Remove some documentation for functions not in 1.0.x

A few functions in the recently added EVP_EncodeInit docs don't apply to
the 1.0.x branches.

Reviewed-by: Richard Levitte <levitte@openssl.org>

.cvsignore

@@ -1,22 +0,0 @@
-openssl.pc
-libcrypto.pc
-libssl.pc
-MINFO
-makefile.one
-tmp
-out
-outinc
-rehash.time
-testlog
-make.log
-maketest.log
-cctest
-cctest.c
-cctest.a
-*.flc
-semantic.cache
-Makefile
-*.dll*
-*.so*
-*.sl*
-*.dylib*

.gitignore

@@ -7,6 +7,7 @@
 .#*
 #*#
 *~
+/.dir-locals.el
 
 # Top level excludes
 /Makefile.bak

.travis-create-release.sh

@@ -0,0 +1,10 @@
+#! /bin/sh
+
+# $1 is expected to be $TRAVIS_OS_NAME
+
+if [ "$1" == osx ]; then
+    make -f Makefile.org \
+	 DISTTARVARS="NAME=_srcdist TAR_COMMAND='\$\$(TAR) \$\$(TARFLAGS) -s \"|^|\$\$(NAME)/|\" -T \$\$(TARFILE).list -cvf -' TARFLAGS='-n' TARFILE=_srcdist.tar" SHELL='sh -vx' dist
+else
+    make -f Makefile.org DISTTARVARS='TARFILE=_srcdist.tar NAME=_srcdist' SHELL='sh -v' dist
+fi

.travis.yml

@@ -0,0 +1,60 @@
+language: c
+
+addons:
+    apt_packages:
+        - binutils-mingw-w64
+        - gcc-mingw-w64
+
+os:
+    - linux
+    - osx
+
+compiler:
+    - clang
+    - gcc
+    - i686-w64-mingw32-gcc
+    - x86_64-w64-mingw32-gcc
+
+env:
+    - CONFIG_OPTS=""
+    - CONFIG_OPTS="shared"
+    - CONFIG_OPTS="-d --strict-warnings"
+
+matrix:
+    exclude:
+        - os: osx
+          compiler: i686-w64-mingw32-gcc
+        - os: osx
+          compiler: x86_64-w64-mingw32-gcc
+        - compiler: i686-w64-mingw32-gcc
+          env: CONFIG_OPTS="-d --strict-warnings"
+        - compiler: x86_64-w64-mingw32-gcc
+          env: CONFIG_OPTS="-d --strict-warnings"
+
+before_script:
+    - sh .travis-create-release.sh $TRAVIS_OS_NAME
+    - tar -xvzf _srcdist.tar.gz
+    - cd _srcdist
+    - if [ "$CC" == i686-w64-mingw32-gcc ]; then
+          export CROSS_COMPILE=${CC%%gcc}; unset CC;
+          ./Configure mingw $CONFIG_OPTS;
+      elif [ "$CC" == x86_64-w64-mingw32-gcc ]; then
+          export CROSS_COMPILE=${CC%%gcc}; unset CC;
+          ./Configure mingw64 $CONFIG_OPTS;
+      else
+          if [ "$CC" == gcc ]; then
+              export CONFIG_OPTS="$CONFIG_OPTS -Wno-error=shadow";
+          fi;
+          ./config $CONFIG_OPTS;
+      fi
+    - cd ..
+
+script:
+    - cd _srcdist
+    - make
+    - if [ -z "$CROSS_COMPILE" ]; then make test; fi
+    - cd ..
+
+notifications:
+    email:
+        - openssl-commits@openssl.org

ACKNOWLEDGMENTS

@@ -1,30 +1,2 @@
-The OpenSSL project depends on volunteer efforts and financial support from
-the end user community. That support comes in the form of donations and paid
-sponsorships, software support contracts, paid consulting services
-and commissioned software development.
-
-Since all these activities support the continued development and improvement
-of OpenSSL we consider all these clients and customers as sponsors of the
-OpenSSL project.
-
-We would like to identify and thank the following such sponsors for their past
-or current significant support of the OpenSSL project:
-
-Major support:
-
-	Qualys		http://www.qualys.com/
-
-Very significant support:
-
-	OpenGear:	http://www.opengear.com/
-
-Significant support:
-
-	PSW Group:	http://www.psw.net/
-	Acano Ltd.	http://acano.com/
-
-Please note that we ask permission to identify sponsors and that some sponsors
-we consider eligible for inclusion here have requested to remain anonymous.
-
-Additional sponsorship or financial support is always welcome: for more
-information please contact the OpenSSL Software Foundation.
+Please https://www.openssl.org/community/thanks.html for the current
+acknowledgements.

CHANGES

@@ -2,6 +2,289 @@
  OpenSSL CHANGES
  _______________
 
+ Changes between 1.0.2g and 1.0.2h [xx XXX xxxx]
+
+  *) Modify behavior of ALPN to invoke callback after SNI/servername
+     callback, such that updates to the SSL_CTX affect ALPN.
+     [Todd Short]
+
+  *) Remove LOW from the DEFAULT cipher list.  This removes singles DES from the
+     default.
+     [Kurt Roeckx]
+
+  *) Only remove the SSLv2 methods with the no-ssl2-method option. When the
+     methods are enabled and ssl2 is disabled the methods return NULL.
+     [Kurt Roeckx]
+
+ Changes between 1.0.2f and 1.0.2g [1 Mar 2016]
+
+  * Disable weak ciphers in SSLv3 and up in default builds of OpenSSL.
+    Builds that are not configured with "enable-weak-ssl-ciphers" will not
+    provide any "EXPORT" or "LOW" strength ciphers.
+    [Viktor Dukhovni]
+
+  * Disable SSLv2 default build, default negotiation and weak ciphers.  SSLv2
+    is by default disabled at build-time.  Builds that are not configured with
+    "enable-ssl2" will not support SSLv2.  Even if "enable-ssl2" is used,
+    users who want to negotiate SSLv2 via the version-flexible SSLv23_method()
+    will need to explicitly call either of:
+
+        SSL_CTX_clear_options(ctx, SSL_OP_NO_SSLv2);
+    or
+        SSL_clear_options(ssl, SSL_OP_NO_SSLv2);
+
+    as appropriate.  Even if either of those is used, or the application
+    explicitly uses the version-specific SSLv2_method() or its client and
+    server variants, SSLv2 ciphers vulnerable to exhaustive search key
+    recovery have been removed.  Specifically, the SSLv2 40-bit EXPORT
+    ciphers, and SSLv2 56-bit DES are no longer available.
+    (CVE-2016-0800)
+    [Viktor Dukhovni]
+
+  *) Fix a double-free in DSA code
+
+     A double free bug was discovered when OpenSSL parses malformed DSA private
+     keys and could lead to a DoS attack or memory corruption for applications
+     that receive DSA private keys from untrusted sources.  This scenario is
+     considered rare.
+
+     This issue was reported to OpenSSL by Adam Langley(Google/BoringSSL) using
+     libFuzzer.
+     (CVE-2016-0705)
+     [Stephen Henson]
+
+  *) Disable SRP fake user seed to address a server memory leak.
+
+     Add a new method SRP_VBASE_get1_by_user that handles the seed properly.
+
+     SRP_VBASE_get_by_user had inconsistent memory management behaviour.
+     In order to fix an unavoidable memory leak, SRP_VBASE_get_by_user
+     was changed to ignore the "fake user" SRP seed, even if the seed
+     is configured.
+
+     Users should use SRP_VBASE_get1_by_user instead. Note that in
+     SRP_VBASE_get1_by_user, caller must free the returned value. Note
+     also that even though configuring the SRP seed attempts to hide
+     invalid usernames by continuing the handshake with fake
+     credentials, this behaviour is not constant time and no strong
+     guarantees are made that the handshake is indistinguishable from
+     that of a valid user.
+     (CVE-2016-0798)
+     [Emilia Käsper]
+
+  *) Fix BN_hex2bn/BN_dec2bn NULL pointer deref/heap corruption
+
+     In the BN_hex2bn function the number of hex digits is calculated using an
+     int value |i|. Later |bn_expand| is called with a value of |i * 4|. For
+     large values of |i| this can result in |bn_expand| not allocating any
+     memory because |i * 4| is negative. This can leave the internal BIGNUM data
+     field as NULL leading to a subsequent NULL ptr deref. For very large values
+     of |i|, the calculation |i * 4| could be a positive value smaller than |i|.
+     In this case memory is allocated to the internal BIGNUM data field, but it
+     is insufficiently sized leading to heap corruption. A similar issue exists
+     in BN_dec2bn. This could have security consequences if BN_hex2bn/BN_dec2bn
+     is ever called by user applications with very large untrusted hex/dec data.
+     This is anticipated to be a rare occurrence.
+
+     All OpenSSL internal usage of these functions use data that is not expected
+     to be untrusted, e.g. config file data or application command line
+     arguments. If user developed applications generate config file data based
+     on untrusted data then it is possible that this could also lead to security
+     consequences. This is also anticipated to be rare.
+
+     This issue was reported to OpenSSL by Guido Vranken.
+     (CVE-2016-0797)
+     [Matt Caswell]
+
+  *) Fix memory issues in BIO_*printf functions
+
+     The internal |fmtstr| function used in processing a "%s" format string in
+     the BIO_*printf functions could overflow while calculating the length of a
+     string and cause an OOB read when printing very long strings.
+
+     Additionally the internal |doapr_outch| function can attempt to write to an
+     OOB memory location (at an offset from the NULL pointer) in the event of a
+     memory allocation failure. In 1.0.2 and below this could be caused where
+     the size of a buffer to be allocated is greater than INT_MAX. E.g. this
+     could be in processing a very long "%s" format string. Memory leaks can
+     also occur.
+
+     The first issue may mask the second issue dependent on compiler behaviour.
+     These problems could enable attacks where large amounts of untrusted data
+     is passed to the BIO_*printf functions. If applications use these functions
+     in this way then they could be vulnerable. OpenSSL itself uses these
+     functions when printing out human-readable dumps of ASN.1 data. Therefore
+     applications that print this data could be vulnerable if the data is from
+     untrusted sources. OpenSSL command line applications could also be
+     vulnerable where they print out ASN.1 data, or if untrusted data is passed
+     as command line arguments.
+
+     Libssl is not considered directly vulnerable. Additionally certificates etc
+     received via remote connections via libssl are also unlikely to be able to
+     trigger these issues because of message size limits enforced within libssl.
+
+     This issue was reported to OpenSSL Guido Vranken.
+     (CVE-2016-0799)
+     [Matt Caswell]
+
+  *) Side channel attack on modular exponentiation
+
+     A side-channel attack was found which makes use of cache-bank conflicts on
+     the Intel Sandy-Bridge microarchitecture which could lead to the recovery
+     of RSA keys.  The ability to exploit this issue is limited as it relies on
+     an attacker who has control of code in a thread running on the same
+     hyper-threaded core as the victim thread which is performing decryptions.
+
+     This issue was reported to OpenSSL by Yuval Yarom, The University of
+     Adelaide and NICTA, Daniel Genkin, Technion and Tel Aviv University, and
+     Nadia Heninger, University of Pennsylvania with more information at
+     http://cachebleed.info.
+     (CVE-2016-0702)
+     [Andy Polyakov]
+
+  *) Change the req app to generate a 2048-bit RSA/DSA key by default,
+     if no keysize is specified with default_bits. This fixes an
+     omission in an earlier change that changed all RSA/DSA key generation
+     apps to use 2048 bits by default.
+     [Emilia Käsper]
+
+ Changes between 1.0.2e and 1.0.2f [28 Jan 2016]
+
+  *) DH small subgroups
+
+     Historically OpenSSL only ever generated DH parameters based on "safe"
+     primes. More recently (in version 1.0.2) support was provided for
+     generating X9.42 style parameter files such as those required for RFC 5114
+     support. The primes used in such files may not be "safe". Where an
+     application is using DH configured with parameters based on primes that are
+     not "safe" then an attacker could use this fact to find a peer's private
+     DH exponent. This attack requires that the attacker complete multiple
+     handshakes in which the peer uses the same private DH exponent. For example
+     this could be used to discover a TLS server's private DH exponent if it's
+     reusing the private DH exponent or it's using a static DH ciphersuite.
+
+     OpenSSL provides the option SSL_OP_SINGLE_DH_USE for ephemeral DH (DHE) in
+     TLS. It is not on by default. If the option is not set then the server
+     reuses the same private DH exponent for the life of the server process and
+     would be vulnerable to this attack. It is believed that many popular
+     applications do set this option and would therefore not be at risk.
+
+     The fix for this issue adds an additional check where a "q" parameter is
+     available (as is the case in X9.42 based parameters). This detects the
+     only known attack, and is the only possible defense for static DH
+     ciphersuites. This could have some performance impact.
+
+     Additionally the SSL_OP_SINGLE_DH_USE option has been switched on by
+     default and cannot be disabled. This could have some performance impact.
+
+     This issue was reported to OpenSSL by Antonio Sanso (Adobe).
+     (CVE-2016-0701)
+     [Matt Caswell]
+
+  *) SSLv2 doesn't block disabled ciphers
+
+     A malicious client can negotiate SSLv2 ciphers that have been disabled on
+     the server and complete SSLv2 handshakes even if all SSLv2 ciphers have
+     been disabled, provided that the SSLv2 protocol was not also disabled via
+     SSL_OP_NO_SSLv2.
+
+     This issue was reported to OpenSSL on 26th December 2015 by Nimrod Aviram
+     and Sebastian Schinzel.
+     (CVE-2015-3197)
+     [Viktor Dukhovni]
+
+  *) Reject DH handshakes with parameters shorter than 1024 bits.
+     [Kurt Roeckx]
+
+ Changes between 1.0.2d and 1.0.2e [3 Dec 2015]
+
+  *) BN_mod_exp may produce incorrect results on x86_64
+
+     There is a carry propagating bug in the x86_64 Montgomery squaring
+     procedure. No EC algorithms are affected. Analysis suggests that attacks
+     against RSA and DSA as a result of this defect would be very difficult to
+     perform and are not believed likely. Attacks against DH are considered just
+     feasible (although very difficult) because most of the work necessary to
+     deduce information about a private key may be performed offline. The amount
+     of resources required for such an attack would be very significant and
+     likely only accessible to a limited number of attackers. An attacker would
+     additionally need online access to an unpatched system using the target
+     private key in a scenario with persistent DH parameters and a private
+     key that is shared between multiple clients. For example this can occur by
+     default in OpenSSL DHE based SSL/TLS ciphersuites.
+
+     This issue was reported to OpenSSL by Hanno Böck.
+     (CVE-2015-3193)
+     [Andy Polyakov]
+
+  *) Certificate verify crash with missing PSS parameter
+
+     The signature verification routines will crash with a NULL pointer
+     dereference if presented with an ASN.1 signature using the RSA PSS
+     algorithm and absent mask generation function parameter. Since these
+     routines are used to verify certificate signature algorithms this can be
+     used to crash any certificate verification operation and exploited in a
+     DoS attack. Any application which performs certificate verification is
+     vulnerable including OpenSSL clients and servers which enable client
+     authentication.
+
+     This issue was reported to OpenSSL by Loïc Jonas Etienne (Qnective AG).
+     (CVE-2015-3194)
+     [Stephen Henson]
+
+  *) X509_ATTRIBUTE memory leak
+
+     When presented with a malformed X509_ATTRIBUTE structure OpenSSL will leak
+     memory. This structure is used by the PKCS#7 and CMS routines so any
+     application which reads PKCS#7 or CMS data from untrusted sources is
+     affected. SSL/TLS is not affected.
+
+     This issue was reported to OpenSSL by Adam Langley (Google/BoringSSL) using
+     libFuzzer.
+     (CVE-2015-3195)
+     [Stephen Henson]
+
+  *) Rewrite EVP_DecodeUpdate (base64 decoding) to fix several bugs.
+     This changes the decoding behaviour for some invalid messages,
+     though the change is mostly in the more lenient direction, and
+     legacy behaviour is preserved as much as possible.
+     [Emilia Käsper]
+
+  *) In DSA_generate_parameters_ex, if the provided seed is too short,
+     use a random seed, as already documented.
+     [Rich Salz and Ismo Puustinen <ismo.puustinen@intel.com>]
+
+ Changes between 1.0.2c and 1.0.2d [9 Jul 2015]
+
+  *) Alternate chains certificate forgery
+
+     During certificate verfification, OpenSSL will attempt to find an
+     alternative certificate chain if the first attempt to build such a chain
+     fails. An error in the implementation of this logic can mean that an
+     attacker could cause certain checks on untrusted certificates to be
+     bypassed, such as the CA flag, enabling them to use a valid leaf
+     certificate to act as a CA and "issue" an invalid certificate.
+
+     This issue was reported to OpenSSL by Adam Langley/David Benjamin
+     (Google/BoringSSL).
+     (CVE-2015-1793)
+     [Matt Caswell]
+
+  *) Race condition handling PSK identify hint
+
+     If PSK identity hints are received by a multi-threaded client then
+     the values are wrongly updated in the parent SSL_CTX structure. This can
+     result in a race condition potentially leading to a double free of the
+     identify hint data.
+     (CVE-2015-3196)
+     [Stephen Henson]
+
+ Changes between 1.0.2b and 1.0.2c [12 Jun 2015]
+
+  *) Fix HMAC ABI incompatibility. The previous version introduced an ABI
+     incompatibility in the handling of HMAC. The previous ABI has now been
+     restored.
+
  Changes between 1.0.2a and 1.0.2b [11 Jun 2015]
 
   *) Malformed ECParameters causes infinite loop
@@ -34,9 +317,9 @@
      callbacks.
 
      This issue was reported to OpenSSL by Robert Swiecki (Google), and
-     independently by Hanno B<EFBFBD>ck.
+     independently by Hanno Böck.
      (CVE-2015-1789)
-     [Emilia K<EFBFBD>sper]
+     [Emilia Käsper]
 
   *) PKCS7 crash with missing EnvelopedContent
 
@@ -50,7 +333,7 @@
 
      This issue was reported to OpenSSL by Michal Zalewski (Google).
      (CVE-2015-1790)
-     [Emilia K<EFBFBD>sper]
+     [Emilia Käsper]
 
   *) CMS verify infinite loop with unknown hash function
 
@@ -180,7 +463,7 @@
 
      This issue was reported to OpenSSL by Michal Zalewski (Google).
      (CVE-2015-0289)
-     [Emilia K<EFBFBD>sper]
+     [Emilia Käsper]
 
   *) DoS via reachable assert in SSLv2 servers fix
 
@@ -188,10 +471,10 @@
      servers that both support SSLv2 and enable export cipher suites by sending
      a specially crafted SSLv2 CLIENT-MASTER-KEY message.
 
-     This issue was discovered by Sean Burford (Google) and Emilia K<EFBFBD>sper
+     This issue was discovered by Sean Burford (Google) and Emilia Käsper
      (OpenSSL development team).
      (CVE-2015-0293)
-     [Emilia K<EFBFBD>sper]
+     [Emilia Käsper]
 
   *) Empty CKE with client auth and DHE fix
 
@@ -251,6 +534,10 @@
 
  Changes between 1.0.1l and 1.0.2 [22 Jan 2015]
 
+  *) Change RSA and DH/DSA key generation apps to generate 2048-bit
+     keys by default.
+     [Kurt Roeckx]
+
   *) Facilitate "universal" ARM builds targeting range of ARM ISAs, e.g.
      ARMv5 through ARMv8, as opposite to "locking" it to single one.
      So far those who have to target multiple plaforms would compromise
@@ -696,12 +983,12 @@
       version does not match the session's version. Resuming with a different
       version, while not strictly forbidden by the RFC, is of questionable
       sanity and breaks all known clients.
-      [David Benjamin, Emilia K<EFBFBD>sper]
+      [David Benjamin, Emilia Käsper]
 
    *) Tighten handling of the ChangeCipherSpec (CCS) message: reject
       early CCS messages during renegotiation. (Note that because
       renegotiation is encrypted, this early CCS was not exploitable.)
-      [Emilia K<EFBFBD>sper]
+      [Emilia Käsper]
 
    *) Tighten client-side session ticket handling during renegotiation:
       ensure that the client only accepts a session ticket if the server sends
@@ -712,7 +999,7 @@
       Similarly, ensure that the client requires a session ticket if one
       was advertised in the ServerHello. Previously, a TLS client would
       ignore a missing NewSessionTicket message.
-      [Emilia K<EFBFBD>sper]
+      [Emilia Käsper]
 
  Changes between 1.0.1i and 1.0.1j [15 Oct 2014]
 
@@ -792,10 +1079,10 @@
      with a null pointer dereference (read) by specifying an anonymous (EC)DH
      ciphersuite and sending carefully crafted handshake messages.
 
-     Thanks to Felix Gr<EFBFBD>bert (Google) for discovering and researching this
+     Thanks to Felix Gröbert (Google) for discovering and researching this
      issue.
      (CVE-2014-3510)
-     [Emilia K<EFBFBD>sper]
+     [Emilia Käsper]
 
   *) By sending carefully crafted DTLS packets an attacker could cause openssl
      to leak memory. This can be exploited through a Denial of Service attack.
@@ -832,7 +1119,7 @@
      properly negotiated with the client. This can be exploited through a
      Denial of Service attack.
 
-     Thanks to Joonas Kuorilehto and Riku Hietam<EFBFBD>ki (Codenomicon) for
+     Thanks to Joonas Kuorilehto and Riku Hietamäki (Codenomicon) for
      discovering and researching this issue.
      (CVE-2014-5139)
      [Steve Henson]
@@ -844,7 +1131,7 @@
 
      Thanks to Ivan Fratric (Google) for discovering this issue.
      (CVE-2014-3508)
-     [Emilia K<EFBFBD>sper, and Steve Henson]
+     [Emilia Käsper, and Steve Henson]
 
   *) Fix ec_GFp_simple_points_make_affine (thus, EC_POINTs_mul etc.)
      for corner cases. (Certain input points at infinity could lead to
@@ -874,22 +1161,22 @@
      client or server. This is potentially exploitable to run arbitrary
      code on a vulnerable client or server.
 
-     Thanks to J<EFBFBD>ri Aedla for reporting this issue. (CVE-2014-0195)
-     [J<EFBFBD>ri Aedla, Steve Henson]
+     Thanks to Jüri Aedla for reporting this issue. (CVE-2014-0195)
+     [Jüri Aedla, Steve Henson]
 
   *) Fix bug in TLS code where clients enable anonymous ECDH ciphersuites
      are subject to a denial of service attack.
 
-     Thanks to Felix Gr<EFBFBD>bert and Ivan Fratric at Google for discovering
+     Thanks to Felix Gröbert and Ivan Fratric at Google for discovering
      this issue. (CVE-2014-3470)
-     [Felix Gr<EFBFBD>bert, Ivan Fratric, Steve Henson]
+     [Felix Gröbert, Ivan Fratric, Steve Henson]
 
   *) Harmonize version and its documentation. -f flag is used to display
      compilation flags.
      [mancha <mancha1@zoho.com>]
 
   *) Fix eckey_priv_encode so it immediately returns an error upon a failure
-     in i2d_ECPrivateKey.
+     in i2d_ECPrivateKey.  Thanks to Ted Unangst for feedback on this issue.
      [mancha <mancha1@zoho.com>]
 
   *) Fix some double frees. These are not thought to be exploitable.
@@ -961,9 +1248,9 @@
      Thanks go to Nadhem Alfardan and Kenny Paterson of the Information
      Security Group at Royal Holloway, University of London
      (www.isg.rhul.ac.uk) for discovering this flaw and Adam Langley and
-     Emilia K<EFBFBD>sper for the initial patch.
+     Emilia Käsper for the initial patch.
      (CVE-2013-0169)
-     [Emilia K<EFBFBD>sper, Adam Langley, Ben Laurie, Andy Polyakov, Steve Henson]
+     [Emilia Käsper, Adam Langley, Ben Laurie, Andy Polyakov, Steve Henson]
 
   *) Fix flaw in AESNI handling of TLS 1.2 and 1.1 records for CBC mode
      ciphersuites which can be exploited in a denial of service attack.
@@ -1138,7 +1425,7 @@
      EC_GROUP_new_by_curve_name() will automatically use these (while
      EC_GROUP_new_curve_GFp() currently prefers the more flexible
      implementations).
-     [Emilia K<EFBFBD>sper, Adam Langley, Bodo Moeller (Google)]
+     [Emilia Käsper, Adam Langley, Bodo Moeller (Google)]
 
   *) Use type ossl_ssize_t instad of ssize_t which isn't available on
      all platforms. Move ssize_t definition from e_os.h to the public
@@ -1414,7 +1701,7 @@
      [Adam Langley (Google)]
 
   *) Fix spurious failures in ecdsatest.c.
-     [Emilia K<EFBFBD>sper (Google)]
+     [Emilia Käsper (Google)]
 
   *) Fix the BIO_f_buffer() implementation (which was mixing different
      interpretations of the '..._len' fields).
@@ -1428,7 +1715,7 @@
      lock to call BN_BLINDING_invert_ex, and avoids one use of
      BN_BLINDING_update for each BN_BLINDING structure (previously,
      the last update always remained unused).
-     [Emilia K<EFBFBD>sper (Google)]
+     [Emilia Käsper (Google)]
 
   *) In ssl3_clear, preserve s3->init_extra along with s3->rbuf.
      [Bob Buckholz (Google)]
@@ -2237,7 +2524,7 @@
 
   *) Add RFC 3161 compliant time stamp request creation, response generation
      and response verification functionality.
-     [Zolt<EFBFBD>n Gl<EFBFBD>zik <zglozik@opentsa.org>, The OpenTSA Project]
+     [Zoltán Glózik <zglozik@opentsa.org>, The OpenTSA Project]
 
   *) Add initial support for TLS extensions, specifically for the server_name
      extension so far.  The SSL_SESSION, SSL_CTX, and SSL data structures now
@@ -3405,7 +3692,7 @@
 
   *) BN_CTX_get() should return zero-valued bignums, providing the same
      initialised value as BN_new().
-     [Geoff Thorpe, suggested by Ulf M<EFBFBD>ller]
+     [Geoff Thorpe, suggested by Ulf Möller]
 
   *) Support for inhibitAnyPolicy certificate extension.
      [Steve Henson]
@@ -3424,7 +3711,7 @@
      some point, these tighter rules will become openssl's default to improve
      maintainability, though the assert()s and other overheads will remain only
      in debugging configurations. See bn.h for more details.
-     [Geoff Thorpe, Nils Larsch, Ulf M<EFBFBD>ller]
+     [Geoff Thorpe, Nils Larsch, Ulf Möller]
 
   *) BN_CTX_init() has been deprecated, as BN_CTX is an opaque structure
      that can only be obtained through BN_CTX_new() (which implicitly
@@ -3491,7 +3778,7 @@
      [Douglas Stebila (Sun Microsystems Laboratories)]
 
   *) Add the possibility to load symbols globally with DSO.
-     [G<EFBFBD>tz Babin-Ebell <babin-ebell@trustcenter.de> via Richard Levitte]
+     [Götz Babin-Ebell <babin-ebell@trustcenter.de> via Richard Levitte]
 
   *) Add the functions ERR_set_mark() and ERR_pop_to_mark() for better
      control of the error stack.
@@ -4206,7 +4493,7 @@
      [Steve Henson]
 
   *) Undo Cygwin change.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Added support for proxy certificates according to RFC 3820.
      Because they may be a security thread to unaware applications,
@@ -4239,11 +4526,11 @@
      [Stephen Henson, reported by UK NISCC]
 
   *) Use Windows randomness collection on Cygwin.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix hang in EGD/PRNGD query when communication socket is closed
      prematurely by EGD/PRNGD.
-     [Darren Tucker <dtucker@zip.com.au> via Lutz J<EFBFBD>nicke, resolves #1014]
+     [Darren Tucker <dtucker@zip.com.au> via Lutz Jänicke, resolves #1014]
 
   *) Prompt for pass phrases when appropriate for PKCS12 input format.
      [Steve Henson]
@@ -4705,7 +4992,7 @@
      pointers passed to them whenever necessary. Otherwise it is possible
      the caller may have overwritten (or deallocated) the original string
      data when a later ENGINE operation tries to use the stored values.
-     [G<EFBFBD>tz Babin-Ebell <babinebell@trustcenter.de>]
+     [Götz Babin-Ebell <babinebell@trustcenter.de>]
 
   *) Improve diagnostics in file reading and command-line digests.
      [Ben Laurie aided and abetted by Solar Designer <solar@openwall.com>]
@@ -6810,7 +7097,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) BN_sqr() bug fix.
-     [Ulf M<EFBFBD>ller, reported by Jim Ellis <jim.ellis@cavium.com>]
+     [Ulf Möller, reported by Jim Ellis <jim.ellis@cavium.com>]
 
   *) Rabin-Miller test analyses assume uniformly distributed witnesses,
      so use BN_pseudo_rand_range() instead of using BN_pseudo_rand()
@@ -6970,7 +7257,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) Fix OAEP check.
-     [Ulf M<EFBFBD>ller, Bodo M<EFBFBD>ller]
+     [Ulf Möller, Bodo Möller]
 
   *) The countermeasure against Bleichbacher's attack on PKCS #1 v1.5
      RSA encryption was accidentally removed in s3_srvr.c in OpenSSL 0.9.5
@@ -7232,10 +7519,10 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) Use better test patterns in bntest.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) rand_win.c fix for Borland C.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
  
   *) BN_rshift bugfix for n == 0.
      [Bodo Moeller]
@@ -7380,14 +7667,14 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) New BIO_shutdown_wr macro, which invokes the BIO_C_SHUTDOWN_WR
      BIO_ctrl (for BIO pairs).
-     [Bodo M<EFBFBD>ller]
+     [Bodo Möller]
 
   *) Add DSO method for VMS.
      [Richard Levitte]
 
   *) Bug fix: Montgomery multiplication could produce results with the
      wrong sign.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add RPM specification openssl.spec and modify it to build three
      packages.  The default package contains applications, application
@@ -7405,7 +7692,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) Don't set the two most significant bits to one when generating a
      random number < q in the DSA library.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) New SSL API mode 'SSL_MODE_AUTO_RETRY'.  This disables the default
      behaviour that SSL_read may result in SSL_ERROR_WANT_READ (even if
@@ -7671,7 +7958,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
   *) Randomness polling function for Win9x, as described in:
      Peter Gutmann, Software Generation of Practically Strong
      Random Numbers.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix so PRNG is seeded in req if using an already existing
      DSA key.
@@ -7891,7 +8178,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) Eliminate non-ANSI declarations in crypto.h and stack.h.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix for SSL server purpose checking. Server checking was
      rejecting certificates which had extended key usage present
@@ -7923,7 +8210,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) Bugfix for linux-elf makefile.one.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) RSA_get_default_method() will now cause a default
      RSA_METHOD to be chosen if one doesn't exist already.
@@ -8012,7 +8299,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) des_quad_cksum() byte order bug fix.
-     [Ulf M<EFBFBD>ller, using the problem description in krb4-0.9.7, where
+     [Ulf Möller, using the problem description in krb4-0.9.7, where
       the solution is attributed to Derrick J Brashear <shadow@DEMENTIA.ORG>]
 
   *) Fix so V_ASN1_APP_CHOOSE works again: however its use is strongly
@@ -8113,7 +8400,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Rolf Haberrecker <rolf@suse.de>]
 
   *) Assembler module support for Mingw32.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Shared library support for HPUX (in shlib/).
      [Lutz Jaenicke <Lutz.Jaenicke@aet.TU-Cottbus.DE> and Anonymous]
@@ -8132,7 +8419,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) BN_mul bugfix: In bn_mul_part_recursion() only the a>a[n] && b>b[n]
      case was implemented. This caused BN_div_recp() to fail occasionally.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add an optional second argument to the set_label() in the perl
      assembly language builder. If this argument exists and is set
@@ -8162,14 +8449,14 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) Fix potential buffer overrun problem in BIO_printf().
-     [Ulf M<EFBFBD>ller, using public domain code by Patrick Powell; problem
+     [Ulf Möller, using public domain code by Patrick Powell; problem
       pointed out by David Sacerdote <das33@cornell.edu>]
 
   *) Support EGD <http://www.lothar.com/tech/crypto/>.  New functions
      RAND_egd() and RAND_status().  In the command line application,
      the EGD socket can be specified like a seed file using RANDFILE
      or -rand.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Allow the string CERTIFICATE to be tolerated in PKCS#7 structures.
      Some CAs (e.g. Verisign) distribute certificates in this form.
@@ -8202,7 +8489,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
         #define OPENSSL_ALGORITHM_DEFINES
         #include <openssl/opensslconf.h>
      defines all pertinent NO_<algo> symbols, such as NO_IDEA, NO_RSA, etc.
-     [Richard Levitte, Ulf and Bodo M<EFBFBD>ller]
+     [Richard Levitte, Ulf and Bodo Möller]
 
   *) Bugfix: Tolerate fragmentation and interleaving in the SSL 3/TLS
      record layer.
@@ -8253,17 +8540,17 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) Bug fix for BN_div_recp() for numerators with an even number of
      bits.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) More tests in bntest.c, and changed test_bn output.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) ./config recognizes MacOS X now.
      [Andy Polyakov]
 
   *) Bug fix for BN_div() when the first words of num and divsor are
      equal (it gave wrong results if (rem=(n1-q*d0)&BN_MASK2) < d0).
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add support for various broken PKCS#8 formats, and command line
      options to produce them.
@@ -8271,11 +8558,11 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) New functions BN_CTX_start(), BN_CTX_get() and BT_CTX_end() to
      get temporary BIGNUMs from a BN_CTX.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Correct return values in BN_mod_exp_mont() and BN_mod_exp2_mont()
      for p == 0.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Change the SSLeay_add_all_*() functions to OpenSSL_add_all_*() and
      include a #define from the old name to the new. The original intent
@@ -8299,7 +8586,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) Source code cleanups: use const where appropriate, eliminate casts,
      use void * instead of char * in lhash.
-     [Ulf M<EFBFBD>ller] 
+     [Ulf Möller] 
 
   *) Bugfix: ssl3_send_server_key_exchange was not restartable
      (the state was not changed to SSL3_ST_SW_KEY_EXCH_B, and because of
@@ -8344,13 +8631,13 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) New function BN_pseudo_rand().
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Clean up BN_mod_mul_montgomery(): replace the broken (and unreadable)
      bignum version of BN_from_montgomery() with the working code from
      SSLeay 0.9.0 (the word based version is faster anyway), and clean up
      the comments.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Avoid a race condition in s2_clnt.c (function get_server_hello) that
      made it impossible to use the same SSL_SESSION data structure in
@@ -8360,25 +8647,25 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
   *) The return value of RAND_load_file() no longer counts bytes obtained
      by stat().  RAND_load_file(..., -1) is new and uses the complete file
      to seed the PRNG (previously an explicit byte count was required).
-     [Ulf M<EFBFBD>ller, Bodo M<EFBFBD>ller]
+     [Ulf Möller, Bodo Möller]
 
   *) Clean up CRYPTO_EX_DATA functions, some of these didn't have prototypes
      used (char *) instead of (void *) and had casts all over the place.
      [Steve Henson]
 
   *) Make BN_generate_prime() return NULL on error if ret!=NULL.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Retain source code compatibility for BN_prime_checks macro:
      BN_is_prime(..., BN_prime_checks, ...) now uses
      BN_prime_checks_for_size to determine the appropriate number of
      Rabin-Miller iterations.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Diffie-Hellman uses "safe" primes: DH_check() return code renamed to
      DH_CHECK_P_NOT_SAFE_PRIME.
      (Check if this is true? OpenPGP calls them "strong".)
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Merge the functionality of "dh" and "gendh" programs into a new program
      "dhparam". The old programs are retained for now but will handle DH keys
@@ -8434,7 +8721,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
   *) Add missing #ifndefs that caused missing symbols when building libssl
      as a shared library without RSA.  Use #ifndef NO_SSL2 instead of
      NO_RSA in ssl/s2*.c. 
-     [Kris Kennaway <kris@hub.freebsd.org>, modified by Ulf M<EFBFBD>ller]
+     [Kris Kennaway <kris@hub.freebsd.org>, modified by Ulf Möller]
 
   *) Precautions against using the PRNG uninitialized: RAND_bytes() now
      has a return value which indicates the quality of the random data
@@ -8443,7 +8730,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      guaranteed to be unique but not unpredictable. RAND_add is like
      RAND_seed, but takes an extra argument for an entropy estimate
      (RAND_seed always assumes full entropy).
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Do more iterations of Rabin-Miller probable prime test (specifically,
      3 for 1024-bit primes, 6 for 512-bit primes, 12 for 256-bit primes
@@ -8473,7 +8760,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) Honor the no-xxx Configure options when creating .DEF files.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add PKCS#10 attributes to field table: challengePassword, 
      unstructuredName and unstructuredAddress. These are taken from
@@ -9307,7 +9594,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) More DES library cleanups: remove references to srand/rand and
      delete an unused file.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add support for the the free Netwide assembler (NASM) under Win32,
      since not many people have MASM (ml) and it can be hard to obtain.
@@ -9396,7 +9683,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      worked.
 
