crypto/modes/modes_lcl.h: let STRICT_ALIGNMENT be on ARMv7.

While ARMv7 in general is capable of unaligned access, not all instructions
actually are. And trouble is that compiler doesn't seem to differentiate
those capable and incapable of unaligned access. Side effect is that kernel
goes into endless loop retrying same instruction triggering unaligned trap.
Problem was observed in xts128.c and ccm128.c modules. It's possible to
resolve it by using (volatile u32*) casts, but letting STRICT_ALIGNMENT
be feels more appropriate.

(cherry picked from commit 3bdd80521a)
Reviewed-by: Dr. Stephen Henson <steve@openssl.org>
Reviewed-by: Tim Hudson <tjh@openssl.org>

.gitignore

@@ -0,0 +1,70 @@
+# Object files
+*.o
+
+# Top level excludes
+/Makefile.bak
+/Makefile
+/*.a
+/include
+/*.pc
+/rehash.time
+
+# Most *.c files under test/ are symlinks
+/test/*.c
+# Apart from these
+!/test/asn1test.c
+!/test/methtest.c
+!/test/dummytest.c
+!/test/igetest.c
+!/test/r160test.c
+!/test/fips_algvs.c
+
+# Certificate symbolic links
+*.0
+
+# Links under apps
+/apps/CA.pl
+/apps/md4.c
+
+
+# Auto generated headers
+/crypto/buildinf.h
+/crypto/opensslconf.h
+
+# Auto generated assembly language source files
+*.s
+!/crypto/bn/asm/pa-risc2.s
+!/crypto/bn/asm/pa-risc2W.s
+
+# Executables
+/apps/openssl
+/test/sha256t
+/test/sha512t
+/test/*test
+/test/fips_aesavs
+/test/fips_desmovs
+/test/fips_dhvs
+/test/fips_drbgvs
+/test/fips_dssvs
+/test/fips_ecdhvs
+/test/fips_ecdsavs
+/test/fips_rngvs
+/test/fips_test_suite
+*.so*
+*.dylib*
+*.dll*
+# Exceptions
+!/test/bctest
+!/crypto/des/times/486-50.sol
+
+# Misc auto generated files
+/tools/c_rehash
+/test/evptests.txt
+lib
+Makefile.save
+*.bak
+# FIPS module specific files.
+/fips/fips_auth.h
+/fips/fips_standalone_sha1
+/fips/fipscanister.o.sha1
+

CHANGES

@@ -4,6 +4,30 @@
 
  Changes between 1.0.1 and 1.1.0  [xx XXX xxxx]
 
+  *) Add perl scripts to calculate FIPS signatures for Windows
+     exectuables including WinCE. 
+     [Andy Polyakov]
+
+  *) Don't attempt to insert current time into AES/3DES tests, we should
+     be just copying input line across and this breaks some systems lacking
+     ctime. 
+     [Steve Henson]
+
+  *) Update Windows build system for FIPS. Don't compile algorithm test
+     utilties by default: the target build_tests is needed for that. Add
+     support for building fips_algvs with the build_algvs target.
+     [Steve Henson]
+
+  *) Add initial cross compilation support for Windows build. The following
+     environment variables should be set:
+
+     FIPS_SHA1_PATH: path to fips_standalone_sha1 exectutable which will
+     be used explicitly and not built.
+     FIPS_SIG: similar to other builds: path to a "get signature" script
+     which is used to obtain the signature of the target instead of
+     executing it on the host.
+     [Steve Henson]
+
   *) Add flag to EC_KEY to use cofactor ECDH if set.
      [Steve Henson]
 

Configure

@@ -136,6 +136,7 @@ my $mips32_asm=":bn-mips.o::aes_cbc.o aes-mips.o:::sha1-mips.o sha256-mips.o::::
 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 $s390x_asm="s390xcap.o s390xcpuid.o:bn-s390x.o s390x-mont.o s390x-gf2m.o::aes_ctr.o aes-s390x.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:::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:::::::ghashv8-armx.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 $ppc32_asm="ppccpuid.o ppccap.o:bn-ppc.o ppc-mont.o ppc64-mont.o::aes_core.o aes_cbc.o aes-ppc.o:::sha1-ppc.o sha256-ppc.o::::::::";
@@ -401,7 +402,8 @@ my %table=(
 # Android: linux-* but without -DTERMIO and pointers to headers and libs.
 "android","gcc:-mandroid -I\$(ANDROID_DEV)/include -B\$(ANDROID_DEV)/lib -O3 -fomit-frame-pointer -Wall::-D_REENTRANT::-ldl:BN_LLONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR:${no_asm}:dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 "android-x86","gcc:-mandroid -I\$(ANDROID_DEV)/include -B\$(ANDROID_DEV)/lib -O3 -fomit-frame-pointer -Wall::-D_REENTRANT::-ldl:BN_LLONG ${x86_gcc_des} ${x86_gcc_opts}:".eval{my $asm=${x86_elf_asm};$asm=~s/:elf/:android/;$asm}.":dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
-"android-armv7","gcc:-march=armv7-a -mandroid -I\$(ANDROID_DEV)/include -B\$(ANDROID_DEV)/lib -O3 -fomit-frame-pointer -Wall::-D_REENTRANT::-ldl:BN_LLONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR:${armv4_asm}:dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
+"android-armv7","gcc:-march=armv7-a -mandroid -I\$(ANDROID_DEV)/include -B\$(ANDROID_DEV)/lib -O3 -fomit-frame-pointer -Wall::-D_REENTRANT::-pie%-ldl:BN_LLONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR:${armv4_asm}:dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
+"android64-aarch64","gcc:-mandroid -fPIC -I\$(ANDROID_DEV)/include -B\$(ANDROID_DEV)/lib -O3 -Wall::-D_REENTRANT::-pie%-ldl:SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR:${aarch64_asm}:linux64:dlfcn:linux-shared:::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 
 #### *BSD [do see comment about ${BSDthreads} above!]
 "BSD-generic32","gcc:-DTERMIOS -O3 -fomit-frame-pointer -Wall::${BSDthreads}:::BN_LLONG RC2_CHAR RC4_INDEX DES_INT DES_UNROLL:${no_asm}:dlfcn:bsd-gcc-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
@@ -409,6 +411,8 @@ my %table=(
 "BSD-x86-elf",	"gcc:-DL_ENDIAN -DTERMIOS -O3 -fomit-frame-pointer -Wall::${BSDthreads}:::BN_LLONG ${x86_gcc_des} ${x86_gcc_opts}:${x86_elf_asm}:dlfcn:bsd-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 "debug-BSD-x86-elf",	"gcc:-DL_ENDIAN -DTERMIOS -O3 -Wall -g::${BSDthreads}:::BN_LLONG ${x86_gcc_des} ${x86_gcc_opts}:${x86_elf_asm}:dlfcn:bsd-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 "BSD-sparcv8",	"gcc:-DB_ENDIAN -DTERMIOS -O3 -mv8 -Wall::${BSDthreads}:::BN_LLONG RC2_CHAR RC4_INDEX DES_INT DES_UNROLL:${sparcv8_asm}:dlfcn:bsd-gcc-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
+"BSD-ppc85xx","gcc:-DTERMIOS -O3 -fomit-frame-pointer -msoft-float -Wall::${BSDthreads}:::BN_LLONG RC2_CHAR RC4_INDEX DES_INT DES_UNROLL:${no_asm}:dlfcn:bsd-gcc-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
+"debug-BSD-ppc85xx","gcc:-DTERMIOS -O0 -fomit-frame-pointer -msoft-float -Wall -g::${BSDthreads}:::BN_LLONG RC2_CHAR RC4_INDEX DES_INT DES_UNROLL:${no_asm}:dlfcn:bsd-gcc-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 
 "BSD-generic64","gcc:-DTERMIOS -O3 -Wall::${BSDthreads}:::SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL:${no_asm}:dlfcn:bsd-gcc-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 # -DMD32_REG_T=int doesn't actually belong in sparc64 target, it
@@ -461,8 +465,8 @@ my %table=(
 "aix64-gcc","gcc:-maix64 -O -DB_ENDIAN::-pthread:AIX::SIXTY_FOUR_BIT_LONG RC4_CHAR:${ppc64_asm}:aix64:dlfcn:aix-shared::-maix64 -shared -Wl,-G:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)::-X64",
 # Below targets assume AIX 5. Idea is to effectively disregard $OBJECT_MODE
 # at build time. $OBJECT_MODE is respected at ./config stage!
-"aix-cc",   "cc:-q32 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst::-qthreaded:AIX::BN_LLONG RC4_CHAR:${ppc32_asm}:aix32:dlfcn:aix-shared::-q32 -G:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)::-X 32",
-"aix64-cc", "cc:-q64 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst::-qthreaded:AIX::SIXTY_FOUR_BIT_LONG RC4_CHAR:${ppc64_asm}:aix64:dlfcn:aix-shared::-q64 -G:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)::-X 64",
+"aix-cc",   "cc:-q32 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst::-qthreaded -D_THREAD_SAFE:AIX::BN_LLONG RC4_CHAR:${ppc32_asm}:aix32:dlfcn:aix-shared::-q32 -G:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)::-X 32",
+"aix64-cc", "cc:-q64 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst::-qthreaded -D_THREAD_SAFE:AIX::SIXTY_FOUR_BIT_LONG RC4_CHAR:${ppc64_asm}:aix64:dlfcn:aix-shared::-q64 -G:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)::-X 64",
 
 #
 # Cray T90 and similar (SDSC)
@@ -579,7 +583,23 @@ my %table=(
 "darwin64-x86_64-cc","cc:-arch x86_64 -O3 -DL_ENDIAN -Wall::-D_REENTRANT:MACOSX:-Wl,-search_paths_first%:SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL:${x86_64_asm}:macosx:dlfcn:darwin-shared:-fPIC -fno-common:-arch x86_64 -dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
 "debug-darwin-ppc-cc","cc:-DBN_DEBUG -DREF_CHECK -DCONF_DEBUG -DCRYPTO_MDEBUG -DB_ENDIAN -g -Wall -O::-D_REENTRANT:MACOSX::BN_LLONG RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:${ppc32_asm}:osx32:dlfcn:darwin-shared:-fPIC:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
 # iPhoneOS/iOS
-"iphoneos-cross","llvm-gcc:-O3 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fomit-frame-pointer -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:BN_LLONG RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:${no_asm}:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
+#
+# It takes three prior-set environment variables to make it work:
+#
+# CROSS_COMPILE=/where/toolchain/is/usr/bin/ [note ending slash]
+# CROSS_TOP=/where/SDKs/are
+# CROSS_SDK=iPhoneOSx.y.sdk
+#
+# Exact paths vary with Xcode releases, but for couple of last ones
+# they would look like this:
+#
+# CROSS_COMPILE=`xcode-select --print-path`/Toolchains/XcodeDefault.xctoolchain/usr/bin/
+# CROSS_TOP=`xcode-select --print-path`/Platforms/iPhoneOS.platform/Developer
+# CROSS_SDK=iPhoneOS7.0.sdk
+#
+"iphoneos-cross","cc:-O3 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fomit-frame-pointer -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:BN_LLONG RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:${no_asm}:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
+"ios-cross","cc:-O3 -arch armv7 -mios-version-min=7.0.0 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:BN_LLONG RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:armcap.o armv4cpuid_ios.o:bn_asm.o armv4-mont.o armv4-gf2m.o::aes_cbc.o aes-armv4.o:::sha1-armv4-large.o sha256-armv4.o sha512-armv4.o:::::::ghash-armv4.o::ios32:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
+"ios64-cross","cc:-O3 -arch arm64 -mios-version-min=7.0.0 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:SIXTY_FOUR_BIT_LONG RC4_CHAR -RC4_CHUNK DES_INT DES_UNROLL -BF_PTR:${aarch64_asm}:ios64:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
 
 ##### A/UX
 "aux3-gcc","gcc:-O2 -DTERMIO::(unknown):AUX:-lbsd:RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:::",
@@ -596,6 +616,7 @@ my %table=(
 ##### VxWorks for various targets
 "vxworks-ppc60x","ccppc:-D_REENTRANT -mrtp -mhard-float -mstrict-align -fno-implicit-fp -DPPC32_fp60x -O2 -fstrength-reduce -fno-builtin -fno-strict-aliasing -Wall -DCPU=PPC32 -DTOOL_FAMILY=gnu -DTOOL=gnu -I\$(WIND_BASE)/target/usr/h -I\$(WIND_BASE)/target/usr/h/wrn/coreip:::VXWORKS:-Wl,--defsym,__wrs_rtp_base=0xe0000000 -L \$(WIND_BASE)/target/usr/lib/ppc/PPC32/common:::::",
 "vxworks-ppcgen","ccppc:-D_REENTRANT -mrtp -msoft-float -mstrict-align -O1 -fno-builtin -fno-strict-aliasing -Wall -DCPU=PPC32 -DTOOL_FAMILY=gnu -DTOOL=gnu -I\$(WIND_BASE)/target/usr/h -I\$(WIND_BASE)/target/usr/h/wrn/coreip:::VXWORKS:-Wl,--defsym,__wrs_rtp_base=0xe0000000 -L \$(WIND_BASE)/target/usr/lib/ppc/PPC32/sfcommon:::::",
+"vxworks-ppcgen-kernel","ccppc:-D_REENTRANT -msoft-float -mstrict-align -O1 -fno-builtin -fno-strict-aliasing -Wall -DCPU=PPC32 -DTOOL_FAMILY=gnu -DTOOL=gnu -I\$(WIND_BASE)/target/h -I\$(WIND_BASE)/target/h/wrn/coreip:::VXWORKS::::::",
 "vxworks-ppc405","ccppc:-g -msoft-float -mlongcall -DCPU=PPC405 -I\$(WIND_BASE)/target/h:::VXWORKS:-r:::::",
 "vxworks-ppc750","ccppc:-ansi -nostdinc -DPPC750 -D_REENTRANT -fvolatile -fno-builtin -fno-for-scope -fsigned-char -Wall -msoft-float -mlongcall -DCPU=PPC604 -I\$(WIND_BASE)/target/h \$(DEBUG_FLAG):::VXWORKS:-r:::::",
 "vxworks-ppc750-debug","ccppc:-ansi -nostdinc -DPPC750 -D_REENTRANT -fvolatile -fno-builtin -fno-for-scope -fsigned-char -Wall -msoft-float -mlongcall -DCPU=PPC604 -I\$(WIND_BASE)/target/h -DBN_DEBUG -DREF_CHECK -DCONF_DEBUG -DBN_CTX_DEBUG -DCRYPTO_MDEBUG -DPEDANTIC -DDEBUG_SAFESTACK -DDEBUG -g:::VXWORKS:-r:::::",
@@ -610,12 +631,14 @@ my %table=(
 "uClinux-dist","$ENV{'CC'}:\$(CFLAGS)::-D_REENTRANT::\$(LDFLAGS) \$(LDLIBS):BN_LLONG:${no_asm}:$ENV{'LIBSSL_dlfcn'}:linux-shared:-fPIC:-shared:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):$ENV{'RANLIB'}::",
 "uClinux-dist64","$ENV{'CC'}:\$(CFLAGS)::-D_REENTRANT::\$(LDFLAGS) \$(LDLIBS):SIXTY_FOUR_BIT_LONG:${no_asm}:$ENV{'LIBSSL_dlfcn'}:linux-shared:-fPIC:-shared:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):$ENV{'RANLIB'}::",
 
+"c64xplus","cl6x:-mv6400+ -o2 -ox -ms -pden -DNO_SYS_TYPES_H -DGETPID_IS_MEANINGLESS -DMD32_REG_T=int -DOPENSSL_SMALL_FOOTPRINT:<c6x.h>::DSPBIOS::BN_LLONG:c64xpluscpuid.o:bn-c64xplus.o c64xplus-gf2m.o::aes-c64xplus.o aes_cbc.o aes_ctr.o:::sha1-c64xplus.o sha256-c64xplus.o sha512-c64xplus.o:::::::ghash-c64xplus.o::void:",
+
 );
 
 my @MK1MF_Builds=qw(VC-WIN64I VC-WIN64A
 		    debug-VC-WIN64I debug-VC-WIN64A
 		    VC-NT VC-CE VC-WIN32 debug-VC-WIN32
-		    BC-32 
+		    BC-32 c64xplus
 		    netware-clib netware-clib-bsdsock
 		    netware-libc netware-libc-bsdsock);
 
@@ -1556,7 +1579,7 @@ if ($rmd160_obj =~ /\.o$/)
 	}
 if ($aes_obj =~ /\.o$/)
 	{
-	$cflags.=" -DAES_ASM";
+	 $cflags.=" -DAES_ASM" if ($aes_obj =~ m/\baes\-/);
 	# aes_ctr.o is not a real file, only indication that assembler
 	# module implements AES_ctr32_encrypt...
 	$cflags.=" -DAES_CTR_ASM" if ($aes_obj =~ s/\s*aes_ctr\.o//);
@@ -1577,7 +1600,7 @@ else	{
 	$wp_obj="wp_block.o";
 	}
 $cmll_obj=$cmll_enc	unless ($cmll_obj =~ /.o$/);
-if ($modes_obj =~ /ghash/)
+if ($modes_obj =~ /ghash\-/)
 	{
 	$cflags.=" -DGHASH_ASM";
 	}

Makefile.fips

@@ -186,7 +186,7 @@ SHARED_LDFLAGS=
 GENERAL=        Makefile
 BASENAME=       openssl
 NAME=           $(BASENAME)-$(VERSION)
-TARFILE=        openssl-fips-2.0-test.tar
+TARFILE=        openssl-fips-2.0.tar
 WTARFILE=       $(NAME)-win.tar
 EXHEADER=       e_os2.h
 HEADER=         e_os.h

TABLE

@@ -862,7 +862,7 @@ $multilib     =
 $cc           = cc
 $cflags       = -q32 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst
 $unistd       = 
-$thread_cflag = -qthreaded
+$thread_cflag = -qthreaded -D_THREAD_SAFE
 $sys_id       = AIX
 $lflags       = 
 $bn_ops       = BN_LLONG RC4_CHAR
@@ -961,7 +961,7 @@ $multilib     =
 $cc           = cc
 $cflags       = -q64 -O -DB_ENDIAN -qmaxmem=16384 -qro -qroconst
 $unistd       = 
-$thread_cflag = -qthreaded
+$thread_cflag = -qthreaded -D_THREAD_SAFE
 $sys_id       = AIX
 $lflags       = 
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR
@@ -3465,8 +3465,42 @@ $ranlib       =
 $arflags      = 
 $multilib     = 
 
+*** ios64-cross
+$cc           = cc
+$cflags       = -O3 -arch arm64 -mios-version-min=7.0.0 -isysroot $(CROSS_TOP)/SDKs/$(CROSS_SDK) -fno-common
+$unistd       = 
+$thread_cflag = -D_REENTRANT
+$sys_id       = iOS
+$lflags       = -Wl,-search_paths_first%
+$bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR -RC4_CHUNK DES_INT DES_UNROLL -BF_PTR
+$cpuid_obj    = 
+$bn_obj       = 
+$ec_obj       = 
+$des_obj      = 
+$aes_obj      = 
+$bf_obj       = 
+$md5_obj      = 
+$sha1_obj     = 
+$cast_obj     = 
+$rc4_obj      = 
+$rmd160_obj   = 
+$rc5_obj      = 
+$wp_obj       = 
+$cmll_obj     = 
+$modes_obj    = 
+$engines_obj  = 
+$perlasm_scheme = void
+$dso_scheme   = dlfcn
+$shared_target= darwin-shared
+$shared_cflag = -fPIC -fno-common
+$shared_ldflag = -dynamiclib
+$shared_extension = .$(SHLIB_MAJOR).$(SHLIB_MINOR).dylib
+$ranlib       = 
+$arflags      = 
+$multilib     = 
+
 *** iphoneos-cross
-$cc           = llvm-gcc
+$cc           = cc
 $cflags       = -O3 -isysroot $(CROSS_TOP)/SDKs/$(CROSS_SDK) -fomit-frame-pointer -fno-common
 $unistd       = 
 $thread_cflag = -D_REENTRANT

c6x/do_fips

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+perl Configure c64xplus fipscanisteronly no-engine
+perl util/mkfiles.pl > MINFO
+perl util/mk1mf.pl auto > c6x/fips.mak
+make -f c6x/fips.mak
+make -f c6x/fips_algvs.mak

c6x/env

@@ -0,0 +1,7 @@
+# MSYS-style PATH
+export PATH=/c/CCStudio_v3.3/c6000/cgtools/bin:/c/Program\ Files/ActivePerl58/bin:$PATH
+
+# Windows-style variables
+export C6X_C_DIR='C:\CCStudio_v3.3\c6000\cgtools\include;C:\CCStudio_v3.3\c6000\cgtools\lib'
+
+export PERL5LIB=C:/CCStudio_v3.3/bin/utilities/ccs_scripting

c6x/fips_standalone_sha1

@@ -0,0 +1,32 @@
+#!/usr/bin/env perl
+#
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+
+unshift(@INC,$dir);
+require "hmac_sha1.pl";
+
+(!@ARV[0] && -f @ARGV[$#ARGV]) || die "usage: $0 [-verify] file";
+
+$verify=shift	if (@ARGV[0] eq "-verify");
+
+sysopen(FD,@ARGV[0],0) || die "$!";
+binmode(FD);
+
+my $ctx = HMAC->Init("etaonrishdlcupfm");
+
+while (read(FD,$blob,4*1024)) { $ctx->Update($blob); }
+
+close(FD);
+
+my $signature = unpack("H*",$ctx->Final());
+
+print "HMAC-SHA1(@ARGV[0])= $signature\n";
+
+if ($verify) {
+	open(FD,"<@ARGV[0].sha1") || die "$!";
+	$line = <FD>;
+	close(FD);
+	exit(0)	if ($line =~ /HMAC\-SHA1\([^\)]*\)=\s*([0-9a-f]+)/i &&
+				$1 eq $signature);
+	die "signature mismatch";
+}

c6x/fipscanister.cmd

@@ -0,0 +1,19 @@
+SECTIONS
+{
+    .text:
+    {
+	*(.fips_text:start)
+	*(.text)
+	*(.const:aes_asm)
+	*(.const:sha_asm)
+	*(.const:des_sptrans)
+	*(.switch)
+	*(.fips_text:end)
+    }
+    .const:
+    {
+	*(.fips_const:start)
+	*(.const)
+	*(.fips_const:end)
+    }
+}

c6x/hmac_sha1.pl

@@ -0,0 +1,196 @@
+#!/usr/bin/env perl
+#
+# Copyright (c) 2011 The OpenSSL Project.
+#
+######################################################################
+#
+# SHA1 and HMAC in Perl by <appro@openssl.org>.
+#
+{ package SHA1;
+  use integer;
+
+    {
+    ################################### SHA1 block code generator
+    my @V = ('$A','$B','$C','$D','$E');
+    my $i;
+
+    sub XUpdate {
+      my $ret;
+	$ret="(\$T=\$W[($i-16)%16]^\$W[($i-14)%16]^\$W[($i-8)%16]^\$W[($i-3)%16],\n\t";
+	if ((1<<31)<<1) {
+	    $ret.="    \$W[$i%16]=((\$T<<1)|(\$T>>31))&0xffffffff)\n\t  ";
+	} else {
+	    $ret.="    \$W[$i%16]=(\$T<<1)|((\$T>>31)&1))\n\t  ";
+	}
+    }
+    sub tail {
+      my ($a,$b,$c,$d,$e)=@V;
+      my $ret;
+	if ((1<<31)<<1) {
+	    $ret.="(($a<<5)|($a>>27));\n\t";
+	    $ret.="$b=($b<<30)|($b>>2);	$e&=0xffffffff;	#$b&=0xffffffff;\n\t";
+	} else {
+	    $ret.="(($a<<5)|($a>>27)&0x1f);\n\t";
+	    $ret.="$b=($b<<30)|($b>>2)&0x3fffffff;\n\t";
+	}
+      $ret;
+    }
+    sub BODY_00_15 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=\$W[$i]+0x5a827999+((($c^$d)&$b)^$d)+".tail();
+    }
+    sub BODY_16_19 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x5a827999+((($c^$d)&$b)^$d)+".tail();
+    }
+    sub BODY_20_39 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x6ed9eba1+($b^$c^$d)+".tail();
+    }
+    sub BODY_40_59 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x8f1bbcdc+(($b&$c)|(($b|$c)&$d))+".tail();
+    }
+    sub BODY_60_79 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0xca62c1d6+($b^$c^$d)+".tail();
+    }
+
+    my $sha1_impl =
+    'sub block {
+	my $self = @_[0];
+	my @W    = unpack("N16",@_[1]);
+	my ($A,$B,$C,$D,$E,$T) = @{$self->{H}};
+	';
+
+	$sha1_impl.='
+	$A &= 0xffffffff;
+	$B &= 0xffffffff;
+	' if ((1<<31)<<1);
+
+	for($i=0;$i<16;$i++){ $sha1_impl.=BODY_00_15(); unshift(@V,pop(@V)); }
+	for(;$i<20;$i++)    { $sha1_impl.=BODY_16_19(); unshift(@V,pop(@V)); }
+	for(;$i<40;$i++)    { $sha1_impl.=BODY_20_39(); unshift(@V,pop(@V)); }
+	for(;$i<60;$i++)    { $sha1_impl.=BODY_40_59(); unshift(@V,pop(@V)); }
+	for(;$i<80;$i++)    { $sha1_impl.=BODY_60_79(); unshift(@V,pop(@V)); }
+
+	$sha1_impl.='
+	$self->{H}[0]+=$A;	$self->{H}[1]+=$B;	$self->{H}[2]+=$C;
+	$self->{H}[3]+=$D;	$self->{H}[4]+=$E;	}';
+
+    #print $sha1_impl,"\n";
+    eval($sha1_impl);		# generate code
+    }
+
+    sub Init {
+	my $class = shift;	# multiple instances...
+	my $self  = {};
+
+	bless $self,$class;
+	$self->{H} = [0x67452301,0xefcdab89,0x98badcfe,0x10325476,0xc3d2e1f0];
+	$self->{N} = 0;
+	return $self;
+    }
+
+    sub Update {
+	my $self = shift;
+	my $msg;
+
+	foreach $msg (@_) {
+	    my $len  = length($msg);
+	    my $num  = length($self->{buf});
+	    my $off  = 0;
+
+	    $self->{N} += $len;
+
+	    if (($num+$len)<64)
+	    {	$self->{buf} .= $msg; next;	}
+	    elsif ($num)
+	    {	$self->{buf} .= substr($msg,0,($off=64-$num));
+		$self->block($self->{buf});
+	    }
+
+	    while(($off+64) <= $len)
+	    {	$self->block(substr($msg,$off,64));
+		$off += 64;
+	    }
+
+	    $self->{buf} = substr($msg,$off);
+	}
+	return $self;
+    }
+
+    sub Final {
+	my $self = shift;
+	my $num  = length($self->{buf});
+
+	$self->{buf} .= chr(0x80); $num++;
+	if ($num>56)
+	{   $self->{buf} .= chr(0)x(64-$num);
+	    $self->block($self->{buf});
+	    $self->{buf}=undef;
+	    $num=0;
+	}
+	$self->{buf} .= chr(0)x(56-$num);
+	$self->{buf} .= pack("N2",($self->{N}>>29)&0x7,$self->{N}<<3);
+	$self->block($self->{buf});
+
+	return pack("N*",@{$self->{H}});
+    }
+
+    sub Selftest {
+	my $hash;
+
+	$hash=SHA1->Init()->Update('abc')->Final();
+	die "SHA1 test#1" if (unpack("H*",$hash) ne 'a9993e364706816aba3e25717850c26c9cd0d89d');
+
+	$hash=SHA1->Init()->Update('abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq')->Final();
+	die "SHA1 test#2" if (unpack("H*",$hash) ne '84983e441c3bd26ebaae4aa1f95129e5e54670f1');
+
+	#$hash=SHA1->Init()->Update('a'x1000000)->Final();
+	#die "SHA1 test#3" if (unpack("H*",$hash) ne '34aa973cd4c4daa4f61eeb2bdbad27316534016f');
+    }
+}
+
+{ package HMAC;
+
+    sub Init {
+	my $class = shift;
+	my $key   = shift;
+	my $self  = {};
+
+	bless $self,$class;
+
+	if (length($key)>64) {
+	    $key = SHA1->Init()->Update($key)->Final();
+	}
+	$key .= chr(0x00)x(64-length($key));
+
+	my @ikey = map($_^=0x36,unpack("C*",$key));
+	($self->{hash} = SHA1->Init())->Update(pack("C*",@ikey));
+	 $self->{okey} = pack("C*",map($_^=0x36^0x5c,@ikey));
+
+	return $self;
+    }
+
+    sub Update {
+	my $self = shift;
+	$self->{hash}->Update(@_);
+	return $self;
+    }
+
+    sub Final {
+	my $self  = shift;
+	my $ihash = $self->{hash}->Final();
+	return SHA1->Init()->Update($self->{okey},$ihash)->Final();
+    }
+
+    sub Selftest {
+	my $hmac;
+
+	$hmac = HMAC->Init('0123456789:;<=>?@ABC')->Update('Sample #2')->Final();
+	die "HMAC test" if (unpack("H*",$hmac) ne '0922d3405faa3d194f82a45830737d5cc6c75d24');
+    }
+}
+
+1;

c6x/incore6x

@@ -0,0 +1,241 @@
+#!/usr/bin/env perl
+#
+# Copyright (c) 2011 The OpenSSL Project.
+#
+# The script embeds fingerprint into TI-COFF executable object.
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+
+unshift(@INC,$dir);
+require "hmac_sha1.pl";
+
+######################################################################
+#
+# COFF symbol table parser by <appro@openssl.org>. The table entries
+# are extended with offset within executable file...
+#
+{ package COFF;
+  use FileHandle;
+
+    sub dup  { my %copy=map {$_} @_; return \%copy; }
+
+    sub Load {
+	my $class = shift;
+	my $self  = {};
+	my $FD    = FileHandle->new();	# autoclose
+
+	bless $self,$class;
+
+	sysopen($FD,shift,0) or die "$!";
+	binmode($FD);
+
+	#################################################
+	# read and parse COFF header...
+	#
+	read($FD,my $coff,22) or die "$!";
+
+	my %coff_header;
+	@coff_header{version,nsects,date,syms_off,nsyms,opt,flags,magic}=
+		unpack("v2V3v3",$coff);
+
+	$!=42;		# signal fipsld to revert to two-step link
+	die "not TI-COFF file" if ($coff_header{version} != 0xC2);
+
+	my $big_endian = ($coff_header{flags}>>9)&1;	# 0 or 1
+
+	my $strings;
+	my $symsize;
+
+	#################################################
+	# load strings table
+	#
+	seek($FD,$coff_header{syms_off}+18*$coff_header{nsyms},0) or die "$!";
+	read($FD,$strings,4) or die "$!";
+	$symsize = unpack("V",$strings);
+	read($FD,$strings,$symsize,4) or die "$!";
+
+	#################################################
+	# read sections
+	#
+	my $i;
+	my @sections;
+
+	# seek to section headers
+	seek($FD,22+@coff_header{opt},0) or die "$!";
+	for ($i=0;$i<$coff_header{nsects};$i++) {
+	    my %coff_shdr;
+	    my $name;
+
+	    read($FD,my $section,48) or die "$!";
+
+	    @coff_shdr{sh_name,sh_phaddr,sh_vaddr,
+			sh_size,sh_offset,sh_relocs,sh_reserved,
+			sh_relocoff,sh_lines,sh_flags} =
+		unpack("a8V9",$section);
+
+	    $name = $coff_shdr{sh_name};
+	    # see if sh_name is a an offset in $strings
+	    my ($hi,$lo) = unpack("V2",$name);
+	    if ($hi==0 && $lo<$symsize) {
+		$name = substr($strings,$lo,64);
+	    }
+	    $coff_shdr{sh_name} = (split(chr(0),$name))[0];
+
+	    push(@sections,dup(%coff_shdr));
+	}
+
+	#################################################
+	# load symbols table
+	#
+	seek($FD,$coff_header{syms_off},0) or die "$!";
+	for ($i=0;$i<$coff_header{nsyms};$i++) {
+	    my %coff_sym;
+	    my $name;
+
+	    read($FD,my $blob,18) or die "$!";
+
+	    @coff_sym{st_name,st_value,st_shndx,reserved,class,aux} =
+		unpack("a8Vv2C2",$blob);
+
+	    # skip aux entries
+	    if ($coff_sym{aux}) {
+		seek($FD,18*$coff_sym{aux},1) or die "$!";
+		$i+=$coff_sym{aux};
+	    }
+
+	    $name = $coff_sym{st_name};
+	    # see if st_name is a an offset in $strings
+	    my ($hi,$lo) = unpack("V2",$name);
+	    if ($hi==0 && $lo<$symsize) {
+		$name = substr($strings,$lo,64);
+	    }
+	    $coff_sym{st_name} = $name = (split(chr(0),$name))[0];
+
+	    my $st_secn = $coff_sym{st_shndx}-1;
+	    if ($st_secn>=0 && $st_secn<=$#sections
+		&& @sections[$st_secn]->{sh_offset}
+		&& $name =~ m/^_[a-z]+/i) {
+		# synthesize st_offset, ...
+		$coff_sym{st_offset} = $coff_sym{st_value}
+				- @sections[$st_secn]->{sh_vaddr}
+				+ @sections[$st_secn]->{sh_offset};
+		$coff_sym{st_section} = @sections[$st_secn]->{sh_name};
+		# ... and add to lookup table
+		$self->{symbols}{$name} = dup(%coff_sym);
+	    }
+	}
+
+	return $self;
+    }
+
+    sub Lookup {
+	my $self = shift;
+	my $name = shift;
+	return $self->{symbols}{"_$name"};
+    }
+
+    sub Traverse {
+	my $self = shift;
+	my $code = shift;
+
+	if (ref($code) eq 'CODE') {
+	    for (keys(%{$self->{symbols}})) { &$code($self->{symbols}{$_}); }
+	}
+    }
+}
+
+######################################################################
+#
+# main()
+#
+my $legacy_mode;
+
+if ($#ARGV<0 || ($#ARGV>0 && !($legacy_mode=(@ARGV[0] =~ /^\-(dso|exe)$/)))) {
+	print STDERR "usage: $0 [-dso|-exe] ti-coff-binary\n";
+	exit(1);
+}
+
+$exe = COFF->Load(@ARGV[$#ARGV]);
+
+$FIPS_text_start	= $exe->Lookup("FIPS_text_start")		or die;
+$FIPS_text_end		= $exe->Lookup("FIPS_text_end")			or die;
+$FIPS_rodata_start	= $exe->Lookup("FIPS_rodata_start")		or die;
+$FIPS_rodata_end	= $exe->Lookup("FIPS_rodata_end")		or die;
+$FIPS_signature		= $exe->Lookup("FIPS_signature")		or die;
+
+# new cross-compile support
+$FIPS_text_startX	= $exe->Lookup("FIPS_text_startX");
+$FIPS_text_endX		= $exe->Lookup("FIPS_text_endX");
+
+if (!$legacy_mode) {
+    if (!$FIPS_text_startX || !$FIPS_text_endX) {
+	print STDERR "@ARGV[$#ARGV] is not cross-compiler aware.\n";
+	exit(42);	# signal fipsld to revert to two-step link
+    }
+
+    $FINGERPRINT_ascii_value
+			= $exe->Lookup("FINGERPRINT_ascii_value");
+}
+if ($FIPS_text_startX && $FIPS_text_endX) {
+    $FIPS_text_start = $FIPS_text_startX;
+    $FIPS_text_end   = $FIPS_text_endX;
+}
+
+sysopen(FD,@ARGV[$#ARGV],$legacy_mode?0:2) or die "$!";	# 2 is read/write
+binmode(FD);
+
+sub HMAC_Update {
+  my ($hmac,$off,$len) = @_;
+  my $blob;
+
+    seek(FD,$off,0)	or die "$!";
+    read(FD,$blob,$len)	or die "$!";
+    $$hmac->Update($blob);
+}
+
+# fips/fips.c:FIPS_incore_fingerprint's Perl twin
+#
+sub FIPS_incore_fingerprint {
+  my $p1  = $FIPS_text_start->{st_offset};
+  my $p2  = $FIPS_text_end->{st_offset};
+  my $p3  = $FIPS_rodata_start->{st_offset};
+  my $p4  = $FIPS_rodata_end->{st_offset};
+  my $sig = $FIPS_signature->{st_offset};
+  my $ctx = HMAC->Init("etaonrishdlcupfm");
+
+    # detect overlapping regions
+    if ($p1<=$p3 && $p2>=$p3) {
+	$p3 = $p1; $p4 = $p2>$p4?$p2:$p4; $p1 = 0; $p2 = 0;
+    } elsif ($p3<=$p1 && $p4>=$p1) {
+	$p3 = $p3; $p4 = $p2>$p4?$p2:$p4; $p1 = 0; $p2 = 0;
+    }
+
+    if ($p1) {
+	HMAC_Update (\$ctx,$p1,$p2-$p1);
+    }
+
+    if ($sig>=$p3 && $sig<$p4) {
+	# "punch" hole
+	HMAC_Update(\$ctx,$p3,$sig-$p3);
+	$p3 = $sig+20;
+	HMAC_Update(\$ctx,$p3,$p4-$p3);
+    } else {
+	HMAC_Update(\$ctx,$p3,$p4-$p3);
+    }
+
+    return $ctx->Final();
+}
+
+$fingerprint = FIPS_incore_fingerprint();
+
+if ($legacy_mode) {
+    print unpack("H*",$fingerprint);
+} elsif ($FINGERPRINT_ascii_value) {
+    seek(FD,$FINGERPRINT_ascii_value->{st_offset},0)	or die "$!";
+    print FD unpack("H*",$fingerprint)			or die "$!";
+} else {
+    seek(FD,$FIPS_signature->{st_offset},0)		or die "$!";
+    print FD $fingerprint				or die "$!";
+}
+
+close (FD);

c6x/run6x

@@ -0,0 +1,43 @@
+#!/usr/bin/env perl
+
+$exe  = @ARGV[0];
+$exe .= ".out" if (! -f $exe);
+die if (! -f $exe);
+
+use CCS_SCRIPTING_PERL;
+
+my $studio=new CCS_SCRIPTING_PERL::CCS_Scripting();
+
+$studio->CCSOpenNamed("*","*",1);	# connect to board
+$studio->TargetReset();
+
+print "loading $exe\n";
+$studio->ProgramLoad($exe);
+
+sub write_string {
+    my ($studio,$addr,$str) = @_;
+    my $len = length($str);
+    my $i;
+
+    for ($i=0; $i<$len; $i++) {
+	$studio->MemoryWrite($CCS_SCRIPTING_PERL::PAGE_DATA,$addr+$i,8,vec($str,$i,8));
+    }
+    $studio->MemoryWrite($CCS_SCRIPTING_PERL::PAGE_DATA,$addr+$i,8,0);
+
+    return $i+1;
+}
+
+$addr= $studio->SymbolGetAddress("__c_args");
+printf "setting up __c_args at 0x%X\n",$addr;#\n";
+
+$studio->MemoryWrite($CCS_SCRIPTING_PERL::PAGE_DATA,$addr,32,$#ARGV+1);
+
+for ($i=0,$strings=$addr+($#ARGV+3)*4; $i<=$#ARGV; $i++) {
+    $off = write_string($studio,$strings,@ARGV[$i]);
+    $studio->MemoryWrite($CCS_SCRIPTING_PERL::PAGE_DATA,$addr+4*($i+1),32,$strings);
+    $strings += $off;
+}
+$studio->MemoryWrite($SCC_SCRIPTING_PERL::PAGE_DATA,$addr+4*($i+1),32,0);
+
+print "running...\n";
+$studio->TargetRun();

config

@@ -219,7 +219,11 @@ case "${SYSTEM}:${RELEASE}:${VERSION}:${MACHINE}" in
 	;;
 
     NetBSD:*:*:*386*)
-        echo "`(/usr/sbin/sysctl -n hw.model || /sbin/sysctl -n hw.model) | sed 's,.*\(.\)86-class.*,i\186,'`-whatever-netbsd"; exit 0
+	if [ -z ${CROSS_COMPILE} ]; then
+           echo "`(/usr/sbin/sysctl -n hw.model || /sbin/sysctl -n hw.model) | sed 's,.*\(.\)86-class.*,i\186,'`-whatever-netbsd"; exit 0
+        else
+           echo "${MACHINE}-whatever-netbsd"; exit 0
+	fi
 	;;
 
     NetBSD:*)
@@ -371,6 +375,10 @@ case "${SYSTEM}:${RELEASE}:${VERSION}:${MACHINE}" in
        echo "nsr-tandem-nsk"; exit 0;
        ;;
 
+    vxworks:kernel*)
+       echo "${MACHINE}-kernel-vxworks"; exit 0;
+       ;;
+
     vxworks*)
        echo "${MACHINE}-whatever-vxworks"; exit 0;
        ;;
@@ -572,6 +580,10 @@ case "$GUESSOS" in
   *-*-iphoneos)
 	options="$options -arch%20${MACHINE}"
 	OUT="iphoneos-cross" ;;
+  armv7-*-ios)
+	OUT="ios-cross" ;;
+  arm64-*-ios*)
+	OUT="ios64-cross" ;;
   alpha-*-linux2)
         ISA=`awk '/cpu model/{print$4;exit(0);}' /proc/cpuinfo`
 	case ${ISA:-generic} in
@@ -597,6 +609,7 @@ case "$GUESSOS" in
 	;;
   ppc-*-linux2) OUT="linux-ppc" ;;
   ppc60x-*-vxworks*) OUT="vxworks-ppc60x" ;;
+  ppcgen-kernel-vxworks*) OUT="vxworks-ppcgen-kernel" ;;
   ppcgen-*-vxworks*) OUT="vxworks-ppcgen" ;;
   pentium-*-vxworks*) OUT="vxworks-pentium" ;;
   simlinux-*-vxworks*) OUT="vxworks-simlinux" ;;
@@ -734,17 +747,23 @@ case "$GUESSOS" in
   sparc64-*-*bsd*)	OUT="BSD-sparc64" ;;
   ia64-*-*bsd*)		OUT="BSD-ia64" ;;
   amd64-*-*bsd*)	OUT="BSD-x86_64" ;;
-  *86*-*-*bsd*)		# mimic ld behaviour when it's looking for libc...
-			if [ -L /usr/lib/libc.so ]; then	# [Free|Net]BSD
-			    libc=/usr/lib/libc.so
-			else					# OpenBSD
-			    # ld searches for highest libc.so.* and so do we
-			    libc=`(ls /usr/lib/libc.so.* | tail -1) 2>/dev/null`
-			fi
-			case "`(file -L $libc) 2>/dev/null`" in
-			*ELF*)	OUT="BSD-x86-elf" ;;
-			*)	OUT="BSD-x86"; options="$options no-sse2" ;;
-			esac ;;
+  *86*-*-*bsd*)		if [ -z ${CROSS_COMPILE} ]; then 
+			   # mimic ld behaviour when it's looking for libc...
+			   if [ -L /usr/lib/libc.so ]; then	# [Free|Net]BSD
+			       libc=/usr/lib/libc.so
+			   else					# OpenBSD
+			       # ld searches for highest libc.so.* and so do we
+			       libc=`(ls /usr/lib/libc.so.* | tail -1) 2>/dev/null`
+			   fi
+			   echo "libc = $libc"
+			   case "`(file -L $libc) 2>/dev/null`" in
+			   *ELF*)	OUT="BSD-x86-elf" ;;
+			   *)	OUT="BSD-x86"; options="$options no-sse2" ;;
+			  esac 
+			else
+			   OUT="BSD-x86-elf"
+			fi;;
+  ppc85xx-*-*bsd*)      OUT="BSD-ppc85xx" ;;  # MPC85XX has no hardware FP accelerator
   *-*-*bsd*)		OUT="BSD-generic32" ;;
 
   *-*-osf)		OUT="osf1-alpha-cc" ;;
@@ -842,6 +861,7 @@ case "$GUESSOS" in
   *-*-qnx6) OUT="QNX6" ;;
   x86-*-android|i?86-*-android) OUT="android-x86" ;;
   armv[7-9]*-*-android) OUT="android-armv7" ;;
+  aarch64-*-android) OUT="android64-aarch64" ;;
   *) OUT=`echo $GUESSOS | awk -F- '{print $3}'`;;
 esac
 

crypto/Makefile

@@ -87,6 +87,7 @@ ppccpuid.s:	ppccpuid.pl;	$(PERL) ppccpuid.pl $(PERLASM_SCHEME) $@
 pariscid.s:	pariscid.pl;	$(PERL) pariscid.pl $(PERLASM_SCHEME) $@
 alphacpuid.s:	alphacpuid.pl
 	$(PERL) $< | $(CC) -E - | tee $@ > /dev/null
+arm64cpuid.S:	arm64cpuid.pl;	$(PERL) arm64cpuid.pl $(PERLASM_SCHEME) > $@
 
 subdirs:
 	@target=all; $(RECURSIVE_MAKE)

crypto/aes/Makefile

@@ -78,6 +78,10 @@ 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

crypto/aes/asm/aes-armv4.pl

@@ -32,8 +32,20 @@
 # Profiler-assisted and platform-specific optimization resulted in 16%
 # improvement on Cortex A8 core and ~21.5 cycles per byte.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $s0="r0";
 $s1="r1";
@@ -171,7 +183,12 @@ AES_encrypt:
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	$rounds,r0		@ inp
 	mov	$key,r2
+#ifdef	__APPLE__
+	mov	$tbl,#AES_encrypt-AES_Te
+	sub	$tbl,r3,$tbl			@ Te
+#else
 	sub	$tbl,r3,#AES_encrypt-AES_Te	@ Te
+#endif
 #if __ARM_ARCH__<7
 	ldrb	$s0,[$rounds,#3]	@ load input data in endian-neutral
 	ldrb	$t1,[$rounds,#2]	@ manner...
@@ -425,7 +442,12 @@ AES_set_encrypt_key:
 	bne	.Labrt
 
