Fix coverity issues in EC after #11807

This should fix 2 issues detected by Coverity and introduced with
https://github.com/openssl/openssl/pull/11807

- CID 1463577:  Memory - corruptions  (ARRAY_VS_SINGLETON)
- CID 1463573:  Memory - corruptions  (ARRAY_VS_SINGLETON)

In practice the tests seem to show that they both aren't real issues,
yet I believe this small change should appease the scanner and at the
same time improve clarity for the reader.

Here is the original report:

```
** CID 1463577:  Memory - corruptions  (ARRAY_VS_SINGLETON)

________________________________________________________________________________________________________
*** CID 1463577:  Memory - corruptions  (ARRAY_VS_SINGLETON)
/crypto/ec/ec_lib.c: 1123 in EC_POINT_mul()
1117
1118         if (group->meth->mul != NULL)
1119             ret = group->meth->mul(group, r, g_scalar, point != NULL
1120                                    && p_scalar != NULL, &point, &p_scalar, ctx);
1121         else
1122             /* use default */
   CID 1463577:  Memory - corruptions  (ARRAY_VS_SINGLETON)
   Passing "&point" to function "ec_wNAF_mul" which uses it as an array. This might corrupt or misinterpret adjacent memory locations.
1123             ret = ec_wNAF_mul(group, r, g_scalar, point != NULL
1124                               && p_scalar != NULL, &point, &p_scalar, ctx);
1125
1126     #ifndef FIPS_MODULE
1127         BN_CTX_free(new_ctx);
1128     #endif

** CID 1463573:  Memory - corruptions  (ARRAY_VS_SINGLETON)

________________________________________________________________________________________________________
*** CID 1463573:  Memory - corruptions  (ARRAY_VS_SINGLETON)
/crypto/ec/ec_lib.c: 1123 in EC_POINT_mul()
1117
1118         if (group->meth->mul != NULL)
1119             ret = group->meth->mul(group, r, g_scalar, point != NULL
1120                                    && p_scalar != NULL, &point, &p_scalar, ctx);
1121         else
1122             /* use default */
   CID 1463573:  Memory - corruptions  (ARRAY_VS_SINGLETON)
   Passing "&p_scalar" to function "ec_wNAF_mul" which uses it as an array. This might corrupt or misinterpret adjacent memory locations.
1123             ret = ec_wNAF_mul(group, r, g_scalar, point != NULL
1124                               && p_scalar != NULL, &point, &p_scalar, ctx);
1125
1126     #ifndef FIPS_MODULE
1127         BN_CTX_free(new_ctx);
1128     #endif
```

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
Reviewed-by: Paul Dale <paul.dale@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11919)

Move decl of OSSL_CRMF_CERTID_dup from {crmf,cmp}_local.h to include/openssl/crmf.h

fixes #11818

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11911)

Re-introduce legacy EVP_PKEY types for provided keys

EVP_PKEYs with provider side internal keys got the key type
EVP_PKEY_NONE.  This turned out to be too disruptive, so we try
instead to find a matching EVP_PKEY_ASN1_METHOD and use whatever
EVP_PKEY type it uses.

To make internal coding easier, we introduce a few internal macros to
distinguish what can be expected from a EVP_PKEY:

- evp_pkey_is_blank(), to detect an unassigned EVP_PKEY.
- evp_pkey_is_typed(), to detect that an EVP_PKEY has been assigned a
  type, which may be an old style type number or a EVP_KEYMGMT method.
- evp_pkey_is_assigned(), to detect that an EVP_PKEY has been assigned
  an key value.
- evp_pkey_is_legacy(), to detect that the internal EVP_PKEY key is a
  legacy one, i.e. will be handled via an EVP_PKEY_ASN1_METHOD and an
  EVP_PKEY_METHOD.
- evp_pkey_is_provided(), to detect that the internal EVP_PKEY key is
  a provider side one, i.e. will be handdled via an EVP_KEYMGMT and
  other provider methods.

This also introduces EVP_PKEY_KEYMGMT, to indicate that this EVP_PKEY
contains a provider side key for which there are no known
EVP_PKEY_ASN1_METHODs or EVP_PKEY_METHODs, i.e. these can only be
handled via EVP_KEYMGMT and other provider methods.