   *) Fix problems with no-hmac etc.
-     [Ulf M<EFBFBD>ller, pointed out by Brian Wellington <bwelling@tislabs.com>]
+     [Ulf Möller, pointed out by Brian Wellington <bwelling@tislabs.com>]
 
   *) New functions RSA_get_default_method(), RSA_set_method() and
      RSA_get_method(). These allows replacement of RSA_METHODs without having
@@ -9513,7 +9800,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Ben Laurie]
 
   *) DES library cleanups.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add support for PKCS#5 v2.0 PBE algorithms. This will permit PKCS#8 to be
      used with any cipher unlike PKCS#5 v1.5 which can at most handle 64 bit
@@ -9556,7 +9843,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Christian Forster <fo@hawo.stw.uni-erlangen.de>]
 
   *) config now generates no-xxx options for missing ciphers.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Support the EBCDIC character set (work in progress).
      File ebcdic.c not yet included because it has a different license.
@@ -9669,7 +9956,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) Move openssl.cnf out of lib/.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix various things to let OpenSSL even pass ``egcc -pipe -O2 -Wall
      -Wshadow -Wpointer-arith -Wcast-align -Wmissing-prototypes
@@ -9726,10 +10013,10 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Ben Laurie]
 
   *) Support Borland C++ builder.
-     [Janez Jere <jj@void.si>, modified by Ulf M<EFBFBD>ller]
+     [Janez Jere <jj@void.si>, modified by Ulf Möller]
 
   *) Support Mingw32.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) SHA-1 cleanups and performance enhancements.
      [Andy Polyakov <appro@fy.chalmers.se>]
@@ -9738,7 +10025,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Andy Polyakov <appro@fy.chalmers.se>]
 
   *) Accept any -xxx and +xxx compiler options in Configure.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Update HPUX configuration.
      [Anonymous]
@@ -9771,7 +10058,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Bodo Moeller]
 
   *) OAEP decoding bug fix.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Support INSTALL_PREFIX for package builders, as proposed by
      David Harris.
@@ -9794,21 +10081,21 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Niels Poppe <niels@netbox.org>]
 
   *) New Configure option no-<cipher> (rsa, idea, rc5, ...).
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Add the PKCS#12 API documentation to openssl.txt. Preliminary support for
      extension adding in x509 utility.
      [Steve Henson]
 
   *) Remove NOPROTO sections and error code comments.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Partial rewrite of the DEF file generator to now parse the ANSI
      prototypes.
      [Steve Henson]
 
   *) New Configure options --prefix=DIR and --openssldir=DIR.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Complete rewrite of the error code script(s). It is all now handled
      by one script at the top level which handles error code gathering,
@@ -9837,7 +10124,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) Move the autogenerated header file parts to crypto/opensslconf.h.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix new 56-bit DES export ciphersuites: they were using 7 bytes instead of
      8 of keying material. Merlin has also confirmed interop with this fix
@@ -9855,13 +10142,13 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Andy Polyakov <appro@fy.chalmers.se>]
 
   *) Change functions to ANSI C.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Fix typos in error codes.
-     [Martin Kraemer <Martin.Kraemer@MchP.Siemens.De>, Ulf M<EFBFBD>ller]
+     [Martin Kraemer <Martin.Kraemer@MchP.Siemens.De>, Ulf Möller]
 
   *) Remove defunct assembler files from Configure.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) SPARC v8 assembler BIGNUM implementation.
      [Andy Polyakov <appro@fy.chalmers.se>]
@@ -9898,7 +10185,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) New Configure option "rsaref".
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Don't auto-generate pem.h.
      [Bodo Moeller]
@@ -9946,7 +10233,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) New functions DSA_do_sign and DSA_do_verify to provide access to
      the raw DSA values prior to ASN.1 encoding.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) Tweaks to Configure
      [Niels Poppe <niels@netbox.org>]
@@ -9956,11 +10243,11 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) New variables $(RANLIB) and $(PERL) in the Makefiles.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
 
   *) New config option to avoid instructions that are illegal on the 80386.
      The default code is faster, but requires at least a 486.
-     [Ulf M<EFBFBD>ller]
+     [Ulf Möller]
   
   *) Got rid of old SSL2_CLIENT_VERSION (inconsistently used) and
      SSL2_SERVER_VERSION (not used at all) macros, which are now the
@@ -10499,7 +10786,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
       Hagino <itojun@kame.net>]
 
   *) File was opened incorrectly in randfile.c.
-     [Ulf M<EFBFBD>ller <ulf@fitug.de>]
+     [Ulf Möller <ulf@fitug.de>]
 
   *) Beginning of support for GeneralizedTime. d2i, i2d, check and print
      functions. Also ASN1_TIME suite which is a CHOICE of UTCTime or
@@ -10509,7 +10796,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
      [Steve Henson]
 
   *) Correct Linux 1 recognition in config.
-     [Ulf M<EFBFBD>ller <ulf@fitug.de>]
+     [Ulf Möller <ulf@fitug.de>]
 
   *) Remove pointless MD5 hash when using DSA keys in ca.
      [Anonymous <nobody@replay.com>]
@@ -10656,7 +10943,7 @@ des-cbc           3624.96k     5258.21k     5530.91k     5624.30k     5628.26k
 
   *) Fix the RSA header declarations that hid a bug I fixed in 0.9.0b but
      was already fixed by Eric for 0.9.1 it seems.
-     [Ben Laurie - pointed out by Ulf M<EFBFBD>ller <ulf@fitug.de>]
+     [Ben Laurie - pointed out by Ulf Möller <ulf@fitug.de>]
 
   *) Autodetect FreeBSD3.
      [Ben Laurie]

CONTRIBUTING

@@ -0,0 +1,38 @@
+HOW TO CONTRIBUTE TO OpenSSL
+----------------------------
+
+Development is coordinated on the openssl-dev mailing list (see
+http://www.openssl.org for information on subscribing). If you
+would like to submit a patch, send it to rt@openssl.org with
+the string "[PATCH]" in the subject. Please be sure to include a
+textual explanation of what your patch does.
+
+You can also make GitHub pull requests. If you do this, please also send
+mail to rt@openssl.org with a brief description and a link to the PR so
+that we can more easily keep track of it.
+
+If you are unsure as to whether a feature will be useful for the general
+OpenSSL community please discuss it on the openssl-dev mailing list first.
+Someone may be already working on the same thing or there may be a good
+reason as to why that feature isn't implemented.
+
+Patches should be as up to date as possible, preferably relative to the
+current Git or the last snapshot. They should follow our coding style
+(see https://www.openssl.org/policies/codingstyle.html) and compile without
+warnings using the --strict-warnings flag.  OpenSSL compiles on many varied
+platforms: try to ensure you only use portable features.
+
+Our preferred format for patch files is "git format-patch" output. For example
+to provide a patch file containing the last commit in your local git repository
+use the following command:
+
+# git format-patch --stdout HEAD^ >mydiffs.patch
+
+Another method of creating an acceptable patch file without using git is as
+follows:
+
+# cd openssl-work
+# [your changes]
+# ./Configure dist; make clean
+# cd ..
+# diff -ur openssl-orig openssl-work > mydiffs.patch

Configure

@@ -58,6 +58,10 @@ my $usage="Usage: Configure [no-<cipher> ...] [enable-<cipher> ...] [experimenta
 #		library and will be loaded in run-time by the OpenSSL library.
 # sctp          include SCTP support
 # 386           generate 80386 code
+# enable-weak-ssl-ciphers
+#		Enable EXPORT and LOW SSLv3 ciphers that are disabled by
+#		default.  Note, weak SSLv2 ciphers are unconditionally
+#		disabled.
 # no-sse2	disables IA-32 SSE2 code, above option implies no-sse2
 # no-<cipher>   build without specified algorithm (rsa, idea, rc5, ...)
 # -<xxx> +<xxx> compiler options are passed through 
@@ -124,6 +128,9 @@ my $clang_disabled_warnings = "-Wno-unused-parameter -Wno-missing-field-initiali
 # -Wextended-offsetof
 my $clang_devteam_warn = "-Wno-unused-parameter -Wno-missing-field-initializers -Wno-language-extension-token -Wno-extended-offsetof -Qunused-arguments";
 
+# Warn that "make depend" should be run?
+my $warn_make_depend = 0;
+
 my $strict_warnings = 0;
 
 my $x86_gcc_des="DES_PTR DES_RISC1 DES_UNROLL";
@@ -416,6 +423,7 @@ my %table=(
 "linux-ia64-icc","icc:-DL_ENDIAN -O2 -Wall::-D_REENTRANT::-ldl -no_cpprt:SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_RISC1 DES_INT:${ia64_asm}:dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR)",
 "linux-x86_64",	"gcc:-m64 -DL_ENDIAN -O3 -Wall::-D_REENTRANT::-ldl:SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL:${x86_64_asm}:elf:dlfcn:linux-shared:-fPIC:-m64:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::64",
 "linux-x86_64-clang",	"clang: -m64 -DL_ENDIAN -O3 -Wall -Wextra $clang_disabled_warnings -Qunused-arguments::-D_REENTRANT::-ldl:SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL:${x86_64_asm}:elf:dlfcn:linux-shared:-fPIC:-m64:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::64",
+"debug-linux-x86_64-clang",	"clang: -DBN_DEBUG -DREF_CHECK -DCONF_DEBUG -DCRYPTO_MDEBUG -m64 -DL_ENDIAN -g -Wall -Wextra $clang_disabled_warnings -Qunused-arguments::-D_REENTRANT::-ldl:SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL:${x86_64_asm}:elf:dlfcn:linux-shared:-fPIC:-m64:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::64",
 "linux-x86_64-icc", "icc:-DL_ENDIAN -O2::-D_REENTRANT::-ldl -no_cpprt:SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL:${x86_64_asm}:elf:dlfcn:linux-shared:-fPIC::.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::64",
 "linux-x32",	"gcc:-mx32 -DL_ENDIAN -O3 -Wall::-D_REENTRANT::-ldl:SIXTY_FOUR_BIT RC4_CHUNK_LL DES_INT DES_UNROLL:${x86_64_asm}:elf:dlfcn:linux-shared:-fPIC:-mx32:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::x32",
 "linux64-s390x",	"gcc:-m64 -DB_ENDIAN -O3 -Wall::-D_REENTRANT::-ldl:SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL:${s390x_asm}:64:dlfcn:linux-shared:-fPIC:-m64:.so.\$(SHLIB_MAJOR).\$(SHLIB_MINOR):::64",
@@ -777,11 +785,13 @@ my %disabled = ( # "what"         => "comment" [or special keyword "experimental
 		 "md2"            => "default",
 		 "rc5"            => "default",
 		 "rfc3779"	  => "default",
-		 "sctp"       => "default",
+		 "sctp"           => "default",
 		 "shared"         => "default",
 		 "ssl-trace"	  => "default",
+		 "ssl2"           => "default",
 		 "store"	  => "experimental",
 		 "unit-test"	  => "default",
+		 "weak-ssl-ciphers" => "default",
 		 "zlib"           => "default",
 		 "zlib-dynamic"   => "default"
 	       );
@@ -1512,7 +1522,7 @@ if ($target =~ /\-icc$/)	# Intel C compiler
 # linker only when --prefix is not /usr.
 if ($target =~ /^BSD\-/)
 	{
-	$shared_ldflag.=" -Wl,-rpath,\$(LIBRPATH)" if ($prefix !~ m|^/usr[/]*$|);
+	$shared_ldflag.=" -Wl,-rpath,\$\$(LIBRPATH)" if ($prefix !~ m|^/usr[/]*$|);
 	}
 
 if ($sys_id ne "")
@@ -1646,21 +1656,22 @@ if ($shlib_version_number =~ /(^[0-9]*)\.([0-9\.]*)/)
 	$shlib_minor=$2;
 	}
 
+my $ecc = $cc;
+$ecc = "clang" if `$cc --version 2>&1` =~ /clang/;
+
 if ($strict_warnings)
 	{
-	my $ecc = $cc;
-	$ecc = "clang" if `$cc --version 2>&1` =~ /clang/;
 	my $wopt;
 	die "ERROR --strict-warnings requires gcc or clang" unless ($ecc =~ /gcc$/ or $ecc =~ /clang$/);
 	foreach $wopt (split /\s+/, $gcc_devteam_warn)
 		{
-		$cflags .= " $wopt" unless ($cflags =~ /$wopt/)
+		$cflags .= " $wopt" unless ($cflags =~ /(^|\s)$wopt(\s|$)/)
 		}
 	if ($ecc eq "clang")
 		{
 		foreach $wopt (split /\s+/, $clang_devteam_warn)
 			{
-			$cflags .= " $wopt" unless ($cflags =~ /$wopt/)
+			$cflags .= " $wopt" unless ($cflags =~ /(^|\s)$wopt(\s|$)/)
 			}
 		}
 	}
@@ -1713,6 +1724,7 @@ while (<IN>)
 		s/^AR=\s*ar/AR= $ar/;
 		s/^RANLIB=.*/RANLIB= $ranlib/;
 		s/^MAKEDEPPROG=.*$/MAKEDEPPROG= $cc/ if $cc eq "gcc";
+		s/^MAKEDEPPROG=.*$/MAKEDEPPROG= $cc/ if $ecc eq "gcc" || $ecc eq "clang";
 		}
 	s/^CFLAG=.*$/CFLAG= $cflags/;
 	s/^DEPFLAG=.*$/DEPFLAG=$depflags/;
@@ -2025,14 +2037,8 @@ EOF
 	    &dofile("apps/CA.pl",'/usr/local/bin/perl','^#!/', '#!%s');
 	}
 	if ($depflags ne $default_depflags && !$make_depend) {
-		print <<EOF;
-
-Since you've disabled or enabled at least one algorithm, you need to do
-the following before building:
-
-	make depend
-EOF
-	}
+            $warn_make_depend++;
+        }
 }
 
 # create the ms/version32.rc file if needed
@@ -2111,12 +2117,18 @@ EOF
 
 print <<\EOF if ($no_shared_warn);
 
-You gave the option 'shared'.  Normally, that would give you shared libraries.
-Unfortunately, the OpenSSL configuration doesn't include shared library support
-for this platform yet, so it will pretend you gave the option 'no-shared'.  If
-you can inform the developpers (openssl-dev\@openssl.org) how to support shared
-libraries on this platform, they will at least look at it and try their best
-(but please first make sure you have tried with a current version of OpenSSL).
+You gave the option 'shared', which is not supported on this platform, so
+we will pretend you gave the option 'no-shared'.  If you know how to implement
+shared libraries, please let us know (but please first make sure you have
+tried with a current version of OpenSSL).
+EOF
+
+print <<EOF if ($warn_make_depend);
+
+*** Because of configuration changes, you MUST do the following before
+*** building:
+
+	make depend
 EOF
 
 exit(0);

INSTALL

@@ -164,10 +164,10 @@
      standard headers).  If it is a problem with OpenSSL itself, please
      report the problem to <openssl-bugs@openssl.org> (note that your
      message will be recorded in the request tracker publicly readable
-     via http://www.openssl.org/support/rt.html and will be forwarded to a
-     public mailing list). Include the output of "make report" in your message.
-     Please check out the request tracker. Maybe the bug was already
-     reported or has already been fixed.
+     at https://www.openssl.org/community/index.html#bugs and will be
+     forwarded to a public mailing list). Include the output of "make
+     report" in your message.  Please check out the request tracker. Maybe
+     the bug was already reported or has already been fixed.
 
      [If you encounter assembler error messages, try the "no-asm"
      configuration option as an immediate fix.]

LICENSE

@@ -12,7 +12,7 @@
   ---------------
 
 /* ====================================================================
- * Copyright (c) 1998-2011 The OpenSSL Project.  All rights reserved.
+ * Copyright (c) 1998-2016 The OpenSSL Project.  All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions

Makefile.org

@@ -180,8 +180,7 @@ SHARED_LDFLAGS=
 GENERAL=        Makefile
 BASENAME=       openssl
 NAME=           $(BASENAME)-$(VERSION)
-TARFILE=        $(NAME).tar
-WTARFILE=       $(NAME)-win.tar
+TARFILE=        ../$(NAME).tar
 EXHEADER=       e_os2.h
 HEADER=         e_os.h
 
@@ -203,7 +202,9 @@ CLEARENV=	TOP= && unset TOP $${LIB+LIB} $${LIBS+LIBS}	\
 		$${SHAREDCMD+SHAREDCMD} $${SHAREDFLAGS+SHAREDFLAGS}	\
 		$${SHARED_LIB+SHARED_LIB} $${LIBEXTRAS+LIBEXTRAS}
 
-BUILDENV=	PLATFORM='$(PLATFORM)' PROCESSOR='$(PROCESSOR)' \
+# LC_ALL=C ensures that error [and other] messages are delivered in
+# same language for uniform treatment.
+BUILDENV=	LC_ALL=C PLATFORM='$(PLATFORM)' PROCESSOR='$(PROCESSOR)'\
 		CC='$(CC)' CFLAG='$(CFLAG)' 			\
 		AS='$(CC)' ASFLAG='$(CFLAG) -c'			\
 		AR='$(AR)' NM='$(NM)' RANLIB='$(RANLIB)'	\
@@ -269,6 +270,7 @@ reflect:
 	@[ -n "$(THIS)" ] && $(CLEARENV) && $(MAKE) $(THIS) -e $(BUILDENV)
 
 sub_all: build_all
+
 build_all: build_libs build_apps build_tests build_tools
 
 build_libs: build_libcrypto build_libssl openssl.pc
@@ -278,15 +280,15 @@ build_libssl: build_ssl libssl.pc
 
 build_crypto:
 	@dir=crypto; target=all; $(BUILD_ONE_CMD)
-build_ssl:
+build_ssl: build_crypto
 	@dir=ssl; target=all; $(BUILD_ONE_CMD)
-build_engines:
+build_engines: build_crypto
 	@dir=engines; target=all; $(BUILD_ONE_CMD)
-build_apps:
+build_apps: build_libs
 	@dir=apps; target=all; $(BUILD_ONE_CMD)
-build_tests:
+build_tests: build_libs
 	@dir=test; target=all; $(BUILD_ONE_CMD)
-build_tools:
+build_tools: build_libs
 	@dir=tools; target=all; $(BUILD_ONE_CMD)
 
 all_testapps: build_libs build_testapps
@@ -496,35 +498,35 @@ TABLE: Configure
 # would occur. Therefore the list of files is temporarily stored into a file
 # and read directly, requiring GNU-Tar. Call "make TAR=gtar dist" if the normal
 # tar does not support the --files-from option.
-tar:
+TAR_COMMAND=$(TAR) $(TARFLAGS) --files-from $(TARFILE).list \
+	                       --owner 0 --group 0 \
+			       --transform 's|^|$(NAME)/|' \
+			       -cvf -
+
+$(TARFILE).list:
+	find * \! -name STATUS \! -name TABLE \! -name '*.o' \! -name '*.a' \
+	       \! -name '*.so' \! -name '*.so.*'  \! -name 'openssl' \
+	       \( \! -name '*test' -o -name bctest -o -name pod2mantest \) \
+	       \! -name '.#*' \! -name '*~' \! -type l \
+	    | sort > $(TARFILE).list
+
+tar: $(TARFILE).list
 	find . -type d -print | xargs chmod 755
 	find . -type f -print | xargs chmod a+r
 	find . -type f -perm -0100 -print | xargs chmod a+x
-	find * \! -path CVS/\* \! -path \*/CVS/\* \! -name CVS \! -name .cvsignore \! -name STATUS \! -name TABLE | sort > ../$(TARFILE).list; \
-	$(TAR) $(TARFLAGS) --files-from ../$(TARFILE).list -cvf - | \
-	tardy --user_number=0  --user_name=openssl \
-	      --group_number=0 --group_name=openssl \
-	      --prefix=openssl-$(VERSION) - |\
-	gzip --best >../$(TARFILE).gz; \
-	rm -f ../$(TARFILE).list; \
-	ls -l ../$(TARFILE).gz
+	$(TAR_COMMAND) | gzip --best > $(TARFILE).gz
+	rm -f $(TARFILE).list
+	ls -l $(TARFILE).gz
 
-tar-snap:
-	@$(TAR) $(TARFLAGS) -cvf - \
-		`find * \! -path CVS/\* \! -path \*/CVS/\* \! -name CVS \! -name .cvsignore \! -name STATUS \! -name TABLE \! -name '*.o' \! -name '*.a' \! -name '*.so' \! -name '*.so.*'  \! -name 'openssl' \! -name '*test' \! -name '.#*' \! -name '*~' | sort` |\
-	tardy --user_number=0  --user_name=openssl \
-	      --group_number=0 --group_name=openssl \
-	      --prefix=openssl-$(VERSION) - > ../$(TARFILE);\
-	ls -l ../$(TARFILE)
+tar-snap: $(TARFILE).list
+	$(TAR_COMMAND) > $(TARFILE)
+	rm -f $(TARFILE).list
+	ls -l $(TARFILE)
 
 dist:   
 	$(PERL) Configure dist
-	@$(MAKE) dist_pem_h
 	@$(MAKE) SDIRS='$(SDIRS)' clean
-	@$(MAKE) TAR='$(TAR)' TARFLAGS='$(TARFLAGS)' tar
-
-dist_pem_h:
-	(cd crypto/pem; $(MAKE) -e $(BUILDENV) pem.h; $(MAKE) clean)
+	@$(MAKE) TAR='$(TAR)' TARFLAGS='$(TARFLAGS)' $(DISTTARVARS) tar
 
 install: all install_docs install_sw
 

Makefile.shared

@@ -272,7 +272,7 @@ link_o.cygwin:
 	SHLIB_SOVER=${LIBVERSION:+"-$(LIBVERSION)"}; \
 	ALLSYMSFLAGS='-Wl,--whole-archive'; \
 	NOALLSYMSFLAGS='-Wl,--no-whole-archive'; \
-	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base $$deffile -Wl,-s,-Bsymbolic"; \
+	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base $$deffile -Wl,-Bsymbolic"; \
 	$(LINK_SO_O)
 #for mingw target if def-file is in use dll-name should match library-name
 link_a.cygwin:
@@ -289,7 +289,7 @@ link_a.cygwin:
 		SHLIB_SOVER=32; \
 		extras="$(LIBNAME).def"; \
 		$(PERL) util/mkdef.pl 32 $$SHLIB > $$extras; \
-		base=; [ $(LIBNAME) = "crypto" ] && base=-Wl,--image-base,0x63000000; \
+		base=; [ $(LIBNAME) = "crypto" -a -n "$(FIPSCANLIB)" ] && base=-Wl,--image-base,0x63000000; \
 	fi; \
 	dll_name=$$SHLIB$$SHLIB_SOVER$$SHLIB_SUFFIX; \
 	$(PERL) util/mkrc.pl $$dll_name | \
@@ -297,7 +297,7 @@ link_a.cygwin:
 	extras="$$extras rc.o"; \
 	ALLSYMSFLAGS='-Wl,--whole-archive'; \
 	NOALLSYMSFLAGS='-Wl,--no-whole-archive'; \
-	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base -Wl,-s,-Bsymbolic -Wl,--out-implib,lib$(LIBNAME).dll.a $$extras"; \
+	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base -Wl,-Bsymbolic -Wl,--out-implib,lib$(LIBNAME).dll.a $$extras"; \
 	[ -f apps/$$dll_name ] && rm apps/$$dll_name; \
 	[ -f test/$$dll_name ] && rm test/$$dll_name; \
 	$(LINK_SO_A) || exit 1; \

NEWS

@@ -5,6 +5,46 @@
   This file gives a brief overview of the major changes between each OpenSSL
   release. For more details please read the CHANGES file.
 
+  Major changes between OpenSSL 1.0.2g and OpenSSL 1.0.2h [under development]
+
+      o
+
+  Major changes between OpenSSL 1.0.2f and OpenSSL 1.0.2g [1 Mar 2016]
+
+      o Disable weak ciphers in SSLv3 and up in default builds of OpenSSL.
+      o Disable SSLv2 default build, default negotiation and weak ciphers
+        (CVE-2016-0800)
+      o Fix a double-free in DSA code (CVE-2016-0705)
+      o Disable SRP fake user seed to address a server memory leak
+        (CVE-2016-0798)
+      o Fix BN_hex2bn/BN_dec2bn NULL pointer deref/heap corruption
+        (CVE-2016-0797)
+      o Fix memory issues in BIO_*printf functions (CVE-2016-0799)
+      o Fix side channel attack on modular exponentiation (CVE-2016-0702)
+
+  Major changes between OpenSSL 1.0.2e and OpenSSL 1.0.2f [28 Jan 2016]
+
+      o DH small subgroups (CVE-2016-0701)
+      o SSLv2 doesn't block disabled ciphers (CVE-2015-3197)
+
+  Major changes between OpenSSL 1.0.2d and OpenSSL 1.0.2e [3 Dec 2015]
+
+      o BN_mod_exp may produce incorrect results on x86_64 (CVE-2015-3193)
+      o Certificate verify crash with missing PSS parameter (CVE-2015-3194)
+      o X509_ATTRIBUTE memory leak (CVE-2015-3195)
+      o Rewrite EVP_DecodeUpdate (base64 decoding) to fix several bugs
+      o In DSA_generate_parameters_ex, if the provided seed is too short,
+        return an error
+
+  Major changes between OpenSSL 1.0.2c and OpenSSL 1.0.2d [9 Jul 2015]
+
+      o Alternate chains certificate forgery (CVE-2015-1793)
+      o Race condition handling PSK identify hint (CVE-2015-3196)
+
+  Major changes between OpenSSL 1.0.2b and OpenSSL 1.0.2c [12 Jun 2015]
+
+      o Fix HMAC ABI incompatibility
+
   Major changes between OpenSSL 1.0.2a and OpenSSL 1.0.2b [11 Jun 2015]
 
       o Malformed ECParameters causes infinite loop (CVE-2015-1788)

README

@@ -1,7 +1,7 @@
 
- OpenSSL 1.0.2b 11 Jun 2015
+ OpenSSL 1.0.2h-dev
 
- Copyright (c) 1998-2011 The OpenSSL Project
+ Copyright (c) 1998-2015 The OpenSSL Project
  Copyright (c) 1995-1998 Eric A. Young, Tim J. Hudson
  All rights reserved.
 
@@ -10,17 +10,17 @@
 
  The OpenSSL Project is a collaborative effort to develop a robust,
  commercial-grade, fully featured, and Open Source toolkit implementing the
- Secure Sockets Layer (SSL v2/v3) and Transport Layer Security (TLS v1)
- protocols as well as a full-strength general purpose cryptography library.
- The project is managed by a worldwide community of volunteers that use the
- Internet to communicate, plan, and develop the OpenSSL toolkit and its
- related documentation.
+ Secure Sockets Layer (SSLv3) and Transport Layer Security (TLS) protocols as
+ well as a full-strength general purpose cryptograpic library. The project is
+ managed by a worldwide community of volunteers that use the Internet to
+ communicate, plan, and develop the OpenSSL toolkit and its related
+ documentation.
 
- OpenSSL is based on the excellent SSLeay library developed from Eric A. Young
+ OpenSSL is descended from the SSLeay library developed by Eric A. Young
  and Tim J. Hudson.  The OpenSSL toolkit is licensed under a dual-license (the
- OpenSSL license plus the SSLeay license) situation, which basically means
- that you are free to get and use it for commercial and non-commercial
- purposes as long as you fulfill the conditions of both licenses.
+ OpenSSL license plus the SSLeay license), which means that you are free to
+ get and use it for commercial and non-commercial purposes as long as you
+ fulfill the conditions of both licenses.
 
  OVERVIEW
  --------
@@ -28,90 +28,39 @@
  The OpenSSL toolkit includes:
 
  libssl.a:
-     Implementation of SSLv2, SSLv3, TLSv1 and the required code to support
-     both SSLv2, SSLv3 and TLSv1 in the one server and client.
+     Provides the client and server-side implementations for SSLv3 and TLS.
 
  libcrypto.a:
-     General encryption and X.509 v1/v3 stuff needed by SSL/TLS but not
-     actually logically part of it. It includes routines for the following:
-
-     Ciphers
-        libdes - EAY's libdes DES encryption package which was floating
-                 around the net for a few years, and was then relicensed by
-                 him as part of SSLeay.  It includes 15 'modes/variations'
-                 of DES (1, 2 and 3 key versions of ecb, cbc, cfb and ofb;
-                 pcbc and a more general form of cfb and ofb) including desx
-                 in cbc mode, a fast crypt(3), and routines to read
-                 passwords from the keyboard.
-        RC4 encryption,
-        RC2 encryption      - 4 different modes, ecb, cbc, cfb and ofb.
-        Blowfish encryption - 4 different modes, ecb, cbc, cfb and ofb.
-        IDEA encryption     - 4 different modes, ecb, cbc, cfb and ofb.
-
-     Digests
-        MD5 and MD2 message digest algorithms, fast implementations,
-        SHA (SHA-0) and SHA-1 message digest algorithms,
-        MDC2 message digest. A DES based hash that is popular on smart cards.
-
-     Public Key
-        RSA encryption/decryption/generation.
-            There is no limit on the number of bits.
-        DSA encryption/decryption/generation.
-            There is no limit on the number of bits.
-        Diffie-Hellman key-exchange/key generation.
-            There is no limit on the number of bits.
-
-     X.509v3 certificates
-        X509 encoding/decoding into/from binary ASN1 and a PEM
-             based ASCII-binary encoding which supports encryption with a
-             private key.  Program to generate RSA and DSA certificate
-             requests and to generate RSA and DSA certificates.
-
-     Systems
-        The normal digital envelope routines and base64 encoding.  Higher
-        level access to ciphers and digests by name.  New ciphers can be
-        loaded at run time.  The BIO io system which is a simple non-blocking
-        IO abstraction.  Current methods supported are file descriptors,
-        sockets, socket accept, socket connect, memory buffer, buffering, SSL
-        client/server, file pointer, encryption, digest, non-blocking testing
-        and null.
-
-     Data structures
-        A dynamically growing hashing system
-        A simple stack.
-        A Configuration loader that uses a format similar to MS .ini files.
+     Provides general cryptographic and X.509 support needed by SSL/TLS but
+     not logically part of it.
 
  openssl:
      A command line tool that can be used for:
-        Creation of RSA, DH and DSA key parameters
+        Creation of key parameters
         Creation of X.509 certificates, CSRs and CRLs
-        Calculation of Message Digests
-        Encryption and Decryption with Ciphers
-        SSL/TLS Client and Server Tests
+        Calculation of message digests
+        Encryption and decryption
+        SSL/TLS client and server tests
         Handling of S/MIME signed or encrypted mail
+        And more...
 