 .Lok:	stmdb   sp!,{r4-r12,lr}
+#ifdef	__APPLE__
+	mov	$tbl,#AES_set_encrypt_key-AES_Te-1024
+	sub	$tbl,r3,$tbl					@ Te4
+#else
 	sub	$tbl,r3,#AES_set_encrypt_key-AES_Te-1024	@ Te4
+#endif
 
 	mov	$rounds,r0		@ inp
 	mov	lr,r1			@ bits
@@ -886,7 +908,12 @@ AES_decrypt:
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	$rounds,r0		@ inp
 	mov	$key,r2
+#ifdef	__APPLE__
+	mov	$tbl,#AES_decrypt-AES_Td
+	sub	$tbl,r3,$tbl				@ Td
+#else
 	sub	$tbl,r3,#AES_decrypt-AES_Td		@ Td
+#endif
 #if __ARM_ARCH__<7
 	ldrb	$s0,[$rounds,#3]	@ load input data in endian-neutral
 	ldrb	$t1,[$rounds,#2]	@ manner...

crypto/aes/asm/aesv8-armx.pl

@@ -0,0 +1,968 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# This module implements support for ARMv8 AES instructions. The
+# module is endian-agnostic in sense that it supports both big- and
+# little-endian cases. As does it support both 32- and 64-bit modes
+# of operation. Latter is achieved by limiting amount of utilized
+# registers to 16, which implies additional NEON load and integer
+# instructions. This has no effect on mighty Apple A7, where results
+# are literally equal to the theoretical estimates based on AES
+# instruction latencies and issue rates. On Cortex-A53, an in-order
+# execution core, this costs up to 10-15%, which is partially
+# compensated by implementing dedicated code path for 128-bit
+# CBC encrypt case. On Cortex-A57 parallelizable mode performance
+# seems to be limited by sheer amount of NEON instructions...
+#
+# Performance in cycles per byte processed with 128-bit key:
+#
+#		CBC enc		CBC dec		CTR
+# Apple A7	2.39		1.20		1.20
+# Cortex-A53	2.45		1.87		1.94
+# Cortex-A57	3.64		1.34		1.32
+
+$flavour = shift;
+$output  = shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
+
+$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 ($flavour !~ /64/);
+
+# Assembler mnemonics are an eclectic mix of 32- and 64-bit syntax,
+# NEON is mostly 32-bit mnemonics, integer - mostly 64. Goal is to
+# maintain both 32- and 64-bit codes within single module and
+# transliterate common code to either flavour with regex vodoo.
+#
+{{{
+my ($inp,$bits,$out,$ptr,$rounds)=("x0","w1","x2","x3","w12");
+my ($zero,$rcon,$mask,$in0,$in1,$tmp,$key)=
+	$flavour=~/64/? map("q$_",(0..6)) : map("q$_",(0..3,8..10));
+
+
+$code.=<<___;
+.align	5
+.Lrcon:
+.long	0x01,0x01,0x01,0x01
+.long	0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d	// rotate-n-splat
+.long	0x1b,0x1b,0x1b,0x1b
+
+.globl	${prefix}_set_encrypt_key
+.type	${prefix}_set_encrypt_key,%function
+.align	5
+${prefix}_set_encrypt_key:
+.Lenc_key:
+___
+$code.=<<___	if ($flavour =~ /64/);
+	stp	x29,x30,[sp,#-16]!
+	add	x29,sp,#0
+___
+$code.=<<___;
+	mov	$ptr,#-1
+	cmp	$inp,#0
+	b.eq	.Lenc_key_abort
+	cmp	$out,#0
+	b.eq	.Lenc_key_abort
+	mov	$ptr,#-2
+	cmp	$bits,#128
+	b.lt	.Lenc_key_abort
+	cmp	$bits,#256
+	b.gt	.Lenc_key_abort
+	tst	$bits,#0x3f
+	b.ne	.Lenc_key_abort
+
+	adr	$ptr,.Lrcon
+	cmp	$bits,#192
+
+	veor	$zero,$zero,$zero
+	vld1.8	{$in0},[$inp],#16
+	mov	$bits,#8		// reuse $bits
+	vld1.32	{$rcon,$mask},[$ptr],#32
+
+	b.lt	.Loop128
+	b.eq	.L192
+	b	.L256
+
+.align	4
+.Loop128:
+	vtbl.8	$key,{$in0},$mask
+	vext.8	$tmp,$zero,$in0,#12
+	vst1.32	{$in0},[$out],#16
+	aese	$key,$zero
+	subs	$bits,$bits,#1
+
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	 veor	$key,$key,$rcon
+	veor	$in0,$in0,$tmp
+	vshl.u8	$rcon,$rcon,#1
+	veor	$in0,$in0,$key
+	b.ne	.Loop128
+
+	vld1.32	{$rcon},[$ptr]
+
+	vtbl.8	$key,{$in0},$mask
+	vext.8	$tmp,$zero,$in0,#12
+	vst1.32	{$in0},[$out],#16
+	aese	$key,$zero
+
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	 veor	$key,$key,$rcon
+	veor	$in0,$in0,$tmp
+	vshl.u8	$rcon,$rcon,#1
+	veor	$in0,$in0,$key
+
+	vtbl.8	$key,{$in0},$mask
+	vext.8	$tmp,$zero,$in0,#12
+	vst1.32	{$in0},[$out],#16
+	aese	$key,$zero
+
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	 veor	$key,$key,$rcon
+	veor	$in0,$in0,$tmp
+	veor	$in0,$in0,$key
+	vst1.32	{$in0},[$out]
+	add	$out,$out,#0x50
+
+	mov	$rounds,#10
+	b	.Ldone
+
+.align	4
+.L192:
+	vld1.8	{$in1},[$inp],#8
+	vmov.i8	$key,#8			// borrow $key
+	vst1.32	{$in0},[$out],#16
+	vsub.i8	$mask,$mask,$key	// adjust the mask
+
+.Loop192:
+	vtbl.8	$key,{$in1},$mask
+	vext.8	$tmp,$zero,$in0,#12
+	vst1.32	{$in1},[$out],#8
+	aese	$key,$zero
+	subs	$bits,$bits,#1
+
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+
+	vdup.32	$tmp,${in0}[3]
+	veor	$tmp,$tmp,$in1
+	 veor	$key,$key,$rcon
+	vext.8	$in1,$zero,$in1,#12
+	vshl.u8	$rcon,$rcon,#1
+	veor	$in1,$in1,$tmp
+	veor	$in0,$in0,$key
+	veor	$in1,$in1,$key
+	vst1.32	{$in0},[$out],#16
+	b.ne	.Loop192
+
+	mov	$rounds,#12
+	add	$out,$out,#0x20
+	b	.Ldone
+
+.align	4
+.L256:
+	vld1.8	{$in1},[$inp]
+	mov	$bits,#7
+	mov	$rounds,#14
+	vst1.32	{$in0},[$out],#16
+
+.Loop256:
+	vtbl.8	$key,{$in1},$mask
+	vext.8	$tmp,$zero,$in0,#12
+	vst1.32	{$in1},[$out],#16
+	aese	$key,$zero
+	subs	$bits,$bits,#1
+
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in0,$in0,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	 veor	$key,$key,$rcon
+	veor	$in0,$in0,$tmp
+	vshl.u8	$rcon,$rcon,#1
+	veor	$in0,$in0,$key
+	vst1.32	{$in0},[$out],#16
+	b.eq	.Ldone
+
+	vdup.32	$key,${in0}[3]		// just splat
+	vext.8	$tmp,$zero,$in1,#12
+	aese	$key,$zero
+
+	veor	$in1,$in1,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in1,$in1,$tmp
+	vext.8	$tmp,$zero,$tmp,#12
+	veor	$in1,$in1,$tmp
+
+	veor	$in1,$in1,$key
+	b	.Loop256
+
+.Ldone:
+	str	$rounds,[$out]
+	mov	$ptr,#0
+
+.Lenc_key_abort:
+	mov	x0,$ptr			// return value
+	`"ldr	x29,[sp],#16"		if ($flavour =~ /64/)`
+	ret
+.size	${prefix}_set_encrypt_key,.-${prefix}_set_encrypt_key
+
+.globl	${prefix}_set_decrypt_key
+.type	${prefix}_set_decrypt_key,%function
+.align	5
+${prefix}_set_decrypt_key:
+___
+$code.=<<___	if ($flavour =~ /64/);
+	stp	x29,x30,[sp,#-16]!
+	add	x29,sp,#0
+___
+$code.=<<___	if ($flavour !~ /64/);
+	stmdb	sp!,{r4,lr}
+___
+$code.=<<___;
+	bl	.Lenc_key
+
+	cmp	x0,#0
+	b.ne	.Ldec_key_abort
+
+	sub	$out,$out,#240		// restore original $out
+	mov	x4,#-16
+	add	$inp,$out,x12,lsl#4	// end of key schedule
+
+	vld1.32	{v0.16b},[$out]
+	vld1.32	{v1.16b},[$inp]
+	vst1.32	{v0.16b},[$inp],x4
+	vst1.32	{v1.16b},[$out],#16
+
+.Loop_imc:
+	vld1.32	{v0.16b},[$out]
+	vld1.32	{v1.16b},[$inp]
+	aesimc	v0.16b,v0.16b
+	aesimc	v1.16b,v1.16b
+	vst1.32	{v0.16b},[$inp],x4
+	vst1.32	{v1.16b},[$out],#16
+	cmp	$inp,$out
+	b.hi	.Loop_imc
+
+	vld1.32	{v0.16b},[$out]
+	aesimc	v0.16b,v0.16b
+	vst1.32	{v0.16b},[$inp]
+
+	eor	x0,x0,x0		// return value
+.Ldec_key_abort:
+___
+$code.=<<___	if ($flavour !~ /64/);
+	ldmia	sp!,{r4,pc}
+___
+$code.=<<___	if ($flavour =~ /64/);
+	ldp	x29,x30,[sp],#16
+	ret
+___
+$code.=<<___;
+.size	${prefix}_set_decrypt_key,.-${prefix}_set_decrypt_key
+___
+}}}
+{{{
+sub gen_block () {
+my $dir = shift;
+my ($e,$mc) = $dir eq "en" ? ("e","mc") : ("d","imc");
+my ($inp,$out,$key)=map("x$_",(0..2));
+my $rounds="w3";
+my ($rndkey0,$rndkey1,$inout)=map("q$_",(0..3));
+
+$code.=<<___;
+.globl	${prefix}_${dir}crypt
+.type	${prefix}_${dir}crypt,%function
+.align	5
+${prefix}_${dir}crypt:
+	ldr	$rounds,[$key,#240]
+	vld1.32	{$rndkey0},[$key],#16
+	vld1.8	{$inout},[$inp]
+	sub	$rounds,$rounds,#2
+	vld1.32	{$rndkey1},[$key],#16
+
+.Loop_${dir}c:
+	aes$e	$inout,$rndkey0
+	vld1.32	{$rndkey0},[$key],#16
+	aes$mc	$inout,$inout
+	subs	$rounds,$rounds,#2
+	aes$e	$inout,$rndkey1
+	vld1.32	{$rndkey1},[$key],#16
+	aes$mc	$inout,$inout
+	b.gt	.Loop_${dir}c
+
+	aes$e	$inout,$rndkey0
+	vld1.32	{$rndkey0},[$key]
+	aes$mc	$inout,$inout
+	aes$e	$inout,$rndkey1
+	veor	$inout,$inout,$rndkey0
+
+	vst1.8	{$inout},[$out]
+	ret
+.size	${prefix}_${dir}crypt,.-${prefix}_${dir}crypt
+___
+}
+&gen_block("en");
+&gen_block("de");
+}}}
+{{{
+my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4)); my $enc="w5";
+my ($rounds,$cnt,$key_,$step,$step1)=($enc,"w6","x7","x8","x12");
+my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7));
+
+my ($dat,$tmp,$rndzero_n_last)=($dat0,$tmp0,$tmp1);
+
+### q8-q15	preloaded key schedule
+
+$code.=<<___;
+.globl	${prefix}_cbc_encrypt
+.type	${prefix}_cbc_encrypt,%function
+.align	5
+${prefix}_cbc_encrypt:
+___
+$code.=<<___	if ($flavour =~ /64/);
+	stp	x29,x30,[sp,#-16]!
+	add	x29,sp,#0
+___
+$code.=<<___	if ($flavour !~ /64/);
+	mov	ip,sp
+	stmdb	sp!,{r4-r8,lr}
+	vstmdb	sp!,{d8-d15}            @ ABI specification says so
+	ldmia	ip,{r4-r5}		@ load remaining args
+___
+$code.=<<___;
+	subs	$len,$len,#16
+	mov	$step,#16
+	b.lo	.Lcbc_abort
+	cclr	$step,eq
+
+	cmp	$enc,#0			// en- or decrypting?
+	ldr	$rounds,[$key,#240]
+	and	$len,$len,#-16
+	vld1.8	{$ivec},[$ivp]
+	vld1.8	{$dat},[$inp],$step
+
+	vld1.32	{q8-q9},[$key]		// load key schedule...
+	sub	$rounds,$rounds,#6
+	add	$key_,$key,x5,lsl#4	// pointer to last 7 round keys
+	sub	$rounds,$rounds,#2
+	vld1.32	{q10-q11},[$key_],#32
+	vld1.32	{q12-q13},[$key_],#32
+	vld1.32	{q14-q15},[$key_],#32
+	vld1.32	{$rndlast},[$key_]
+
+	add	$key_,$key,#32
+	mov	$cnt,$rounds
+	b.eq	.Lcbc_dec
+
+	cmp	$rounds,#2
+	veor	$dat,$dat,$ivec
+	veor	$rndzero_n_last,q8,$rndlast
+	b.eq	.Lcbc_enc128
+
+.Loop_cbc_enc:
+	aese	$dat,q8
+	vld1.32	{q8},[$key_],#16
+	aesmc	$dat,$dat
+	subs	$cnt,$cnt,#2
+	aese	$dat,q9
+	vld1.32	{q9},[$key_],#16
+	aesmc	$dat,$dat
+	b.gt	.Loop_cbc_enc
+
+	aese	$dat,q8
+	aesmc	$dat,$dat
+	 subs	$len,$len,#16
+	aese	$dat,q9
+	aesmc	$dat,$dat
+	 cclr	$step,eq
+	aese	$dat,q10
+	aesmc	$dat,$dat
+	 add	$key_,$key,#16
+	aese	$dat,q11
+	aesmc	$dat,$dat
+	 vld1.8	{q8},[$inp],$step
+	aese	$dat,q12
+	aesmc	$dat,$dat
+	 veor	q8,q8,$rndzero_n_last
+	aese	$dat,q13
+	aesmc	$dat,$dat
+	 vld1.32 {q9},[$key_],#16	// re-pre-load rndkey[1]
+	aese	$dat,q14
+	aesmc	$dat,$dat
+	aese	$dat,q15
+
+	 mov	$cnt,$rounds
+	veor	$ivec,$dat,$rndlast
+	vst1.8	{$ivec},[$out],#16
+	b.hs	.Loop_cbc_enc
+
+	b	.Lcbc_done
+
+.align	5
+.Lcbc_enc128:
+	vld1.32	{$in0-$in1},[$key_]
+	aese	$dat,q8
+	aesmc	$dat,$dat
+	b	.Lenter_cbc_enc128
+.Loop_cbc_enc128:
+	aese	$dat,q8
+	aesmc	$dat,$dat
+	 vst1.8	{$ivec},[$out],#16
+.Lenter_cbc_enc128:
+	aese	$dat,q9
+	aesmc	$dat,$dat
+	 subs	$len,$len,#16
+	aese	$dat,$in0
+	aesmc	$dat,$dat
+	 cclr	$step,eq
+	aese	$dat,$in1
+	aesmc	$dat,$dat
+	aese	$dat,q10
+	aesmc	$dat,$dat
+	aese	$dat,q11
+	aesmc	$dat,$dat
+	 vld1.8	{q8},[$inp],$step
+	aese	$dat,q12
+	aesmc	$dat,$dat
+	aese	$dat,q13
+	aesmc	$dat,$dat
+	aese	$dat,q14
+	aesmc	$dat,$dat
+	 veor	q8,q8,$rndzero_n_last
+	aese	$dat,q15
+	veor	$ivec,$dat,$rndlast
+	b.hs	.Loop_cbc_enc128
+
+	vst1.8	{$ivec},[$out],#16
+	b	.Lcbc_done
+___
+{
+my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9));
+$code.=<<___;
+.align	5
+.Lcbc_dec:
+	vld1.8	{$dat2},[$inp],#16
+	subs	$len,$len,#32		// bias
+	add	$cnt,$rounds,#2
+	vorr	$in1,$dat,$dat
+	vorr	$dat1,$dat,$dat
+	vorr	$in2,$dat2,$dat2
+	b.lo	.Lcbc_dec_tail
+
+	vorr	$dat1,$dat2,$dat2
+	vld1.8	{$dat2},[$inp],#16
+	vorr	$in0,$dat,$dat
+	vorr	$in1,$dat1,$dat1
+	vorr	$in2,$dat2,$dat2
+
+.Loop3x_cbc_dec:
+	aesd	$dat0,q8
+	aesd	$dat1,q8
+	aesd	$dat2,q8
+	vld1.32	{q8},[$key_],#16
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	subs	$cnt,$cnt,#2
+	aesd	$dat0,q9
+	aesd	$dat1,q9
+	aesd	$dat2,q9
+	vld1.32	{q9},[$key_],#16
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	b.gt	.Loop3x_cbc_dec
+
+	aesd	$dat0,q8
+	aesd	$dat1,q8
+	aesd	$dat2,q8
+	 veor	$tmp0,$ivec,$rndlast
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 veor	$tmp1,$in0,$rndlast
+	aesd	$dat0,q9
+	aesd	$dat1,q9
+	aesd	$dat2,q9
+	 veor	$tmp2,$in1,$rndlast
+	 subs	$len,$len,#0x30
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 vorr	$ivec,$in2,$in2
+	 mov.lo	x6,$len			// x6, $cnt, is zero at this point
+	aesd	$dat0,q12
+	aesd	$dat1,q12
+	aesd	$dat2,q12
+	 add	$inp,$inp,x6		// $inp is adjusted in such way that
+					// at exit from the loop $dat1-$dat2
+					// are loaded with last "words"
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 mov	$key_,$key
+	aesd	$dat0,q13
+	aesd	$dat1,q13
+	aesd	$dat2,q13
+	 vld1.8	{$in0},[$inp],#16
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 vld1.8	{$in1},[$inp],#16
+	aesd	$dat0,q14
+	aesd	$dat1,q14
+	aesd	$dat2,q14
+	 vld1.8	{$in2},[$inp],#16
+	aesimc	$dat0,$dat0
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 vld1.32 {q8},[$key_],#16	// re-pre-load rndkey[0]
+	aesd	$dat0,q15
+	aesd	$dat1,q15
+	aesd	$dat2,q15
+
+	 add	$cnt,$rounds,#2
+	veor	$tmp0,$tmp0,$dat0
+	veor	$tmp1,$tmp1,$dat1
+	veor	$dat2,$dat2,$tmp2
+	 vld1.32 {q9},[$key_],#16	// re-pre-load rndkey[1]
+	 vorr	$dat0,$in0,$in0
+	vst1.8	{$tmp0},[$out],#16
+	 vorr	$dat1,$in1,$in1
+	vst1.8	{$tmp1},[$out],#16
+	vst1.8	{$dat2},[$out],#16
+	 vorr	$dat2,$in2,$in2
+	b.hs	.Loop3x_cbc_dec
+
+	cmn	$len,#0x30
+	b.eq	.Lcbc_done
+	nop
+
+.Lcbc_dec_tail:
+	aesd	$dat1,q8
+	aesd	$dat2,q8
+	vld1.32	{q8},[$key_],#16
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	subs	$cnt,$cnt,#2
+	aesd	$dat1,q9
+	aesd	$dat2,q9
+	vld1.32	{q9},[$key_],#16
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	b.gt	.Lcbc_dec_tail
+
+	aesd	$dat1,q8
+	aesd	$dat2,q8
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	aesd	$dat1,q9
+	aesd	$dat2,q9
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	aesd	$dat1,q12
+	aesd	$dat2,q12
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 cmn	$len,#0x20
+	aesd	$dat1,q13
+	aesd	$dat2,q13
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 veor	$tmp1,$ivec,$rndlast
+	aesd	$dat1,q14
+	aesd	$dat2,q14
+	aesimc	$dat1,$dat1
+	aesimc	$dat2,$dat2
+	 veor	$tmp2,$in1,$rndlast
+	aesd	$dat1,q15
+	aesd	$dat2,q15
+	b.eq	.Lcbc_dec_one
+	veor	$tmp1,$tmp1,$dat1
+	veor	$tmp2,$tmp2,$dat2
+	 vorr	$ivec,$in2,$in2
+	vst1.8	{$tmp1},[$out],#16
+	vst1.8	{$tmp2},[$out],#16
+	b	.Lcbc_done
+
+.Lcbc_dec_one:
+	veor	$tmp1,$tmp1,$dat2
+	 vorr	$ivec,$in2,$in2
+	vst1.8	{$tmp1},[$out],#16
+
+.Lcbc_done:
+	vst1.8	{$ivec},[$ivp]
+.Lcbc_abort:
+___
+}
+$code.=<<___	if ($flavour !~ /64/);
+	vldmia	sp!,{d8-d15}
+	ldmia	sp!,{r4-r8,pc}
+___
+$code.=<<___	if ($flavour =~ /64/);
+	ldr	x29,[sp],#16
+	ret
+___
+$code.=<<___;
+.size	${prefix}_cbc_encrypt,.-${prefix}_cbc_encrypt
+___
+}}}
+{{{
+my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4));
+my ($rounds,$cnt,$key_)=("w5","w6","x7");
+my ($ctr,$tctr0,$tctr1,$tctr2)=map("w$_",(8..10,12));
+my $step="x12";		# aliases with $tctr2
+
+my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7));
+my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9));
+
+my ($dat,$tmp)=($dat0,$tmp0);
+
+### q8-q15	preloaded key schedule
+
+$code.=<<___;
+.globl	${prefix}_ctr32_encrypt_blocks
+.type	${prefix}_ctr32_encrypt_blocks,%function
+.align	5
+${prefix}_ctr32_encrypt_blocks:
+___
+$code.=<<___	if ($flavour =~ /64/);
+	stp		x29,x30,[sp,#-16]!
+	add		x29,sp,#0
+___
+$code.=<<___	if ($flavour !~ /64/);
+	mov		ip,sp
+	stmdb		sp!,{r4-r10,lr}
+	vstmdb		sp!,{d8-d15}            @ ABI specification says so
+	ldr		r4, [ip]		@ load remaining arg
+___
+$code.=<<___;
+	ldr		$rounds,[$key,#240]
+
+	ldr		$ctr, [$ivp, #12]
+	vld1.32		{$dat0},[$ivp]
+
+	vld1.32		{q8-q9},[$key]		// load key schedule...
+	sub		$rounds,$rounds,#4
+	mov		$step,#16
+	cmp		$len,#2
+	add		$key_,$key,x5,lsl#4	// pointer to last 5 round keys
+	sub		$rounds,$rounds,#2
+	vld1.32		{q12-q13},[$key_],#32
+	vld1.32		{q14-q15},[$key_],#32
+	vld1.32		{$rndlast},[$key_]
+	add		$key_,$key,#32
+	mov		$cnt,$rounds
+	cclr		$step,lo
+#ifndef __ARMEB__
+	rev		$ctr, $ctr
+#endif
+	vorr		$dat1,$dat0,$dat0
+	add		$tctr1, $ctr, #1
+	vorr		$dat2,$dat0,$dat0
+	add		$ctr, $ctr, #2
+	vorr		$ivec,$dat0,$dat0
+	rev		$tctr1, $tctr1
+	vmov.32		${dat1}[3],$tctr1
+	b.ls		.Lctr32_tail
+	rev		$tctr2, $ctr
+	sub		$len,$len,#3		// bias
+	vmov.32		${dat2}[3],$tctr2
+	b		.Loop3x_ctr32
+
+.align	4
+.Loop3x_ctr32:
+	aese		$dat0,q8
+	aese		$dat1,q8
+	aese		$dat2,q8
+	vld1.32		{q8},[$key_],#16
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	aesmc		$dat2,$dat2
+	subs		$cnt,$cnt,#2
+	aese		$dat0,q9
+	aese		$dat1,q9
+	aese		$dat2,q9
+	vld1.32		{q9},[$key_],#16
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	aesmc		$dat2,$dat2
+	b.gt		.Loop3x_ctr32
+
+	aese		$dat0,q8
+	aese		$dat1,q8
+	aese		$dat2,q8
+	 mov		$key_,$key
+	aesmc		$tmp0,$dat0
+	 vld1.8		{$in0},[$inp],#16
+	aesmc		$tmp1,$dat1
+	aesmc		$dat2,$dat2
+	 vorr		$dat0,$ivec,$ivec
+	aese		$tmp0,q9
+	 vld1.8		{$in1},[$inp],#16
+	aese		$tmp1,q9
+	aese		$dat2,q9
+	 vorr		$dat1,$ivec,$ivec
+	aesmc		$tmp0,$tmp0
+	 vld1.8		{$in2},[$inp],#16
+	aesmc		$tmp1,$tmp1
+	aesmc		$tmp2,$dat2
+	 vorr		$dat2,$ivec,$ivec
+	 add		$tctr0,$ctr,#1
+	aese		$tmp0,q12
+	aese		$tmp1,q12
+	aese		$tmp2,q12
+	 veor		$in0,$in0,$rndlast
+	 add		$tctr1,$ctr,#2
+	aesmc		$tmp0,$tmp0
+	aesmc		$tmp1,$tmp1
+	aesmc		$tmp2,$tmp2
+	 veor		$in1,$in1,$rndlast
+	 add		$ctr,$ctr,#3
+	aese		$tmp0,q13
+	aese		$tmp1,q13
+	aese		$tmp2,q13
+	 veor		$in2,$in2,$rndlast
+	 rev		$tctr0,$tctr0
+	aesmc		$tmp0,$tmp0
+	 vld1.32	 {q8},[$key_],#16	// re-pre-load rndkey[0]
+	aesmc		$tmp1,$tmp1
+	aesmc		$tmp2,$tmp2
+	 vmov.32	${dat0}[3], $tctr0
+	 rev		$tctr1,$tctr1
+	aese		$tmp0,q14
+	aese		$tmp1,q14
+	aese		$tmp2,q14
+	 vmov.32	${dat1}[3], $tctr1
+	 rev		$tctr2,$ctr
+	aesmc		$tmp0,$tmp0
+	aesmc		$tmp1,$tmp1
+	aesmc		$tmp2,$tmp2
+	 vmov.32	${dat2}[3], $tctr2
+	 subs		$len,$len,#3
+	aese		$tmp0,q15
+	aese		$tmp1,q15
+	aese		$tmp2,q15
+
+	 mov		$cnt,$rounds
+	veor		$in0,$in0,$tmp0
+	veor		$in1,$in1,$tmp1
+	veor		$in2,$in2,$tmp2
+	 vld1.32	 {q9},[$key_],#16	// re-pre-load rndkey[1]
+	vst1.8		{$in0},[$out],#16
+	vst1.8		{$in1},[$out],#16
+	vst1.8		{$in2},[$out],#16
+	b.hs		.Loop3x_ctr32
+
+	adds		$len,$len,#3
+	b.eq		.Lctr32_done
+	cmp		$len,#1
+	mov		$step,#16
+	cclr		$step,eq
+
+.Lctr32_tail:
+	aese		$dat0,q8
+	aese		$dat1,q8
+	vld1.32		{q8},[$key_],#16
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	subs		$cnt,$cnt,#2
+	aese		$dat0,q9
+	aese		$dat1,q9
+	vld1.32		{q9},[$key_],#16
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	b.gt		.Lctr32_tail
+
+	aese		$dat0,q8
+	aese		$dat1,q8
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	aese		$dat0,q9
+	aese		$dat1,q9
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	 vld1.8		{$in0},[$inp],$step
+	aese		$dat0,q12
+	aese		$dat1,q12
+	 vld1.8		{$in1},[$inp]
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	aese		$dat0,q13
+	aese		$dat1,q13
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	aese		$dat0,q14
+	aese		$dat1,q14
+	 veor		$in0,$in0,$rndlast
+	aesmc		$dat0,$dat0
+	aesmc		$dat1,$dat1
+	 veor		$in1,$in1,$rndlast
+	aese		$dat0,q15
+	aese		$dat1,q15
+
+	cmp		$len,#1
+	veor		$in0,$in0,$dat0
+	veor		$in1,$in1,$dat1
+	vst1.8		{$in0},[$out],#16
+	b.eq		.Lctr32_done
+	vst1.8		{$in1},[$out]
+
+.Lctr32_done:
+___
+$code.=<<___	if ($flavour !~ /64/);
+	vldmia		sp!,{d8-d15}
+	ldmia		sp!,{r4-r10,pc}
+___
+$code.=<<___	if ($flavour =~ /64/);
+	ldr		x29,[sp],#16
+	ret
+___
+$code.=<<___;
+.size	${prefix}_ctr32_encrypt_blocks,.-${prefix}_ctr32_encrypt_blocks
+___
+}}}
+$code.=<<___;
+#endif
+___
+########################################
+if ($flavour =~ /64/) {			######## 64-bit code
+    my %opcode = (
+	"aesd"	=>	0x4e285800,	"aese"	=>	0x4e284800,
+	"aesimc"=>	0x4e287800,	"aesmc"	=>	0x4e286800	);
+
+    local *unaes = sub {
+	my ($mnemonic,$arg)=@_;
+
+	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o	&&
+	sprintf ".inst\t0x%08x\t//%s %s",
+			$opcode{$mnemonic}|$1|($2<<5),
+			$mnemonic,$arg;
+    };
+
+    foreach(split("\n",$code)) {
+	s/\`([^\`]*)\`/eval($1)/geo;
+
+	s/\bq([0-9]+)\b/"v".($1<8?$1:$1+8).".16b"/geo;	# old->new registers
+	s/@\s/\/\//o;			# old->new style commentary
+
+	#s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo	or
+	s/cclr\s+([wx])([^,]+),\s*([a-z]+)/csel	$1$2,$1zr,$1$2,$3/o	or
+	s/mov\.([a-z]+)\s+([wx][0-9]+),\s*([wx][0-9]+)/csel	$2,$3,$2,$1/o	or
+	s/vmov\.i8/movi/o	or	# fix up legacy mnemonics
+	s/vext\.8/ext/o		or
+	s/vrev32\.8/rev32/o	or
+	s/vtst\.8/cmtst/o	or
+	s/vshr/ushr/o		or
+	s/^(\s+)v/$1/o		or	# strip off v prefix
+	s/\bbx\s+lr\b/ret/o;
+
+	# fix up remainig legacy suffixes
+	s/\.[ui]?8//o;
+	m/\],#8/o and s/\.16b/\.8b/go;
+	s/\.[ui]?32//o and s/\.16b/\.4s/go;
+	s/\.[ui]?64//o and s/\.16b/\.2d/go;
+	s/\.[42]([sd])\[([0-3])\]/\.$1\[$2\]/o;
+
+	print $_,"\n";
+    }
+} else {				######## 32-bit code
+    my %opcode = (
+	"aesd"	=>	0xf3b00340,	"aese"	=>	0xf3b00300,
+	"aesimc"=>	0xf3b003c0,	"aesmc"	=>	0xf3b00380	);
+
+    local *unaes = sub {
+	my ($mnemonic,$arg)=@_;
+
+	if ($arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o) {
+	    my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19)
+					 |(($2&7)<<1) |(($2&8)<<2);
+	    # since ARMv7 instructions are always encoded little-endian.
+	    # correct solution is to use .inst directive, but older
+	    # assemblers don't implement it:-(
+	    sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s",
+			$word&0xff,($word>>8)&0xff,
+			($word>>16)&0xff,($word>>24)&0xff,
+			$mnemonic,$arg;
+	}
+    };
+
+    sub unvtbl {
+	my $arg=shift;
+
+	$arg =~ m/q([0-9]+),\s*\{q([0-9]+)\},\s*q([0-9]+)/o &&
+	sprintf	"vtbl.8	d%d,{q%d},d%d\n\t".
+		"vtbl.8	d%d,{q%d},d%d", 2*$1,$2,2*$3, 2*$1+1,$2,2*$3+1;	
+    }
+
+    sub unvdup32 {
+	my $arg=shift;
+
+	$arg =~ m/q([0-9]+),\s*q([0-9]+)\[([0-3])\]/o &&
+	sprintf	"vdup.32	q%d,d%d[%d]",$1,2*$2+($3>>1),$3&1;	
+    }
+
+    sub unvmov32 {
+	my $arg=shift;
+
+	$arg =~ m/q([0-9]+)\[([0-3])\],(.*)/o &&
+	sprintf	"vmov.32	d%d[%d],%s",2*$1+($2>>1),$2&1,$3;	
+    }
+
+    foreach(split("\n",$code)) {
+	s/\`([^\`]*)\`/eval($1)/geo;
+
+	s/\b[wx]([0-9]+)\b/r$1/go;		# new->old registers
+	s/\bv([0-9])\.[12468]+[bsd]\b/q$1/go;	# new->old registers
+	s/\/\/\s?/@ /o;				# new->old style commentary
+
+	# fix up remainig new-style suffixes
+	s/\{q([0-9]+)\},\s*\[(.+)\],#8/sprintf "{d%d},[$2]!",2*$1/eo	or
+	s/\],#[0-9]+/]!/o;
+
+	s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo	or
+	s/cclr\s+([^,]+),\s*([a-z]+)/mov$2	$1,#0/o	or
+	s/vtbl\.8\s+(.*)/unvtbl($1)/geo			or
+	s/vdup\.32\s+(.*)/unvdup32($1)/geo		or
+	s/vmov\.32\s+(.*)/unvmov32($1)/geo		or
+	s/^(\s+)b\./$1b/o				or
+	s/^(\s+)mov\./$1mov/o				or
+	s/^(\s+)ret/$1bx\tlr/o;
+
+	print $_,"\n";
+    }
+}
+
+close STDOUT;

crypto/arm64cpuid.pl

@@ -0,0 +1,68 @@
+#!/usr/bin/env perl
+
+$flavour = shift;
+$output  = shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
+
+$code.=<<___;
+#include "arm_arch.h"
+
+.text
+.arch	armv8-a+crypto
+
+.align	5
+.globl	_armv7_neon_probe
+.type	_armv7_neon_probe,%function
+_armv7_neon_probe:
+	orr	v15.16b, v15.16b, v15.16b
+	ret
+.size	_armv7_neon_probe,.-_armv7_neon_probe
+
+.globl	_armv7_tick
+.type	_armv7_tick,%function
+_armv7_tick:
+#ifdef	__APPLE__
+	mrs	x0, CNTPCT_EL0
+#else
+	mrs	x0, CNTVCT_EL0
+#endif
+	ret
+.size	_armv7_tick,.-_armv7_tick
+
+.globl	_armv8_aes_probe
+.type	_armv8_aes_probe,%function
+_armv8_aes_probe:
+	aese	v0.16b, v0.16b
+	ret
+.size	_armv8_aes_probe,.-_armv8_aes_probe
+
+.globl	_armv8_sha1_probe
+.type	_armv8_sha1_probe,%function
+_armv8_sha1_probe:
+	sha1h	s0, s0
+	ret
+.size	_armv8_sha1_probe,.-_armv8_sha1_probe
+
+.globl	_armv8_sha256_probe
+.type	_armv8_sha256_probe,%function
+_armv8_sha256_probe:
+	sha256su0	v0.4s, v0.4s
+	ret
+.size	_armv8_sha256_probe,.-_armv8_sha256_probe
+.globl	_armv8_pmull_probe
+.type	_armv8_pmull_probe,%function
+_armv8_pmull_probe:
+	pmull	v0.1q, v0.1d, v0.1d
+	ret
+.size	_armv8_pmull_probe,.-_armv8_pmull_probe
+___
+
+print $code;
+close STDOUT;

crypto/arm_arch.h

@@ -10,13 +10,22 @@
 #   define __ARMEL__
 #  endif
 # elif defined(__GNUC__)
+#  if  defined(__aarch64__)
+#   define __ARM_ARCH__ 8
+#   if __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
+#    define __ARMEB__
+#   else
+#    define __ARMEL__
+#   endif
   /*
    * Why doesn't gcc define __ARM_ARCH__? Instead it defines
    * bunch of below macros. See all_architectires[] table in
    * gcc/config/arm/arm.c. On a side note it defines
    * __ARMEL__/__ARMEB__ for little-/big-endian.
    */
-#  if	defined(__ARM_ARCH_7__)	|| defined(__ARM_ARCH_7A__)	|| \
+#  elif defined(__ARM_ARCH_8A__)
+#    define __ARM_ARCH__ 8
+#  elif	defined(__ARM_ARCH_7__)	|| defined(__ARM_ARCH_7A__)	|| \
 	defined(__ARM_ARCH_7R__)|| defined(__ARM_ARCH_7M__)	|| \
 	defined(__ARM_ARCH_7EM__)
 #   define __ARM_ARCH__ 7
@@ -42,10 +51,14 @@
 
 #if !__ASSEMBLER__
 extern unsigned int OPENSSL_armcap_P;
+#endif
                                      
 #define ARMV7_NEON      (1<<0)
 #define ARMV7_TICK      (1<<1)
-#endif
+#define ARMV8_AES       (1<<2)
+#define ARMV8_SHA1      (1<<3)
+#define ARMV8_SHA256    (1<<4)
+#define ARMV8_PMULL     (1<<5)
 
 #endif
 #endif

crypto/armcap.c

@@ -20,6 +20,10 @@ static void ill_handler (int sig) { siglongjmp(ill_jmp,sig); }
  */
 void _armv7_neon_probe(void);
 unsigned int _armv7_tick(void);
+void _armv8_aes_probe(void);
+void _armv8_sha1_probe(void);
+void _armv8_sha256_probe(void);
+void _armv8_pmull_probe(void);
 
 unsigned int OPENSSL_rdtsc(void)
 	{
@@ -68,6 +72,28 @@ void OPENSSL_cpuid_setup(void)
 		{
 		_armv7_neon_probe();
 		OPENSSL_armcap_P |= ARMV7_NEON;
+#ifdef __aarch64__
+		if (sigsetjmp(ill_jmp,1) == 0)
+			{
+			_armv8_pmull_probe();
+			OPENSSL_armcap_P |= ARMV8_PMULL|ARMV8_AES;
+			}
+		else if (sigsetjmp(ill_jmp,1) == 0)
+			{
+			_armv8_aes_probe();
+			OPENSSL_armcap_P |= ARMV8_AES;
+			}
+		if (sigsetjmp(ill_jmp,1) == 0)
+			{
+			_armv8_sha1_probe();
+			OPENSSL_armcap_P |= ARMV8_SHA1;
+			}
+		if (sigsetjmp(ill_jmp,1) == 0)
+			{
+			_armv8_sha256_probe();
+			OPENSSL_armcap_P |= ARMV8_SHA256;
+			}
+#endif
 		}
 	if (sigsetjmp(ill_jmp,1) == 0)
 		{

crypto/armv4cpuid_ios.S

@@ -0,0 +1,210 @@
+#include "arm_arch.h"
+
+.text
+.code	32
+
+.align	5
+.globl	_OPENSSL_atomic_add
+
+_OPENSSL_atomic_add:
+#if __ARM_ARCH__>=6
+Ladd:	ldrex	r2,[r0]
+	add	r3,r2,r1
+	strex	r2,r3,[r0]
+	cmp	r2,#0
+	bne	Ladd
+	mov	r0,r3
+	bx	lr
+#else
+	stmdb	sp!,{r4,r5,r6,lr}
+	ldr	r2,Lspinlock
+	adr	r3,Lspinlock
+	mov	r4,r0
+	mov	r5,r1
+	add	r6,r3,r2	@ &spinlock
+	b	.+8
+Lspin:	bl	sched_yield
+	mov	r0,#-1
+	swp	r0,r0,[r6]
+	cmp	r0,#0
+	bne	Lspin
+
+	ldr	r2,[r4]
+	add	r2,r2,r5
+	str	r2,[r4]
+	str	r0,[r6]		@ release spinlock
+	ldmia	sp!,{r4,r5,r6,lr}
+	tst	lr,#1
+	moveq	pc,lr
+.word	0xe12fff1e	@ bx	lr
+#endif
+
+
+.globl	_OPENSSL_cleanse
+
+_OPENSSL_cleanse:
+	eor	ip,ip,ip
+	cmp	r1,#7
+	subhs	r1,r1,#4
+	bhs	Lot
+	cmp	r1,#0
+	beq	Lcleanse_done
+Little:
+	strb	ip,[r0],#1
+	subs	r1,r1,#1
+	bhi	Little
+	b	Lcleanse_done
+
+Lot:	tst	r0,#3
+	beq	Laligned
+	strb	ip,[r0],#1
+	sub	r1,r1,#1
+	b	Lot
+Laligned:
+	str	ip,[r0],#4
+	subs	r1,r1,#4
+	bhs	Laligned
+	adds	r1,r1,#4
+	bne	Little
+Lcleanse_done:
+#if __ARM_ARCH__>=5
+	bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr
+.word	0xe12fff1e	@ bx	lr
+#endif
+
+
+
+
+.align	5
+.globl	__armv7_neon_probe
+
+__armv7_neon_probe:
+	vorr	q0,q0,q0
+	bx	lr
+
+
+.globl	__armv7_tick
+
+__armv7_tick:
+#ifdef	__APPLE__
+	mrrc	p15,0,r0,r1,c14		@ CNTPCT
+#else
+	mrrc	p15,1,r0,r1,c14		@ CNTVCT
+#endif
+	bx	lr
+
+
+.globl	__armv8_aes_probe
+
+__armv8_aes_probe:
+.byte	0x00,0x03,0xb0,0xf3	@ aese.8	q0,q0
+	bx	lr
+
+
+.globl	__armv8_sha1_probe
+
+__armv8_sha1_probe:
+.byte	0x40,0x0c,0x00,0xf2	@ sha1c.32	q0,q0,q0
+	bx	lr
+
+
+.globl	__armv8_sha256_probe
+
+__armv8_sha256_probe:
+.byte	0x40,0x0c,0x00,0xf3	@ sha256h.32	q0,q0,q0
+	bx	lr
+
+.globl	__armv8_pmull_probe
+
+__armv8_pmull_probe:
+.byte	0x00,0x0e,0xa0,0xf2	@ vmull.p64	q0,d0,d0
+	bx	lr
+
+.globl	_OPENSSL_wipe_cpu
+
+_OPENSSL_wipe_cpu:
+	ldr	r0,LOPENSSL_armcap
+	adr	r1,LOPENSSL_armcap
+	ldr	r0,[r1,r0]
+#ifdef	__APPLE__
+	ldr	r0,[r0]
+#endif
+	eor	r2,r2,r2
+	eor	r3,r3,r3
+	eor	ip,ip,ip
+	tst	r0,#1
+	beq	Lwipe_done
+	veor	q0, q0, q0
+	veor	q1, q1, q1
+	veor	q2, q2, q2
+	veor	q3, q3, q3
+	veor	q8, q8, q8
+	veor	q9, q9, q9
+	veor	q10, q10, q10
+	veor	q11, q11, q11
+	veor	q12, q12, q12
+	veor	q13, q13, q13
+	veor	q14, q14, q14
+	veor	q15, q15, q15
+Lwipe_done:
+	mov	r0,sp
+#if __ARM_ARCH__>=5
+	bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr
+.word	0xe12fff1e	@ bx	lr
+#endif
+
+
+.globl	_OPENSSL_instrument_bus
+
+_OPENSSL_instrument_bus:
+	eor	r0,r0,r0
+#if __ARM_ARCH__>=5
+	bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr
+.word	0xe12fff1e	@ bx	lr
+#endif
+
+
+.globl	_OPENSSL_instrument_bus2
+
+_OPENSSL_instrument_bus2:
+	eor	r0,r0,r0
+#if __ARM_ARCH__>=5
+	bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr
+.word	0xe12fff1e	@ bx	lr
+#endif
+
+
+.align	5
+LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-.
+#if __ARM_ARCH__>=6
+.align	5
+#else
+Lspinlock:
+.word	atomic_add_spinlock-Lspinlock
+.align	5
+
+.data
+.align	2
+atomic_add_spinlock:
+.word
+#endif
+
+.comm	_OPENSSL_armcap_P,4
+.non_lazy_symbol_pointer
+OPENSSL_armcap_P:
+.indirect_symbol	_OPENSSL_armcap_P
+.long	0
+.private_extern	_OPENSSL_armcap_P

crypto/bn/asm/armv4-gf2m.pl

@@ -21,8 +21,20 @@
 # runs in even less cycles, ~30, improvement is measurable only on
 # longer keys. One has to optimize code elsewhere to get NEON glow...
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 sub Dlo()   { shift=~m|q([1]?[0-9])|?"d".($1*2):"";     }
 sub Dhi()   { shift=~m|q([1]?[0-9])|?"d".($1*2+1):"";   }
@@ -170,11 +182,18 @@ bn_GF2m_mul_2x2:
 #if __ARM_ARCH__>=7
 	ldr	r12,.LOPENSSL_armcap
 .Lpic:	ldr	r12,[pc,r12]
+#ifdef	__APPLE__
+	ldr	r12,[r12]
+#endif
 	tst	r12,#1
 	beq	.Lialu
 
 	veor	$A1,$A1
+#ifdef	__APPLE__
+	vmov	$B1,r3,r3		@ two copies of b1
+#else
 	vmov.32	$B1,r3,r3		@ two copies of b1
+#endif
 	vmov.32	${A1}[0],r1		@ a1
 
 	veor	$A0,$A0

crypto/bn/asm/armv4-mont.pl

@@ -23,8 +23,20 @@
 # than 1/2KB. Windows CE port would be trivial, as it's exclusively
 # about decorations, ABI and instruction syntax are identical.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $num="r0";	# starts as num argument, but holds &tp[num-1]
 $ap="r1";