Fixes #11823

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11913)

GOST external tests

[extended tests]

Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11792)

Fix the parameter types of the CRYPTO_EX_dup function type.

This fixes a strict aliasing issue in ui_dup_method_data.

The parameter type of CRYPTO_EX_dup's from_d parameter
is in fact void **, since it points to a pointer.

This function is rarely used, therefore fix the param type
although that may be considered an API breaking change.

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/2986)

Adjust length of some strncpy() calls

This fixes warnings detected by -Wstringop-truncation.

Reviewed-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
(Merged from https://github.com/openssl/openssl/pull/11878)

Prevent use after free of global_engine_lock

If buggy application calls engine functions after cleanup of engines
already happened the global_engine_lock will be used although
already freed.

See for example:
https://bugzilla.redhat.com/show_bug.cgi?id=1831086

Reviewed-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
(Merged from https://github.com/openssl/openssl/pull/11896)

Coverity 1463571: Null pointer dereferences (FORWARD_NULL)

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
(Merged from https://github.com/openssl/openssl/pull/11892)

Coverity 1463574: Null pointer dereferences (REVERSE_INULL)

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
(Merged from https://github.com/openssl/openssl/pull/11892)

Coverity 1463576: Error handling issues (CHECKED_RETURN)

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
(Merged from https://github.com/openssl/openssl/pull/11892)

Coverity 1463258: Incorrect expression (EVALUATION_ORDER)

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
(Merged from https://github.com/openssl/openssl/pull/11892)

There is no -signreq option in CA.pl

CLA: trivial

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11876)

STORE: Make try_decode_PrivateKey() ENGINE aware

This function only considered the built-in and application
EVP_PKEY_ASN1_METHODs, and is now amended with a loop that goes
through all loaded engines, using whatever table of methods they each
have.

Fixes #11861

Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11872)

rsa_padding_add_PKCS1_OAEP_mgf1_with_libctx(): fix check of |md|

In the FIPS module, the code as written generate an unconditional
error.

Fixes #11865

Reviewed-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <paul.dale@oracle.com>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11869)

Refactor the provider side DER constants and writers

This splits up all the providers/common/der/*.c.in so the generated
portion is on its own and all related DER writing routines are in
their own files.  This also ensures that the DIGEST consstants aren't
reproduced in several files (resulting in symbol clashes).

Finally, the production of OID macros is moved to the generated header
files, allowing other similar macros, or DER constant arrays, to be
built on top of them.

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11868)

deprecate EC_POINT_make_affine and EC_POINTs_make_affine

Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11874)

t1_trce: Fix remaining places where the 24 bit shift overflow happens

[extended tests]

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11857)

Avoid potential overflow to the sign bit when shifting left 24 places

Although there are platforms where int is 64 bit, 2GiB large BIGNUMs
instead of 4GiB should be "big enough for everybody".

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11857)

Cast the unsigned char to unsigned int before shifting left

This is needed to avoid automatic promotion to signed int.

Fixes #11853

[extended tests]

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11857)

Fix egd and devrandom source configs

./config --with-rand-seed=egd

need to defines OPENSSL_RAND_SEED_EGD and OPENSSL_NO_EGD
so get rid of OPENSSL_NO_EGD (compiles but I did not really test EGD)

./config --with-rand-seed=devrandom

does not work since wait_random_seeded works under the assumption
that OPENSSL_RAND_SEED_GETRANDOM is supposed to be enabled as well,
that is usually the case, but not when only devrandom is enabled.
Skip the wait code in this special case.

Reviewed-by: Paul Dale <paul.dale@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11848)

Add OSSL_PROVIDER_do_all()

This allows applications to iterate over all loaded providers.

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11858)

Update early data exchange scenarios in doc

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11816)

Update limitation of psk_client_cb and psk_server_cb in usage with TLSv1.3

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11816)

Test for the SSL_OP_IGNORE_UNEXPECTED_EOF option

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11735)

Introducing option SSL_OP_IGNORE_UNEXPECTED_EOF

Partially fixes #11209.