  INSTALLATION
  ------------
 
- To install this package under a Unix derivative, read the INSTALL file.  For
- a Win32 platform, read the INSTALL.W32 file.  For OpenVMS systems, read
- INSTALL.VMS.
-
- Read the documentation in the doc/ directory.  It is quite rough, but it
- lists the functions; you will probably have to look at the code to work out
- how to use them. Look at the example programs.
-
- PROBLEMS
- --------
-
- For some platforms, there are some known problems that may affect the user
- or application author.  We try to collect those in doc/PROBLEMS, with current
- thoughts on how they should be solved in a future of OpenSSL.
+ See the appropriate file:
+        INSTALL         Linux, Unix, etc.
+        INSTALL.DJGPP   DOS platform with DJGPP
+        INSTALL.NW      Netware
+        INSTALL.OS2     OS/2
+        INSTALL.VMS     VMS
+        INSTALL.W32     Windows (32bit)
+        INSTALL.W64     Windows (64bit)
+        INSTALL.WCE     Windows CE
 
  SUPPORT
  -------
 
- See the OpenSSL website www.openssl.org for details of how to obtain
+ See the OpenSSL website www.openssl.org for details on how to obtain
  commercial technical support.
 
  If you have any problems with OpenSSL then please take the following steps
@@ -137,56 +86,34 @@
 
  Email the report to:
 
-    openssl-bugs@openssl.org
+    rt@openssl.org
 
- Note that the request tracker should NOT be used for general assistance
- or support queries. Just because something doesn't work the way you expect
- does not mean it is necessarily a bug in OpenSSL.
+ In order to avoid spam, this is a moderated mailing list, and it might
+ take a day for the ticket to show up.  (We also scan posts to make sure
+ that security disclosures aren't publically posted by mistake.) Mail
+ to this address is recorded in the public RT (request tracker) database
+ (see https://www.openssl.org/community/index.html#bugs for details) and
+ also forwarded the public openssl-dev mailing list.  Confidential mail
+ may be sent to openssl-security@openssl.org (PGP key available from the
+ key servers).
 
- Note that mail to openssl-bugs@openssl.org is recorded in the public
- request tracker database (see https://www.openssl.org/support/rt.html
- for details) and also forwarded to a public mailing list. Confidential
- mail may be sent to openssl-security@openssl.org (PGP key available from
- the key servers).
+ Please do NOT use this for general assistance or support queries.
+ Just because something doesn't work the way you expect does not mean it
+ is necessarily a bug in OpenSSL.
+
+ You can also make GitHub pull requests. If you do this, please also send
+ mail to rt@openssl.org with a link to the PR so that we can more easily
+ keep track of it.
 
  HOW TO CONTRIBUTE TO OpenSSL
  ----------------------------
 
- Development is coordinated on the openssl-dev mailing list (see
- http://www.openssl.org for information on subscribing). If you
- would like to submit a patch, send it to openssl-bugs@openssl.org with
- the string "[PATCH]" in the subject. Please be sure to include a
- textual explanation of what your patch does.
+ See CONTRIBUTING
 
- If you are unsure as to whether a feature will be useful for the general
- OpenSSL community please discuss it on the openssl-dev mailing list first.
- Someone may be already working on the same thing or there may be a good
- reason as to why that feature isn't implemented.
-
- Patches should be as up to date as possible, preferably relative to the
- current Git or the last snapshot. They should follow the coding style of
- OpenSSL and compile without warnings. Some of the core team developer targets
- can be used for testing purposes, (debug-steve64, debug-geoff etc). OpenSSL
- compiles on many varied platforms: try to ensure you only use portable
- features.
-
- Note: For legal reasons, contributions from the US can be accepted only
- if a TSU notification and a copy of the patch are sent to crypt@bis.doc.gov
- (formerly BXA) with a copy to the ENC Encryption Request Coordinator;
- please take some time to look at
-    http://www.bis.doc.gov/Encryption/PubAvailEncSourceCodeNofify.html [sic]
- and
-    http://w3.access.gpo.gov/bis/ear/pdf/740.pdf (EAR Section 740.13(e))
- for the details. If "your encryption source code is too large to serve as
- an email attachment", they are glad to receive it by fax instead; hope you
- have a cheap long-distance plan.
-
- Our preferred format for changes is "diff -u" output. You might
- generate it like this:
-
- # cd openssl-work
- # [your changes]
- # ./Configure dist; make clean
- # cd ..
- # diff -ur openssl-orig openssl-work > mydiffs.patch
+ LEGALITIES
+ ----------
 
+ A number of nations, in particular the U.S., restrict the use or export
+ of cryptography. If you are potentially subject to such restrictions
+ you should seek competent professional legal advice before attempting to
+ develop or distribute cryptographic code.

apps/.cvsignore

@@ -1,8 +0,0 @@
-openssl
-Makefile.save
-der_chop
-der_chop.bak
-CA.pl
-*.flc
-semantic.cache
-*.dll

apps/Makefile

@@ -135,7 +135,7 @@ update: openssl-vms.cnf local_depend
 depend: local_depend
 	@if [ -z "$(THIS)" ]; then $(MAKE) -f $(TOP)/Makefile reflect THIS=$@; fi
 local_depend:
-	@[ -z "$(THIS)" ] || $(MAKEDEPEND) -- $(CFLAG) $(INCLUDES) $(DEPFLAG) -- $(PROGS) $(SRC); \
+	@[ -z "$(THIS)" ] || $(MAKEDEPEND) -- $(CFLAG) $(INCLUDES) $(DEPFLAG) -- $(PROGS) $(SRC)
 
 dclean:
 	$(PERL) -pe 'if (/^# DO NOT DELETE THIS LINE/) {print; exit(0);}' $(MAKEFILE) >Makefile.new

apps/app_rand.c

@@ -124,10 +124,7 @@ int app_RAND_load_file(const char *file, BIO *bio_e, int dont_warn)
     char buffer[200];
 
 #ifdef OPENSSL_SYS_WINDOWS
-    BIO_printf(bio_e, "Loading 'screen' into random state -");
-    BIO_flush(bio_e);
     RAND_screen();
-    BIO_printf(bio_e, " done\n");
 #endif
 
     if (file == NULL)

apps/apps.c

@@ -119,9 +119,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#if !defined(OPENSSL_SYSNAME_WIN32) && !defined(OPENSSL_SYSNAME_WINCE) && !defined(NETWARE_CLIB)
-# include <strings.h>
-#endif
 #include <sys/types.h>
 #include <ctype.h>
 #include <errno.h>
@@ -1352,7 +1349,11 @@ int set_name_ex(unsigned long *flags, const char *arg)
         {"ca_default", XN_FLAG_MULTILINE, 0xffffffffL},
         {NULL, 0, 0}
     };
-    return set_multi_opts(flags, arg, ex_tbl);
+    if (set_multi_opts(flags, arg, ex_tbl) == 0)
+        return 0;
+    if ((*flags & XN_FLAG_SEP_MASK) == 0)
+        *flags |= XN_FLAG_SEP_CPLUS_SPC;
+    return 1;
 }
 
 int set_ext_copy(int *copy_type, const char *arg)
@@ -2441,7 +2442,11 @@ int bio_to_mem(unsigned char **out, int maxlen, BIO *in)
         else
             len = 1024;
         len = BIO_read(in, tbuf, len);
-        if (len <= 0)
+        if (len < 0) {
+            BIO_free(mem);
+            return -1;
+        }
+        if (len == 0)
             break;
         if (BIO_write(mem, tbuf, len) != len) {
             BIO_free(mem);
@@ -2458,7 +2463,7 @@ int bio_to_mem(unsigned char **out, int maxlen, BIO *in)
     return ret;
 }
 
-int pkey_ctrl_string(EVP_PKEY_CTX *ctx, char *value)
+int pkey_ctrl_string(EVP_PKEY_CTX *ctx, const char *value)
 {
     int rv;
     char *stmp, *vtmp = NULL;

apps/apps.h

@@ -321,7 +321,7 @@ int args_verify(char ***pargs, int *pargc,
                 int *badarg, BIO *err, X509_VERIFY_PARAM **pm);
 void policies_print(BIO *out, X509_STORE_CTX *ctx);
 int bio_to_mem(unsigned char **out, int maxlen, BIO *in);
-int pkey_ctrl_string(EVP_PKEY_CTX *ctx, char *value);
+int pkey_ctrl_string(EVP_PKEY_CTX *ctx, const char *value);
 int init_gen_str(BIO *err, EVP_PKEY_CTX **pctx,
                  const char *algname, ENGINE *e, int do_param);
 int do_X509_sign(BIO *err, X509 *x, EVP_PKEY *pkey, const EVP_MD *md,

apps/asn1pars.c

@@ -313,9 +313,9 @@ int MAIN(int argc, char **argv)
             }
             typ = ASN1_TYPE_get(at);
             if ((typ == V_ASN1_OBJECT)
+                || (typ == V_ASN1_BOOLEAN)
                 || (typ == V_ASN1_NULL)) {
-                BIO_printf(bio_err, "Can't parse %s type\n",
-                           typ == V_ASN1_NULL ? "NULL" : "OBJECT");
+                BIO_printf(bio_err, "Can't parse %s type\n", ASN1_tag2str(typ));
                 ERR_print_errors(bio_err);
                 goto end;
             }

apps/ca.c

@@ -99,25 +99,19 @@
 #undef PROG
 #define PROG ca_main
 
-#define BASE_SECTION    "ca"
-#define CONFIG_FILE "openssl.cnf"
+#define BASE_SECTION            "ca"
+#define CONFIG_FILE             "openssl.cnf"
 
 #define ENV_DEFAULT_CA          "default_ca"
 
-#define STRING_MASK     "string_mask"
+#define STRING_MASK             "string_mask"
 #define UTF8_IN                 "utf8"
 
-#define ENV_DIR                 "dir"
-#define ENV_CERTS               "certs"
-#define ENV_CRL_DIR             "crl_dir"
-#define ENV_CA_DB               "CA_DB"
 #define ENV_NEW_CERTS_DIR       "new_certs_dir"
 #define ENV_CERTIFICATE         "certificate"
 #define ENV_SERIAL              "serial"
 #define ENV_CRLNUMBER           "crlnumber"
-#define ENV_CRL                 "crl"
 #define ENV_PRIVATE_KEY         "private_key"
-#define ENV_RANDFILE            "RANDFILE"
 #define ENV_DEFAULT_DAYS        "default_days"
 #define ENV_DEFAULT_STARTDATE   "default_startdate"
 #define ENV_DEFAULT_ENDDATE     "default_enddate"
@@ -2538,6 +2532,8 @@ static int do_updatedb(CA_DB *db)
     char **rrow, *a_tm_s;
 
     a_tm = ASN1_UTCTIME_new();
+    if (a_tm == NULL)
+        return -1;
 
     /* get actual time and make a string */
     a_tm = X509_gmtime_adj(a_tm, 0);

apps/ecparam.c

@@ -416,14 +416,13 @@ int MAIN(int argc, char **argv)
     }
 
     if (check) {
-        if (group == NULL)
-            BIO_printf(bio_err, "no elliptic curve parameters\n");
         BIO_printf(bio_err, "checking elliptic curve parameters: ");
         if (!EC_GROUP_check(group, NULL)) {
             BIO_printf(bio_err, "failed\n");
             ERR_print_errors(bio_err);
-        } else
-            BIO_printf(bio_err, "ok\n");
+            goto end;
+        }
+        BIO_printf(bio_err, "ok\n");
 
     }
 

apps/engine.c

@@ -1,4 +1,4 @@
-/* apps/engine.c -*- mode: C; c-file-style: "eay" -*- */
+/* apps/engine.c */
 /*
  * Written by Richard Levitte <richard@levitte.org> for the OpenSSL project
  * 2000.
@@ -99,8 +99,6 @@ static void identity(char *ptr)
 
 static int append_buf(char **buf, const char *s, int *size, int step)
 {
-    int l = strlen(s);
-
     if (*buf == NULL) {
         *size = step;
         *buf = OPENSSL_malloc(*size);
@@ -109,9 +107,6 @@ static int append_buf(char **buf, const char *s, int *size, int step)
         **buf = '\0';
     }
 
-    if (**buf != '\0')
-        l += 2;                 /* ", " */
-
     if (strlen(*buf) + strlen(s) >= (unsigned int)*size) {
         *size += step;
         *buf = OPENSSL_realloc(*buf, *size);

apps/ocsp.c

@@ -209,6 +209,7 @@ int MAIN(int argc, char **argv)
                 OPENSSL_free(tport);
             if (tpath)
                 OPENSSL_free(tpath);
+            thost = tport = tpath = NULL;
             if (args[1]) {
                 args++;
                 if (!OCSP_parse_url(*args, &host, &port, &path, &use_ssl)) {
@@ -1040,7 +1041,7 @@ static int make_ocsp_response(OCSP_RESPONSE **resp, OCSP_REQUEST *req,
     bs = OCSP_BASICRESP_new();
     thisupd = X509_gmtime_adj(NULL, 0);
     if (ndays != -1)
-        nextupd = X509_gmtime_adj(NULL, nmin * 60 + ndays * 3600 * 24);
+        nextupd = X509_time_adj_ex(NULL, ndays, nmin * 60, NULL);
 
     /* Examine each certificate id in the request */
     for (i = 0; i < id_count; i++) {
@@ -1260,8 +1261,8 @@ static OCSP_RESPONSE *query_responder(BIO *err, BIO *cbio, const char *path,
         return NULL;
     }
 
-    if (BIO_get_fd(cbio, &fd) <= 0) {
-        BIO_puts(err, "Can't get connection fd\n");
+    if (BIO_get_fd(cbio, &fd) < 0) {
+        BIO_puts(bio_err, "Can't get connection fd\n");
         goto err;
     }
 

apps/pkcs12.c

@@ -79,7 +79,8 @@ const EVP_CIPHER *enc;
 # define CLCERTS         0x8
 # define CACERTS         0x10
 
-int get_cert_chain(X509 *cert, X509_STORE *store, STACK_OF(X509) **chain);
+static int get_cert_chain(X509 *cert, X509_STORE *store,
+                          STACK_OF(X509) **chain);
 int dump_certs_keys_p12(BIO *out, PKCS12 *p12, char *pass, int passlen,
                         int options, char *pempass);
 int dump_certs_pkeys_bags(BIO *out, STACK_OF(PKCS12_SAFEBAG) *bags,
@@ -134,13 +135,6 @@ int MAIN(int argc, char **argv)
 
     apps_startup();
 
-# ifdef OPENSSL_FIPS
-    if (FIPS_mode())
-        cert_pbe = NID_pbe_WithSHA1And3_Key_TripleDES_CBC;
-    else
-# endif
-        cert_pbe = NID_pbe_WithSHA1And40BitRC2_CBC;
-
     enc = EVP_des_ede3_cbc();
     if (bio_err == NULL)
         bio_err = BIO_new_fp(stderr, BIO_NOCLOSE);
@@ -148,6 +142,13 @@ int MAIN(int argc, char **argv)
     if (!load_config(bio_err, NULL))
         goto end;
 
+# ifdef OPENSSL_FIPS
+    if (FIPS_mode())
+        cert_pbe = NID_pbe_WithSHA1And3_Key_TripleDES_CBC;
+    else
+# endif
+        cert_pbe = NID_pbe_WithSHA1And40BitRC2_CBC;
+
     args = argv + 1;
 
     while (*args) {
@@ -594,7 +595,7 @@ int MAIN(int argc, char **argv)
             vret = get_cert_chain(ucert, store, &chain2);
             X509_STORE_free(store);
 
-            if (!vret) {
+            if (vret == X509_V_OK) {
                 /* Exclude verified certificate */
                 for (i = 1; i < sk_X509_num(chain2); i++)
                     sk_X509_push(certs, sk_X509_value(chain2, i));
@@ -602,7 +603,7 @@ int MAIN(int argc, char **argv)
                 X509_free(sk_X509_value(chain2, 0));
                 sk_X509_free(chain2);
             } else {
-                if (vret >= 0)
+                if (vret != X509_V_ERR_UNSPECIFIED)
                     BIO_printf(bio_err, "Error %s getting chain.\n",
                                X509_verify_cert_error_string(vret));
                 else
@@ -906,36 +907,25 @@ int dump_certs_pkeys_bag(BIO *out, PKCS12_SAFEBAG *bag, char *pass,
 
 /* Given a single certificate return a verified chain or NULL if error */
 
-/* Hope this is OK .... */
-
-int get_cert_chain(X509 *cert, X509_STORE *store, STACK_OF(X509) **chain)
+static int get_cert_chain(X509 *cert, X509_STORE *store,
+                          STACK_OF(X509) **chain)
 {
     X509_STORE_CTX store_ctx;
-    STACK_OF(X509) *chn;
+    STACK_OF(X509) *chn = NULL;
     int i = 0;
 
-    /*
-     * FIXME: Should really check the return status of X509_STORE_CTX_init
-     * for an error, but how that fits into the return value of this function
-     * is less obvious.
-     */
-    X509_STORE_CTX_init(&store_ctx, store, cert, NULL);
-    if (X509_verify_cert(&store_ctx) <= 0) {
-        i = X509_STORE_CTX_get_error(&store_ctx);
-        if (i == 0)
-            /*
-             * avoid returning 0 if X509_verify_cert() did not set an
-             * appropriate error value in the context
-             */
-            i = -1;
-        chn = NULL;
-        goto err;
-    } else
+    if (!X509_STORE_CTX_init(&store_ctx, store, cert, NULL)) {
+        *chain = NULL;
+        return X509_V_ERR_UNSPECIFIED;
+    }
+
+    if (X509_verify_cert(&store_ctx) > 0)
         chn = X509_STORE_CTX_get1_chain(&store_ctx);
- err:
+    else if ((i = X509_STORE_CTX_get_error(&store_ctx)) == 0)
+        i = X509_V_ERR_UNSPECIFIED;
+
     X509_STORE_CTX_cleanup(&store_ctx);
     *chain = chn;
-
     return i;
 }
 

apps/pkcs7.c

@@ -235,12 +235,16 @@ int MAIN(int argc, char **argv)
         i = OBJ_obj2nid(p7->type);
         switch (i) {
         case NID_pkcs7_signed:
-            certs = p7->d.sign->cert;
-            crls = p7->d.sign->crl;
+            if (p7->d.sign != NULL) {
+                certs = p7->d.sign->cert;
+                crls = p7->d.sign->crl;
+            }
             break;
         case NID_pkcs7_signedAndEnveloped:
-            certs = p7->d.signed_and_enveloped->cert;
-            crls = p7->d.signed_and_enveloped->crl;
+            if (p7->d.signed_and_enveloped != NULL) {
+                certs = p7->d.signed_and_enveloped->cert;
+                crls = p7->d.signed_and_enveloped->crl;
+            }
             break;
         default:
             break;

apps/pkeyutl.c

@@ -73,11 +73,12 @@ static void usage(void);
 #define PROG pkeyutl_main
 
 static EVP_PKEY_CTX *init_ctx(int *pkeysize,
-                              char *keyfile, int keyform, int key_type,
-                              char *passargin, int pkey_op, ENGINE *e);
+                              const char *keyfile, int keyform, int key_type,
+                              char *passargin, int pkey_op, ENGINE *e,
+                              int   impl);
 
 static int setup_peer(BIO *err, EVP_PKEY_CTX *ctx, int peerform,
-                      const char *file);
+                      const char *file, ENGINE* e);
 
 static int do_keyop(EVP_PKEY_CTX *ctx, int pkey_op,
                     unsigned char *out, size_t *poutlen,
@@ -97,10 +98,13 @@ int MAIN(int argc, char **argv)
     EVP_PKEY_CTX *ctx = NULL;
     char *passargin = NULL;
     int keysize = -1;
-
+    int engine_impl = 0;
     unsigned char *buf_in = NULL, *buf_out = NULL, *sig = NULL;
-    size_t buf_outlen;
+    size_t buf_outlen = 0;
     int buf_inlen = 0, siglen = -1;
+    const char *inkey = NULL;
+    const char *peerkey = NULL;
+    STACK_OF(OPENSSL_STRING) *pkeyopts = NULL;
 
     int ret = 1, rv = -1;
 
@@ -134,21 +138,13 @@ int MAIN(int argc, char **argv)
         } else if (!strcmp(*argv, "-inkey")) {
             if (--argc < 1)
                 badarg = 1;
-            else {
-                ctx = init_ctx(&keysize,
-                               *(++argv), keyform, key_type,
-                               passargin, pkey_op, e);
-                if (!ctx) {
-                    BIO_puts(bio_err, "Error initializing context\n");
-                    ERR_print_errors(bio_err);
-                    badarg = 1;
-                }
-            }
+            else
+                inkey = *++argv;
         } else if (!strcmp(*argv, "-peerkey")) {
             if (--argc < 1)
                 badarg = 1;
-            else if (!setup_peer(bio_err, ctx, peerform, *(++argv)))
-                badarg = 1;
+            else
+                peerkey = *++argv;
         } else if (!strcmp(*argv, "-passin")) {
             if (--argc < 1)
                 badarg = 1;
@@ -171,6 +167,8 @@ int MAIN(int argc, char **argv)
                 badarg = 1;
             else
                 e = setup_engine(bio_err, *(++argv), 0);
+        } else if (!strcmp(*argv, "-engine_impl")) {
+                engine_impl = 1;
         }
 #endif
         else if (!strcmp(*argv, "-pubin"))
@@ -187,23 +185,21 @@ int MAIN(int argc, char **argv)
             pkey_op = EVP_PKEY_OP_VERIFY;
         else if (!strcmp(*argv, "-verifyrecover"))
             pkey_op = EVP_PKEY_OP_VERIFYRECOVER;
-        else if (!strcmp(*argv, "-rev"))
-            rev = 1;
         else if (!strcmp(*argv, "-encrypt"))
             pkey_op = EVP_PKEY_OP_ENCRYPT;
         else if (!strcmp(*argv, "-decrypt"))
             pkey_op = EVP_PKEY_OP_DECRYPT;
         else if (!strcmp(*argv, "-derive"))
             pkey_op = EVP_PKEY_OP_DERIVE;
+        else if (!strcmp(*argv, "-rev"))
+            rev = 1;
         else if (strcmp(*argv, "-pkeyopt") == 0) {
             if (--argc < 1)
                 badarg = 1;
-            else if (!ctx) {
-                BIO_puts(bio_err, "-pkeyopt command before -inkey\n");
-                badarg = 1;
-            } else if (pkey_ctrl_string(ctx, *(++argv)) <= 0) {
-                BIO_puts(bio_err, "parameter setting error\n");
-                ERR_print_errors(bio_err);
+            else if ((pkeyopts == NULL &&
+                     (pkeyopts = sk_OPENSSL_STRING_new_null()) == NULL) ||
+                    sk_OPENSSL_STRING_push(pkeyopts, *++argv) == 0) {
+                BIO_puts(bio_err, "out of memory\n");
                 goto end;
             }
         } else
@@ -216,10 +212,37 @@ int MAIN(int argc, char **argv)
         argv++;
     }
 
-    if (!ctx) {
+    if (inkey == NULL ||
+        (peerkey != NULL && pkey_op != EVP_PKEY_OP_DERIVE)) {
         usage();
         goto end;
     }
+    ctx = init_ctx(&keysize, inkey, keyform, key_type,
+                   passargin, pkey_op, e, engine_impl);
+    if (!ctx) {
+        BIO_puts(bio_err, "Error initializing context\n");
+        ERR_print_errors(bio_err);
+        goto end;
+    }
+    if (peerkey != NULL && !setup_peer(bio_err, ctx, peerform, peerkey, e)) {
+        BIO_puts(bio_err, "Error setting up peer key\n");
+        ERR_print_errors(bio_err);
+        goto end;
+    }
+    if (pkeyopts != NULL) {
+        int num = sk_OPENSSL_STRING_num(pkeyopts);
+        int i;
+
+        for (i = 0; i < num; ++i) {
+            const char *opt = sk_OPENSSL_STRING_value(pkeyopts, i);
+
+            if (pkey_ctrl_string(ctx, opt) <= 0) {
+                BIO_puts(bio_err, "parameter setting error\n");
+                ERR_print_errors(bio_err);
+                goto end;
+            }
+        }
+    }
 
     if (sigfile && (pkey_op != EVP_PKEY_OP_VERIFY)) {
         BIO_puts(bio_err, "Signature file specified for non verify\n");
@@ -269,7 +292,7 @@ int MAIN(int argc, char **argv)
         }
         siglen = bio_to_mem(&sig, keysize * 10, sigbio);
         BIO_free(sigbio);
-        if (siglen <= 0) {
+        if (siglen < 0) {
             BIO_printf(bio_err, "Error reading signature data\n");
             goto end;
         }
@@ -278,7 +301,7 @@ int MAIN(int argc, char **argv)
     if (in) {
         /* Read the input data */
         buf_inlen = bio_to_mem(&buf_in, keysize * 10, in);
-        if (buf_inlen <= 0) {
+        if (buf_inlen < 0) {
             BIO_printf(bio_err, "Error reading input Data\n");
             exit(1);
         }
@@ -306,7 +329,7 @@ int MAIN(int argc, char **argv)
     } else {
         rv = do_keyop(ctx, pkey_op, NULL, (size_t *)&buf_outlen,
                       buf_in, (size_t)buf_inlen);
-        if (rv > 0) {
+        if (rv > 0 && buf_outlen != 0) {
             buf_out = OPENSSL_malloc(buf_outlen);
             if (!buf_out)
                 rv = -1;
@@ -336,12 +359,14 @@ int MAIN(int argc, char **argv)
         EVP_PKEY_CTX_free(ctx);
     BIO_free(in);
     BIO_free_all(out);
-    if (buf_in)
+    if (buf_in != NULL)
         OPENSSL_free(buf_in);
-    if (buf_out)
+    if (buf_out != NULL)
         OPENSSL_free(buf_out);
-    if (sig)
+    if (sig != NULL)
         OPENSSL_free(sig);
+    if (pkeyopts != NULL)
+        sk_OPENSSL_STRING_free(pkeyopts);
     return ret;
 }
 
@@ -368,18 +393,21 @@ static void usage()
     BIO_printf(bio_err, "-hexdump        hex dump output\n");
 #ifndef OPENSSL_NO_ENGINE
     BIO_printf(bio_err,
-               "-engine e       use engine e, possibly a hardware device.\n");
+               "-engine e       use engine e, maybe a hardware device, for loading keys.\n");
+    BIO_printf(bio_err, "-engine_impl    also use engine given by -engine for crypto operations\n");
 #endif
     BIO_printf(bio_err, "-passin arg     pass phrase source\n");
 
 }
 
 static EVP_PKEY_CTX *init_ctx(int *pkeysize,
-                              char *keyfile, int keyform, int key_type,
-                              char *passargin, int pkey_op, ENGINE *e)
+                              const char *keyfile, int keyform, int key_type,
+                              char *passargin, int pkey_op, ENGINE *e,
+                              int   engine_impl)
 {
     EVP_PKEY *pkey = NULL;
     EVP_PKEY_CTX *ctx = NULL;
+    ENGINE *impl = NULL;
     char *passin = NULL;
     int rv = -1;
     X509 *x;
@@ -418,9 +446,14 @@ static EVP_PKEY_CTX *init_ctx(int *pkeysize,
 
     if (!pkey)
         goto end;
-
-    ctx = EVP_PKEY_CTX_new(pkey, e);
-
+        
+#ifndef OPENSSL_NO_ENGINE
+    if (engine_impl)
+	impl = e;
+#endif
+            
+    ctx = EVP_PKEY_CTX_new(pkey, impl);
+    
     EVP_PKEY_free(pkey);
 
     if (!ctx)
@@ -467,16 +500,15 @@ static EVP_PKEY_CTX *init_ctx(int *pkeysize,
 }
 
 static int setup_peer(BIO *err, EVP_PKEY_CTX *ctx, int peerform,
-                      const char *file)
+                      const char *file, ENGINE* e)
 {
     EVP_PKEY *peer = NULL;
+    ENGINE* engine = NULL;
     int ret;
-    if (!ctx) {
-        BIO_puts(err, "-peerkey command before -inkey\n");
-        return 0;
-    }
 
-    peer = load_pubkey(bio_err, file, peerform, 0, NULL, NULL, "Peer Key");
+    if (peerform == FORMAT_ENGINE)
+        engine = e;
+    peer = load_pubkey(bio_err, file, peerform, 0, NULL, engine, "Peer Key");
 
     if (!peer) {
         BIO_printf(bio_err, "Error reading peer key %s\n", file);

apps/req.c

@@ -101,8 +101,8 @@
 #define STRING_MASK     "string_mask"
 #define UTF8_IN         "utf8"
 
-#define DEFAULT_KEY_LENGTH      512
-#define MIN_KEY_LENGTH          384
+#define DEFAULT_KEY_LENGTH      2048
+#define MIN_KEY_LENGTH          512
 
 #undef PROG
 #define PROG    req_main

apps/rsautl.c

@@ -250,7 +250,7 @@ int MAIN(int argc, char **argv)
 
     if (outfile) {
         if (!(out = BIO_new_file(outfile, "wb"))) {
-            BIO_printf(bio_err, "Error Reading Output File\n");
+            BIO_printf(bio_err, "Error Writing Output File\n");
             ERR_print_errors(bio_err);
             goto end;
         }
@@ -276,7 +276,7 @@ int MAIN(int argc, char **argv)
 
     /* Read the input data */
     rsa_inlen = BIO_read(in, rsa_in, keysize * 2);
-    if (rsa_inlen <= 0) {
+    if (rsa_inlen < 0) {
         BIO_printf(bio_err, "Error reading input Data\n");
         exit(1);
     }
@@ -311,7 +311,7 @@ int MAIN(int argc, char **argv)
 
     }
 
-    if (rsa_outlen <= 0) {
+    if (rsa_outlen < 0) {
         BIO_printf(bio_err, "RSA operation error\n");
         ERR_print_errors(bio_err);
         goto end;

apps/s_cb.c

@@ -981,6 +981,11 @@ void MS_CALLBACK tlsext_cb(SSL *s, int client_server, int type,
         extname = "next protocol";
         break;
 #endif
+#ifdef TLSEXT_TYPE_application_layer_protocol_negotiation
+    case TLSEXT_TYPE_application_layer_protocol_negotiation:
+        extname = "application layer protocol negotiation";
+        break;
+#endif
 
     case TLSEXT_TYPE_padding:
         extname = "TLS padding";

apps/s_client.c

@@ -308,7 +308,7 @@ static void sc_usage(void)
                " -connect host:port - who to connect to (default is %s:%s)\n",
                SSL_HOST_NAME, PORT_STR);
     BIO_printf(bio_err,
-               " -verify_host host - check peer certificate matches \"host\"\n");
+               " -verify_hostname host - check peer certificate matches \"host\"\n");
     BIO_printf(bio_err,
                " -verify_email email - check peer certificate matches \"email\"\n");
     BIO_printf(bio_err,
@@ -390,8 +390,6 @@ static void sc_usage(void)
                " -no_tls1_2/-no_tls1_1/-no_tls1/-no_ssl3/-no_ssl2 - turn off that protocol\n");
     BIO_printf(bio_err,
                " -bugs         - Switch on all SSL implementation bug workarounds\n");
-    BIO_printf(bio_err,
-               " -serverpref   - Use server's cipher preferences (only SSLv2)\n");
     BIO_printf(bio_err,
                " -cipher       - preferred cipher to use, use the 'openssl ciphers'\n");
     BIO_printf(bio_err,
@@ -424,6 +422,14 @@ static void sc_usage(void)
                " -no_ticket        - disable use of RFC4507bis session tickets\n");
     BIO_printf(bio_err,
                " -serverinfo types - send empty ClientHello extensions (comma-separated numbers)\n");
+    BIO_printf(bio_err,
+               " -curves arg       - Elliptic curves to advertise (colon-separated list)\n");
+    BIO_printf(bio_err,
+               " -sigalgs arg      - Signature algorithms to support (colon-separated list)\n");
+    BIO_printf(bio_err,
+               " -client_sigalgs arg - Signature algorithms to support for client\n");
+    BIO_printf(bio_err,
+               "                       certificate authentication (colon-separated list)\n");
 #endif
 #ifndef OPENSSL_NO_NEXTPROTONEG
     BIO_printf(bio_err,
@@ -2065,6 +2071,9 @@ int MAIN(int argc, char **argv)
         sk_X509_pop_free(chain, X509_free);
     if (pass)
         OPENSSL_free(pass);
+#ifndef OPENSSL_NO_SRP
+    OPENSSL_free(srp_arg.srppassin);
+#endif
     if (vpm)
         X509_VERIFY_PARAM_free(vpm);
     ssl_excert_free(exc);

apps/s_server.c

@@ -429,6 +429,8 @@ typedef struct srpsrvparm_st {
 static int MS_CALLBACK ssl_srp_server_param_cb(SSL *s, int *ad, void *arg)
 {
     srpsrvparm *p = (srpsrvparm *) arg;
+    int ret = SSL3_AL_FATAL;
+
     if (p->login == NULL && p->user == NULL) {
         p->login = SSL_get_srp_username(s);
         BIO_printf(bio_err, "SRP username = \"%s\"\n", p->login);
@@ -437,21 +439,25 @@ static int MS_CALLBACK ssl_srp_server_param_cb(SSL *s, int *ad, void *arg)
 
     if (p->user == NULL) {
         BIO_printf(bio_err, "User %s doesn't exist\n", p->login);
-        return SSL3_AL_FATAL;
+        goto err;
     }
+
     if (SSL_set_srp_server_param
         (s, p->user->N, p->user->g, p->user->s, p->user->v,
          p->user->info) < 0) {
         *ad = SSL_AD_INTERNAL_ERROR;
-        return SSL3_AL_FATAL;
+        goto err;
     }
     BIO_printf(bio_err,
                "SRP parameters set: username = \"%s\" info=\"%s\" \n",
                p->login, p->user->info);
-    /* need to check whether there are memory leaks */
+    ret = SSL_ERROR_NONE;
+
+err:
+    SRP_user_pwd_free(p->user);
     p->user = NULL;
     p->login = NULL;
-    return SSL_ERROR_NONE;
+    return ret;
 }
 