crypto/bn/asm/bn-c64xplus.asm

@@ -0,0 +1,333 @@
+;;====================================================================
+;; Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+;; project.
+;;
+;; Rights for redistribution and usage in source and binary forms are
+;; granted according to the OpenSSL license. Warranty of any kind is
+;; disclaimed.
+;;====================================================================
+;; Compiler-generated multiply-n-add SPLOOP runs at 12*n cycles, n
+;; being the number of 32-bit words, addition - 8*n. Corresponding 4x
+;; unrolled SPLOOP-free loops - at ~8*n and ~5*n. Below assembler
+;; SPLOOPs spin at ... 2*n cycles [plus epilogue].
+;;====================================================================
+	.text
+
+	.asg	B3,RA
+	.asg	A4,ARG0
+	.asg	B4,ARG1
+	.asg	A6,ARG2
+	.asg	B6,ARG3
+	.asg	A8,ARG4
+	.asg	B8,ARG5
+	.asg	A4,RET
+	.asg	A15,FP
+	.asg	B14,DP
+	.asg	B15,SP
+
+	.global	_bn_mul_add_words
+_bn_mul_add_words:
+	.asmfunc
+	MV	ARG2,B0
+  [!B0]	BNOP	RA
+||[!B0]	MVK	0,RET
+   [B0]	MVC	B0,ILC
+   [B0]	ZERO	A19		; high part of accumulator
+|| [B0]	MV	ARG0,A2
+|| [B0]	MV	ARG3,A3
+	NOP	3
+
+	SPLOOP	2		; 2*n+10
+;;====================================================================
+	LDW	*ARG1++,B7	; ap[i]
+	NOP	3
+	LDW	*ARG0++,A7	; rp[i]
+	MPY32U	B7,A3,A17:A16
+	NOP	3		; [2,0] in epilogue
+	ADDU	A16,A7,A21:A20
+	ADDU	A19,A21:A20,A19:A18
+||	MV.S	A17,A23
+	SPKERNEL 2,1		; leave slot for "return value"
+||	STW	A18,*A2++	; rp[i]
+||	ADD	A19,A23,A19
+;;====================================================================
+	BNOP	RA,4
+	MV	A19,RET		; return value
+	.endasmfunc
+
+	.global	_bn_mul_words
+_bn_mul_words:
+	.asmfunc
+	MV	ARG2,B0
+  [!B0]	BNOP	RA
+||[!B0]	MVK	0,RET
+   [B0]	MVC	B0,ILC
+   [B0]	ZERO	A19		; high part of accumulator
+	NOP	3
+
+	SPLOOP	2		; 2*n+10
+;;====================================================================
+	LDW	*ARG1++,A7	; ap[i]
+	NOP	4
+	MPY32U	A7,ARG3,A17:A16
+	NOP	4		; [2,0] in epiloque
+	ADDU	A19,A16,A19:A18
+||	MV.S	A17,A21
+	SPKERNEL 2,1		; leave slot for "return value"
+||	STW	A18,*ARG0++	; rp[i]
+||	ADD.L	A19,A21,A19
+;;====================================================================
+	BNOP	RA,4
+	MV	A19,RET		; return value
+	.endasmfunc
+
+	.global	_bn_sqr_words
+_bn_sqr_words:
+	.asmfunc
+	MV	ARG2,B0
+  [!B0]	BNOP	RA
+||[!B0]	MVK	0,RET
+   [B0]	MVC	B0,ILC
+   [B0]	MV	ARG0,B2
+|| [B0]	ADD	4,ARG0,ARG0
+	NOP	3
+
+	SPLOOP	2		; 2*n+10
+;;====================================================================
+	LDW	*ARG1++,B7	; ap[i]
+	NOP	4
+	MPY32U	B7,B7,B1:B0
+	NOP	3		; [2,0] in epilogue
+	STW	B0,*B2++(8)	; rp[2*i]
+	MV	B1,A1
+	SPKERNEL 2,0		; fully overlap BNOP RA,5
+||	STW	A1,*ARG0++(8)	; rp[2*i+1]
+;;====================================================================
+	BNOP	RA,5
+	.endasmfunc
+
+	.global	_bn_add_words
+_bn_add_words:
+	.asmfunc
+	MV	ARG3,B0
+  [!B0]	BNOP	RA
+||[!B0]	MVK	0,RET
+   [B0]	MVC	B0,ILC
+   [B0]	ZERO	A1		; carry flag
+|| [B0]	MV	ARG0,A3
+	NOP	3
+
+	SPLOOP	2		; 2*n+6
+;;====================================================================
+	LDW	*ARG2++,A7	; bp[i]
+||	LDW	*ARG1++,B7	; ap[i]
+	NOP	4
+	ADDU	A7,B7,A9:A8
+	ADDU	A1,A9:A8,A1:A0
+	SPKERNEL 0,0		; fully overlap BNOP RA,5
+||	STW	A0,*A3++	; write result
+||	MV	A1,RET		; keep carry flag in RET
+;;====================================================================
+	BNOP	RA,5
+	.endasmfunc
+
+	.global	_bn_sub_words
+_bn_sub_words:
+	.asmfunc
+	MV	ARG3,B0
+  [!B0]	BNOP	RA
+||[!B0]	MVK	0,RET
+   [B0]	MVC	B0,ILC
+   [B0]	ZERO	A2		; borrow flag
+|| [B0]	MV	ARG0,A3
+	NOP	3
+
+	SPLOOP	2		; 2*n+6
+;;====================================================================
+	LDW	*ARG2++,A7	; bp[i]
+||	LDW	*ARG1++,B7	; ap[i]
+	NOP	4
+	SUBU	B7,A7,A1:A0
+  [A2]	SUB	A1:A0,1,A1:A0
+	SPKERNEL 0,1		; leave slot for "return borrow flag"
+||	STW	A0,*A3++	; write result
+||	AND	1,A1,A2		; pass on borrow flag
+;;====================================================================
+	BNOP	RA,4
+	AND	1,A1,RET	; return borrow flag
+	.endasmfunc
+
+	.global	_bn_div_words
+	.global	__divull
+_bn_div_words:
+	.asmfunc
+	CALLP	__divull,A3	; jump to rts64plus.lib
+||	MV	ARG0,A5
+||	MV	ARG1,ARG0
+||	MV	ARG2,ARG1
+||	ZERO	B5
+	.endasmfunc
+
+;;====================================================================
+;; Not really Comba algorithm, just straightforward NxM... Dedicated
+;; fully unrolled real Comba implementations are asymptotically 2x
+;; faster, but naturally larger undertaking. Purpose of this exercise
+;; was rather to learn to master nested SPLOOPs...
+;;====================================================================
+	.global	_bn_sqr_comba8
+	.global	_bn_mul_comba8
+_bn_sqr_comba8:
+	MV	ARG1,ARG2
+_bn_mul_comba8:
+	.asmfunc
+	MVK	8,B0		; N, RILC
+||	MVK	8,A0		; M, outer loop counter
+||	MV	ARG1,A5		; copy ap
+||	MV	ARG0,B4		; copy rp
+||	ZERO	B19		; high part of accumulator
+	MVC	B0,RILC
+||	SUB	B0,2,B1		; N-2, initial ILC
+||	SUB	B0,1,B2		; const B2=N-1
+||	LDW	*A5++,B6	; ap[0]
+||	MV	A0,A3		; const A3=M
+sploopNxM?:			; for best performance arrange M<=N
+   [A0]	SPLOOPD	2		; 2*n+10
+||	MVC	B1,ILC
+||	ADDAW	B4,B0,B5
+||	ZERO	B7
+||	LDW	*A5++,A9	; pre-fetch ap[1]
+||	ZERO	A1
+||	SUB	A0,1,A0
+;;====================================================================
+;; SPLOOP from bn_mul_add_words, but with flipped A<>B register files.
+;; This is because of Advisory 15 from TI publication SPRZ247I.
+	LDW	*ARG2++,A7	; bp[i]
+	NOP	3
+   [A1]	LDW	*B5++,B7	; rp[i]
+	MPY32U	A7,B6,B17:B16
+	NOP	3
+	ADDU	B16,B7,B21:B20
+	ADDU	B19,B21:B20,B19:B18
+||	MV.S	B17,B23
+	SPKERNEL
+||	STW	B18,*B4++	; rp[i]
+||	ADD.S	B19,B23,B19
+;;====================================================================
+outer?:				; m*2*(n+1)+10
+	SUBAW	ARG2,A3,ARG2	; rewind bp to bp[0]
+	SPMASKR
+||	CMPGT	A0,1,A2		; done pre-fetching ap[i+1]?
+	MVD	A9,B6		; move through .M unit(*)
+   [A2]	LDW	*A5++,A9	; pre-fetch ap[i+1]
+	SUBAW	B5,B2,B5	; rewind rp to rp[1]
+	MVK	1,A1
+   [A0]	BNOP.S1	outer?,4
+|| [A0]	SUB.L	A0,1,A0
+	STW	B19,*B4--[B2]	; rewind rp tp rp[1]
+||	ZERO.S	B19		; high part of accumulator
+;; end of outer?
+	BNOP	RA,5		; return
+	.endasmfunc
+;; (*)	It should be noted that B6 is used as input to MPY32U in
+;;	chronologically next cycle in *preceding* SPLOOP iteration.
+;;	Normally such arrangement would require DINT, but at this
+;;	point SPLOOP is draining and interrupts are disabled
+;;	implicitly.
+
+	.global	_bn_sqr_comba4
+	.global	_bn_mul_comba4
+_bn_sqr_comba4:
+	MV	ARG1,ARG2
+_bn_mul_comba4:
+	.asmfunc
+	.if	0
+	BNOP	sploopNxM?,3
+	;; Above mentioned m*2*(n+1)+10 does not apply in n=m=4 case,
+	;; because of read-after-write penalties, it's rather
+	;; n*2*(n+3)+10, or 66 cycles [plus various overheads]...
+	MVK	4,B0		; N, RILC
+||	MVK	4,A0		; M, outer loop counter
+||	MV	ARG1,A5		; copy ap
+||	MV	ARG0,B4		; copy rp
+||	ZERO	B19		; high part of accumulator
+	MVC	B0,RILC
+||	SUB	B0,2,B1		; first ILC
+||	SUB	B0,1,B2		; const B2=N-1
+||	LDW	*A5++,B6	; ap[0]
+||	MV	A0,A3		; const A3=M
+	.else
+	;; This alternative is exercise in fully unrolled Comba
+	;; algorithm implementation that operates at n*(n+1)+12, or
+	;; as little as 32 cycles...
+	LDW	*ARG1[0],B16	; a[0]
+||	LDW	*ARG2[0],A16	; b[0]
+	LDW	*ARG1[1],B17	; a[1]
+||	LDW	*ARG2[1],A17	; b[1]
+	LDW	*ARG1[2],B18	; a[2]
+||	LDW	*ARG2[2],A18	; b[2]
+	LDW	*ARG1[3],B19	; a[3]
+||	LDW	*ARG2[3],A19	; b[3]
+	NOP
+	MPY32U	A16,B16,A1:A0	; a[0]*b[0]
+	MPY32U	A17,B16,A23:A22	; a[0]*b[1]
+	MPY32U	A16,B17,A25:A24	; a[1]*b[0]
+	MPY32U	A16,B18,A27:A26	; a[2]*b[0]
+	STW	A0,*ARG0[0]
+||	MPY32U	A17,B17,A29:A28	; a[1]*b[1]
+	MPY32U	A18,B16,A31:A30	; a[0]*b[2]
+||	ADDU	A22,A1,A1:A0
+	MV	A23,B0
+||	MPY32U	A19,B16,A21:A20	; a[3]*b[0]
+||	ADDU	A24,A1:A0,A1:A0
+	ADDU	A25,B0,B1:B0
+||	STW	A0,*ARG0[1]
+||	MPY32U	A18,B17,A23:A22	; a[2]*b[1]
+||	ADDU	A26,A1,A9:A8
+	ADDU	A27,B1,B9:B8
+||	MPY32U	A17,B18,A25:A24	; a[1]*b[2]
+||	ADDU	A28,A9:A8,A9:A8
+	ADDU	A29,B9:B8,B9:B8
+||	MPY32U	A16,B19,A27:A26	; a[0]*b[3]
+||	ADDU	A30,A9:A8,A9:A8
+	ADDU	A31,B9:B8,B9:B8
+||	ADDU	B0,A9:A8,A9:A8
+	STW	A8,*ARG0[2]
+||	ADDU	A20,A9,A1:A0
+	ADDU	A21,B9,B1:B0
+||	MPY32U	A19,B17,A21:A20	; a[3]*b[1]
+||	ADDU	A22,A1:A0,A1:A0
+	ADDU	A23,B1:B0,B1:B0
+||	MPY32U	A18,B18,A23:A22	; a[2]*b[2]
+||	ADDU	A24,A1:A0,A1:A0
+	ADDU	A25,B1:B0,B1:B0
+||	MPY32U	A17,B19,A25:A24	; a[1]*b[3]
+||	ADDU	A26,A1:A0,A1:A0
+	ADDU	A27,B1:B0,B1:B0
+||	ADDU	B8,A1:A0,A1:A0
+	STW	A0,*ARG0[3]
+||	MPY32U	A19,B18,A27:A26	; a[3]*b[2]
+||	ADDU	A20,A1,A9:A8
+	ADDU	A21,B1,B9:B8
+||	MPY32U	A18,B19,A29:A28	; a[2]*b[3]
+||	ADDU	A22,A9:A8,A9:A8
+	ADDU	A23,B9:B8,B9:B8
+||	MPY32U	A19,B19,A31:A30	; a[3]*b[3]
+||	ADDU	A24,A9:A8,A9:A8
+	ADDU	A25,B9:B8,B9:B8
+||	ADDU	B0,A9:A8,A9:A8
+	STW	A8,*ARG0[4]
+||	ADDU	A26,A9,A1:A0
+	ADDU	A27,B9,B1:B0
+||	ADDU	A28,A1:A0,A1:A0
+	ADDU	A29,B1:B0,B1:B0
+||	BNOP	RA
+||	ADDU	B8,A1:A0,A1:A0
+	STW	A0,*ARG0[5]
+||	ADDU	A30,A1,A9:A8
+	ADD	A31,B1,B8
+	ADDU	B0,A9:A8,A9:A8	; removed || to avoid cross-path stall below
+	ADD	B8,A9,A9
+||	STW	A8,*ARG0[6]
+	STW	A9,*ARG0[7]
+	.endif
+	.endasmfunc

crypto/bn/asm/c64xplus-gf2m.pl

@@ -0,0 +1,146 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# February 2012
+#
+# The module implements bn_GF2m_mul_2x2 polynomial multiplication
+# used in bn_gf2m.c. It's kind of low-hanging mechanical port from
+# C for the time being... The subroutine runs in 37 cycles, which is
+# 4.5x faster than compiler-generated code. Though comparison is
+# totally unfair, because this module utilizes Galois Field Multiply
+# instruction.
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+($rp,$a1,$a0,$b1,$b0)=("A4","B4","A6","B6","A8");   # argument vector
+
+($Alo,$Alox0,$Alox1,$Alox2,$Alox3)=map("A$_",(16..20));
+($Ahi,$Ahix0,$Ahix1,$Ahix2,$Ahix3)=map("B$_",(16..20));
+($B_0,$B_1,$B_2,$B_3)=("B5","A5","A7","B7");
+($A,$B)=($Alo,$B_1);
+$xFF="B1";
+
+sub mul_1x1_upper {
+my ($A,$B)=@_;
+$code.=<<___;
+	EXTU	$B,8,24,$B_2		; smash $B to 4 bytes
+||	AND	$B,$xFF,$B_0
+||	SHRU	$B,24,$B_3
+	SHRU	$A,16,   $Ahi		; smash $A to two halfwords
+||	EXTU	$A,16,16,$Alo
+
+	XORMPY	$Alo,$B_2,$Alox2	; 16x8 bits muliplication
+||	XORMPY	$Ahi,$B_2,$Ahix2
+||	EXTU	$B,16,24,$B_1
+	XORMPY	$Alo,$B_0,$Alox0
+||	XORMPY	$Ahi,$B_0,$Ahix0
+	XORMPY	$Alo,$B_3,$Alox3
+||	XORMPY	$Ahi,$B_3,$Ahix3
+	XORMPY	$Alo,$B_1,$Alox1
+||	XORMPY	$Ahi,$B_1,$Ahix1
+___
+}
+sub mul_1x1_merged {
+my ($OUTlo,$OUThi,$A,$B)=@_;
+$code.=<<___;
+	 EXTU	$B,8,24,$B_2		; smash $B to 4 bytes
+||	 AND	$B,$xFF,$B_0
+||	 SHRU	$B,24,$B_3
+	 SHRU	$A,16,   $Ahi		; smash $A to two halfwords
+||	 EXTU	$A,16,16,$Alo
+
+	XOR	$Ahix0,$Alox2,$Ahix0
+||	MV	$Ahix2,$OUThi
+||	 XORMPY	$Alo,$B_2,$Alox2
+	 XORMPY	$Ahi,$B_2,$Ahix2
+||	 EXTU	$B,16,24,$B_1
+||	 XORMPY	$Alo,$B_0,A1		; $Alox0
+	XOR	$Ahix1,$Alox3,$Ahix1
+||	SHL	$Ahix0,16,$OUTlo
+||	SHRU	$Ahix0,16,$Ahix0
+	XOR	$Alox0,$OUTlo,$OUTlo
+||	XOR	$Ahix0,$OUThi,$OUThi
+||	 XORMPY	$Ahi,$B_0,$Ahix0
+||	 XORMPY	$Alo,$B_3,$Alox3
+||	SHL	$Alox1,8,$Alox1
+||	SHL	$Ahix3,8,$Ahix3
+	XOR	$Alox1,$OUTlo,$OUTlo
+||	XOR	$Ahix3,$OUThi,$OUThi
+||	 XORMPY	$Ahi,$B_3,$Ahix3
+||	SHL	$Ahix1,24,$Alox1
+||	SHRU	$Ahix1,8, $Ahix1
+	XOR	$Alox1,$OUTlo,$OUTlo
+||	XOR	$Ahix1,$OUThi,$OUThi
+||	 XORMPY	$Alo,$B_1,$Alox1
+||	 XORMPY	$Ahi,$B_1,$Ahix1
+||	 MV	A1,$Alox0
+___
+}
+sub mul_1x1_lower {
+my ($OUTlo,$OUThi)=@_;
+$code.=<<___;
+	;NOP
+	XOR	$Ahix0,$Alox2,$Ahix0
+||	MV	$Ahix2,$OUThi
+	NOP
+	XOR	$Ahix1,$Alox3,$Ahix1
+||	SHL	$Ahix0,16,$OUTlo
+||	SHRU	$Ahix0,16,$Ahix0
+	XOR	$Alox0,$OUTlo,$OUTlo
+||	XOR	$Ahix0,$OUThi,$OUThi
+||	SHL	$Alox1,8,$Alox1
+||	SHL	$Ahix3,8,$Ahix3
+	XOR	$Alox1,$OUTlo,$OUTlo
+||	XOR	$Ahix3,$OUThi,$OUThi
+||	SHL	$Ahix1,24,$Alox1
+||	SHRU	$Ahix1,8, $Ahix1
+	XOR	$Alox1,$OUTlo,$OUTlo
+||	XOR	$Ahix1,$OUThi,$OUThi
+___
+}
+$code.=<<___;
+	.text
+
+	.global	_bn_GF2m_mul_2x2
+_bn_GF2m_mul_2x2:
+	.asmfunc
+	MVK	0xFF,$xFF
+___
+	&mul_1x1_upper($a0,$b0);		# a0<61>b0
+$code.=<<___;
+||	MV	$b1,$B
+	MV	$a1,$A
+___
+	&mul_1x1_merged("A28","B28",$A,$B);	# a0<61>b0/a1<61>b1
+$code.=<<___;
+||	XOR	$b0,$b1,$B
+	XOR	$a0,$a1,$A
+___
+	&mul_1x1_merged("A31","B31",$A,$B);	# a1<61>b1/(a0+a1)<29>(b0+b1)
+$code.=<<___;
+	XOR	A28,A31,A29
+||	XOR	B28,B31,B29			; a0<61>b0+a1<61>b1
+___
+	&mul_1x1_lower("A30","B30");		# (a0+a1)<29>(b0+b1)
+$code.=<<___;
+||	BNOP	B3
+	XOR	A29,A30,A30
+||	XOR	B29,B30,B30			; (a0+a1)<29>(b0+b1)-a0<61>b0-a1<61>b1
+	XOR	B28,A30,A30
+||	STW	A28,*${rp}[0]
+	XOR	B30,A31,A31
+||	STW	A30,*${rp}[1]
+	STW	A31,*${rp}[2]
+	STW	B31,*${rp}[3]
+	.endasmfunc
+___
+
+print $code;
+close STDOUT;

crypto/bn/bn_nist.c

@@ -366,6 +366,10 @@ static void nist_cp_bn(BN_ULONG *buf, BN_ULONG *a, int top)
 # endif
 #endif /* BN_BITS2 != 64 */
 
+#if defined(_TMS320C6X) && defined(NIST_INT64)
+# undef NIST_INT64     /* compiler bug */
+# pragma diag_suppress 177
+#endif
 
 #define nist_set_192(to, from, a1, a2, a3) \
 	{ \
@@ -1047,6 +1051,11 @@ int BN_nist_mod_384(BIGNUM *r, const BIGNUM *a, const BIGNUM *field,
 	return 1;
 	}
 
+#ifdef _WIN32_WCE
+/* Workaround for compiler bug under CE */
+#pragma optimize( "", off )
+#endif
+
 #define BN_NIST_521_RSHIFT	(521%BN_BITS2)
 #define BN_NIST_521_LSHIFT	(BN_BITS2-BN_NIST_521_RSHIFT)
 #define BN_NIST_521_TOP_MASK	((BN_ULONG)BN_MASK2>>BN_NIST_521_LSHIFT)
@@ -1113,6 +1122,10 @@ int BN_nist_mod_521(BIGNUM *r, const BIGNUM *a, const BIGNUM *field,
 	return 1;
 	}
 
+#ifdef _WIN32_WCE
+#pragma optimize( "", on )
+#endif
+
 int (*BN_nist_mod_func(const BIGNUM *p))(BIGNUM *r, const BIGNUM *a, const BIGNUM *field, BN_CTX *ctx)
 	{
 	if (BN_ucmp(&_bignum_nist_p_192, p) == 0)

crypto/c64xpluscpuid.pl

@@ -0,0 +1,246 @@
+#!/usr/bin/env perl
+#
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$code.=<<___;
+	.text
+
+	.asg	B3,RA
+
+	.global	_OPENSSL_rdtsc
+_OPENSSL_rdtsc:
+	.asmfunc
+	B	RA
+	MVC	TSCL,B0
+	MVC	TSCH,B1
+  [!B0]	MVC	B0,TSCL		; start TSC
+	MV	B0,A4
+	MV	B1,A5
+	.endasmfunc
+
+	.global	_OPENSSL_cleanse
+_OPENSSL_cleanse:
+	.asmfunc
+	ZERO	A3:A2
+||	ZERO	B2
+||	SHRU	B4,3,B0		; is length >= 8
+||	ADD	1,A4,B6
+  [!B0]	BNOP	RA
+||	ZERO	A1
+||	ZERO	B1
+   [B0]	MVC	B0,ILC
+||[!B0]	CMPLT	0,B4,A1
+||[!B0]	CMPLT	1,B4,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+||[!B0]	CMPLT	2,B4,A1
+||[!B0]	CMPLT	3,B4,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+||[!B0]	CMPLT	4,B4,A1
+||[!B0]	CMPLT	5,B4,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+||[!B0]	CMPLT	6,B4,A1
+   [A1]	STB	A2,*A4++[2]
+
+	SPLOOP	1
+	STNDW	A3:A2,*A4++
+||	SUB	B4,8,B4
+	SPKERNEL
+
+	MV	B4,B0		; remaining bytes
+||	ADD	1,A4,B6
+||	BNOP	RA
+   [B0]	CMPLT	0,B0,A1
+|| [B0]	CMPLT	1,B0,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+|| [B0]	CMPLT	2,B0,A1
+|| [B0]	CMPLT	3,B0,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+|| [B0]	CMPLT	4,B0,A1
+|| [B0]	CMPLT	5,B0,B1
+   [A1]	STB	A2,*A4++[2]
+|| [B1] STB	B2,*B6++[2]
+|| [B0]	CMPLT	6,B0,A1
+   [A1]	STB	A2,*A4++[2]
+	.endasmfunc
+
+	.global	_OPENSSL_atomic_add
+_OPENSSL_atomic_add:
+	.asmfunc
+	MV	A4,B0
+atomic_add?:
+	LL	*B0,B5
+	NOP	4
+	ADD	B4,B5,B5
+	SL	B5,*B0
+	CMTL	*B0,B1
+	NOP	4
+  [!B1]	B	atomic_add?
+   [B1]	BNOP	RA,4
+	MV	B5,A4
+	.endasmfunc
+
+	.global	_OPENSSL_wipe_cpu
+_OPENSSL_wipe_cpu:
+	.asmfunc
+	ZERO	A0
+||	ZERO	B0
+||	ZERO	A1
+||	ZERO	B1
+	ZERO	A3:A2
+||	MVD	B0,B2
+||	ZERO	A4
+||	ZERO	B4
+||	ZERO	A5
+||	ZERO	B5
+||	BNOP	RA
+	ZERO	A7:A6
+||	ZERO	B7:B6
+||	ZERO	A8
+||	ZERO	B8
+||	ZERO	A9
+||	ZERO	B9
+	ZERO	A17:A16
+||	ZERO	B17:B16
+||	ZERO	A18
+||	ZERO	B18
+||	ZERO	A19
+||	ZERO	B19
+	ZERO	A21:A20
+||	ZERO	B21:B20
+||	ZERO	A22
+||	ZERO	B22
+||	ZERO	A23
+||	ZERO	B23
+	ZERO	A25:A24
+||	ZERO	B25:B24
+||	ZERO	A26
+||	ZERO	B26
+||	ZERO	A27
+||	ZERO	B27
+	ZERO	A29:A28
+||	ZERO	B29:B28
+||	ZERO	A30
+||	ZERO	B30
+||	ZERO	A31
+||	ZERO	B31
+	.endasmfunc
+
+CLFLUSH	.macro	CONTROL,ADDR,LEN
+	B	passthrough?
+||	STW	ADDR,*CONTROL[0]
+	STW	LEN,*CONTROL[1]
+spinlock?:
+	LDW	*CONTROL[1],A0
+	NOP	3
+passthrough?:
+	NOP
+  [A0]	BNOP	spinlock?,5
+	.endm
+
+	.global	_OPENSSL_instrument_bus
+_OPENSSL_instrument_bus:
+	.asmfunc
+	MV	B4,B0			; reassign sizeof(output)
+||	MV	A4,B4			; reassign output
+||	MVK	0x00004030,A3
+	MV	B0,A4			; return value
+||	MVK	1,A1
+||	MVKH	0x01840000,A3		; L1DWIBAR
+	MVC	TSCL,B8			; collect 1st tick
+||	MVK	0x00004010,A5
+	MV	B8,B9			; lasttick = tick
+||	MVK	0,B7			; lastdiff = 0
+||	MVKH	0x01840000,A5		; L2WIBAR
+	CLFLUSH	A3,B4,A1		; write-back and invalidate L1D line
+	CLFLUSH	A5,B4,A1		; write-back and invalidate L2 line
+	LL	*B4,B5
+	NOP	4
+	ADD	B7,B5,B5
+	SL	B5,*B4
+	CMTL	*B4,B1
+	NOP	4
+	STW	B5,*B4
+bus_loop1?:
+	MVC	TSCL,B8
+|| [B0]	SUB	B0,1,B0
+	SUB	B8,B9,B7		; lastdiff = tick - lasttick
+||	MV	B8,B9			; lasttick = tick
+	CLFLUSH	A3,B4,A1		; write-back and invalidate L1D line
+	CLFLUSH	A5,B4,A1		; write-back and invalidate L2 line
+	LL	*B4,B5
+	NOP	4
+	ADD	B7,B5,B5
+	SL	B5,*B4
+	CMTL	*B4,B1
+	STW	B5,*B4			; [!B1] is removed to flatten samples
+||	ADDK	4,B4
+|| [B0]	BNOP	bus_loop1?,5
+
+	BNOP	RA,5
+	.endasmfunc
+
+	.global	_OPENSSL_instrument_bus2
+_OPENSSL_instrument_bus2:
+	.asmfunc
+	MV	A6,B0			; reassign max
+||	MV	B4,A6			; reassing sizeof(output)
+||	MVK	0x00004030,A3
+	MV	A4,B4			; reassign output
+||	MVK	0,A4			; return value
+||	MVK	1,A1
+||	MVKH	0x01840000,A3		; L1DWIBAR
+
+	MVC	TSCL,B8			; collect 1st tick
+||	MVK	0x00004010,A5
+	MV	B8,B9			; lasttick = tick
+||	MVK	0,B7			; lastdiff = 0
+||	MVKH	0x01840000,A5		; L2WIBAR
+	CLFLUSH	A3,B4,A1		; write-back and invalidate L1D line
+	CLFLUSH	A5,B4,A1		; write-back and invalidate L2 line
+	LL	*B4,B5
+	NOP	4
+	ADD	B7,B5,B5
+	SL	B5,*B4
+	CMTL	*B4,B1
+	NOP	4
+	STW	B5,*B4
+
+	MVC	TSCL,B8			; collect 1st diff
+	SUB	B8,B9,B7		; lastdiff = tick - lasttick
+||	MV	B8,B9			; lasttick = tick
+||	SUB	B0,1,B0
+bus_loop2?:
+	CLFLUSH	A3,B4,A1		; write-back and invalidate L1D line
+	CLFLUSH	A5,B4,A1		; write-back and invalidate L2 line
+	LL	*B4,B5
+	NOP	4
+	ADD	B7,B5,B5
+	SL	B5,*B4
+	CMTL	*B4,B1
+	STW	B5,*B4			; [!B1] is removed to flatten samples
+||[!B0]	BNOP	bus_loop2_done?,2
+||	SUB	B0,1,B0
+	MVC	TSCL,B8
+	SUB	B8,B9,B8
+||	MV	B8,B9
+	CMPEQ	B8,B7,B2
+||	MV	B8,B7
+  [!B2]	ADDAW	B4,1,B4
+||[!B2]	ADDK	1,A4
+	CMPEQ	A4,A6,A2
+  [!A2]	BNOP	bus_loop2?,5
+
+bus_loop2_done?:
+	BNOP	RA,5
+	.endasmfunc
+___
+
+print $code;
+close STDOUT;

crypto/cmac/cmac.c

@@ -77,19 +77,17 @@ struct CMAC_CTX_st
 
 /* Make temporary keys K1 and K2 */
 
-static void make_kn(unsigned char *k1, unsigned char *l, int bl)
+static void make_kn(unsigned char *k1, const unsigned char *l, int bl)
 	{
 	int i;
+	unsigned char c = l[0], carry = c>>7, cnext;
+
 	/* Shift block to left, including carry */
-	for (i = 0; i < bl; i++)
-		{
-		k1[i] = l[i] << 1;
-		if (i < bl - 1 && l[i + 1] & 0x80)
-			k1[i] |= 1;
-		}
+	for (i = 0; i < bl-1; i++, c = cnext)
+		k1[i] = (c << 1) | ((cnext=l[i+1]) >> 7);
+
 	/* If MSB set fixup with R */
-	if (l[0] & 0x80)
-		k1[bl - 1] ^= bl == 16 ? 0x87 : 0x1b;
+	k1[i] = (c << 1) ^ ((0-carry)&(bl==16?0x87:0x1b));
 	}
 
 CMAC_CTX *CMAC_CTX_new(void)
@@ -143,7 +141,8 @@ int CMAC_CTX_copy(CMAC_CTX *out, const CMAC_CTX *in)
 int CMAC_Init(CMAC_CTX *ctx, const void *key, size_t keylen, 
 			const EVP_CIPHER *cipher, ENGINE *impl)
 	{
-	static unsigned char zero_iv[EVP_MAX_BLOCK_LENGTH];
+	__fips_constseg
+	static const unsigned char zero_iv[EVP_MAX_BLOCK_LENGTH] = {0};
 	/* All zeros means restart */
 	if (!key && !cipher && !impl && keylen == 0)
 		{
@@ -152,6 +151,8 @@ int CMAC_Init(CMAC_CTX *ctx, const void *key, size_t keylen,
 			return 0;
 		if (!M_EVP_EncryptInit_ex(&ctx->cctx, NULL, NULL, NULL, zero_iv))
 			return 0;
+		memset(ctx->tbl, 0, M_EVP_CIPHER_CTX_block_size(&ctx->cctx));	
+		ctx->nlast_block = 0;
 		return 1;
 		}
 	/* Initialiase context */

crypto/cryptlib.c

@@ -297,7 +297,7 @@ void OPENSSL_showfatal (const char *fmta,...)
 	DWORD out;
 
 	va_start (ap,fmta);
-	len=_vsnprintf((char *)buf,sizeof(buf),fmt,ap);
+	len=_vsnprintf((char *)buf,sizeof(buf),fmta,ap);
 	WriteFile(h,buf,len<0?sizeof(buf):(DWORD)len,&out,NULL);
 	va_end (ap);
 	return;
@@ -382,7 +382,9 @@ void OpenSSLDie(const char *file,int line,const char *assertion)
 	abort();
 #else
 	/* Win32 abort() customarily shows a dialog, but we just did that... */
+#ifdef SIGABRT
 	raise(SIGABRT);
+#endif
 	_exit(3);
 #endif
 	}

crypto/des/spr.h

@@ -56,6 +56,9 @@
  * [including the GNU Public Licence.]
  */
 
+#ifdef _TMS320C6X
+#  pragma DATA_SECTION(DES_SPtrans,".const:des_sptrans")
+#endif
 __fips_constseg
 OPENSSL_GLOBAL const DES_LONG DES_SPtrans[8][64]={
 {

crypto/evp/e_aes.c

@@ -471,6 +471,35 @@ const EVP_CIPHER *EVP_aes_##keylen##_##mode(void) \
 { return &aes_##keylen##_##mode; }
 #endif
 
+#if defined(OPENSSL_CPUID_OBJ) && defined(__aarch64__)
+#include "arm_arch.h"
+#if __ARM_ARCH__>=7
+# 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)	\
@@ -489,6 +518,19 @@ 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);
+		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)
 		{
@@ -517,6 +559,26 @@ 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);
+		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)
 		{
@@ -795,6 +857,28 @@ static int aes_gcm_ctrl(EVP_CIPHER_CTX *c, int type, int arg, void *ptr)
 		/* Extra padding: tag appended to record */
 		return EVP_GCM_TLS_TAG_LEN;
 
+	case EVP_CTRL_COPY:
+		{
+			EVP_CIPHER_CTX *out = ptr;
+			EVP_AES_GCM_CTX *gctx_out = out->cipher_data;
+			if (gctx->gcm.key)
+				{
+				if (gctx->gcm.key != &gctx->ks)
+					return 0;
+				gctx_out->gcm.key = &gctx_out->ks;
+				}
+			if (gctx->iv == c->iv)
+				gctx_out->iv = out->iv;
+			else
+			{
+				gctx_out->iv = OPENSSL_malloc(gctx->ivlen);
+				if (!gctx_out->iv)
+					return 0;
+				memcpy(gctx_out->iv, gctx->iv, gctx->ivlen);
+			}
+			return 1;
+		}
+
 	default:
 		return -1;
 
@@ -809,6 +893,21 @@ static int aes_gcm_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 		return 1;
 	if (key)
 		{ do {
+#ifdef HWAES_CAPABLE
+		if (HWAES_CAPABLE)
+			{
+			HWAES_set_encrypt_key(key,ctx->key_len*8,&gctx->ks);
+			CRYPTO_gcm128_init(&gctx->gcm,&gctx->ks,
+					(block128_f)HWAES_encrypt);
+#ifdef HWAES_ctr32_encrypt_blocks
+			gctx->ctr = (ctr128_f)HWAES_ctr32_encrypt_blocks;
+#else
+			gctx->ctr = NULL;
+#endif
+			break;
+			}
+		else
+#endif
 #ifdef BSAES_CAPABLE
 		if (BSAES_CAPABLE)
 			{
@@ -956,8 +1055,6 @@ static int aes_gcm_cipher(EVP_CIPHER_CTX *ctx, unsigned char *out,
 
 	if (!gctx->iv_set)
 		return -1;
-	if (!ctx->encrypt && gctx->taglen < 0)
-		return -1;
 	if (in)
 		{
 		if (out == NULL)
@@ -999,6 +1096,8 @@ static int aes_gcm_cipher(EVP_CIPHER_CTX *ctx, unsigned char *out,
 		{
 		if (!ctx->encrypt)
 			{
+			if (gctx->taglen < 0)
+				return -1;
 			if (CRYPTO_gcm128_finish(&gctx->gcm,
 					ctx->buf, gctx->taglen) != 0)
 				return -1;
@@ -1016,7 +1115,8 @@ static int aes_gcm_cipher(EVP_CIPHER_CTX *ctx, unsigned char *out,
 
 #define CUSTOM_FLAGS	(EVP_CIPH_FLAG_DEFAULT_ASN1 \
 		| EVP_CIPH_CUSTOM_IV | EVP_CIPH_FLAG_CUSTOM_CIPHER \
-		| EVP_CIPH_ALWAYS_CALL_INIT | EVP_CIPH_CTRL_INIT)
+		| EVP_CIPH_ALWAYS_CALL_INIT | EVP_CIPH_CTRL_INIT \
+		| EVP_CIPH_CUSTOM_COPY)
 
 BLOCK_CIPHER_custom(NID_aes,128,1,12,gcm,GCM,
 		EVP_CIPH_FLAG_FIPS|EVP_CIPH_FLAG_AEAD_CIPHER|CUSTOM_FLAGS)
@@ -1028,7 +1128,25 @@ BLOCK_CIPHER_custom(NID_aes,256,1,12,gcm,GCM,
 static int aes_xts_ctrl(EVP_CIPHER_CTX *c, int type, int arg, void *ptr)
 	{
 	EVP_AES_XTS_CTX *xctx = c->cipher_data;
-	if (type != EVP_CTRL_INIT)
+	if (type == EVP_CTRL_COPY)
+		{
+		EVP_CIPHER_CTX *out = ptr;
+		EVP_AES_XTS_CTX *xctx_out = out->cipher_data;
+		if (xctx->xts.key1)
+			{
+			if (xctx->xts.key1 != &xctx->ks1)
+				return 0;
+			xctx_out->xts.key1 = &xctx_out->ks1;
+			}
+		if (xctx->xts.key2)
+			{
+			if (xctx->xts.key2 != &xctx->ks2)
+				return 0;
+			xctx_out->xts.key2 = &xctx_out->ks2;
+			}
+		return 1;
+		}
+	else if (type != EVP_CTRL_INIT)
 		return -1;
 	/* key1 and key2 are used as an indicator both key and IV are set */
 	xctx->xts.key1 = NULL;
@@ -1047,6 +1165,29 @@ static int aes_xts_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 		{
 		xctx->stream = NULL;
 		/* key_len is two AES keys */
+#ifdef HWAES_CAPABLE
+		if (HWAES_CAPABLE)
+			{
+			if (enc)
+			    {
+			    HWAES_set_encrypt_key(key, ctx->key_len * 4, &xctx->ks1);
+			    xctx->xts.block1 = (block128_f)HWAES_encrypt;
+			    }
+			else
+			    {
+			    HWAES_set_decrypt_key(key, ctx->key_len * 4, &xctx->ks1);
+			    xctx->xts.block1 = (block128_f)HWAES_decrypt;
+			    }
+
+			HWAES_set_encrypt_key(key + ctx->key_len/2,
+						    ctx->key_len * 4, &xctx->ks2);
+			xctx->xts.block2 = (block128_f)HWAES_encrypt;
+
+			xctx->xts.key1 = &xctx->ks1;
+			break;
+			}
+		else
+#endif
 #ifdef VPAES_CAPABLE
 		if (VPAES_CAPABLE)
 		    {
@@ -1125,7 +1266,8 @@ static int aes_xts_cipher(EVP_CIPHER_CTX *ctx, unsigned char *out,
 #define aes_xts_cleanup NULL
 
 #define XTS_FLAGS	(EVP_CIPH_FLAG_DEFAULT_ASN1 | EVP_CIPH_CUSTOM_IV \
-			 | EVP_CIPH_ALWAYS_CALL_INIT | EVP_CIPH_CTRL_INIT)
+			 | EVP_CIPH_ALWAYS_CALL_INIT | EVP_CIPH_CTRL_INIT \
+			 | EVP_CIPH_CUSTOM_COPY)
 
 BLOCK_CIPHER_custom(NID_aes,128,1,16,xts,XTS,EVP_CIPH_FLAG_FIPS|XTS_FLAGS)
 BLOCK_CIPHER_custom(NID_aes,256,1,16,xts,XTS,EVP_CIPH_FLAG_FIPS|XTS_FLAGS)
@@ -1175,6 +1317,19 @@ static int aes_ccm_ctrl(EVP_CIPHER_CTX *c, int type, int arg, void *ptr)
 		cctx->len_set = 0;
 		return 1;
 
+	case EVP_CTRL_COPY:
+		{
+			EVP_CIPHER_CTX *out = ptr;
+			EVP_AES_CCM_CTX *cctx_out = out->cipher_data;
+			if (cctx->ccm.key)
+				{
+				if (cctx->ccm.key != &cctx->ks)
+					return 0;
+				cctx_out->ccm.key = &cctx_out->ks;
+				}
+			return 1;
+		}
+
 	default:
 		return -1;
 
@@ -1189,12 +1344,26 @@ static int aes_ccm_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 		return 1;
 	if (key) do
 		{
+#ifdef HWAES_CAPABLE
+		if (HWAES_CAPABLE)
+			{
+			HWAES_set_encrypt_key(key,ctx->key_len*8,&cctx->ks);
+
+			CRYPTO_ccm128_init(&cctx->ccm, cctx->M, cctx->L,
+					&cctx->ks, (block128_f)HWAES_encrypt);
+			cctx->str = NULL;
+			cctx->key_set = 1;
+			break;
+			}
+		else
+#endif
 #ifdef VPAES_CAPABLE
 		if (VPAES_CAPABLE)
 			{
 			vpaes_set_encrypt_key(key, ctx->key_len*8, &cctx->ks);
 			CRYPTO_ccm128_init(&cctx->ccm, cctx->M, cctx->L,
 					&cctx->ks, (block128_f)vpaes_encrypt);
+			cctx->str = NULL;
 			cctx->key_set = 1;
 			break;
 			}

crypto/modes/Makefile

@@ -56,11 +56,14 @@ ghash-alpha.s:	asm/ghash-alpha.pl
 	$(PERL) $< | $(CC) -E - | tee $@ > /dev/null
 ghash-parisc.s:	asm/ghash-parisc.pl
 	$(PERL) asm/ghash-parisc.pl $(PERLASM_SCHEME) $@
+ghashv8-armx.S:	asm/ghashv8-armx.pl
+	$(PERL) asm/ghashv8-armx.pl $(PERLASM_SCHEME) $@
 
 # GNU make "catch all"
 ghash-%.S:	asm/ghash-%.pl;	$(PERL) $< $(PERLASM_SCHEME) $@
 
 ghash-armv4.o:	ghash-armv4.S
+ghashv8-armx.o:	ghashv8-armx.S
 
 files:
 	$(PERL) $(TOP)/util/files.pl Makefile >> $(TOP)/MINFO

crypto/modes/asm/ghash-armv4.pl

@@ -57,8 +57,20 @@
 # *native* byte order on current platform. See gcm128.c for working
 # example...
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $Xi="r0";	# argument block
 $Htbl="r1";
@@ -112,6 +124,11 @@ $code=<<___;
 .text
 .code	32
 
