From f1625f274acf5dcd5601f6cb5e29e233b2a441a3 Mon Sep 17 00:00:00 2001 From: djm <> Date: Sat, 6 Sep 2008 12:15:54 +0000 Subject: import of OpenSSL 0.9.8h --- src/lib/libcrypto/bn/Makefile | 286 +++++++------- src/lib/libcrypto/bn/asm/mo-586.pl | 603 +++++++++++++++++++++++++++++ src/lib/libcrypto/bn/bntest.c | 775 +++++++++++++++++++++++++++++++++++-- src/lib/libcrypto/bn/exptest.c | 3 + 4 files changed, 1506 insertions(+), 161 deletions(-) create mode 100644 src/lib/libcrypto/bn/asm/mo-586.pl (limited to 'src/lib/libcrypto/bn') diff --git a/src/lib/libcrypto/bn/Makefile b/src/lib/libcrypto/bn/Makefile index 9969d242cc..e97c751390 100644 --- a/src/lib/libcrypto/bn/Makefile +++ b/src/lib/libcrypto/bn/Makefile @@ -8,11 +8,6 @@ CC= cc CPP= $(CC) -E INCLUDES= -I.. -I$(TOP) -I../../include CFLAG=-g -INSTALL_PREFIX= -OPENSSLDIR= /usr/local/ssl -INSTALLTOP=/usr/local/ssl -MAKEDEPPROG= makedepend -MAKEDEPEND= $(TOP)/util/domd $(TOP) -MD $(MAKEDEPPROG) MAKEFILE= Makefile AR= ar r @@ -22,6 +17,7 @@ BN_ASM= bn_asm.o CFLAGS= $(INCLUDES) $(CFLAG) ASFLAGS= $(INCLUDES) $(ASFLAG) +AFLAGS= $(ASFLAGS) GENERAL=Makefile TEST=bntest.c exptest.c @@ -31,12 +27,14 @@ LIB=$(TOP)/libcrypto.a LIBSRC= bn_add.c bn_div.c bn_exp.c bn_lib.c bn_ctx.c bn_mul.c bn_mod.c \ bn_print.c bn_rand.c bn_shift.c bn_word.c bn_blind.c \ bn_kron.c bn_sqrt.c bn_gcd.c bn_prime.c bn_err.c bn_sqr.c bn_asm.c \ - bn_recp.c bn_mont.c bn_mpi.c bn_exp2.c bn_x931p.c + bn_recp.c bn_mont.c bn_mpi.c bn_exp2.c bn_gf2m.c bn_nist.c \ + bn_depr.c bn_const.c LIBOBJ= bn_add.o bn_div.o bn_exp.o bn_lib.o bn_ctx.o bn_mul.o bn_mod.o \ bn_print.o bn_rand.o bn_shift.o bn_word.o bn_blind.o \ bn_kron.o bn_sqrt.o bn_gcd.o bn_prime.o bn_err.o bn_sqr.o $(BN_ASM) \ - bn_recp.o bn_mont.o bn_mpi.o bn_exp2.o bn_x931p.o + bn_recp.o bn_mont.o bn_mpi.o bn_exp2.o bn_gf2m.o bn_nist.o \ + bn_depr.o bn_const.o SRC= $(LIBSRC) @@ -64,70 +62,60 @@ lib: $(LIBOBJ) $(RANLIB) $(LIB) || echo Never mind. @touch lib -# elf -asm/bn86-elf.s: asm/bn-586.pl ../perlasm/x86asm.pl - (cd asm; $(PERL) bn-586.pl elf $(CFLAGS) > bn86-elf.s) - -asm/co86-elf.s: asm/co-586.pl ../perlasm/x86asm.pl - (cd asm; $(PERL) co-586.pl elf $(CFLAGS) > co86-elf.s) - +# ELF +bn86-elf.s: asm/bn-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) bn-586.pl elf $(CFLAGS) > ../$@) +co86-elf.s: asm/co-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) co-586.pl elf $(CFLAGS) > ../$@) +mo86-elf.s: asm/mo-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) mo-586.pl elf $(CFLAGS) > ../$@) +# COFF +bn86-cof.s: asm/bn-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) bn-586.pl coff $(CFLAGS) > ../$@) +co86-cof.s: asm/co-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) co-586.pl coff $(CFLAGS) > ../$@) +mo86-cof.s: asm/mo-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) mo-586.pl coff $(CFLAGS) > ../$@) # a.out -asm/bn86-out.o: asm/bn86unix.cpp - $(CPP) -DOUT asm/bn86unix.cpp | as -o asm/bn86-out.o - -asm/co86-out.o: asm/co86unix.cpp - $(CPP) -DOUT asm/co86unix.cpp | as -o asm/co86-out.o - -# bsdi -asm/bn86bsdi.o: asm/bn86unix.cpp - $(CPP) -DBSDI asm/bn86unix.cpp | sed 's/ :/:/' | as -o asm/bn86bsdi.o - -asm/co86bsdi.o: asm/co86unix.cpp - $(CPP) -DBSDI asm/co86unix.cpp | sed 's/ :/:/' | as -o asm/co86bsdi.o - -asm/bn86unix.cpp: asm/bn-586.pl ../perlasm/x86asm.pl - (cd asm; $(PERL) bn-586.pl cpp >bn86unix.cpp ) - -asm/co86unix.cpp: asm/co-586.pl ../perlasm/x86asm.pl - (cd asm; $(PERL) co-586.pl cpp >co86unix.cpp ) - -asm/sparcv8.o: asm/sparcv8.S - -asm/sparcv8plus.o: asm/sparcv8plus.S - -# Old GNU assembler doesn't understand V9 instructions, so we -# hire /usr/ccs/bin/as to do the job. Note that option is called -# *-gcc27, but even gcc 2>=8 users may experience similar problem -# if they didn't bother to upgrade GNU assembler. Such users should -# not choose this option, but be adviced to *remove* GNU assembler -# or upgrade it. -asm/sparcv8plus-gcc27.o: asm/sparcv8plus.S - $(CC) $(ASFLAGS) -E asm/sparcv8plus.S | \ - /usr/ccs/bin/as -xarch=v8plus - -o asm/sparcv8plus-gcc27.o - - -asm/ia64.o: asm/ia64.S - -# Some compiler drivers (most notably HP-UX and Intel C++) don't -# understand .S extension:-( I wish I could pipe output from cc -E, -# but it's too compiler driver/ABI dependent to cover with a single -# rule... -asm/ia64-cpp.o: asm/ia64.S - $(CC) $(ASFLAGS) -E asm/ia64.S > /tmp/ia64.$$$$.s && \ - $(CC) $(ASFLAGS) -c -o asm/ia64-cpp.o /tmp/ia64.$$$$.s; \ - rm -f /tmp/ia64.$$$$.s - -asm/x86_64-gcc.o: asm/x86_64-gcc.c - $(CC) $(ASFLAGS) -c -o $@ $< - -asm/pa-risc2W.o: asm/pa-risc2W.s - /usr/ccs/bin/as -o asm/pa-risc2W.o asm/pa-risc2W.s - -asm/linux_ppc32.s: asm/ppc.pl; $(PERL) $< $@ -asm/linux_ppc64.s: asm/ppc.pl; $(PERL) $< $@ -asm/aix_ppc32.s: asm/ppc.pl; $(PERL) asm/ppc.pl $@ -asm/aix_ppc64.s: asm/ppc.pl; $(PERL) asm/ppc.pl $@ -asm/osx_ppc32.s: asm/ppc.pl; $(PERL) $< $@ +bn86-out.s: asm/bn-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) bn-586.pl a.out $(CFLAGS) > ../$@) +co86-out.s: asm/co-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) co-586.pl a.out $(CFLAGS) > ../$@) +mo86-out.s: asm/mo-586.pl ../perlasm/x86asm.pl + (cd asm; $(PERL) mo-586.pl a.out $(CFLAGS) > ../$@) + +sparcv8.o: asm/sparcv8.S + $(CC) $(CFLAGS) -c asm/sparcv8.S +sparcv8plus.o: asm/sparcv8plus.S + $(CC) $(CFLAGS) -c asm/sparcv8plus.S + +bn-mips3.o: asm/mips3.s + @if [ "$(CC)" = "gcc" ]; then \ + ABI=`expr "$(CFLAGS)" : ".