Before OpenSSL 3.0 in case when peer does not send close_notify,
the behaviour was to set SSL_ERROR_SYSCALL error with errno 0.
This behaviour has changed. The SSL_OP_IGNORE_UNEXPECTED_EOF restores
the old behaviour for compatibility's sake.

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11735)

Use {module,install}-mac, not -checksum

As the documentation points out, these fipsmodule.cnf fields are a MAC,
not a digest or checksum.  Rename them to be correct.

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11369)

Revise fips_install.pod

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11369)

Revise x509v3_config.pod

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11369)

Revise fips_config.pod

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11369)

Add missing pragma weak declaration to lhash.h

The missing symbol caused a linker failure on solaris x86_64.

Fixes #11796

Reviewed-by: Matthias St. Pierre <Matthias.St.Pierre@ncp-e.com>
Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11798)

deprecate EC precomputation functionality

Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
(Merged from https://github.com/openssl/openssl/pull/11851)

New Russian TLS 1.2 implementation

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11442)

GOST-related objects changes

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11442)

Constants for new GOST TLS 1.2 ciphersuites

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11442)

CORE: query for operations only once per provider (unless no_store is true)

When a desired algorithm wasn't available, we didn't register anywhere
that an attempt had been made, with the result that next time the same
attempt was made, the whole process would be done again.

To avoid this churn, we register a bit for each operation that has
been queried in the libcrypto provider object, and test it before
trying the same query and method construction loop again.

If course, if the provider has told us not to cache, we don't register
this bit.

Fixes #11814

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11842)

Use _get0_ functions instead of _get_.

Fix build error on some platforms

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
(Merged from https://github.com/openssl/openssl/pull/10757)

s_client: Show cert algorithms & validity period

Add certificate validity period (v) and public key & signature algorithms (a) to the "Certificate Chain" output.

Eg:
Certificate chain
 0 s:C = US, ST = California, L = Mountain View, O = Google LLC, CN = www.google.com
   i:C = US, O = Google Trust Services, CN = GTS CA 1O1
   a:PKEY: id-ecPublicKey, 256 (bit); sigalg: RSA-SHA256
   v:NotBefore: Dec  3 14:49:26 2019 GMT; NotAfter: Feb 25 14:49:26 2020 GMT
 1 s:C = US, O = Google Trust Services, CN = GTS CA 1O1
   i:OU = GlobalSign Root CA - R2, O = GlobalSign, CN = GlobalSign
   a:PKEY: rsaEncryption, 2048 (bit); sigalg: RSA-SHA256
   v:NotBefore: Jun 15 00:00:42 2017 GMT; NotAfter: Dec 15 00:00:42 2021 GMT

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
(Merged from https://github.com/openssl/openssl/pull/10757)

Fix some places where X509_up_ref is used
without error handling.

This takes up the ball from #11278
without trying to solve everything at once.

[extended tests]

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
(Merged from https://github.com/openssl/openssl/pull/11850)

TTY_get() in crypto/ui/ui_openssl.c open_console() can also return errno 1 (EPERM, Linux)

Signed-off-by: Maxim Zakharov <5158255+Maxime2@users.noreply.github.com>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11767)

Delete the sslprovider test

This was added before the changes to the sslap/ssl_new/ssl_old tests which
run those tests with a non-default library context. It no longer adds
anything that those tests don't already do, so it can be deleted.

This also fixes a number of run-checker build failures which were failing
in this test if TLSv1.2 was disabled.

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11832)

Fix small documentation issues

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11835)

deprecate EC_POINTs_mul function

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11807)

Update documentation following changes of various types

The previous commit changed the types of various objects passed between
the core and providers. Therefore the documentation needs to be updated
to reflect that.

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11758)

Maintain strict type discipline between the core and providers

A provider could be linked against a different version of libcrypto than
the version of libcrypto that loaded the provider. Different versions of
libcrypto could define opaque types differently. It must never occur that
a type created in one libcrypto is used directly by the other libcrypto.
This will cause crashes.

We can "cheat" for "built-in" providers that are part of libcrypto itself,
because we know that the two libcrypto versions are the same - but not for
other providers.

To ensure this does not occur we use different types names for the handful
of opaque types that are passed between the core and providers.