+#ifdef  __APPLE__
+#define ldrplb	ldrbpl
+#define ldrneb	ldrbne
+#endif
+
 .type	rem_4bit,%object
 .align	5
 rem_4bit:
@@ -326,9 +343,9 @@ $code.=<<___;
 .align	4
 gcm_gmult_neon:
 	sub		$Htbl,#16		@ point at H in GCM128_CTX
-	vld1.64		`&Dhi("$IN")`,[$Xi,:64]!@ load Xi
+	vld1.64		`&Dhi("$IN")`,[$Xi]!	@ load Xi
 	vmov.i32	$mod,#0xe1		@ our irreducible polynomial
-	vld1.64		`&Dlo("$IN")`,[$Xi,:64]!
+	vld1.64		`&Dlo("$IN")`,[$Xi]!
 	vshr.u64	$mod,#32
 	vldmia		$Htbl,{$Hhi-$Hlo}	@ load H
 	veor		$zero,$zero
@@ -349,9 +366,9 @@ gcm_gmult_neon:
 .type	gcm_ghash_neon,%function
 .align	4
 gcm_ghash_neon:
-	vld1.64		`&Dhi("$Z")`,[$Xi,:64]!	@ load Xi
+	vld1.64		`&Dhi("$Z")`,[$Xi]!	@ load Xi
 	vmov.i32	$mod,#0xe1		@ our irreducible polynomial
-	vld1.64		`&Dlo("$Z")`,[$Xi,:64]!
+	vld1.64		`&Dlo("$Z")`,[$Xi]!
 	vshr.u64	$mod,#32
 	vldmia		$Xi,{$Hhi-$Hlo}		@ load H
 	veor		$zero,$zero
@@ -410,8 +427,8 @@ gcm_ghash_neon:
 	vrev64.8	$Z,$Z
 #endif
 	sub		$Xi,#16	
-	vst1.64		`&Dhi("$Z")`,[$Xi,:64]!	@ write out Xi
-	vst1.64		`&Dlo("$Z")`,[$Xi,:64]
+	vst1.64		`&Dhi("$Z")`,[$Xi]!	@ write out Xi
+	vst1.64		`&Dlo("$Z")`,[$Xi]
 
 	bx	lr
 .size	gcm_ghash_neon,.-gcm_ghash_neon

crypto/modes/asm/ghash-c64xplus.pl

@@ -0,0 +1,231 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# December 2011
+#
+# The module implements GCM GHASH function and underlying single
+# multiplication operation in GF(2^128). Even though subroutines
+# have _4bit suffix, they are not using any tables, but rely on
+# hardware Galois Field Multiply support. Streamed GHASH processes
+# byte in ~7 cycles, which is >6x faster than "4-bit" table-driven
+# code compiled with TI's cl6x 6.0 with -mv6400+ -o2 flags. We are
+# comparing apples vs. oranges, but compiler surely could have done
+# better, because theoretical [though not necessarily achievable]
+# estimate for "4-bit" table-driven implementation is ~12 cycles.
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+($Xip,$Htable,$inp,$len)=("A4","B4","A6","B6");	# arguments
+
+($Z0,$Z1,$Z2,$Z3,	$H0, $H1, $H2, $H3,
+			$H0x,$H1x,$H2x,$H3x)=map("A$_",(16..27));
+($H01u,$H01y,$H2u,$H3u,	$H0y,$H1y,$H2y,$H3y,
+			$H0z,$H1z,$H2z,$H3z)=map("B$_",(16..27));
+($FF000000,$E10000)=("B30","B31");
+($xip,$x0,$x1,$xib)=map("B$_",(6..9));	# $xip zaps $len
+ $xia="A9";
+($rem,$res)=("B4","B5");		# $rem zaps $Htable
+
+$code.=<<___;
+	.text
+
+	.asg	B3,RA
+
+	.if	0
+	.global	_gcm_gmult_1bit
+_gcm_gmult_1bit:
+	ADDAD	$Htable,2,$Htable
+	.endif
+	.global	_gcm_gmult_4bit
+_gcm_gmult_4bit:
+	.asmfunc
+	LDDW	*${Htable}[-1],$H1:$H0	; H.lo
+	LDDW	*${Htable}[-2],$H3:$H2	; H.hi
+||	MV	$Xip,${xip}		; reassign Xi
+||	MVK	15,B1			; SPLOOPD constant
+
+	MVK	0xE1,$E10000
+||	LDBU	*++${xip}[15],$x1	; Xi[15]
+	MVK	0xFF,$FF000000
+||	LDBU	*--${xip},$x0		; Xi[14]
+	SHL	$E10000,16,$E10000	; [pre-shifted] reduction polynomial
+	SHL	$FF000000,24,$FF000000	; upper byte mask
+||	BNOP	ghash_loop?
+||	MVK	1,B0			; take a single spin
+
+	PACKH2	$H0,$H1,$xia		; pack H0' and H1's upper bytes
+	AND	$H2,$FF000000,$H2u	; H2's upper byte
+	AND	$H3,$FF000000,$H3u	; H3's upper byte
+||	SHRU	$H2u,8,$H2u
+	SHRU	$H3u,8,$H3u
+||	ZERO	$Z1:$Z0
+	SHRU2	$xia,8,$H01u
+||	ZERO	$Z3:$Z2
+	.endasmfunc
+
+	.global	_gcm_ghash_4bit
+_gcm_ghash_4bit:
+	.asmfunc
+	LDDW	*${Htable}[-1],$H1:$H0	; H.lo
+||	SHRU	$len,4,B0		; reassign len
+	LDDW	*${Htable}[-2],$H3:$H2	; H.hi
+||	MV	$Xip,${xip}		; reassign Xi
+||	MVK	15,B1			; SPLOOPD constant
+
+	MVK	0xE1,$E10000
+|| [B0]	LDNDW	*${inp}[1],$H1x:$H0x
+	MVK	0xFF,$FF000000
+|| [B0]	LDNDW	*${inp}++[2],$H3x:$H2x
+	SHL	$E10000,16,$E10000	; [pre-shifted] reduction polynomial
+||	LDDW	*${xip}[1],$Z1:$Z0
+	SHL	$FF000000,24,$FF000000	; upper byte mask
+||	LDDW	*${xip}[0],$Z3:$Z2
+
+	PACKH2	$H0,$H1,$xia		; pack H0' and H1's upper bytes
+	AND	$H2,$FF000000,$H2u	; H2's upper byte
+	AND	$H3,$FF000000,$H3u	; H3's upper byte
+||	SHRU	$H2u,8,$H2u
+	SHRU	$H3u,8,$H3u
+	SHRU2	$xia,8,$H01u
+
+|| [B0]	XOR	$H0x,$Z0,$Z0		; Xi^=inp
+|| [B0]	XOR	$H1x,$Z1,$Z1
+	.if	.LITTLE_ENDIAN
+   [B0]	XOR	$H2x,$Z2,$Z2
+|| [B0]	XOR	$H3x,$Z3,$Z3
+|| [B0]	SHRU	$Z1,24,$xia		; Xi[15], avoid cross-path stall
+	STDW	$Z1:$Z0,*${xip}[1]
+|| [B0]	SHRU	$Z1,16,$x0		; Xi[14]
+|| [B0]	ZERO	$Z1:$Z0
+	.else
+   [B0]	XOR	$H2x,$Z2,$Z2
+|| [B0]	XOR	$H3x,$Z3,$Z3
+|| [B0]	MV	$Z0,$xia		; Xi[15], avoid cross-path stall
+	STDW	$Z1:$Z0,*${xip}[1]
+|| [B0] SHRU	$Z0,8,$x0		; Xi[14]
+|| [B0]	ZERO	$Z1:$Z0
+	.endif
+	STDW	$Z3:$Z2,*${xip}[0]
+|| [B0]	ZERO	$Z3:$Z2
+|| [B0]	MV	$xia,$x1
+   [B0]	ADDK	14,${xip}
+
+ghash_loop?:
+	SPLOOPD	6			; 6*16+7
+||	MVC	B1,ILC
+|| [B0]	SUB	B0,1,B0
+||	ZERO	A0
+||	ADD	$x1,$x1,$xib		; SHL	$x1,1,$xib
+||	SHL	$x1,1,$xia
+___
+
+########____________________________
+#  0    D2.     M1          M2      |
+#  1            M1                  |
+#  2            M1          M2      |
+#  3        D1. M1          M2      |
+#  4        S1. L1                  |
+#  5    S2  S1x L1          D2  L2  |____________________________
+#  6/0          L1  S1      L2  S2x |D2.     M1          M2      |
+#  7/1          L1  S1  D1x S2  M2  |        M1                  |
+#  8/2              S1  L1x S2      |        M1          M2      |
+#  9/3              S1  L1x         |    D1. M1          M2      |
+# 10/4                  D1x         |    S1. L1                  |
+# 11/5                              |S2  S1x L1          D2  L2  |____________
+# 12/6/0                D1x       __|        L1  S1      L2  S2x |D2.     ....
+#    7/1                                     L1  S1  D1x S2  M2  |        ....
+#    8/2                                         S1  L1x S2      |        ....
+#####...                                         ................|............
+$code.=<<___;
+	XORMPY	$H0,$xia,$H0x		; 0	; H<>Xi[i]
+||	XORMPY	$H01u,$xib,$H01y
+|| [A0]	LDBU	*--${xip},$x0
+	XORMPY	$H1,$xia,$H1x		; 1
+	XORMPY	$H2,$xia,$H2x		; 2
+||	XORMPY	$H2u,$xib,$H2y
+	XORMPY	$H3,$xia,$H3x		; 3
+||	XORMPY	$H3u,$xib,$H3y
+||[!A0]	MVK.D	15,A0				; *--${xip} counter
+	XOR.L	$H0x,$Z0,$Z0		; 4	; Z^=H<>Xi[i]
+|| [A0]	SUB.S	A0,1,A0
+	XOR.L	$H1x,$Z1,$Z1		; 5
+||	AND.D	$H01y,$FF000000,$H0z
+||	SWAP2.L	$H01y,$H1y		;	; SHL	$H01y,16,$H1y
+||	SHL	$x0,1,$xib
+||	SHL	$x0,1,$xia
+
+	XOR.L	$H2x,$Z2,$Z2		; 6/0	; [0,0] in epilogue
+||	SHL	$Z0,1,$rem		;	; rem=Z<<1
+||	SHRMB.S	$Z1,$Z0,$Z0		;	; Z>>=8
+||	AND.L	$H1y,$FF000000,$H1z
+	XOR.L	$H3x,$Z3,$Z3		; 7/1
+||	SHRMB.S	$Z2,$Z1,$Z1
+||	XOR.D	$H0z,$Z0,$Z0			; merge upper byte products
+||	AND.S	$H2y,$FF000000,$H2z
+||	XORMPY	$E10000,$rem,$res	;	; implicit rem&0x1FE
+	XOR.L	$H1z,$Z1,$Z1		; 8/2
+||	SHRMB.S	$Z3,$Z2,$Z2
+||	AND.S	$H3y,$FF000000,$H3z
+	XOR.L	$H2z,$Z2,$Z2		; 9/3
+||	SHRU	$Z3,8,$Z3
+	XOR.D	$H3z,$Z3,$Z3		; 10/4
+	NOP				; 11/5
+
+	SPKERNEL 0,2
+||	XOR.D	$res,$Z3,$Z3		; 12/6/0; Z^=res
+
+	; input pre-fetch is possible where D1 slot is available...
+   [B0]	LDNDW	*${inp}[1],$H1x:$H0x	; 8/-
+   [B0]	LDNDW	*${inp}++[2],$H3x:$H2x	; 9/-
+	NOP				; 10/-
+	.if	.LITTLE_ENDIAN
+	SWAP2	$Z0,$Z1			; 11/-
+||	SWAP4	$Z1,$Z0
+	SWAP4	$Z1,$Z1			; 12/-
+||	SWAP2	$Z0,$Z0
+	SWAP2	$Z2,$Z3
+||	SWAP4	$Z3,$Z2
+||[!B0]	BNOP	RA
+	SWAP4	$Z3,$Z3
+||	SWAP2	$Z2,$Z2
+|| [B0]	BNOP	ghash_loop?
+   [B0]	XOR	$H0x,$Z0,$Z0		; Xi^=inp
+|| [B0]	XOR	$H1x,$Z1,$Z1
+   [B0]	XOR	$H2x,$Z2,$Z2
+|| [B0]	XOR	$H3x,$Z3,$Z3
+|| [B0]	SHRU	$Z1,24,$xia		; Xi[15], avoid cross-path stall
+	STDW	$Z1:$Z0,*${xip}[1]
+|| [B0]	SHRU	$Z1,16,$x0		; Xi[14]
+|| [B0]	ZERO	$Z1:$Z0
+	.else
+  [!B0]	BNOP	RA			; 11/-
+   [B0]	BNOP	ghash_loop?		; 12/-
+   [B0]	XOR	$H0x,$Z0,$Z0		; Xi^=inp
+|| [B0]	XOR	$H1x,$Z1,$Z1
+   [B0]	XOR	$H2x,$Z2,$Z2
+|| [B0]	XOR	$H3x,$Z3,$Z3
+|| [B0]	MV	$Z0,$xia		; Xi[15], avoid cross-path stall
+	STDW	$Z1:$Z0,*${xip}[1]
+|| [B0] SHRU	$Z0,8,$x0		; Xi[14]
+|| [B0]	ZERO	$Z1:$Z0
+	.endif
+	STDW	$Z3:$Z2,*${xip}[0]
+|| [B0]	ZERO	$Z3:$Z2
+|| [B0]	MV	$xia,$x1
+   [B0]	ADDK	14,${xip}
+	.endasmfunc
+
+	.sect	.const
+	.cstring "GHASH for C64x+, CRYPTOGAMS by <appro\@openssl.org>"
+	.align	4
+___
+
+print $code;
+close STDOUT;

crypto/modes/asm/ghashv8-armx.pl

@@ -0,0 +1,376 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# GHASH for ARMv8 Crypto Extension, 64-bit polynomial multiplication.
+#
+# June 2014
+#
+# Initial version was developed in tight cooperation with Ard
+# Biesheuvel <ard.biesheuvel@linaro.org> from bits-n-pieces from
+# other assembly modules. Just like aesv8-armx.pl this module
+# supports both AArch32 and AArch64 execution modes.
+#
+# July 2014
+#
+# Implement 2x aggregated reduction [see ghash-x86.pl for background
+# information].
+#
+# Current performance in cycles per processed byte:
+#
+#		PMULL[2]	32-bit NEON(*)
+# Apple A7	0.92		5.62
+# Cortex-A53	1.01		8.39
+# Cortex-A57	1.17		7.61
+#
+# (*)	presented for reference/comparison purposes;
+
+$flavour = shift;
+$output  = shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
+
+$Xi="x0";	# argument block
+$Htbl="x1";
+$inp="x2";
+$len="x3";
+
+$inc="x12";
+
+{
+my ($Xl,$Xm,$Xh,$IN)=map("q$_",(0..3));
+my ($t0,$t1,$t2,$xC2,$H,$Hhl,$H2)=map("q$_",(8..14));
+
+$code=<<___;
+#include "arm_arch.h"
+
+.text
+___
+$code.=".arch	armv8-a+crypto\n"	if ($flavour =~ /64/);
+$code.=".fpu	neon\n.code	32\n"	if ($flavour !~ /64/);
+
+$code.=<<___;
+.global	gcm_init_v8
+.type	gcm_init_v8,%function
+.align	4
+gcm_init_v8:
+	vld1.64		{$t1},[x1]		@ load H
+	vmov.i8		$xC2,#0xe1
+	vshl.i64	$xC2,$xC2,#57		@ 0xc2.0
+	vext.8		$IN,$t1,$t1,#8
+	vshr.u64	$t2,$xC2,#63
+	vdup.32		$t1,${t1}[1]
+	vext.8		$t0,$t2,$xC2,#8		@ t0=0xc2....01
+	vshr.u64	$t2,$IN,#63
+	vshr.s32	$t1,$t1,#31		@ broadcast carry bit
+	vand		$t2,$t2,$t0
+	vshl.i64	$IN,$IN,#1
+	vext.8		$t2,$t2,$t2,#8
+	vand		$t0,$t0,$t1
+	vorr		$IN,$IN,$t2		@ H<<<=1
+	veor		$H,$IN,$t0		@ twisted H
+	vst1.64		{$H},[x0],#16
+
+	@ calculate H^2
+	vext.8		$t0,$H,$H,#8		@ Karatsuba pre-processing
+	vpmull.p64	$Xl,$H,$H
+	veor		$t0,$t0,$H
+	vpmull2.p64	$Xh,$H,$H
+	vpmull.p64	$Xm,$t0,$t0
+
+	vext.8		$t1,$Xl,$Xh,#8		@ Karatsuba post-processing
+	veor		$t2,$Xl,$Xh
+	veor		$Xm,$Xm,$t1
+	veor		$Xm,$Xm,$t2
+	vpmull.p64	$t2,$Xl,$xC2		@ 1st phase
+
+	vmov		$Xh#lo,$Xm#hi		@ Xh|Xm - 256-bit result
+	vmov		$Xm#hi,$Xl#lo		@ Xm is rotated Xl
+	veor		$Xl,$Xm,$t2
+
+	vext.8		$t2,$Xl,$Xl,#8		@ 2nd phase
+	vpmull.p64	$Xl,$Xl,$xC2
+	veor		$t2,$t2,$Xh
+	veor		$H2,$Xl,$t2
+
+	vext.8		$t1,$H2,$H2,#8		@ Karatsuba pre-processing
+	veor		$t1,$t1,$H2
+	vext.8		$Hhl,$t0,$t1,#8		@ pack Karatsuba pre-processed
+	vst1.64		{$Hhl-$H2},[x0]
+
+	ret
+.size	gcm_init_v8,.-gcm_init_v8
+
+.global	gcm_gmult_v8
+.type	gcm_gmult_v8,%function
+.align	4
+gcm_gmult_v8:
+	vld1.64		{$t1},[$Xi]		@ load Xi
+	vmov.i8		$xC2,#0xe1
+	vld1.64		{$H-$Hhl},[$Htbl]	@ load twisted H, ...
+	vshl.u64	$xC2,$xC2,#57
+#ifndef __ARMEB__
+	vrev64.8	$t1,$t1
+#endif
+	vext.8		$IN,$t1,$t1,#8
+
+	vpmull.p64	$Xl,$H,$IN		@ H.lo<6C>Xi.lo
+	veor		$t1,$t1,$IN		@ Karatsuba pre-processing
+	vpmull2.p64	$Xh,$H,$IN		@ H.hi<68>Xi.hi
+	vpmull.p64	$Xm,$Hhl,$t1		@ (H.lo+H.hi)<29>(Xi.lo+Xi.hi)
+
+	vext.8		$t1,$Xl,$Xh,#8		@ Karatsuba post-processing
+	veor		$t2,$Xl,$Xh
+	veor		$Xm,$Xm,$t1
+	veor		$Xm,$Xm,$t2
+	vpmull.p64	$t2,$Xl,$xC2		@ 1st phase
+
+	vmov		$Xh#lo,$Xm#hi		@ Xh|Xm - 256-bit result
+	vmov		$Xm#hi,$Xl#lo		@ Xm is rotated Xl
+	veor		$Xl,$Xm,$t2
+
+	vext.8		$t2,$Xl,$Xl,#8		@ 2nd phase
+	vpmull.p64	$Xl,$Xl,$xC2
+	veor		$t2,$t2,$Xh
+	veor		$Xl,$Xl,$t2
+
+#ifndef __ARMEB__
+	vrev64.8	$Xl,$Xl
+#endif
+	vext.8		$Xl,$Xl,$Xl,#8
+	vst1.64		{$Xl},[$Xi]		@ write out Xi
+
+	ret
+.size	gcm_gmult_v8,.-gcm_gmult_v8
+
+.global	gcm_ghash_v8
+.type	gcm_ghash_v8,%function
+.align	4
+gcm_ghash_v8:
+___
+$code.=<<___		if ($flavour !~ /64/);
+	vstmdb		sp!,{d8-d15}
+___
+$code.=<<___;
+	vld1.64		{$Xl},[$Xi]		@ load [rotated] Xi
+	subs		$len,$len,#32
+	vmov.i8		$xC2,#0xe1
+	mov		$inc,#16
+	vld1.64		{$H-$Hhl},[$Htbl],#32	@ load twisted H, ..., H^2
+	vld1.64		{$H2},[$Htbl]
+	cclr		$inc,eq
+	vext.8		$Xl,$Xl,$Xl,#8
+	vld1.64		{$t0},[$inp],#16	@ load [rotated] I[0]
+	vshl.u64	$xC2,$xC2,#57		@ 0xc2.0
+#ifndef __ARMEB__
+	vrev64.8	$t0,$t0
+	vrev64.8	$Xl,$Xl
+#endif
+	vext.8		$IN,$t0,$t0,#8
+	b.lo		.Lodd_tail_v8
+___
+{ my ($Xln,$Xmn,$Xhn,$In) = map("q$_",(4..7));
+	#######
+	# Xi+2 =[H*(Ii+1 + Xi+1)] mod P =
+	#	[(H*Ii+1) + (H*Xi+1)] mod P =
+	#	[(H*Ii+1) + H^2*(Ii+Xi)] mod P
+	#
+$code.=<<___;
+	vld1.64		{$t1},[$inp],$inc	@ load [rotated] I[1]
+#ifndef __ARMEB__
+	vrev64.8	$t1,$t1
+#endif
+	vext.8		$In,$t1,$t1,#8
+	veor		$IN,$IN,$Xl		@ I[i]^=Xi
+	vpmull.p64	$Xln,$H,$In		@ H<>Ii+1
+	veor		$t1,$t1,$In		@ Karatsuba pre-processing
+	vpmull2.p64	$Xhn,$H,$In
+	b		.Loop_mod2x_v8
+
+.align	4
+.Loop_mod2x_v8:
+	vext.8		$t2,$IN,$IN,#8
+	subs		$len,$len,#32
+	vpmull.p64	$Xl,$H2,$IN		@ H^2.lo<6C>Xi.lo
+	cclr		$inc,lo
+
+	 vpmull.p64	$Xmn,$Hhl,$t1
+	veor		$t2,$t2,$IN		@ Karatsuba pre-processing
+	vpmull2.p64	$Xh,$H2,$IN		@ H^2.hi<68>Xi.hi
+	veor		$Xl,$Xl,$Xln		@ accumulate
+	vpmull2.p64	$Xm,$Hhl,$t2		@ (H^2.lo+H^2.hi)<29>(Xi.lo+Xi.hi)
+	 vld1.64	{$t0},[$inp],$inc	@ load [rotated] I[i]
+
+	veor		$Xh,$Xh,$Xhn
+	 cclr		$inc,eq
+	veor		$Xm,$Xm,$Xmn
+
+	vext.8		$t1,$Xl,$Xh,#8		@ Karatsuba post-processing
+	veor		$t2,$Xl,$Xh
+	veor		$Xm,$Xm,$t1
+	 vld1.64	{$t1},[$inp],$inc	@ load [rotated] I[i+1]
+#ifndef __ARMEB__
+	 vrev64.8	$t0,$t0
+#endif
+	veor		$Xm,$Xm,$t2
+	vpmull.p64	$t2,$Xl,$xC2		@ 1st phase
+
+#ifndef __ARMEB__
+	 vrev64.8	$t1,$t1
+#endif
+	vmov		$Xh#lo,$Xm#hi		@ Xh|Xm - 256-bit result
+	vmov		$Xm#hi,$Xl#lo		@ Xm is rotated Xl
+	 vext.8		$In,$t1,$t1,#8
+	 vext.8		$IN,$t0,$t0,#8
+	veor		$Xl,$Xm,$t2
+	 vpmull.p64	$Xln,$H,$In		@ H<>Ii+1
+	veor		$IN,$IN,$Xh		@ accumulate $IN early
+
+	vext.8		$t2,$Xl,$Xl,#8		@ 2nd phase
+	vpmull.p64	$Xl,$Xl,$xC2
+	veor		$IN,$IN,$t2
+	 veor		$t1,$t1,$In		@ Karatsuba pre-processing
+	veor		$IN,$IN,$Xl
+	 vpmull2.p64	$Xhn,$H,$In
+	b.hs		.Loop_mod2x_v8
+
+	veor		$Xh,$Xh,$t2
+	vext.8		$IN,$t0,$t0,#8		@ re-construct $IN
+	adds		$len,$len,#32
+	veor		$Xl,$Xl,$Xh		@ re-construct $Xl
+	b.eq		.Ldone_v8
+___
+}
+$code.=<<___;
+.Lodd_tail_v8:
+	vext.8		$t2,$Xl,$Xl,#8
+	veor		$IN,$IN,$Xl		@ inp^=Xi
+	veor		$t1,$t0,$t2		@ $t1 is rotated inp^Xi
+
+	vpmull.p64	$Xl,$H,$IN		@ H.lo<6C>Xi.lo
+	veor		$t1,$t1,$IN		@ Karatsuba pre-processing
+	vpmull2.p64	$Xh,$H,$IN		@ H.hi<68>Xi.hi
+	vpmull.p64	$Xm,$Hhl,$t1		@ (H.lo+H.hi)<29>(Xi.lo+Xi.hi)
+
+	vext.8		$t1,$Xl,$Xh,#8		@ Karatsuba post-processing
+	veor		$t2,$Xl,$Xh
+	veor		$Xm,$Xm,$t1
+	veor		$Xm,$Xm,$t2
+	vpmull.p64	$t2,$Xl,$xC2		@ 1st phase
+
+	vmov		$Xh#lo,$Xm#hi		@ Xh|Xm - 256-bit result
+	vmov		$Xm#hi,$Xl#lo		@ Xm is rotated Xl
+	veor		$Xl,$Xm,$t2
+
+	vext.8		$t2,$Xl,$Xl,#8		@ 2nd phase
+	vpmull.p64	$Xl,$Xl,$xC2
+	veor		$t2,$t2,$Xh
+	veor		$Xl,$Xl,$t2
+
+.Ldone_v8:
+#ifndef __ARMEB__
+	vrev64.8	$Xl,$Xl
+#endif
+	vext.8		$Xl,$Xl,$Xl,#8
+	vst1.64		{$Xl},[$Xi]		@ write out Xi
+
+___
+$code.=<<___		if ($flavour !~ /64/);
+	vldmia		sp!,{d8-d15}
+___
+$code.=<<___;
+	ret
+.size	gcm_ghash_v8,.-gcm_ghash_v8
+___
+}
+$code.=<<___;
+.asciz  "GHASH for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align  2
+___
+
+if ($flavour =~ /64/) {			######## 64-bit code
+    sub unvmov {
+	my $arg=shift;
+
+	$arg =~ m/q([0-9]+)#(lo|hi),\s*q([0-9]+)#(lo|hi)/o &&
+	sprintf	"ins	v%d.d[%d],v%d.d[%d]",$1,($2 eq "lo")?0:1,$3,($4 eq "lo")?0:1;
+    }
+    foreach(split("\n",$code)) {
+	s/cclr\s+([wx])([^,]+),\s*([a-z]+)/csel	$1$2,$1zr,$1$2,$3/o	or
+	s/vmov\.i8/movi/o		or	# fix up legacy mnemonics
+	s/vmov\s+(.*)/unvmov($1)/geo	or
+	s/vext\.8/ext/o			or
+	s/vshr\.s/sshr\.s/o		or
+	s/vshr/ushr/o			or
+	s/^(\s+)v/$1/o			or	# strip off v prefix
+	s/\bbx\s+lr\b/ret/o;
+
+	s/\bq([0-9]+)\b/"v".($1<8?$1:$1+8).".16b"/geo;	# old->new registers
+	s/@\s/\/\//o;				# old->new style commentary
+
+	# fix up remainig legacy suffixes
+	s/\.[ui]?8(\s)/$1/o;
+	s/\.[uis]?32//o and s/\.16b/\.4s/go;
+	m/\.p64/o and s/\.16b/\.1q/o;		# 1st pmull argument
+	m/l\.p64/o and s/\.16b/\.1d/go;		# 2nd and 3rd pmull arguments
+	s/\.[uisp]?64//o and s/\.16b/\.2d/go;
+	s/\.[42]([sd])\[([0-3])\]/\.$1\[$2\]/o;
+
+	print $_,"\n";
+    }
+} else {				######## 32-bit code
+    sub unvdup32 {
+	my $arg=shift;
+
+	$arg =~ m/q([0-9]+),\s*q([0-9]+)\[([0-3])\]/o &&
+	sprintf	"vdup.32	q%d,d%d[%d]",$1,2*$2+($3>>1),$3&1;
+    }
+    sub unvpmullp64 {
+	my ($mnemonic,$arg)=@_;
+
+	if ($arg =~ m/q([0-9]+),\s*q([0-9]+),\s*q([0-9]+)/o) {
+	    my $word = 0xf2a00e00|(($1&7)<<13)|(($1&8)<<19)
+				 |(($2&7)<<17)|(($2&8)<<4)
+				 |(($3&7)<<1) |(($3&8)<<2);
+	    $word |= 0x00010001	 if ($mnemonic =~ "2");
+	    # since ARMv7 instructions are always encoded little-endian.
+	    # correct solution is to use .inst directive, but older
+	    # assemblers don't implement it:-(
+	    sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s",
+			$word&0xff,($word>>8)&0xff,
+			($word>>16)&0xff,($word>>24)&0xff,
+			$mnemonic,$arg;
+	}
+    }
+
+    foreach(split("\n",$code)) {
+	s/\b[wx]([0-9]+)\b/r$1/go;		# new->old registers
+	s/\bv([0-9])\.[12468]+[bsd]\b/q$1/go;	# new->old registers
+	s/\/\/\s?/@ /o;				# new->old style commentary
+
+	# fix up remainig new-style suffixes
+	s/\],#[0-9]+/]!/o;
+
+	s/cclr\s+([^,]+),\s*([a-z]+)/mov$2	$1,#0/o			or
+	s/vdup\.32\s+(.*)/unvdup32($1)/geo				or
+	s/v?(pmull2?)\.p64\s+(.*)/unvpmullp64($1,$2)/geo		or
+	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
+	s/^(\s+)b\./$1b/o						or
+	s/^(\s+)ret/$1bx\tlr/o;
+
+	print $_,"\n";
+    }
+}
+
+close STDOUT; # enforce flush

crypto/modes/gcm128.c

@@ -645,7 +645,7 @@ static void gcm_gmult_1bit(u64 Xi[2],const u64 H[2])
 
 #endif
 
-#if	TABLE_BITS==4 && defined(GHASH_ASM)
+#if	TABLE_BITS==4 && (defined(GHASH_ASM) || defined(OPENSSL_CPUID_OBJ))
 # if	!defined(I386_ONLY) && \
 	(defined(__i386)	|| defined(__i386__)	|| \
 	 defined(__x86_64)	|| defined(__x86_64__)	|| \
@@ -666,14 +666,25 @@ void gcm_ghash_4bit_mmx(u64 Xi[2],const u128 Htable[16],const u8 *inp,size_t len
 void gcm_gmult_4bit_x86(u64 Xi[2],const u128 Htable[16]);
 void gcm_ghash_4bit_x86(u64 Xi[2],const u128 Htable[16],const u8 *inp,size_t len);
 #  endif
-# elif defined(__arm__) || defined(__arm)
+# elif defined(__arm__) || defined(__arm) || defined(__aarch64__)
 #  include "arm_arch.h"
 #  if __ARM_ARCH__>=7
 #   define GHASH_ASM_ARM
 #   define GCM_FUNCREF_4BIT
+#   if defined(__aarch64__)
+#    define PMULL_CAPABLE	(OPENSSL_armcap_P & ARMV8_PMULL)
+#   endif
+#   if defined(__arm__) || defined(__arm)
+#    define NEON_CAPABLE	(OPENSSL_armcap_P & ARMV7_NEON)
+#   endif
 void gcm_gmult_neon(u64 Xi[2],const u128 Htable[16]);
 void gcm_ghash_neon(u64 Xi[2],const u128 Htable[16],const u8 *inp,size_t len);
+void gcm_init_v8(u128 Htable[16],const u64 Xi[2]);
+void gcm_gmult_v8(u64 Xi[2],const u128 Htable[16]);
+void gcm_ghash_v8(u64 Xi[2],const u128 Htable[16],const u8 *inp,size_t len);
 #  endif
+# elif defined(_TMS320C6400_PLUS)
+#   define GHASH_ASM_C64Xplus
 # endif
 #endif
 
@@ -738,14 +749,28 @@ void CRYPTO_gcm128_init(GCM128_CONTEXT *ctx,void *key,block128_f block)
 	ctx->ghash = gcm_ghash_4bit;
 #  endif
 # elif	defined(GHASH_ASM_ARM)
-	if (OPENSSL_armcap_P & ARMV7_NEON) {
+#  ifdef PMULL_CAPABLE
+	if (PMULL_CAPABLE) {
+		gcm_init_v8(ctx->Htable,ctx->H.u);
+		ctx->gmult = gcm_gmult_v8;
+		ctx->ghash = gcm_ghash_v8;
+	} else
+#  endif
+#  ifdef NEON_CAPABLE
+	if (NEON_CAPABLE) {
 		ctx->gmult = gcm_gmult_neon;
 		ctx->ghash = gcm_ghash_neon;
-	} else {
+	} else
+#  endif
+	{
 		gcm_init_4bit(ctx->Htable,ctx->H.u);
 		ctx->gmult = gcm_gmult_4bit;
 		ctx->ghash = gcm_ghash_4bit;
 	}
+# elif defined(GHASH_ASM_C64Xplus)
+	/* C64x+ assembler doesn't use tables, skip gcm_init_4bit.
+	 * This is likely to trigger "function never referenced"
+	 * warning and code being eliminated. */
 # else
 	gcm_init_4bit(ctx->Htable,ctx->H.u);
 # endif
@@ -1397,7 +1422,7 @@ int CRYPTO_gcm128_finish(GCM128_CONTEXT *ctx,const unsigned char *tag,
 	void (*gcm_gmult_p)(u64 Xi[2],const u128 Htable[16])	= ctx->gmult;
 #endif
 
-	if (ctx->mres)
+	if (ctx->mres || ctx->ares)
 		GCM_MUL(ctx,Xi);
 
 	if (is_endian.little) {

crypto/modes/modes_lcl.h

@@ -29,10 +29,7 @@ typedef unsigned char u8;
 #if defined(__i386)	|| defined(__i386__)	|| \
     defined(__x86_64)	|| defined(__x86_64__)	|| \
     defined(_M_IX86)	|| defined(_M_AMD64)	|| defined(_M_X64) || \
-    defined(__s390__)	|| defined(__s390x__)	|| \
-    ( (defined(__arm__)	|| defined(__arm)) && \
-      (defined(__ARM_ARCH_7__)	|| defined(__ARM_ARCH_7A__) || \
-       defined(__ARM_ARCH_7R__)	|| defined(__ARM_ARCH_7M__)) )
+    defined(__s390__)	|| defined(__s390x__)
 # undef STRICT_ALIGNMENT
 #endif
 

crypto/perlasm/arm-xlate.pl

@@ -0,0 +1,165 @@
+#!/usr/bin/env perl
+
+# ARM assembler distiller by <appro>.
+
+my $flavour = shift;
+my $output = shift;
+open STDOUT,">$output" || die "can't open $output: $!";
+
+$flavour = "linux32" if (!$flavour or $flavour eq "void");
+
+my %GLOBALS;
+my $dotinlocallabels=($flavour=~/linux/)?1:0;
+
+################################################################
+# directives which need special treatment on different platforms
+################################################################
+my $arch = sub {
+    if ($flavour =~ /linux/)	{ ".arch\t".join(',',@_); }
+    else			{ ""; }
+};
+my $fpu = sub {
+    if ($flavour =~ /linux/)	{ ".fpu\t".join(',',@_); }
+    else			{ ""; }
+};
+my $hidden = sub {
+    if ($flavour =~ /ios/)	{ ".private_extern\t".join(',',@_); }
+    else			{ ".hidden\t".join(',',@_); }
+};
+my $comm = sub {
+    my @args = split(/,\s*/,shift);
+    my $name = @args[0];
+    my $global = \$GLOBALS{$name};
+    my $ret;
+
+    if ($flavour =~ /ios32/)	{
+	$ret = ".comm\t_$name,@args[1]\n";
+	$ret .= ".non_lazy_symbol_pointer\n";
+	$ret .= "$name:\n";
+	$ret .= ".indirect_symbol\t_$name\n";
+	$ret .= ".long\t0";
+	$name = "_$name";
+    } else			{ $ret = ".comm\t".join(',',@args); }
+
+    $$global = $name;
+    $ret;
+};
+my $globl = sub {
+    my $name = shift;
+    my $global = \$GLOBALS{$name};
+    my $ret;
+
+    SWITCH: for ($flavour) {
+	/ios/		&& do { $name = "_$name";
+				last;
+			      };
+    }
+
+    $ret = ".globl	$name" if (!$ret);
+    $$global = $name;
+    $ret;
+};
+my $global = $globl;
+my $extern = sub {
+    &$globl(@_);
+    return;	# return nothing
+};
+my $type = sub {
+    if ($flavour =~ /linux/)	{ ".type\t".join(',',@_); }
+    else			{ ""; }
+};
+my $size = sub {
+    if ($flavour =~ /linux/)	{ ".size\t".join(',',@_); }
+    else			{ ""; }
+};
+my $inst = sub {
+    if ($flavour =~ /linux/)    { ".inst\t".join(',',@_); }
+    else                        { ".long\t".join(',',@_); }
+};
+my $asciz = sub {
+    my $line = join(",",@_);
+    if ($line =~ /^"(.*)"$/)
+    {	".byte	" . join(",",unpack("C*",$1),0) . "\n.align	2";	}
+    else
+    {	"";	}
+};
+
+sub range {
+  my ($r,$sfx,$start,$end) = @_;
+
+    join(",",map("$r$_$sfx",($start..$end)));
+}
+
+sub expand_line {
+  my $line = shift;
+  my @ret = ();
+
+    pos($line)=0;
+
+    while ($line =~ m/\G[^@\/\{\"]*/g) {
+	if ($line =~ m/\G(@|\/\/|$)/gc) {
+	    last;
+	}
+	elsif ($line =~ m/\G\{/gc) {
+	    my $saved_pos = pos($line);
+	    $line =~ s/\G([rdqv])([0-9]+)([^\-]*)\-\1([0-9]+)\3/range($1,$3,$2,$4)/e;
+	    pos($line) = $saved_pos;
+	    $line =~ m/\G[^\}]*\}/g;
+	}
+	elsif ($line =~ m/\G\"/gc) {
+	    $line =~ m/\G[^\"]*\"/g;
+	}
+    }
+
+    $line =~ s/\b(\w+)/$GLOBALS{$1} or $1/ge;
+
+    return $line;
+}
+
+while($line=<>) {
+
+    if ($line =~ m/^\s*(#|@|\/\/)/)	{ print $line; next; }
+
+    $line =~ s|/\*.*\*/||;	# get rid of C-style comments...
+    $line =~ s|^\s+||;		# ... and skip white spaces in beginning...
+    $line =~ s|\s+$||;		# ... and at the end
+
+    {
+	$line =~ s|[\b\.]L(\w{2,})|L$1|g;	# common denominator for Locallabel
+	$line =~ s|\bL(\w{2,})|\.L$1|g	if ($dotinlocallabels);
+    }
+
+    {
+	$line =~ s|(^[\.\w]+)\:\s*||;
+	my $label = $1;
+	if ($label) {
+	    printf "%s:",($GLOBALS{$label} or $label);
+	}
+    }
+
+    if ($line !~ m/^[#@]/) {
+	$line =~ s|^\s*(\.?)(\S+)\s*||;
+	my $c = $1; $c = "\t" if ($c eq "");
+	my $mnemonic = $2;
+	my $opcode;
+	if ($mnemonic =~ m/([^\.]+)\.([^\.]+)/) {
+	    $opcode = eval("\$$1_$2");
+	} else {
+	    $opcode = eval("\$$mnemonic");
+	}
+
+	my $arg=expand_line($line);
+
+	if (ref($opcode) eq 'CODE') {
+		$line = &$opcode($arg);
+	} elsif ($mnemonic)         {
+		$line = $c.$mnemonic;
+		$line.= "\t$arg" if ($arg);
+	}
+    }
+
+    print $line if ($line);
+    print "\n";
+}
+
+close STDOUT;

crypto/rsa/rsa_eay.c

@@ -494,7 +494,7 @@ static int RSA_eay_private_encrypt(int flen, const unsigned char *from,
 	if (padding == RSA_X931_PADDING)
 		{
 		BN_sub(f, rsa->n, ret);
-		if (BN_cmp(ret, f))
+		if (BN_cmp(ret, f) > 0)
 			res = f;
 		else
 			res = ret;

crypto/sha/Makefile

@@ -90,6 +90,9 @@ sha512-%.S:	asm/sha512-%.pl;	$(PERL) $< $(PERLASM_SCHEME) $@
 sha1-armv4-large.o:	sha1-armv4-large.S
 sha256-armv4.o:		sha256-armv4.S
 sha512-armv4.o:		sha512-armv4.S
+sha1-armv8.o:		sha1-armv8.S
+sha256-armv8.o:		sha256-armv8.S
+sha512-armv8.o:		sha512-armv8.S
 
 files:
 	$(PERL) $(TOP)/util/files.pl Makefile >> $(TOP)/MINFO

crypto/sha/asm/sha1-armv4-large.pl

@@ -52,8 +52,20 @@
 # Profiler-assisted and platform-specific optimization resulted in 10%
 # improvement on Cortex A8 core and 12.2 cycles per byte.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";
 $inp="r1";
@@ -177,6 +189,7 @@ for($i=0;$i<5;$i++) {
 $code.=<<___;
 	teq	$Xi,sp
 	bne	.L_00_15		@ [((11+4)*5+2)*3]
+	sub	sp,sp,#25*4
 ___
 	&BODY_00_15(@V);	unshift(@V,pop(@V));
 	&BODY_16_19(@V);	unshift(@V,pop(@V));
@@ -186,7 +199,6 @@ ___
 $code.=<<___;
 
 	ldr	$K,.LK_20_39		@ [+15+16*4]
-	sub	sp,sp,#25*4
 	cmn	sp,#0			@ [+3], clear carry to denote 20_39
 .L_20_39_or_60_79:
 ___