*-mabi=\([n3264]*\)"` && \ + as -$$ABI -O -o $@ asm/mips3.s; \ + else $(CC) -c $(CFLAGS) -o $@ asm/mips3.s; fi + +x86_64-gcc.o: asm/x86_64-gcc.c + $(CC) $(CFLAGS) -c -o $@ asm/x86_64-gcc.c +x86_64-mont.s: asm/x86_64-mont.pl + $(PERL) asm/x86_64-mont.pl $@ + +bn-ia64.s: asm/ia64.S + $(CC) $(CFLAGS) -E asm/ia64.S > $@ + +# GNU assembler fails to compile PA-RISC2 modules, insist on calling +# vendor assembler... +pa-risc2W.o: asm/pa-risc2W.s + /usr/ccs/bin/as -o pa-risc2W.o asm/pa-risc2W.s +pa-risc2.o: asm/pa-risc2.s + /usr/ccs/bin/as -o pa-risc2.o asm/pa-risc2.s + +# ppc - AIX, Linux, MacOS X... +linux_ppc32.s: asm/ppc.pl; $(PERL) $< $@ +linux_ppc64.s: asm/ppc.pl; $(PERL) $< $@ +aix_ppc32.s: asm/ppc.pl; $(PERL) asm/ppc.pl $@ +aix_ppc64.s: asm/ppc.pl; $(PERL) asm/ppc.pl $@ +osx_ppc32.s: asm/ppc.pl; $(PERL) $< $@ files: $(PERL) $(TOP)/util/files.pl Makefile >> $(TOP)/MINFO @@ -138,6 +126,7 @@ links: @$(PERL) $(TOP)/util/mklink.pl ../../apps $(APPS) install: + @[ -n "$(INSTALLTOP)" ] # should be set by top Makefile... @headerlist="$(EXHEADER)"; for i in $$headerlist ; \ do \ (cp $$i $(INSTALL_PREFIX)$(INSTALLTOP)/include/openssl/$$i; \ @@ -161,6 +150,7 @@ lint: lint -DLINT $(INCLUDES) $(SRC)>fluff depend: + @[ -n "$(MAKEDEPEND)" ] # should be set by upper Makefile... $(MAKEDEPEND) -- $(CFLAG) $(INCLUDES) $(DEPFLAG) -- $(PROGS) $(LIBSRC) dclean: @@ -168,7 +158,7 @@ dclean: mv -f Makefile.new $(MAKEFILE) clean: - rm -f asm/co86unix.cpp asm/bn86unix.cpp asm/*-elf.* *.o */*.o *.obj lib tags core .pure .nfs* *.old *.bak fluff bn_asm.s + rm -f *.s *.o *.obj lib tags core .pure .nfs* *.old *.bak fluff # DO NOT DELETE THIS LINE -- make depend depends on it. @@ -176,101 +166,131 @@ bn_add.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_add.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_add.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_add.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_add.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_add.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_add.o: ../cryptlib.h bn_add.c bn_lcl.h +bn_add.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_add.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_add.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_add.c bn_lcl.h bn_asm.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_asm.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_asm.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_asm.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_asm.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_asm.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_asm.o: ../cryptlib.h bn_asm.c bn_lcl.h +bn_asm.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_asm.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_asm.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_asm.c bn_lcl.h bn_blind.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_blind.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_blind.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_blind.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_blind.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_blind.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_blind.o: ../cryptlib.h bn_blind.c bn_lcl.h +bn_blind.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_blind.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_blind.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_blind.c bn_lcl.h +bn_const.o: ../../include/openssl/e_os2.h ../../include/openssl/opensslconf.h +bn_const.o: ../../include/openssl/ossl_typ.h bn.h bn_const.c bn_ctx.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_ctx.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_ctx.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_ctx.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_ctx.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_ctx.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_ctx.o: ../cryptlib.h bn_ctx.c bn_lcl.h +bn_ctx.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_ctx.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_ctx.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_ctx.c bn_lcl.h +bn_depr.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h +bn_depr.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h +bn_depr.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h +bn_depr.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h +bn_depr.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_depr.o: ../../include/openssl/rand.h ../../include/openssl/safestack.h +bn_depr.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h +bn_depr.o: ../cryptlib.h bn_depr.c bn_lcl.h bn_div.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_div.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_div.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_div.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_div.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_div.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_div.o: ../cryptlib.h bn_div.c bn_lcl.h +bn_div.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_div.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_div.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_div.c bn_lcl.h bn_err.o: ../../include/openssl/bio.h ../../include/openssl/bn.h bn_err.o: ../../include/openssl/crypto.h ../../include/openssl/e_os2.h bn_err.o: ../../include/openssl/err.h ../../include/openssl/lhash.h bn_err.o: ../../include/openssl/opensslconf.h ../../include/openssl/opensslv.h -bn_err.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h -bn_err.o: ../../include/openssl/symhacks.h bn_err.c +bn_err.o: ../../include/openssl/ossl_typ.h ../../include/openssl/safestack.h +bn_err.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h +bn_err.o: bn_err.c bn_exp.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_exp.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_exp.