 #endif
@@ -498,7 +504,7 @@ static void sv_usage(void)
     BIO_printf(bio_err,
                " -accept arg   - port to accept on (default is %d)\n", PORT);
     BIO_printf(bio_err,
-               " -verify_host host - check peer certificate matches \"host\"\n");
+               " -verify_hostname host - check peer certificate matches \"host\"\n");
     BIO_printf(bio_err,
                " -verify_email email - check peer certificate matches \"email\"\n");
     BIO_printf(bio_err,
@@ -652,6 +658,12 @@ static void sv_usage(void)
                " -no_ticket    - disable use of RFC4507bis session tickets\n");
     BIO_printf(bio_err,
                " -legacy_renegotiation - enable use of legacy renegotiation (dangerous)\n");
+    BIO_printf(bio_err,
+               " -sigalgs arg      - Signature algorithms to support (colon-separated list)\n");
+    BIO_printf(bio_err,
+               " -client_sigalgs arg  - Signature algorithms to support for client \n");
+    BIO_printf(bio_err,
+               "                        certificate authentication (colon-separated list)\n");
 # ifndef OPENSSL_NO_NEXTPROTONEG
     BIO_printf(bio_err,
                " -nextprotoneg arg - set the advertised protocols for the NPN extension (comma-separated list)\n");
@@ -2446,9 +2458,10 @@ static int sv_body(char *hostname, int s, int stype, unsigned char *context)
 #ifndef OPENSSL_NO_SRP
                 while (SSL_get_error(con, k) == SSL_ERROR_WANT_X509_LOOKUP) {
                     BIO_printf(bio_s_out, "LOOKUP renego during write\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
                     srp_callback_parm.user =
-                        SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                              srp_callback_parm.login);
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
                     if (srp_callback_parm.user)
                         BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                    srp_callback_parm.user->info);
@@ -2502,9 +2515,10 @@ static int sv_body(char *hostname, int s, int stype, unsigned char *context)
 #ifndef OPENSSL_NO_SRP
                 while (SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
                     BIO_printf(bio_s_out, "LOOKUP renego during read\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
                     srp_callback_parm.user =
-                        SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                              srp_callback_parm.login);
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
                     if (srp_callback_parm.user)
                         BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                    srp_callback_parm.user->info);
@@ -2599,9 +2613,10 @@ static int init_ssl_connection(SSL *con)
     while (i <= 0 && SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
         BIO_printf(bio_s_out, "LOOKUP during accept %s\n",
                    srp_callback_parm.login);
+        SRP_user_pwd_free(srp_callback_parm.user);
         srp_callback_parm.user =
-            SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                  srp_callback_parm.login);
+            SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                   srp_callback_parm.login);
         if (srp_callback_parm.user)
             BIO_printf(bio_s_out, "LOOKUP done %s\n",
                        srp_callback_parm.user->info);
@@ -2843,9 +2858,10 @@ static int www_body(char *hostname, int s, int stype, unsigned char *context)
                    && SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
                 BIO_printf(bio_s_out, "LOOKUP during accept %s\n",
                            srp_callback_parm.login);
+                SRP_user_pwd_free(srp_callback_parm.user);
                 srp_callback_parm.user =
-                    SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                          srp_callback_parm.login);
+                    SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                           srp_callback_parm.login);
                 if (srp_callback_parm.user)
                     BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                srp_callback_parm.user->info);
@@ -2881,6 +2897,22 @@ static int www_body(char *hostname, int s, int stype, unsigned char *context)
                 goto err;
             } else {
                 BIO_printf(bio_s_out, "read R BLOCK\n");
+#ifndef OPENSSL_NO_SRP
+                if (BIO_should_io_special(io)
+                    && BIO_get_retry_reason(io) == BIO_RR_SSL_X509_LOOKUP) {
+                    BIO_printf(bio_s_out, "LOOKUP renego during read\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
+                    srp_callback_parm.user =
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
+                    if (srp_callback_parm.user)
+                        BIO_printf(bio_s_out, "LOOKUP done %s\n",
+                                   srp_callback_parm.user->info);
+                    else
+                        BIO_printf(bio_s_out, "LOOKUP not successful\n");
+                    continue;
+                }
+#endif
 #if defined(OPENSSL_SYS_NETWARE)
                 delay(1000);
 #elif !defined(OPENSSL_SYS_MSDOS) && !defined(__DJGPP__)
@@ -3211,6 +3243,22 @@ static int rev_body(char *hostname, int s, int stype, unsigned char *context)
             ERR_print_errors(bio_err);
             goto end;
         }
+#ifndef OPENSSL_NO_SRP
+        if (BIO_should_io_special(io)
+            && BIO_get_retry_reason(io) == BIO_RR_SSL_X509_LOOKUP) {
+            BIO_printf(bio_s_out, "LOOKUP renego during accept\n");
+            SRP_user_pwd_free(srp_callback_parm.user);
+            srp_callback_parm.user =
+                SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                       srp_callback_parm.login);
+            if (srp_callback_parm.user)
+                BIO_printf(bio_s_out, "LOOKUP done %s\n",
+                           srp_callback_parm.user->info);
+            else
+                BIO_printf(bio_s_out, "LOOKUP not successful\n");
+            continue;
+        }
+#endif
     }
     BIO_printf(bio_err, "CONNECTION ESTABLISHED\n");
     print_ssl_summary(bio_err, con);
@@ -3224,6 +3272,22 @@ static int rev_body(char *hostname, int s, int stype, unsigned char *context)
                 goto err;
             } else {
                 BIO_printf(bio_s_out, "read R BLOCK\n");
+#ifndef OPENSSL_NO_SRP
+                if (BIO_should_io_special(io)
+                    && BIO_get_retry_reason(io) == BIO_RR_SSL_X509_LOOKUP) {
+                    BIO_printf(bio_s_out, "LOOKUP renego during read\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
+                    srp_callback_parm.user =
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
+                    if (srp_callback_parm.user)
+                        BIO_printf(bio_s_out, "LOOKUP done %s\n",
+                                   srp_callback_parm.user->info);
+                    else
+                        BIO_printf(bio_s_out, "LOOKUP not successful\n");
+                    continue;
+                }
+#endif
 #if defined(OPENSSL_SYS_NETWARE)
                 delay(1000);
 #elif !defined(OPENSSL_SYS_MSDOS) && !defined(__DJGPP__)

apps/speed.c

@@ -1,4 +1,4 @@
-/* apps/speed.c -*- mode:C; c-file-style: "eay" -*- */
+/* apps/speed.c */
 /* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
  * All rights reserved.
  *

apps/x509.c

@@ -1226,12 +1226,7 @@ static int sign(X509 *x, EVP_PKEY *pkey, int days, int clrext,
     if (X509_gmtime_adj(X509_get_notBefore(x), 0) == NULL)
         goto err;
 
-    /* Lets just make it 12:00am GMT, Jan 1 1970 */
-    /* memcpy(x->cert_info->validity->notBefore,"700101120000Z",13); */
-    /* 28 days to be certified */
-
-    if (X509_gmtime_adj(X509_get_notAfter(x), (long)60 * 60 * 24 * days) ==
-        NULL)
+    if (X509_time_adj_ex(X509_get_notAfter(x), days, 0, NULL) == NULL)
         goto err;
 
     if (!X509_set_pubkey(x, pkey))

appveyor.yml

@@ -0,0 +1,60 @@
+platform:
+    - x86
+    - x64
+
+environment:
+    matrix:
+        - VSVER: 9
+        - VSVER: 10
+        - VSVER: 11
+        - VSVER: 12
+        - VSVER: 14
+
+configuration:
+    - plain
+    - shared
+
+matrix:
+    allow_failures:
+        - platform: x64
+          VSVER: 9
+        - platform: x64
+          VSVER: 10
+        - platform: x64
+          VSVER: 11
+
+before_build:
+    - ps: >-
+        If ($env:Platform -Match "x86") {
+            $env:VCVARS_PLATFORM="x86"
+            $env:TARGET="VC-WIN32"
+            $env:DO="do_ms"
+        } Else {
+            $env:VCVARS_PLATFORM="amd64"
+            $env:TARGET="VC-WIN64A"
+            $env:DO="do_win64a"
+        }
+    - ps: >-
+        If ($env:Configuration -Like "*shared*") {
+            $env:MAK="ntdll.mak"
+        } Else {
+            $env:MAK="nt.mak"
+        }
+    - ps: $env:VSCOMNTOOLS=(Get-Content ("env:VS" + "$env:VSVER" + "0COMNTOOLS"))
+    - call "%VSCOMNTOOLS%\..\..\VC\vcvarsall.bat" %VCVARS_PLATFORM%
+    - perl Configure %TARGET% no-asm
+    - call ms\%DO%
+
+build_script:
+    - nmake /f ms\%MAK%
+
+test_script:
+    - nmake /f ms\%MAK% test
+
+notifications:
+    - provider: Email
+      to:
+          - openssl-commits@openssl.org
+      on_build_success: false
+      on_build_failure: true
+      on_build_status_changed: true

config

@@ -852,7 +852,8 @@ case "$GUESSOS" in
   # *-dgux) OUT="dgux" ;;
   mips-sony-newsos4) OUT="newsos4-gcc" ;;
   *-*-cygwin_pre1.3) OUT="Cygwin-pre1.3" ;;
-  *-*-cygwin) OUT="Cygwin" ;;
+  i[3456]86-*-cygwin) OUT="Cygwin" ;;
+  *-*-cygwin) OUT="Cygwin-${MACHINE}" ;;
   t3e-cray-unicosmk) OUT="cray-t3e" ;;
   j90-cray-unicos) OUT="cray-j90" ;;
   nsr-tandem-nsk) OUT="tandem-c89" ;;

crypto/.cvsignore

@@ -1,8 +0,0 @@
-lib
-buildinf.h
-opensslconf.h
-Makefile.save
-*.flc
-semantic.cache
-*cpuid.s
-uplink-cof.s

crypto/aes/.cvsignore

@@ -1,8 +0,0 @@
-lib
-Makefile.save
-*.flc
-semantic.cache
-aes-*.s
-aesni-*.s
-bsaes-*.s
-vpaes-*.s

crypto/aes/aes.h

@@ -1,4 +1,4 @@
-/* crypto/aes/aes.h -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes.h */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_cbc.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_cbc.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_cbc.c */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_cfb.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_cfb.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_cfb.c */
 /* ====================================================================
  * Copyright (c) 2002-2006 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_core.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_core.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_core.c */
 /**
  * rijndael-alg-fst.c
  *

crypto/aes/aes_ctr.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_ctr.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_ctr.c */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_ecb.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_ecb.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_ecb.c */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_ige.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_ige.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_ige.c */
 /* ====================================================================
  * Copyright (c) 2006 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_locl.h

@@ -1,4 +1,4 @@
-/* crypto/aes/aes.h -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes.h */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_misc.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_misc.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_misc.c */
 /* ====================================================================
  * Copyright (c) 1998-2002 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_ofb.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_ofb.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_ofb.c */
 /* ====================================================================
  * Copyright (c) 2002-2006 The OpenSSL Project.  All rights reserved.
  *

crypto/aes/aes_x86core.c

@@ -1,4 +1,4 @@
-/* crypto/aes/aes_core.c -*- mode:C; c-file-style: "eay" -*- */
+/* crypto/aes/aes_core.c */
 /**
  * rijndael-alg-fst.c
  *

crypto/aes/asm/aes-586.pl

@@ -45,7 +45,7 @@
 # the undertaken effort was that it appeared that in tight IA-32
 # register window little-endian flavor could achieve slightly higher
 # Instruction Level Parallelism, and it indeed resulted in up to 15%
-# better performance on most recent <EFBFBD>-archs...
+# better performance on most recent µ-archs...
 #
 # Third version adds AES_cbc_encrypt implementation, which resulted in
 # up to 40% performance imrovement of CBC benchmark results. 40% was
@@ -224,7 +224,7 @@ sub _data_word() { my $i; while(defined($i=shift)) { &data_word($i,$i); } }
 $speed_limit=512;	# chunks smaller than $speed_limit are
 			# processed with compact routine in CBC mode
 $small_footprint=1;	# $small_footprint=1 code is ~5% slower [on
-			# recent <EFBFBD>-archs], but ~5 times smaller!
+			# recent µ-archs], but ~5 times smaller!
 			# I favor compact code to minimize cache
 			# contention and in hope to "collect" 5% back
 			# in real-life applications...
@@ -565,7 +565,7 @@ sub enctransform()
 # Performance is not actually extraordinary in comparison to pure
 # x86 code. In particular encrypt performance is virtually the same.
 # Decrypt performance on the other hand is 15-20% better on newer
-# <EFBFBD>-archs [but we're thankful for *any* improvement here], and ~50%
+# µ-archs [but we're thankful for *any* improvement here], and ~50%
 # better on PIII:-) And additionally on the pros side this code
 # eliminates redundant references to stack and thus relieves/
 # minimizes the pressure on the memory bus.

crypto/aes/asm/aes-ppc.pl

@@ -590,7 +590,7 @@ Lenc_loop:
 	xor	$s2,$t2,$acc14
 	xor	$s3,$t3,$acc15
 	addi	$key,$key,16
-	bdnz-	Lenc_loop
+	bdnz	Lenc_loop
 
 	addi	$Tbl2,$Tbl0,2048
 	nop
@@ -1068,7 +1068,7 @@ Ldec_loop:
 	xor	$s2,$t2,$acc14
 	xor	$s3,$t3,$acc15
 	addi	$key,$key,16
-	bdnz-	Ldec_loop
+	bdnz	Ldec_loop
 
 	addi	$Tbl2,$Tbl0,2048
 	nop

crypto/aes/asm/aes-s390x.pl

@@ -818,13 +818,9 @@ $code.=<<___ if (!$softonly);
 	tmhl	%r0,0x4000	# check for message-security assist
 	jz	.Lekey_internal
 
-	lghi	%r0,0		# query capability vector
-	la	%r1,16($sp)
-	.long	0xb92f0042	# kmc %r4,%r2
-
-	llihh	%r1,0x8000
-	srlg	%r1,%r1,0(%r5)
-	ng	%r1,16($sp)
+	llihh	%r0,0x8000
+	srlg	%r0,%r0,0(%r5)
+	ng	%r0,48(%r1)	# check kmc capability vector
 	jz	.Lekey_internal
 
 	lmg	%r0,%r1,0($inp)	# just copy 128 bits...
@@ -1444,13 +1440,10 @@ $code.=<<___ if (0);	######### kmctr code was measured to be ~12% slower
 
 	llgfr	$s0,%r0
 	lgr	$s1,%r1
-	lghi	%r0,0
-	la	%r1,16($sp)
-	.long	0xb92d2042	# kmctr %r4,%r2,%r2
-
+	larl	%r1,OPENSSL_s390xcap_P
 	llihh	%r0,0x8000	# check if kmctr supports the function code
 	srlg	%r0,%r0,0($s0)
-	ng	%r0,16($sp)
+	ng	%r0,64(%r1)	# check kmctr capability vector
 	lgr	%r0,$s0
 	lgr	%r1,$s1
 	jz	.Lctr32_km_loop
@@ -1597,12 +1590,10 @@ $code.=<<___ if(1);
 	llgfr	$s0,%r0			# put aside the function code
 	lghi	$s1,0x7f
 	nr	$s1,%r0
-	lghi	%r0,0			# query capability vector
-	la	%r1,$tweak-16($sp)
-	.long	0xb92e0042		# km %r4,%r2
-	llihh	%r1,0x8000
-	srlg	%r1,%r1,32($s1)		# check for 32+function code
-	ng	%r1,$tweak-16($sp)
+	larl	%r1,OPENSSL_s390xcap_P
+	llihh	%r0,0x8000
+	srlg	%r0,%r0,32($s1)		# check for 32+function code
+	ng	%r0,32(%r1)		# check km capability vector
 	lgr	%r0,$s0			# restore the function code
 	la	%r1,0($key1)		# restore $key1
 	jz	.Lxts_km_vanilla
@@ -2229,7 +2220,7 @@ ___
 }
 $code.=<<___;
 .string	"AES for s390x, CRYPTOGAMS by <appro\@openssl.org>"
-.comm	OPENSSL_s390xcap_P,16,8
+.comm	OPENSSL_s390xcap_P,80,8
 ___
 
 $code =~ s/\`([^\`]*)\`/eval $1/gem;

crypto/aes/asm/aesni-mb-x86_64.pl

@@ -63,7 +63,7 @@ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
 	$avx = ($1>=10) + ($1>=11);
 }
 
-if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/) {
+if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) {
 	$avx = ($2>=3.0) + ($2>3.0);
 }
 

crypto/aes/asm/aesni-sha1-x86_64.pl

@@ -94,7 +94,7 @@ $avx=1 if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) &&
 $avx=1 if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
 	   `ml64 2>&1` =~ /Version ([0-9]+)\./ &&
 	   $1>=10);
-$avx=1 if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/ && $2>=3.0);
+$avx=1 if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/ && $2>=3.0);
 
 $shaext=1;	### set to zero if compiling for 1.0.1
 

crypto/aes/asm/aesni-sha256-x86_64.pl

@@ -59,7 +59,7 @@ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
 	$avx = ($1>=10) + ($1>=12);
 }
 
-if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/) {
+if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) {
 	$avx = ($2>=3.0) + ($2>3.0);
 }
 
@@ -139,11 +139,8 @@ $code.=<<___ if ($avx>1);
 	je	${func}_avx2
 ___
 $code.=<<___;
-	and	\$`1<<30`,%eax			# mask "Intel CPU" bit
-	and	\$`1<<28|1<<9`,%r10d		# mask AVX+SSSE3 bits
-	or	%eax,%r10d
-	cmp	\$`1<<28|1<<9|1<<30`,%r10d
-	je	${func}_avx
+	and	\$`1<<28`,%r10d			# check for AVX
+	jnz	${func}_avx
 	ud2
 ___
 						}

crypto/aes/asm/aesni-x86.pl

@@ -88,7 +88,7 @@ $inout3="xmm5";	$in1="xmm5";
 $inout4="xmm6";	$in0="xmm6";
 $inout5="xmm7";	$ivec="xmm7";
 
-# AESNI extenstion
+# AESNI extension
 sub aeskeygenassist
 { my($dst,$src,$imm)=@_;
     if ("$dst:$src" =~ /xmm([0-7]):xmm([0-7])/)

crypto/aes/asm/vpaes-ppc.pl

@@ -337,24 +337,27 @@ Lenc_entry:
 	addi	$inp, $inp, 15		# 15 is not a typo
 	 ?lvsr	$outperm, 0, $out
 	?lvsl	$keyperm, 0, $key	# prepare for unaligned access
-	 vnor	$outmask, v7, v7	# 0xff..ff
 	lvx	$inptail, 0, $inp	# redundant in aligned case
-	 ?vperm	$outmask, v7, $outmask, $outperm
-	 lvx	$outhead, 0, $out
 	?vperm	v0, v0, $inptail, $inpperm
 
 	bl	_vpaes_encrypt_core
 
-	vperm	v0, v0, v0, $outperm	# rotate right/left
-	vsel	v1, $outhead, v0, $outmask
-	vmr	$outhead, v0
-	stvx	v1, 0, $out
-	addi	$out, $out, 15		# 15 is not a typo
-	########
+	andi.	r8, $out, 15
+	li	r9, 16
+	beq	Lenc_out_aligned
 
-	lvx	v1, 0, $out		# redundant in aligned case
-	vsel	v1, $outhead, v1, $outmask
-	stvx	v1, 0, $out
+	vperm	v0, v0, v0, $outperm	# rotate right/left
+	mtctr	r9
+Lenc_out_unaligned:
+	stvebx	v0, 0, $out
+	addi	$out, $out, 1
+	bdnz	Lenc_out_unaligned
+	b	Lenc_done
+
+.align	4
+Lenc_out_aligned:
+	stvx	v0, 0, $out
+Lenc_done:
 
 	li	r10,`15+6*$SIZE_T`
 	li	r11,`31+6*$SIZE_T`
@@ -566,24 +569,27 @@ Ldec_entry:
 	addi	$inp, $inp, 15		# 15 is not a typo
 	 ?lvsr	$outperm, 0, $out
 	?lvsl	$keyperm, 0, $key
-	 vnor	$outmask, v7, v7	# 0xff..ff
 	lvx	$inptail, 0, $inp	# redundant in aligned case
-	 ?vperm	$outmask, v7, $outmask, $outperm
-	 lvx	$outhead, 0, $out
 	?vperm	v0, v0, $inptail, $inpperm
 
 	bl	_vpaes_decrypt_core
 
-	vperm	v0, v0, v0, $outperm	# rotate right/left
-	vsel	v1, $outhead, v0, $outmask
-	vmr	$outhead, v0
-	stvx	v1, 0, $out
-	addi	$out, $out, 15		# 15 is not a typo
-	########
+	andi.	r8, $out, 15
+	li	r9, 16
+	beq	Ldec_out_aligned
 
-	lvx	v1, 0, $out		# redundant in aligned case
-	vsel	v1, $outhead, v1, $outmask
-	stvx	v1, 0, $out
+	vperm	v0, v0, v0, $outperm	# rotate right/left
+	mtctr	r9
+Ldec_out_unaligned:
+	stvebx	v0, 0, $out
+	addi	$out, $out, 1
+	bdnz	Ldec_out_unaligned
+	b	Ldec_done
+
+.align	4
+Ldec_out_aligned:
+	stvx	v0, 0, $out
+Ldec_done:
 
 	li	r10,`15+6*$SIZE_T`
 	li	r11,`31+6*$SIZE_T`
@@ -658,11 +664,11 @@ Ldec_entry:
 	$PUSH	r0, `$FRAME+$SIZE_T*2+$LRSAVE`($sp)
 
 	and	r30, r5, r9		# copy length&-16
+	andi.	r9, $out, 15		# is $out aligned?
 	mr	r5, r6			# copy pointer to key
 	mr	r31, r7			# copy pointer to iv
-	blt	Lcbc_abort
-	cmpwi	r8, 0			# test direction
 	li	r6, -1
+	mcrf	cr1, cr0		# put aside $out alignment flag
 	mr	r7, r12			# copy vrsave
 	mtspr	256, r6			# preserve all AltiVec registers
 
@@ -672,6 +678,7 @@ Ldec_entry:
 	lvx	v25, r9, r31
 	?vperm	v24, v24, v25, $inpperm
 
+	cmpwi	r8, 0			# test direction
 	neg	r8, $inp		# prepare for unaligned access
 	 vxor	v7, v7, v7
 	?lvsl	$keyperm, 0, $key
@@ -681,13 +688,37 @@ Ldec_entry:
 	lvx	$inptail, 0, $inp
 	 ?vperm	$outmask, v7, $outmask, $outperm
 	addi	$inp, $inp, 15		# 15 is not a typo
-	 lvx	$outhead, 0, $out
 
 	beq	Lcbc_decrypt
 
 	bl	_vpaes_encrypt_preheat
 	li	r0, 16
 
+	beq	cr1, Lcbc_enc_loop	# $out is aligned
+
+	vmr	v0, $inptail
+	lvx	$inptail, 0, $inp
+	addi	$inp, $inp, 16
+	?vperm	v0, v0, $inptail, $inpperm
+	vxor	v0, v0, v24		# ^= iv
+
+	bl	_vpaes_encrypt_core
+
+	andi.	r8, $out, 15
+	vmr	v24, v0			# put aside iv
+	sub	r9, $out, r8
+	vperm	$outhead, v0, v0, $outperm	# rotate right/left
+
+Lcbc_enc_head:
+	stvebx	$outhead, r8, r9
+	cmpwi	r8, 15
+	addi	r8, r8, 1
+	bne	Lcbc_enc_head
+
+	sub.	r30, r30, r0		# len -= 16
+	addi	$out, $out, 16
+	beq	Lcbc_unaligned_done
+
 Lcbc_enc_loop:
 	vmr	v0, $inptail
 	lvx	$inptail, 0, $inp
@@ -713,6 +744,32 @@ Lcbc_decrypt:
 	bl	_vpaes_decrypt_preheat
 	li	r0, 16
 
+	beq	cr1, Lcbc_dec_loop	# $out is aligned
+
+	vmr	v0, $inptail
+	lvx	$inptail, 0, $inp
+	addi	$inp, $inp, 16
+	?vperm	v0, v0, $inptail, $inpperm
+	vmr	v25, v0			# put aside input
+
+	bl	_vpaes_decrypt_core
+
+	andi.	r8, $out, 15
+	vxor	v0, v0, v24		# ^= iv
+	vmr	v24, v25
+	sub	r9, $out, r8
+	vperm	$outhead, v0, v0, $outperm	# rotate right/left
+
+Lcbc_dec_head:
+	stvebx	$outhead, r8, r9
+	cmpwi	r8, 15
+	addi	r8, r8, 1
+	bne	Lcbc_dec_head
+
+	sub.	r30, r30, r0		# len -= 16
+	addi	$out, $out, 16
+	beq	Lcbc_unaligned_done
+
 Lcbc_dec_loop:
 	vmr	v0, $inptail
 	lvx	$inptail, 0, $inp
@@ -733,23 +790,29 @@ Lcbc_dec_loop:
 	bne	Lcbc_dec_loop
 
 Lcbc_done:
-	addi	$out, $out, -1
-	lvx	v1, 0, $out		# redundant in aligned case
-	vsel	v1, $outhead, v1, $outmask
-	stvx	v1, 0, $out
+	beq	cr1, Lcbc_write_iv	# $out is aligned
 
+Lcbc_unaligned_done:
+	andi.	r8, $out, 15
+	sub	$out, $out, r8
+	li	r9, 0
+Lcbc_tail:
+	stvebx	$outhead, r9, $out
+	addi	r9, r9, 1
+	cmpw	r9, r8
+	bne	Lcbc_tail
+
+Lcbc_write_iv:
 	neg	r8, r31			# write [potentially unaligned] iv
+	li	r10, 4
 	?lvsl	$outperm, 0, r8
-	li	r6, 15
-	vnor	$outmask, v7, v7	# 0xff..ff
-	?vperm	$outmask, v7, $outmask, $outperm
-	lvx	$outhead, 0, r31
+	li	r11, 8
+	li	r12, 12
 	vperm	v24, v24, v24, $outperm	# rotate right/left
-	vsel	v0, $outhead, v24, $outmask
-	lvx	v1, r6, r31
-	stvx	v0, 0, r31
-	vsel	v1, v24, v1, $outmask
-	stvx	v1, r6, r31
+	stvewx	v24, 0, r31		# ivp is at least 32-bit aligned
+	stvewx	v24, r10, r31
+	stvewx	v24, r11, r31
+	stvewx	v24, r12, r31
 
 	mtspr	256, r7			# restore vrsave
 	li	r10,`15+6*$SIZE_T`
@@ -872,18 +935,21 @@ _vpaes_schedule_core:
 
 	# encrypting, output zeroth round key after transform
 	li	r8, 0x30		# mov	\$0x30,%r8d
-	addi	r10, r12, 0x80		# lea	.Lk_sr(%rip),%r10
+	li	r9, 4
+	li	r10, 8
+	li	r11, 12
 
 	?lvsr	$outperm, 0, $out	# prepare for unaligned access
 	vnor	$outmask, v9, v9	# 0xff..ff
-	lvx	$outhead, 0, $out
 	?vperm	$outmask, v9, $outmask, $outperm
 
 	#stvx	v0, 0, $out		# vmovdqu	%xmm0,	(%rdx)
-	vperm	v1, v0, v0, $outperm	# rotate right/left
-	vsel	v2, $outhead, v1, $outmask
-	vmr	$outhead, v1
-	stvx	v2, 0, $out
+	vperm	$outhead, v0, v0, $outperm	# rotate right/left
+	stvewx	$outhead, 0, $out	# some are superfluous
+	stvewx	$outhead, r9, $out
+	stvewx	$outhead, r10, $out
+	addi	r10, r12, 0x80		# lea	.Lk_sr(%rip),%r10
+	stvewx	$outhead, r11, $out
 	b	Lschedule_go
 
 Lschedule_am_decrypting:
@@ -893,20 +959,24 @@ Lschedule_am_decrypting:
 	addi	r10, r12, 0x80		# lea	.Lk_sr(%rip),%r10
 	# decrypting, output zeroth round key after shiftrows
 	lvx	v1, r8, r10		# vmovdqa	(%r8,%r10),	%xmm1
+	li	r9, 4
+	li	r10, 8
+	li	r11, 12
 	vperm	v4, v3, v3, v1		# vpshufb	%xmm1,	%xmm3,	%xmm3
 
 	neg	r0, $out		# prepare for unaligned access
 	?lvsl	$outperm, 0, r0
-	addi	$out, $out, 15		# 15 is not typo
 	vnor	$outmask, v9, v9	# 0xff..ff
-	lvx	$outhead, 0, $out
 	?vperm	$outmask, $outmask, v9, $outperm
 
 	#stvx	v4, 0, $out		# vmovdqu	%xmm3,	(%rdx)
-	vperm	v4, v4, v4, $outperm	# rotate right/left
-	vsel	v2, $outhead, v4, $outmask
-	vmr	$outhead, v4
-	stvx	v2, 0, $out
+	vperm	$outhead, v4, v4, $outperm	# rotate right/left
+	stvewx	$outhead, 0, $out	# some are superfluous
+	stvewx	$outhead, r9, $out
+	stvewx	$outhead, r10, $out
+	addi	r10, r12, 0x80		# lea	.Lk_sr(%rip),%r10
+	stvewx	$outhead, r11, $out
+	addi	$out, $out, 15		# 15 is not typo
 	xori	r8, r8, 0x30		# xor	\$0x30, %r8
 
 Lschedule_go:
@@ -1038,14 +1108,15 @@ Lschedule_mangle_last:
 
 	#stvx	v0, r0, $out		# vmovdqu	%xmm0,	(%rdx)		# save last key
 	vperm	v0, v0, v0, $outperm	# rotate right/left
+	li	r10, 4
 	vsel	v2, $outhead, v0, $outmask
-	vmr	$outhead, v0
+	li	r11, 8
 	stvx	v2, 0, $out
-
-	addi	$out, $out, 15		# 15 is not typo
-	lvx	v1, 0, $out		# redundant in aligned case
-	vsel	v1, $outhead, v1, $outmask
-	stvx	v1, 0, $out
+	li	r12, 12
+	stvewx	v0, 0, $out		# some (or all) are redundant
+	stvewx	v0, r10, $out
+	stvewx	v0, r11, $out
+	stvewx	v0, r12, $out
 	b	Lschedule_mangle_done
 
 .align	4
@@ -1057,15 +1128,18 @@ Lschedule_mangle_last_dec:
 	bl	_vpaes_schedule_transform	# output transform
 
 	#stvx	v0, r0, $out		# vmovdqu	%xmm0,	(%rdx)		# save last key
+	addi	r9, $out, -15		# -15 is not typo
 	vperm	v0, v0, v0, $outperm	# rotate right/left
+	li	r10, 4
 	vsel	v2, $outhead, v0, $outmask
-	vmr	$outhead, v0
+	li	r11, 8
 	stvx	v2, 0, $out
+	li	r12, 12
+	stvewx	v0, 0, r9		# some (or all) are redundant
+	stvewx	v0, r10, r9
+	stvewx	v0, r11, r9
+	stvewx	v0, r12, r9
 
-	addi	$out, $out, -15		# -15 is not typo
-	lvx	v1, 0, $out		# redundant in aligned case
-	vsel	v1, $outhead, v1, $outmask
-	stvx	v1, 0, $out
 
 Lschedule_mangle_done:
 	mtlr	r7

crypto/asn1/.cvsignore

@@ -1,4 +0,0 @@
-lib
-Makefile.save
-*.flc
-semantic.cache

crypto/asn1/a_bytes.c

@@ -200,13 +200,13 @@ ASN1_STRING *d2i_ASN1_bytes(ASN1_STRING **a, const unsigned char **pp,
     } else {
         if (len != 0) {
             if ((ret->length < len) || (ret->data == NULL)) {
-                if (ret->data != NULL)
-                    OPENSSL_free(ret->data);
                 s = (unsigned char *)OPENSSL_malloc((int)len + 1);
                 if (s == NULL) {
                     i = ERR_R_MALLOC_FAILURE;
                     goto err;
                 }
+                if (ret->data != NULL)
+                    OPENSSL_free(ret->data);
             } else
                 s = ret->data;
             memcpy(s, p, (int)len);

crypto/asn1/a_d2i_fp.c

@@ -141,6 +141,7 @@ void *ASN1_item_d2i_fp(const ASN1_ITEM *it, FILE *in, void *x)
 #endif
 
 #define HEADER_SIZE   8
+#define ASN1_CHUNK_INITIAL_SIZE (16 * 1024)
 static int asn1_d2i_read_bio(BIO *in, BUF_MEM **pb)
 {
     BUF_MEM *b;
@@ -217,29 +218,44 @@ static int asn1_d2i_read_bio(BIO *in, BUF_MEM **pb)
             /* suck in c.slen bytes of data */
             want = c.slen;
             if (want > (len - off)) {
+                size_t chunk_max = ASN1_CHUNK_INITIAL_SIZE;
+
                 want -= (len - off);
                 if (want > INT_MAX /* BIO_read takes an int length */  ||
                     len + want < len) {
                     ASN1err(ASN1_F_ASN1_D2I_READ_BIO, ASN1_R_TOO_LONG);
                     goto err;
                 }
-                if (!BUF_MEM_grow_clean(b, len + want)) {
-                    ASN1err(ASN1_F_ASN1_D2I_READ_BIO, ERR_R_MALLOC_FAILURE);
-                    goto err;
-                }
                 while (want > 0) {
-                    i = BIO_read(in, &(b->data[len]), want);
-                    if (i <= 0) {
-                        ASN1err(ASN1_F_ASN1_D2I_READ_BIO,
-                                ASN1_R_NOT_ENOUGH_DATA);
+                    /*
+                     * Read content in chunks of increasing size
+                     * so we can return an error for EOF without
+                     * having to allocate the entire content length
+                     * in one go.
+                     */
+                    size_t chunk = want > chunk_max ? chunk_max : want;
+
+                    if (!BUF_MEM_grow_clean(b, len + chunk)) {
+                        ASN1err(ASN1_F_ASN1_D2I_READ_BIO, ERR_R_MALLOC_FAILURE);
                         goto err;
                     }
+                    want -= chunk;
+                    while (chunk > 0) {
+                        i = BIO_read(in, &(b->data[len]), chunk);
+                        if (i <= 0) {
+                            ASN1err(ASN1_F_ASN1_D2I_READ_BIO,
+                                    ASN1_R_NOT_ENOUGH_DATA);
+                            goto err;
+                        }
                     /*
                      * This can't overflow because |len+want| didn't
                      * overflow.
                      */
-                    len += i;
-                    want -= i;
+                        len += i;
+                        chunk -= i;
+                    }
+                    if (chunk_max < INT_MAX/2)
+                        chunk_max *= 2;
                 }
             }
             if (off + c.slen < off) {

crypto/asn1/asn1_lib.c

@@ -63,7 +63,7 @@
 #include <openssl/asn1_mac.h>
 
 static int asn1_get_length(const unsigned char **pp, int *inf, long *rl,
-                           int max);
+                           long max);
 static void asn1_put_length(unsigned char **pp, int length);
 const char ASN1_version[] = "ASN.1" OPENSSL_VERSION_PTEXT;
 