crypto/sha/asm/sha1-armv8.pl

@@ -0,0 +1,343 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA1 for ARMv8.
+#
+# Performance in cycles per processed byte and improvement coefficient
+# over code generated with "default" compiler:
+#
+#		hardware-assisted	software(*)
+# Apple A7	2.31			4.13 (+14%)
+# Cortex-A53	2.19			8.73 (+108%)
+# Cortex-A57	2.35			7.88 (+74%)
+#
+# (*)	Software results are presented mostly for reference purposes.
+
+$flavour = shift;
+$output  = shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
+
+($ctx,$inp,$num)=("x0","x1","x2");
+@Xw=map("w$_",(3..17,19));
+@Xx=map("x$_",(3..17,19));
+@V=($A,$B,$C,$D,$E)=map("w$_",(20..24));
+($t0,$t1,$t2,$K)=map("w$_",(25..28));
+
+
+sub BODY_00_19 {
+my ($i,$a,$b,$c,$d,$e)=@_;
+my $j=($i+2)&15;
+
+$code.=<<___ if ($i<15 && !($i&1));
+	lsr	@Xx[$i+1],@Xx[$i],#32
+___
+$code.=<<___ if ($i<14 && !($i&1));
+	ldr	@Xx[$i+2],[$inp,#`($i+2)*4-64`]
+___
+$code.=<<___ if ($i<14 && ($i&1));
+#ifdef	__ARMEB__
+	ror	@Xx[$i+1],@Xx[$i+1],#32
+#else
+	rev32	@Xx[$i+1],@Xx[$i+1]
+#endif
+___
+$code.=<<___ if ($i<14);
+	bic	$t0,$d,$b
+	and	$t1,$c,$b
+	ror	$t2,$a,#27
+	add	$d,$d,$K		// future e+=K
+	orr	$t0,$t0,$t1
+	add	$e,$e,$t2		// e+=rot(a,5)
+	ror	$b,$b,#2
+	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+___
+$code.=<<___ if ($i==19);
+	movz	$K,#0xeba1
+	movk	$K,#0x6ed9,lsl#16
+___
+$code.=<<___ if ($i>=14);
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
+	bic	$t0,$d,$b
+	and	$t1,$c,$b
+	ror	$t2,$a,#27
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
+	add	$d,$d,$K		// future e+=K
+	orr	$t0,$t0,$t1
+	add	$e,$e,$t2		// e+=rot(a,5)
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
+	ror	$b,$b,#2
+	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+	 ror	@Xw[$j],@Xw[$j],#31
+___
+}
+
+sub BODY_40_59 {
+my ($i,$a,$b,$c,$d,$e)=@_;
+my $j=($i+2)&15;
+
+$code.=<<___ if ($i==59);
+	movz	$K,#0xc1d6
+	movk	$K,#0xca62,lsl#16
+___
+$code.=<<___;
+	orr	$t0,$b,$c
+	and	$t1,$b,$c
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
+	ror	$t2,$a,#27
+	and	$t0,$t0,$d
+	add	$d,$d,$K		// future e+=K
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
+	add	$e,$e,$t2		// e+=rot(a,5)
+	orr	$t0,$t0,$t1
+	ror	$b,$b,#2
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
+	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+	 ror	@Xw[$j],@Xw[$j],#31
+___
+}
+
+sub BODY_20_39 {
+my ($i,$a,$b,$c,$d,$e)=@_;
+my $j=($i+2)&15;
+
+$code.=<<___ if ($i==39);
+	movz	$K,#0xbcdc
+	movk	$K,#0x8f1b,lsl#16
+___
+$code.=<<___ if ($i<78);
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
+	eor	$t0,$d,$b
+	ror	$t2,$a,#27
+	add	$d,$d,$K		// future e+=K
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
+	eor	$t0,$t0,$c
+	add	$e,$e,$t2		// e+=rot(a,5)
+	ror	$b,$b,#2
+	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
+	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+	 ror	@Xw[$j],@Xw[$j],#31
+___
+$code.=<<___ if ($i==78);
+	ldp	@Xw[1],@Xw[2],[$ctx]
+	eor	$t0,$d,$b
+	ror	$t2,$a,#27
+	add	$d,$d,$K		// future e+=K
+	eor	$t0,$t0,$c
+	add	$e,$e,$t2		// e+=rot(a,5)
+	ror	$b,$b,#2
+	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+___
+$code.=<<___ if ($i==79);
+	ldp	@Xw[3],@Xw[4],[$ctx,#8]
+	eor	$t0,$d,$b
+	ror	$t2,$a,#27
+	eor	$t0,$t0,$c
+	add	$e,$e,$t2		// e+=rot(a,5)
+	ror	$b,$b,#2
+	ldr	@Xw[5],[$ctx,#16]
+	add	$e,$e,$t0		// e+=F(b,c,d)
+___
+}
+
+$code.=<<___;
+#include "arm_arch.h"
+
+.text
+
+.extern	OPENSSL_armcap_P
+.globl	sha1_block_data_order
+.type	sha1_block_data_order,%function
+.align	6
+sha1_block_data_order:
+	ldr	x16,.LOPENSSL_armcap_P
+	adr	x17,.LOPENSSL_armcap_P
+	add	x16,x16,x17
+	ldr	w16,[x16]
+	tst	w16,#ARMV8_SHA1
+	b.ne	.Lv8_entry
+
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+
+	ldp	$A,$B,[$ctx]
+	ldp	$C,$D,[$ctx,#8]
+	ldr	$E,[$ctx,#16]
+
+.Loop:
+	ldr	@Xx[0],[$inp],#64
+	movz	$K,#0x7999
+	sub	$num,$num,#1
+	movk	$K,#0x5a82,lsl#16
+#ifdef	__ARMEB__
+	ror	$Xx[0],@Xx[0],#32
+#else
+	rev32	@Xx[0],@Xx[0]
+#endif
+	add	$E,$E,$K		// warm it up
+	add	$E,$E,@Xw[0]
+___
+for($i=0;$i<20;$i++)	{ &BODY_00_19($i,@V); unshift(@V,pop(@V)); }
+for(;$i<40;$i++)	{ &BODY_20_39($i,@V); unshift(@V,pop(@V)); }
+for(;$i<60;$i++)	{ &BODY_40_59($i,@V); unshift(@V,pop(@V)); }
+for(;$i<80;$i++)	{ &BODY_20_39($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	add	$B,$B,@Xw[2]
+	add	$C,$C,@Xw[3]
+	add	$A,$A,@Xw[1]
+	add	$D,$D,@Xw[4]
+	add	$E,$E,@Xw[5]
+	stp	$A,$B,[$ctx]
+	stp	$C,$D,[$ctx,#8]
+	str	$E,[$ctx,#16]
+	cbnz	$num,.Loop
+
+	ldp	x19,x20,[sp,#16]
+	ldp	x21,x22,[sp,#32]
+	ldp	x23,x24,[sp,#48]
+	ldp	x25,x26,[sp,#64]
+	ldp	x27,x28,[sp,#80]
+	ldr	x29,[sp],#96
+	ret
+.size	sha1_block_data_order,.-sha1_block_data_order
+___
+{{{
+my ($ABCD,$E,$E0,$E1)=map("v$_.16b",(0..3));
+my @MSG=map("v$_.16b",(4..7));
+my @Kxx=map("v$_.4s",(16..19));
+my ($W0,$W1)=("v20.4s","v21.4s");
+my $ABCD_SAVE="v22.16b";
+
+$code.=<<___;
+.type	sha1_block_armv8,%function
+.align	6
+sha1_block_armv8:
+.Lv8_entry:
+	stp	x29,x30,[sp,#-16]!
+	add	x29,sp,#0
+
+	adr	x4,.Lconst
+	eor	$E,$E,$E
+	ld1.32	{$ABCD},[$ctx],#16
+	ld1.32	{$E}[0],[$ctx]
+	sub	$ctx,$ctx,#16
+	ld1.32	{@Kxx[0]-@Kxx[3]},[x4]
+
+.Loop_hw:
+	ld1	{@MSG[0]-@MSG[3]},[$inp],#64
+	sub	$num,$num,#1
+	rev32	@MSG[0],@MSG[0]
+	rev32	@MSG[1],@MSG[1]
+
+	add.i32	$W0,@Kxx[0],@MSG[0]
+	rev32	@MSG[2],@MSG[2]
+	orr	$ABCD_SAVE,$ABCD,$ABCD	// offload
+
+	add.i32	$W1,@Kxx[0],@MSG[1]
+	rev32	@MSG[3],@MSG[3]
+	sha1h	$E1,$ABCD
+	sha1c	$ABCD,$E,$W0		// 0
+	add.i32	$W0,@Kxx[$j],@MSG[2]
+	sha1su0	@MSG[0],@MSG[1],@MSG[2]
+___
+for ($j=0,$i=1;$i<20-3;$i++) {
+my $f=("c","p","m","p")[$i/5];
+$code.=<<___;
+	sha1h	$E0,$ABCD		// $i
+	sha1$f	$ABCD,$E1,$W1
+	add.i32	$W1,@Kxx[$j],@MSG[3]
+	sha1su1	@MSG[0],@MSG[3]
+___
+$code.=<<___ if ($i<20-4);
+	sha1su0	@MSG[1],@MSG[2],@MSG[3]
+___
+	($E0,$E1)=($E1,$E0);		($W0,$W1)=($W1,$W0);
+	push(@MSG,shift(@MSG));		$j++ if ((($i+3)%5)==0);
+}
+$code.=<<___;
+	sha1h	$E0,$ABCD		// $i
+	sha1p	$ABCD,$E1,$W1
+	add.i32	$W1,@Kxx[$j],@MSG[3]
+
+	sha1h	$E1,$ABCD		// 18
+	sha1p	$ABCD,$E0,$W0
+
+	sha1h	$E0,$ABCD		// 19
+	sha1p	$ABCD,$E1,$W1
+
+	add.i32	$E,$E,$E0
+	add.i32	$ABCD,$ABCD,$ABCD_SAVE
+
+	cbnz	$num,.Loop_hw
+
+	st1.32	{$ABCD},[$ctx],#16
+	st1.32	{$E}[0],[$ctx]
+
+	ldr	x29,[sp],#16
+	ret
+.size	sha1_block_armv8,.-sha1_block_armv8
+.align	6
+.Lconst:
+.long	0x5a827999,0x5a827999,0x5a827999,0x5a827999	//K_00_19
+.long	0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1	//K_20_39
+.long	0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc	//K_40_59
+.long	0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6	//K_60_79
+.LOPENSSL_armcap_P:
+.quad	OPENSSL_armcap_P-.
+.asciz	"SHA1 block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+.comm	OPENSSL_armcap_P,4,4
+___
+}}}
+
+{   my	%opcode = (
+	"sha1c"		=> 0x5e000000,	"sha1p"		=> 0x5e001000,
+	"sha1m"		=> 0x5e002000,	"sha1su0"	=> 0x5e003000,
+	"sha1h"		=> 0x5e280800,	"sha1su1"	=> 0x5e281800	);
+
+    sub unsha1 {
+	my ($mnemonic,$arg)=@_;
+
+	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o
+	&&
+	sprintf ".inst\t0x%08x\t//%s %s",
+			$opcode{$mnemonic}|$1|($2<<5)|($3<<16),
+			$mnemonic,$arg;
+    }
+}
+
+foreach(split("\n",$code)) {
+
+	s/\`([^\`]*)\`/eval($1)/geo;
+
+	s/\b(sha1\w+)\s+([qv].*)/unsha1($1,$2)/geo;
+
+	s/\.\w?32\b//o		and s/\.16b/\.4s/go;
+	m/(ld|st)1[^\[]+\[0\]/o	and s/\.4s/\.s/go;
+
+	print $_,"\n";
+}
+
+close STDOUT;

crypto/sha/asm/sha1-c64xplus.pl

@@ -0,0 +1,323 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA1 for C64x+.
+#
+# November 2011
+#
+# If compared to compiler-generated code with similar characteristics,
+# i.e. compiled with OPENSSL_SMALL_FOOTPRINT and utilizing SPLOOPs,
+# this implementation is 25% smaller and >2x faster. In absolute terms
+# performance is (quite impressive) ~6.5 cycles per processed byte.
+# Fully unrolled assembler would be ~5x larger and is likely to be
+# ~15% faster. It would be free from references to intermediate ring
+# buffer, but put more pressure on L1P [both because the code would be
+# larger and won't be using SPLOOP buffer]. There are no plans to
+# realize fully unrolled variant though...
+#
+# !!! Note that this module uses AMR, which means that all interrupt
+# service routines are expected to preserve it and for own well-being
+# zero it upon entry.
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+($CTX,$INP,$NUM) = ("A4","B4","A6");		# arguments
+
+($A,$B,$C,$D,$E, $Arot,$F,$F0,$T,$K) = map("A$_",(16..20, 21..25));
+($X0,$X2,$X8,$X13) = ("A26","B26","A27","B27");
+($TX0,$TX1,$TX2,$TX3) = map("B$_",(28..31));
+($XPA,$XPB) = ("A5","B5");			# X circular buffer
+($Actx,$Bctx,$Cctx,$Dctx,$Ectx) = map("A$_",(3,6..9));	# zaps $NUM
+
+$code=<<___;
+	.text
+
+	.asg	B3,RA
+	.asg	A15,FP
+	.asg	B15,SP
+
+	.if	.BIG_ENDIAN
+	.asg	MV,SWAP2
+	.asg	MV,SWAP4
+	.endif
+
+	.global	_sha1_block_data_order
+_sha1_block_data_order:
+	.asmfunc stack_usage(64)
+	MV	$NUM,A0			; reassign $NUM
+||	MVK	-64,B0
+  [!A0]	BNOP	RA			; if ($NUM==0) return;
+|| [A0]	STW	FP,*SP--[16]		; save frame pointer and alloca(64)
+|| [A0]	MV	SP,FP
+   [A0]	LDW	*${CTX}[0],$A		; load A-E...
+|| [A0]	AND	B0,SP,SP		; align stack at 64 bytes
+   [A0]	LDW	*${CTX}[1],$B
+|| [A0]	SUBAW	SP,2,SP			; reserve two words above buffer
+   [A0]	LDW	*${CTX}[2],$C
+|| [A0]	MVK	0x00404,B0
+   [A0]	LDW	*${CTX}[3],$D
+|| [A0]	MVKH	0x50000,B0		; 0x050404, 64 bytes for $XP[AB]
+   [A0]	LDW	*${CTX}[4],$E
+|| [A0]	MVC	B0,AMR			; setup circular addressing
+	LDNW	*${INP}++,$TX1		; pre-fetch input
+	NOP	1
+
+loop?:
+	MVK	0x00007999,$K
+||	ADDAW	SP,2,$XPA
+||	SUB	A0,1,A0
+||	MVK	13,B0
+	MVKH	0x5a820000,$K		; K_00_19
+||	ADDAW	SP,2,$XPB
+||	MV	$A,$Actx
+||	MV	$B,$Bctx
+;;==================================================
+	SPLOOPD	5			; BODY_00_13
+||	MV	$C,$Cctx
+||	MV	$D,$Dctx
+||	MV	$E,$Ectx
+||	MVC	B0,ILC
+
+	ROTL	$A,5,$Arot
+||	AND	$C,$B,$F
+||	ANDN	$D,$B,$F0
+||	ADD	$K,$E,$T		; T=E+K
+
+	XOR	$F0,$F,$F		; F_00_19(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+||	SWAP2	$TX1,$TX2
+||	LDNW	*${INP}++,$TX1
+
+	ADD	$F,$T,$T		; T+=F_00_19(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	SWAP4	$TX2,$TX3		; byte swap
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+
+	ADD	$TX3,$T,$A		; A=T+Xi
+||	STW	$TX3,*${XPB}++
+	SPKERNEL
+;;==================================================
+	ROTL	$A,5,$Arot		; BODY_14
+||	AND	$C,$B,$F
+||	ANDN	$D,$B,$F0
+||	ADD	$K,$E,$T		; T=E+K
+
+	XOR	$F0,$F,$F		; F_00_19(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+||	SWAP2	$TX1,$TX2
+||	LDNW	*${INP}++,$TX1
+
+	ADD	$F,$T,$T		; T+=F_00_19(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	SWAP4	$TX2,$TX2		; byte swap
+||	LDW	*${XPA}++,$X0		; fetches from X ring buffer are
+||	LDW	*${XPB}[4],$X2		; 2 iterations ahead
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+||	LDW	*${XPA}[7],$X8
+||	MV	$TX3,$X13		; ||	LDW	*${XPB}[15],$X13
+||	MV	$TX2,$TX3
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+||	STW	$TX2,*${XPB}++
+;;==================================================
+	ROTL	$A,5,$Arot		; BODY_15
+||	AND	$C,$B,$F
+||	ANDN	$D,$B,$F0
+||	ADD	$K,$E,$T		; T=E+K
+
+	XOR	$F0,$F,$F		; F_00_19(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+||	SWAP2	$TX1,$TX2
+
+	ADD	$F,$T,$T		; T+=F_00_19(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	SWAP4	$TX2,$TX2		; byte swap
+||	XOR	$X0,$X2,$TX0		; Xupdate XORs are 1 iteration ahead
+||	LDW	*${XPA}++,$X0
+||	LDW	*${XPB}[4],$X2
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+||	XOR	$X8,$X13,$TX1
+||	LDW	*${XPA}[7],$X8
+||	MV	$TX3,$X13		; ||	LDW	*${XPB}[15],$X13
+||	MV	$TX2,$TX3
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+||	STW	$TX2,*${XPB}++
+||	XOR	$TX0,$TX1,$TX1
+||	MVK	3,B0
+;;==================================================
+	SPLOOPD	5			; BODY_16_19
+||	MVC	B0,ILC
+
+	ROTL	$A,5,$Arot
+||	AND	$C,$B,$F
+||	ANDN	$D,$B,$F0
+||	ADD	$K,$E,$T		; T=E+K
+||	ROTL	$TX1,1,$TX2		; Xupdate output
+
+	XOR	$F0,$F,$F		; F_00_19(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+
+	ADD	$F,$T,$T		; T+=F_00_19(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	XOR	$X0,$X2,$TX0
+||	LDW	*${XPA}++,$X0
+||	LDW	*${XPB}[4],$X2
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+||	XOR	$X8,$X13,$TX1
+||	LDW	*${XPA}[7],$X8
+||	MV	$TX3,$X13		; ||	LDW	*${XPB}[15],$X13
+||	MV	$TX2,$TX3
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+||	STW	$TX2,*${XPB}++
+||	XOR	$TX0,$TX1,$TX1
+	SPKERNEL
+
+	MVK	0xffffeba1,$K
+||	MVK	19,B0
+	MVKH	0x6ed90000,$K		; K_20_39
+___
+sub BODY_20_39 {
+$code.=<<___;
+;;==================================================
+	SPLOOPD	5			; BODY_20_39
+||	MVC	B0,ILC
+
+	ROTL	$A,5,$Arot
+||	XOR	$B,$C,$F
+||	ADD	$K,$E,$T		; T=E+K
+||	ROTL	$TX1,1,$TX2		; Xupdate output
+
+	XOR	$D,$F,$F		; F_20_39(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+
+	ADD	$F,$T,$T		; T+=F_20_39(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	XOR	$X0,$X2,$TX0
+||	LDW	*${XPA}++,$X0
+||	LDW	*${XPB}[4],$X2
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+||	XOR	$X8,$X13,$TX1
+||	LDW	*${XPA}[7],$X8
+||	MV	$TX3,$X13		; ||	LDW	*${XPB}[15],$X13
+||	MV	$TX2,$TX3
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+||	STW	$TX2,*${XPB}++		; last one is redundant
+||	XOR	$TX0,$TX1,$TX1
+	SPKERNEL
+___
+$code.=<<___ if (!shift);
+	MVK	0xffffbcdc,$K
+	MVKH	0x8f1b0000,$K		; K_40_59
+___
+}	&BODY_20_39();
+$code.=<<___;
+;;==================================================
+	SPLOOPD	5			; BODY_40_59
+||	MVC	B0,ILC
+||	AND	$B,$C,$F
+||	AND	$B,$D,$F0
+
+	ROTL	$A,5,$Arot
+||	XOR	$F0,$F,$F
+||	AND	$C,$D,$F0
+||	ADD	$K,$E,$T		; T=E+K
+||	ROTL	$TX1,1,$TX2		; Xupdate output
+
+	XOR	$F0,$F,$F		; F_40_59(B,C,D)
+||	MV	$D,$E			; E=D
+||	MV	$C,$D			; D=C
+
+	ADD	$F,$T,$T		; T+=F_40_59(B,C,D)
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+||	XOR	$X0,$X2,$TX0
+||	LDW	*${XPA}++,$X0
+||	LDW	*${XPB}[4],$X2
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	MV	$A,$B			; B=A
+||	XOR	$X8,$X13,$TX1
+||	LDW	*${XPA}[7],$X8
+||	MV	$TX3,$X13		; ||	LDW	*${XPB}[15],$X13
+||	MV	$TX2,$TX3
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+||	STW	$TX2,*${XPB}++
+||	XOR	$TX0,$TX1,$TX1
+||	AND	$B,$C,$F
+||	AND	$B,$D,$F0
+	SPKERNEL
+
+	MVK	0xffffc1d6,$K
+||	MVK	18,B0
+	MVKH	0xca620000,$K		; K_60_79
+___
+	&BODY_20_39(-1);		# BODY_60_78
+$code.=<<___;
+;;==================================================
+   [A0]	B	loop?
+||	ROTL	$A,5,$Arot		; BODY_79
+||	XOR	$B,$C,$F
+||	ROTL	$TX1,1,$TX2		; Xupdate output
+
+   [A0]	LDNW	*${INP}++,$TX1		; pre-fetch input
+||	ADD	$K,$E,$T		; T=E+K
+||	XOR	$D,$F,$F		; F_20_39(B,C,D)
+
+	ADD	$F,$T,$T		; T+=F_20_39(B,C,D)
+||	ADD	$Ectx,$D,$E		; E=D,E+=Ectx
+||	ADD	$Dctx,$C,$D		; D=C,D+=Dctx
+||	ROTL	$B,30,$C		; C=ROL(B,30)
+
+	ADD	$Arot,$T,$T		; T+=ROL(A,5)
+||	ADD	$Bctx,$A,$B		; B=A,B+=Bctx
+
+	ADD	$TX2,$T,$A		; A=T+Xi
+
+	ADD	$Actx,$A,$A		; A+=Actx
+||	ADD	$Cctx,$C,$C		; C+=Cctx
+;; end of loop?
+
+	BNOP	RA			; return
+||	MV	FP,SP			; restore stack pointer
+||	LDW	*FP[0],FP		; restore frame pointer
+	STW	$A,*${CTX}[0]		; emit A-E...
+||	MVK	0,B0
+	STW	$B,*${CTX}[1]
+||	MVC	B0,AMR			; clear AMR
+	STW	$C,*${CTX}[2]
+	STW	$D,*${CTX}[3]
+	STW	$E,*${CTX}[4]
+	.endasmfunc
+
+	.sect	.const
+	.cstring "SHA1 block transform for C64x+, CRYPTOGAMS by <appro\@openssl.org>"
+	.align	4
+___
+
+print $code;
+close STDOUT;

crypto/sha/asm/sha256-armv4.pl

@@ -23,8 +23,20 @@
 # Profiler-assisted and platform-specific optimization resulted in 16%
 # improvement on Cortex A8 core and ~17 cycles per processed byte.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";	$t0="r0";
 $inp="r1";	$t3="r1";

crypto/sha/asm/sha256-c64xplus.pl

@@ -0,0 +1,292 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA256 for C64x+.
+#
+# January 2012
+#
+# Performance is just below 10 cycles per processed byte, which is
+# almost 40% faster than compiler-generated code. Unroll is unlikely
+# to give more than ~8% improvement...
+#
+# !!! Note that this module uses AMR, which means that all interrupt
+# service routines are expected to preserve it and for own well-being
+# zero it upon entry.
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+($CTXA,$INP,$NUM) = ("A4","B4","A6");            # arguments
+ $K256="A3";
+
+($A,$Actx,$B,$Bctx,$C,$Cctx,$D,$Dctx,$T2,$S0,$s1,$t0a,$t1a,$t2a,$X9,$X14)
+	=map("A$_",(16..31));
+($E,$Ectx,$F,$Fctx,$G,$Gctx,$H,$Hctx,$T1,$S1,$s0,$t0e,$t1e,$t2e,$X1,$X15)
+	=map("B$_",(16..31));
+
+($Xia,$Xib)=("A5","B5");			# circular/ring buffer
+ $CTXB=$t2e;
+
+($Xn,$X0,$K)=("B7","B8","B9");
+($Maj,$Ch)=($T2,"B6");
+
+$code.=<<___;
+	.text
+
+	.asg	B3,RA
+	.asg	A15,FP
+	.asg	B15,SP
+
+	.if	.BIG_ENDIAN
+	.asg	SWAP2,MV
+	.asg	SWAP4,MV
+	.endif
+
+	.global	_sha256_block_data_order
+_sha256_block_data_order:
+	.asmfunc stack_usage(64)
+	MV	$NUM,A0				; reassign $NUM
+||	MVK	-64,B0
+  [!A0]	BNOP	RA				; if ($NUM==0) return;
+|| [A0]	STW	FP,*SP--[16]			; save frame pointer and alloca(64)
+|| [A0]	MV	SP,FP
+   [A0]	ADDKPC	_sha256_block_data_order,B2
+|| [A0]	AND	B0,SP,SP			; align stack at 64 bytes
+   [A0]	MVK	0x00404,B1
+|| [A0]	MVKL	(K256-_sha256_block_data_order),$K256
+   [A0]	MVKH	0x50000,B1
+|| [A0]	MVKH	(K256-_sha256_block_data_order),$K256
+   [A0]	MVC	B1,AMR				; setup circular addressing
+|| [A0]	MV	SP,$Xia
+   [A0]	MV	SP,$Xib
+|| [A0]	ADD	B2,$K256,$K256
+|| [A0]	MV	$CTXA,$CTXB
+|| [A0]	SUBAW	SP,2,SP				; reserve two words above buffer
+	LDW	*${CTXA}[0],$A			; load ctx
+||	LDW	*${CTXB}[4],$E
+	LDW	*${CTXA}[1],$B
+||	LDW	*${CTXB}[5],$F
+	LDW	*${CTXA}[2],$C
+||	LDW	*${CTXB}[6],$G
+	LDW	*${CTXA}[3],$D
+||	LDW	*${CTXB}[7],$H
+
+	LDNW	*$INP++,$Xn			; pre-fetch input
+	LDW	*$K256++,$K			; pre-fetch K256[0]
+	MVK	14,B0				; loop counters
+	MVK	47,B1
+||	ADDAW	$Xia,9,$Xia
+outerloop?:
+	SUB	A0,1,A0
+||	MV	$A,$Actx
+||	MV	$E,$Ectx
+||	MVD	$B,$Bctx
+||	MVD	$F,$Fctx
+	MV	$C,$Cctx
+||	MV	$G,$Gctx
+||	MVD	$D,$Dctx
+||	MVD	$H,$Hctx
+||	SWAP4	$Xn,$X0
+
+	SPLOOPD	8				; BODY_00_14
+||	MVC	B0,ILC
+||	SWAP2	$X0,$X0
+
+	LDNW	*$INP++,$Xn
+||	ROTL	$A,30,$S0
+||	OR	$A,$B,$Maj
+||	AND	$A,$B,$t2a
+||	ROTL	$E,26,$S1
+||	AND	$F,$E,$Ch
+||	ANDN	$G,$E,$t2e
+	ROTL	$A,19,$t0a
+||	AND	$C,$Maj,$Maj
+||	ROTL	$E,21,$t0e
+||	XOR	$t2e,$Ch,$Ch			; Ch(e,f,g) = (e&f)^(~e&g)
+	ROTL	$A,10,$t1a
+||	OR	$t2a,$Maj,$Maj			; Maj(a,b,c) = ((a|b)&c)|(a&b)
+||	ROTL	$E,7,$t1e
+||	ADD	$K,$H,$T1			; T1 = h + K256[i]
+	ADD	$X0,$T1,$T1			; T1 += X[i];
+||	STW	$X0,*$Xib++
+||	XOR	$t0a,$S0,$S0
+||	XOR	$t0e,$S1,$S1
+	XOR	$t1a,$S0,$S0			; Sigma0(a)
+||	XOR	$t1e,$S1,$S1			; Sigma1(e)
+||	LDW	*$K256++,$K			; pre-fetch K256[i+1]
+||	ADD	$Ch,$T1,$T1			; T1 += Ch(e,f,g)
+	ADD	$S1,$T1,$T1			; T1 += Sigma1(e)
+||	ADD	$S0,$Maj,$T2			; T2 = Sigma0(a) + Maj(a,b,c)
+||	ROTL	$G,0,$H				; h = g
+||	MV	$F,$G				; g = f
+||	MV	$X0,$X14
+||	SWAP4	$Xn,$X0
+	SWAP2	$X0,$X0
+||	MV	$E,$F				; f = e
+||	ADD	$D,$T1,$E			; e = d + T1
+||	MV	$C,$D				; d = c
+	MV	$B,$C				; c = b
+||	MV	$A,$B				; b = a
+||	ADD	$T1,$T2,$A			; a = T1 + T2
+	SPKERNEL
+
+	ROTL	$A,30,$S0			; BODY_15
+||	OR	$A,$B,$Maj
+||	AND	$A,$B,$t2a
+||	ROTL	$E,26,$S1
+||	AND	$F,$E,$Ch
+||	ANDN	$G,$E,$t2e
+||	LDW	*${Xib}[1],$Xn			; modulo-scheduled
+	ROTL	$A,19,$t0a
+||	AND	$C,$Maj,$Maj
+||	ROTL	$E,21,$t0e
+||	XOR	$t2e,$Ch,$Ch			; Ch(e,f,g) = (e&f)^(~e&g)
+||	LDW	*${Xib}[2],$X1			; modulo-scheduled
+	ROTL	$A,10,$t1a
+||	OR	$t2a,$Maj,$Maj			; Maj(a,b,c) = ((a|b)&c)|(a&b)
+||	ROTL	$E,7,$t1e
+||	ADD	$K,$H,$T1			; T1 = h + K256[i]
+	ADD	$X0,$T1,$T1			; T1 += X[i];
+||	STW	$X0,*$Xib++
+||	XOR	$t0a,$S0,$S0
+||	XOR	$t0e,$S1,$S1
+	XOR	$t1a,$S0,$S0			; Sigma0(a)
+||	XOR	$t1e,$S1,$S1			; Sigma1(e)
+||	LDW	*$K256++,$K			; pre-fetch K256[i+1]
+||	ADD	$Ch,$T1,$T1			; T1 += Ch(e,f,g)
+	ADD	$S1,$T1,$T1			; T1 += Sigma1(e)
+||	ADD	$S0,$Maj,$T2			; T2 = Sigma0(a) + Maj(a,b,c)
+||	ROTL	$G,0,$H				; h = g
+||	MV	$F,$G				; g = f
+||	MV	$X0,$X15
+	MV	$E,$F				; f = e
+||	ADD	$D,$T1,$E			; e = d + T1
+||	MV	$C,$D				; d = c
+||	MV	$Xn,$X0				; modulo-scheduled
+||	LDW	*$Xia,$X9			; modulo-scheduled
+||	ROTL	$X1,25,$t0e			; modulo-scheduled
+||	ROTL	$X14,15,$t0a			; modulo-scheduled
+	SHRU	$X1,3,$s0			; modulo-scheduled
+||	SHRU	$X14,10,$s1			; modulo-scheduled
+||	ROTL	$B,0,$C				; c = b
+||	MV	$A,$B				; b = a
+||	ADD	$T1,$T2,$A			; a = T1 + T2
+
+	SPLOOPD	10				; BODY_16_63
+||	MVC	B1,ILC
+||	ROTL	$X1,14,$t1e			; modulo-scheduled
+||	ROTL	$X14,13,$t1a			; modulo-scheduled
+
+	XOR	$t0e,$s0,$s0
+||	XOR	$t0a,$s1,$s1
+||	MV	$X15,$X14
+||	MV	$X1,$Xn
+	XOR	$t1e,$s0,$s0			; sigma0(X[i+1])
+||	XOR	$t1a,$s1,$s1			; sigma1(X[i+14])
+||	LDW	*${Xib}[2],$X1			; module-scheduled
+	ROTL	$A,30,$S0
+||	OR	$A,$B,$Maj
+||	AND	$A,$B,$t2a
+||	ROTL	$E,26,$S1
+||	AND	$F,$E,$Ch
+||	ANDN	$G,$E,$t2e
+||	ADD	$X9,$X0,$X0			; X[i] += X[i+9]
+	ROTL	$A,19,$t0a
+||	AND	$C,$Maj,$Maj
+||	ROTL	$E,21,$t0e
+||	XOR	$t2e,$Ch,$Ch			; Ch(e,f,g) = (e&f)^(~e&g)
+||	ADD	$s0,$X0,$X0			; X[i] += sigma1(X[i+1])
+	ROTL	$A,10,$t1a
+||	OR	$t2a,$Maj,$Maj			; Maj(a,b,c) = ((a|b)&c)|(a&b)
+||	ROTL	$E,7,$t1e
+||	ADD	$H,$K,$T1			; T1 = h + K256[i]
+||	ADD	$s1,$X0,$X0			; X[i] += sigma1(X[i+14])
+	XOR	$t0a,$S0,$S0
+||	XOR	$t0e,$S1,$S1
+||	ADD	$X0,$T1,$T1			; T1 += X[i]
+||	STW	$X0,*$Xib++
+	XOR	$t1a,$S0,$S0			; Sigma0(a)
+||	XOR	$t1e,$S1,$S1			; Sigma1(e)
+||	ADD	$Ch,$T1,$T1			; T1 += Ch(e,f,g)
+||	MV	$X0,$X15
+||	ROTL	$G,0,$H				; h = g
+||	LDW	*$K256++,$K			; pre-fetch K256[i+1]
+	ADD	$S1,$T1,$T1			; T1 += Sigma1(e)
+||	ADD	$S0,$Maj,$T2			; T2 = Sigma0(a) + Maj(a,b,c)
+||	MV	$F,$G				; g = f
+||	MV	$Xn,$X0				; modulo-scheduled
+||	LDW	*++$Xia,$X9			; modulo-scheduled
+||	ROTL	$X1,25,$t0e			; module-scheduled
+||	ROTL	$X14,15,$t0a			; modulo-scheduled
+	ROTL	$X1,14,$t1e			; modulo-scheduled
+||	ROTL	$X14,13,$t1a			; modulo-scheduled
+||	MV	$E,$F				; f = e
+||	ADD	$D,$T1,$E			; e = d + T1
+||	MV	$C,$D				; d = c
+||	MV	$B,$C				; c = b
+	MV	$A,$B				; b = a
+||	ADD	$T1,$T2,$A			; a = T1 + T2
+||	SHRU	$X1,3,$s0			; modulo-scheduled
+||	SHRU	$X14,10,$s1			; modulo-scheduled
+	SPKERNEL
+
+   [A0]	B	outerloop?
+|| [A0]	LDNW	*$INP++,$Xn			; pre-fetch input
+|| [A0]	ADDK	-260,$K256			; rewind K256
+||	ADD	$Actx,$A,$A			; accumulate ctx
+||	ADD	$Ectx,$E,$E
+||	ADD	$Bctx,$B,$B
+	ADD	$Fctx,$F,$F
+||	ADD	$Cctx,$C,$C
+||	ADD	$Gctx,$G,$G
+||	ADD	$Dctx,$D,$D
+||	ADD	$Hctx,$H,$H
+|| [A0]	LDW	*$K256++,$K			; pre-fetch K256[0]
+
+  [!A0]	BNOP	RA
+||[!A0]	MV	$CTXA,$CTXB
+  [!A0]	MV	FP,SP				; restore stack pointer
+||[!A0]	LDW	*FP[0],FP			; restore frame pointer
+  [!A0]	STW	$A,*${CTXA}[0]  		; save ctx
+||[!A0]	STW	$E,*${CTXB}[4]
+||[!A0]	MVK	0,B0
+  [!A0]	STW	$B,*${CTXA}[1]
+||[!A0]	STW	$F,*${CTXB}[5]
+||[!A0]	MVC	B0,AMR				; clear AMR
+	STW	$C,*${CTXA}[2]
+||	STW	$G,*${CTXB}[6]
+	STW	$D,*${CTXA}[3]
+||	STW	$H,*${CTXB}[7]
+	.endasmfunc
+
+	.sect	".const:sha_asm"
+	.align	128
+K256:
+	.uword	0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.uword	0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.uword	0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.uword	0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.uword	0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.uword	0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.uword	0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.uword	0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.uword	0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.uword	0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.uword	0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.uword	0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.uword	0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.uword	0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.uword	0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.uword	0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+	.cstring "SHA256 block transform for C64x+, CRYPTOGAMS by <appro\@openssl.org>"
+	.align	4
+
+___
+
+print $code;

crypto/sha/asm/sha512-armv4.pl

@@ -38,8 +38,20 @@ $hi="HI";
 $lo="LO";
 # ====================================================================
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/^\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";	# parameter block
 $inp="r1";
@@ -221,17 +233,21 @@ WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
 WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
 .size	K512,.-K512
 .LOPENSSL_armcap:
-.word	OPENSSL_armcap_P-sha512_block_data_order
+.word	OPENSSL_armcap_P-.Lsha512_block_data_order
 .skip	32-4
 
 .global	sha512_block_data_order
 .type	sha512_block_data_order,%function
 sha512_block_data_order:
+.Lsha512_block_data_order:
 	sub	r3,pc,#8		@ sha512_block_data_order
 	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
 #if __ARM_ARCH__>=7
 	ldr	r12,.LOPENSSL_armcap
 	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+#ifdef	__APPLE__
+	ldr	r12,[r12]
+#endif
 	tst	r12,#1
 	bne	.LNEON
 #endif

crypto/sha/asm/sha512-armv8.pl

@@ -0,0 +1,428 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA256/512 for ARMv8.
+#
+# Performance in cycles per processed byte and improvement coefficient
+# over code generated with "default" compiler:
+#
+#		SHA256-hw	SHA256(*)	SHA512
+# Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
+# Cortex-A53	2.38		15.6 (+110%)	10.1 (+190%(***))
+# Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
+# 
+# (*)	Software SHA256 results are of lesser relevance, presented
+#	mostly for informational purposes.
+# (**)	The result is a trade-off: it's possible to improve it by
+#	10% (or by 1 cycle per round), but at the cost of 20% loss
+#	on Cortex-A53 (or by 4 cycles per round).
+# (***)	Super-impressive coefficients over gcc-generated code are
+#	indication of some compiler "pathology", most notably code
+#	generated with -mgeneral-regs-only is significanty faster
+#	and lags behind assembly only by 50-90%.
+
+$flavour=shift;
+$output=shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+die "can't locate arm-xlate.pl";
+
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
+
+if ($output =~ /512/) {
+	$BITS=512;
+	$SZ=8;
+	@Sigma0=(28,34,39);
+	@Sigma1=(14,18,41);
+	@sigma0=(1,  8, 7);
+	@sigma1=(19,61, 6);
+	$rounds=80;
+	$reg_t="x";
+} else {
+	$BITS=256;
+	$SZ=4;
+	@Sigma0=( 2,13,22);
+	@Sigma1=( 6,11,25);
+	@sigma0=( 7,18, 3);
+	@sigma1=(17,19,10);
+	$rounds=64;
+	$reg_t="w";
+}
+
+$func="sha${BITS}_block_data_order";
+
+($ctx,$inp,$num,$Ktbl)=map("x$_",(0..2,30));
+
+@X=map("$reg_t$_",(3..15,0..2));
+@V=($A,$B,$C,$D,$E,$F,$G,$H)=map("$reg_t$_",(20..27));
+($t0,$t1,$t2,$t3)=map("$reg_t$_",(16,17,19,28));
+
+sub BODY_00_xx {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my $j=($i+1)&15;
+my ($T0,$T1,$T2)=(@X[($i-8)&15],@X[($i-9)&15],@X[($i-10)&15]);
+   $T0=@X[$i+3] if ($i<11);
+
+$code.=<<___	if ($i<16);
+#ifndef	__ARMEB__
+	rev	@X[$i],@X[$i]			// $i
+#endif
+___
+$code.=<<___	if ($i<13 && ($i&1));
+	ldp	@X[$i+1],@X[$i+2],[$inp],#2*$SZ
+___
+$code.=<<___	if ($i==13);
+	ldp	@X[14],@X[15],[$inp]
+___
+$code.=<<___	if ($i>=14);
+	ldr	@X[($i-11)&15],[sp,#`$SZ*(($i-11)%4)`]
+___
+$code.=<<___	if ($i>0 && $i<16);
+	add	$a,$a,$t1			// h+=Sigma0(a)
+___
+$code.=<<___	if ($i>=11);
+	str	@X[($i-8)&15],[sp,#`$SZ*(($i-8)%4)`]
+___
+# While ARMv8 specifies merged rotate-n-logical operation such as
+# 'eor x,y,z,ror#n', it was found to negatively affect performance
+# on Apple A7. The reason seems to be that it requires even 'y' to
+# be available earlier. This means that such merged instruction is
+# not necessarily best choice on critical path... On the other hand
+# Cortex-A5x handles merged instructions much better than disjoint
+# rotate and logical... See (**) footnote above.
+$code.=<<___	if ($i<15);
+	ror	$t0,$e,#$Sigma1[0]
+	add	$h,$h,$t2			// h+=K[i]
+	eor	$T0,$e,$e,ror#`$Sigma1[2]-$Sigma1[1]`
+	and	$t1,$f,$e
+	bic	$t2,$g,$e
+	add	$h,$h,@X[$i&15]			// h+=X[i]
+	orr	$t1,$t1,$t2			// Ch(e,f,g)
+	eor	$t2,$a,$b			// a^b, b^c in next round
+	eor	$t0,$t0,$T0,ror#$Sigma1[1]	// Sigma1(e)
+	ror	$T0,$a,#$Sigma0[0]
+	add	$h,$h,$t1			// h+=Ch(e,f,g)
+	eor	$t1,$a,$a,ror#`$Sigma0[2]-$Sigma0[1]`
+	add	$h,$h,$t0			// h+=Sigma1(e)
+	and	$t3,$t3,$t2			// (b^c)&=(a^b)
+	add	$d,$d,$h			// d+=h
+	eor	$t3,$t3,$b			// Maj(a,b,c)
+	eor	$t1,$T0,$t1,ror#$Sigma0[1]	// Sigma0(a)
+	add	$h,$h,$t3			// h+=Maj(a,b,c)
+	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
+	//add	$h,$h,$t1			// h+=Sigma0(a)
+___
+$code.=<<___	if ($i>=15);
+	ror	$t0,$e,#$Sigma1[0]
+	add	$h,$h,$t2			// h+=K[i]
+	ror	$T1,@X[($j+1)&15],#$sigma0[0]
+	and	$t1,$f,$e
+	ror	$T2,@X[($j+14)&15],#$sigma1[0]
+	bic	$t2,$g,$e
+	ror	$T0,$a,#$Sigma0[0]
+	add	$h,$h,@X[$i&15]			// h+=X[i]
+	eor	$t0,$t0,$e,ror#$Sigma1[1]
+	eor	$T1,$T1,@X[($j+1)&15],ror#$sigma0[1]
+	orr	$t1,$t1,$t2			// Ch(e,f,g)
+	eor	$t2,$a,$b			// a^b, b^c in next round
+	eor	$t0,$t0,$e,ror#$Sigma1[2]	// Sigma1(e)
+	eor	$T0,$T0,$a,ror#$Sigma0[1]
+	add	$h,$h,$t1			// h+=Ch(e,f,g)
+	and	$t3,$t3,$t2			// (b^c)&=(a^b)
+	eor	$T2,$T2,@X[($j+14)&15],ror#$sigma1[1]
+	eor	$T1,$T1,@X[($j+1)&15],lsr#$sigma0[2]	// sigma0(X[i+1])
+	add	$h,$h,$t0			// h+=Sigma1(e)
+	eor	$t3,$t3,$b			// Maj(a,b,c)
+	eor	$t1,$T0,$a,ror#$Sigma0[2]	// Sigma0(a)
+	eor	$T2,$T2,@X[($j+14)&15],lsr#$sigma1[2]	// sigma1(X[i+14])
+	add	@X[$j],@X[$j],@X[($j+9)&15]
+	add	$d,$d,$h			// d+=h
+	add	$h,$h,$t3			// h+=Maj(a,b,c)
+	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
+	add	@X[$j],@X[$j],$T1
+	add	$h,$h,$t1			// h+=Sigma0(a)
+	add	@X[$j],@X[$j],$T2
+___
+	($t2,$t3)=($t3,$t2);
+}
+
+$code.=<<___;
+#include "arm_arch.h"
+
+.text
+
+.extern	OPENSSL_armcap_P
+.globl	$func
+.type	$func,%function
+.align	6
+$func:
+___
+$code.=<<___	if ($SZ==4);
+	ldr	x16,.LOPENSSL_armcap_P
+	adr	x17,.LOPENSSL_armcap_P
+	add	x16,x16,x17
+	ldr	w16,[x16]
+	tst	w16,#ARMV8_SHA256
+	b.ne	.Lv8_entry
+___
+$code.=<<___;
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	sub	sp,sp,#4*$SZ
+
+	ldp	$A,$B,[$ctx]				// load context
+	ldp	$C,$D,[$ctx,#2*$SZ]
+	ldp	$E,$F,[$ctx,#4*$SZ]
+	add	$num,$inp,$num,lsl#`log(16*$SZ)/log(2)`	// end of input
+	ldp	$G,$H,[$ctx,#6*$SZ]
+	adr	$Ktbl,.LK$BITS
+	stp	$ctx,$num,[x29,#96]
+
+.Loop:
+	ldp	@X[0],@X[1],[$inp],#2*$SZ
+	ldr	$t2,[$Ktbl],#$SZ			// *K++
+	eor	$t3,$B,$C				// magic seed
+	str	$inp,[x29,#112]
+___
+for ($i=0;$i<16;$i++)	{ &BODY_00_xx($i,@V); unshift(@V,pop(@V)); }
+$code.=".Loop_16_xx:\n";
+for (;$i<32;$i++)	{ &BODY_00_xx($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	cbnz	$t2,.Loop_16_xx
+
+	ldp	$ctx,$num,[x29,#96]
+	ldr	$inp,[x29,#112]
+	sub	$Ktbl,$Ktbl,#`$SZ*($rounds+1)`		// rewind
+
+	ldp	@X[0],@X[1],[$ctx]
+	ldp	@X[2],@X[3],[$ctx,#2*$SZ]
+	add	$inp,$inp,#14*$SZ			// advance input pointer
+	ldp	@X[4],@X[5],[$ctx,#4*$SZ]
+	add	$A,$A,@X[0]
+	ldp	@X[6],@X[7],[$ctx,#6*$SZ]
+	add	$B,$B,@X[1]
+	add	$C,$C,@X[2]
+	add	$D,$D,@X[3]
+	stp	$A,$B,[$ctx]
+	add	$E,$E,@X[4]
+	add	$F,$F,@X[5]
+	stp	$C,$D,[$ctx,#2*$SZ]
+	add	$G,$G,@X[6]
+	add	$H,$H,@X[7]
+	cmp	$inp,$num
+	stp	$E,$F,[$ctx,#4*$SZ]
+	stp	$G,$H,[$ctx,#6*$SZ]
+	b.ne	.Loop
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#4*$SZ
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#128
+	ret
+.size	$func,.-$func
+
+.align	6
+.type	.LK$BITS,%object
+.LK$BITS:
+___
+$code.=<<___ if ($SZ==8);
+	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
+	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
+	.quad	0x3956c25bf348b538,0x59f111f1b605d019
+	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
+	.quad	0xd807aa98a3030242,0x12835b0145706fbe
+	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
+	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
+	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
+	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
+	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
+	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
+	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
+	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
+	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
+	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
+	.quad	0x06ca6351e003826f,0x142929670a0e6e70
+	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
+	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
+	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
+	.quad	0x81c2c92e47edaee6,0x92722c851482353b
+	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
+	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
+	.quad	0xd192e819d6ef5218,0xd69906245565a910
+	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
+	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
+	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
+	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
+	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
+	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
+	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
+	.quad	0x90befffa23631e28,0xa4506cebde82bde9
+	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
+	.quad	0xca273eceea26619c,0xd186b8c721c0c207
+	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
+	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
+	.quad	0x113f9804bef90dae,0x1b710b35131c471b
+	.quad	0x28db77f523047d84,0x32caab7b40c72493
+	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
+	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
+	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
+	.quad	0	// terminator
+___
+$code.=<<___ if ($SZ==4);
+	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+	.long	0	//terminator
+___
+$code.=<<___;
+.size	.LK$BITS,.-.LK$BITS
+.align	3
+.LOPENSSL_armcap_P:
+	.quad	OPENSSL_armcap_P-.
+.asciz	"SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+___
+
+if ($SZ==4) {
+my $Ktbl="x3";
+
+my ($ABCD,$EFGH,$abcd)=map("v$_.16b",(0..2));
+my @MSG=map("v$_.16b",(4..7));
+my ($W0,$W1)=("v16.4s","v17.4s");
+my ($ABCD_SAVE,$EFGH_SAVE)=("v18.16b","v19.16b");
+
+$code.=<<___;
+.type	sha256_block_armv8,%function
+.align	6
+sha256_block_armv8:
+.Lv8_entry:
+	stp		x29,x30,[sp,#-16]!
+	add		x29,sp,#0
+
+	ld1.32		{$ABCD,$EFGH},[$ctx]
+	adr		$Ktbl,.LK256
+
+.Loop_hw:
+	ld1		{@MSG[0]-@MSG[3]},[$inp],#64
+	sub		$num,$num,#1
+	ld1.32		{$W0},[$Ktbl],#16
+	rev32		@MSG[0],@MSG[0]
+	rev32		@MSG[1],@MSG[1]
+	rev32		@MSG[2],@MSG[2]
+	rev32		@MSG[3],@MSG[3]
+	orr		$ABCD_SAVE,$ABCD,$ABCD		// offload
+	orr		$EFGH_SAVE,$EFGH,$EFGH
+___
+for($i=0;$i<12;$i++) {
+$code.=<<___;
+	ld1.32		{$W1},[$Ktbl],#16
+	add.i32		$W0,$W0,@MSG[0]
+	sha256su0	@MSG[0],@MSG[1]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+	sha256su1	@MSG[0],@MSG[2],@MSG[3]
+___
+	($W0,$W1)=($W1,$W0);	push(@MSG,shift(@MSG));
+}
+$code.=<<___;
+	ld1.32		{$W1},[$Ktbl],#16
+	add.i32		$W0,$W0,@MSG[0]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	ld1.32		{$W0},[$Ktbl],#16
+	add.i32		$W1,$W1,@MSG[1]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	ld1.32		{$W1},[$Ktbl]
+	add.i32		$W0,$W0,@MSG[2]
+	sub		$Ktbl,$Ktbl,#$rounds*$SZ-16	// rewind
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	add.i32		$W1,$W1,@MSG[3]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	add.i32		$ABCD,$ABCD,$ABCD_SAVE
+	add.i32		$EFGH,$EFGH,$EFGH_SAVE
+
+	cbnz		$num,.Loop_hw
+
+	st1.32		{$ABCD,$EFGH},[$ctx]
+
+	ldr		x29,[sp],#16
+	ret
+.size	sha256_block_armv8,.-sha256_block_armv8
+___
+}
+
+$code.=<<___;
+.comm	OPENSSL_armcap_P,4,4
+___
+
+{   my  %opcode = (
+	"sha256h"	=> 0x5e004000,	"sha256h2"	=> 0x5e005000,
+	"sha256su0"	=> 0x5e282800,	"sha256su1"	=> 0x5e006000	);
+
+    sub unsha256 {
+	my ($mnemonic,$arg)=@_;
+
+	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o
+	&&
+	sprintf ".inst\t0x%08x\t//%s %s",
+			$opcode{$mnemonic}|$1|($2<<5)|($3<<16),
+			$mnemonic,$arg;
+    }
+}
+
+foreach(split("\n",$code)) {
+
+	s/\`([^\`]*)\`/eval($1)/geo;
+
+	s/\b(sha256\w+)\s+([qv].*)/unsha256($1,$2)/geo;
+
+	s/\.\w?32\b//o		and s/\.16b/\.4s/go;
+	m/(ld|st)1[^\[]+\[0\]/o	and s/\.4s/\.s/go;
+
+	print $_,"\n";
+}
+
+close STDOUT;