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11758)

CORE: Fix a couple of bugs in algorithm_do_this()

The call of ossl_provider_query_operation() used |data->operation_id|,
when |cur_operation| should be used.

If any ossl_provider_query_operation() call returned NULL, the loop
was stopped, when it should just continue on to the next operation.

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11837)

Test TLSv1.3 out-of-band PSK with all 5 ciphersuites

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11785)

Fix crash in early data send with out-of-band PSK using AES CCM

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11785)

Fix all MD036 (emphasis used instead of heading)

The main fixes were errors in itemized lists "*)" instead of "*"

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matthias St. Pierre <Matthias.St.Pierre@ncp-e.com>
(Merged from https://github.com/openssl/openssl/pull/11770)

Add "md-nits" make target

Also fix a nit in recent CHANGES.md update.

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
Reviewed-by: Matthias St. Pierre <Matthias.St.Pierre@ncp-e.com>
(Merged from https://github.com/openssl/openssl/pull/11770)

Add 'methods' parameter to setup_engine() in apps.c for individual method defaults

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/4277)

Clean up macro definitions of openssl_fdset() in apps.h and sockets.h

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/4277)

Use OSSL_STORE for load_{,pub}key() and load_cert() in apps/lib/apps.c

This also adds the more flexible and general load_key_cert_crl()
as well as helper functions get_passwd(), cleanse(), and clear_free()
to be used also in apps/cmp.c etc.

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11755)

Nit-fix: remove whitespace in doc/man3/EVP_PKEY_fromdata.pod causing warning

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11755)

Guard use of struct tms with #ifdef __TMS like done earlier in apps/lib/apps.c

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11755)

Build: make apps/progs.c depend on configdata.pm

Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11824)

SSL: refactor ssl_cert_lookup_by_pkey() to work with provider side keys

Fixes #11720

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11828)

Ignore some auto-generated DER files

Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11830)

Prepare for 3.0 alpha 3

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

Prepare for release of 3.0 alpha 2

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

Update copyright year

Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11839)

If SOURCE_DATE_EPOCH is defined, use it for copyright year

Using the date from SOURCE_DATE_EPOCH instead of the current date makes
it possible to reproduce a build that was built on a different year:
https://reproducible-builds.org/specs/source-date-epoch/

This is fixing an issue we had while building Tor Browser:
https://trac.torproject.org/projects/tor/ticket/33535

CLA: trivial

Reviewed-by: Paul Dale <paul.dale@oracle.com>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11296)

Correct alignment calculation in ssl3_setup_write

The alignment calculation in ssl3_setup_write incorrectly results in an
alignment allowance of
(-SSL3_RT_HEADER_LENGTH) & (SSL3_ALIGN_PAYLOAD - 1) bytes. This equals 3
in almost all cases. The maximum alignment actually used in do_ssl3_write
is (SSL3_ALIGN_PAYLOAD - 1). This equals 7 bytes in almost all cases. So
there is a potential to overrun the buffer by up to 4 bytes.

Fortunately, the encryption overhead allowed for is 80 bytes which
consists of 16 bytes for the cipher block size and 64 bytes for the MAC
output. However the biggest MAC that we ever produce is HMAC-384 which is
48 bytes - so we have a headroom of 16 bytes (i.e. more than the 4 bytes
of potential overrun).

Thanks to Nagesh Hegde for reporting this.

Fixes #11766

Reviewed-by: Ben Kaduk <kaduk@mit.edu>
(Merged from https://github.com/openssl/openssl/pull/11768)

Configure: Avoid SIXTY_FOUR_BIT for linux-mips64

This is a 32-bit ABI build (as opposed to linux64-mips64).
Setting SIXTY_FOUR_BIT breaks hardware optimizations, at least on
octeon processors.

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11725)

dev/release.sh: Add --reviewer to set reviewers

Doing this is kind of contrary to how we normally do things, as this
constitutes a kind of pre-approval.  However, without this, the normal
review process will modify the reviewed commits, and render the
annotated release tag invalid, which forces the person doing the
release to re-tag manually.

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11630)

Pass "-z defs" to the linker via "-Wl,-z,defs" rather than with gcc's -z
flag (which is not supported by older compilers).