@@ -131,7 +131,7 @@ int ASN1_get_object(const unsigned char **pp, long *plength, int *ptag,
     }
     *ptag = tag;
     *pclass = xclass;
-    if (!asn1_get_length(&p, &inf, plength, (int)max))
+    if (!asn1_get_length(&p, &inf, plength, max))
         goto err;
 
     if (inf && !(ret & V_ASN1_CONSTRUCTED))
@@ -159,14 +159,14 @@ int ASN1_get_object(const unsigned char **pp, long *plength, int *ptag,
 }
 
 static int asn1_get_length(const unsigned char **pp, int *inf, long *rl,
-                           int max)
+                           long max)
 {
     const unsigned char *p = *pp;
     unsigned long ret = 0;
-    unsigned int i;
+    unsigned long i;
 
     if (max-- < 1)
-        return (0);
+        return 0;
     if (*p == 0x80) {
         *inf = 1;
         ret = 0;
@@ -175,15 +175,11 @@ static int asn1_get_length(const unsigned char **pp, int *inf, long *rl,
         *inf = 0;
         i = *p & 0x7f;
         if (*(p++) & 0x80) {
-            if (i > sizeof(long))
+            if (i > sizeof(ret) || max < (long)i)
                 return 0;
-            if (max-- == 0)
-                return (0);
             while (i-- > 0) {
                 ret <<= 8L;
                 ret |= *(p++);
-                if (max-- == 0)
-                    return (0);
             }
         } else
             ret = i;
@@ -192,7 +188,7 @@ static int asn1_get_length(const unsigned char **pp, int *inf, long *rl,
         return 0;
     *pp = p;
     *rl = (long)ret;
-    return (1);
+    return 1;
 }
 
 /*

crypto/asn1/asn1_par.c

@@ -62,6 +62,10 @@
 #include <openssl/objects.h>
 #include <openssl/asn1.h>
 
+#ifndef ASN1_PARSE_MAXDEPTH
+#define ASN1_PARSE_MAXDEPTH 128
+#endif
+
 static int asn1_print_info(BIO *bp, int tag, int xclass, int constructed,
                            int indent);
 static int asn1_parse2(BIO *bp, const unsigned char **pp, long length,
@@ -128,6 +132,12 @@ static int asn1_parse2(BIO *bp, const unsigned char **pp, long length,
 #else
     dump_indent = 6;            /* Because we know BIO_dump_indent() */
 #endif
+
+    if (depth > ASN1_PARSE_MAXDEPTH) {
+            BIO_puts(bp, "BAD RECURSION DEPTH\n");
+            return 0;
+    }
+
     p = *pp;
     tot = p + length;
     op = p - 1;
@@ -163,6 +173,8 @@ static int asn1_parse2(BIO *bp, const unsigned char **pp, long length,
         if (!asn1_print_info(bp, tag, xclass, j, (indent) ? depth : 0))
             goto end;
         if (j & V_ASN1_CONSTRUCTED) {
+            const unsigned char *sp;
+
             ep = p + len;
             if (BIO_write(bp, "\n", 1) <= 0)
                 goto end;
@@ -172,6 +184,7 @@ static int asn1_parse2(BIO *bp, const unsigned char **pp, long length,
                 goto end;
             }
             if ((j == 0x21) && (len == 0)) {
+                sp = p;
                 for (;;) {
                     r = asn1_parse2(bp, &p, (long)(tot - p),
                                     offset + (p - *pp), depth + 1,
@@ -180,19 +193,25 @@ static int asn1_parse2(BIO *bp, const unsigned char **pp, long length,
                         ret = 0;
                         goto end;
                     }
-                    if ((r == 2) || (p >= tot))
+                    if ((r == 2) || (p >= tot)) {
+                        len = p - sp;
                         break;
+                    }
                 }
-            } else
+            } else {
+                long tmp = len;
+
                 while (p < ep) {
-                    r = asn1_parse2(bp, &p, (long)len,
-                                    offset + (p - *pp), depth + 1,
+                    sp = p;
+                    r = asn1_parse2(bp, &p, tmp, offset + (p - *pp), depth + 1,
                                     indent, dump);
                     if (r == 0) {
                         ret = 0;
                         goto end;
                     }
+                    tmp -= p - sp;
                 }
+            }
         } else if (xclass != 0) {
             p += len;
             if (BIO_write(bp, "\n", 1) <= 0)

crypto/asn1/d2i_pr.c

@@ -72,6 +72,7 @@ EVP_PKEY *d2i_PrivateKey(int type, EVP_PKEY **a, const unsigned char **pp,
                          long length)
 {
     EVP_PKEY *ret;
+    const unsigned char *p = *pp;
 
     if ((a == NULL) || (*a == NULL)) {
         if ((ret = EVP_PKEY_new()) == NULL) {
@@ -94,21 +95,23 @@ EVP_PKEY *d2i_PrivateKey(int type, EVP_PKEY **a, const unsigned char **pp,
     }
 
     if (!ret->ameth->old_priv_decode ||
-        !ret->ameth->old_priv_decode(ret, pp, length)) {
+        !ret->ameth->old_priv_decode(ret, &p, length)) {
         if (ret->ameth->priv_decode) {
             PKCS8_PRIV_KEY_INFO *p8 = NULL;
-            p8 = d2i_PKCS8_PRIV_KEY_INFO(NULL, pp, length);
+            p8 = d2i_PKCS8_PRIV_KEY_INFO(NULL, &p, length);
             if (!p8)
                 goto err;
             EVP_PKEY_free(ret);
             ret = EVP_PKCS82PKEY(p8);
             PKCS8_PRIV_KEY_INFO_free(p8);
-
+            if (ret == NULL)
+                goto err;
         } else {
             ASN1err(ASN1_F_D2I_PRIVATEKEY, ERR_R_ASN1_LIB);
             goto err;
         }
     }
+    *pp = p;
     if (a != NULL)
         (*a) = ret;
     return (ret);
@@ -136,6 +139,7 @@ EVP_PKEY *d2i_AutoPrivateKey(EVP_PKEY **a, const unsigned char **pp,
      * input is surrounded by an ASN1 SEQUENCE.
      */
     inkey = d2i_ASN1_SEQUENCE_ANY(NULL, &p, length);
+    p = *pp;
     /*
      * Since we only need to discern "traditional format" RSA and DSA keys we
      * can just count the elements.
@@ -146,7 +150,7 @@ EVP_PKEY *d2i_AutoPrivateKey(EVP_PKEY **a, const unsigned char **pp,
         keytype = EVP_PKEY_EC;
     else if (sk_ASN1_TYPE_num(inkey) == 3) { /* This seems to be PKCS8, not
                                               * traditional format */
-        PKCS8_PRIV_KEY_INFO *p8 = d2i_PKCS8_PRIV_KEY_INFO(NULL, pp, length);
+        PKCS8_PRIV_KEY_INFO *p8 = d2i_PKCS8_PRIV_KEY_INFO(NULL, &p, length);
         EVP_PKEY *ret;
 
         sk_ASN1_TYPE_pop_free(inkey, ASN1_TYPE_free);
@@ -157,6 +161,9 @@ EVP_PKEY *d2i_AutoPrivateKey(EVP_PKEY **a, const unsigned char **pp,
         }
         ret = EVP_PKCS82PKEY(p8);
         PKCS8_PRIV_KEY_INFO_free(p8);
+        if (ret == NULL)
+            return NULL;
+        *pp = p;
         if (a) {
             *a = ret;
         }

crypto/asn1/t_x509.c

@@ -140,7 +140,8 @@ int X509_print_ex(BIO *bp, X509 *x, unsigned long nmflags,
             goto err;
 
         bs = X509_get_serialNumber(x);
-        if (bs->length <= (int)sizeof(long)) {
+        if (bs->length < (int)sizeof(long)
+            || (bs->length == sizeof(long) && (bs->data[0] & 0x80) == 0)) {
             l = ASN1_INTEGER_get(bs);
             if (bs->type == V_ASN1_NEG_INTEGER) {
                 l = -l;

crypto/asn1/tasn_dec.c

@@ -180,6 +180,8 @@ int ASN1_item_ex_d2i(ASN1_VALUE **pval, const unsigned char **in, long len,
     int otag;
     int ret = 0;
     ASN1_VALUE **pchptr, *ptmpval;
+    int combine = aclass & ASN1_TFLG_COMBINE;
+    aclass &= ~ASN1_TFLG_COMBINE;
     if (!pval)
         return 0;
     if (aux && aux->asn1_cb)
@@ -350,9 +352,9 @@ int ASN1_item_ex_d2i(ASN1_VALUE **pval, const unsigned char **in, long len,
         }
 
         asn1_set_choice_selector(pval, i, it);
-        *in = p;
         if (asn1_cb && !asn1_cb(ASN1_OP_D2I_POST, pval, it, NULL))
             goto auxerr;
+        *in = p;
         return 1;
 
     case ASN1_ITYPE_NDEF_SEQUENCE:
@@ -489,9 +491,9 @@ int ASN1_item_ex_d2i(ASN1_VALUE **pval, const unsigned char **in, long len,
         /* Save encoding */
         if (!asn1_enc_save(pval, *in, p - *in, it))
             goto auxerr;
-        *in = p;
         if (asn1_cb && !asn1_cb(ASN1_OP_D2I_POST, pval, it, NULL))
             goto auxerr;
+        *in = p;
         return 1;
 
     default:
@@ -500,7 +502,8 @@ int ASN1_item_ex_d2i(ASN1_VALUE **pval, const unsigned char **in, long len,
  auxerr:
     ASN1err(ASN1_F_ASN1_ITEM_EX_D2I, ASN1_R_AUX_ERROR);
  err:
-    ASN1_item_ex_free(pval, it);
+    if (combine == 0)
+        ASN1_item_ex_free(pval, it);
     if (errtt)
         ERR_add_error_data(4, "Field=", errtt->field_name,
                            ", Type=", it->sname);
@@ -689,7 +692,7 @@ static int asn1_template_noexp_d2i(ASN1_VALUE **val,
     } else {
         /* Nothing special */
         ret = ASN1_item_ex_d2i(val, &p, len, ASN1_ITEM_ptr(tt->item),
-                               -1, 0, opt, ctx);
+                               -1, tt->flags & ASN1_TFLG_COMBINE, opt, ctx);
         if (!ret) {
             ASN1err(ASN1_F_ASN1_TEMPLATE_NOEXP_D2I, ERR_R_NESTED_ASN1_ERROR);
             goto err;
@@ -714,7 +717,7 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
     long plen;
     char cst, inf, free_cont = 0;
     const unsigned char *p;
-    BUF_MEM buf;
+    BUF_MEM buf = { 0, NULL, 0 };
     const unsigned char *cont = NULL;
     long len;
     if (!pval) {
@@ -790,7 +793,6 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
         } else {
             len = p - cont + plen;
             p += plen;
-            buf.data = NULL;
         }
     } else if (cst) {
         if (utype == V_ASN1_NULL || utype == V_ASN1_BOOLEAN
@@ -799,9 +801,9 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
             ASN1err(ASN1_F_ASN1_D2I_EX_PRIMITIVE, ASN1_R_TYPE_NOT_PRIMITIVE);
             return 0;
         }
-        buf.length = 0;
-        buf.max = 0;
-        buf.data = NULL;
+
+        /* Free any returned 'buf' content */
+        free_cont = 1;
         /*
          * Should really check the internal tags are correct but some things
          * may get this wrong. The relevant specs say that constructed string
@@ -809,18 +811,16 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
          * So instead just check for UNIVERSAL class and ignore the tag.
          */
         if (!asn1_collect(&buf, &p, plen, inf, -1, V_ASN1_UNIVERSAL, 0)) {
-            free_cont = 1;
             goto err;
         }
         len = buf.length;
         /* Append a final null to string */
         if (!BUF_MEM_grow_clean(&buf, len + 1)) {
             ASN1err(ASN1_F_ASN1_D2I_EX_PRIMITIVE, ERR_R_MALLOC_FAILURE);
-            return 0;
+            goto err;
         }
         buf.data[len] = 0;
         cont = (const unsigned char *)buf.data;
-        free_cont = 1;
     } else {
         cont = p;
         len = plen;
@@ -828,6 +828,7 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
     }
 
     /* We now have content length and type: translate into a structure */
+    /* asn1_ex_c2i may reuse allocated buffer, and so sets free_cont to 0 */
     if (!asn1_ex_c2i(pval, cont, len, utype, &free_cont, it))
         goto err;
 

crypto/asn1/x_bignum.c

@@ -141,8 +141,9 @@ static int bn_c2i(ASN1_VALUE **pval, const unsigned char *cont, int len,
                   int utype, char *free_cont, const ASN1_ITEM *it)
 {
     BIGNUM *bn;
-    if (!*pval)
-        bn_new(pval, it);
+
+    if (*pval == NULL && !bn_new(pval, it))
+        return 0;
     bn = (BIGNUM *)*pval;
     if (!BN_bin2bn(cont, len, bn)) {
         bn_free(pval, it);

crypto/asn1/x_name.c

@@ -66,6 +66,13 @@
 typedef STACK_OF(X509_NAME_ENTRY) STACK_OF_X509_NAME_ENTRY;
 DECLARE_STACK_OF(STACK_OF_X509_NAME_ENTRY)
 
+/*
+ * Maximum length of X509_NAME: much larger than anything we should
+ * ever see in practice.
+ */
+
+#define X509_NAME_MAX (1024 * 1024)
+
 static int x509_name_ex_d2i(ASN1_VALUE **val,
                             const unsigned char **in, long len,
                             const ASN1_ITEM *it,
@@ -192,6 +199,10 @@ static int x509_name_ex_d2i(ASN1_VALUE **val,
     int i, j, ret;
     STACK_OF(X509_NAME_ENTRY) *entries;
     X509_NAME_ENTRY *entry;
+    if (len > X509_NAME_MAX) {
+        ASN1err(ASN1_F_X509_NAME_EX_D2I, ASN1_R_TOO_LONG);
+        return 0;
+    }
     q = p;
 
     /* Get internal representation of Name */

crypto/asn1/x_pubkey.c

@@ -188,13 +188,16 @@ EVP_PKEY *d2i_PUBKEY(EVP_PKEY **a, const unsigned char **pp, long length)
 {
     X509_PUBKEY *xpk;
     EVP_PKEY *pktmp;
-    xpk = d2i_X509_PUBKEY(NULL, pp, length);
+    const unsigned char *q;
+    q = *pp;
+    xpk = d2i_X509_PUBKEY(NULL, &q, length);
     if (!xpk)
         return NULL;
     pktmp = X509_PUBKEY_get(xpk);
     X509_PUBKEY_free(xpk);
     if (!pktmp)
         return NULL;
+    *pp = q;
     if (a) {
         EVP_PKEY_free(*a);
         *a = pktmp;

crypto/asn1/x_x509.c

@@ -180,16 +180,15 @@ X509 *d2i_X509_AUX(X509 **a, const unsigned char **pp, long length)
     if (!a || *a == NULL) {
         freeret = 1;
     }
-    ret = d2i_X509(a, pp, length);
+    ret = d2i_X509(a, &q, length);
     /* If certificate unreadable then forget it */
     if (!ret)
         return NULL;
     /* update length */
-    length -= *pp - q;
-    if (!length)
-        return ret;
-    if (!d2i_X509_CERT_AUX(&ret->aux, pp, length))
+    length -= q - *pp;
+    if (length > 0 && !d2i_X509_CERT_AUX(&ret->aux, &q, length))
         goto err;
+    *pp = q;
     return ret;
  err:
     if (freeret) {
@@ -202,10 +201,20 @@ X509 *d2i_X509_AUX(X509 **a, const unsigned char **pp, long length)
 
 int i2d_X509_AUX(X509 *a, unsigned char **pp)
 {
-    int length;
+    int length, tmplen;
+    unsigned char *start = pp != NULL ? *pp : NULL;
     length = i2d_X509(a, pp);
-    if (a)
-        length += i2d_X509_CERT_AUX(a->aux, pp);
+    if (length < 0 || a == NULL)
+        return length;
+
+    tmplen = i2d_X509_CERT_AUX(a->aux, pp);
+    if (tmplen < 0) {
+        if (start != NULL)
+            *pp = start;
+        return tmplen;
+    }
+    length += tmplen;
+
     return length;
 }
 

crypto/asn1/x_x509a.c

@@ -163,10 +163,13 @@ int X509_add1_reject_object(X509 *x, ASN1_OBJECT *obj)
     if (!(objtmp = OBJ_dup(obj)))
         return 0;
     if (!(aux = aux_get(x)))
-        return 0;
+        goto err;
     if (!aux->reject && !(aux->reject = sk_ASN1_OBJECT_new_null()))
-        return 0;
+        goto err;
     return sk_ASN1_OBJECT_push(aux->reject, objtmp);
+ err:
+    ASN1_OBJECT_free(objtmp);
+    return 0;
 }
 
 void X509_trust_clear(X509 *x)

crypto/bf/.cvsignore

@@ -1,5 +0,0 @@
-lib
-Makefile.save
-*.flc
-semantic.cache
-bf-*.s

crypto/bf/asm/.cvsignore

@@ -1,4 +0,0 @@
-bx86unix.cpp
-bx86-elf.s
-*.flc
-semantic.cache

crypto/bio/.cvsignore

@@ -1,4 +0,0 @@
-lib
-Makefile.save
-*.flc
-semantic.cache

crypto/bio/b_dump.c

@@ -104,7 +104,6 @@ int BIO_dump_indent_cb(int (*cb) (const void *data, size_t len, void *u),
     if ((rows * dump_width) < len)
         rows++;
     for (i = 0; i < rows; i++) {
-        buf[0] = '\0';          /* start with empty string */
         BUF_strlcpy(buf, str, sizeof buf);
         BIO_snprintf(tmp, sizeof tmp, "%04x - ", i * dump_width);
         BUF_strlcat(buf, tmp, sizeof buf);

crypto/bio/b_print.c

@@ -125,16 +125,16 @@
 # define LLONG long
 #endif
 
-static void fmtstr(char **, char **, size_t *, size_t *,
-                   const char *, int, int, int);
-static void fmtint(char **, char **, size_t *, size_t *,
-                   LLONG, int, int, int, int);
-static void fmtfp(char **, char **, size_t *, size_t *,
-                  LDOUBLE, int, int, int);
-static void doapr_outch(char **, char **, size_t *, size_t *, int);
-static void _dopr(char **sbuffer, char **buffer,
-                  size_t *maxlen, size_t *retlen, int *truncated,
-                  const char *format, va_list args);
+static int fmtstr(char **, char **, size_t *, size_t *,
+                  const char *, int, int, int);
+static int fmtint(char **, char **, size_t *, size_t *,
+                  LLONG, int, int, int, int);
+static int fmtfp(char **, char **, size_t *, size_t *,
+                 LDOUBLE, int, int, int);
+static int doapr_outch(char **, char **, size_t *, size_t *, int);
+static int _dopr(char **sbuffer, char **buffer,
+                 size_t *maxlen, size_t *retlen, int *truncated,
+                 const char *format, va_list args);
 
 /* format read states */
 #define DP_S_DEFAULT    0
@@ -165,7 +165,7 @@ static void _dopr(char **sbuffer, char **buffer,
 #define char_to_int(p) (p - '0')
 #define OSSL_MAX(p,q) ((p >= q) ? p : q)
 
-static void
+static int
 _dopr(char **sbuffer,
       char **buffer,
       size_t *maxlen,
@@ -196,7 +196,8 @@ _dopr(char **sbuffer,
             if (ch == '%')
                 state = DP_S_FLAGS;
             else
-                doapr_outch(sbuffer, buffer, &currlen, maxlen, ch);
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, ch))
+                    return 0;
             ch = *format++;
             break;
         case DP_S_FLAGS:
@@ -302,8 +303,9 @@ _dopr(char **sbuffer,
                     value = va_arg(args, int);
                     break;
                 }
-                fmtint(sbuffer, buffer, &currlen, maxlen,
-                       value, 10, min, max, flags);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen, value, 10, min,
+                            max, flags))
+                    return 0;
                 break;
             case 'X':
                 flags |= DP_F_UP;
@@ -326,17 +328,19 @@ _dopr(char **sbuffer,
                     value = (LLONG) va_arg(args, unsigned int);
                     break;
                 }
-                fmtint(sbuffer, buffer, &currlen, maxlen, value,
-                       ch == 'o' ? 8 : (ch == 'u' ? 10 : 16),
-                       min, max, flags);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen, value,
+                            ch == 'o' ? 8 : (ch == 'u' ? 10 : 16),
+                            min, max, flags))
+                    return 0;
                 break;
             case 'f':
                 if (cflags == DP_C_LDOUBLE)
                     fvalue = va_arg(args, LDOUBLE);
                 else
                     fvalue = va_arg(args, double);
-                fmtfp(sbuffer, buffer, &currlen, maxlen,
-                      fvalue, min, max, flags);
+                if (!fmtfp(sbuffer, buffer, &currlen, maxlen, fvalue, min, max,
+                           flags))
+                    return 0;
                 break;
             case 'E':
                 flags |= DP_F_UP;
@@ -355,8 +359,9 @@ _dopr(char **sbuffer,
                     fvalue = va_arg(args, double);
                 break;
             case 'c':
-                doapr_outch(sbuffer, buffer, &currlen, maxlen,
-                            va_arg(args, int));
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen,
+                            va_arg(args, int)))
+                    return 0;
                 break;
             case 's':
                 strvalue = va_arg(args, char *);
@@ -366,13 +371,15 @@ _dopr(char **sbuffer,
                     else
                         max = *maxlen;
                 }
-                fmtstr(sbuffer, buffer, &currlen, maxlen, strvalue,
-                       flags, min, max);
+                if (!fmtstr(sbuffer, buffer, &currlen, maxlen, strvalue,
+                            flags, min, max))
+                    return 0;
                 break;
             case 'p':
                 value = (long)va_arg(args, void *);
-                fmtint(sbuffer, buffer, &currlen, maxlen,
-                       value, 16, min, max, flags | DP_F_NUM);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen,
+                            value, 16, min, max, flags | DP_F_NUM))
+                    return 0;
                 break;
             case 'n':          /* XXX */
                 if (cflags == DP_C_SHORT) {
@@ -394,7 +401,8 @@ _dopr(char **sbuffer,
                 }
                 break;
             case '%':
-                doapr_outch(sbuffer, buffer, &currlen, maxlen, ch);
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, ch))
+                    return 0;
                 break;
             case 'w':
                 /* not supported yet, treat as next char */
@@ -418,46 +426,56 @@ _dopr(char **sbuffer,
     *truncated = (currlen > *maxlen - 1);
     if (*truncated)
         currlen = *maxlen - 1;
-    doapr_outch(sbuffer, buffer, &currlen, maxlen, '\0');
+    if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, '\0'))
+        return 0;
     *retlen = currlen - 1;
-    return;
+    return 1;
 }
 
-static void
+static int
 fmtstr(char **sbuffer,
        char **buffer,
        size_t *currlen,
        size_t *maxlen, const char *value, int flags, int min, int max)
 {
-    int padlen, strln;
+    int padlen;
+    size_t strln;
     int cnt = 0;
 
     if (value == 0)
         value = "<NULL>";
-    for (strln = 0; value[strln]; ++strln) ;
+
+    strln = strlen(value);
+    if (strln > INT_MAX)
+        strln = INT_MAX;
+
     padlen = min - strln;
-    if (padlen < 0)
+    if (min < 0 || padlen < 0)
         padlen = 0;
     if (flags & DP_F_MINUS)
         padlen = -padlen;
 
     while ((padlen > 0) && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --padlen;
         ++cnt;
     }
     while (*value && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, *value++);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, *value++))
+            return 0;
         ++cnt;
     }
     while ((padlen < 0) && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++padlen;
         ++cnt;
     }
+    return 1;
 }
 
-static void
+static int
 fmtint(char **sbuffer,
        char **buffer,
        size_t *currlen,
@@ -517,37 +535,44 @@ fmtint(char **sbuffer,
 
     /* spaces */
     while (spadlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --spadlen;
     }
 
     /* sign */
     if (signvalue)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+            return 0;
 
     /* prefix */
     while (*prefix) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, *prefix);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, *prefix))
+            return 0;
         prefix++;
     }
 
     /* zeros */
     if (zpadlen > 0) {
         while (zpadlen > 0) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+            if(!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+                return 0;
             --zpadlen;
         }
     }
     /* digits */
-    while (place > 0)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, convert[--place]);
+    while (place > 0) {
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, convert[--place]))
+            return 0;
+    }
 
     /* left justified spaces */
     while (spadlen < 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++spadlen;
     }
-    return;
+    return 1;
 }
 
 static LDOUBLE abs_val(LDOUBLE value)
@@ -578,7 +603,7 @@ static long roundv(LDOUBLE value)
     return intpart;
 }
 
-static void
+static int
 fmtfp(char **sbuffer,
       char **buffer,
       size_t *currlen,
@@ -657,47 +682,61 @@ fmtfp(char **sbuffer,
 
     if ((flags & DP_F_ZERO) && (padlen > 0)) {
         if (signvalue) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+            if (!doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+                return 0;
             --padlen;
             signvalue = 0;
         }
         while (padlen > 0) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+            if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+                return 0;
             --padlen;
         }
     }
     while (padlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --padlen;
     }
-    if (signvalue)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+    if (signvalue && !doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+        return 0;
 
-    while (iplace > 0)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, iconvert[--iplace]);
+    while (iplace > 0) {
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, iconvert[--iplace]))
+            return 0;
+    }
 
     /*
      * Decimal point. This should probably use locale to find the correct
      * char to print out.
      */
     if (max > 0 || (flags & DP_F_NUM)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, '.');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '.'))
+            return 0;
 
-        while (fplace > 0)
-            doapr_outch(sbuffer, buffer, currlen, maxlen, fconvert[--fplace]);
+        while (fplace > 0) {
+            if(!doapr_outch(sbuffer, buffer, currlen, maxlen,
+                            fconvert[--fplace]))
+                return 0;
+        }
     }
     while (zpadlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+            return 0;
         --zpadlen;
     }
 
     while (padlen < 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++padlen;
     }
+    return 1;
 }
 
-static void
+#define BUFFER_INC  1024
+
+static int
 doapr_outch(char **sbuffer,
             char **buffer, size_t *currlen, size_t *maxlen, int c)
 {
@@ -708,24 +747,25 @@ doapr_outch(char **sbuffer,
     assert(*currlen <= *maxlen);
 
     if (buffer && *currlen == *maxlen) {
-        *maxlen += 1024;
+        if (*maxlen > INT_MAX - BUFFER_INC)
+            return 0;
+
+        *maxlen += BUFFER_INC;
         if (*buffer == NULL) {
             *buffer = OPENSSL_malloc(*maxlen);
-            if (!*buffer) {
-                /* Panic! Can't really do anything sensible. Just return */
-                return;
-            }
+            if (*buffer == NULL)
+                return 0;
             if (*currlen > 0) {
                 assert(*sbuffer != NULL);
                 memcpy(*buffer, *sbuffer, *currlen);
             }
             *sbuffer = NULL;
         } else {
-            *buffer = OPENSSL_realloc(*buffer, *maxlen);
-            if (!*buffer) {
-                /* Panic! Can't really do anything sensible. Just return */
-                return;
-            }
+            char *tmpbuf;
+            tmpbuf = OPENSSL_realloc(*buffer, *maxlen);
+            if (tmpbuf == NULL)
+                return 0;
+            *buffer = tmpbuf;
         }
     }
 
@@ -736,7 +776,7 @@ doapr_outch(char **sbuffer,
             (*buffer)[(*currlen)++] = (char)c;
     }
 
-    return;
+    return 1;
 }
 
 /***************************************************************************/
@@ -768,7 +808,11 @@ int BIO_vprintf(BIO *bio, const char *format, va_list args)
 
     dynbuf = NULL;
     CRYPTO_push_info("doapr()");
-    _dopr(&hugebufp, &dynbuf, &hugebufsize, &retlen, &ignored, format, args);
+    if (!_dopr(&hugebufp, &dynbuf, &hugebufsize, &retlen, &ignored, format,
+                args)) {
+        OPENSSL_free(dynbuf);
+        return -1;
+    }
     if (dynbuf) {
         ret = BIO_write(bio, dynbuf, (int)retlen);
         OPENSSL_free(dynbuf);
@@ -803,7 +847,8 @@ int BIO_vsnprintf(char *buf, size_t n, const char *format, va_list args)
     size_t retlen;
     int truncated;
 
-    _dopr(&buf, NULL, &n, &retlen, &truncated, format, args);
+    if(!_dopr(&buf, NULL, &n, &retlen, &truncated, format, args))
+        return -1;
 
     if (truncated)
         /*

crypto/bio/bio.h

@@ -291,7 +291,7 @@ void BIO_clear_flags(BIO *b, int flags);
  * BIO_CB_RETURN flag indicates if it is after the call
  */
 # define BIO_CB_RETURN   0x80
-# define BIO_CB_return(a) ((a)|BIO_CB_RETURN))
+# define BIO_CB_return(a) ((a)|BIO_CB_RETURN)
 # define BIO_cb_pre(a)   (!((a)&BIO_CB_RETURN))
 # define BIO_cb_post(a)  ((a)&BIO_CB_RETURN)
 
@@ -479,11 +479,11 @@ struct bio_dgram_sctp_prinfo {
 # define BIO_get_conn_hostname(b)  BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,0)
 # define BIO_get_conn_port(b)      BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,1)
 # define BIO_get_conn_ip(b)               BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,2)
-# define BIO_get_conn_int_port(b) BIO_int_ctrl(b,BIO_C_GET_CONNECT,3,0)
+# define BIO_get_conn_int_port(b) BIO_ctrl(b,BIO_C_GET_CONNECT,3,NULL)
 
 # define BIO_set_nbio(b,n)       BIO_ctrl(b,BIO_C_SET_NBIO,(n),NULL)
 
-/* BIO_s_accept_socket() */
+/* BIO_s_accept() */
 # define BIO_set_accept_port(b,name) BIO_ctrl(b,BIO_C_SET_ACCEPT,0,(char *)name)
 # define BIO_get_accept_port(b)  BIO_ptr_ctrl(b,BIO_C_GET_ACCEPT,0)
 /* #define BIO_set_nbio(b,n)    BIO_ctrl(b,BIO_C_SET_NBIO,(n),NULL) */
@@ -496,6 +496,7 @@ struct bio_dgram_sctp_prinfo {
 # define BIO_set_bind_mode(b,mode) BIO_ctrl(b,BIO_C_SET_BIND_MODE,mode,NULL)
 # define BIO_get_bind_mode(b,mode) BIO_ctrl(b,BIO_C_GET_BIND_MODE,0,NULL)
 
+/* BIO_s_accept() and BIO_s_connect() */
 # define BIO_do_connect(b)       BIO_do_handshake(b)
 # define BIO_do_accept(b)        BIO_do_handshake(b)
 # define BIO_do_handshake(b)     BIO_ctrl(b,BIO_C_DO_STATE_MACHINE,0,NULL)
@@ -515,12 +516,15 @@ struct bio_dgram_sctp_prinfo {
 # define BIO_get_url(b,url)      BIO_ctrl(b,BIO_C_GET_PROXY_PARAM,2,(char *)(url))
 # define BIO_get_no_connect_return(b)    BIO_ctrl(b,BIO_C_GET_PROXY_PARAM,5,NULL)
 
+/* BIO_s_datagram(), BIO_s_fd(), BIO_s_socket(), BIO_s_accept() and BIO_s_connect() */
 # define BIO_set_fd(b,fd,c)      BIO_int_ctrl(b,BIO_C_SET_FD,c,fd)
 # define BIO_get_fd(b,c)         BIO_ctrl(b,BIO_C_GET_FD,0,(char *)c)
 
+/* BIO_s_file() */
 # define BIO_set_fp(b,fp,c)      BIO_ctrl(b,BIO_C_SET_FILE_PTR,c,(char *)fp)
 # define BIO_get_fp(b,fpp)       BIO_ctrl(b,BIO_C_GET_FILE_PTR,0,(char *)fpp)
 
+/* BIO_s_fd() and BIO_s_file() */
 # define BIO_seek(b,ofs) (int)BIO_ctrl(b,BIO_C_FILE_SEEK,ofs,NULL)
 # define BIO_tell(b)     (int)BIO_ctrl(b,BIO_C_FILE_TELL,0,NULL)
 
@@ -685,7 +689,7 @@ long BIO_debug_callback(BIO *bio, int cmd, const char *argp, int argi,
                         long argl, long ret);
 
 BIO_METHOD *BIO_s_mem(void);
-BIO *BIO_new_mem_buf(void *buf, int len);
+BIO *BIO_new_mem_buf(const void *buf, int len);
 BIO_METHOD *BIO_s_socket(void);
 BIO_METHOD *BIO_s_connect(void);
 BIO_METHOD *BIO_s_accept(void);

crypto/bio/bss_bio.c

@@ -1,4 +1,4 @@
-/* crypto/bio/bss_bio.c  -*- Mode: C; c-file-style: "eay" -*- */
+/* crypto/bio/bss_bio.c  */
 /* ====================================================================
  * Copyright (c) 1998-2003 The OpenSSL Project.  All rights reserved.
  *

crypto/bio/bss_conn.c

@@ -419,7 +419,7 @@ static long conn_ctrl(BIO *b, int cmd, long num, void *ptr)
 {
     BIO *dbio;
     int *ip;
-    const char **pptr;
+    const char **pptr = NULL;
     long ret = 1;
     BIO_CONNECT *data;
 