crypto/sha/asm/sha512-c64xplus.pl

@@ -0,0 +1,410 @@
+#!/usr/bin/env perl
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA512 for C64x+.
+#
+# January 2012
+#
+# Performance is 19 cycles per processed byte. Compared to block
+# transform function from sha512.c compiled with cl6x with -mv6400+
+# -o2 -DOPENSSL_SMALL_FOOTPRINT it's almost 7x faster and 2x smaller.
+# Loop unroll won't make it, this implementation, any faster, because
+# it's effectively dominated by SHRU||SHL pairs and you can't schedule
+# more of them.
+#
+# !!! Note that this module uses AMR, which means that all interrupt
+# service routines are expected to preserve it and for own well-being
+# zero it upon entry.
+
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+($CTXA,$INP,$NUM) = ("A4","B4","A6");            # arguments
+ $K512="A3";
+
+($Ahi,$Actxhi,$Bhi,$Bctxhi,$Chi,$Cctxhi,$Dhi,$Dctxhi,
+ $Ehi,$Ectxhi,$Fhi,$Fctxhi,$Ghi,$Gctxhi,$Hhi,$Hctxhi)=map("A$_",(16..31));
+($Alo,$Actxlo,$Blo,$Bctxlo,$Clo,$Cctxlo,$Dlo,$Dctxlo,
+ $Elo,$Ectxlo,$Flo,$Fctxlo,$Glo,$Gctxlo,$Hlo,$Hctxlo)=map("B$_",(16..31));
+
+($S1hi,$CHhi,$S0hi,$t0hi)=map("A$_",(10..13));
+($S1lo,$CHlo,$S0lo,$t0lo)=map("B$_",(10..13));
+($T1hi,         $T2hi)=         ("A6","A7");
+($T1lo,$T1carry,$T2lo,$T2carry)=("B6","B7","B8","B9");
+($Khi,$Klo)=("A9","A8");
+($MAJhi,$MAJlo)=($T2hi,$T2lo);
+($t1hi,$t1lo)=($Khi,"B2");
+ $CTXB=$t1lo;
+
+($Xihi,$Xilo)=("A5","B5");			# circular/ring buffer
+
+$code.=<<___;
+	.text
+
+	.asg	B3,RA
+	.asg	A15,FP
+	.asg	B15,SP
+
+	.if	.BIG_ENDIAN
+	.asg	$Khi,KHI
+	.asg	$Klo,KLO
+	.else
+	.asg	$Khi,KLO
+	.asg	$Klo,KHI
+	.endif
+
+	.global	_sha512_block_data_order
+_sha512_block_data_order:
+	.asmfunc stack_usage(40+128)
+	MV	$NUM,A0				; reassign $NUM
+||	MVK	-128,B0
+  [!A0]	BNOP	RA				; if ($NUM==0) return;
+|| [A0]	STW	FP,*SP--(40)			; save frame pointer
+|| [A0]	MV	SP,FP
+   [A0]	STDW	B13:B12,*SP[4]
+|| [A0]	MVK	0x00404,B1
+   [A0]	STDW	B11:B10,*SP[3]
+|| [A0]	STDW	A13:A12,*FP[-3]
+|| [A0]	MVKH	0x60000,B1
+   [A0]	STDW	A11:A10,*SP[1]
+|| [A0]	MVC	B1,AMR				; setup circular addressing
+|| [A0]	ADD	B0,SP,SP			; alloca(128)
+   [A0]	AND	B0,SP,SP			; align stack at 128 bytes
+|| [A0]	ADDKPC	_sha512_block_data_order,B1
+|| [A0]	MVKL	(K512-_sha512_block_data_order),$K512
+   [A0]	MVKH	(K512-_sha512_block_data_order),$K512
+|| [A0]	SUBAW	SP,2,SP				; reserve two words above buffer
+	ADDAW	SP,3,$Xilo
+	ADDAW	SP,2,$Xihi
+
+||	MV	$CTXA,$CTXB
+	LDW	*${CTXA}[0^.LITTLE_ENDIAN],$Ahi	; load ctx
+||	LDW	*${CTXB}[1^.LITTLE_ENDIAN],$Alo
+||	ADD	B1,$K512,$K512
+	LDW	*${CTXA}[2^.LITTLE_ENDIAN],$Bhi
+||	LDW	*${CTXB}[3^.LITTLE_ENDIAN],$Blo
+	LDW	*${CTXA}[4^.LITTLE_ENDIAN],$Chi
+||	LDW	*${CTXB}[5^.LITTLE_ENDIAN],$Clo
+	LDW	*${CTXA}[6^.LITTLE_ENDIAN],$Dhi
+||	LDW	*${CTXB}[7^.LITTLE_ENDIAN],$Dlo
+	LDW	*${CTXA}[8^.LITTLE_ENDIAN],$Ehi
+||	LDW	*${CTXB}[9^.LITTLE_ENDIAN],$Elo
+	LDW	*${CTXA}[10^.LITTLE_ENDIAN],$Fhi
+||	LDW	*${CTXB}[11^.LITTLE_ENDIAN],$Flo
+	LDW	*${CTXA}[12^.LITTLE_ENDIAN],$Ghi
+||	LDW	*${CTXB}[13^.LITTLE_ENDIAN],$Glo
+	LDW	*${CTXA}[14^.LITTLE_ENDIAN],$Hhi
+||	LDW	*${CTXB}[15^.LITTLE_ENDIAN],$Hlo
+
+	LDNDW	*$INP++,B11:B10			; pre-fetch input
+	LDDW	*$K512++,$Khi:$Klo		; pre-fetch K512[0]
+outerloop?:
+	MVK	15,B0				; loop counters
+||	MVK	64,B1
+||	SUB	A0,1,A0
+	MV	$Ahi,$Actxhi
+||	MV	$Alo,$Actxlo
+||	MV	$Bhi,$Bctxhi
+||	MV	$Blo,$Bctxlo
+||	MV	$Chi,$Cctxhi
+||	MV	$Clo,$Cctxlo
+||	MVD	$Dhi,$Dctxhi
+||	MVD	$Dlo,$Dctxlo
+	MV	$Ehi,$Ectxhi
+||	MV	$Elo,$Ectxlo
+||	MV	$Fhi,$Fctxhi
+||	MV	$Flo,$Fctxlo
+||	MV	$Ghi,$Gctxhi
+||	MV	$Glo,$Gctxlo
+||	MVD	$Hhi,$Hctxhi
+||	MVD	$Hlo,$Hctxlo
+loop0_15?:
+	.if	.BIG_ENDIAN
+	MV	B11,$T1hi
+||	MV	B10,$T1lo
+	.else
+	SWAP4	B10,$T1hi
+||	SWAP4	B11,$T1lo
+	SWAP2	$T1hi,$T1hi
+||	SWAP2	$T1lo,$T1lo
+	.endif
+loop16_79?:
+	STW	$T1hi,*$Xihi++[2]
+||	STW	$T1lo,*$Xilo++[2]			; X[i] = T1
+||	ADD	$Hhi,$T1hi,$T1hi
+||	ADDU	$Hlo,$T1lo,$T1carry:$T1lo		; T1 += h
+||	SHRU	$Ehi,14,$S1hi
+||	SHL	$Ehi,32-14,$S1lo
+	XOR	$Fhi,$Ghi,$CHhi
+||	XOR	$Flo,$Glo,$CHlo
+||	ADD	KHI,$T1hi,$T1hi
+||	ADDU	KLO,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += K512[i]
+||	SHRU	$Elo,14,$t0lo
+||	SHL	$Elo,32-14,$t0hi
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	AND	$Ehi,$CHhi,$CHhi
+||	AND	$Elo,$CHlo,$CHlo
+||	ROTL	$Ghi,0,$Hhi
+||	ROTL	$Glo,0,$Hlo				; h = g
+||	SHRU	$Ehi,18,$t0hi
+||	SHL	$Ehi,32-18,$t0lo
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	XOR	$Ghi,$CHhi,$CHhi
+||	XOR	$Glo,$CHlo,$CHlo			; Ch(e,f,g) = ((f^g)&e)^g
+||	ROTL	$Fhi,0,$Ghi
+||	ROTL	$Flo,0,$Glo				; g = f
+||	SHRU	$Elo,18,$t0lo
+||	SHL	$Elo,32-18,$t0hi
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	OR	$Ahi,$Bhi,$MAJhi
+||	OR	$Alo,$Blo,$MAJlo
+||	ROTL	$Ehi,0,$Fhi
+||	ROTL	$Elo,0,$Flo				; f = e
+||	SHRU	$Ehi,41-32,$t0lo
+||	SHL	$Ehi,64-41,$t0hi
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	AND	$Chi,$MAJhi,$MAJhi
+||	AND	$Clo,$MAJlo,$MAJlo
+||	ROTL	$Dhi,0,$Ehi
+||	ROTL	$Dlo,0,$Elo				; e = d
+||	SHRU	$Elo,41-32,$t0hi
+||	SHL	$Elo,64-41,$t0lo
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo			; Sigma1(e)
+||	AND	$Ahi,$Bhi,$t1hi
+||	AND	$Alo,$Blo,$t1lo
+||	ROTL	$Chi,0,$Dhi
+||	ROTL	$Clo,0,$Dlo				; d = c
+||	SHRU	$Ahi,28,$S0hi
+||	SHL	$Ahi,32-28,$S0lo
+	OR	$t1hi,$MAJhi,$MAJhi
+||	OR	$t1lo,$MAJlo,$MAJlo			; Maj(a,b,c) = ((a|b)&c)|(a&b)
+||	ADD	$CHhi,$T1hi,$T1hi
+||	ADDU	$CHlo,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += Ch(e,f,g)
+||	ROTL	$Bhi,0,$Chi
+||	ROTL	$Blo,0,$Clo				; c = b
+||	SHRU	$Alo,28,$t0lo
+||	SHL	$Alo,32-28,$t0hi
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	ADD	$S1hi,$T1hi,$T1hi
+||	ADDU	$S1lo,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += Sigma1(e)
+||	ROTL	$Ahi,0,$Bhi
+||	ROTL	$Alo,0,$Blo				; b = a
+||	SHRU	$Ahi,34-32,$t0lo
+||	SHL	$Ahi,64-34,$t0hi
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	ADD	$MAJhi,$T1hi,$T2hi
+||	ADDU	$MAJlo,$T1carry:$T1lo,$T2carry:$T2lo	; T2 = T1+Maj(a,b,c)
+||	SHRU	$Alo,34-32,$t0hi
+||	SHL	$Alo,64-34,$t0lo
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	ADD	$Ehi,$T1hi,$T1hi
+||	ADDU	$Elo,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += e
+|| [B0]	BNOP	loop0_15?
+||	SHRU	$Ahi,39-32,$t0lo
+||	SHL	$Ahi,64-39,$t0hi
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+|| [B0]	LDNDW	*$INP++,B11:B10				; pre-fetch input
+||[!B1]	BNOP	break?
+||	SHRU	$Alo,39-32,$t0hi
+||	SHL	$Alo,64-39,$t0lo
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo			; Sigma0(a)
+||	ADD	$T1carry,$T1hi,$Ehi
+||	MV	$T1lo,$Elo				; e = T1
+||[!B0]	LDW	*${Xihi}[28],$T1hi
+||[!B0]	LDW	*${Xilo}[28],$T1lo			; X[i+14]
+	ADD	$S0hi,$T2hi,$T2hi
+||	ADDU	$S0lo,$T2carry:$T2lo,$T2carry:$T2lo	; T2 += Sigma0(a)
+|| [B1]	LDDW	*$K512++,$Khi:$Klo			; pre-fetch K512[i]
+	NOP						; avoid cross-path stall
+	ADD	$T2carry,$T2hi,$Ahi
+||	MV	$T2lo,$Alo				; a = T2
+|| [B0]	SUB	B0,1,B0
+;;===== branch to loop00_15? is taken here
+	NOP
+;;===== branch to break? is taken here
+	LDW	*${Xihi}[2],$T2hi
+||	LDW	*${Xilo}[2],$T2lo			; X[i+1]
+||	SHRU	$T1hi,19,$S1hi
+||	SHL	$T1hi,32-19,$S1lo
+	SHRU	$T1lo,19,$t0lo
+||	SHL	$T1lo,32-19,$t0hi
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	SHRU	$T1hi,61-32,$t0lo
+||	SHL	$T1hi,64-61,$t0hi
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	SHRU	$T1lo,61-32,$t0hi
+||	SHL	$T1lo,64-61,$t0lo
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	SHRU	$T1hi,6,$t0hi
+||	SHL	$T1hi,32-6,$t0lo
+	XOR	$t0hi,$S1hi,$S1hi
+||	XOR	$t0lo,$S1lo,$S1lo
+||	SHRU	$T1lo,6,$t0lo
+||	LDW	*${Xihi}[18],$T1hi
+||	LDW	*${Xilo}[18],$T1lo			; X[i+9]
+	XOR	$t0lo,$S1lo,$S1lo			; sigma1(Xi[i+14])
+
+||	LDW	*${Xihi}[0],$CHhi
+||	LDW	*${Xilo}[0],$CHlo			; X[i]
+||	SHRU	$T2hi,1,$S0hi
+||	SHL	$T2hi,32-1,$S0lo
+	SHRU	$T2lo,1,$t0lo
+||	SHL	$T2lo,32-1,$t0hi
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	SHRU	$T2hi,8,$t0hi
+||	SHL	$T2hi,32-8,$t0lo
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	SHRU	$T2lo,8,$t0lo
+||	SHL	$T2lo,32-8,$t0hi
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	ADD	$S1hi,$T1hi,$T1hi
+||	ADDU	$S1lo,$T1lo,$T1carry:$T1lo		; T1 = X[i+9]+sigma1()
+|| [B1]	BNOP	loop16_79?
+||	SHRU	$T2hi,7,$t0hi
+||	SHL	$T2hi,32-7,$t0lo
+	XOR	$t0hi,$S0hi,$S0hi
+||	XOR	$t0lo,$S0lo,$S0lo
+||	ADD	$CHhi,$T1hi,$T1hi
+||	ADDU	$CHlo,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += X[i]
+||	SHRU	$T2lo,7,$t0lo
+	XOR	$t0lo,$S0lo,$S0lo			; sigma0(Xi[i+1]
+
+	ADD	$S0hi,$T1hi,$T1hi
+||	ADDU	$S0lo,$T1carry:$T1lo,$T1carry:$T1lo	; T1 += sigma0()
+|| [B1]	SUB	B1,1,B1
+	NOP						; avoid cross-path stall
+	ADD	$T1carry,$T1hi,$T1hi
+;;===== branch to loop16_79? is taken here
+
+break?:
+	ADD	$Ahi,$Actxhi,$Ahi		; accumulate ctx
+||	ADDU	$Alo,$Actxlo,$Actxlo:$Alo
+|| [A0]	LDNDW	*$INP++,B11:B10			; pre-fetch input
+|| [A0]	ADDK	-640,$K512			; rewind pointer to K512
+	ADD	$Bhi,$Bctxhi,$Bhi
+||	ADDU	$Blo,$Bctxlo,$Bctxlo:$Blo
+|| [A0]	LDDW	*$K512++,$Khi:$Klo		; pre-fetch K512[0]
+	ADD	$Chi,$Cctxhi,$Chi
+||	ADDU	$Clo,$Cctxlo,$Cctxlo:$Clo
+||	ADD	$Actxlo,$Ahi,$Ahi
+||[!A0]	MV	$CTXA,$CTXB
+	ADD	$Dhi,$Dctxhi,$Dhi
+||	ADDU	$Dlo,$Dctxlo,$Dctxlo:$Dlo
+||	ADD	$Bctxlo,$Bhi,$Bhi
+||[!A0]	STW	$Ahi,*${CTXA}[0^.LITTLE_ENDIAN]	; save ctx
+||[!A0]	STW	$Alo,*${CTXB}[1^.LITTLE_ENDIAN]
+	ADD	$Ehi,$Ectxhi,$Ehi
+||	ADDU	$Elo,$Ectxlo,$Ectxlo:$Elo
+||	ADD	$Cctxlo,$Chi,$Chi
+|| [A0]	BNOP	outerloop?
+||[!A0]	STW	$Bhi,*${CTXA}[2^.LITTLE_ENDIAN]
+||[!A0]	STW	$Blo,*${CTXB}[3^.LITTLE_ENDIAN]
+	ADD	$Fhi,$Fctxhi,$Fhi
+||	ADDU	$Flo,$Fctxlo,$Fctxlo:$Flo
+||	ADD	$Dctxlo,$Dhi,$Dhi
+||[!A0]	STW	$Chi,*${CTXA}[4^.LITTLE_ENDIAN]
+||[!A0]	STW	$Clo,*${CTXB}[5^.LITTLE_ENDIAN]
+	ADD	$Ghi,$Gctxhi,$Ghi
+||	ADDU	$Glo,$Gctxlo,$Gctxlo:$Glo
+||	ADD	$Ectxlo,$Ehi,$Ehi
+||[!A0]	STW	$Dhi,*${CTXA}[6^.LITTLE_ENDIAN]
+||[!A0]	STW	$Dlo,*${CTXB}[7^.LITTLE_ENDIAN]
+	ADD	$Hhi,$Hctxhi,$Hhi
+||	ADDU	$Hlo,$Hctxlo,$Hctxlo:$Hlo
+||	ADD	$Fctxlo,$Fhi,$Fhi
+||[!A0]	STW	$Ehi,*${CTXA}[8^.LITTLE_ENDIAN]
+||[!A0]	STW	$Elo,*${CTXB}[9^.LITTLE_ENDIAN]
+	ADD	$Gctxlo,$Ghi,$Ghi
+||[!A0]	STW	$Fhi,*${CTXA}[10^.LITTLE_ENDIAN]
+||[!A0]	STW	$Flo,*${CTXB}[11^.LITTLE_ENDIAN]
+	ADD	$Hctxlo,$Hhi,$Hhi
+||[!A0]	STW	$Ghi,*${CTXA}[12^.LITTLE_ENDIAN]
+||[!A0]	STW	$Glo,*${CTXB}[13^.LITTLE_ENDIAN]
+;;===== branch to outerloop? is taken here
+
+	STW	$Hhi,*${CTXA}[14^.LITTLE_ENDIAN]
+||	STW	$Hlo,*${CTXB}[15^.LITTLE_ENDIAN]
+||	MVK	-40,B0
+	ADD	FP,B0,SP			; destroy circular buffer
+||	LDDW	*FP[-4],A11:A10
+	LDDW	*SP[2],A13:A12
+||	LDDW	*FP[-2],B11:B10
+	LDDW	*SP[4],B13:B12
+||	BNOP	RA
+	LDW	*++SP(40),FP			; restore frame pointer
+	MVK	0,B0
+	MVC	B0,AMR				; clear AMR
+	NOP	2				; wait till FP is committed
+	.endasmfunc
+
+	.sect	".const:sha_asm"
+	.align	128
+K512:
+	.uword	0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd
+	.uword	0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc
+	.uword	0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019
+	.uword	0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118
+	.uword	0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe
+	.uword	0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2
+	.uword	0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1
+	.uword	0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694
+	.uword	0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3
+	.uword	0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65
+	.uword	0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483
+	.uword	0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5
+	.uword	0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210
+	.uword	0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4
+	.uword	0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725
+	.uword	0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70
+	.uword	0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926
+	.uword	0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df
+	.uword	0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8
+	.uword	0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b
+	.uword	0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001
+	.uword	0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30
+	.uword	0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910
+	.uword	0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8
+	.uword	0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53
+	.uword	0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8
+	.uword	0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb
+	.uword	0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3
+	.uword	0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60
+	.uword	0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec
+	.uword	0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9
+	.uword	0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b
+	.uword	0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207
+	.uword	0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178
+	.uword	0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6
+	.uword	0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b
+	.uword	0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493
+	.uword	0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c
+	.uword	0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a
+	.uword	0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817
+	.cstring "SHA512 block transform for C64x+, CRYPTOGAMS by <appro\@openssl.org>"
+	.align	4
+___
+
+print $code;
+close STDOUT;

crypto/uid.c

@@ -65,7 +65,7 @@ int OPENSSL_issetugid(void)
 	return issetugid();
 	}
 
-#elif defined(OPENSSL_SYS_WIN32) || defined(OPENSSL_SYS_VXWORKS) || defined(OPENSSL_SYS_NETWARE)
+#elif defined(OPENSSL_SYS_WIN32) || defined(OPENSSL_SYS_VXWORKS) || defined(OPENSSL_SYS_NETWARE) || defined(_TMS320C6X)
 
 int OPENSSL_issetugid(void)
 	{

e_os.h

@@ -306,7 +306,7 @@ static unsigned int _strlen31(const char *str)
 #      undef isupper
 #      undef isxdigit
 #    endif
-#    if defined(_MSC_VER) && !defined(_DLL) && defined(stdin)
+#    if defined(_MSC_VER) && !defined(_WIN32_WCE) && !defined(_DLL) && defined(stdin)
 #      if _MSC_VER>=1300
 #        undef stdin
 #        undef stdout
@@ -332,8 +332,10 @@ static unsigned int _strlen31(const char *str)
 #      endif
 #    endif
 #  endif
-#  include <io.h>
-#  include <fcntl.h>
+#  if !defined(OPENSSL_FIPSCANISTER)
+#    include <io.h>
+#    include <fcntl.h>
+#  endif
 
 #  ifdef OPENSSL_SYS_WINCE
 #    define OPENSSL_NO_POSIX_IO
@@ -668,7 +670,7 @@ extern char *sys_errlist[]; extern int sys_nerr;
 #if defined(OPENSSL_SYS_WINDOWS)
 #  define strcasecmp _stricmp
 #  define strncasecmp _strnicmp
-#elif defined(OPENSSL_SYS_VMS)
+#elif defined(OPENSSL_SYS_VMS) || defined(OPENSSL_SYS_DSPBIOS)
 /* VMS below version 7.0 doesn't have strcasecmp() */
 #  include "o_str.h"
 #  define strcasecmp OPENSSL_strcasecmp

fips/aes/fips_aesavs.c

@@ -99,7 +99,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
     {
     const EVP_CIPHER *cipher = NULL;
 
-    if (strcasecmp(amode, "CBC") == 0)
+    if (fips_strcasecmp(amode, "CBC") == 0)
 	{
 	switch (akeysz)
 		{
@@ -117,7 +117,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
 		}
 
 	}
-    else if (strcasecmp(amode, "ECB") == 0)
+    else if (fips_strcasecmp(amode, "ECB") == 0)
 	{
 	switch (akeysz)
 		{
@@ -134,7 +134,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
 		break;
 		}
 	}
-    else if (strcasecmp(amode, "CFB128") == 0)
+    else if (fips_strcasecmp(amode, "CFB128") == 0)
 	{
 	switch (akeysz)
 		{
@@ -169,7 +169,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
 		break;
 		}
 	}
-    else if(!strcasecmp(amode,"CFB1"))
+    else if(!fips_strcasecmp(amode,"CFB1"))
 	{
 	switch (akeysz)
 		{
@@ -186,7 +186,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
 		break;
 		}
 	}
-    else if(!strcasecmp(amode,"CFB8"))
+    else if(!fips_strcasecmp(amode,"CFB8"))
 	{
 	switch (akeysz)
 		{
@@ -215,7 +215,7 @@ static int AESTest(EVP_CIPHER_CTX *ctx,
 	}
     if (FIPS_cipherinit(ctx, cipher, aKey, iVec, dir) <= 0)
 	return 0;
-    if(!strcasecmp(amode,"CFB1"))
+    if(!fips_strcasecmp(amode,"CFB1"))
 	M_EVP_CIPHER_CTX_set_flags(ctx, EVP_CIPH_FLAG_LENGTH_BITS);
     if (dir)
 		FIPS_cipher(ctx, ciphertext, plaintext, len);
@@ -635,10 +635,8 @@ static int proc_file(char *rqfile, char *rspfile)
 		char *xp, *pp = ibuf+2;
 		int n;
 		if (akeysz)
-		    { /* insert current time & date */
-		    time_t rtim = time(0);
-		    fputs("# ", rfp);
-		    copy_line(ctime(&rtim), rfp);
+		    {
+		    copy_line(ibuf, rfp);
 		    }
 		else
 		    {
@@ -876,11 +874,11 @@ int main(int argc, char **argv)
 
     if (argc > 1)
 	{
-	if (strcasecmp(argv[1], "-d") == 0)
+	if (fips_strcasecmp(argv[1], "-d") == 0)
 	    {
 	    d_opt = 1;
 	    }
-	else if (strcasecmp(argv[1], "-f") == 0)
+	else if (fips_strcasecmp(argv[1], "-f") == 0)
 	    {
 	    d_opt = 0;
 	    }

fips/aes/fips_gcmtest.c

@@ -75,10 +75,11 @@ int main(int argc, char **argv)
 
 #include "fips_utl.h"
 
+static char buf[204800];
+static char lbuf[204800];
+
 static void gcmtest(FILE *in, FILE *out, int encrypt)
 	{
-	char buf[2048];
-	char lbuf[2048];
 	char *keyword, *value;
 	int keylen = -1, ivlen = -1, aadlen = -1, taglen = -1, ptlen = -1;
 	int rv;
@@ -266,8 +267,6 @@ static void gcmtest(FILE *in, FILE *out, int encrypt)
 
 static void xtstest(FILE *in, FILE *out)
 	{
-	char buf[204800];
-	char lbuf[204800];
 	char *keyword, *value;
 	int inlen = 0;
 	int encrypt = 0;
@@ -340,8 +339,6 @@ static void xtstest(FILE *in, FILE *out)
 
 static void ccmtest(FILE *in, FILE *out)
 	{
-	char buf[200048];
-	char lbuf[200048];
 	char *keyword, *value;
 	long l;
 	unsigned char *Key = NULL, *Nonce = NULL;

fips/des/fips_des_selftest.c

@@ -83,7 +83,7 @@ static const struct
 
 int FIPS_selftest_des()
     {
-    int n, ret = 0;
+    int n, ret = 1;
     EVP_CIPHER_CTX ctx;
     FIPS_cipher_ctx_init(&ctx);
 
@@ -93,10 +93,8 @@ int FIPS_selftest_des()
 	if (!fips_cipher_test(FIPS_TEST_CIPHER, &ctx, EVP_des_ede3_ecb(),
 				tests3[n].key, NULL,
 				tests3[n].plaintext, tests3[n].ciphertext, 8))
-		goto err;
+		ret = 0;
 	}
-    ret = 1;
-    err:
     FIPS_cipher_ctx_cleanup(&ctx);
     if (ret == 0)
 	    FIPSerr(FIPS_F_FIPS_SELFTEST_DES,FIPS_R_SELFTEST_FAILED);

fips/des/fips_desmovs.c

@@ -356,10 +356,8 @@ static int tproc_file(char *rqfile, char *rspfile)
 		char *xp, *pp = ibuf+2;
 		int n;
 		if(*amode)
-		    { /* insert current time & date */
-		    time_t rtim = time(0);
-		    fputs("# ", rfp);
-		    copy_line(ctime(&rtim), rfp);
+		    {
+		    copy_line(ibuf, rfp);
 		    }
 		else
 		    {

fips/dh/fips_dhvs.c

@@ -286,7 +286,7 @@ int main(int argc, char **argv)
 	return 0;
 	parse_error:
 	fprintf(stderr, "Error Parsing request file\n");
-	exit(1);
+	return 1;
 	}
 
 #endif

fips/dsa/fips_dsatest.c

@@ -62,8 +62,10 @@
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
+#ifndef NO_SYS_TYPES_H
 #include <sys/types.h>
 #include <sys/stat.h>
+#endif
 
 #include "e_os.h"
 

fips/dsa/fips_dssvs.c

@@ -46,7 +46,8 @@ static int parse_mod(char *line, int *pdsa2, int *pL, int *pN,
 	if (strcmp(keyword, "L"))
 		return 0;
 	*pL = atoi(value);
-	strcpy(line, p + 1);
+	strcpy(lbuf, p + 1);
+        strcpy(line, lbuf);
 	if (pmd)
 		p = strchr(line, ',');
 	else
@@ -552,6 +553,11 @@ static void keypair(FILE *in, FILE *out)
 	    int n=atoi(value);
 
 	    dsa = FIPS_dsa_new();
+	    if (!dsa)
+		{
+		fprintf(stderr, "DSA allocation error\n");
+		exit(1);
+		}
 	    if (!dsa2 && !dsa_builtin_paramgen(dsa, L, N, NULL, NULL, 0,
 						NULL, NULL, NULL, NULL))
 			{
@@ -578,8 +584,7 @@ static void keypair(FILE *in, FILE *out)
 		do_bn_print_name(out, "Y",dsa->pub_key);
 	    	fputs(RESP_EOL, out);
 		}
-	    if (dsa)
-		FIPS_dsa_free(dsa);
+	    FIPS_dsa_free(dsa);
 	    }
 	}
     }

fips/ecdsa/fips_ecdsa_selftest.c

@@ -143,7 +143,7 @@ int FIPS_selftest_ecdsa()
 	EC_KEY *ec = NULL;
 	BIGNUM *x = NULL, *y = NULL, *d = NULL;
 	EVP_PKEY pk;
-	int rv = 0;
+	int rv = 0, test_err = 0;
 	size_t i;
 
 	for (i = 0; i < sizeof(test_ec_data)/sizeof(EC_SELFTEST_DATA); i++)
@@ -173,12 +173,12 @@ int FIPS_selftest_ecdsa()
 		if (!fips_pkey_signature_test(FIPS_TEST_SIGNATURE, &pk, NULL, 0,
 						NULL, 0, EVP_sha512(), 0,
 						ecd->name))
-			goto err;
+			test_err = 1;
 		EC_KEY_free(ec);
 		ec = NULL;
 		}
-
-	rv = 1;
+	if (test_err == 0)
+		rv = 1;
 
 	err:
 

fips/fips.c

@@ -81,7 +81,7 @@ static int fips_started = 0;
 static int fips_is_owning_thread(void);
 static int fips_set_owning_thread(void);
 static int fips_clear_owning_thread(void);
-static unsigned char *fips_signature_witness(void);
+static const unsigned char *fips_signature_witness(void);
 
 #define fips_w_lock()	CRYPTO_w_lock(CRYPTO_LOCK_FIPS)
 #define fips_w_unlock()	CRYPTO_w_unlock(CRYPTO_LOCK_FIPS)
@@ -148,7 +148,10 @@ void fips_set_selftest_fail(void)
 
 extern const void         *FIPS_text_start(),  *FIPS_text_end();
 extern const unsigned char FIPS_rodata_start[], FIPS_rodata_end[];
-unsigned char              FIPS_signature [20] = { 0 };
+#ifdef _TMS320C6X
+const
+#endif
+unsigned char              FIPS_signature [20] = { 0, 0xff };
 __fips_constseg
 static const char          FIPS_hmac_key[]="etaonrishdlcupfm";
 
@@ -413,9 +416,8 @@ int fips_clear_owning_thread(void)
 	return ret;
 	}
 
-unsigned char *fips_signature_witness(void)
+const unsigned char *fips_signature_witness(void)
 	{
-	extern unsigned char FIPS_signature[];
 	return FIPS_signature;
 	}
 

fips/fips_canister.c

@@ -29,12 +29,15 @@ const void         *FIPS_text_end(void);
 
 #if !defined(FIPS_REF_POINT_IS_CROSS_COMPILER_AWARE)
 # if	(defined(__ANDROID__) && (defined(__arm__) || defined(__arm)	|| \
+				  defined(__aarch64__)			|| \
 				  defined(__i386__)|| defined(__i386)))	|| \
 	(defined(__vxworks)   && (defined(__ppc__) || defined(__ppc)	|| \
 				  defined(__mips__)|| defined(__mips)))	|| \
+        (defined(__NetBSD__)  && (defined(__powerpc__) || defined(__i386))) || \
 	(defined(__linux)     && ((defined(__PPC__) && !defined(__PPC64__)) || \
 				  defined(__arm__) || defined(__arm)))	|| \
 	(defined(__APPLE__) /* verified on all MacOS X & iOS flavors */)|| \
+	(defined(_TMS320C6X))						|| \
 	(defined(_WIN32)      && defined(_MSC_VER))
 #  define FIPS_REF_POINT_IS_CROSS_COMPILER_AWARE
 # endif
@@ -70,6 +73,10 @@ const unsigned int FIPS_text_startX[]=
 #  pragma const_seg("fipsro$a")
 #  pragma const_seg()
    __declspec(allocate("fipsro$a"))
+# elif defined(_TMS320C6X)
+#  pragma CODE_SECTION(instruction_pointer,".fips_text:start")
+#  pragma CODE_SECTION(FIPS_ref_point,".fips_text:start")
+#  pragma DATA_SECTION(FIPS_rodata_start,".fips_const:start")
 # endif
 const unsigned int FIPS_rodata_start[]=
 	{ 0x46495053, 0x5f726f64, 0x6174615f, 0x73746172 };
@@ -87,6 +94,10 @@ const unsigned int FIPS_text_endX[]=
 #  pragma const_seg("fipsro$z")
 #  pragma const_seg()
    __declspec(allocate("fipsro$z"))
+# elif defined(_TMS320C6X)
+#  pragma CODE_SECTION(instruction_pointer,".fips_text:end")
+#  pragma CODE_SECTION(FIPS_ref_point,".fips_text:end")
+#  pragma DATA_SECTION(FIPS_rodata_end,".fips_const:end")
 # endif
 const unsigned int FIPS_rodata_end[]=
 	{ 0x46495053, 0x5f726f64, 0x6174615f, 0x656e645b };

fips/fips_premain.c

@@ -53,6 +53,12 @@
   int lib$initialize();
   globaldef int (*lib_init_ref)() = lib$initialize;
 # pragma __standard
+#elif defined(_TMS320C6X)
+# if defined(__TI_EABI__)
+  asm("\t.sect \".init_array\"\n\t.align 4\n\t.field FINGERPRINT_premain,32");
+# else
+  asm("\t.sect \".pinit\"\n\t.align 4\n\t.field _FINGERPRINT_premain,32");
+# endif
 #elif 0
   The rest has to be taken care of through command line:
 

fips/fips_premain.c.sha1

@@ -1 +1 @@
-HMAC-SHA1(fips_premain.c)= 1eaf66f76187877ff403708a2948d240f92736a0
+HMAC-SHA1(fips_premain.c)= 65b20c3cec235cec85af848e1cd2dfdfa101804a

fips/fips_test_suite.c

@@ -40,12 +40,46 @@ int main(int argc, char *argv[])
 
 #include <openssl/rsa.h>
 #include <openssl/dsa.h>
+#include <openssl/ecdsa.h>
 #include <openssl/dh.h>
 
 #include <openssl/fips.h>
 #include <openssl/fips_rand.h>
 #include "fips_utl.h"
 
+static int verbose = 0;
+
+static int fips_module_mode_set_verbose(int mode, const char *pass)
+	{
+	int rv;
+	if (verbose)
+		printf("Attempting to %s FIPS mode\n", mode ? "Enter" : "Leave");
+	rv = FIPS_module_mode_set(mode, pass);
+	if (verbose)
+		printf("FIPS_module_mode() returned %d\n", FIPS_module_mode());
+	return rv;
+	}
+
+static void do_print_rsa_key(RSA *rsa)
+	{
+    	if (!verbose)
+		return;
+	do_bn_print_name(stdout, "RSA key modulus value", rsa->e);
+	do_bn_print_name(stdout, "RSA key publicExponent value", rsa->n);
+	do_bn_print_name(stdout, "RSA key pricateExponent value", rsa->d);
+	do_bn_print_name(stdout, "RSA key prime1 value", rsa->p);
+	do_bn_print_name(stdout, "RSA key prime2 value", rsa->q);
+	do_bn_print_name(stdout, "RSA key exponent1 value", rsa->dmp1);
+	do_bn_print_name(stdout, "RSA key exponent2 value", rsa->dmq1);
+	do_bn_print_name(stdout, "RSA key coefficient value", rsa->iqmp);
+	}
+
+static void do_print_buf(char *name, unsigned char *buf, int buflen)
+	{
+	if (verbose)
+		OutputValue(name, buf, buflen, stdout, 0);
+	}
+
 /* AES: encrypt and decrypt known plaintext, verify result matches original plaintext
 */
 static int FIPS_aes_test(void)
@@ -57,14 +91,30 @@ static int FIPS_aes_test(void)
 	unsigned char plaintext[16] = "etaonrishdlcu";
 	EVP_CIPHER_CTX ctx;
 	FIPS_cipher_ctx_init(&ctx);
+	if (verbose)
+		{
+		do_print_buf("Key", key, sizeof(key));
+		do_print_buf("Plaintext", plaintext, sizeof(plaintext));
+		}
 	if (FIPS_cipherinit(&ctx, EVP_aes_128_ecb(), key, NULL, 1) <= 0)
 		goto err;
 	FIPS_cipher(&ctx, citmp, plaintext, 16);
+	if (verbose)
+		{
+		do_print_buf("Ciphertext", citmp, sizeof(plaintext));
+		printf("AES 128 bit ECB mode decryption started\n");
+		}
 	if (FIPS_cipherinit(&ctx, EVP_aes_128_ecb(), key, NULL, 0) <= 0)
 		goto err;
 	FIPS_cipher(&ctx, pltmp, citmp, 16);
+	do_print_buf("Recovered Plaintext", pltmp, sizeof(plaintext));
 	if (memcmp(pltmp, plaintext, 16))
+		{
+		printf("Comparison failure!!\n");
 		goto err;
+		}
+	if (verbose)
+		printf("Comparison success.\n");
 	ret = 1;
 	err:
 	FIPS_cipher_ctx_cleanup(&ctx);
@@ -83,6 +133,13 @@ static int FIPS_aes_gcm_test(void)
 	unsigned char plaintext[16] = "etaonrishdlcu";
 	EVP_CIPHER_CTX ctx;
 	FIPS_cipher_ctx_init(&ctx);
+	if (verbose)
+		{
+		do_print_buf("Key", key, sizeof(key));
+		do_print_buf("IV", key, sizeof(iv));
+		do_print_buf("Plaintext", plaintext, sizeof(plaintext));
+		do_print_buf("AAD", aad, sizeof(aad));
+		}
 	if (FIPS_cipherinit(&ctx, EVP_aes_128_gcm(), key, iv, 1) <= 0)
 		goto err;
 	FIPS_cipher(&ctx, NULL, aad, sizeof(aad));
@@ -91,6 +148,12 @@ static int FIPS_aes_gcm_test(void)
 	if (!FIPS_cipher_ctx_ctrl(&ctx, EVP_CTRL_GCM_GET_TAG, 16, tagtmp))
 		goto err;
 
+	if (verbose)
+		{
+		do_print_buf("Ciphertext", citmp, sizeof(citmp));
+		do_print_buf("Tag", tagtmp, sizeof(tagtmp));
+		}
+
 	if (FIPS_cipherinit(&ctx, EVP_aes_128_gcm(), key, iv, 0) <= 0)
 		goto err;
 	if (!FIPS_cipher_ctx_ctrl(&ctx, EVP_CTRL_GCM_SET_TAG, 16, tagtmp))
@@ -103,8 +166,17 @@ static int FIPS_aes_gcm_test(void)
 	if (FIPS_cipher(&ctx, NULL, NULL, 0) < 0)
 		goto err;
 
+	if (verbose)
+		do_print_buf("Recovered Plaintext", pltmp, sizeof(plaintext));
+
 	if (memcmp(pltmp, plaintext, 16))
+		{
+		if (verbose)
+			printf("Comparison failure!!\n");
 		goto err;
+		}
+
+	printf("Comparison sucess.\n");
 
 	ret = 1;
 	err:
@@ -122,20 +194,110 @@ static int FIPS_des3_test(void)
     	unsigned char plaintext[] = { 'e', 't', 'a', 'o', 'n', 'r', 'i', 's' };
 	EVP_CIPHER_CTX ctx;
 	FIPS_cipher_ctx_init(&ctx);
+	if (verbose)
+		{
+		do_print_buf("Key", key, sizeof(key));
+		do_print_buf("Plaintext", plaintext, sizeof(plaintext));
+		}
 	if (FIPS_cipherinit(&ctx, EVP_des_ede3_ecb(), key, NULL, 1) <= 0)
 		goto err;
 	FIPS_cipher(&ctx, citmp, plaintext, 8);
+	if (verbose)
+		{
+		do_print_buf("Ciphertext", citmp, sizeof(plaintext));
+		printf("DES3 ECB mode decryption\n");
+		}
 	if (FIPS_cipherinit(&ctx, EVP_des_ede3_ecb(), key, NULL, 0) <= 0)
 		goto err;
 	FIPS_cipher(&ctx, pltmp, citmp, 8);
+	if (verbose)
+		do_print_buf("Recovered Plaintext", pltmp, sizeof(plaintext));
 	if (memcmp(pltmp, plaintext, 8))
+		{
+		if (verbose)
+			printf("Comparison failure!!\n");
+
 		goto err;
+		}
+	if (verbose)
+		printf("Comparison success\n");
 	ret = 1;
 	err:
 	FIPS_cipher_ctx_cleanup(&ctx);
 	return ret;
 	}
 
+/*
+ * ECDSA: generate keys and sign, verify input plaintext.
+ */
+static int FIPS_ecdsa_test(void)
+    {
+    EC_KEY *ec = NULL;
+    unsigned char dgst[] = "etaonrishdlc";
+    int r = 0;
+    ECDSA_SIG *sig = NULL;
+
+    ERR_clear_error();
+    ec = FIPS_ec_key_new_by_curve_name(NID_X9_62_prime256v1);
+    if (!ec)
+	goto end;
+    if (!FIPS_ec_key_generate_key(ec))
+	goto end;
+
+    if (verbose)
+	{
+	BIGNUM *Qx, *Qy;
+	BN_CTX *ctx;
+	const EC_GROUP *grp;
+	const EC_POINT *pt;
+	const BIGNUM *priv;
+	Qx = BN_new();
+	Qy = BN_new();
+	ctx = BN_CTX_new();
+	grp = EC_KEY_get0_group(ec);
+	pt = EC_KEY_get0_public_key(ec);
+	priv = EC_KEY_get0_private_key(ec);
+	printf("EC Key using P-256\n");
+	if (!EC_POINT_get_affine_coordinates_GFp(grp, pt, Qx, Qy, ctx))
+		goto end;
+	
+	do_bn_print_name(stdout, "ECDSA key x coordinate", Qx);
+	do_bn_print_name(stdout, "ECDSA key y coordinate", Qy);
+	do_bn_print_name(stdout, "ECDSA key private value", priv);
+	BN_free(Qx);
+	BN_free(Qy);
+	BN_CTX_free(ctx);
+	printf("Signing string \"%s\" using SHA256\n", dgst);
+	}
+
+    sig = FIPS_ecdsa_sign(ec, dgst, sizeof(dgst) -1, EVP_sha256());
+    if (!sig)
+	{
+	if (verbose)
+		printf("Signing Failed!!\n");
+	goto end;
+	}
+
+    if (verbose)
+	{
+	printf("Signing successful\n");
+	do_bn_print_name(stdout, "ECDSA signature r value", sig->r);
+	do_bn_print_name(stdout, "ECDSA signature s value", sig->s);
+	}
+
+    r = FIPS_ecdsa_verify(ec, dgst, sizeof(dgst) -1, EVP_sha256(), sig);
+    if (verbose)
+	printf("ECDSA verification %s\n", r ? "Successful." : "Failed!!");
+    end:
+    if (sig)
+	FIPS_ecdsa_sig_free(sig);
+    if (ec)
+  	  FIPS_ec_key_free(ec);
+    if (r != 1)
+	return 0;
+    return 1;
+    }
+
 /*
  * DSA: generate keys and sign, verify input plaintext.
  */
@@ -157,11 +319,34 @@ static int FIPS_dsa_test(int bad)
     if (bad)
 	    BN_add_word(dsa->pub_key, 1);
 
+    if (verbose)
+	{
+	do_bn_print_name(stdout, "DSA key p value", dsa->p);
+	do_bn_print_name(stdout, "DSA key q value", dsa->q);
+	do_bn_print_name(stdout, "DSA key g value", dsa->g);
+	do_bn_print_name(stdout, "DSA key public_key value", dsa->pub_key);
+	do_bn_print_name(stdout, "DSA key private key value", dsa->priv_key);
+	printf("Signing string \"%s\" using SHA256\n", dgst);
+	}
+
     sig = FIPS_dsa_sign(dsa, dgst, sizeof(dgst) -1, EVP_sha256());
     if (!sig)
+	{
+	if (verbose)
+		printf("Signing Failed!!\n");
 	goto end;
+	}
+
+    if (verbose)
+	{
+	printf("Signing successful\n");
+	do_bn_print_name(stdout, "DSA signature r value", sig->r);
+	do_bn_print_name(stdout, "DSA signature s value", sig->s);
+	}
 
     r = FIPS_dsa_verify(dsa, dgst, sizeof(dgst) -1, EVP_sha256(), sig);
+    if (verbose)
+	printf("DSA verification %s\n", r ? "Successful." : "Failed!!");
     end:
     if (sig)
 	FIPS_dsa_sig_free(sig);
@@ -196,12 +381,30 @@ static int FIPS_rsa_test(int bad)
     if (bad)
 	    BN_add_word(key->n, 1);
 