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_exp.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_exp.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_exp.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_exp.o: ../cryptlib.h bn_exp.c bn_lcl.h +bn_exp.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_exp.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_exp.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_exp.c bn_lcl.h bn_exp2.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_exp2.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_exp2.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_exp2.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_exp2.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_exp2.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_exp2.o: ../cryptlib.h bn_exp2.c bn_lcl.h +bn_exp2.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_exp2.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_exp2.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_exp2.c bn_lcl.h bn_gcd.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_gcd.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_gcd.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_gcd.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_gcd.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_gcd.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_gcd.o: ../cryptlib.h bn_gcd.c bn_lcl.h -bn_kron.o: ../../include/openssl/bn.h ../../include/openssl/e_os2.h -bn_kron.o: ../../include/openssl/opensslconf.h bn_kron.c bn_lcl.h +bn_gcd.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_gcd.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_gcd.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_gcd.c bn_lcl.h +bn_gf2m.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h +bn_gf2m.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h +bn_gf2m.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h +bn_gf2m.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h +bn_gf2m.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_gf2m.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_gf2m.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_gf2m.c bn_lcl.h +bn_kron.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h +bn_kron.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h +bn_kron.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h +bn_kron.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h +bn_kron.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_kron.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_kron.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_kron.c bn_lcl.h bn_lib.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_lib.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_lib.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_lib.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_lib.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_lib.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_lib.o: ../cryptlib.h bn_lcl.h bn_lib.c +bn_lib.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_lib.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_lib.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_lib.c bn_mod.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_mod.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_mod.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_mod.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_mod.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_mod.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_mod.o: ../cryptlib.h bn_lcl.h bn_mod.c +bn_mod.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_mod.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_mod.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_mod.c bn_mont.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_mont.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_mont.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_mont.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_mont.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_mont.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_mont.o: ../cryptlib.h bn_lcl.h bn_mont.c +bn_mont.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_mont.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_mont.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_mont.c bn_mpi.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_mpi.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_mpi.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_mpi.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_mpi.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_mpi.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_mpi.o: ../cryptlib.h bn_lcl.h bn_mpi.c +bn_mpi.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_mpi.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_mpi.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_mpi.c bn_mul.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_mul.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_mul.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_mul.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_mul.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_mul.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_mul.o: ../cryptlib.h bn_lcl.h bn_mul.c +bn_mul.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_mul.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_mul.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_mul.c +bn_nist.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h +bn_nist.