@@ -442,19 +442,28 @@ static long conn_ctrl(BIO *b, int cmd, long num, void *ptr)
     case BIO_C_GET_CONNECT:
         if (ptr != NULL) {
             pptr = (const char **)ptr;
-            if (num == 0) {
-                *pptr = data->param_hostname;
+        }
 
-            } else if (num == 1) {
-                *pptr = data->param_port;
-            } else if (num == 2) {
-                *pptr = (char *)&(data->ip[0]);
-            } else if (num == 3) {
-                *((int *)ptr) = data->port;
+        if (b->init) {
+            if (pptr != NULL) {
+                ret = 1;
+                if (num == 0) {
+                    *pptr = data->param_hostname;
+                } else if (num == 1) {
+                    *pptr = data->param_port;
+                } else if (num == 2) {
+                    *pptr = (char *)&(data->ip[0]);
+                } else {
+                    ret = 0;
+                }
             }
-            if ((!b->init) || (ptr == NULL))
+            if (num == 3) {
+                ret = data->port;
+            }
+        } else {
+            if (pptr != NULL)
                 *pptr = "not initialized";
-            ret = 1;
+            ret = 0;
         }
         break;
     case BIO_C_SET_CONNECT:

crypto/bio/bss_dgram.c

@@ -519,10 +519,8 @@ static long dgram_ctrl(BIO *b, int cmd, long num, void *ptr)
     switch (cmd) {
     case BIO_CTRL_RESET:
         num = 0;
-    case BIO_C_FILE_SEEK:
         ret = 0;
         break;
-    case BIO_C_FILE_TELL:
     case BIO_CTRL_INFO:
         ret = 0;
         break;

crypto/bio/bss_file.c

@@ -115,9 +115,8 @@ static BIO_METHOD methods_filep = {
     NULL,
 };
 
-BIO *BIO_new_file(const char *filename, const char *mode)
+static FILE *file_fopen(const char *filename, const char *mode)
 {
-    BIO *ret;
     FILE *file = NULL;
 
 #  if defined(_WIN32) && defined(CP_UTF8)
@@ -164,6 +163,14 @@ BIO *BIO_new_file(const char *filename, const char *mode)
 #  else
     file = fopen(filename, mode);
 #  endif
+    return (file);
+}
+
+BIO *BIO_new_file(const char *filename, const char *mode)
+{
+    BIO  *ret;
+    FILE *file = file_fopen(filename, mode);
+
     if (file == NULL) {
         SYSerr(SYS_F_FOPEN, get_last_sys_error());
         ERR_add_error_data(5, "fopen('", filename, "','", mode, "')");
@@ -386,7 +393,7 @@ static long MS_CALLBACK file_ctrl(BIO *b, int cmd, long num, void *ptr)
         else
             strcat(p, "t");
 #  endif
-        fp = fopen(ptr, p);
+        fp = file_fopen(ptr, p);
         if (fp == NULL) {
             SYSerr(SYS_F_FOPEN, get_last_sys_error());
             ERR_add_error_data(5, "fopen('", ptr, "','", p, "')");

crypto/bio/bss_mem.c

@@ -91,7 +91,8 @@ BIO_METHOD *BIO_s_mem(void)
     return (&mem_method);
 }
 
-BIO *BIO_new_mem_buf(void *buf, int len)
+
+BIO *BIO_new_mem_buf(const void *buf, int len)
 {
     BIO *ret;
     BUF_MEM *b;
@@ -105,7 +106,8 @@ BIO *BIO_new_mem_buf(void *buf, int len)
     if (!(ret = BIO_new(BIO_s_mem())))
         return NULL;
     b = (BUF_MEM *)ret->ptr;
-    b->data = buf;
+    /* Cast away const and trust in the MEM_RDONLY flag. */
+    b->data = (void *)buf;
     b->length = sz;
     b->max = sz;
     ret->flags |= BIO_FLAGS_MEM_RDONLY;

crypto/bn/.cvsignore

@@ -1,10 +0,0 @@
-lib
-Makefile.save
-*.flc
-semantic.cache
-co-*.s
-bn-*.s
-*-mont.s
-modexp512-x86_64.s
-*-gf2m.s
-x86_64-mont5.s

crypto/bn/Makefile

@@ -252,7 +252,8 @@ 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/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_exp.o: ../../include/openssl/symhacks.h ../constant_time_locl.h
+bn_exp.o: ../cryptlib.h bn_exp.c bn_lcl.h rsaz_exp.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

crypto/bn/asm/.cvsignore

@@ -1,6 +0,0 @@
-bn86unix.cpp
-co86unix.cpp
-bn86-elf.s
-co86-elf.s
-*.flc
-semantic.cache

crypto/bn/asm/armv4-gf2m.pl

@@ -27,7 +27,7 @@
 # referred below, which improves ECDH and ECDSA verify benchmarks
 # by 18-40%.
 #
-# C<EFBFBD>mara, D.; Gouv<EFBFBD>a, C. P. L.; L<EFBFBD>pez, J. & Dahab, R.: Fast Software
+# Câmara, D.; Gouvêa, C. P. L.; López, J. & Dahab, R.: Fast Software
 # Polynomial Multiplication on ARM Processors using the NEON Engine.
 # 
 # http://conradoplg.cryptoland.net/files/2010/12/mocrysen13.pdf
@@ -136,7 +136,7 @@ ___
 ################
 # void	bn_GF2m_mul_2x2(BN_ULONG *r,
 #	BN_ULONG a1,BN_ULONG a0,
-#	BN_ULONG b1,BN_ULONG b0);	# r[3..0]=a1a0<EFBFBD>b1b0
+#	BN_ULONG b1,BN_ULONG b0);	# r[3..0]=a1a0·b1b0
 {
 $code.=<<___;
 .global	bn_GF2m_mul_2x2
@@ -159,7 +159,7 @@ $code.=<<___;
 	mov	$mask,#7<<2
 	sub	sp,sp,#32		@ allocate tab[8]
 
-	bl	mul_1x1_ialu		@ a1<EFBFBD>b1
+	bl	mul_1x1_ialu		@ a1·b1
 	str	$lo,[$ret,#8]
 	str	$hi,[$ret,#12]
 
@@ -169,13 +169,13 @@ $code.=<<___;
 	 eor	r2,r2,$a
 	eor	$b,$b,r3
 	 eor	$a,$a,r2
-	bl	mul_1x1_ialu		@ a0<EFBFBD>b0
+	bl	mul_1x1_ialu		@ a0·b0
 	str	$lo,[$ret]
 	str	$hi,[$ret,#4]
 
 	eor	$a,$a,r2
 	eor	$b,$b,r3
-	bl	mul_1x1_ialu		@ (a1+a0)<EFBFBD>(b1+b0)
+	bl	mul_1x1_ialu		@ (a1+a0)·(b1+b0)
 ___
 @r=map("r$_",(6..9));
 $code.=<<___;

crypto/bn/asm/ia64.S

@@ -422,7 +422,7 @@ bn_mul_add_words:
 
 // This loop spins in 3*(n+10) ticks on Itanium and in 2*(n+10) on
 // Itanium 2. Yes, unlike previous versions it scales:-) Previous
-// version was peforming *all* additions in IALU and was starving
+// version was performing *all* additions in IALU and was starving
 // for those even on Itanium 2. In this version one addition is
 // moved to FPU and is folded with multiplication. This is at cost
 // of propogating the result from previous call to this subroutine
@@ -568,7 +568,7 @@ bn_sqr_comba8:
 // I've estimated this routine to run in ~120 ticks, but in reality
 // (i.e. according to ar.itc) it takes ~160 ticks. Are those extra
 // cycles consumed for instructions fetch? Or did I misinterpret some
-// clause in Itanium <EFBFBD>-architecture manual? Comments are welcomed and
+// clause in Itanium µ-architecture manual? Comments are welcomed and
 // highly appreciated.
 //
 // On Itanium 2 it takes ~190 ticks. This is because of stalls on

crypto/bn/asm/ppc-mont.pl

@@ -191,7 +191,7 @@ L1st:
 
 	addi	$j,$j,$BNSZ	; j++
 	addi	$tp,$tp,$BNSZ	; tp++
-	bdnz-	L1st
+	bdnz	L1st
 ;L1st
 	addc	$lo0,$alo,$hi0
 	addze	$hi0,$ahi
@@ -253,7 +253,7 @@ Linner:
 	addze	$hi1,$hi1
 	$ST	$lo1,0($tp)	; tp[j-1]
 	addi	$tp,$tp,$BNSZ	; tp++
-	bdnz-	Linner
+	bdnz	Linner
 ;Linner
 	$LD	$tj,$BNSZ($tp)	; tp[j]
 	addc	$lo0,$alo,$hi0
@@ -276,7 +276,7 @@ Linner:
 	slwi	$tj,$num,`log($BNSZ)/log(2)`
 	$UCMP	$i,$tj
 	addi	$i,$i,$BNSZ
-	ble-	Louter
+	ble	Louter
 
 	addi	$num,$num,2	; restore $num
 	subfc	$j,$j,$j	; j=0 and "clear" XER[CA]
@@ -289,7 +289,7 @@ Lsub:	$LDX	$tj,$tp,$j
 	subfe	$aj,$nj,$tj	; tp[j]-np[j]
 	$STX	$aj,$rp,$j
 	addi	$j,$j,$BNSZ
-	bdnz-	Lsub
+	bdnz	Lsub
 
 	li	$j,0
 	mtctr	$num
@@ -304,7 +304,7 @@ Lcopy:				; copy or in-place refresh
 	$STX	$tj,$rp,$j
 	$STX	$j,$tp,$j	; zap at once
 	addi	$j,$j,$BNSZ
-	bdnz-	Lcopy
+	bdnz	Lcopy
 
 	$POP	$tj,0($sp)
 	li	r3,1

crypto/bn/asm/ppc.pl

@@ -1556,7 +1556,7 @@ Lppcasm_sub_mainloop:
 				# if carry = 1 this is r7-r8. Else it
 				# is r7-r8 -1 as we need.
 	$STU	r6,$BNSZ(r3)
-	bdnz-	Lppcasm_sub_mainloop
+	bdnz	Lppcasm_sub_mainloop
 Lppcasm_sub_adios:	
 	subfze	r3,r0		# if carry bit is set then r3 = 0 else -1
 	andi.	r3,r3,1         # keep only last bit.
@@ -1603,7 +1603,7 @@ Lppcasm_add_mainloop:
 	$LDU	r8,$BNSZ(r5)
 	adde	r8,r7,r8
 	$STU	r8,$BNSZ(r3)
-	bdnz-	Lppcasm_add_mainloop
+	bdnz	Lppcasm_add_mainloop
 Lppcasm_add_adios:	
 	addze	r3,r0			#return carry bit.
 	blr
@@ -1762,7 +1762,7 @@ Lppcasm_sqr_mainloop:
 	$UMULH  r8,r6,r6
 	$STU	r7,$BNSZ(r3)
 	$STU	r8,$BNSZ(r3)
-	bdnz-	Lppcasm_sqr_mainloop
+	bdnz	Lppcasm_sqr_mainloop
 Lppcasm_sqr_adios:	
 	blr
 	.long	0
@@ -1827,7 +1827,7 @@ Lppcasm_mw_LOOP:
 	
 	addi	r3,r3,`4*$BNSZ`
 	addi	r4,r4,`4*$BNSZ`
-	bdnz-	Lppcasm_mw_LOOP
+	bdnz	Lppcasm_mw_LOOP
 
 Lppcasm_mw_REM:
 	andi.	r5,r5,0x3
@@ -1951,7 +1951,7 @@ Lppcasm_maw_mainloop:
 	$ST	r11,`3*$BNSZ`(r3)
 	addi	r3,r3,`4*$BNSZ`
 	addi	r4,r4,`4*$BNSZ`
-	bdnz-	Lppcasm_maw_mainloop
+	bdnz	Lppcasm_maw_mainloop
 	
 Lppcasm_maw_leftover:
 	andi.	r5,r5,0x3

crypto/bn/asm/ppc64-mont.pl

@@ -94,6 +94,8 @@ if ($flavour =~ /32/) {
 	$POP=	"ld";
 } else { die "nonsense $flavour"; }
 
+$LITTLE_ENDIAN = ($flavour=~/le$/) ? 4 : 0;
+
 $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
 ( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
 ( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
@@ -294,12 +296,12 @@ $code.=<<___ if ($SIZE_T==8);
 
 	extrdi	$t0,$a0,32,32		; lwz	$t0,4($ap)
 	extrdi	$t1,$a0,32,0		; lwz	$t1,0($ap)
-	lwz	$t2,12($ap)		; load a[1] as 32-bit word pair
-	lwz	$t3,8($ap)
-	lwz	$t4,4($np)		; load n[0] as 32-bit word pair
-	lwz	$t5,0($np)
-	lwz	$t6,12($np)		; load n[1] as 32-bit word pair
-	lwz	$t7,8($np)
+	lwz	$t2,`12^$LITTLE_ENDIAN`($ap)	; load a[1] as 32-bit word pair
+	lwz	$t3,`8^$LITTLE_ENDIAN`($ap)
+	lwz	$t4,`4^$LITTLE_ENDIAN`($np)	; load n[0] as 32-bit word pair
+	lwz	$t5,`0^$LITTLE_ENDIAN`($np)
+	lwz	$t6,`12^$LITTLE_ENDIAN`($np)	; load n[1] as 32-bit word pair
+	lwz	$t7,`8^$LITTLE_ENDIAN`($np)
 ___
 $code.=<<___ if ($SIZE_T==4);
 	lwz	$a0,0($ap)		; pull ap[0,1] value
@@ -463,14 +465,14 @@ $code.=<<___;
 L1st:
 ___
 $code.=<<___ if ($SIZE_T==8);
-	lwz	$t0,4($ap)		; load a[j] as 32-bit word pair
-	lwz	$t1,0($ap)
-	lwz	$t2,12($ap)		; load a[j+1] as 32-bit word pair
-	lwz	$t3,8($ap)
-	lwz	$t4,4($np)		; load n[j] as 32-bit word pair
-	lwz	$t5,0($np)
-	lwz	$t6,12($np)		; load n[j+1] as 32-bit word pair
-	lwz	$t7,8($np)
+	lwz	$t0,`4^$LITTLE_ENDIAN`($ap)	; load a[j] as 32-bit word pair
+	lwz	$t1,`0^$LITTLE_ENDIAN`($ap)
+	lwz	$t2,`12^$LITTLE_ENDIAN`($ap)	; load a[j+1] as 32-bit word pair
+	lwz	$t3,`8^$LITTLE_ENDIAN`($ap)
+	lwz	$t4,`4^$LITTLE_ENDIAN`($np)	; load n[j] as 32-bit word pair
+	lwz	$t5,`0^$LITTLE_ENDIAN`($np)
+	lwz	$t6,`12^$LITTLE_ENDIAN`($np)	; load n[j+1] as 32-bit word pair
+	lwz	$t7,`8^$LITTLE_ENDIAN`($np)
 ___
 $code.=<<___ if ($SIZE_T==4);
 	lwz	$t0,0($ap)		; load a[j..j+3] as 32-bit word pairs
@@ -505,14 +507,14 @@ $code.=<<___;
 ___
 } else {
 $code.=<<___;
-	lwz	$t1,`$FRAME+0`($sp)
-	lwz	$t0,`$FRAME+4`($sp)
-	lwz	$t3,`$FRAME+8`($sp)
-	lwz	$t2,`$FRAME+12`($sp)
-	lwz	$t5,`$FRAME+16`($sp)
-	lwz	$t4,`$FRAME+20`($sp)
-	lwz	$t7,`$FRAME+24`($sp)
-	lwz	$t6,`$FRAME+28`($sp)
+	lwz	$t1,`$FRAME+0^$LITTLE_ENDIAN`($sp)
+	lwz	$t0,`$FRAME+4^$LITTLE_ENDIAN`($sp)
+	lwz	$t3,`$FRAME+8^$LITTLE_ENDIAN`($sp)
+	lwz	$t2,`$FRAME+12^$LITTLE_ENDIAN`($sp)
+	lwz	$t5,`$FRAME+16^$LITTLE_ENDIAN`($sp)
+	lwz	$t4,`$FRAME+20^$LITTLE_ENDIAN`($sp)
+	lwz	$t7,`$FRAME+24^$LITTLE_ENDIAN`($sp)
+	lwz	$t6,`$FRAME+28^$LITTLE_ENDIAN`($sp)
 ___
 }
 $code.=<<___;
@@ -651,8 +653,8 @@ $code.=<<___;
 
 	fmadd	$T1a,$N1,$na,$T1a
 	fmadd	$T1b,$N1,$nb,$T1b
-	 lwz	$t3,`$FRAME+32`($sp)	; permuted $t1
-	 lwz	$t2,`$FRAME+36`($sp)	; permuted $t0
+	 lwz	$t3,`$FRAME+32^$LITTLE_ENDIAN`($sp)	; permuted $t1
+	 lwz	$t2,`$FRAME+36^$LITTLE_ENDIAN`($sp)	; permuted $t0
 	 addc	$t4,$t4,$carry
 	 adde	$t5,$t5,$c1
 	 srwi	$carry,$t4,16
@@ -673,8 +675,8 @@ $code.=<<___;
 
 	fmadd	$T1a,$N0,$nc,$T1a
 	fmadd	$T1b,$N0,$nd,$T1b
-	 lwz	$t7,`$FRAME+40`($sp)	; permuted $t3
-	 lwz	$t6,`$FRAME+44`($sp)	; permuted $t2
+	 lwz	$t7,`$FRAME+40^$LITTLE_ENDIAN`($sp)	; permuted $t3
+	 lwz	$t6,`$FRAME+44^$LITTLE_ENDIAN`($sp)	; permuted $t2
 	 addc	$t2,$t2,$carry
 	 adde	$t3,$t3,$c1
 	 srwi	$carry,$t2,16
@@ -686,8 +688,8 @@ $code.=<<___;
 	 insrwi	$carry,$t3,16,0
 	fmadd	$T3a,$N2,$nc,$T3a
 	fmadd	$T3b,$N2,$nd,$T3b
-	 lwz	$t1,`$FRAME+48`($sp)	; permuted $t5
-	 lwz	$t0,`$FRAME+52`($sp)	; permuted $t4
+	 lwz	$t1,`$FRAME+48^$LITTLE_ENDIAN`($sp)	; permuted $t5
+	 lwz	$t0,`$FRAME+52^$LITTLE_ENDIAN`($sp)	; permuted $t4
 	 addc	$t6,$t6,$carry
 	 adde	$t7,$t7,$c1
 	 srwi	$carry,$t6,16
@@ -699,8 +701,8 @@ $code.=<<___;
 
 	fctid	$T0a,$T0a
 	fctid	$T0b,$T0b
-	 lwz	$t5,`$FRAME+56`($sp)	; permuted $t7
-	 lwz	$t4,`$FRAME+60`($sp)	; permuted $t6
+	 lwz	$t5,`$FRAME+56^$LITTLE_ENDIAN`($sp)	; permuted $t7
+	 lwz	$t4,`$FRAME+60^$LITTLE_ENDIAN`($sp)	; permuted $t6
 	 addc	$t0,$t0,$carry
 	 adde	$t1,$t1,$c1
 	 srwi	$carry,$t0,16
@@ -732,7 +734,7 @@ $code.=<<___;
 ___
 }
 $code.=<<___;
-	bdnz-	L1st
+	bdnz	L1st
 
 	fctid	$dota,$dota
 	fctid	$dotb,$dotb
@@ -787,14 +789,14 @@ $code.=<<___;
 ___
 } else {
 $code.=<<___;
-	lwz	$t1,`$FRAME+0`($sp)
-	lwz	$t0,`$FRAME+4`($sp)
-	lwz	$t3,`$FRAME+8`($sp)
-	lwz	$t2,`$FRAME+12`($sp)
-	lwz	$t5,`$FRAME+16`($sp)
-	lwz	$t4,`$FRAME+20`($sp)
-	lwz	$t7,`$FRAME+24`($sp)
-	lwz	$t6,`$FRAME+28`($sp)
+	lwz	$t1,`$FRAME+0^$LITTLE_ENDIAN`($sp)
+	lwz	$t0,`$FRAME+4^$LITTLE_ENDIAN`($sp)
+	lwz	$t3,`$FRAME+8^$LITTLE_ENDIAN`($sp)
+	lwz	$t2,`$FRAME+12^$LITTLE_ENDIAN`($sp)
+	lwz	$t5,`$FRAME+16^$LITTLE_ENDIAN`($sp)
+	lwz	$t4,`$FRAME+20^$LITTLE_ENDIAN`($sp)
+	lwz	$t7,`$FRAME+24^$LITTLE_ENDIAN`($sp)
+	lwz	$t6,`$FRAME+28^$LITTLE_ENDIAN`($sp)
 	stfd	$dota,`$FRAME+64`($sp)
 	stfd	$dotb,`$FRAME+72`($sp)
 
@@ -823,14 +825,14 @@ $code.=<<___;
 	 stw	$t0,12($tp)		; tp[j-1]
 	 stw	$t4,8($tp)
 
-	lwz	$t3,`$FRAME+32`($sp)	; permuted $t1
-	lwz	$t2,`$FRAME+36`($sp)	; permuted $t0
-	lwz	$t7,`$FRAME+40`($sp)	; permuted $t3
-	lwz	$t6,`$FRAME+44`($sp)	; permuted $t2
-	lwz	$t1,`$FRAME+48`($sp)	; permuted $t5
-	lwz	$t0,`$FRAME+52`($sp)	; permuted $t4
-	lwz	$t5,`$FRAME+56`($sp)	; permuted $t7
-	lwz	$t4,`$FRAME+60`($sp)	; permuted $t6
+	lwz	$t3,`$FRAME+32^$LITTLE_ENDIAN`($sp)	; permuted $t1
+	lwz	$t2,`$FRAME+36^$LITTLE_ENDIAN`($sp)	; permuted $t0
+	lwz	$t7,`$FRAME+40^$LITTLE_ENDIAN`($sp)	; permuted $t3
+	lwz	$t6,`$FRAME+44^$LITTLE_ENDIAN`($sp)	; permuted $t2
+	lwz	$t1,`$FRAME+48^$LITTLE_ENDIAN`($sp)	; permuted $t5
+	lwz	$t0,`$FRAME+52^$LITTLE_ENDIAN`($sp)	; permuted $t4
+	lwz	$t5,`$FRAME+56^$LITTLE_ENDIAN`($sp)	; permuted $t7
+	lwz	$t4,`$FRAME+60^$LITTLE_ENDIAN`($sp)	; permuted $t6
 
 	addc	$t2,$t2,$carry
 	adde	$t3,$t3,$c1
@@ -857,10 +859,10 @@ $code.=<<___;
 	 stw	$t2,20($tp)		; tp[j]
 	 stwu	$t0,16($tp)
 
-	lwz	$t7,`$FRAME+64`($sp)
-	lwz	$t6,`$FRAME+68`($sp)
-	lwz	$t5,`$FRAME+72`($sp)
-	lwz	$t4,`$FRAME+76`($sp)
+	lwz	$t7,`$FRAME+64^$LITTLE_ENDIAN`($sp)
+	lwz	$t6,`$FRAME+68^$LITTLE_ENDIAN`($sp)
+	lwz	$t5,`$FRAME+72^$LITTLE_ENDIAN`($sp)
+	lwz	$t4,`$FRAME+76^$LITTLE_ENDIAN`($sp)
 
 	addc	$t6,$t6,$carry
 	adde	$t7,$t7,$c1
@@ -1165,23 +1167,23 @@ ___
 $code.=<<___;
 	fmadd	$T1a,$N1,$na,$T1a
 	fmadd	$T1b,$N1,$nb,$T1b
-	 lwz	$t1,`$FRAME+0`($sp)
-	 lwz	$t0,`$FRAME+4`($sp)
+	 lwz	$t1,`$FRAME+0^$LITTLE_ENDIAN`($sp)
+	 lwz	$t0,`$FRAME+4^$LITTLE_ENDIAN`($sp)
 	fmadd	$T2a,$N2,$na,$T2a
 	fmadd	$T2b,$N2,$nb,$T2b
-	 lwz	$t3,`$FRAME+8`($sp)
-	 lwz	$t2,`$FRAME+12`($sp)
+	 lwz	$t3,`$FRAME+8^$LITTLE_ENDIAN`($sp)
+	 lwz	$t2,`$FRAME+12^$LITTLE_ENDIAN`($sp)
 	fmadd	$T3a,$N3,$na,$T3a
 	fmadd	$T3b,$N3,$nb,$T3b
-	 lwz	$t5,`$FRAME+16`($sp)
-	 lwz	$t4,`$FRAME+20`($sp)
+	 lwz	$t5,`$FRAME+16^$LITTLE_ENDIAN`($sp)
+	 lwz	$t4,`$FRAME+20^$LITTLE_ENDIAN`($sp)
 	 addc	$t0,$t0,$carry
 	 adde	$t1,$t1,$c1
 	 srwi	$carry,$t0,16
 	fmadd	$T0a,$N0,$na,$T0a
 	fmadd	$T0b,$N0,$nb,$T0b
-	 lwz	$t7,`$FRAME+24`($sp)
-	 lwz	$t6,`$FRAME+28`($sp)
+	 lwz	$t7,`$FRAME+24^$LITTLE_ENDIAN`($sp)
+	 lwz	$t6,`$FRAME+28^$LITTLE_ENDIAN`($sp)
 	 srwi	$c1,$t1,16
 	 insrwi	$carry,$t1,16,0
 
@@ -1218,8 +1220,8 @@ $code.=<<___;
 	fctid	$T1a,$T1a
 	 addc	$t0,$t0,$t2
 	 adde	$t4,$t4,$t3
-	 lwz	$t3,`$FRAME+32`($sp)	; permuted $t1
-	 lwz	$t2,`$FRAME+36`($sp)	; permuted $t0
+	 lwz	$t3,`$FRAME+32^$LITTLE_ENDIAN`($sp)	; permuted $t1
+	 lwz	$t2,`$FRAME+36^$LITTLE_ENDIAN`($sp)	; permuted $t0
 	fctid	$T1b,$T1b
 	 addze	$carry,$carry
 	 addze	$c1,$c1
@@ -1229,19 +1231,19 @@ $code.=<<___;
 	 addc	$t2,$t2,$carry
 	 adde	$t3,$t3,$c1
 	 srwi	$carry,$t2,16
-	 lwz	$t7,`$FRAME+40`($sp)	; permuted $t3
-	 lwz	$t6,`$FRAME+44`($sp)	; permuted $t2
+	 lwz	$t7,`$FRAME+40^$LITTLE_ENDIAN`($sp)	; permuted $t3
+	 lwz	$t6,`$FRAME+44^$LITTLE_ENDIAN`($sp)	; permuted $t2
 	fctid	$T2b,$T2b
 	 srwi	$c1,$t3,16
 	 insrwi	$carry,$t3,16,0
-	 lwz	$t1,`$FRAME+48`($sp)	; permuted $t5
-	 lwz	$t0,`$FRAME+52`($sp)	; permuted $t4
+	 lwz	$t1,`$FRAME+48^$LITTLE_ENDIAN`($sp)	; permuted $t5
+	 lwz	$t0,`$FRAME+52^$LITTLE_ENDIAN`($sp)	; permuted $t4
 	fctid	$T3a,$T3a
 	 addc	$t6,$t6,$carry
 	 adde	$t7,$t7,$c1
 	 srwi	$carry,$t6,16
-	 lwz	$t5,`$FRAME+56`($sp)	; permuted $t7
-	 lwz	$t4,`$FRAME+60`($sp)	; permuted $t6
+	 lwz	$t5,`$FRAME+56^$LITTLE_ENDIAN`($sp)	; permuted $t7
+	 lwz	$t4,`$FRAME+60^$LITTLE_ENDIAN`($sp)	; permuted $t6
 	fctid	$T3b,$T3b
 
 	 insrwi	$t2,$t6,16,0		; 64..95 bits
@@ -1278,7 +1280,7 @@ $code.=<<___;
 ___
 }
 $code.=<<___;
-	bdnz-	Linner
+	bdnz	Linner
 
 	fctid	$dota,$dota
 	fctid	$dotb,$dotb
@@ -1354,14 +1356,14 @@ $code.=<<___;
 ___
 } else {
 $code.=<<___;
-	lwz	$t1,`$FRAME+0`($sp)
-	lwz	$t0,`$FRAME+4`($sp)
-	lwz	$t3,`$FRAME+8`($sp)
-	lwz	$t2,`$FRAME+12`($sp)
-	lwz	$t5,`$FRAME+16`($sp)
-	lwz	$t4,`$FRAME+20`($sp)
-	lwz	$t7,`$FRAME+24`($sp)
-	lwz	$t6,`$FRAME+28`($sp)
+	lwz	$t1,`$FRAME+0^$LITTLE_ENDIAN`($sp)
+	lwz	$t0,`$FRAME+4^$LITTLE_ENDIAN`($sp)
+	lwz	$t3,`$FRAME+8^$LITTLE_ENDIAN`($sp)
+	lwz	$t2,`$FRAME+12^$LITTLE_ENDIAN`($sp)
+	lwz	$t5,`$FRAME+16^$LITTLE_ENDIAN`($sp)
+	lwz	$t4,`$FRAME+20^$LITTLE_ENDIAN`($sp)
+	lwz	$t7,`$FRAME+24^$LITTLE_ENDIAN`($sp)
+	lwz	$t6,`$FRAME+28^$LITTLE_ENDIAN`($sp)
 	stfd	$dota,`$FRAME+64`($sp)
 	stfd	$dotb,`$FRAME+72`($sp)
 
@@ -1397,14 +1399,14 @@ $code.=<<___;
 	 stw	$t0,4($tp)		; tp[j-1]
 	 stw	$t4,0($tp)
 
-	lwz	$t3,`$FRAME+32`($sp)	; permuted $t1
-	lwz	$t2,`$FRAME+36`($sp)	; permuted $t0
-	lwz	$t7,`$FRAME+40`($sp)	; permuted $t3
-	lwz	$t6,`$FRAME+44`($sp)	; permuted $t2
-	lwz	$t1,`$FRAME+48`($sp)	; permuted $t5
-	lwz	$t0,`$FRAME+52`($sp)	; permuted $t4
-	lwz	$t5,`$FRAME+56`($sp)	; permuted $t7
-	lwz	$t4,`$FRAME+60`($sp)	; permuted $t6
+	lwz	$t3,`$FRAME+32^$LITTLE_ENDIAN`($sp)	; permuted $t1
+	lwz	$t2,`$FRAME+36^$LITTLE_ENDIAN`($sp)	; permuted $t0
+	lwz	$t7,`$FRAME+40^$LITTLE_ENDIAN`($sp)	; permuted $t3
+	lwz	$t6,`$FRAME+44^$LITTLE_ENDIAN`($sp)	; permuted $t2
+	lwz	$t1,`$FRAME+48^$LITTLE_ENDIAN`($sp)	; permuted $t5
+	lwz	$t0,`$FRAME+52^$LITTLE_ENDIAN`($sp)	; permuted $t4
+	lwz	$t5,`$FRAME+56^$LITTLE_ENDIAN`($sp)	; permuted $t7
+	lwz	$t4,`$FRAME+60^$LITTLE_ENDIAN`($sp)	; permuted $t6
 
 	addc	$t2,$t2,$carry
 	adde	$t3,$t3,$c1
@@ -1433,12 +1435,12 @@ $code.=<<___;
 
 	addc	$t2,$t2,$t6
 	adde	$t0,$t0,$t7
-	 lwz	$t7,`$FRAME+64`($sp)
-	 lwz	$t6,`$FRAME+68`($sp)
+	 lwz	$t7,`$FRAME+64^$LITTLE_ENDIAN`($sp)
+	 lwz	$t6,`$FRAME+68^$LITTLE_ENDIAN`($sp)
 	addze	$carry,$carry
 	addze	$c1,$c1
-	 lwz	$t5,`$FRAME+72`($sp)
-	 lwz	$t4,`$FRAME+76`($sp)
+	 lwz	$t5,`$FRAME+72^$LITTLE_ENDIAN`($sp)
+	 lwz	$t4,`$FRAME+76^$LITTLE_ENDIAN`($sp)
 
 	addc	$t6,$t6,$carry
 	adde	$t7,$t7,$c1
@@ -1488,7 +1490,7 @@ Lsub:	ldx	$t0,$tp,$i
 	stdx	$t0,$rp,$i
 	stdx	$t2,$t6,$i
 	addi	$i,$i,16
-	bdnz-	Lsub
+	bdnz	Lsub
 
 	li	$i,0
 	subfe	$ovf,$i,$ovf	; handle upmost overflow bit
@@ -1515,7 +1517,7 @@ Lcopy:				; copy or in-place refresh
 	stdx	$i,$tp,$i	; zap tp at once
 	stdx	$i,$t4,$i
 	addi	$i,$i,16
-	bdnz-	Lcopy
+	bdnz	Lcopy
 ___
 $code.=<<___ if ($SIZE_T==4);
 	subf	$np,$num,$np	; rewind np
@@ -1548,7 +1550,7 @@ Lsub:	lwz	$t0,12($tp)	; load tp[j..j+3] in 64-bit word order
 	stw	$t5,8($rp)
 	stw	$t6,12($rp)
 	stwu	$t7,16($rp)
-	bdnz-	Lsub
+	bdnz	Lsub
 
 	li	$i,0
 	subfe	$ovf,$i,$ovf	; handle upmost overflow bit
@@ -1580,7 +1582,7 @@ Lcopy:				; copy or in-place refresh
 	stwu	$t3,16($rp)
 	std	$i,8($tp)	; zap tp at once
 	stdu	$i,16($tp)
-	bdnz-	Lcopy
+	bdnz	Lcopy
 ___
 