+    if (verbose)
+	{
+    	do_print_rsa_key(key);
+	printf("Signing string \"%s\" using SHA256\n", input_ptext);
+	}
+
     if (!FIPS_rsa_sign(key, input_ptext, sizeof(input_ptext) - 1, EVP_sha256(),
 			RSA_PKCS1_PADDING, 0, NULL, buf, &slen))
+	{
+	if (verbose)
+		printf("RSA Signing failed!!\n");
 	goto end;
+	}
+
+    if (verbose)
+	{
+	printf("RSA signing successul\n");
+	do_print_buf("RSA signature", buf, slen);
+	}
 
     r = FIPS_rsa_verify(key, input_ptext, sizeof(input_ptext) - 1, EVP_sha256(),
 			RSA_PKCS1_PADDING, 0, NULL, buf, slen);
+    if (verbose)
+	printf("RSA Verification %s\n", r == 1 ? "Successful" : "Failed!!");
     end:
     if (key)
   	  FIPS_rsa_free(key);
@@ -223,6 +426,11 @@ static int FIPS_sha1_test()
 
     ERR_clear_error();
     if (!FIPS_digest(str,sizeof(str) - 1,md, NULL, EVP_sha1())) return 0;
+    if (verbose)
+	{
+	printf("Digesting string %s\n", str);
+	do_print_buf("Digest value", md, sizeof(md));
+	}
     if (memcmp(md,digest,sizeof(md)))
         return 0;
     return 1;
@@ -242,6 +450,11 @@ static int FIPS_sha256_test()
 
     ERR_clear_error();
     if (!FIPS_digest(str,sizeof(str) - 1,md, NULL, EVP_sha256())) return 0;
+    if (verbose)
+	{
+	printf("Digesting string %s\n", str);
+	do_print_buf("Digest value", md, sizeof(md));
+	}
     if (memcmp(md,digest,sizeof(md)))
         return 0;
     return 1;
@@ -263,6 +476,11 @@ static int FIPS_sha512_test()
 
     ERR_clear_error();
     if (!FIPS_digest(str,sizeof(str) - 1,md, NULL, EVP_sha512())) return 0;
+    if (verbose)
+	{
+	printf("Digesting string %s\n", str);
+	do_print_buf("Digest value", md, sizeof(md));
+	}
     if (memcmp(md,digest,sizeof(md)))
         return 0;
     return 1;
@@ -284,8 +502,19 @@ static int FIPS_hmac_sha1_test()
 
     ERR_clear_error();
     if (!HMAC(EVP_sha1(),key,sizeof(key)-1,iv,sizeof(iv)-1,out,&outlen)) return 0;
+    if (verbose)
+	{
+	do_print_buf("HMAC key", key, sizeof(key) -1);
+	do_print_buf("HMAC input", iv, sizeof(iv) -1);
+	do_print_buf("HMAC output", out, outlen);
+	}
     if (memcmp(out,kaval,outlen))
+	{
+	if (verbose)
+		printf("HMAC comparison failed!!\n");
         return 0;
+	}
+    printf("HMAC comparison successful.\n");
     return 1;
     }
 
@@ -305,6 +534,19 @@ static int FIPS_hmac_sha224_test()
 
     ERR_clear_error();
     if (!HMAC(EVP_sha224(),key,sizeof(key)-1,iv,sizeof(iv)-1,out,&outlen)) return 0;
+    if (verbose)
+	{
+	do_print_buf("HMAC key", key, sizeof(key) -1);
+	do_print_buf("HMAC input", iv, sizeof(iv) -1);
+	do_print_buf("HMAC output", out, outlen);
+	}
+    if (memcmp(out,kaval,outlen))
+	{
+	if (verbose)
+		printf("HMAC comparison failed!!\n");
+        return 0;
+	}
+    printf("HMAC comparison successful.\n");
     if (memcmp(out,kaval,outlen))
         return 0;
     return 1;
@@ -326,8 +568,19 @@ static int FIPS_hmac_sha256_test()
 
     ERR_clear_error();
     if (!HMAC(EVP_sha256(),key,sizeof(key)-1,iv,sizeof(iv)-1,out,&outlen)) return 0;
+    if (verbose)
+	{
+	do_print_buf("HMAC key", key, sizeof(key) -1);
+	do_print_buf("HMAC input", iv, sizeof(iv) -1);
+	do_print_buf("HMAC output", out, outlen);
+	}
     if (memcmp(out,kaval,outlen))
+	{
+	if (verbose)
+		printf("HMAC comparison failed!!\n");
         return 0;
+	}
+    printf("HMAC comparison successful.\n");
     return 1;
     }
 
@@ -348,8 +601,19 @@ static int FIPS_hmac_sha384_test()
 
     ERR_clear_error();
     if (!HMAC(EVP_sha384(),key,sizeof(key)-1,iv,sizeof(iv)-1,out,&outlen)) return 0;
+    if (verbose)
+	{
+	do_print_buf("HMAC key", key, sizeof(key) -1);
+	do_print_buf("HMAC input", iv, sizeof(iv) -1);
+	do_print_buf("HMAC output", out, outlen);
+	}
     if (memcmp(out,kaval,outlen))
+	{
+	if (verbose)
+		printf("HMAC comparison failed!!\n");
         return 0;
+	}
+    printf("HMAC comparison successful.\n");
     return 1;
     }
 
@@ -371,8 +635,19 @@ static int FIPS_hmac_sha512_test()
 
     ERR_clear_error();
     if (!HMAC(EVP_sha512(),key,sizeof(key)-1,iv,sizeof(iv)-1,out,&outlen)) return 0;
+    if (verbose)
+	{
+	do_print_buf("HMAC key", key, sizeof(key) -1);
+	do_print_buf("HMAC input", iv, sizeof(iv) -1);
+	do_print_buf("HMAC output", out, outlen);
+	}
     if (memcmp(out,kaval,outlen))
+	{
+	if (verbose)
+		printf("HMAC comparison failed!!\n");
         return 0;
+	}
+    printf("HMAC comparison successful.\n");
     return 1;
     }
 
@@ -407,18 +682,15 @@ static int FIPS_cmac_aes128_test()
     out = OPENSSL_malloc(outlen);
     if (!CMAC_Final(ctx, out, &outlen))
 	    goto end;
-#if 0
-    {
-    char *hexout = OPENSSL_malloc(outlen * 2 + 1);
-    bin2hex(out, outlen, hexout);
-    printf("CMAC-AES128: res = %s\n", hexout);
-    OPENSSL_free(hexout);
-    }
-    r = 1;
-#else
     if (!memcmp(out,kaval,outlen))
 	    r = 1;
-#endif
+    if (verbose)
+	{
+	do_print_buf("CMAC key", key, sizeof(key));
+	do_print_buf("CMAC input", data, sizeof(data) -1);
+	do_print_buf("CMAC output", out, outlen);
+	printf("CMAC comparison %s\n", r == 1 ? "successful." : "Failed!!");
+	}
     end:
     CMAC_CTX_free(ctx);
     if (out)
@@ -458,18 +730,15 @@ static int FIPS_cmac_aes192_test()
     out = OPENSSL_malloc(outlen);
     if (!CMAC_Final(ctx, out, &outlen))
 	    goto end;
-#if 0
-    {
-    char *hexout = OPENSSL_malloc(outlen * 2 + 1);
-    bin2hex(out, outlen, hexout);
-    printf("CMAC-AES192: res = %s\n", hexout);
-    OPENSSL_free(hexout);
-    }
-    r = 1;
-#else
     if (!memcmp(out,kaval,outlen))
 	    r = 1;
-#endif
+    if (verbose)
+	{
+	do_print_buf("CMAC key", key, sizeof(key));
+	do_print_buf("CMAC input", data, sizeof(data) -1);
+	do_print_buf("CMAC output", out, outlen);
+	printf("CMAC comparison %s\n", r == 1 ? "successful." : "Failed!!");
+	}
     end:
     CMAC_CTX_free(ctx);
     if (out)
@@ -510,18 +779,15 @@ static int FIPS_cmac_aes256_test()
     out = OPENSSL_malloc(outlen);
     if (!CMAC_Final(ctx, out, &outlen))
 	    goto end;
-#if 0
-    {
-    char *hexout = OPENSSL_malloc(outlen * 2 + 1);
-    bin2hex(out, outlen, hexout);
-    printf("CMAC-AES256: res = %s\n", hexout);
-    OPENSSL_free(hexout);
-    }
-    r = 1;
-#else
     if (!memcmp(out,kaval,outlen))
 	    r = 1;
-#endif
+    if (verbose)
+	{
+	do_print_buf("CMAC key", key, sizeof(key));
+	do_print_buf("CMAC input", data, sizeof(data) -1);
+	do_print_buf("CMAC output", out, outlen);
+	printf("CMAC comparison %s\n", r == 1 ? "successful." : "Failed!!");
+	}
     end:
     CMAC_CTX_free(ctx);
     if (out)
@@ -560,18 +826,15 @@ static int FIPS_cmac_tdea3_test()
     out = OPENSSL_malloc(outlen);
     if (!CMAC_Final(ctx, out, &outlen))
 	    goto end;
-#if 0
-    {
-    char *hexout = OPENSSL_malloc(outlen * 2 + 1);
-    bin2hex(out, outlen, hexout);
-    printf("CMAC-TDEA3: res = %s\n", hexout);
-    OPENSSL_free(hexout);
-    }
-    r = 1;
-#else
     if (!memcmp(out,kaval,outlen))
 	    r = 1;
-#endif
+    if (verbose)
+	{
+	do_print_buf("CMAC key", key, sizeof(key));
+	do_print_buf("CMAC input", data, sizeof(data) -1);
+	do_print_buf("CMAC output", out, outlen);
+	printf("CMAC comparison %s\n", r == 1 ? "successful." : "Failed!!");
+	}
     end:
     CMAC_CTX_free(ctx);
     if (out)
@@ -627,7 +890,11 @@ static int Zeroize()
     for(i = 0; i < sizeof(userkey); i++) printf("%02x", userkey[i]);
         printf("\n");
     RAND_bytes(userkey, sizeof userkey);
-    printf("\tchar buffer key after overwriting: \n\t\t");
+    printf("\tchar buffer key after overwriting with random key: \n\t\t");
+    for(i = 0; i < sizeof(userkey); i++) printf("%02x", userkey[i]);
+        printf("\n");
+    OPENSSL_cleanse(userkey, sizeof(userkey));
+    printf("\tchar buffer key after zeroization: \n\t\t");
     for(i = 0; i < sizeof(userkey); i++) printf("%02x", userkey[i]);
         printf("\n");
 
@@ -747,9 +1014,13 @@ static const char * Fail(const char *msg)
     return msg; 
     }
 
-static void test_msg(const char *msg, int result)
-	{
-	printf("%s...%s\n", msg, result ? "successful" : Fail("Failed!"));
+#define test_msg(msg, rtest) \
+	{ \
+	int rv; \
+	if (verbose) \
+		printf("%s...started\n", msg); \
+	rv = rtest; \
+	printf("%s...%s\n", msg, rv ? "successful" : Fail("Failed!")); \
 	}
 
 /* Table of IDs for POST translating between NIDs and names */
@@ -810,13 +1081,15 @@ static const char *lookup_id(int id)
 static int fail_id = -1;
 static int fail_sub = -1;
 static int fail_key = -1;
+static int sub_num = -1, sub_count = -1;
+static int sub_fail_num = -1;
 
 static int st_err, post_quiet = 0;
 
 static int post_cb(int op, int id, int subid, void *ex)
 	{
 	const char *idstr, *exstr = "";
-	char asctmp[20];
+	char asctmp[20], teststr[80];
 	int keytype = -1;
 	int exp_fail = 0;
 #ifdef FIPS_POST_TIME
@@ -935,6 +1208,16 @@ static int post_cb(int op, int id, int subid, void *ex)
 		&& (fail_sub == -1 || fail_sub == subid))
 			exp_fail = 1;
 
+	if (sub_num > 0)
+		{
+		if (sub_fail_num == sub_num)
+			exp_fail = 1;
+		sprintf(teststr, "\t\t%s %s (POST subtest #%d) test",
+						idstr, exstr, sub_num);
+		}
+	else
+		sprintf(teststr, "\t\t%s %s test", idstr, exstr);
+
 	switch(op)
 		{
 		case FIPS_POST_BEGIN:
@@ -945,9 +1228,16 @@ static int post_cb(int op, int id, int subid, void *ex)
 		clock_gettime(CLOCK_REALTIME, &tstart);
 #endif
 		printf("\tPOST started\n");
+		sub_num = 1;
 		break;
 
 		case FIPS_POST_END:
+		if (sub_count == -1)
+			sub_count = sub_num;
+		else if (sub_num != sub_count)
+			printf("Inconsistent POST count %d != %d\n",
+							sub_num, sub_count);
+		sub_num = -1;
 		printf("\tPOST %s\n", id ? "Success" : "Failed");
 #ifdef FIPS_POST_TIME
 		clock_gettime(CLOCK_REALTIME, &tend);
@@ -959,21 +1249,22 @@ static int post_cb(int op, int id, int subid, void *ex)
 
 		case FIPS_POST_STARTED:
 		if (!post_quiet && !exp_fail)
-			printf("\t\t%s %s test started\n", idstr, exstr);
+			printf("%s started\n", teststr);
 #ifdef FIPS_POST_TIME
 		clock_gettime(CLOCK_REALTIME, &start);
 #endif
 		break;
 
 		case FIPS_POST_SUCCESS:
+		if (sub_num > 0)
+			sub_num++;
 		if (exp_fail)
 			{
-			printf("\t\t%s %s test OK but should've failed\n",
-								idstr, exstr);
+			printf("%s OK but should've failed\n", teststr);
 			st_err++;
 			}
 		else if (!post_quiet)
-			printf("\t\t%s %s test OK\n", idstr, exstr);
+			printf("%s OK\n", teststr);
 #ifdef FIPS_POST_TIME
 		clock_gettime(CLOCK_REALTIME, &end);
 		printf("\t\t\tTook %f seconds\n",
@@ -983,15 +1274,13 @@ static int post_cb(int op, int id, int subid, void *ex)
 		break;
 
 		case FIPS_POST_FAIL:
+		if (sub_num > 0)
+			sub_num++;
 		if (exp_fail)
-			{
-			printf("\t\t%s %s test failed as expected\n",
-							idstr, exstr);
-			}
+			printf("%s failed as expected\n", teststr);
 		else
 			{
-			printf("\t\t%s %s test Failed Incorrectly!!\n",
-							idstr, exstr);
+			printf("%s Failed Incorrectly!!\n", teststr);
 			st_err++;
 			}
 		break;
@@ -999,7 +1288,7 @@ static int post_cb(int op, int id, int subid, void *ex)
 		case FIPS_POST_CORRUPT:
 		if (exp_fail)
 			{
-			printf("\t\t%s %s test failure induced\n", idstr, exstr);
+			printf("%s failure induced\n", teststr);
 			return 0;
 			}
 		break;
@@ -1008,63 +1297,48 @@ static int post_cb(int op, int id, int subid, void *ex)
 	return 1;
 	}
 
-/* Test POST induced failures */
-
-typedef struct 
-	{
-	const char *name;
-	int id, subid, keyid;
-	} fail_list;
-
-static fail_list flist[] =
-	{
-	{"Integrity", FIPS_TEST_INTEGRITY, -1, -1},
-	{"AES", FIPS_TEST_CIPHER, NID_aes_128_ecb, -1},
-	{"DES3", FIPS_TEST_CIPHER, NID_des_ede3_ecb, -1},
-	{"AES-GCM", FIPS_TEST_GCM, -1, -1},
-	{"AES-CCM", FIPS_TEST_CCM, -1, -1},
-	{"AES-XTS", FIPS_TEST_XTS, -1, -1},
-	{"Digest", FIPS_TEST_DIGEST, -1, -1},
-	{"HMAC", FIPS_TEST_HMAC, -1, -1},
-	{"CMAC", FIPS_TEST_CMAC, -1, -1},
-	{"DRBG", FIPS_TEST_DRBG, -1, -1},
-	{"X9.31 PRNG", FIPS_TEST_X931, -1, -1},
-	{"RSA", FIPS_TEST_SIGNATURE, -1, EVP_PKEY_RSA},
-	{"DSA", FIPS_TEST_SIGNATURE, -1, EVP_PKEY_DSA},
-	{"ECDSA", FIPS_TEST_SIGNATURE, -1, EVP_PKEY_EC},
-	{"ECDH", FIPS_TEST_ECDH, -1, -1},
-	{NULL, -1, -1, -1}
-	};
-
 static int do_fail_all(int fullpost, int fullerr)
 	{
-	fail_list *ftmp;
 	int rv;
 	size_t i;
+	int sub_fail;
 	RSA *rsa = NULL;
 	DSA *dsa = NULL;
 	DRBG_CTX *dctx = NULL, *defctx = NULL;
 	EC_KEY *ec = NULL;
 	BIGNUM *bn = NULL;
+	unsigned char key[16] = {1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16};
+	EVP_CIPHER_CTX ctx;
 	unsigned char out[10];
 	if (!fullpost)
 		post_quiet = 1;
 	if (!fullerr)
 		no_err = 1;
-	FIPS_module_mode_set(0, NULL);
-	for (ftmp = flist; ftmp->name; ftmp++)
+	fips_module_mode_set_verbose(0, NULL);
+	for (sub_fail = 1; sub_fail < sub_count; sub_fail++)
 		{
-		printf("    Testing induced failure of %s test\n", ftmp->name);
-		fail_id = ftmp->id;
-		fail_sub = ftmp->subid;
-		fail_key = ftmp->keyid;
-		rv = FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS);
+		sub_fail_num = sub_fail;
+		printf("    Testing induced failure of POST subtest %d\n",
+								sub_fail);
+		rv = fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS);
 		if (rv)
 			{
 			printf("\tFIPS mode incorrectly successful!!\n");
 			st_err++;
 			}
+		printf("\tAttempting crypto operation after failed POST... ");
+		FIPS_cipher_ctx_init(&ctx);
+		rv = FIPS_cipherinit(&ctx, EVP_aes_128_ecb(), key, NULL, 1);
+		if (rv > 0)
+			{
+			printf("succeeded incorrectly!!\n");
+			st_err++;
+			}
+		else
+			printf("failed as expected.\n");
+		FIPS_cipher_ctx_cleanup(&ctx);
 		}
+	sub_fail_num = -1;
 	printf("    Testing induced failure of RSA keygen test\n");
 	/* NB POST will succeed with a pairwise test failures as
 	 * it is not used during POST.
@@ -1072,7 +1346,7 @@ static int do_fail_all(int fullpost, int fullerr)
 	fail_id = FIPS_TEST_PAIRWISE;
 	fail_key = EVP_PKEY_RSA;
 	/* Now enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1092,12 +1366,12 @@ static int do_fail_all(int fullpost, int fullerr)
 		printf("\tRSA key generation failed as expected.\n");
 
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 
 	printf("    Testing induced failure of DSA keygen test\n");
 	fail_key = EVP_PKEY_DSA;
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1116,9 +1390,9 @@ static int do_fail_all(int fullpost, int fullerr)
 		printf("\tDSA key generation failed as expected.\n");
 
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1147,9 +1421,9 @@ static int do_fail_all(int fullpost, int fullerr)
 	fail_sub = -1;
 	fail_key = -1;
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1182,9 +1456,9 @@ static int do_fail_all(int fullpost, int fullerr)
 	FIPS_drbg_stick(0);
 
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1212,9 +1486,9 @@ static int do_fail_all(int fullpost, int fullerr)
 	else
 		printf("\tDRBG continuous PRNG entropy failed as expected\n");
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1222,9 +1496,9 @@ static int do_fail_all(int fullpost, int fullerr)
 	FIPS_drbg_free(dctx);
 
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1252,9 +1526,9 @@ static int do_fail_all(int fullpost, int fullerr)
 	FIPS_x931_stick(0);
 
 	/* Leave FIPS mode to clear error */
-	FIPS_module_mode_set(0, NULL);
+	fips_module_mode_set_verbose(0, NULL);
 	/* Enter FIPS mode successfully */
-	if (!FIPS_module_mode_set(1, FIPS_AUTH_USER_PASS))
+	if (!fips_module_mode_set_verbose(1, FIPS_AUTH_USER_PASS))
 		{
 		printf("\tError entering FIPS mode\n");
 		st_err++;
@@ -1337,6 +1611,12 @@ int main(int argc, char **argv)
 
     FIPS_post_set_callback(post_cb);
 
+#if (defined(__arm__) || defined(__aarch64__))
+    extern unsigned int OPENSSL_armcap_P;
+    if (0 == OPENSSL_armcap_P)
+	fprintf(stderr, "Optimizations disabled\n");
+#endif
+
     printf("\tFIPS-mode test application\n");
 
     printf("\t%s\n\n", FIPS_module_version_text());
@@ -1426,6 +1706,9 @@ int main(int argc, char **argv)
 	} else if (!strcmp(*args, "fullerr")) {
 		fullerr = 1;
 	    	no_exit = 1;
+	} else if (!strcmp(*args, "verbose")) {
+		verbose = 1;
+		no_exit = 1;
         } else {
             printf("Bad argument \"%s\"\n", *args);
             return 1;
@@ -1435,7 +1718,7 @@ int main(int argc, char **argv)
 
     if ((argc != 1) && !no_exit) {
     		fips_algtest_init_nofips();
-        	if (!FIPS_module_mode_set(1, pass)) {
+        	if (!fips_module_mode_set_verbose(1, pass)) {
         	    printf("Power-up self test failed\n");
 		    return 1;
 		}
@@ -1456,7 +1739,7 @@ int main(int argc, char **argv)
     /* Power-up self test
     */
     ERR_clear_error();
-    test_msg("2. Automatic power-up self test", FIPS_module_mode_set(1, pass));
+    test_msg("2a. Automatic power-up self test", fips_module_mode_set_verbose(1, pass));
     if (!FIPS_module_mode())
 	return 1;
     if (do_drbg_stick)
@@ -1464,6 +1747,8 @@ int main(int argc, char **argv)
     if (do_rng_stick)
             FIPS_x931_stick(1);
 
+    test_msg("2b. On demand self test", FIPS_selftest());
+
     /* AES encryption/decryption
     */
     test_msg("3a. AES encryption/decryption", FIPS_aes_test());
@@ -1564,7 +1849,10 @@ int main(int argc, char **argv)
     	printf("\t%s\n", do_drbg_all() ? "successful as expected"
 					: Fail("failed INCORRECTLY!") );
 
-    printf("13. Induced test failure check...\n");
+    test_msg("13. ECDSA key generation and signature validation",
+    						FIPS_ecdsa_test());
+
+    printf("14. Induced test failure check...\n");
     printf("\t%s\n", do_fail_all(fullpost, fullerr) ? "successful as expected"
 					: Fail("failed INCORRECTLY!") );
     printf("\nAll tests completed with %d errors\n", Error);

fips/fipsalgtest.pl

@@ -495,6 +495,7 @@ my $onedir = 0;
 my $filter = "";
 my $tvdir;
 my $tprefix;
+my $sfprefix = "";
 my $debug          = 0;
 my $quiet          = 0;
 my $notest         = 0;
@@ -615,6 +616,9 @@ foreach (@ARGV) {
     elsif (/--script-tprefix=(.*)$/) {
         $stprefix = $1;
     }
+    elsif (/--script-fprefix=(.*)$/) {
+        $sfprefix = $1;
+    }
     elsif (/--mkdir=(.*)$/) {
         $mkcmd = $1;
     }
@@ -1017,6 +1021,10 @@ END
             $out =~ s|/req/(\S+)\.req|/$rspdir/$1.rsp|;
             my $outdir = $out;
             $outdir =~ s|/[^/]*$||;
+            if ( !-d $outdir  && ($outfile eq "" || $minimal_script)) {
+                print STDERR "DEBUG: Creating directory $outdir\n" if $debug;
+                mkdir($outdir) || die "Can't create directory $outdir";
+            }
 	    if ($outfile ne "") {
 	    	if ($win32) {
 		    $outdir =~ tr|/|\\|;
@@ -1039,12 +1047,9 @@ END
 		    }
 		$lastdir = $outdir;
 		}
-            } elsif ( !-d $outdir ) {
-                print STDERR "DEBUG: Creating directory $outdir\n" if $debug;
-                mkdir($outdir) || die "Can't create directory $outdir";
             }
         }
-        my $cmd = "$tcmd \"$req\" \"$out\"";
+        my $cmd = "$tcmd \"$sfprefix$req\" \"$sfprefix$out\"";
         print STDERR "DEBUG: running test $tname\n" if ( $debug && !$verify );
 	if ($outfile ne "") {
 	    if ($minimal_script) {

fips/fipssyms.h

@@ -589,6 +589,7 @@
 #define AES_encrypt fips_aes_encrypt
 #define AES_set_decrypt_key fips_aes_set_decrypt_key
 #define AES_set_encrypt_key fips_aes_set_encrypt_key
+#define AES_ctr32_encrypt fips_aes_ctr32_encrypt
 #define BN_from_montgomery fips_bn_from_montgomery
 #define BN_num_bits_word FIPS_bn_num_bits_word
 #define DES_SPtrans fips_des_sptrans
@@ -667,6 +668,50 @@
 #define bn_mul_mont_gather5 fips_bn_mul_mont_gather5
 #define bn_scatter5 fips_bn_scatter5
 #define bn_gather5 fips_bn_gather5
+#define _armv8_aes_probe _fips_armv8_aes_probe
+#define _armv8_pmull_probe _fips_armv8_pmull_probe
+#define _armv8_sha1_probe _fips_armv8_sha1_probe
+#define _armv8_sha256_probe _fips_armv8_sha256_probe
+#define aes_v8_encrypt fips_aes_v8_encrypt
+#define aes_v8_decrypt fips_aes_v8_decrypt
+#define aes_v8_set_encrypt_key fips_aes_v8_set_encrypt_key
+#define aes_v8_set_decrypt_key fips_aes_v8_set_decrypt_key
+#define aes_v8_cbc_encrypt fips_aes_v8_cbc_encrypt
+#define aes_v8_ctr32_encrypt_blocks fips_aes_v8_ctr32_encrypt_blocks
+#define gcm_init_v8 fips_gcm_init_v8
+#define gcm_gmult_v8 fips_gcm_gmult_v8
+#define gcm_ghash_v8 fips_gcm_ghash_v8
+#if defined(__APPLE__) && __ASSEMBLER__
+#define _OPENSSL_armcap_P _fips_openssl_armcap_P
+#define __armv7_neon_probe __fips_armv7_neon_probe
+#define __armv7_tick __fips_armv7_tick
+#define __armv8_aes_probe __fips_armv8_aes_probe
+#define __armv8_pmull_probe __fips_armv8_pmull_probe
+#define __armv8_sha1_probe __fips_armv8_sha1_probe
+#define __armv8_sha256_probe __fips_armv8_sha256_probe
+#define _aes_v8_encrypt _fips_aes_v8_encrypt
+#define _aes_v8_decrypt _fips_aes_v8_decrypt
+#define _aes_v8_set_encrypt_key _fips_aes_v8_set_encrypt_key
+#define _aes_v8_set_decrypt_key _fips_aes_v8_set_decrypt_key
+#define _aes_v8_cbc_encrypt _fips_aes_v8_cbc_encrypt
+#define _aes_v8_ctr32_encrypt_blocks _fips_aes_v8_ctr32_encrypt_blocks
+#define _gcm_init_v8 _fips_gcm_init_v8
+#define _gcm_gmult_v8 _fips_gcm_gmult_v8
+#define _gcm_ghash_v8 _fips_gcm_ghash_v8
+#define _sha1_block_data_order _fips_sha1_block_data_order
+#define _sha256_block_data_order _fips_sha256_block_data_order
+#define _sha512_block_data_order _fips_sha512_block_data_order
+#define _AES_decrypt _fips_aes_decrypt
+#define _AES_encrypt _fips_aes_encrypt
+#define _AES_set_decrypt_key _fips_aes_set_decrypt_key
+#define _AES_set_encrypt_key _fips_aes_set_encrypt_key
+#define _gcm_gmult_4bit _fips_gcm_gmult_4bit
+#define _gcm_ghash_4bit _fips_gcm_ghash_4bit
+#define _gcm_gmult_neon _fips_gcm_gmult_neon
+#define _gcm_ghash_neon _fips_gcm_ghash_neon
+#define _bn_GF2m_mul_2x2 _fips_bn_GF2m_mul_2x2
+#define _OPENSSL_cleanse _FIPS_openssl_cleanse
+#endif
 
 #if defined(_MSC_VER)
 # pragma const_seg("fipsro$b")

fips/rand/fips_drbgvs.c

@@ -182,7 +182,7 @@ int main(int argc,char **argv)
 	int r, nid = 0;
 	int pr = 0;
 	char buf[2048], lbuf[2048];
-	unsigned char randout[2048];
+	unsigned char *randout = NULL;
 	char *keyword = NULL, *value = NULL;
 
 	unsigned char *ent = NULL, *nonce = NULL, *pers = NULL, *adin = NULL;
@@ -298,6 +298,8 @@ int main(int argc,char **argv)
 			else
 				exit(1);
 			}
+		if (!strcmp(keyword, "[ReturnedBitsLen"))
+			randoutlen = atoi(value) / 8;
 
 		if (!strcmp(keyword, "EntropyInput"))
 			{
@@ -327,7 +329,11 @@ int main(int argc,char **argv)
 			FIPS_drbg_set_callbacks(dctx, test_entropy, 0, 0,
 							test_nonce, 0);
 			FIPS_drbg_set_app_data(dctx, &t);
-			randoutlen = (int)FIPS_drbg_get_blocklength(dctx);
+			if (randoutlen == 0)
+				randoutlen = (int)FIPS_drbg_get_blocklength(dctx);
+			if (randout)
+				OPENSSL_free(randout);
+			randout = OPENSSL_malloc(randoutlen);
 			r = FIPS_drbg_instantiate(dctx, pers, perslen);
 			if (!r)
 				{
@@ -406,6 +412,8 @@ int main(int argc,char **argv)
 			}
 
 		}
+	if (randout)
+		OPENSSL_free(randout);
 	if (in && in != stdin)
 		fclose(in);
 	if (out && out != stdout)

fips/rand/fips_rand.c

@@ -66,7 +66,7 @@
 #include <openssl/aes.h>
 #include <openssl/err.h>
 #include <openssl/fips_rand.h>
-#if !(defined(OPENSSL_SYS_WIN32) || defined(OPENSSL_SYS_VXWORKS))
+#if !(defined(OPENSSL_SYS_WIN32) || defined(OPENSSL_SYS_VXWORKS) || defined(OPENSSL_SYSNAME_DSPBIOS))
 # include <sys/time.h>
 #endif
 #if defined(OPENSSL_SYS_VXWORKS)
@@ -232,8 +232,13 @@ void FIPS_get_timevec(unsigned char *buf, unsigned long *pctr)
 	{
 #ifdef OPENSSL_SYS_WIN32
 	FILETIME ft;
+#ifdef _WIN32_WCE
+	SYSTEMTIME t;
+#endif
 #elif defined(OPENSSL_SYS_VXWORKS)
         struct timespec ts;
+#elif defined(OPENSSL_SYSNAME_DSPBIOS)
+	unsigned long long TSC, OPENSSL_rdtsc();
 #else
 	struct timeval tv;
 #endif
@@ -243,7 +248,12 @@ void FIPS_get_timevec(unsigned char *buf, unsigned long *pctr)
 #endif
 
 #ifdef OPENSSL_SYS_WIN32
+#ifdef _WIN32_WCE
+	GetSystemTime(&t);
+	SystemTimeToFileTime(&t, &ft);
+#else
 	GetSystemTimeAsFileTime(&ft);
+#endif
 	buf[0] = (unsigned char) (ft.dwHighDateTime & 0xff);
 	buf[1] = (unsigned char) ((ft.dwHighDateTime >> 8) & 0xff);
 	buf[2] = (unsigned char) ((ft.dwHighDateTime >> 16) & 0xff);
@@ -262,6 +272,16 @@ void FIPS_get_timevec(unsigned char *buf, unsigned long *pctr)
 	buf[5] = (unsigned char) ((ts.tv_nsec >> 8) & 0xff);
 	buf[6] = (unsigned char) ((ts.tv_nsec >> 16) & 0xff);
 	buf[7] = (unsigned char) ((ts.tv_nsec >> 24) & 0xff);
+#elif defined(OPENSSL_SYSNAME_DSPBIOS)
+	TSC = OPENSSL_rdtsc();
+	buf[0] = (unsigned char) (TSC & 0xff);
+	buf[1] = (unsigned char) ((TSC >> 8) & 0xff);
+	buf[2] = (unsigned char) ((TSC >> 16) & 0xff);
+	buf[3] = (unsigned char) ((TSC >> 24) & 0xff);
+	buf[4] = (unsigned char) ((TSC >> 32) & 0xff);
+	buf[5] = (unsigned char) ((TSC >> 40) & 0xff);
+	buf[6] = (unsigned char) ((TSC >> 48) & 0xff);
+	buf[7] = (unsigned char) ((TSC >> 56) & 0xff);
 #else
 	gettimeofday(&tv,NULL);
 	buf[0] = (unsigned char) (tv.tv_sec & 0xff);

fips/rsa/fips_rsa_sign.c

@@ -288,8 +288,11 @@ int FIPS_rsa_sign_digest(RSA *rsa, const unsigned char *md, int md_len,
 			*siglen=j;
 			}
 		psserr:
-		OPENSSL_cleanse(sbuf, i);
-		OPENSSL_free(sbuf);
+		if (sbuf)
+			{
+			OPENSSL_cleanse(sbuf, i);
+			OPENSSL_free(sbuf);
+			}
 		return ret;
 		}
 

fips/sha/Makefile

@@ -30,7 +30,8 @@ LIB=$(TOP)/libcrypto.a
 LIBSRC=fips_sha1_selftest.c
 LIBOBJ=fips_sha1_selftest.o
 
-SRC= $(LIBSRC) fips_standalone_sha1.c
+SRC= $(LIBSRC)
+PROGS= fips_standalone_sha1.c
 
 EXHEADER=
 HEADER=	

fips/utl/fips_enc.c

@@ -208,6 +208,7 @@ int FIPS_cipherinit(EVP_CIPHER_CTX *ctx, const EVP_CIPHER *cipher,
 			break;
 
 			case EVP_CIPH_CTR_MODE:
+			ctx->num = 0;
 			/* Don't reuse IV for CTR mode */
 			if(iv)
 				memcpy(ctx->iv, iv, M_EVP_CIPHER_CTX_iv_length(ctx));

iOS/Makefile

@@ -0,0 +1,76 @@
+#
+#  OpenSSL/iOS/Makefile
+#
+
+DIR=		iOS
+TOP=		..
+CC=		cc
+INCLUDES=	-I$(TOP) -I$(TOP)/include
+CFLAG=		-g -static
+MAKEFILE=	Makefile
+PERL=		perl
+RM=		rm -f
+
+EXE=incore_macho
+
+CFLAGS= $(INCLUDES) $(CFLAG)
+
+top:
+	@$(MAKE) -f $(TOP)/Makefile reflect THIS=exe
+
+exe:	fips_algvs.app/fips_algvs
+
+incore_macho:			incore_macho.c $(TOP)/crypto/sha/sha1dgst.c
+	$(HOSTCC) $(HOSTCFLAGS) -I$(TOP)/include -I$(TOP)/crypto -o $@ incore_macho.c $(TOP)/crypto/sha/sha1dgst.c
+
+fips_algvs.app/fips_algvs:	$(TOP)/test/fips_algvs.c $(TOP)/fips/fipscanister.o fopen.m incore_macho
+	FIPS_SIG=./incore_macho \
+	$(TOP)/fips/fipsld $(CFLAGS) -I$(TOP)/fips -o $@ \
+		$(TOP)/test/fips_algvs.c $(TOP)/fips/fipscanister.o \
+		fopen.m -framework Foundation || rm $@
+	codesign -f -s "iPhone Developer" --entitlements fips_algvs.app/Entitlements.plist fips_algvs.app || rm $@
+
+install:
+	@[ -n "$(INSTALLTOP)" ] # should be set by top Makefile...
+	@set -e; for i in $(EXE); \
+	do  \
+	(echo installing $$i; \
+	 cp $$i $(INSTALL_PREFIX)$(INSTALLTOP)/bin/$$i.new; \
+	 chmod 755 $(INSTALL_PREFIX)$(INSTALLTOP)/bin/$$i.new; \
+	 mv -f $(INSTALL_PREFIX)$(INSTALLTOP)/bin/$$i.new $(INSTALL_PREFIX)$(INSTALLTOP)/bin/$$i ); \
+	 done;
+	@set -e; for i in $(SCRIPTS); \
+	do  \
+	(echo installing $$i; \
+	 cp $$i $(INSTALL_PREFIX)$(OPENSSLDIR)/misc/$$i.new; \
+	 chmod 755 $(INSTALL_PREFIX)$(OPENSSLDIR)/misc/$$i.new; \
+	 mv -f $(INSTALL_PREFIX)$(OPENSSLDIR)/misc/$$i.new $(INSTALL_PREFIX)$(OPENSSLDIR)/misc/$$i ); \
+	 done
+
+tags:
+	ctags $(SRC)
+
+tests:
+
+links:
+
+lint:
+	lint -DLINT $(INCLUDES) $(SRC)>fluff
+
+depend:
+	@if [ -z "$(THIS)" ]; then \
+	    $(MAKE) -f $(TOP)/Makefile reflect THIS=$@; \
+	else \
+	    $(MAKEDEPEND) -- $(CFLAG) $(INCLUDES) $(DEPFLAG) -- $(PROGS) $(SRC); \
+	fi
+
+dclean:
+	$(PERL) -pe 'if (/^# DO NOT DELETE THIS LINE/) {print; exit(0);}' $(MAKEFILE) >Makefile.new
+	mv -f Makefile.new $(MAKEFILE)
+
+clean:
+	rm -f *.o *.obj lib tags core .pure .nfs* *.old *.bak fluff $(EXE)
+	rm -f fips_algvs.app/fips_algvs
+
+# DO NOT DELETE THIS LINE -- make depend depends on it.
+

iOS/fips_algvs.app/Entitlements.plist

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>get-task-allow</key>
+    <true/>
+</dict>
+</plist>

iOS/fips_algvs.app/Info.plist

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>CFBundleName</key>
+	<string>fips_algvs</string>
+	<key>CFBundleSupportedPlatforms</key>
+	<array>
+	    <string>iPhoneOS</string>
+	</array>
+	<key>CFBundleExecutable</key>
+	<string>fips_algvs</string>
+	<key>CFBundleIdentifier</key>
+	<string>fips_algvs</string>
+	<key>CFBundleResourceSpecification</key>
+	<string>ResourceRules.plist</string>
+	<key>LSRequiresIPhoneOS</key>
+	<true/>
+	<key>CFBundleDisplayName</key>
+	<string>fips_algvs</string>
+	<key>CFBundleVersion</key>
+	<string>1.0</string>
+</dict>
+</plist>

iOS/fips_algvs.app/ResourceRules.plist

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>rules</key>
+	<dict>
+		<key>.*</key>
+		<true/>
+		<key>Info.plist</key>
+		<dict>
+			<key>omit</key>
+			<true/>
+			<key>weight</key>
+			<real>10</real>
+		</dict>
+		<key>ResourceRules.plist</key>
+		<dict>
+			<key>omit</key>
+			<true/>
+			<key>weight</key>
+			<real>100</real>
+		</dict>
+	</dict>
+</dict>
+</plist>

iOS/fopen.m

@@ -0,0 +1,93 @@
+#include <stdio.h>
+#include <dlfcn.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <Foundation/Foundation.h>
+ 
+static FILE *(*libc_fopen)(const char *, const char *) = NULL;
+
+__attribute__((constructor))
+static void pre_main(void)
+{
+    /*
+     * Pull reference to fopen(3) from libc.
+     */
+    void *handle = dlopen("libSystem.B.dylib",RTLD_LAZY);
+
+    if (handle) {
+        libc_fopen = dlsym(handle,"fopen");
+        dlclose(handle);
+    }
+
+    /*
+     * Change to Documents directory.
+     */
+    NSString *docs = [NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES) lastObject];
+
+    NSFileManager *filemgr = [NSFileManager defaultManager];
+    [filemgr changeCurrentDirectoryPath: docs];
+    [filemgr release];
+}
+
+char *mkdirhier(char *path)
+{
+    char *slash;
+    struct stat buf;
+
+    if (path[0]=='.' && path[1]=='/') path+=2;
+
+    if ((slash = strrchr(path,'/'))) {
+	*slash = '\0';
+	if (stat(path,&buf)==0) {
+	    *slash = '/';
+	    return NULL;
+	}
+	(void)mkdirhier(path);
+	mkdir (path,0777);
+	*slash = '/';
+    }
+
+    return slash;
+}
+/*
+ * Replacement fopen(3)
+ */
+FILE *fopen(const char *filename, const char *mode)
+{
+    FILE *ret;
+
+    if ((ret = (*libc_fopen)(filename,mode)) == NULL) {
+        /*
+         * If file is not present in Documents directory, try from Bundle.
+         */
+        NSString *nsspath = [NSString stringWithFormat:@"%@/%s",
+                                   [[NSBundle mainBundle] bundlePath],
+                                   filename];
+
+        if ((ret = (*libc_fopen)([nsspath cStringUsingEncoding:NSUTF8StringEncoding],mode)) == NULL &&
+	    mode[0]=='w' &&
+	    ((filename[0]!='.' && filename[0]!='/') ||
+	     (filename[0]=='.' && filename[1]=='/')) ) {
+	    /*
+	     * If not present in Bundle, create directory in Documents
+	     */
+	    char *path = strdup(filename), *slash;
+	    static int once = 1;
+
+	    if ((slash = mkdirhier(path)) && once) {
+		/*
+		 * For some reason iOS truncates first created file
+		 * upon program exit, so we create one preemptively...
+		 */
+		once = 0;
+		strcpy(slash,"/.0");
+		creat(path,0444);
+	    }
+	    free(path);
+	    ret = (*libc_fopen)(filename,mode);
+	}
+    }
+
+    return ret;
+}

ms/do_fips.bat

@@ -1,7 +1,10 @@
-@echo off
+rem @echo off
 
 SET ASM=%1
 SET EXARG=
+SET MFILE=ntdll.mak
+
+if NOT X%OSVERSION% == X goto wince
 
 if NOT X%PROCESSOR_ARCHITECTURE% == X goto defined 
 
@@ -42,6 +45,14 @@ SET TARGET=VC-WIN64A
 if x%ASM% == xno-asm goto compile
 SET ASM=nasm
 
+goto compile
+
+:wince
+
+echo Auto Configuring for WinCE
+SET TARGET=VC-CE
+SET MFILE=cedll.mak
+
 :compile
 
 if x%ASM% == xno-asm SET EXARG=no-asm
@@ -52,13 +63,13 @@ echo on
 
 perl util\mkfiles.pl >MINFO
 @if ERRORLEVEL 1 goto error
-perl util\mk1mf.pl dll %ASM% %TARGET% >ms\ntdll.mak
+perl util\mk1mf.pl dll %ASM% %TARGET% >ms\%MFILE%
 @if ERRORLEVEL 1 goto error
 
-nmake -f ms\ntdll.mak clean
-nmake -f ms\ntdll.mak
+nmake -f ms\%MFILE% clean
+nmake -f ms\%MFILE%
 @if ERRORLEVEL 1 goto error
-nmake -f ms\ntdll.mak install
+nmake -f ms\%MFILE% install
 @if ERRORLEVEL 1 goto error
 
 @echo.

test/Makefile

@@ -12,6 +12,7 @@ PERL=		perl
 # KRB5 stuff
 KRB5_INCLUDES=
 LIBKRB5=
+TEST=		fips_algvs.c
 
 PEX_LIBS=
 EX_LIBS= #-lnsl -lsocket

test/fips_algvs.c

@@ -70,6 +70,67 @@ int main(int argc, char **argv)
 }
 #else
 
+#if defined(__vxworks)
+
+#include <taskLibCommon.h>
+#include <string.h>
+
+int fips_algvs_main(int argc, char **argv);
+#define main fips_algvs_main
+
+static int fips_algvs_argv(char *a0)
+{
+	char *argv[32] = { "fips_algvs" };
+	int argc = 1;
+	int main_ret;
+
+	if (a0) {
+		char *scan = a0, *arg = a0;
+
+		while (*scan) {
+			if (*scan++ == ' ') {
+				scan[-1] = '\0';
+				argv[argc++] = arg;
+				if (argc == (sizeof(argv)/sizeof(argv[0])-1))
+					break;
+
+				while (*scan == ' ') scan++;
+				arg = scan;
+			}
+		}
+		if (*scan == '\0') argv[argc++] = arg;
+	}
+
+	argv[argc] = NULL;
+
+	main_ret = fips_algvs_main(argc, argv);
+
+	if (a0) free(a0);
+
+	return main_ret;
+}
+
+int fips_algvs(int a0)
+{
+	return taskSpawn("fips_algvs", 100, (VX_FP_TASK | VX_SPE_TASK), 100000,
+			(FUNCPTR)fips_algvs_argv,
+			a0 ? strdup(a0) : 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+}
+
+static FILE *fips_fopen(const char *path, const char *mode)
+{
+	char fips_path [256];
+
+	if (path[0] != '/' && strlen(path) < (sizeof(fips_path)-8)) {
+		strcpy(fips_path,"/fips0/");
+		strcat(fips_path,path);
+		return fopen(fips_path,mode);
+	}
+	return fopen(path,mode);
+}
+#define fopen fips_fopen
+#endif
+
 #define FIPS_ALGVS
 
 extern int fips_aesavs_main(int argc, char **argv);
@@ -89,6 +150,7 @@ extern int fips_rsavtest_main(int argc, char **argv);
 extern int fips_shatest_main(int argc, char **argv);
 extern int fips_test_suite_main(int argc, char **argv);
 