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h +bn_nist.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h +bn_nist.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h +bn_nist.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_nist.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_nist.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_nist.c bn_prime.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_prime.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_prime.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h @@ -283,9 +303,9 @@ bn_print.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_print.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_print.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_print.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_print.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_print.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_print.o: ../cryptlib.h bn_lcl.h bn_print.c +bn_print.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_print.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_print.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_print.c bn_rand.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_rand.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_rand.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h @@ -298,36 +318,34 @@ bn_recp.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_recp.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_recp.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_recp.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_recp.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_recp.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_recp.o: ../cryptlib.h bn_lcl.h bn_recp.c +bn_recp.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_recp.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_recp.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_recp.c bn_shift.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_shift.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_shift.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_shift.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_shift.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_shift.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_shift.o: ../cryptlib.h bn_lcl.h bn_shift.c +bn_shift.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_shift.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_shift.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_shift.c bn_sqr.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_sqr.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_sqr.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_sqr.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_sqr.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_sqr.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_sqr.o: ../cryptlib.h bn_lcl.h bn_sqr.c +bn_sqr.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_sqr.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_sqr.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_sqr.c bn_sqrt.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_sqrt.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_sqrt.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_sqrt.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_sqrt.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_sqrt.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_sqrt.o: ../cryptlib.h bn_lcl.h bn_sqrt.c +bn_sqrt.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_sqrt.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_sqrt.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_sqrt.c bn_word.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h bn_word.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h bn_word.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h bn_word.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h -bn_word.o: ../../include/openssl/opensslv.h ../../include/openssl/safestack.h -bn_word.o: ../../include/openssl/stack.h ../../include/openssl/symhacks.h -bn_word.o: ../cryptlib.h bn_lcl.h bn_word.c -bn_x931p.o: ../../include/openssl/bn.h ../../include/openssl/e_os2.h -bn_x931p.o: ../../include/openssl/opensslconf.h bn_x931p.c +bn_word.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h +bn_word.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h +bn_word.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_lcl.h bn_word.c diff --git a/src/lib/libcrypto/bn/asm/mo-586.pl b/src/lib/libcrypto/bn/asm/mo-586.pl new file mode 100644 index 0000000000..0982293094 --- /dev/null +++ b/src/lib/libcrypto/bn/asm/mo-586.pl @@ -0,0 +1,603 @@ +#!/usr/bin/env perl + +# This is crypto/bn/asm/x86-mont.pl (with asciz from crypto/perlasm/x86asm.pl) +# from OpenSSL 0.9.9-dev + +sub ::asciz +{ my @str=unpack("C*",shift); + push @str,0; + while ($#str>15) { + &data_byte(@str[0..15]); + foreach (0..15) { shift @str; } + } + &data_byte(@str) if (@str); +} + +# ==================================================================== +# Written by Andy Polyakov 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/. +# ==================================================================== + +# October 2005 +# +# This is a "teaser" code, as it can be improved in several ways... +# First of all non-SSE2 path should be implemented (yes, for now it +# performs Montgomery multiplication/convolution only on SSE2-capable +# CPUs such as P4, others fall down to original code). Then inner loop +# can be unrolled and modulo-scheduled to improve ILP and possibly +# moved to 128-bit XMM register bank (though it would require