CLA: trivial

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11815)

test/evp_extra_test.c: Add OPENSSL_NO_CMAC around CMAC test

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Tomas Mraz <tmraz@fedoraproject.org>
(Merged from https://github.com/openssl/openssl/pull/11833)

PROV: make some DER AID arrays non-static, to avoid clang complaints

The problem encountered is that some arrays were deemed unnecessary by
clang, for example:

    providers/common/der/der_rsa.c:424:28: error: variable 'der_aid_sha224Identifier' is not needed and will not be emitted [-Werror,-Wunneeded-internal-declaration]
    static const unsigned char der_aid_sha224Identifier[] = {
                               ^

However, these arrays are used in sizeof() expressions in other parts
of the code that's actually used, making that warning-turned-error a
practical problem.  We solve this by making the array non-static,
which guarantees that the arrays will be emitted, even though
unnecessarily.  Fortunately, they are very small.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

.travis.yml: never use -Werror, use --strict-warnings instead

There are a few things in the OpenSSL code that are known to give
warnings that we know are harmless.  We test our builds accordingly.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

test/recipes/15-test_rsapss.t: Add test with unrestricted signature

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

test/ssl-tests/20-cert-select.cnf.in: Re-enable RSA-PSS related tests

There were a few RSA-PSS related tests that were disabled for non-default
library contexts.  We now re-enable them.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

test/evp_pkey_provided_test.c: Display first, compare after

To make it easier to check the generated key manually, display it
before comparing diverse other serializations.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV & ASYM_CIPHER: Adapt the RSA asymmetric cipher code for PSS-parameters

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

EVP: Refactor the RSA-PSS key generation controls for providers

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV & SIGNATURE: Adapt the RSA signature code for PSS-parameters

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

EVP: For SIGNATURE operations, pass the propquery early

Instead of passing it with signature->digest_verify_init() and
signature->digest_sign_init(), we pass it with signature->newctx().
This allows the digests that are indicated by RSA PSS parameters
to have a useful propquery.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV & SERIALIZER: Adapt the RSA serializers for PSS-parameters

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV & KEYMGMT: Add PSS-parameter support in the RSA KEYMGMT implementation

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV: Refactor the RSA SIGNATURE implementation for better param control

We want to catch errors in passed parameters early, which requires
kowledge of the ongoing operation.  Fortunately, that's possible by
re-using the EVP_PKEY_OP macros in specific init functions.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

PROV: Refactor the RSA DER support

We separate out the NIST arc OIDs to a separate file, so it can be
re-used, and also the DIGEST OIDs.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

DER writer: Add the possibility to abandon empty SEQUENCEs

In some cases, a SEQUENCE that contains only optional fields may end
up empty.  In some cases, this may be represented by dropping the
SEQUENCE entirely from the encoded DER.

To do this, we detect the case where WPACKET_FLAGS_ABANDON_ON_ZERO_LENGTH
is used, and adapt accordingly.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

RSA: Add PSS-parameter processing in EVP_PKEY_ASN1_METHOD functions

The import and export functions are affected.  We also refactor them
to assign the RSA key type more carefully.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

RSA: Add a less loaded PSS-parameter structure

RSA_PSS_PARAMS carries with it a lot of baggage in form of X509_ALGOR
and ASN1_INTEGER, which we would rather avoid in our providers.
Therefore, we create a parallell structure - RSA_PSS_PARAMS_30 - that
contains the same information, but uses numeric identities (*) and C
integers (**).  This makes it simpler to handle.

Note that neither this structure nor its contents are passed between
libcrypto and the providers.  Instead, the numeric identities are
translated to and from names, which are then passed over that
boundary.

For future considerations, we might consider dropping RSA_PSS_PARAMS
entirely.  For now, it's still reserved for EVP_PKEY_ASN1_METHOD code,
which RSA_PSS_PARAMS_30 is (almost entirely) reserved for use in our
providers.

(*) We use NIDs in this case, because we already have them and because
only algorithms that libcrypto knows about are permitted in PSS
restrictions.  We could use any number series we want, as long as we
know for sure what they represent.

