-armv7.o
+$aes_obj      = aes_cbc.o aes-armv4.o bsaes-armv7.o aesv8-armx.o
 $bf_obj       = 
 $md5_obj      = 
 $sha1_obj     = sha1-armv4-large.o sha256-armv4.o sha512-armv4.o
diff --git a/crypto/aes/Makefile b/crypto/aes/Makefile
index 1c32ee7f02..192464c9db 100644
--- a/crypto/aes/Makefile
+++ b/crypto/aes/Makefile
@@ -86,6 +86,10 @@ aes-parisc.s:	asm/aes-parisc.pl
 aes-mips.S:	asm/aes-mips.pl
 	$(PERL) asm/aes-mips.pl $(PERLASM_SCHEME) $@
 
+aesv8-armx.S:	asm/aesv8-armx.pl
+	$(PERL) asm/aesv8-armx.pl $(PERLASM_SCHEME) $@
+aesv8-armx.o:	aesv8-armx.S
+
 # GNU make "catch all"
 aes-%.S:	asm/aes-%.pl;	$(PERL) $< $(PERLASM_SCHEME) $@
 aes-armv4.o:	aes-armv4.S
diff --git a/crypto/aes/asm/aesv8-armx.pl b/crypto/aes/asm/aesv8-armx.pl
index 763377f2cc..55a8ff77c5 100755
--- a/crypto/aes/asm/aesv8-armx.pl
+++ b/crypto/aes/asm/aesv8-armx.pl
@@ -23,9 +23,16 @@
 # Cortex-A5x	n/a		n/a
 
 $flavour = shift;
-$prefix="AES";
+open STDOUT,">".shift;
 
-$code=".text\n";
+$prefix="aes_v8";
+
+$code=<<___;
+#include "arm_arch.h"
+
+#if __ARM_ARCH__>=7
+.text
+___
 $code.=".arch	armv8-a+crypto\n"	if ($flavour =~ /64/);
 $code.=".fpu	neon\n.code	32\n"	if ($flavour !~ /64/);
 
@@ -669,7 +676,7 @@ $code.=<<___;
 	subs		$len,$len,#2
 	b.lo		.Lctr32_tail
 
-#ifndef BIG_ENDIAN
+#ifndef __ARMEB__
 	rev		$ctr, $ctr
 #endif
 	vorr		$dat1,$dat0,$dat0
@@ -862,6 +869,9 @@ $code.=<<___;
 .size	${prefix}_ctr32_encrypt_blocks,.-${prefix}_ctr32_encrypt_blocks
 ___
 }}}
+$code.=<<___;
+#endif
+___
 ########################################
 if ($flavour =~ /64/) {			######## 64-bit code
     my %opcode = (
diff --git a/crypto/evp/e_aes.c b/crypto/evp/e_aes.c
index f8a69a0b5e..6ba452593b 100644
--- a/crypto/evp/e_aes.c
+++ b/crypto/evp/e_aes.c
@@ -900,13 +900,38 @@ const EVP_CIPHER *EVP_aes_##keylen##_##mode(void) \
 
 #endif
 
-#if defined(AES_ASM) && defined(BSAES_ASM) && (defined(__arm__) || defined(__arm))
+#if defined(OPENSSL_CPUID_OBJ) && (defined(__arm__) || defined(__arm) || defined(__aarch64__))
 #include "arm_arch.h"
 #if __ARM_ARCH__>=7
-#define BSAES_CAPABLE	(OPENSSL_armcap_P & ARMV7_NEON)
+# if defined(BSAES_ASM)
+#  define BSAES_CAPABLE	(OPENSSL_armcap_P & ARMV7_NEON)
+# endif
+# define HWAES_CAPABLE (OPENSSL_armcap_P & ARMV8_AES)
+# define HWAES_set_encrypt_key aes_v8_set_encrypt_key
+# define HWAES_set_decrypt_key aes_v8_set_decrypt_key
+# define HWAES_encrypt aes_v8_encrypt
+# define HWAES_decrypt aes_v8_decrypt
+# define HWAES_cbc_encrypt aes_v8_cbc_encrypt
+# define HWAES_ctr32_encrypt_blocks aes_v8_ctr32_encrypt_blocks
 #endif
 #endif
 
+#if defined(HWAES_CAPABLE)
+int HWAES_set_encrypt_key(const unsigned char *userKey, const int bits,
+	AES_KEY *key);
+int HWAES_set_decrypt_key(const unsigned char *userKey, const int bits,
+	AES_KEY *key);
+void HWAES_encrypt(const unsigned char *in, unsigned char *out,
+	const AES_KEY *key);
+void HWAES_decrypt(const unsigned char *in, unsigned char *out,
+	const AES_KEY *key);
+void HWAES_cbc_encrypt(const unsigned char *in, unsigned char *out,
+	size_t length, const AES_KEY *key,
+	unsigned char *ivec, const int enc);
+void HWAES_ctr32_encrypt_blocks(const unsigned char *in, unsigned char *out,
+	size_t len, const AES_KEY *key, const unsigned char ivec[16]);
+#endif
+
 #define BLOCK_CIPHER_generic_pack(nid,keylen,flags)		\
 	BLOCK_CIPHER_generic(nid,keylen,16,16,cbc,cbc,CBC,flags|EVP_CIPH_FLAG_DEFAULT_ASN1)	\
 	BLOCK_CIPHER_generic(nid,keylen,16,0,ecb,ecb,ECB,flags|EVP_CIPH_FLAG_DEFAULT_ASN1)	\
@@ -925,6 +950,19 @@ static int aes_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 	mode = ctx->cipher->flags & EVP_CIPH_MODE;
 	if ((mode == EVP_CIPH_ECB_MODE || mode == EVP_CIPH_CBC_MODE)
 	    && !enc)
+#ifdef HWAES_CAPABLE
+	    if (HWAES_CAPABLE)
+		{
+		ret = HWAES_set_decrypt_key(key,ctx->key_len*8,&dat->ks.ks);
+		dat->block      = (block128_f)HWAES_decrypt;
+		dat->stream.cbc = NULL;
+#ifdef HWAES_cbc_encrypt
+		if (mode==EVP_CIPH_CBC_MODE)
+		    dat->stream.cbc = (cbc128_f)HWAES_cbc_encrypt;
+#endif
+		}
+	    else
+#endif
 #ifdef BSAES_CAPABLE
 	    if (BSAES_CAPABLE && mode==EVP_CIPH_CBC_MODE)
 		{
@@ -953,6 +991,26 @@ static int aes_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 					NULL;
 		}
 	else
+#ifdef HWAES_CAPABLE
+	    if (HWAES_CAPABLE)
+		{
+		ret = HWAES_set_encrypt_key(key,ctx->key_len*8,&dat->ks.ks);
+		dat->block      = (block128_f)HWAES_encrypt;
+		dat->stream.cbc = NULL;
+#ifdef HWAES_cbc_encrypt
+		if (mode==EVP_CIPH_CBC_MODE)
+		    dat->stream.cbc = (cbc128_f)HWAES_cbc_encrypt;
+		else
+#endif
+#ifdef HWAES_ctr32_encrypt_blocks
+		if (mode==EVP_CIPH_CTR_MODE)
+		    dat->stream.ctr = (ctr128_f)HWAES_ctr32_encrypt_blocks;
+		else
+#endif
+		(void)0;	/* terminate potentially open 'else' */
+		}
+	    else
+#endif
 #ifdef BSAES_CAPABLE
 	    if (BSAES_CAPABLE && mode==EVP_CIPH_CTR_MODE)
 		{