input +# rearrangement and/or increase bus bandwidth utilization). Dedicated +# squaring procedure should give further performance improvement... +# Yet, for being draft, the code improves rsa512 *sign* benchmark by +# 110%(!), rsa1024 one - by 70% and rsa4096 - by 20%:-) + +# December 2006 +# +# Modulo-scheduling SSE2 loops results in further 15-20% improvement. +# Integer-only code [being equipped with dedicated squaring procedure] +# gives ~40% on rsa512 sign benchmark... + +push(@INC,"perlasm","../../perlasm"); +require "x86asm.pl"; + +&asm_init($ARGV[0],$0); + +$sse2=0; +for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); } + +&external_label("OPENSSL_ia32cap_P") if ($sse2); + +&function_begin("bn_mul_mont"); + +$i="edx"; +$j="ecx"; +$ap="esi"; $tp="esi"; # overlapping variables!!! +$rp="edi"; $bp="edi"; # overlapping variables!!! +$np="ebp"; +$num="ebx"; + +$_num=&DWP(4*0,"esp"); # stack top layout +$_rp=&DWP(4*1,"esp"); +$_ap=&DWP(4*2,"esp"); +$_bp=&DWP(4*3,"esp"); +$_np=&DWP(4*4,"esp"); +$_n0=&DWP(4*5,"esp"); $_n0q=&QWP(4*5,"esp"); +$_sp=&DWP(4*6,"esp"); +$_bpend=&DWP(4*7,"esp"); +$frame=32; # size of above frame rounded up to 16n + + &xor ("eax","eax"); + &mov ("edi",&wparam(5)); # int num + &cmp ("edi",4); + &jl (&label("just_leave")); + + &lea ("esi",&wparam(0)); # put aside pointer to argument block + &lea ("edx",&wparam(1)); # load ap + &mov ("ebp","esp"); # saved stack pointer! + &add ("edi",2); # extra two words on top of tp + &neg ("edi"); + &lea ("esp",&DWP(-$frame,"esp","edi",4)); # alloca($frame+4*(num+2)) + &neg ("edi"); + + # minimize cache contention by arraning 2K window between stack + # pointer and ap argument [np is also position sensitive vector, + # but it's assumed to be near ap, as it's allocated at ~same + # time]. + &mov ("eax","esp"); + &sub ("eax","edx"); + &and ("eax",2047); + &sub ("esp","eax"); # this aligns sp and ap modulo 2048 + + &xor ("edx","esp"); + &and ("edx",2048); + &xor ("edx",2048); + &sub ("esp","edx"); # this splits them apart modulo 4096 + + &and ("esp",-64); # align to cache line + + ################################# load argument block... + &mov ("eax",&DWP(0*4,"esi"));# BN_ULONG *rp + &mov ("ebx",&DWP(1*4,"esi"));# const BN_ULONG *ap + &mov ("ecx",&DWP(2*4,"esi"));# const BN_ULONG *bp + &mov ("edx",&DWP(3*4,"esi"));# const BN_ULONG *np + &mov ("esi",&DWP(4*4,"esi"));# const BN_ULONG *n0 + #&mov ("edi",&DWP(5*4,"esi"));# int num + + &mov ("esi",&DWP(0,"esi")); # pull n0[0] + &mov ($_rp,"eax"); # ... save a copy of argument block + &mov ($_ap,"ebx"); + &mov ($_bp,"ecx"); + &mov ($_np,"edx"); + &mov ($_n0,"esi"); + &lea ($num,&DWP(-3,"edi")); # num=num-1 to assist modulo-scheduling + #&mov ($_num,$num); # redundant as $num is not reused + &mov ($_sp,"ebp"); # saved stack pointer! + +if($sse2) { +$acc0="mm0"; # mmx register bank layout +$acc1="mm1"; +$car0="mm2"; +$car1="mm3"; +$mul0="mm4"; +$mul1="mm5"; +$temp="mm6"; +$mask="mm7"; + + &picmeup("eax","OPENSSL_ia32cap_P"); + &bt (&DWP(0,"eax"),26); + &jnc (&label("non_sse2")); + + &mov ("eax",-1); + &movd ($mask,"eax"); # mask 32 lower bits + + &mov ($ap,$_ap); # load input pointers + &mov ($bp,$_bp); + &mov ($np,$_np); + + &xor ($i,$i); # i=0 + &xor ($j,$j); # j=0 + + &movd ($mul0,&DWP(0,$bp)); # bp[0] + &movd ($mul1,&DWP(0,$ap)); # ap[0] + &movd ($car1,&DWP(0,$np)); # np[0] + + &pmuludq($mul1,$mul0); # ap[0]*bp[0] + &movq ($car0,$mul1); + &movq ($acc0,$mul1); # I wish movd worked for + &pand ($acc0,$mask); # inter-register transfers + + &pmuludq($mul1,$_n0q); # *=n0 + + &pmuludq($car1,$mul1); # "t[0]"*np[0]*n0 + &paddq ($car1,$acc0); + + &movd ($acc1,&DWP(4,$np)); # np[1] + &movd ($acc0,&DWP(4,$ap)); # ap[1] + + &psrlq ($car0,32); + &psrlq ($car1,32); + + &inc ($j); # j++ +&set_label("1st",16); + &pmuludq($acc0,$mul0); # ap[j]*bp[0] + &pmuludq($acc1,$mul1); # np[j]*m1 + &paddq ($car0,$acc0); # +=c0 + &paddq ($car1,$acc1); # +=c1 + + &movq ($acc0,$car0); + &pand ($acc0,$mask); + &movd ($acc1,&DWP(4,$np,$j,4)); # np[j+1] + &paddq ($car1,$acc0); # +=ap[j]*bp[0]; + &movd ($acc0,&DWP(4,$ap,$j,4)); # ap[j+1] + &psrlq ($car0,32); + &movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[j-1]= + &psrlq ($car1,32); + + &lea ($j,&DWP(1,$j)); + &cmp ($j,$num); + &jl (&label("1st")); + + &pmuludq($acc0,$mul0); # ap[num-1]*bp[0] + &pmuludq($acc1,$mul1); # np[num-1]*m1 + &paddq ($car0,$acc0); # +=c0 + &paddq ($car1,$acc1); # +=c1 + + &movq ($acc0,$car0); + &pand ($acc0,$mask); + &paddq ($car1,$acc0); # +=ap[num-1]*bp[0]; + &movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[num-2]= + + &psrlq ($car0,32); + &psrlq ($car1,32); + + &paddq ($car1,$car0); + &movq (&QWP($frame,"esp",$num,4),$car1); # tp[num].tp[num-1] + + &inc ($i); # i++ +&set_label("outer"); + &xor ($j,$j); # j=0 + + &movd ($mul0,&DWP(0,$bp,$i,4)); # bp[i] + &movd ($mul1,&DWP(0,$ap)); # ap[0] + &movd ($temp,&DWP($frame,"esp")); # tp[0] + &movd ($car1,&DWP(0,$np)); # np[0] + &pmuludq($mul1,$mul0); # ap[0]*bp[i] + + &paddq ($mul1,$temp); # +=tp[0] + &movq ($acc0,$mul1); + &movq ($car0,$mul1); + &pand ($acc0,$mask); + + &pmuludq($mul1,$_n0q); # *=n0 + + &pmuludq($car1,$mul1); + &paddq ($car1,$acc0); + + &movd ($temp,&DWP($frame+4,"esp")); # tp[1] + &movd ($acc1,&DWP(4,$np)); # np[1] + &movd ($acc0,&DWP(4,$ap)); # ap[1] + + &psrlq ($car0,32); + &psrlq ($car1,32); + &paddq ($car0,$temp); # +=tp[1] + + &inc ($j); # j++ + &dec ($num); +&set_label("inner"); + &pmuludq($acc0,$mul0); # ap[j]*bp[i] + &pmuludq($acc1,$mul1); # np[j]*m1 + &paddq ($car0,$acc0); # +=c0 + &paddq ($car1,$acc1); # +=c1 + + &movq ($acc0,$car0); + &movd ($temp,&DWP($frame+4,"esp",$j,4));# tp[j+1] + &pand ($acc0,$mask); + &movd ($acc1,&DWP(4,$np,$j,4)); # np[j+1] + &paddq ($car1,$acc0); # +=ap[j]*bp[i]+tp[j] + &movd ($acc0,&DWP(4,$ap,$j,4)); # ap[j+1] + &psrlq ($car0,32); + &movd (&DWP($frame-4,"esp",$j,4),$car1);# tp[j-1]= + &psrlq ($car1,32); + &paddq ($car0,$temp); # +=tp[j+1] + + &dec ($num); + &lea ($j,&DWP(1,$j)); # j++ + &jnz (&label("inner")); + + &mov ($num,$j); + &pmuludq($acc0,$mul0); # ap[num-1]*bp[i] + &pmuludq($acc1,$mul1); # np[num-1]*m1 + &paddq ($car0,$acc0); # +=c0 + &paddq ($car1,$acc1); # +=c1 + + &movq ($acc0,$car0); + &pand ($acc0,$mask); + &paddq ($car1,$acc0); # +=ap[num-1]*bp[i]+tp[num-1] + &movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[num-2]= + &psrlq ($car0,32); + &psrlq ($car1,32); + + &movd ($temp,&DWP($frame+4,"esp",$num,4)); # += tp[num] + &paddq ($car1,$car0); + &paddq ($car1,$temp); + &movq (&QWP($frame,"esp",$num,4),$car1); # tp[num].tp[num-1] + + &lea ($i,&DWP(1,$i)); # i++ + &cmp ($i,$num); + &jle (&label("outer")); + + &emms (); # done with mmx bank + &jmp (&label("common_tail")); + +&set_label("non_sse2",16); +} + +if (0) { + &mov ("esp",$_sp); + &xor ("eax","eax"); # signal "not fast enough [yet]" + &jmp (&label("just_leave")); + # While the below code provides competitive performance for + # all key lengthes on modern Intel cores, it's still more + # than 10% slower for 4096-bit key elsewhere:-( "Competitive" + # means compared to the original integer-only assembler. + # 512-bit RSA sign is better by ~40%, but that's about all + # one can say about all CPUs... +} else { +$inp="esi"; # integer path uses these registers differently +$word="edi"; +$carry="ebp"; + + &mov ($inp,$_ap); + &lea ($carry,&DWP(1,$num)); + &mov ($word,$_bp); + &xor ($j,$j); # j=0 + &mov ("edx",$inp); + &and ($carry,1); # see if num is even + &sub ("edx",$word); # see if ap==bp + &lea ("eax",&DWP(4,$word,$num,4)); # &bp[num] + &or ($carry,"edx"); + &mov ($word,&DWP(0,$word)); # bp[0] + &jz (&label("bn_sqr_mont")); + &mov ($_bpend,"eax"); + &mov ("eax",&DWP(0,$inp)); + &xor ("edx","edx"); + +&set_label("mull",16); + &mov ($carry,"edx"); + &mul ($word); # ap[j]*bp[0] + &add ($carry,"eax"); + &lea ($j,&DWP(1,$j)); + &adc ("edx",0); + &mov ("eax",&DWP(0,$inp,$j,4)); # ap[j+1] + &cmp ($j,$num); + &mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]= + &jl (&label("mull")); + + &mov ($carry,"edx"); + &mul ($word); # ap[num-1]*bp[0] + &mov ($word,$_n0); + &add ("eax",$carry); + &mov ($inp,$_np); + &adc ("edx",0); + &imul ($word,&DWP($frame,"esp")); # n0*tp[0] + + &mov (&DWP($frame,"esp",$num,4),"eax"); # tp[num-1]= + &xor ($j,$j); + &mov (&DWP($frame+4,"esp",$num,4),"edx"); # tp[num]= + &mov (&DWP($frame+8,"esp",$num,4),$j); # tp[num+1]= + + &mov ("eax",&DWP(0,$inp)); # np[0] + &mul ($word); # np[0]*m + &add ("eax",&DWP($frame,"esp")); # +=tp[0] + &mov ("eax",&DWP(4,$inp)); # np[1] + &adc ("edx",0); + &inc ($j); + + &jmp (&label("2ndmadd")); + +&set_label("1stmadd",16); + &mov ($carry,"edx"); + &mul ($word); # ap[j]*bp[i] + &add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j] + &lea ($j,&DWP(1,$j)); + &adc ("edx",0); + &add ($carry,"eax"); + &mov ("eax",&DWP(0,$inp,$j,4)); # ap[j+1] + &adc ("edx",0); + &cmp ($j,$num); + &mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]= + &jl (&label("1stmadd")); + + &mov ($carry,"edx"); + &mul ($word); # ap[num-1]*bp[i] + &add ("eax",&DWP($frame,"esp",$num,4)); # +=tp[num-1] + &mov ($word,$_n0); + &adc ("edx",0); + &mov ($inp,$_np); + &add ($carry,"eax"); + &adc ("edx",0); + &imul ($word,&DWP($frame,"esp")); # n0*tp[0] + + &xor ($j,$j); + &add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num] + &mov (&DWP($frame,"esp",$num,4),$carry); # tp[num-1]= + &adc ($j,0); + &mov ("eax",&DWP(0,$inp)); # np[0] + &mov (&DWP($frame+4,"esp",$num,4),"edx"); # tp[num]= + &mov (&DWP($frame+8,"esp",$num,4),$j); # tp[num+1]= + + &mul ($word); # np[0]*m + &add ("eax",&DWP($frame,"esp")); # +=tp[0] + &mov ("eax",&DWP(4,$inp)); # np[1] + &adc ("edx",0); + &mov ($j,1); + +&set_label("2ndmadd",16); + &mov ($carry,"edx"); + &mul ($word); # np[j]*m + &add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j] + &lea ($j,&DWP(1,$j)); + &adc ("edx",0); + &add ($carry,"eax"); + &mov ("eax",&DWP(0,$inp,$j,4)); # np[j+1] + &adc ("edx",0); + &cmp ($j,$num); + &mov (&DWP($frame-8,"esp",$j,4),$carry); # tp[j-1]= + &jl (&label("2ndmadd")); + + &mov ($carry,"edx"); + &mul ($word); # np[j]*m + &add ($carry,&DWP($frame,"esp",$num,4)); # +=tp[num-1] + &adc ("edx",0); + &add ($carry,"eax"); + &adc ("edx",0); + &mov (&DWP($frame-4,"esp",$num,4),$carry); # tp[num-2]= + + &xor ("eax","eax"); + &mov ($j,$_bp); # &bp[i] + &add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num] + &adc ("eax",&DWP($frame+8,"esp",$num,4)); # +=tp[num+1] + &lea ($j,&DWP(4,$j)); + &mov (&DWP($frame,"esp",$num,4),"edx"); # tp[num-1]= + &cmp ($j,$_bpend); + &mov (&DWP($frame+4,"esp",$num,4),"eax"); # tp[num]= + &je (&label("common_tail")); + + &mov ($word,&DWP(0,$j)); # bp[i+1] + &mov ($inp,$_ap); + &mov ($_bp,$j); # &bp[++i] + &xor ($j,$j); + &xor ("edx","edx"); + &mov ("eax",&DWP(0,$inp)); + &jmp (&label("1stmadd")); + +&set_label("bn_sqr_mont",16); +$sbit=$num; + &mov ($_num,$num); + &mov ($_bp,$j); # i=0 + + &mov ("eax",$word); # ap[0] + &mul ($word); # ap[0]*ap[0] + &mov (&DWP($frame,"esp"),"eax"); # tp[0]= + &mov ($sbit,"edx"); + &shr ("edx",1); + &and ($sbit,1); + &inc ($j); +&set_label("sqr",16); + &mov ("eax",&DWP(0,$inp,$j,4)); # ap[j] + &mov ($carry,"edx"); + &mul ($word); # ap[j]*ap[0] + &add ("eax",$carry); + &lea ($j,&DWP(1,$j)); + &adc ("edx",0); + &lea ($carry,&DWP(0,$sbit,"eax",2)); + &shr ("eax",31); + &cmp ($j,$_num); + &mov ($sbit,"eax"); + &mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]= + &jl (&label("sqr")); + + &mov ("eax",&DWP(0,$inp,$j,4)); # ap[num-1] + &mov ($carry,"edx"); + &mul ($word); # ap[num-1]*ap[0] + &add ("eax",$carry); + &mov ($word,$_n0); + &adc ("edx",0); + &mov ($inp,$_np); + &lea ($carry,&DWP(0,$sbit,"eax",2)); + &imul ($word,&DWP($frame,"esp")); # n0*tp[0] + &shr ("eax",31); + &mov (&DWP($frame,"esp",$j,4),$carry); # tp[num-1]= + + &lea ($carry,&DWP(0,"eax","edx",2)); + &mov ("eax",&DWP(0,$inp)); # np[0] + &shr ("edx",31); + &mov (&DWP($frame+4,"esp",$j,4),$carry); # tp[num]= + &mov (&DWP($frame+8,"esp",$j,4),"edx"); # tp[num+1]= + + &mul ($word); # np[0]*m + &add ("eax",&DWP($frame,"esp")); # +=tp[0] + &mov ($num,$j); + &adc ("edx",0); + &mov ("eax",&DWP(4,$inp)); # np[1] + &mov ($j,1); + +&set_label("3rdmadd",16); + &mov ($carry,"edx"); + &mul ($word); # np[j]*m + &add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j] + &adc ("edx",0); + &add ($carry,"eax"); + &mov ("eax",&DWP(4,$inp,$j,4)); # np[j+1] + &adc ("edx",0); + &mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j-1]= + + &mov ($carry,"edx"); + &mul ($word); # np[j+1]*m + &add ($carry,&DWP($frame+4,"esp",$j,4)); # +=tp[j+1] + &lea ($j,&DWP(2,$j)); + &adc ("edx",0); + &add ($carry,"eax"); + &mov ("eax",&DWP(0,$inp,$j,4)); # np[j+2] + &adc ("edx",0); + &cmp ($j,$num); + &mov (&DWP($frame-8,"esp",$j,4),$carry); # tp[j]= + &jl (&label("3rdmadd")); + + &mov ($carry,"edx"); + &mul ($word); # np[j]*m + &add ($carry,&DWP($frame,"esp",$num,4)); # +=tp[num-1] + &adc ("edx",0); + &add ($carry,"eax"); + &adc ("edx",0); + &mov (&DWP($frame-4,"esp",$num,4),$carry); # tp[num-2]= + + &mov ($j,$_bp); # i + &xor ("eax","eax"); + &mov ($inp,$_ap); + &add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num] + &adc ("eax",&DWP($frame+8,"esp",$num,4)); # +=tp[num+1] + &mov (&DWP($frame,"esp",$num,4),"edx"); # tp[num-1]= + &cmp ($j,$num); + &mov (&DWP($frame+4,"esp",$num,4),"eax"); # tp[num]= + &je (&label("common_tail")); + + &mov ($word,&DWP(4,$inp,$j,4)); # ap[i] + &lea ($j,&DWP(1,$j)); + &mov ("eax",$word); + &mov ($_bp,$j); # ++i + &mul ($word); # ap[i]*ap[i] + &add ("eax",&DWP($frame,"esp",$j,4)); # +=tp[i] + &adc ("edx",0); + &mov (&DWP($frame,"esp",$j,4),"eax"); # tp[i]= + &xor ($carry,$carry); + &cmp ($j,$num); + &lea ($j,&DWP(1,$j)); + &je (&label("sqrlast")); + + &mov ($sbit,"edx"); # zaps $num + &shr ("edx",1); + &and ($sbit,1); +&set_label("sqradd",16); + &mov ("eax",&DWP(0,$inp,$j,4)); # ap[j] + &mov ($carry,"edx"); + &mul ($word); # ap[j]*ap[i] + &add ("eax",$carry); + &lea ($carry,&DWP(0,"eax","eax")); + &adc ("edx",0); + &shr ("eax",31); + &add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j] + &lea ($j,&DWP(1,$j)); + &adc ("eax",0); + &add ($carry,$sbit); + &adc ("eax",0); + &cmp ($j,$_num); + &mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]= + &mov ($sbit,"eax"); + &jle (&label("sqradd")); + + &mov ($carry,"edx"); + &lea ("edx",&DWP(0,$sbit,"edx",2)); + &shr ($carry,31); +&set_label("sqrlast"); + &mov ($word,$_n0); + &mov ($inp,$_np); + &imul ($word,&DWP($frame,"esp")); # n0*tp[0] + + &add ("edx",&DWP($frame,"esp",$j,4)); # +=tp[num] + &mov ("eax",&DWP(0,$inp)); # np[0] + &adc ($carry,0); + &mov (&DWP($frame,"esp",$j,4),"edx"); # tp[num]= + &mov (&DWP($frame+4,"esp",$j,4),$carry); # tp[num+1]= + + &mul ($word); # np[0]*m + &add ("eax",&DWP($frame,"esp")); # +=tp[0] + &lea ($num,&DWP(-1,$j)); + &adc ("edx",0); + &mov ($j,1); + &mov ("eax",&DWP(4,$inp)); # np[1] + + &jmp (&label("3rdmadd")); +} + +&set_label("common_tail",16); + &mov ($np,$_np); # load modulus pointer + &mov ($rp,$_rp); # load result pointer + &lea ($tp,&DWP($frame,"esp")); # [$ap and $bp are zapped] + + &mov ("eax",&DWP(0,$tp)); # tp[0] + &mov ($j,$num); # j=num-1 + &xor ($i,$i); # i=0 and clear CF! + +&set_label("sub",16); + &sbb ("eax",&DWP(0,$np,$i,4)); + &mov (&DWP(0,$rp,$i,4),"eax"); # rp[i]=tp[i]-np[i] + &dec ($j); # doesn't affect CF! + &mov ("eax",&DWP(4,$tp,$i,4)); # tp[i+1] + &lea ($i,&DWP(1,$i)); # i++ + &jge (&label("sub")); + + &sbb ("eax",0); # handle upmost overflow bit + &and ($tp,"eax"); + ¬ ("eax"); + &mov ($np,$rp); + &and ($np,"eax"); + &or ($tp,$np); # tp=carry?tp:rp + +&set_label("copy",16); # copy or in-place refresh + &mov ("eax",&DWP(0,$tp,$num,4)); + &mov (&DWP(0,$rp,$num,4),"eax"); # rp[i]=tp[i] + &mov (&DWP($frame,"esp",$num,4),$j); # zap temporary vector + &dec ($num); + &jge (&label("copy")); + + &mov ("esp",$_sp); # pull saved stack pointer + &mov ("eax",1); +&set_label("just_leave"); +&function_end("bn_mul_mont"); + +&asciz("Montgomery Multiplication for x86, CRYPTOGAMS by "); + +&asm_finish(); diff --git a/src/lib/libcrypto/bn/bntest.c b/src/lib/libcrypto/bn/bntest.c index 685007d330..310763eca0 100644 --- a/src/lib/libcrypto/bn/bntest.c +++ b/src/lib/libcrypto/bn/bntest.c @@ -55,6 +55,25 @@ * copied and put under another distribution licence * [including the GNU Public Licence.] */ +/* ==================================================================== + * Copyright 2002 Sun Microsystems, Inc. ALL RIGHTS RESERVED. + * + * Portions of the attached software ("Contribution") are developed by + * SUN MICROSYSTEMS, INC., and are contributed to the OpenSSL project. + * + * The Contribution is licensed pursuant to the Eric Young open source + * license provided above. + * + * The binary polynomial arithmetic software is originally written by + * Sheueling Chang Shantz and Douglas Stebila of Sun Microsystems Laboratories. + * + */ + +/* Until the key-gen callbacks are modified to use newer prototypes, we allow + * deprecated functions for openssl-internal code */ +#ifdef OPENSSL_NO_DEPRECATED +#undef OPENSSL_NO_DEPRECATED +#endif #include #include @@ -79,6 +98,7 @@ int test_lshift(BIO *bp,BN_CTX *ctx,BIGNUM *a_); int test_rshift1(BIO *bp); int test_rshift(BIO *bp,BN_CTX *ctx); int test_div(BIO *bp,BN_CTX *ctx); +int test_div_word(BIO *bp); int test_div_recp(BIO *bp,BN_CTX *ctx); int test_mul(BIO *bp); int test_sqr(BIO *bp,BN_CTX *ctx); @@ -88,6 +108,15 @@ int test_mod_mul(BIO *bp,BN_CTX *ctx); int test_mod_exp(BIO *bp,BN_CTX *ctx); int test_mod_exp_mont_consttime(BIO *bp,BN_CTX *ctx); int test_exp(BIO *bp,BN_CTX *ctx); +int test_gf2m_add(BIO *bp); +int test_gf2m_mod(BIO *bp); +int test_gf2m_mod_mul(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_sqr(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_inv(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_div(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_exp(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_sqrt(BIO *bp,BN_CTX *ctx); +int test_gf2m_mod_solve_quad(BIO *bp,BN_CTX *ctx); int test_kron(BIO *bp,BN_CTX *ctx); int test_sqrt(BIO *bp,BN_CTX *ctx); int rand_neg(void); @@ -155,80 +184,120 @@ int main(int argc, char *argv[]) message(out,"BN_add"); if (!test_add(out)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_sub"); if (!test_sub(out)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_lshift1"); if (!test_lshift1(out)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_lshift (fixed)"); if (!test_lshift(out,ctx,BN_bin2bn(lst,sizeof(lst)-1,NULL))) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_lshift"); if (!test_lshift(out,ctx,NULL)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_rshift1"); if (!test_rshift1(out)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_rshift"); if (!test_rshift(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_sqr"); if (!test_sqr(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mul"); if (!test_mul(out)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_div"); if (!test_div(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); + + message(out,"BN_div_word"); + if (!test_div_word(out)) goto err; + (void)BIO_flush(out); message(out,"BN_div_recp"); if (!test_div_recp(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mod"); if (!test_mod(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mod_mul"); if (!test_mod_mul(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mont"); if (!test_mont(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mod_exp"); if (!test_mod_exp(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mod_exp_mont_consttime"); if (!test_mod_exp_mont_consttime(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_exp"); if (!test_exp(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_kronecker"); if (!test_kron(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); message(out,"BN_mod_sqrt"); if (!test_sqrt(out,ctx)) goto err; - BIO_flush(out); + (void)BIO_flush(out); + + message(out,"BN_GF2m_add"); + if (!test_gf2m_add(out)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod"); + if (!test_gf2m_mod(out)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_mul"); + if (!test_gf2m_mod_mul(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_sqr"); + if (!test_gf2m_mod_sqr(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_inv"); + if (!test_gf2m_mod_inv(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_div"); + if (!test_gf2m_mod_div(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_exp"); + if (!test_gf2m_mod_exp(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_sqrt"); + if (!test_gf2m_mod_sqrt(out,ctx)) goto err; + (void)BIO_flush(out); + + message(out,"BN_GF2m_mod_solve_quad"); + if (!test_gf2m_mod_solve_quad(out,ctx)) goto err; + (void)BIO_flush(out); BN_CTX_free(ctx); BIO_free(out); @@ -237,8 +306,8 @@ int main(int argc, char *argv[]) EXIT(0); err: BIO_puts(out,"1\n"); /* make sure the Perl script fed by bc notices - * the failure, see test_bn in test/Makefile */ - BIO_flush(out); + * the failure, see test_bn in test/Makefile.ssl*/ + (void)BIO_flush(out); ERR_load_crypto_strings(); ERR_print_errors_fp(stderr); EXIT(1); @@ -404,6 +473,78 @@ int test_div(BIO *bp, BN_CTX *ctx) return(1); } +static void print_word(BIO *bp,BN_ULONG w) + { +#ifdef SIXTY_FOUR_BIT + if (sizeof(w) > sizeof(unsigned long)) + { + unsigned long h=(unsigned long)(w>>32), + l=(unsigned long)(w); + + if (h) BIO_printf(bp,"%lX%08lX",h,l); + else BIO_printf(bp,"%lX",l); + return; + } +#endif + BIO_printf(bp,"%lX",w); + } + +int test_div_word(BIO *bp) + { + BIGNUM a,b; + BN_ULONG r,s; + int i; + + BN_init(&a); + BN_init(&b); + + for (i=0; ineg = rand_neg(); putc('\n', stderr); @@ -1023,6 +1741,7 @@ int test_kron(BIO *bp, BN_CTX *ctx) int test_sqrt(BIO *bp, BN_CTX *ctx) { + BN_GENCB cb; BIGNUM *a,*p,*r; int i, j; int ret = 0; @@ -1031,7 +1750,9 @@ int test_sqrt(BIO *bp, BN_CTX *ctx) p = BN_new(); r = BN_new(); if (a == NULL || p == NULL || r == NULL) goto err; - + + BN_GENCB_set(&cb, genprime_cb, NULL); + for (i = 0; i < 16; i++) { if (i < 8) @@ -1045,7 +1766,7 @@ int test_sqrt(BIO *bp, BN_CTX *ctx) if (!BN_set_word(a, 32)) goto err; if (!BN_set_word(r, 2*i + 1)) goto err; - if (!BN_generate_prime(p, 256, 0, a, r, genprime_cb, NULL)) goto err; + if (!BN_generate_prime_ex(p, 256, 0, a, r, &cb)) goto err; putc('\n', stderr); } p->neg = rand_neg(); diff --git a/src/lib/libcrypto/bn/exptest.c b/src/lib/libcrypto/bn/exptest.c index 28aaac2ac1..f598a07cf5 100644 --- a/src/lib/libcrypto/bn/exptest.c +++ b/src/lib/libcrypto/bn/exptest.c @@ -195,6 +195,9 @@ int main(int argc, char *argv[]) err: ERR_load_crypto_strings(); ERR_print_errors(out); +#ifdef OPENSSL_SYS_NETWARE + printf("ERROR\n"); +#endif EXIT(1); return(1); } -- cgit v1.2.3-55-g6feb