 $code.=<<___;

crypto/bn/asm/rsaz-avx2.pl

@@ -443,7 +443,7 @@ $TEMP2 = $B2;
 $TEMP3 = $Y1;
 $TEMP4 = $Y2;
 $code.=<<___;
-	#we need to fix indexes 32-39 to avoid overflow
+	# we need to fix indices 32-39 to avoid overflow
 	vmovdqu		32*8(%rsp), $ACC8		# 32*8-192($tp0),
 	vmovdqu		32*9(%rsp), $ACC1		# 32*9-192($tp0)
 	vmovdqu		32*10(%rsp), $ACC2		# 32*10-192($tp0)
@@ -1592,68 +1592,128 @@ rsaz_1024_scatter5_avx2:
 .type	rsaz_1024_gather5_avx2,\@abi-omnipotent
 .align	32
 rsaz_1024_gather5_avx2:
+	vzeroupper
+	mov	%rsp,%r11
 ___
 $code.=<<___ if ($win64);
 	lea	-0x88(%rsp),%rax
-	vzeroupper
 .LSEH_begin_rsaz_1024_gather5:
 	# I can't trust assembler to use specific encoding:-(
-	.byte	0x48,0x8d,0x60,0xe0		#lea	-0x20(%rax),%rsp
-	.byte	0xc5,0xf8,0x29,0x70,0xe0	#vmovaps %xmm6,-0x20(%rax)
-	.byte	0xc5,0xf8,0x29,0x78,0xf0	#vmovaps %xmm7,-0x10(%rax)
-	.byte	0xc5,0x78,0x29,0x40,0x00	#vmovaps %xmm8,0(%rax)
-	.byte	0xc5,0x78,0x29,0x48,0x10	#vmovaps %xmm9,0x10(%rax)
-	.byte	0xc5,0x78,0x29,0x50,0x20	#vmovaps %xmm10,0x20(%rax)
-	.byte	0xc5,0x78,0x29,0x58,0x30	#vmovaps %xmm11,0x30(%rax)
-	.byte	0xc5,0x78,0x29,0x60,0x40	#vmovaps %xmm12,0x40(%rax)
-	.byte	0xc5,0x78,0x29,0x68,0x50	#vmovaps %xmm13,0x50(%rax)
-	.byte	0xc5,0x78,0x29,0x70,0x60	#vmovaps %xmm14,0x60(%rax)
-	.byte	0xc5,0x78,0x29,0x78,0x70	#vmovaps %xmm15,0x70(%rax)
+	.byte	0x48,0x8d,0x60,0xe0		# lea	-0x20(%rax),%rsp
+	.byte	0xc5,0xf8,0x29,0x70,0xe0	# vmovaps %xmm6,-0x20(%rax)
+	.byte	0xc5,0xf8,0x29,0x78,0xf0	# vmovaps %xmm7,-0x10(%rax)
+	.byte	0xc5,0x78,0x29,0x40,0x00	# vmovaps %xmm8,0(%rax)
+	.byte	0xc5,0x78,0x29,0x48,0x10	# vmovaps %xmm9,0x10(%rax)
+	.byte	0xc5,0x78,0x29,0x50,0x20	# vmovaps %xmm10,0x20(%rax)
+	.byte	0xc5,0x78,0x29,0x58,0x30	# vmovaps %xmm11,0x30(%rax)
+	.byte	0xc5,0x78,0x29,0x60,0x40	# vmovaps %xmm12,0x40(%rax)
+	.byte	0xc5,0x78,0x29,0x68,0x50	# vmovaps %xmm13,0x50(%rax)
+	.byte	0xc5,0x78,0x29,0x70,0x60	# vmovaps %xmm14,0x60(%rax)
+	.byte	0xc5,0x78,0x29,0x78,0x70	# vmovaps %xmm15,0x70(%rax)
 ___
 $code.=<<___;
-	lea	.Lgather_table(%rip),%r11
-	mov	$power,%eax
-	and	\$3,$power
-	shr	\$2,%eax			# cache line number
-	shl	\$4,$power			# offset within cache line
+	lea	-0x100(%rsp),%rsp
+	and	\$-32, %rsp
+	lea	.Linc(%rip), %r10
+	lea	-128(%rsp),%rax			# control u-op density
 
-	vmovdqu		-32(%r11),%ymm7		# .Lgather_permd
-	vpbroadcastb	8(%r11,%rax), %xmm8
-	vpbroadcastb	7(%r11,%rax), %xmm9
-	vpbroadcastb	6(%r11,%rax), %xmm10
-	vpbroadcastb	5(%r11,%rax), %xmm11
-	vpbroadcastb	4(%r11,%rax), %xmm12
-	vpbroadcastb	3(%r11,%rax), %xmm13
-	vpbroadcastb	2(%r11,%rax), %xmm14
-	vpbroadcastb	1(%r11,%rax), %xmm15
+	vmovd		$power, %xmm4
+	vmovdqa		(%r10),%ymm0
+	vmovdqa		32(%r10),%ymm1
+	vmovdqa		64(%r10),%ymm5
+	vpbroadcastd	%xmm4,%ymm4
 
-	lea	64($inp,$power),$inp
-	mov	\$64,%r11			# size optimization
-	mov	\$9,%eax
-	jmp	.Loop_gather_1024
+	vpaddd		%ymm5, %ymm0, %ymm2
+	vpcmpeqd	%ymm4, %ymm0, %ymm0
+	vpaddd		%ymm5, %ymm1, %ymm3
+	vpcmpeqd	%ymm4, %ymm1, %ymm1
+	vmovdqa		%ymm0, 32*0+128(%rax)
+	vpaddd		%ymm5, %ymm2, %ymm0
+	vpcmpeqd	%ymm4, %ymm2, %ymm2
+	vmovdqa		%ymm1, 32*1+128(%rax)
+	vpaddd		%ymm5, %ymm3, %ymm1
+	vpcmpeqd	%ymm4, %ymm3, %ymm3
+	vmovdqa		%ymm2, 32*2+128(%rax)
+	vpaddd		%ymm5, %ymm0, %ymm2
+	vpcmpeqd	%ymm4, %ymm0, %ymm0
+	vmovdqa		%ymm3, 32*3+128(%rax)
+	vpaddd		%ymm5, %ymm1, %ymm3
+	vpcmpeqd	%ymm4, %ymm1, %ymm1
+	vmovdqa		%ymm0, 32*4+128(%rax)
+	vpaddd		%ymm5, %ymm2, %ymm8
+	vpcmpeqd	%ymm4, %ymm2, %ymm2
+	vmovdqa		%ymm1, 32*5+128(%rax)
+	vpaddd		%ymm5, %ymm3, %ymm9
+	vpcmpeqd	%ymm4, %ymm3, %ymm3
+	vmovdqa		%ymm2, 32*6+128(%rax)
+	vpaddd		%ymm5, %ymm8, %ymm10
+	vpcmpeqd	%ymm4, %ymm8, %ymm8
+	vmovdqa		%ymm3, 32*7+128(%rax)
+	vpaddd		%ymm5, %ymm9, %ymm11
+	vpcmpeqd	%ymm4, %ymm9, %ymm9
+	vpaddd		%ymm5, %ymm10, %ymm12
+	vpcmpeqd	%ymm4, %ymm10, %ymm10
+	vpaddd		%ymm5, %ymm11, %ymm13
+	vpcmpeqd	%ymm4, %ymm11, %ymm11
+	vpaddd		%ymm5, %ymm12, %ymm14
+	vpcmpeqd	%ymm4, %ymm12, %ymm12
+	vpaddd		%ymm5, %ymm13, %ymm15
+	vpcmpeqd	%ymm4, %ymm13, %ymm13
+	vpcmpeqd	%ymm4, %ymm14, %ymm14
+	vpcmpeqd	%ymm4, %ymm15, %ymm15
+
+	vmovdqa	-32(%r10),%ymm7			# .Lgather_permd
+	lea	128($inp), $inp
+	mov	\$9,$power
 
-.align	32
 .Loop_gather_1024:
-	vpand		-64($inp),		%xmm8,%xmm0
-	vpand		($inp),			%xmm9,%xmm1
-	vpand		64($inp),		%xmm10,%xmm2
-	vpand		($inp,%r11,2),		%xmm11,%xmm3
-	 vpor					%xmm0,%xmm1,%xmm1
-	vpand		64($inp,%r11,2),	%xmm12,%xmm4
-	 vpor					%xmm2,%xmm3,%xmm3
-	vpand		($inp,%r11,4),		%xmm13,%xmm5
-	 vpor					%xmm1,%xmm3,%xmm3
-	vpand		64($inp,%r11,4),	%xmm14,%xmm6
-	 vpor					%xmm4,%xmm5,%xmm5
-	vpand		-128($inp,%r11,8),	%xmm15,%xmm2
-	lea		($inp,%r11,8),$inp
-	 vpor					%xmm3,%xmm5,%xmm5
-	 vpor					%xmm2,%xmm6,%xmm6
-	 vpor					%xmm5,%xmm6,%xmm6
-	vpermd		%ymm6,%ymm7,%ymm6
-	vmovdqu		%ymm6,($out)
+	vmovdqa		32*0-128($inp),	%ymm0
+	vmovdqa		32*1-128($inp),	%ymm1
+	vmovdqa		32*2-128($inp),	%ymm2
+	vmovdqa		32*3-128($inp),	%ymm3
+	vpand		32*0+128(%rax),	%ymm0,	%ymm0
+	vpand		32*1+128(%rax),	%ymm1,	%ymm1
+	vpand		32*2+128(%rax),	%ymm2,	%ymm2
+	vpor		%ymm0, %ymm1, %ymm4
+	vpand		32*3+128(%rax),	%ymm3,	%ymm3
+	vmovdqa		32*4-128($inp),	%ymm0
+	vmovdqa		32*5-128($inp),	%ymm1
+	vpor		%ymm2, %ymm3, %ymm5
+	vmovdqa		32*6-128($inp),	%ymm2
+	vmovdqa		32*7-128($inp),	%ymm3
+	vpand		32*4+128(%rax),	%ymm0,	%ymm0
+	vpand		32*5+128(%rax),	%ymm1,	%ymm1
+	vpand		32*6+128(%rax),	%ymm2,	%ymm2
+	vpor		%ymm0, %ymm4, %ymm4
+	vpand		32*7+128(%rax),	%ymm3,	%ymm3
+	vpand		32*8-128($inp),	%ymm8,	%ymm0
+	vpor		%ymm1, %ymm5, %ymm5
+	vpand		32*9-128($inp),	%ymm9,	%ymm1
+	vpor		%ymm2, %ymm4, %ymm4
+	vpand		32*10-128($inp),%ymm10,	%ymm2
+	vpor		%ymm3, %ymm5, %ymm5
+	vpand		32*11-128($inp),%ymm11,	%ymm3
+	vpor		%ymm0, %ymm4, %ymm4
+	vpand		32*12-128($inp),%ymm12,	%ymm0
+	vpor		%ymm1, %ymm5, %ymm5
+	vpand		32*13-128($inp),%ymm13,	%ymm1
+	vpor		%ymm2, %ymm4, %ymm4
+	vpand		32*14-128($inp),%ymm14,	%ymm2
+	vpor		%ymm3, %ymm5, %ymm5
+	vpand		32*15-128($inp),%ymm15,	%ymm3
+	lea		32*16($inp), $inp
+	vpor		%ymm0, %ymm4, %ymm4
+	vpor		%ymm1, %ymm5, %ymm5
+	vpor		%ymm2, %ymm4, %ymm4
+	vpor		%ymm3, %ymm5, %ymm5
+
+	vpor		%ymm5, %ymm4, %ymm4
+	vextracti128	\$1, %ymm4, %xmm5	# upper half is cleared
+	vpor		%xmm4, %xmm5, %xmm5
+	vpermd		%ymm5,%ymm7,%ymm5
+	vmovdqu		%ymm5,($out)
 	lea		32($out),$out
-	dec	%eax
+	dec	$power
 	jnz	.Loop_gather_1024
 
 	vpxor	%ymm0,%ymm0,%ymm0
@@ -1661,20 +1721,20 @@ $code.=<<___;
 	vzeroupper
 ___
 $code.=<<___ if ($win64);
-	movaps	(%rsp),%xmm6
-	movaps	0x10(%rsp),%xmm7
-	movaps	0x20(%rsp),%xmm8
-	movaps	0x30(%rsp),%xmm9
-	movaps	0x40(%rsp),%xmm10
-	movaps	0x50(%rsp),%xmm11
-	movaps	0x60(%rsp),%xmm12
-	movaps	0x70(%rsp),%xmm13
-	movaps	0x80(%rsp),%xmm14
-	movaps	0x90(%rsp),%xmm15
-	lea	0xa8(%rsp),%rsp
+	movaps	-0xa8(%r11),%xmm6
+	movaps	-0x98(%r11),%xmm7
+	movaps	-0x88(%r11),%xmm8
+	movaps	-0x78(%r11),%xmm9
+	movaps	-0x68(%r11),%xmm10
+	movaps	-0x58(%r11),%xmm11
+	movaps	-0x48(%r11),%xmm12
+	movaps	-0x38(%r11),%xmm13
+	movaps	-0x28(%r11),%xmm14
+	movaps	-0x18(%r11),%xmm15
 .LSEH_end_rsaz_1024_gather5:
 ___
 $code.=<<___;
+	lea	(%r11),%rsp
 	ret
 .size	rsaz_1024_gather5_avx2,.-rsaz_1024_gather5_avx2
 ___
@@ -1708,8 +1768,10 @@ $code.=<<___;
 	.long	0,2,4,6,7,7,7,7
 .Lgather_permd:
 	.long	0,7,1,7,2,7,3,7
-.Lgather_table:
-	.byte	0,0,0,0,0,0,0,0, 0xff,0,0,0,0,0,0,0
+.Linc:
+	.long	0,0,0,0, 1,1,1,1
+	.long	2,2,2,2, 3,3,3,3
+	.long	4,4,4,4, 4,4,4,4
 .align	64
 ___
 
@@ -1837,18 +1899,19 @@ rsaz_se_handler:
 	.rva	rsaz_se_handler
 	.rva	.Lmul_1024_body,.Lmul_1024_epilogue
 .LSEH_info_rsaz_1024_gather5:
-	.byte	0x01,0x33,0x16,0x00
-	.byte	0x36,0xf8,0x09,0x00	#vmovaps 0x90(rsp),xmm15
-	.byte	0x31,0xe8,0x08,0x00	#vmovaps 0x80(rsp),xmm14
-	.byte	0x2c,0xd8,0x07,0x00	#vmovaps 0x70(rsp),xmm13
-	.byte	0x27,0xc8,0x06,0x00	#vmovaps 0x60(rsp),xmm12
-	.byte	0x22,0xb8,0x05,0x00	#vmovaps 0x50(rsp),xmm11
-	.byte	0x1d,0xa8,0x04,0x00	#vmovaps 0x40(rsp),xmm10
-	.byte	0x18,0x98,0x03,0x00	#vmovaps 0x30(rsp),xmm9
-	.byte	0x13,0x88,0x02,0x00	#vmovaps 0x20(rsp),xmm8
-	.byte	0x0e,0x78,0x01,0x00	#vmovaps 0x10(rsp),xmm7
-	.byte	0x09,0x68,0x00,0x00	#vmovaps 0x00(rsp),xmm6
-	.byte	0x04,0x01,0x15,0x00	#sub	rsp,0xa8
+	.byte	0x01,0x36,0x17,0x0b
+	.byte	0x36,0xf8,0x09,0x00	# vmovaps 0x90(rsp),xmm15
+	.byte	0x31,0xe8,0x08,0x00	# vmovaps 0x80(rsp),xmm14
+	.byte	0x2c,0xd8,0x07,0x00	# vmovaps 0x70(rsp),xmm13
+	.byte	0x27,0xc8,0x06,0x00	# vmovaps 0x60(rsp),xmm12
+	.byte	0x22,0xb8,0x05,0x00	# vmovaps 0x50(rsp),xmm11
+	.byte	0x1d,0xa8,0x04,0x00	# vmovaps 0x40(rsp),xmm10
+	.byte	0x18,0x98,0x03,0x00	# vmovaps 0x30(rsp),xmm9
+	.byte	0x13,0x88,0x02,0x00	# vmovaps 0x20(rsp),xmm8
+	.byte	0x0e,0x78,0x01,0x00	# vmovaps 0x10(rsp),xmm7
+	.byte	0x09,0x68,0x00,0x00	# vmovaps 0x00(rsp),xmm6
+	.byte	0x04,0x01,0x15,0x00	# sub	  rsp,0xa8
+	.byte	0x00,0xb3,0x00,0x00	# set_frame r11
 ___
 }
 

crypto/bn/asm/rsaz-x86_64.pl

@@ -113,7 +113,7 @@ if (!$addx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
 	$addx = ($1>=12);
 }
 
-if (!$addx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9])\.([0-9]+)/) {
+if (!$addx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9])\.([0-9]+)/) {
 	my $ver = $2 + $3/100.0;	# 3.1->3.01, 3.10->3.10
 	$addx = ($ver>=3.03);
 }
@@ -915,9 +915,76 @@ rsaz_512_mul_gather4:
 	push	%r14
 	push	%r15
 
-	mov	$pwr, $pwr
-	subq	\$128+24, %rsp
+	subq	\$`128+24+($win64?0xb0:0)`, %rsp
+___
+$code.=<<___	if ($win64);
+	movaps	%xmm6,0xa0(%rsp)
+	movaps	%xmm7,0xb0(%rsp)
+	movaps	%xmm8,0xc0(%rsp)
+	movaps	%xmm9,0xd0(%rsp)
+	movaps	%xmm10,0xe0(%rsp)
+	movaps	%xmm11,0xf0(%rsp)
+	movaps	%xmm12,0x100(%rsp)
+	movaps	%xmm13,0x110(%rsp)
+	movaps	%xmm14,0x120(%rsp)
+	movaps	%xmm15,0x130(%rsp)
+___
+$code.=<<___;
 .Lmul_gather4_body:
+	movd	$pwr,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1	# 00000002000000020000000200000002
+	movdqa	.Linc(%rip),%xmm0	# 00000001000000010000000000000000
+
+	pshufd	\$0,%xmm8,%xmm8		# broadcast $power
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..15 to $power
+#
+for($i=0;$i<4;$i++) {
+$code.=<<___;
+	paddd	%xmm`$i`,%xmm`$i+1`
+	pcmpeqd	%xmm8,%xmm`$i`
+	movdqa	%xmm7,%xmm`$i+3`
+___
+}
+for(;$i<7;$i++) {
+$code.=<<___;
+	paddd	%xmm`$i`,%xmm`$i+1`
+	pcmpeqd	%xmm8,%xmm`$i`
+___
+}
+$code.=<<___;
+	pcmpeqd	%xmm8,%xmm7
+
+	movdqa	16*0($bp),%xmm8
+	movdqa	16*1($bp),%xmm9
+	movdqa	16*2($bp),%xmm10
+	movdqa	16*3($bp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	16*4($bp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	16*5($bp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	16*6($bp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	16*7($bp),%xmm15
+	leaq	128($bp), %rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	\$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
 ___
 $code.=<<___ if ($addx);
 	movl	\$0x80100,%r11d
@@ -926,45 +993,38 @@ $code.=<<___ if ($addx);
 	je	.Lmulx_gather
 ___
 $code.=<<___;
-	movl	64($bp,$pwr,4), %eax
-	movq	$out, %xmm0		# off-load arguments
-	movl	($bp,$pwr,4), %ebx
-	movq	$mod, %xmm1
-	movq	$n0, 128(%rsp)
+	movq	%xmm8,%rbx
+
+	movq	$n0, 128(%rsp)		# off-load arguments
+	movq	$out, 128+8(%rsp)
+	movq	$mod, 128+16(%rsp)
 
-	shlq	\$32, %rax
-	or	%rax, %rbx
 	movq	($ap), %rax
 	 movq	8($ap), %rcx
-	 leaq	128($bp,$pwr,4), %rbp
 	mulq	%rbx			# 0 iteration
 	movq	%rax, (%rsp)
 	movq	%rcx, %rax
 	movq	%rdx, %r8
 
 	mulq	%rbx
-	 movd	(%rbp), %xmm4
 	addq	%rax, %r8
 	movq	16($ap), %rax
 	movq	%rdx, %r9
 	adcq	\$0, %r9
 
 	mulq	%rbx
-	 movd	64(%rbp), %xmm5
 	addq	%rax, %r9
 	movq	24($ap), %rax
 	movq	%rdx, %r10
 	adcq	\$0, %r10
 
 	mulq	%rbx
-	 pslldq	\$4, %xmm5
 	addq	%rax, %r10
 	movq	32($ap), %rax
 	movq	%rdx, %r11
 	adcq	\$0, %r11
 
 	mulq	%rbx
-	 por	%xmm5, %xmm4
 	addq	%rax, %r11
 	movq	40($ap), %rax
 	movq	%rdx, %r12
@@ -977,14 +1037,12 @@ $code.=<<___;
 	adcq	\$0, %r13
 
 	mulq	%rbx
-	 leaq	128(%rbp), %rbp
 	addq	%rax, %r13
 	movq	56($ap), %rax
 	movq	%rdx, %r14
 	adcq	\$0, %r14
 	
 	mulq	%rbx
-	 movq	%xmm4, %rbx
 	addq	%rax, %r14
 	 movq	($ap), %rax
 	movq	%rdx, %r15
@@ -996,6 +1054,35 @@ $code.=<<___;
 
 .align	32
 .Loop_mul_gather:
+	movdqa	16*0(%rbp),%xmm8
+	movdqa	16*1(%rbp),%xmm9
+	movdqa	16*2(%rbp),%xmm10
+	movdqa	16*3(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	16*4(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	16*5(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	16*6(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	16*7(%rbp),%xmm15
+	leaq	128(%rbp), %rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	\$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,%rbx
+
 	mulq	%rbx
 	addq	%rax, %r8
 	movq	8($ap), %rax
@@ -1004,7 +1091,6 @@ $code.=<<___;
 	adcq	\$0, %r8
 
 	mulq	%rbx
-	 movd	(%rbp), %xmm4
 	addq	%rax, %r9
 	movq	16($ap), %rax
 	adcq	\$0, %rdx
@@ -1013,7 +1099,6 @@ $code.=<<___;
 	adcq	\$0, %r9
 
 	mulq	%rbx
-	 movd	64(%rbp), %xmm5
 	addq	%rax, %r10
 	movq	24($ap), %rax
 	adcq	\$0, %rdx
@@ -1022,7 +1107,6 @@ $code.=<<___;
 	adcq	\$0, %r10
 
 	mulq	%rbx
-	 pslldq	\$4, %xmm5
 	addq	%rax, %r11
 	movq	32($ap), %rax
 	adcq	\$0, %rdx
@@ -1031,7 +1115,6 @@ $code.=<<___;
 	adcq	\$0, %r11
 
 	mulq	%rbx
-	 por	%xmm5, %xmm4
 	addq	%rax, %r12
 	movq	40($ap), %rax
 	adcq	\$0, %rdx
@@ -1056,7 +1139,6 @@ $code.=<<___;
 	adcq	\$0, %r14
 
 	mulq	%rbx
-	 movq	%xmm4, %rbx
 	addq	%rax, %r15
 	 movq	($ap), %rax
 	adcq	\$0, %rdx
@@ -1064,7 +1146,6 @@ $code.=<<___;
 	movq	%rdx, %r15	
 	adcq	\$0, %r15
 
-	leaq	128(%rbp), %rbp
 	leaq	8(%rdi), %rdi
 
 	decl	%ecx
@@ -1079,8 +1160,8 @@ $code.=<<___;
 	movq	%r14, 48(%rdi)
 	movq	%r15, 56(%rdi)
 
-	movq	%xmm0, $out
-	movq	%xmm1, %rbp
+	movq	128+8(%rsp), $out
+	movq	128+16(%rsp), %rbp
 
 	movq	(%rsp), %r8
 	movq	8(%rsp), %r9
@@ -1098,45 +1179,37 @@ $code.=<<___ if ($addx);
 
 .align	32
 .Lmulx_gather:
-	mov	64($bp,$pwr,4), %eax
-	movq	$out, %xmm0		# off-load arguments
-	lea	128($bp,$pwr,4), %rbp
-	mov	($bp,$pwr,4), %edx
-	movq	$mod, %xmm1
-	mov	$n0, 128(%rsp)
+	movq	%xmm8,%rdx
+
+	mov	$n0, 128(%rsp)		# off-load arguments
+	mov	$out, 128+8(%rsp)
+	mov	$mod, 128+16(%rsp)
 
-	shl	\$32, %rax
-	or	%rax, %rdx
 	mulx	($ap), %rbx, %r8	# 0 iteration
 	mov	%rbx, (%rsp)
 	xor	%edi, %edi		# cf=0, of=0
 
 	mulx	8($ap), %rax, %r9
-	 movd	(%rbp), %xmm4
 
 	mulx	16($ap), %rbx, %r10
-	 movd	64(%rbp), %xmm5
 	adcx	%rax, %r8
 
 	mulx	24($ap), %rax, %r11
-	 pslldq	\$4, %xmm5
 	adcx	%rbx, %r9
 
 	mulx	32($ap), %rbx, %r12
-	 por	%xmm5, %xmm4
 	adcx	%rax, %r10
 
 	mulx	40($ap), %rax, %r13
 	adcx	%rbx, %r11
 
 	mulx	48($ap), %rbx, %r14
-	 lea	128(%rbp), %rbp
 	adcx	%rax, %r12
 	
 	mulx	56($ap), %rax, %r15
-	 movq	%xmm4, %rdx
 	adcx	%rbx, %r13
 	adcx	%rax, %r14
+	.byte	0x67
 	mov	%r8, %rbx
 	adcx	%rdi, %r15		# %rdi is 0
 
@@ -1145,24 +1218,48 @@ $code.=<<___ if ($addx);
 
 .align	32
 .Loop_mulx_gather:
-	mulx	($ap), %rax, %r8
+	movdqa	16*0(%rbp),%xmm8
+	movdqa	16*1(%rbp),%xmm9
+	movdqa	16*2(%rbp),%xmm10
+	movdqa	16*3(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	16*4(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	16*5(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	16*6(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	16*7(%rbp),%xmm15
+	leaq	128(%rbp), %rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	\$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,%rdx
+
+	.byte	0xc4,0x62,0xfb,0xf6,0x86,0x00,0x00,0x00,0x00	# mulx	($ap), %rax, %r8
 	adcx	%rax, %rbx
 	adox	%r9, %r8
 
 	mulx	8($ap), %rax, %r9
-	.byte	0x66,0x0f,0x6e,0xa5,0x00,0x00,0x00,0x00		# movd	(%rbp), %xmm4
 	adcx	%rax, %r8
 	adox	%r10, %r9
 
 	mulx	16($ap), %rax, %r10
-	 movd	64(%rbp), %xmm5
-	 lea	128(%rbp), %rbp
 	adcx	%rax, %r9
 	adox	%r11, %r10
 
 	.byte	0xc4,0x62,0xfb,0xf6,0x9e,0x18,0x00,0x00,0x00	# mulx	24($ap), %rax, %r11
-	 pslldq	\$4, %xmm5
-	 por	%xmm5, %xmm4
 	adcx	%rax, %r10
 	adox	%r12, %r11
 
@@ -1176,10 +1273,10 @@ $code.=<<___ if ($addx);
 
 	.byte	0xc4,0x62,0xfb,0xf6,0xb6,0x30,0x00,0x00,0x00	# mulx	48($ap), %rax, %r14
 	adcx	%rax, %r13
+	.byte	0x67
 	adox	%r15, %r14
 
 	mulx	56($ap), %rax, %r15
-	 movq	%xmm4, %rdx
 	 mov	%rbx, 64(%rsp,%rcx,8)
 	adcx	%rax, %r14
 	adox	%rdi, %r15
@@ -1198,10 +1295,10 @@ $code.=<<___ if ($addx);
 	mov	%r14, 64+48(%rsp)
 	mov	%r15, 64+56(%rsp)
 
-	movq	%xmm0, $out
-	movq	%xmm1, %rbp
+	mov	128(%rsp), %rdx		# pull arguments
+	mov	128+8(%rsp), $out
+	mov	128+16(%rsp), %rbp
 
-	mov	128(%rsp), %rdx		# pull $n0
 	mov	(%rsp), %r8
 	mov	8(%rsp), %r9
 	mov	16(%rsp), %r10
@@ -1229,6 +1326,21 @@ $code.=<<___;
 	call	__rsaz_512_subtract
 
 	leaq	128+24+48(%rsp), %rax
+___
+$code.=<<___	if ($win64);
+	movaps	0xa0-0xc8(%rax),%xmm6
+	movaps	0xb0-0xc8(%rax),%xmm7
+	movaps	0xc0-0xc8(%rax),%xmm8
+	movaps	0xd0-0xc8(%rax),%xmm9
+	movaps	0xe0-0xc8(%rax),%xmm10
+	movaps	0xf0-0xc8(%rax),%xmm11
+	movaps	0x100-0xc8(%rax),%xmm12
+	movaps	0x110-0xc8(%rax),%xmm13
+	movaps	0x120-0xc8(%rax),%xmm14
+	movaps	0x130-0xc8(%rax),%xmm15
+	lea	0xb0(%rax),%rax
+___
+$code.=<<___;
 	movq	-48(%rax), %r15
 	movq	-40(%rax), %r14
 	movq	-32(%rax), %r13
@@ -1258,7 +1370,7 @@ rsaz_512_mul_scatter4:
 	mov	$pwr, $pwr
 	subq	\$128+24, %rsp
 .Lmul_scatter4_body:
-	leaq	($tbl,$pwr,4), $tbl
+	leaq	($tbl,$pwr,8), $tbl
 	movq	$out, %xmm0		# off-load arguments
 	movq	$mod, %xmm1
 	movq	$tbl, %xmm2
@@ -1329,30 +1441,14 @@ $code.=<<___;
 
 	call	__rsaz_512_subtract
 
-	movl	%r8d, 64*0($inp)	# scatter
-	shrq	\$32, %r8
-	movl	%r9d, 64*2($inp)
-	shrq	\$32, %r9
-	movl	%r10d, 64*4($inp)
-	shrq	\$32, %r10
-	movl	%r11d, 64*6($inp)
-	shrq	\$32, %r11
-	movl	%r12d, 64*8($inp)
-	shrq	\$32, %r12
-	movl	%r13d, 64*10($inp)
-	shrq	\$32, %r13
-	movl	%r14d, 64*12($inp)
-	shrq	\$32, %r14
-	movl	%r15d, 64*14($inp)
-	shrq	\$32, %r15
-	movl	%r8d, 64*1($inp)
-	movl	%r9d, 64*3($inp)
-	movl	%r10d, 64*5($inp)
-	movl	%r11d, 64*7($inp)
-	movl	%r12d, 64*9($inp)
-	movl	%r13d, 64*11($inp)
-	movl	%r14d, 64*13($inp)
-	movl	%r15d, 64*15($inp)
+	movq	%r8, 128*0($inp)	# scatter
+	movq	%r9, 128*1($inp)
+	movq	%r10, 128*2($inp)
+	movq	%r11, 128*3($inp)
+	movq	%r12, 128*4($inp)
+	movq	%r13, 128*5($inp)
+	movq	%r14, 128*6($inp)
+	movq	%r15, 128*7($inp)
 
 	leaq	128+24+48(%rsp), %rax
 	movq	-48(%rax), %r15
@@ -1956,16 +2052,14 @@ $code.=<<___;
 .type	rsaz_512_scatter4,\@abi-omnipotent
 .align	16
 rsaz_512_scatter4:
-	leaq	($out,$power,4), $out
+	leaq	($out,$power,8), $out
 	movl	\$8, %r9d
 	jmp	.Loop_scatter
 .align	16
 .Loop_scatter:
 	movq	($inp), %rax
 	leaq	8($inp), $inp
-	movl	%eax, ($out)
-	shrq	\$32, %rax
-	movl	%eax, 64($out)
+	movq	%rax, ($out)
 	leaq	128($out), $out
 	decl	%r9d
 	jnz	.Loop_scatter
@@ -1976,22 +2070,106 @@ rsaz_512_scatter4:
 .type	rsaz_512_gather4,\@abi-omnipotent
 .align	16
 rsaz_512_gather4:
-	leaq	($inp,$power,4), $inp
+___
+$code.=<<___	if ($win64);
+.LSEH_begin_rsaz_512_gather4:
+	.byte	0x48,0x81,0xec,0xa8,0x00,0x00,0x00	# sub    $0xa8,%rsp
+	.byte	0x0f,0x29,0x34,0x24			# movaps %xmm6,(%rsp)
+	.byte	0x0f,0x29,0x7c,0x24,0x10		# movaps %xmm7,0x10(%rsp)
+	.byte	0x44,0x0f,0x29,0x44,0x24,0x20		# movaps %xmm8,0x20(%rsp)
+	.byte	0x44,0x0f,0x29,0x4c,0x24,0x30		# movaps %xmm9,0x30(%rsp)
+	.byte	0x44,0x0f,0x29,0x54,0x24,0x40		# movaps %xmm10,0x40(%rsp)
+	.byte	0x44,0x0f,0x29,0x5c,0x24,0x50		# movaps %xmm11,0x50(%rsp)
+	.byte	0x44,0x0f,0x29,0x64,0x24,0x60		# movaps %xmm12,0x60(%rsp)
+	.byte	0x44,0x0f,0x29,0x6c,0x24,0x70		# movaps %xmm13,0x70(%rsp)
+	.byte	0x44,0x0f,0x29,0xb4,0x24,0x80,0,0,0	# movaps %xmm14,0x80(%rsp)
+	.byte	0x44,0x0f,0x29,0xbc,0x24,0x90,0,0,0	# movaps %xmm15,0x90(%rsp)
+___
+$code.=<<___;
+	movd	$power,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1	# 00000002000000020000000200000002
+	movdqa	.Linc(%rip),%xmm0	# 00000001000000010000000000000000
+
+	pshufd	\$0,%xmm8,%xmm8		# broadcast $power
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..15 to $power
+#
+for($i=0;$i<4;$i++) {
+$code.=<<___;
+	paddd	%xmm`$i`,%xmm`$i+1`
+	pcmpeqd	%xmm8,%xmm`$i`
+	movdqa	%xmm7,%xmm`$i+3`
+___
+}
+for(;$i<7;$i++) {
+$code.=<<___;
+	paddd	%xmm`$i`,%xmm`$i+1`
+	pcmpeqd	%xmm8,%xmm`$i`
+___
+}
+$code.=<<___;
+	pcmpeqd	%xmm8,%xmm7
 	movl	\$8, %r9d
 	jmp	.Loop_gather
 .align	16
 .Loop_gather:
-	movl	($inp), %eax
-	movl	64($inp), %r8d
+	movdqa	16*0($inp),%xmm8
+	movdqa	16*1($inp),%xmm9
+	movdqa	16*2($inp),%xmm10
+	movdqa	16*3($inp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	16*4($inp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	16*5($inp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	16*6($inp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	16*7($inp),%xmm15
 	leaq	128($inp), $inp
-	shlq	\$32, %r8
-	or	%r8, %rax
-	movq	%rax, ($out)
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	\$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,($out)
 	leaq	8($out), $out
 	decl	%r9d
 	jnz	.Loop_gather
+___
+$code.=<<___	if ($win64);
+	movaps	0x00(%rsp),%xmm6
+	movaps	0x10(%rsp),%xmm7
+	movaps	0x20(%rsp),%xmm8
+	movaps	0x30(%rsp),%xmm9
+	movaps	0x40(%rsp),%xmm10
+	movaps	0x50(%rsp),%xmm11
+	movaps	0x60(%rsp),%xmm12
+	movaps	0x70(%rsp),%xmm13
+	movaps	0x80(%rsp),%xmm14
+	movaps	0x90(%rsp),%xmm15
+	add	\$0xa8,%rsp
+___
+$code.=<<___;
 	ret
+.LSEH_end_rsaz_512_gather4:
 .size	rsaz_512_gather4,.-rsaz_512_gather4
+
+.align	64
+.Linc:
+	.long	0,0, 1,1
+	.long	2,2, 2,2
 ___
 }
 