+#if !defined(_TMS320C6400_PLUS)
 #include "fips_aesavs.c"
 #include "fips_cmactest.c"
 #include "fips_desmovs.c"
@@ -106,6 +168,28 @@ extern int fips_test_suite_main(int argc, char **argv);
 #include "fips_shatest.c"
 #include "fips_test_suite.c"
 
+#else
+#include "aes/fips_aesavs.c"
+#include "cmac/fips_cmactest.c"
+#include "des/fips_desmovs.c"
+#include "dh/fips_dhvs.c"
+#include "rand/fips_drbgvs.c"
+#include "dsa/fips_dssvs.c"
+#include "ecdh/fips_ecdhvs.c"
+#include "ecdsa/fips_ecdsavs.c"
+#include "aes/fips_gcmtest.c"
+#include "hmac/fips_hmactest.c"
+#include "rand/fips_rngvs.c"
+#include "rsa/fips_rsagtest.c"
+#include "rsa/fips_rsastest.c"
+#include "rsa/fips_rsavtest.c"
+#include "sha/fips_shatest.c"
+#include "fips_test_suite.c"
+
+#pragma DATA_SECTION(aucCmBootDspLoad, "BootDspSection");
+volatile unsigned char aucCmBootDspLoad[8*1024];
+#endif
+
 typedef struct
 	{
 	const char *name;
@@ -221,7 +305,7 @@ static int run_prg(int argc, char **argv)
 
 int main(int argc, char **argv)
 	{
-	char buf[1024];
+	static char buf[1024];
 	char **args = argv + 1;
 	const char *sname = "fipstests.sh";
 	ARGS arg;
@@ -238,6 +322,20 @@ int main(int argc, char **argv)
 	CRYPTO_mem_ctrl(CRYPTO_MEM_CHECK_ON);
 #endif
 
+#if defined(_TMS320C6400_PLUS)
+	SysInit();
+#endif
+
+#if (defined(__arm__) || defined(__aarch64__))
+	if (*args && !strcmp(*args, "-noaccel"))
+		{
+		extern unsigned int OPENSSL_armcap_P;
+
+		OPENSSL_armcap_P=0;
+		args++;
+		argc--;
+		}
+#endif
 	if (*args && *args[0] != '-')
 		{
 		rv = run_prg(argc - 1, args);

util/fips_standalone_sha1

@@ -0,0 +1,32 @@
+#!/usr/bin/env perl
+#
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+
+unshift(@INC,$dir);
+require "hmac_sha1.pl";
+
+(!@ARV[0] && -f @ARGV[$#ARGV]) || die "usage: $0 [-verify] file";
+
+$verify=shift	if (@ARGV[0] eq "-verify");
+
+sysopen(FD,@ARGV[0],0) || die "$!";
+binmode(FD);
+
+my $ctx = HMAC->Init("etaonrishdlcupfm");
+
+while (read(FD,$blob,4*1024)) { $ctx->Update($blob); }
+
+close(FD);
+
+my $signature = unpack("H*",$ctx->Final());
+
+print "HMAC-SHA1(@ARGV[0])= $signature\n";
+
+if ($verify) {
+	open(FD,"<@ARGV[0].sha1") || die "$!";
+	$line = <FD>;
+	close(FD);
+	exit(0)	if ($line =~ /HMAC\-SHA1\([^\)]*\)=\s*([0-9a-f]+)/i &&
+				$1 eq $signature);
+	die "signature mismatch";
+}

util/fipsas.pl

@@ -8,9 +8,6 @@ my @ARGS = @ARGV;
 
 my $top = shift @ARGS;
 my $target = shift @ARGS;
-my $tmptarg = $target;
-
-$tmptarg =~ s/\.[^\\\/\.]+$/.tmp/;
 
 my $runasm = 1;
 
@@ -40,43 +37,31 @@ while (<IN>)
 	last if (/assembler/)
 	}
 
-# Store all renames.
+# Store all renames [noting minimal length].
+my $minlen=0x10000;
 while (<IN>)
 	{
-	if (/^#define\s+(\w+)\s+(\w+)\b/)
+	if (/^#define\s+_?(\w+)\s+_?(\w+)\b/)
 		{
 		$edits{$1} = $2;
+		my $len = length($1);
+		$minlen = $len if ($len<$minlen);
 		}
 	}
 
-my ($from, $to);
+open(IN,"$target") || die "Can't open $target for reading";
 
-#delete any temp file lying around
+@code = <IN>;	# suck in whole file
 
-unlink $tmptarg;
+close IN;
 
-#rename target temporarily
-my $rencnt = 0;
-# On windows the previous file doesn't always close straight away
-# so retry the rename operation a few times if it fails.
-while (!rename($target, $tmptarg))
-        {
-        sleep 2;
-        die "Can't rename $target" if ($rencnt++ > 10);
-        }
+open(OUT,">$target") || die "Can't open $target for writing";
 
-#edit target
-open(IN,$tmptarg) || die "Can't open temporary file";
-open(OUT, ">$target") || die "Can't open output file $target";
-
-while (<IN>)
-{
-	while (($from, $to) = each %edits)
-		{
-		s/(\b_*)$from(\b)/$1$to$2/g;
-		}
-	print OUT $_;
-}
+foreach $line (@code)
+	{
+	$line =~ s/\b(_?)(\w{$minlen,})\b/$1.($edits{$2} or $2)/geo;
+	print OUT $line;
+	}
 
 close OUT;
 
@@ -87,14 +72,5 @@ if ($runasm)
 
 	my $rv = $?;
 
-	# restore target
-	unlink $target;
-	rename $tmptarg, $target;
-
 	die "Error executing assembler!" if $rv != 0;
 	}
-else
-	{
-	# Don't care about target
-	unlink $tmptarg;
-	}

util/fipsdist.pl

@@ -58,7 +58,7 @@ while (<STDIN>)
 		}
 	else
 		{
-		next unless (/^(fips\/|crypto|util|test|include|ms)/);
+		next unless (/^(fips\/|crypto|util|test|include|ms|c6x)/);
 		}
 	if (/^crypto\/([^\/]+)/)
 		{

util/fipslink.pl

@@ -33,14 +33,24 @@ check_hash($sha1_exe, "fipscanister.lib");
 
 print "Integrity check OK\n";
 
-print "$fips_cc $fips_cc_args $fips_libdir/fips_premain.c\n";
-system "$fips_cc $fips_cc_args $fips_libdir/fips_premain.c";
-die "First stage Compile failure" if $? != 0;
+if (is_premain_linked(@ARGV)) {
+	print "$fips_cc $fips_cc_args $fips_libdir/fips_premain.c\n";
+	system "$fips_cc $fips_cc_args $fips_libdir/fips_premain.c";
+	die "First stage Compile failure" if $? != 0;
+} elsif (!defined($ENV{FIPS_SIG})) {
+	die "no fips_premain.obj linked";
+}
 
 print "$fips_link @ARGV\n";
 system "$fips_link @ARGV";
 die "First stage Link failure" if $? != 0;
 
+if (defined($ENV{FIPS_SIG})) {
+	print "$ENV{FIPS_SIG} $fips_target\n";
+	system "$ENV{FIPS_SIG} $fips_target";
+	die "$ENV{FIPS_SIG} $fips_target failed" if $? != 0;
+	exit;
+}
 
 print "$fips_premain_dso $fips_target\n";
 system("$fips_premain_dso $fips_target >$fips_target.sha1");
@@ -61,6 +71,22 @@ print "$fips_link @ARGV\n";
 system "$fips_link @ARGV";
 die "Second stage Link failure" if $? != 0;
 
+sub is_premain_linked
+	{
+	return 1 if (grep /fips_premain\.obj/,@_);
+	foreach (@_)
+		{
+		if (/^@(.*)/ && -f $1)
+			{
+			open FD,$1 or die "can't open $1";
+			my $ret = (grep /fips_premain\.obj/,<FD>)?1:0;
+			close FD;
+			return $ret;
+			}
+		}
+	return 0;
+	}
+
 sub check_hash
 	{
 	my ($sha1_exe, $filename) = @_;

util/hmac_sha1.pl

@@ -0,0 +1,196 @@
+#!/usr/bin/env perl
+#
+# Copyright (c) 2011 The OpenSSL Project.
+#
+######################################################################
+#
+# SHA1 and HMAC in Perl by <appro@openssl.org>.
+#
+{ package SHA1;
+  use integer;
+
+    {
+    ################################### SHA1 block code generator
+    my @V = ('$A','$B','$C','$D','$E');
+    my $i;
+
+    sub XUpdate {
+      my $ret;
+	$ret="(\$T=\$W[($i-16)%16]^\$W[($i-14)%16]^\$W[($i-8)%16]^\$W[($i-3)%16],\n\t";
+	if ((1<<31)<<1) {
+	    $ret.="    \$W[$i%16]=((\$T<<1)|(\$T>>31))&0xffffffff)\n\t  ";
+	} else {
+	    $ret.="    \$W[$i%16]=(\$T<<1)|((\$T>>31)&1))\n\t  ";
+	}
+    }
+    sub tail {
+      my ($a,$b,$c,$d,$e)=@V;
+      my $ret;
+	if ((1<<31)<<1) {
+	    $ret.="(($a<<5)|($a>>27));\n\t";
+	    $ret.="$b=($b<<30)|($b>>2);	$e&=0xffffffff;	#$b&=0xffffffff;\n\t";
+	} else {
+	    $ret.="(($a<<5)|($a>>27)&0x1f);\n\t";
+	    $ret.="$b=($b<<30)|($b>>2)&0x3fffffff;\n\t";
+	}
+      $ret;
+    }
+    sub BODY_00_15 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=\$W[$i]+0x5a827999+((($c^$d)&$b)^$d)+".tail();
+    }
+    sub BODY_16_19 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x5a827999+((($c^$d)&$b)^$d)+".tail();
+    }
+    sub BODY_20_39 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x6ed9eba1+($b^$c^$d)+".tail();
+    }
+    sub BODY_40_59 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0x8f1bbcdc+(($b&$c)|(($b|$c)&$d))+".tail();
+    }
+    sub BODY_60_79 {
+	my ($a,$b,$c,$d,$e)=@V;
+	"$e+=".XUpdate()."+0xca62c1d6+($b^$c^$d)+".tail();
+    }
+
+    my $sha1_impl =
+    'sub block {
+	my $self = @_[0];
+	my @W    = unpack("N16",@_[1]);
+	my ($A,$B,$C,$D,$E,$T) = @{$self->{H}};
+	';
+
+	$sha1_impl.='
+	$A &= 0xffffffff;
+	$B &= 0xffffffff;
+	' if ((1<<31)<<1);
+
+	for($i=0;$i<16;$i++){ $sha1_impl.=BODY_00_15(); unshift(@V,pop(@V)); }
+	for(;$i<20;$i++)    { $sha1_impl.=BODY_16_19(); unshift(@V,pop(@V)); }
+	for(;$i<40;$i++)    { $sha1_impl.=BODY_20_39(); unshift(@V,pop(@V)); }
+	for(;$i<60;$i++)    { $sha1_impl.=BODY_40_59(); unshift(@V,pop(@V)); }
+	for(;$i<80;$i++)    { $sha1_impl.=BODY_60_79(); unshift(@V,pop(@V)); }
+
+	$sha1_impl.='
+	$self->{H}[0]+=$A;	$self->{H}[1]+=$B;	$self->{H}[2]+=$C;
+	$self->{H}[3]+=$D;	$self->{H}[4]+=$E;	}';
+
+    #print $sha1_impl,"\n";
+    eval($sha1_impl);		# generate code
+    }
+
+    sub Init {
+	my $class = shift;	# multiple instances...
+	my $self  = {};
+
+	bless $self,$class;
+	$self->{H} = [0x67452301,0xefcdab89,0x98badcfe,0x10325476,0xc3d2e1f0];
+	$self->{N} = 0;
+	return $self;
+    }
+
+    sub Update {
+	my $self = shift;
+	my $msg;
+
+	foreach $msg (@_) {
+	    my $len  = length($msg);
+	    my $num  = length($self->{buf});
+	    my $off  = 0;
+
+	    $self->{N} += $len;
+
+	    if (($num+$len)<64)
+	    {	$self->{buf} .= $msg; next;	}
+	    elsif ($num)
+	    {	$self->{buf} .= substr($msg,0,($off=64-$num));
+		$self->block($self->{buf});
+	    }
+
+	    while(($off+64) <= $len)
+	    {	$self->block(substr($msg,$off,64));
+		$off += 64;
+	    }
+
+	    $self->{buf} = substr($msg,$off);
+	}
+	return $self;
+    }
+
+    sub Final {
+	my $self = shift;
+	my $num  = length($self->{buf});
+
+	$self->{buf} .= chr(0x80); $num++;
+	if ($num>56)
+	{   $self->{buf} .= chr(0)x(64-$num);
+	    $self->block($self->{buf});
+	    $self->{buf}=undef;
+	    $num=0;
+	}
+	$self->{buf} .= chr(0)x(56-$num);
+	$self->{buf} .= pack("N2",($self->{N}>>29)&0x7,$self->{N}<<3);
+	$self->block($self->{buf});
+
+	return pack("N*",@{$self->{H}});
+    }
+
+    sub Selftest {
+	my $hash;
+
+	$hash=SHA1->Init()->Update('abc')->Final();
+	die "SHA1 test#1" if (unpack("H*",$hash) ne 'a9993e364706816aba3e25717850c26c9cd0d89d');
+
+	$hash=SHA1->Init()->Update('abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq')->Final();
+	die "SHA1 test#2" if (unpack("H*",$hash) ne '84983e441c3bd26ebaae4aa1f95129e5e54670f1');
+
+	#$hash=SHA1->Init()->Update('a'x1000000)->Final();
+	#die "SHA1 test#3" if (unpack("H*",$hash) ne '34aa973cd4c4daa4f61eeb2bdbad27316534016f');
+    }
+}
+
+{ package HMAC;
+
+    sub Init {
+	my $class = shift;
+	my $key   = shift;
+	my $self  = {};
+
+	bless $self,$class;
+
+	if (length($key)>64) {
+	    $key = SHA1->Init()->Update($key)->Final();
+	}
+	$key .= chr(0x00)x(64-length($key));
+
+	my @ikey = map($_^=0x36,unpack("C*",$key));
+	($self->{hash} = SHA1->Init())->Update(pack("C*",@ikey));
+	 $self->{okey} = pack("C*",map($_^=0x36^0x5c,@ikey));
+
+	return $self;
+    }
+
+    sub Update {
+	my $self = shift;
+	$self->{hash}->Update(@_);
+	return $self;
+    }
+
+    sub Final {
+	my $self  = shift;
+	my $ihash = $self->{hash}->Final();
+	return SHA1->Init()->Update($self->{okey},$ihash)->Final();
+    }
+
+    sub Selftest {
+	my $hmac;
+
+	$hmac = HMAC->Init('0123456789:;<=>?@ABC')->Update('Sample #2')->Final();
+	die "HMAC test" if (unpack("H*",$hmac) ne '0922d3405faa3d194f82a45830737d5cc6c75d24');
+    }
+}
+
+1;

util/incore

@@ -382,7 +382,7 @@ if (!$legacy_mode) {
     }
 
     $FINGERPRINT_ascii_value
-			= $exe->Lookup("FINGERPRINT_ascii_value")	or die;
+			= $exe->Lookup("FINGERPRINT_ascii_value");
 
 }
 if ($FIPS_text_startX && $FIPS_text_endX) {
@@ -439,9 +439,12 @@ $fingerprint = FIPS_incore_fingerprint();
 
 if ($legacy_mode) {
     print unpack("H*",$fingerprint);
-} else {
+} elsif (defined($FINGERPRINT_ascii_value)) {
     seek(FD,$FINGERPRINT_ascii_value->{st_offset},0)	or die "$!";
     print FD unpack("H*",$fingerprint)			or die "$!";
+} else {
+    seek(FD,$FIPS_signature->{st_offset},0)		or die "$!";
+    print FD $fingerprint				or die "$!";
 }
 
 close (FD);

util/mk1mf.pl

@@ -23,6 +23,7 @@ local $fips_canister_path = "";
 my $fips_premain_dso_exe_path = "";
 my $fips_premain_c_path = "";
 my $fips_sha1_exe_path = "";
+my $fips_sha1_exe_build = 1;
 
 local $fipscanisterbuild = 0;
 
@@ -248,6 +249,10 @@ elsif (($platform eq "netware-clib") || ($platform eq "netware-libc") ||
 	$BSDSOCK=1 if ($platform eq "netware-libc-bsdsock") || ($platform eq "netware-clib-bsdsock");
 	require 'netware.pl';
 	}
+elsif ($platform eq "c64xplus")
+	{
+	require "TI_CGTOOLS.pl";
+	}
 else
 	{
 	require "unix.pl";
@@ -500,8 +505,16 @@ if ($fips)
 	{
 	if ($fips_sha1_exe_path eq "")
 		{
-		$fips_sha1_exe_path =
-			"\$(BIN_D)${o}fips_standalone_sha1$exep";
+		$fips_sha1_exe_path = $ENV{"FIPS_SHA1_PATH"};
+		if (defined $fips_sha1_exe_path)
+			{
+			$fips_sha1_exe_build = 0;
+			}
+		else
+			{
+			$fips_sha1_exe_path =
+				"\$(BIN_D)${o}fips_standalone_sha1$exep";
+			}
 		}
 	}
 	else
@@ -545,7 +558,7 @@ if ($fips)
 
 if ($fipscanisteronly)
 	{
-	$build_targets = "\$(O_FIPSCANISTER) \$(T_EXE)";
+	$build_targets = "\$(O_FIPSCANISTER)";
 	$libs_dep = "";
 	}
 
@@ -567,9 +580,14 @@ if ($fipscanisteronly)
 	\$(CP) \"fips${o}fips_premain.c.sha1\" \"\$(INSTALLTOP)${o}lib\"
 	\$(CP) \"\$(INCO_D)${o}fips.h\" \"\$(INSTALLTOP)${o}include${o}openssl\"
 	\$(CP) \"\$(INCO_D)${o}fips_rand.h\" \"\$(INSTALLTOP)${o}include${o}openssl\"
-	\$(CP) "\$(BIN_D)${o}fips_standalone_sha1$exep" \"\$(INSTALLTOP)${o}bin\"
 	\$(CP) \"util${o}fipslink.pl\" \"\$(INSTALLTOP)${o}bin\"
 EOF
+	if ($fips_sha1_exe_build)
+		{
+		$extra_install .= <<"EOF";
+	\$(CP) "\$(BIN_D)${o}fips_standalone_sha1$exep" \"\$(INSTALLTOP)${o}bin\"
+EOF
+		}
 	}
 elsif ($shlib)
 	{
@@ -716,7 +734,7 @@ LIBS_DEP=$libs_dep
 EOF
 
 $rules=<<"EOF";
-all: banner \$(TMP_D) \$(BIN_D) \$(TEST_D) \$(LIB_D) \$(INCO_D) headers \$(FIPS_SHA1_EXE) $build_targets
+all: banner \$(TMP_D) \$(BIN_D) \$(TEST_D) \$(LIB_D) \$(INCO_D) headers $build_targets
 
 banner:
 $banner
@@ -744,7 +762,11 @@ headers: \$(HEADER) \$(EXHEADER)
 
 lib: \$(LIBS_DEP) \$(E_SHLIB)
 
-exe: \$(T_EXE) \$(BIN_D)$o\$(E_EXE)$exep
+exe: \$(BIN_D)$o\$(E_EXE)$exep
+
+build_tests: \$(T_EXE)
+
+build_algvs: \$(T_SRC) \$(BIN_D)${o}fips_algvs$exep
 
 install: all
 	\$(MKDIR) \"\$(INSTALLTOP)\"
@@ -842,10 +864,13 @@ if ($fips)
 		}
 	$rules.=&cc_compile_target("\$(OBJ_D)${o}fips_standalone_sha1$obj",
 		"fips${o}sha${o}fips_standalone_sha1.c",
-		"\$(SHLIB_CFLAGS)");
+		"\$(APP_CFLAGS)");
 	$rules.=&cc_compile_target("\$(OBJ_D)${o}\$(E_PREMAIN_DSO)$obj",
 		"fips${o}fips_premain.c",
-		"-DFINGERPRINT_PREMAIN_DSO_LOAD \$(SHLIB_CFLAGS)");
+		"-DFINGERPRINT_PREMAIN_DSO_LOAD \$(APP_CFLAGS)");
+	$rules.=&cc_compile_target("\$(OBJ_D)${o}fips_algvs$obj",
+		"test${o}fips_algvs.c",
+		"\$(APP_CFLAGS)");
 	}
 
 foreach (values %lib_nam)
@@ -878,6 +903,7 @@ EOF
 }
 
 $defs.=&do_defs("T_EXE",$test,"\$(TEST_D)",$exep);
+$defs.=&do_defs("T_SRC",$test,"\$(TMP_D)",".c");
 foreach (split(/\s+/,$test))
 	{
 	my $t_libs;
@@ -899,8 +925,11 @@ foreach (split(/\s+/,$test))
 
 	$tt="\$(OBJ_D)${o}$t${obj}";
 	$rules.=&do_link_rule("\$(TEST_D)$o$t$exep",$tt,"\$(LIBS_DEP)","$t_libs \$(EX_LIBS)", $ltype);
+	$rules.=&do_copy_rule("\$(TMP_D)",$_,".c");
 	}
 
+	$rules.=&do_link_rule("\$(TEST_D)${o}fips_algvs$exep","\$(OBJ_D)${o}fips_algvs$obj","\$(LIBS_DEP)","\$(O_FIPSCANISTER) \$(EX_LIBS)", 2) if $fips;
+
 $defs.=&do_defs("E_SHLIB",$engines . $otherlibs,"\$(ENG_D)",$shlibp);
 
 foreach (split(/\s+/,$engines))
@@ -955,20 +984,20 @@ if ($fips)
 					"\$(OBJ_D)${o}fips_start$obj",
 					"\$(FIPSOBJ)",
 					"\$(OBJ_D)${o}fips_end$obj",
-					"\$(FIPS_SHA1_EXE)", "");
+					"");
 		# FIXME
 		$rules.=&do_link_rule("\$(FIPS_SHA1_EXE)",
 					"\$(OBJ_D)${o}fips_standalone_sha1$obj \$(OBJ_D)${o}sha1dgst$obj $sha1_asm_obj",
-					"","\$(EX_LIBS)", 1);
+					"","\$(EX_LIBS)", 1) if $fips_sha1_exe_build;
 		}
 	else
 		{
 		$rules.=&do_link_rule("\$(FIPS_SHA1_EXE)",
 					"\$(OBJ_D)${o}fips_standalone_sha1$obj \$(O_FIPSCANISTER)",
-					"","", 1);
+					"","", 1) if $fips_sha1_exe_build;
 
 		}
-	$rules.=&do_link_rule("\$(PREMAIN_DSO_EXE)","\$(OBJ_D)${o}\$(E_PREMAIN_DSO)$obj \$(CRYPTOOBJ) \$(O_FIPSCANISTER)","","\$(EX_LIBS)", 1);
+	$rules.=&do_link_rule("\$(PREMAIN_DSO_EXE)","\$(OBJ_D)${o}\$(E_PREMAIN_DSO)$obj \$(CRYPTOOBJ) \$(O_FIPSCANISTER)","","\$(EX_LIBS)", 1) unless defined $ENV{"FIPS_SIG"};
 	
 	}
 
@@ -1192,6 +1221,10 @@ sub do_compile_rule
 			{
 			$ret.=&Sasm_compile_target("$to${o}$n$obj",$s,$n);
 			}
+		elsif (-f ($s="${d}${o}asm${o}${n}.asm"))
+			{
+			$ret.=&cc_compile_target("$to${o}$n$obj","$s",$ex);
+			}
 		else	{ die "no rule for $_"; }
 		}
 	return($ret);

util/msincore

@@ -0,0 +1,169 @@
+#!/usr/bin/env perl
+#
+# Copyright (c) 2012 The OpenSSL Project.
+#
+# The script embeds fingerprint into Microsoft PE-COFF executable object.
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+
+unshift(@INC,$dir);
+require "hmac_sha1.pl";
+
+######################################################################
+#
+# PE-COFF segment table parser by <appro@openssl.org>.
+#
+{ package PECOFF;
+  use FileHandle;
+
+    sub dup  { my %copy=map {$_} @_; return \%copy; }
+
+    sub Load {
+	my $class = shift;
+	my $self  = {};
+	my $FD    = FileHandle->new();	# autoclose
+	my $file  = shift;
+
+	bless $self,$class;
+
+	sysopen($FD,$file,0)		or die "$!";
+	binmode($FD);
+
+	#################################################
+	# read IMAGE_DOS_HEADER
+	#
+	read($FD,my $mz,64) or die "$!";
+	my @dos_header=unpack("a2C58V",$mz);
+
+	$!=42;		# signal fipsld to revert to two-step link
+	die "$file is not PE-COFF image" if (@dos_header[0] ne "MZ");
+
+	my $e_lfanew=pop(@dos_header);
+	seek($FD,$e_lfanew,0)		or die "$!";
+	read($FD,my $magic,4)		or die "$!";
+
+	$!=42;		# signal fipsld to revert to two-step link
+	die "$file is not PE-COFF image" if (unpack("V",$magic)!=0x4550);
+
+	#################################################
+	# read and parse COFF header...
+	#
+	read($FD,my $coff,20) or die "$!";
+
+	my %coff_header;
+	@coff_header{machine,nsects,date,syms_off,nsyms,opt,flags}=
+		unpack("v2V3v2",$coff);
+
+	my $strings;
+	my $symsize;
+
+	#################################################
+	# load strings table
+	#
+	if ($coff_header{syms_off}) {
+	    seek($FD,$coff_header{syms_off}+18*$coff_header{nsyms},0) or die "$!";
+	    read($FD,$strings,4) or die "$!";
+	    $symsize = unpack("V",$strings);
+	    read($FD,$strings,$symsize,4) or die "$!";
+	}
+
+	#################################################
+	# read sections
+	#
+	my $i;
+
+	# seek to section headers
+	seek($FD,$e_lfanew+24+@coff_header{opt},0) or die "$!";
+
+	for ($i=0;$i<$coff_header{nsects};$i++) {
+	    my %coff_shdr;
+	    my $name;
+
+	    read($FD,my $section,40) or die "$!";
+
+	    @coff_shdr{sh_name,sh_vsize,sh_vaddr,
+	    		sh_rawsize,sh_offset,sh_relocs,sh_lines,
+			sh_nrelocls,sh_nlines,sh_flags} =
+		unpack("a8V6v2V",$section);
+
+	    $name = $coff_shdr{sh_name};
+	    # see if sh_name is an offset in $strings
+	    my ($hi,$lo) = unpack("V2",$name);
+	    if ($hi==0 && $lo<$symsize) {
+		$name = substr($strings,$lo,64);
+	    }
+	    $name = (split(chr(0),$name))[0];
+	    $coff_shdr{sh_name} = $name;
+
+	    $self->{sections}{$name} = dup(%coff_shdr);
+	}
+
+	return $self;
+    }
+
+    sub Lookup {
+	my $self = shift;
+	my $name = shift;
+	return $self->{sections}{$name};
+    }
+}
+
+######################################################################
+#
+# main()
+#
+my $legacy_mode;
+
+if ($#ARGV<0 || ($#ARGV>0 && !($legacy_mode=(@ARGV[0] =~ /^\-(dso|exe)$/)))) {
+	print STDERR "usage: $0 [-dso|-exe] pe-coff-binary\n";
+	exit(1);
+}
+
+$exe = PECOFF->Load(@ARGV[$#ARGV]);
+
+sysopen(FD,@ARGV[$#ARGV],$legacy_mode?0:2) or die "$!";	# 2 is read/write
+binmode(FD);
+
+sub FIPS_incore_fingerprint {
+  my $ctx = HMAC->Init("etaonrishdlcupfm");
+  my ($beg,$end);
+  my $sect;
+
+    $sect = $exe->Lookup("fipstx")	or die "no fipstx section";
+
+    seek(FD,$sect->{sh_offset},0)	or die "$!";
+    read(FD,$blob,$sect->{sh_vsize})	or die "$!";
+
+    ($beg = index($blob,"SPIFxet_ts_tXtra")) >= 0
+					or die "no FIPS_text_startX";
+    ($end = rindex($blob,"SPIFxet_ne_t][Xd")) >= 0
+					or die "no FIPS_text_endX";
+
+    $ctx->Update(substr($blob,$beg,$end-$beg));
+
+    $sect = $exe->Lookup("fipsro")	or die "no fipsro section";
+
+    seek(FD,$sect->{sh_offset},0)	or die "$!";
+    read(FD,$blob,$sect->{sh_vsize})	or die "$!";
+
+    ($beg = index($blob,"SPIFdor__atarats",40)) >= 0
+					or die "no FIPS_rodata_start";
+    ($end = rindex($blob,"SPIFdor__ata[dne")) >= 0
+					or die "no FIPS_rodata_end";
+
+    $ctx->Update(substr($blob,$beg,$end-$beg));
+
+    return $ctx->Final();
+}
+
+$fingerprint = FIPS_incore_fingerprint();
+
+if ($legacy_mode) {
+    print unpack("H*",$fingerprint);
+} else {
+    my $sect = $exe->Lookup("fipsro");
+    seek(FD,$sect->{sh_offset},0)		or die "$!";
+    print FD unpack("H*",$fingerprint)		or die "$!";
+}
+
+close (FD);

util/pl/TI_CGTOOLS.pl

@@ -0,0 +1,274 @@
+#!/usr/local/bin/perl
+#
+# TI_CGTOOLS.pl, Texas Instruments CGTOOLS under Unix or MSYS.
+#
+
+$ssl=	"ssl";
+$crypto="crypto";
+
+if ($fips && !$shlib)
+	{
+	$crypto="fips";
+	$crypto_compat = "cryptocompat.lib";
+	}
+else
+	{
+	$crypto="crypto";
+	}
+
+if ($fipscanisterbuild)
+	{
+	$fips_canister_path = "\$(LIB_D)/fipscanister.obj";
+	}
+
+$o='/';
+$cp='cp';
+$cp2='$(PERL) util/copy.pl -stripcr';
+$mkdir='$(PERL) util/mkdir-p.pl';
+$rm='rm -f';
+
+$zlib_lib="zlib1.lib";
+
+# Santize -L options for ms link
+$l_flags =~ s/-L("\[^"]+")/\/libpath:$1/g;
+$l_flags =~ s/-L(\S+)/\/libpath:$1/g;
+
+# C compiler stuff
+$cc='cl6x';
+$base_cflags= " $mf_cflag";
+my $f;
+$opt_cflags='';
+$dbg_cflags=$f.' -g -DDEBUG -D_DEBUG';
+$lflags='';
+
+*::cc_compile_target = sub {
+	my ($target,$source,$ex_flags)=@_;
+	my $ret;
+
+	$ex_flags.=" -DMK1MF_BUILD" if ($source =~/cversion/);
+	$ret ="$target: \$(SRC_D)$o$source\n\t";
+	if ($fipscanisterbuild && $source=~/\.asm$/) {
+		$ret.="\$(PERL) util${o}fipsas.pl . \$< norunasm \$(CFLAG)\n\t";
+	}
+	$ret.="\$(CC) --obj_directory=\$(OBJ_D) $ex_flags -c \$(SRC_D)$o$source\n";
+	$target =~ s/.*${o}([^${o}]+)/$1/;
+	$source =~ s/.*${o}([^${o}\.]+)\..*/$1${obj}/;
+	$ret.="\tmv \$(OBJ_D)${o}$source \$(OBJ_D)${o}$target\n" if ($target ne $source);
+	$ret.="\n";
+	return($ret);
+};
+*::perlasm_compile_target = sub {
+	my ($target,$source,$bname)=@_;
+	my $ret;
+
+	$bname =~ s/(.*)\.[^\.]$/$1/;
+	$ret=<<___;
+\$(TMP_D)$o$bname.asm: $source
+	\$(PERL) $source \$\@
+___
+	$ret .= "\t\$(PERL) util${o}fipsas.pl . \$@ norunasm \$(CFLAG)\n" if $fipscanisterbuild;
+
+	$ret.=<<___;
+
+$target: \$(TMP_D)$o$bname.asm
+	\$(ASM) --obj_directory=\$(OBJ_D) \$(TMP_D)$o$bname.asm
+
+___
+};
+
+$mlflags='';
+
+$out_def ="c6x";
+$tmp_def ="$out_def/tmp";
+$inc_def="$out_def/inc";
+
+if ($debug)
+	{
+	$cflags=$dbg_cflags.$base_cflags;
+	}
+else
+	{
+	$cflags=$opt_cflags.$base_cflags;
+	}
+
+$obj='.obj';
+$asm_suffix='.asm';
+$ofile="";
+
+# EXE linking stuff
+$link='$(CC) -z';
+$efile="-o ";
+$exep='.out';
+$ex_libs='';
+
+# static library stuff
+$mklib='ar6x';
+$ranlib='';
+$plib="";
+$libp=".lib";
+$shlibp=($shlib)?".dll":".lib";
+$lfile='-o ';
+
+$shlib_ex_obj="";
+$asm='$(CC) $(CFLAG) -c';
+
+$bn_asm_obj='';
+$bn_asm_src='';
+$des_enc_obj='';
+$des_enc_src='';
+$bf_enc_obj='';
+$bf_enc_src='';
+
+if (!$no_asm)
+	{
+	import_asm($mf_bn_asm, "bn", \$bn_asm_obj, \$bn_asm_src);
+	import_asm($mf_aes_asm, "aes", \$aes_asm_obj, \$aes_asm_src);
+	import_asm($mf_des_asm, "des", \$des_enc_obj, \$des_enc_src);
+	import_asm($mf_bf_asm, "bf", \$bf_enc_obj, \$bf_enc_src);
+	import_asm($mf_cast_asm, "cast", \$cast_enc_obj, \$cast_enc_src);
+	import_asm($mf_rc4_asm, "rc4", \$rc4_enc_obj, \$rc4_enc_src);
+	import_asm($mf_rc5_asm, "rc5", \$rc5_enc_obj, \$rc5_enc_src);
+	import_asm($mf_md5_asm, "md5", \$md5_asm_obj, \$md5_asm_src);
+	import_asm($mf_sha_asm, "sha", \$sha1_asm_obj, \$sha1_asm_src);
+	import_asm($mf_rmd_asm, "ripemd", \$rmd160_asm_obj, \$rmd160_asm_src);
+	import_asm($mf_wp_asm, "whrlpool", \$whirlpool_asm_obj, \$whirlpool_asm_src);
+	import_asm($mf_modes_asm, "modes", \$modes_asm_obj, \$modes_asm_src);
+	import_asm($mf_cpuid_asm, "", \$cpuid_asm_obj, \$cpuid_asm_src);
+	$perl_asm = 1;
+	}
+
+sub do_lib_rule
+	{
+	my($objs,$target,$name,$shlib,$ign,$base_addr) = @_;
+	local($ret);
+
+	$taget =~ s/\//$o/g if $o ne '/';
+	my $base_arg;
+	if ($base_addr ne "")
+		{
+		$base_arg= " /base:$base_addr";
+		}
+	else
+		{
+		$base_arg = "";
+		}
+	if ($name ne "")
+		{
+		$name =~ tr/a-z/A-Z/;
+		$name = "/def:ms/${name}.def";
+		}
+
+#	$target="\$(LIB_D)$o$target";
+#	$ret.="$target: $objs\n";
+	if (!$shlib)
+		{
+#		$ret.="\t\$(RM) \$(O_$Name)\n";
+		$ret.="$target: $objs\n";
+		$ret.="\t\$(MKLIB) $lfile$target $objs\n";
+		}
+	else
+		{
+		local($ex)=($target =~ /O_CRYPTO/)?'':' $(L_CRYPTO)';
+		$ex.=" $zlib_lib" if $zlib_opt == 1 && $target =~ /O_CRYPTO/;
+
+ 		if ($fips && $target =~ /O_CRYPTO/)
+			{
+			$ret.="$target: $objs \$(PREMAIN_DSO_EXE)";
+			$ret.="\n\tFIPS_LINK=\"\$(LINK)\" \\\n";
+			$ret.="\tFIPS_CC=\$(CC)\\\n";
+			$ret.="\tFIPS_CC_ARGS=/Fo\$(OBJ_D)${o}fips_premain.obj \$(SHLIB_CFLAGS) -c\\\n";
+			$ret.="\tPREMAIN_DSO_EXE=\$(PREMAIN_DSO_EXE)\\\n";
+			$ret.="\tFIPS_SHA1_EXE=\$(FIPS_SHA1_EXE)\\\n";
+			$ret.="\tFIPS_TARGET=$target\\\n";
+			$ret.="\tFIPSLIB_D=\$(FIPSLIB_D)\\\n";
+			$ret.="\t\$(FIPSLINK) \$(MLFLAGS) /map $base_arg $efile$target ";
+			$ret.="$name \$(SHLIB_EX_OBJ) $objs \$(EX_LIBS) ";
+			$ret.="\$(OBJ_D)${o}fips_premain.obj $ex\n";
+			}
+		else
+			{
+			$ret.="$target: $objs";
+			$ret.="\n\t\$(LINK) \$(MLFLAGS) $efile$target $name \$(SHLIB_EX_OBJ) $objs $ex \$(EX_LIBS)\n";
+			}
+
+		$ret.="\tIF EXIST \$@.manifest mt -nologo -manifest \$@.manifest -outputresource:\$@;2\n\n";
+		}
+	$ret.="\n";
+	return($ret);
+	}
+
+sub do_link_rule
+	{
+	my($target,$files,$dep_libs,$libs,$standalone)=@_;
+	local($ret,$_);
+	$file =~ s/\//$o/g if $o ne '/';
+	$n=&bname($targer);
+	$ret.="$target: $files $dep_libs\n";
+	if ($standalone == 1)
+		{
+		$ret.="	\$(LINK) \$(LFLAGS) $efile$target ";
+		$ret.= "\$(EX_LIBS) " if ($files =~ /O_FIPSCANISTER/ && !$fipscanisterbuild);
+		$ret.="$files $libs\n";
+		}
+	elsif ($standalone == 2)
+		{
+		$ret.="\t\$(LINK) \$(LFLAGS) $efile$target $files \$(O_FIPSCANISTER) $out_def/application.cmd\n";
+		$ret.="\t$out_def/incore6x $target\n\n";
+		}
+	else
+		{
+		$ret.="\t\$(LINK) \$(LFLAGS) $efile$target ";
+		$ret.="\t\$(APP_EX_OBJ) $files $libs\n";
+		}
+	return($ret);
+	}
+
+sub do_rlink_rule
+	{
+	local($target,$rl_start, $rl_mid, $rl_end,$dep_libs,$libs)=@_;
+	local($ret,$_);
+	my $files = "$rl_start $rl_mid $rl_end";
+
+	$file =~ s/\//$o/g if $o ne '/';
+	$n=&bname($target);
+	$ret.="$target: $files $dep_libs\n";
+	$ret.="\t\$(LINK) -r $lfile$target $files $out_def/fipscanister.cmd\n";
+	$ret.="\t\$(PERL) $out_def${o}fips_standalone_sha1 $target > ${target}.sha1\n";
+	$ret.="\t\$(PERL) util${o}copy.pl -stripcr fips${o}fips_premain.c \$(LIB_D)${o}fips_premain.c\n";
+	$ret.="\t\$(CP) fips${o}fips_premain.c.sha1 \$(LIB_D)${o}fips_premain.c.sha1\n";
+	$ret.="\n";
+	return($ret);
+	}
+
+sub import_asm
+	{
+	my ($mf_var, $asm_name, $oref, $sref) = @_;
+	my $asm_dir;
+	if ($asm_name eq "")
+		{
+		$asm_dir = "crypto$o";
+		}
+	else
+		{
+		$asm_dir = "crypto$o$asm_name$oasm$o";
+		}
+
+	$$oref = "";
+	$$sref = "";
+	$mf_var =~ s/\.o//g;
+
+	foreach (split(/ /, $mf_var))
+		{
+		$$sref .= $asm_dir . $_ . ".asm ";
+		}
+	foreach (split(/ /, $mf_var))
+		{
+		$$oref .= "\$(TMP_D)\\" . $_ . ".obj ";
+		}
+	$$oref =~ s/ $//;
+	$$sref =~ s/ $//;
+
+	}
+
+
+1;

util/pl/VC-32.pl

@@ -49,8 +49,7 @@ if ($FLAVOR =~ /WIN64/)
     # considered safe to ignore.
     # 
     $base_cflags= " $mf_cflag";
-    my $f = $shlib?' /MD':' /MT';
-    $lib_cflag='/Zl' if (!$shlib);	# remove /DEFAULTLIBs from static lib
+    my $f = ($shlib and !$fipscanisterbuild)?' /MD':' /MT';
     $opt_cflags=$f.' /Ox';
     $dbg_cflags=$f.'d /Od -DDEBUG -D_DEBUG';
     $lflags="/nologo /subsystem:console /opt:ref";
@@ -123,23 +122,28 @@ elsif ($FLAVOR =~ /CE/)
     }
 
     $cc='$(CC)';
-    $base_cflags=' /W3 /WX /GF /Gy /nologo -DUNICODE -D_UNICODE -DOPENSSL_SYSNAME_WINCE -DWIN32_LEAN_AND_MEAN -DL_ENDIAN -DDSO_WIN32 -DNO_CHMOD -DOPENSSL_SMALL_FOOTPRINT';
+    $base_cflags=' /W3 /GF /Gy /nologo -DUNICODE -D_UNICODE -DOPENSSL_SYSNAME_WINCE -DWIN32_LEAN_AND_MEAN -DL_ENDIAN -DDSO_WIN32 -DNO_CHMOD -DOPENSSL_SMALL_FOOTPRINT';
     $base_cflags.=" $wcecdefs";
     $base_cflags.=' -I$(WCECOMPAT)/include'		if (defined($ENV{'WCECOMPAT'}));
     $base_cflags.=' -I$(PORTSDK_LIBPATH)/../../include'	if (defined($ENV{'PORTSDK_LIBPATH'}));
-    $opt_cflags=' /MC /O1i';	# optimize for space, but with intrinsics...
-    $dbg_clfags=' /MC /Od -DDEBUG -D_DEBUG';
+    if (`cl 2>&1` =~ /Version 1[4-9]\./) {
+	$base_cflags.=($shlib and !$fipscanisterbuild)?' /MD':' /MT';
+    } else {
+	$base_cflags.=' /MC';
+    }
+    $opt_cflags=' /O1i';	# optimize for space, but with intrinsics...
+    $dbg_cflags=' /Od -DDEBUG -D_DEBUG';
     $lflags="/nologo /opt:ref $wcelflag";
     }
 else	# Win32
     {
     $base_cflags= " $mf_cflag";
-    my $f = $shlib?' /MD':' /MT';
-    $lib_cflag='/Zl' if (!$shlib);	# remove /DEFAULTLIBs from static lib
+    my $f = ($shlib and !$fipscanisterbuild)?' /MD':' /MT';
     $opt_cflags=$f.' /Ox /O2 /Ob2';
     $dbg_cflags=$f.'d /Od -DDEBUG -D_DEBUG';
     $lflags="/nologo /subsystem:console /opt:ref";
     }
+$lib_cflag='/Zl' if (!$shlib or $fipscanisterbuild);	# remove /DEFAULTLIBs
 $mlflags='';
 
 $out_def ="out32";	$out_def.="dll"			if ($shlib);
@@ -174,12 +178,12 @@ $rsc="rc";
 $efile="/out:";
 $exep='.exe';
 if ($no_sock)		{ $ex_libs=''; }
-elsif ($FLAVOR =~ /CE/)	{ $ex_libs='winsock.lib'; }
+elsif ($FLAVOR =~ /CE/)	{ $ex_libs='ws2.lib'; }
 else			{ $ex_libs='ws2_32.lib'; }
 
 if ($FLAVOR =~ /CE/)
 	{
-	$ex_libs.=' $(WCECOMPAT)/lib/wcecompatex.lib'	if (defined($ENV{'WCECOMPAT'}));
+	$ex_libs.=' $(WCECOMPAT)/lib/wcecompatex.lib crypt32.lib coredll.lib corelibc.lib'	if (defined($ENV{'WCECOMPAT'}));
 	$ex_libs.=' $(PORTSDK_LIBPATH)/portlib.lib'	if (defined($ENV{'PORTSDK_LIBPATH'}));
 	$ex_libs.=' /nodefaultlib:oldnames.lib coredll.lib corelibc.lib' if ($ENV{'TARGETCPU'} eq "X86");
 	}
@@ -284,7 +288,8 @@ elsif ($shlib && $FLAVOR =~ /CE/)
 	{
 	$mlflags.=" $lflags /dll";
 	$lflags.=' /entry:mainCRTstartup' if(defined($ENV{'PORTSDK_LIBPATH'}));
-	$lib_cflag.=" -D_WINDLL -D_DLL";
+	$lib_cflag.=" -D_WINDLL";
+	$lib_cflag.=" -D_DLL" if (!$fipscanisterbuild);
 	}
 
 sub do_lib_rule
@@ -389,8 +394,9 @@ sub do_rlink_rule
 
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($targer);
-	$ret.="$target: $files $dep_libs \$(FIPS_SHA1_EXE)\n";
-	$ret.="\t\$(PERL) ms\\segrenam.pl \$\$a $rl_start\n";
+	$ret.="$target: $files $dep_libs";
+	$ret.=" \$(FIPS_SHA1_EXE)" unless defined $ENV{"FIPS_SHA1_PATH"};
+  	$ret.="\n\t\$(PERL) ms\\segrenam.pl \$\$a $rl_start\n";
 	$ret.="\t\$(PERL) ms\\segrenam.pl \$\$b $rl_mid\n";
 	$ret.="\t\$(PERL) ms\\segrenam.pl \$\$c $rl_end\n";
 	$ret.="\t\$(MKLIB) $lfile$target @<<\n\t$files\n<<\n";