(**) That's for saltlen and for trailerfield, which are never expect
to surpass the set of numbers that fit in a regular 'int'.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

RSA: Add rsa_schemes.c, to store scheme data and translator functions

The scheme currently added is OAEP-PSSDigestAlgorithms codified.
The translator functions translate an EVP_MD into a NID, and a NID
into a name, to support the creation and parsing of OSSL_PARAM items.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

RSA: Extract much of the rsa_pkey_export_to() code to a separate function

The resulting function, rsa_todata(), is designed to be usable by
providers as well.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

RSA: Add RSA key types

The support of restricted RSA key types (OAEP and PSS) was lacking, or
dependent on the presence of restriction parameters.  For example,
this means that even though an RSA-PSS key may have been generated, it
may appear as a plain unrestricted RSA key if parameters weren't
present (which is the case when default restriction parameters are
used)

To make it clearer what an RSA key is intended for, and avoid
depending in an EVP_PKEY, we introduce RSA key types.  This is done by
reserving a section of the RSA flags (4 bits, which allows a total of
16 different types).

This isn't terribly important for EVP_PKEY_ASN1_METHOD code, as that
has access to the wrapping EVP_PKEY.  This is very important for
provider code, which has no access to the wrapping EVP_PKEY.

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11710)

test/evp_extra_test.c: Add test for CMAC keygen with a NULL engine

Verifies that #11671 is fixed

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11674)

EVP: Only use the engine when one is defined, in pkey_mac_ctrl()

Fixes #11671

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/11674)

Add documentation for ASN1_INTEGER_new() and ASN1_INTEGER_free()

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
Reviewed-by: Dmitry Belyavskiy <beldmit@gmail.com>
(Merged from https://github.com/openssl/openssl/pull/11795)

Rename OSSL_CMP_CTX_set1_clCert() to OSSL_CMP_CTX_set1_cert()

Also update documentation and example code in openssl-cmp.pod.in

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Add -reqin_new_tid option to apps/cmp.c and OSSL_CMP_MSG_update_transactionID()

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Improve CMP documentation regarding use of untrusted certs

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Chunk 11 of CMP contribution to OpenSSL: CMP command-line interface

Certificate Management Protocol (CMP, RFC 4210) extension to OpenSSL
Also includes CRMF (RFC 4211) and HTTP transfer (RFC 6712).
Adds the CMP and CRMF API to libcrypto and the "cmp" app to the CLI.
Adds extensive documentation and tests.

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Preliminary fix of memory leak in try_decode_PKCS12() - full fix is in #11733

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Improve description of algorithm NIDs in doc/man3/OSSL_CMP_CTX_new.pod

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

Reflect constifications of 62dcd2aa in doc/man3/OSSL_CRMF_MSG_get0_tmpl.pod

Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11470)

OSSL_STORE: Make the 'file' scheme loader handle MSBLOB and PVK files

This involves exposing two pvkfmt.c functions, but only internally.

Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11756)

OSSL_STORE: Better information when prompting for pass phrases

The prompt includes the URI, to make it clear which object needs a
pass phrase.

Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11756)

OSSL_STORE: Make it possible to attach an OSSL_STORE to an opened BIO

This capability existed internally, and is now made public.

Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
(Merged from https://github.com/openssl/openssl/pull/11756)

PROV: Adapt all our providers to use the new PROV_CTX structure

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11803)

PROV: Add a proper provider context structure for OpenSSL providers

The provider context structure is made to include the following information:

- The core provider handle (first argument to the provider init
  function).  This handle is meant to be used in all upcalls that need
  it.

- A library context, used for any libcrypto calls that need it, done in
  the provider itself.

Regarding the library context, that's generally only needed if the
provider makes any libcrypto calls, i.e. is linked with libcrypto.  That
happens to be the case for all OpenSSL providers, but is applicable for
other providers that use libcrypto internally as well.

The normal thing to do for a provider init function is to create its own
library context.  For a provider that's meant to become a dynamically
loadable module, this is what MUST be done.
However, we do not do that in the default provider; it uses the library
context associated with the core provider handle instead.  This is
permissible, although generally discouraged, as long as the provider in
question is guaranteed to be built-in, into libcrypto or into the
application that uses it.

Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/11803)