@@ -2039,6 +2217,18 @@ se_handler:
 
 	lea	128+24+48(%rax),%rax
 
+	lea	.Lmul_gather4_epilogue(%rip),%rbx
+	cmp	%r10,%rbx
+	jne	.Lse_not_in_mul_gather4
+
+	lea	0xb0(%rax),%rax
+
+	lea	-48-0xa8(%rax),%rsi
+	lea	512($context),%rdi
+	mov	\$20,%ecx
+	.long	0xa548f3fc		# cld; rep movsq
+
+.Lse_not_in_mul_gather4:
 	mov	-8(%rax),%rbx
 	mov	-16(%rax),%rbp
 	mov	-24(%rax),%r12
@@ -2090,7 +2280,7 @@ se_handler:
 	pop	%rdi
 	pop	%rsi
 	ret
-.size	sqr_handler,.-sqr_handler
+.size	se_handler,.-se_handler
 
 .section	.pdata
 .align	4
@@ -2114,6 +2304,10 @@ se_handler:
 	.rva	.LSEH_end_rsaz_512_mul_by_one
 	.rva	.LSEH_info_rsaz_512_mul_by_one
 
+	.rva	.LSEH_begin_rsaz_512_gather4
+	.rva	.LSEH_end_rsaz_512_gather4
+	.rva	.LSEH_info_rsaz_512_gather4
+
 .section	.xdata
 .align	8
 .LSEH_info_rsaz_512_sqr:
@@ -2136,6 +2330,19 @@ se_handler:
 	.byte	9,0,0,0
 	.rva	se_handler
 	.rva	.Lmul_by_one_body,.Lmul_by_one_epilogue		# HandlerData[]
+.LSEH_info_rsaz_512_gather4:
+	.byte	0x01,0x46,0x16,0x00
+	.byte	0x46,0xf8,0x09,0x00	# vmovaps 0x90(rsp),xmm15
+	.byte	0x3d,0xe8,0x08,0x00	# vmovaps 0x80(rsp),xmm14
+	.byte	0x34,0xd8,0x07,0x00	# vmovaps 0x70(rsp),xmm13
+	.byte	0x2e,0xc8,0x06,0x00	# vmovaps 0x60(rsp),xmm12
+	.byte	0x28,0xb8,0x05,0x00	# vmovaps 0x50(rsp),xmm11
+	.byte	0x22,0xa8,0x04,0x00	# vmovaps 0x40(rsp),xmm10
+	.byte	0x1c,0x98,0x03,0x00	# vmovaps 0x30(rsp),xmm9
+	.byte	0x16,0x88,0x02,0x00	# vmovaps 0x20(rsp),xmm8
+	.byte	0x10,0x78,0x01,0x00	# vmovaps 0x10(rsp),xmm7
+	.byte	0x0b,0x68,0x00,0x00	# vmovaps 0x00(rsp),xmm6
+	.byte	0x07,0x01,0x15,0x00	# sub     rsp,0xa8
 ___
 }
 

crypto/bn/asm/s390x-gf2m.pl

@@ -172,19 +172,19 @@ ___
 if ($SIZE_T==8) {
 my @r=map("%r$_",(6..9));
 $code.=<<___;
-	bras	$ra,_mul_1x1			# a1<EFBFBD>b1
+	bras	$ra,_mul_1x1			# a1·b1
 	stmg	$lo,$hi,16($rp)
 
 	lg	$a,`$stdframe+128+4*$SIZE_T`($sp)
 	lg	$b,`$stdframe+128+6*$SIZE_T`($sp)
-	bras	$ra,_mul_1x1			# a0<EFBFBD>b0
+	bras	$ra,_mul_1x1			# a0·b0
 	stmg	$lo,$hi,0($rp)
 
 	lg	$a,`$stdframe+128+3*$SIZE_T`($sp)
 	lg	$b,`$stdframe+128+5*$SIZE_T`($sp)
 	xg	$a,`$stdframe+128+4*$SIZE_T`($sp)
 	xg	$b,`$stdframe+128+6*$SIZE_T`($sp)
-	bras	$ra,_mul_1x1			# (a0+a1)<EFBFBD>(b0+b1)
+	bras	$ra,_mul_1x1			# (a0+a1)·(b0+b1)
 	lmg	@r[0],@r[3],0($rp)
 
 	xgr	$lo,$hi

crypto/bn/asm/s390x.S

@@ -18,71 +18,106 @@
 .align	4
 bn_mul_add_words:
 	lghi	zero,0		// zero = 0
-	la	%r1,0(%r2)	// put rp aside
-	lghi	%r2,0		// i=0;
+	la	%r1,0(%r2)	// put rp aside [to give way to]
+	lghi	%r2,0		// return value
 	ltgfr	%r4,%r4
 	bler	%r14		// if (len<=0) return 0;
 
-	stmg	%r6,%r10,48(%r15)
-	lghi	%r10,3
-	lghi	%r8,0		// carry = 0
-	nr	%r10,%r4	// len%4
+	stmg	%r6,%r13,48(%r15)
+	lghi	%r2,3
+	lghi	%r12,0		// carry = 0
+	slgr	%r1,%r3		// rp-=ap
+	nr	%r2,%r4		// len%4
 	sra	%r4,2		// cnt=len/4
 	jz	.Loop1_madd	// carry is incidentally cleared if branch taken
 	algr	zero,zero	// clear carry
 
-.Loop4_madd:
-	lg	%r7,0(%r2,%r3)	// ap[i]
+	lg	%r7,0(%r3)	// ap[0]
+	lg	%r9,8(%r3)	// ap[1]
 	mlgr	%r6,%r5		// *=w
-	alcgr	%r7,%r8		// +=carry
-	alcgr	%r6,zero
-	alg	%r7,0(%r2,%r1)	// +=rp[i]
-	stg	%r7,0(%r2,%r1)	// rp[i]=
+	brct	%r4,.Loop4_madd
+	j	.Loop4_madd_tail
 
-	lg	%r9,8(%r2,%r3)
+.Loop4_madd:
 	mlgr	%r8,%r5
+	lg	%r11,16(%r3)	// ap[i+2]
+	alcgr	%r7,%r12	// +=carry
+	alcgr	%r6,zero
+	alg	%r7,0(%r3,%r1)	// +=rp[i]
+	stg	%r7,0(%r3,%r1)	// rp[i]=
+
+	mlgr	%r10,%r5
+	lg	%r13,24(%r3)
 	alcgr	%r9,%r6
 	alcgr	%r8,zero
-	alg	%r9,8(%r2,%r1)
-	stg	%r9,8(%r2,%r1)
+	alg	%r9,8(%r3,%r1)
+	stg	%r9,8(%r3,%r1)
+
+	mlgr	%r12,%r5
+	lg	%r7,32(%r3)
+	alcgr	%r11,%r8
+	alcgr	%r10,zero
+	alg	%r11,16(%r3,%r1)
+	stg	%r11,16(%r3,%r1)
 
-	lg	%r7,16(%r2,%r3)
 	mlgr	%r6,%r5
-	alcgr	%r7,%r8
-	alcgr	%r6,zero
-	alg	%r7,16(%r2,%r1)
-	stg	%r7,16(%r2,%r1)
+	lg	%r9,40(%r3)
+	alcgr	%r13,%r10
+	alcgr	%r12,zero
+	alg	%r13,24(%r3,%r1)
+	stg	%r13,24(%r3,%r1)
 
-	lg	%r9,24(%r2,%r3)
-	mlgr	%r8,%r5
-	alcgr	%r9,%r6
-	alcgr	%r8,zero
-	alg	%r9,24(%r2,%r1)
-	stg	%r9,24(%r2,%r1)
-
-	la	%r2,32(%r2)	// i+=4
+	la	%r3,32(%r3)	// i+=4
 	brct	%r4,.Loop4_madd
 
-	la	%r10,1(%r10)		// see if len%4 is zero ...
-	brct	%r10,.Loop1_madd	// without touching condition code:-)
+.Loop4_madd_tail:
+	mlgr	%r8,%r5
+	lg	%r11,16(%r3)
+	alcgr	%r7,%r12	// +=carry
+	alcgr	%r6,zero
+	alg	%r7,0(%r3,%r1)	// +=rp[i]
+	stg	%r7,0(%r3,%r1)	// rp[i]=
+
+	mlgr	%r10,%r5
+	lg	%r13,24(%r3)
+	alcgr	%r9,%r6
+	alcgr	%r8,zero
+	alg	%r9,8(%r3,%r1)
+	stg	%r9,8(%r3,%r1)
+
+	mlgr	%r12,%r5
+	alcgr	%r11,%r8
+	alcgr	%r10,zero
+	alg	%r11,16(%r3,%r1)
+	stg	%r11,16(%r3,%r1)
+
+	alcgr	%r13,%r10
+	alcgr	%r12,zero
+	alg	%r13,24(%r3,%r1)
+	stg	%r13,24(%r3,%r1)
+
+	la	%r3,32(%r3)	// i+=4
+
+	la	%r2,1(%r2)	// see if len%4 is zero ...
+	brct	%r2,.Loop1_madd	// without touching condition code:-)
 
 .Lend_madd:
-	alcgr	%r8,zero	// collect carry bit
-	lgr	%r2,%r8
-	lmg	%r6,%r10,48(%r15)
+	lgr	%r2,zero	// return value
+	alcgr	%r2,%r12	// collect even carry bit
+	lmg	%r6,%r13,48(%r15)
 	br	%r14
 
 .Loop1_madd:
-	lg	%r7,0(%r2,%r3)	// ap[i]
+	lg	%r7,0(%r3)	// ap[i]
 	mlgr	%r6,%r5		// *=w
-	alcgr	%r7,%r8		// +=carry
+	alcgr	%r7,%r12	// +=carry
 	alcgr	%r6,zero
-	alg	%r7,0(%r2,%r1)	// +=rp[i]
-	stg	%r7,0(%r2,%r1)	// rp[i]=
+	alg	%r7,0(%r3,%r1)	// +=rp[i]
+	stg	%r7,0(%r3,%r1)	// rp[i]=
 
-	lgr	%r8,%r6
-	la	%r2,8(%r2)	// i++
-	brct	%r10,.Loop1_madd
+	lgr	%r12,%r6
+	la	%r3,8(%r3)	// i++
+	brct	%r2,.Loop1_madd
 
 	j	.Lend_madd
 .size	bn_mul_add_words,.-bn_mul_add_words

crypto/bn/asm/x86-gf2m.pl

@@ -14,7 +14,7 @@
 # the time being... Except that it has three code paths: pure integer
 # code suitable for any x86 CPU, MMX code suitable for PIII and later
 # and PCLMULQDQ suitable for Westmere and later. Improvement varies
-# from one benchmark and <EFBFBD>-arch to another. Below are interval values
+# from one benchmark and µ-arch to another. Below are interval values
 # for 163- and 571-bit ECDH benchmarks relative to compiler-generated
 # code:
 #
@@ -226,22 +226,22 @@ if ($sse2) {
 	&push	("edi");
 	&mov	($a,&wparam(1));
 	&mov	($b,&wparam(3));
-	&call	("_mul_1x1_mmx");	# a1<EFBFBD>b1
+	&call	("_mul_1x1_mmx");	# a1·b1
 	&movq	("mm7",$R);
 
 	&mov	($a,&wparam(2));
 	&mov	($b,&wparam(4));
-	&call	("_mul_1x1_mmx");	# a0<EFBFBD>b0
+	&call	("_mul_1x1_mmx");	# a0·b0
 	&movq	("mm6",$R);
 
 	&mov	($a,&wparam(1));
 	&mov	($b,&wparam(3));
 	&xor	($a,&wparam(2));
 	&xor	($b,&wparam(4));
-	&call	("_mul_1x1_mmx");	# (a0+a1)<EFBFBD>(b0+b1)
+	&call	("_mul_1x1_mmx");	# (a0+a1)·(b0+b1)
 	&pxor	($R,"mm7");
 	&mov	($a,&wparam(0));
-	&pxor	($R,"mm6");		# (a0+a1)<EFBFBD>(b0+b1)-a1<EFBFBD>b1-a0<EFBFBD>b0
+	&pxor	($R,"mm6");		# (a0+a1)·(b0+b1)-a1·b1-a0·b0
 
 	&movq	($A,$R);
 	&psllq	($R,32);
@@ -266,13 +266,13 @@ if ($sse2) {
 
 	&mov	($a,&wparam(1));
 	&mov	($b,&wparam(3));
-	&call	("_mul_1x1_ialu");	# a1<EFBFBD>b1
+	&call	("_mul_1x1_ialu");	# a1·b1
 	&mov	(&DWP(8,"esp"),$lo);
 	&mov	(&DWP(12,"esp"),$hi);
 
 	&mov	($a,&wparam(2));
 	&mov	($b,&wparam(4));
-	&call	("_mul_1x1_ialu");	# a0<EFBFBD>b0
+	&call	("_mul_1x1_ialu");	# a0·b0
 	&mov	(&DWP(0,"esp"),$lo);
 	&mov	(&DWP(4,"esp"),$hi);
 
@@ -280,7 +280,7 @@ if ($sse2) {
 	&mov	($b,&wparam(3));
 	&xor	($a,&wparam(2));
 	&xor	($b,&wparam(4));
-	&call	("_mul_1x1_ialu");	# (a0+a1)<EFBFBD>(b0+b1)
+	&call	("_mul_1x1_ialu");	# (a0+a1)·(b0+b1)
 
 	&mov	("ebp",&wparam(0));
 		 @r=("ebx","ecx","edi","esi");

crypto/bn/asm/x86-mont.pl

@@ -85,6 +85,21 @@ $frame=32;				# size of above frame rounded up to 16n
 
 	&and	("esp",-64);		# align to cache line
 
+	# Some OSes, *cough*-dows, insist on stack being "wired" to
+	# physical memory in strictly sequential manner, i.e. if stack
+	# allocation spans two pages, then reference to farmost one can
+	# be punishable by SEGV. But page walking can do good even on
+	# other OSes, because it guarantees that villain thread hits
+	# the guard page before it can make damage to innocent one...
+	&mov	("eax","ebp");
+	&sub	("eax","esp");
+	&and	("eax",-4096);
+&set_label("page_walk");
+	&mov	("edx",&DWP(0,"esp","eax"));
+	&sub	("eax",4096);
+	&data_byte(0x2e);
+	&jnc	(&label("page_walk"));
+
 	################################# load argument block...
 	&mov	("eax",&DWP(0*4,"esi"));# BN_ULONG *rp
 	&mov	("ebx",&DWP(1*4,"esi"));# const BN_ULONG *ap

crypto/bn/asm/x86_64-gcc.c

@@ -65,7 +65,7 @@
 # undef mul_add
 
 /*-
- * "m"(a), "+m"(r)      is the way to favor DirectPath <EFBFBD>-code;
+ * "m"(a), "+m"(r)      is the way to favor DirectPath µ-code;
  * "g"(0)               let the compiler to decide where does it
  *                      want to keep the value of zero;
  */

crypto/bn/asm/x86_64-gf2m.pl

@@ -13,7 +13,7 @@
 # in bn_gf2m.c. It's kind of low-hanging mechanical port from C for
 # the time being... Except that it has two code paths: code suitable
 # for any x86_64 CPU and PCLMULQDQ one suitable for Westmere and
-# later. Improvement varies from one benchmark and <EFBFBD>-arch to another.
+# later. Improvement varies from one benchmark and µ-arch to another.
 # Vanilla code path is at most 20% faster than compiler-generated code
 # [not very impressive], while PCLMULQDQ - whole 85%-160% better on
 # 163- and 571-bit ECDH benchmarks on Intel CPUs. Keep in mind that
@@ -184,13 +184,13 @@ ___
 $code.=<<___;
 	movdqa		%xmm0,%xmm4
 	movdqa		%xmm1,%xmm5
-	pclmulqdq	\$0,%xmm1,%xmm0	# a1<EFBFBD>b1
+	pclmulqdq	\$0,%xmm1,%xmm0	# a1·b1
 	pxor		%xmm2,%xmm4
 	pxor		%xmm3,%xmm5
-	pclmulqdq	\$0,%xmm3,%xmm2	# a0<EFBFBD>b0
-	pclmulqdq	\$0,%xmm5,%xmm4	# (a0+a1)<EFBFBD>(b0+b1)
+	pclmulqdq	\$0,%xmm3,%xmm2	# a0·b0
+	pclmulqdq	\$0,%xmm5,%xmm4	# (a0+a1)·(b0+b1)
 	xorps		%xmm0,%xmm4
-	xorps		%xmm2,%xmm4	# (a0+a1)<EFBFBD>(b0+b1)-a0<EFBFBD>b0-a1<EFBFBD>b1
+	xorps		%xmm2,%xmm4	# (a0+a1)·(b0+b1)-a0·b0-a1·b1
 	movdqa		%xmm4,%xmm5
 	pslldq		\$8,%xmm4
 	psrldq		\$8,%xmm5
@@ -225,13 +225,13 @@ $code.=<<___;
 	mov	\$0xf,$mask
 	mov	$a1,$a
 	mov	$b1,$b
-	call	_mul_1x1		# a1<EFBFBD>b1
+	call	_mul_1x1		# a1·b1
 	mov	$lo,16(%rsp)
 	mov	$hi,24(%rsp)
 
 	mov	48(%rsp),$a
 	mov	64(%rsp),$b
-	call	_mul_1x1		# a0<EFBFBD>b0
+	call	_mul_1x1		# a0·b0
 	mov	$lo,0(%rsp)
 	mov	$hi,8(%rsp)
 
@@ -239,7 +239,7 @@ $code.=<<___;
 	mov	56(%rsp),$b
 	xor	48(%rsp),$a
 	xor	64(%rsp),$b
-	call	_mul_1x1		# (a0+a1)<EFBFBD>(b0+b1)
+	call	_mul_1x1		# (a0+a1)·(b0+b1)
 ___
 	@r=("%rbx","%rcx","%rdi","%rsi");
 $code.=<<___;

crypto/bn/asm/x86_64-mont.pl

@@ -68,6 +68,11 @@ if (!$addx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
 	$addx = ($1>=12);
 }
 
+if (!$addx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9])\.([0-9]+)/) {
+	my $ver = $2 + $3/100.0;	# 3.1->3.01, 3.10->3.10
+	$addx = ($ver>=3.03);
+}
+
 # int bn_mul_mont(
 $rp="%rdi";	# BN_ULONG *rp,
 $ap="%rsi";	# const BN_ULONG *ap,
@@ -125,6 +130,20 @@ $code.=<<___;
 
 	mov	%r11,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul_body:
+	# Some OSes, *cough*-dows, insist on stack being "wired" to
+	# physical memory in strictly sequential manner, i.e. if stack
+	# allocation spans two pages, then reference to farmost one can
+	# be punishable by SEGV. But page walking can do good even on
+	# other OSes, because it guarantees that villain thread hits
+	# the guard page before it can make damage to innocent one...
+	sub	%rsp,%r11
+	and	\$-4096,%r11
+.Lmul_page_walk:
+	mov	(%rsp,%r11),%r10
+	sub	\$4096,%r11
+	.byte	0x66,0x2e		# predict non-taken
+	jnc	.Lmul_page_walk
+
 	mov	$bp,%r12		# reassign $bp
 ___
 		$bp="%r12";
@@ -337,6 +356,14 @@ $code.=<<___;
 
 	mov	%r11,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul4x_body:
+	sub	%rsp,%r11
+	and	\$-4096,%r11
+.Lmul4x_page_walk:
+	mov	(%rsp,%r11),%r10
+	sub	\$4096,%r11
+	.byte	0x2e			# predict non-taken
+	jnc	.Lmul4x_page_walk
+
 	mov	$rp,16(%rsp,$num,8)	# tp[num+2]=$rp
 	mov	%rdx,%r12		# reassign $bp
 ___
@@ -770,100 +797,135 @@ bn_sqr8x_mont:
 	# 4096. this is done to allow memory disambiguation logic
 	# do its job.
 	#
-	lea	-64(%rsp,$num,4),%r11
+	lea	-64(%rsp,$num,2),%r11
 	mov	($n0),$n0		# *n0
 	sub	$aptr,%r11
 	and	\$4095,%r11
 	cmp	%r11,%r10
 	jb	.Lsqr8x_sp_alt
 	sub	%r11,%rsp		# align with $aptr
-	lea	-64(%rsp,$num,4),%rsp	# alloca(frame+4*$num)
+	lea	-64(%rsp,$num,2),%rsp	# alloca(frame+2*$num)
 	jmp	.Lsqr8x_sp_done
 
 .align	32
 .Lsqr8x_sp_alt:
-	lea	4096-64(,$num,4),%r10	# 4096-frame-4*$num
-	lea	-64(%rsp,$num,4),%rsp	# alloca(frame+4*$num)
+	lea	4096-64(,$num,2),%r10	# 4096-frame-2*$num
+	lea	-64(%rsp,$num,2),%rsp	# alloca(frame+2*$num)
 	sub	%r10,%r11
 	mov	\$0,%r10
 	cmovc	%r10,%r11
 	sub	%r11,%rsp
 .Lsqr8x_sp_done:
 	and	\$-64,%rsp
-	mov	$num,%r10	
+	mov	%rax,%r11
+	sub	%rsp,%r11
+	and	\$-4096,%r11
+.Lsqr8x_page_walk:
+	mov	(%rsp,%r11),%r10
+	sub	\$4096,%r11
+	.byte	0x2e			# predict non-taken
+	jnc	.Lsqr8x_page_walk
+
+	mov	$num,%r10
 	neg	$num
 
-	lea	64(%rsp,$num,2),%r11	# copy of modulus
 	mov	$n0,  32(%rsp)
 	mov	%rax, 40(%rsp)		# save original %rsp
 .Lsqr8x_body:
 
-	mov	$num,$i
-	movq	%r11, %xmm2		# save pointer to modulus copy
-	shr	\$3+2,$i
-	mov	OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	.Lsqr8x_copy_n
-
-.align	32
-.Lsqr8x_copy_n:
-	movq	8*0($nptr),%xmm0
-	movq	8*1($nptr),%xmm1
-	movq	8*2($nptr),%xmm3
-	movq	8*3($nptr),%xmm4
-	lea	8*4($nptr),$nptr
-	movdqa	%xmm0,16*0(%r11)
-	movdqa	%xmm1,16*1(%r11)
-	movdqa	%xmm3,16*2(%r11)
-	movdqa	%xmm4,16*3(%r11)
-	lea	16*4(%r11),%r11
-	dec	$i
-	jnz	.Lsqr8x_copy_n
-
+	movq	$nptr, %xmm2		# save pointer to modulus
 	pxor	%xmm0,%xmm0
 	movq	$rptr,%xmm1		# save $rptr
 	movq	%r10, %xmm3		# -$num
 ___
 $code.=<<___ if ($addx);
+	mov	OPENSSL_ia32cap_P+8(%rip),%eax
 	and	\$0x80100,%eax
 	cmp	\$0x80100,%eax
 	jne	.Lsqr8x_nox
 
 	call	bn_sqrx8x_internal	# see x86_64-mont5 module
-
-	pxor	%xmm0,%xmm0
-	lea	48(%rsp),%rax
-	lea	64(%rsp,$num,2),%rdx
-	shr	\$3+2,$num
-	mov	40(%rsp),%rsi		# restore %rsp
-	jmp	.Lsqr8x_zero
+					# %rax	top-most carry
+					# %rbp	nptr
+					# %rcx	-8*num
+					# %r8	end of tp[2*num]
+	lea	(%r8,%rcx),%rbx
+	mov	%rcx,$num
+	mov	%rcx,%rdx
+	movq	%xmm1,$rptr
+	sar	\$3+2,%rcx		# %cf=0
+	jmp	.Lsqr8x_sub
 
 .align	32
 .Lsqr8x_nox:
 ___
 $code.=<<___;
 	call	bn_sqr8x_internal	# see x86_64-mont5 module
-
-	pxor	%xmm0,%xmm0
-	lea	48(%rsp),%rax
-	lea	64(%rsp,$num,2),%rdx
-	shr	\$3+2,$num
-	mov	40(%rsp),%rsi		# restore %rsp
-	jmp	.Lsqr8x_zero
+					# %rax	top-most carry
+					# %rbp	nptr
+					# %r8	-8*num
+					# %rdi	end of tp[2*num]
+	lea	(%rdi,$num),%rbx
+	mov	$num,%rcx
+	mov	$num,%rdx
+	movq	%xmm1,$rptr
+	sar	\$3+2,%rcx		# %cf=0
+	jmp	.Lsqr8x_sub
 
 .align	32
-.Lsqr8x_zero:
-	movdqa	%xmm0,16*0(%rax)	# wipe t
-	movdqa	%xmm0,16*1(%rax)
-	movdqa	%xmm0,16*2(%rax)
-	movdqa	%xmm0,16*3(%rax)
-	lea	16*4(%rax),%rax
-	movdqa	%xmm0,16*0(%rdx)	# wipe n
-	movdqa	%xmm0,16*1(%rdx)
-	movdqa	%xmm0,16*2(%rdx)
-	movdqa	%xmm0,16*3(%rdx)
-	lea	16*4(%rdx),%rdx
-	dec	$num
-	jnz	.Lsqr8x_zero
+.Lsqr8x_sub:
+	mov	8*0(%rbx),%r12
+	mov	8*1(%rbx),%r13
+	mov	8*2(%rbx),%r14
+	mov	8*3(%rbx),%r15
+	lea	8*4(%rbx),%rbx
+	sbb	8*0(%rbp),%r12
+	sbb	8*1(%rbp),%r13
+	sbb	8*2(%rbp),%r14
+	sbb	8*3(%rbp),%r15
+	lea	8*4(%rbp),%rbp
+	mov	%r12,8*0($rptr)
+	mov	%r13,8*1($rptr)
+	mov	%r14,8*2($rptr)
+	mov	%r15,8*3($rptr)
+	lea	8*4($rptr),$rptr
+	inc	%rcx			# preserves %cf
+	jnz	.Lsqr8x_sub
+
+	sbb	\$0,%rax		# top-most carry
+	lea	(%rbx,$num),%rbx	# rewind
+	lea	($rptr,$num),$rptr	# rewind
+
+	movq	%rax,%xmm1
+	pxor	%xmm0,%xmm0
+	pshufd	\$0,%xmm1,%xmm1
+	mov	40(%rsp),%rsi		# restore %rsp
+	jmp	.Lsqr8x_cond_copy
+
+.align	32
+.Lsqr8x_cond_copy:
+	movdqa	16*0(%rbx),%xmm2
+	movdqa	16*1(%rbx),%xmm3
+	lea	16*2(%rbx),%rbx
+	movdqu	16*0($rptr),%xmm4
+	movdqu	16*1($rptr),%xmm5
+	lea	16*2($rptr),$rptr
+	movdqa	%xmm0,-16*2(%rbx)	# zero tp
+	movdqa	%xmm0,-16*1(%rbx)
+	movdqa	%xmm0,-16*2(%rbx,%rdx)
+	movdqa	%xmm0,-16*1(%rbx,%rdx)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-16*2($rptr)
+	movdqu	%xmm5,-16*1($rptr)
+	add	\$32,$num
+	jnz	.Lsqr8x_cond_copy
 
 	mov	\$1,%rax
 	mov	-48(%rsi),%r15
@@ -901,8 +963,17 @@ bn_mulx4x_mont:
 	sub	$num,%r10		# -$num
 	mov	($n0),$n0		# *n0
 	lea	-72(%rsp,%r10),%rsp	# alloca(frame+$num+8)
-	lea	($bp,$num),%r10
 	and	\$-128,%rsp
+	mov	%rax,%r11
+	sub	%rsp,%r11
+	and	\$-4096,%r11
+.Lmulx4x_page_walk:
+	mov	(%rsp,%r11),%r10
+	sub	\$4096,%r11
+	.byte	0x66,0x2e		# predict non-taken
+	jnc	.Lmulx4x_page_walk
+
+	lea	($bp,$num),%r10
 	##############################################################
 	# Stack layout
 	# +0	num
@@ -1130,64 +1201,75 @@ $code.=<<___;
 	adc	$zero,%r15		# modulo-scheduled
 	sub	0*8($tptr),$zero	# pull top-most carry
 	adc	%r15,%r14
-	mov	-8($nptr),$mi
 	sbb	%r15,%r15		# top-most carry
 	mov	%r14,-1*8($tptr)
 
 	cmp	16(%rsp),$bptr
 	jne	.Lmulx4x_outer
 
-	sub	%r14,$mi		# compare top-most words
-	sbb	$mi,$mi
-	or	$mi,%r15
-
-	neg	$num
-	xor	%rdx,%rdx
-	mov	32(%rsp),$rptr		# restore rp
 	lea	64(%rsp),$tptr
-
-	pxor	%xmm0,%xmm0
-	mov	0*8($nptr,$num),%r8
-	mov	1*8($nptr,$num),%r9
-	neg	%r8
-	jmp	.Lmulx4x_sub_entry
+	sub	$num,$nptr		# rewind $nptr
+	neg	%r15
+	mov	$num,%rdx
+	shr	\$3+2,$num		# %cf=0
+	mov	32(%rsp),$rptr		# restore rp
+	jmp	.Lmulx4x_sub
 
 .align	32
 .Lmulx4x_sub:
-	mov	0*8($nptr,$num),%r8
-	mov	1*8($nptr,$num),%r9
-	not	%r8
-.Lmulx4x_sub_entry:
-	mov	2*8($nptr,$num),%r10
-	not	%r9
-	and	%r15,%r8
-	mov	3*8($nptr,$num),%r11
-	not	%r10
-	and	%r15,%r9
-	not	%r11
-	and	%r15,%r10
-	and	%r15,%r11
-
-	neg	%rdx			# mov %rdx,%cf
-	adc	0*8($tptr),%r8
-	adc	1*8($tptr),%r9
-	movdqa	%xmm0,($tptr)
-	adc	2*8($tptr),%r10
-	adc	3*8($tptr),%r11
-	movdqa	%xmm0,16($tptr)
-	lea	4*8($tptr),$tptr
-	sbb	%rdx,%rdx		# mov %cf,%rdx
-
-	mov	%r8,0*8($rptr)
-	mov	%r9,1*8($rptr)
-	mov	%r10,2*8($rptr)
-	mov	%r11,3*8($rptr)
-	lea	4*8($rptr),$rptr
-
-	add	\$32,$num
+	mov	8*0($tptr),%r11
+	mov	8*1($tptr),%r12
+	mov	8*2($tptr),%r13
+	mov	8*3($tptr),%r14
+	lea	8*4($tptr),$tptr
+	sbb	8*0($nptr),%r11
+	sbb	8*1($nptr),%r12
+	sbb	8*2($nptr),%r13
+	sbb	8*3($nptr),%r14
+	lea	8*4($nptr),$nptr
+	mov	%r11,8*0($rptr)
+	mov	%r12,8*1($rptr)
+	mov	%r13,8*2($rptr)
+	mov	%r14,8*3($rptr)
+	lea	8*4($rptr),$rptr
+	dec	$num			# preserves %cf
 	jnz	.Lmulx4x_sub
 
+	sbb	\$0,%r15		# top-most carry
+	lea	64(%rsp),$tptr
+	sub	%rdx,$rptr		# rewind
+
+	movq	%r15,%xmm1
+	pxor	%xmm0,%xmm0
+	pshufd	\$0,%xmm1,%xmm1
 	mov	40(%rsp),%rsi		# restore %rsp
+	jmp	.Lmulx4x_cond_copy
+
+.align	32
+.Lmulx4x_cond_copy:
+	movdqa	16*0($tptr),%xmm2
+	movdqa	16*1($tptr),%xmm3
+	lea	16*2($tptr),$tptr
+	movdqu	16*0($rptr),%xmm4
+	movdqu	16*1($rptr),%xmm5
+	lea	16*2($rptr),$rptr
+	movdqa	%xmm0,-16*2($tptr)	# zero tp
+	movdqa	%xmm0,-16*1($tptr)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-16*2($rptr)
+	movdqu	%xmm5,-16*1($rptr)
+	sub	\$32,%rdx
+	jnz	.Lmulx4x_cond_copy
+
+	mov	%rdx,($tptr)
+
 	mov	\$1,%rax
 	mov	-48(%rsi),%r15
 	mov	-40(%rsi),%r14