This patch optimizes SM4 for ARM processor using ASIMD instruction
It will improve performance if both of following conditions are met:
1) Input data equal to or more than 4 blocks
2) Cipher mode allows parallelism, including ECB,CTR,GCM or CBC decryption
This patch implements SM4 SBOX lookup in vector registers, with the
benefit of constant processing time over existing C implementation.
It is only enabled for micro-architecture N1/V1. In the ideal scenario,
performance can reach up to 2.7X
When either of above two conditions is not met, e.g. single block input
or CFB/OFB mode, CBC encryption, performance could drop about 50%.
The assembly code has been reviewed internally by ARM engineer
Fangming.Fang@arm.com
Signed-off-by: Daniel Hu <Daniel.Hu@arm.com>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17951)
CLI changes: New parameter -digest to CLI command openssl cms, to
provide pre-computed digest for use with -sign.
API changes: New function CMS_final_digest(), like CMS_final() but
uses a pre-computed digest instead of computing it from the data.
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: David von Oheimb <david.von.oheimb@siemens.com>
Reviewed-by: Todd Short <todd.short@me.com>
(Merged from https://github.com/openssl/openssl/pull/15348)
This refactors OSSL_LIB_CTX to avoid using CRYPTO_EX_DATA. The assorted
objects to be managed by OSSL_LIB_CTX are hardcoded and are initialized
eagerly rather than lazily, which avoids the need for locking on access
in most cases.
Fixes#17116.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17881)
Partial fix for #17064. Avoid excessive writes to the cache line
containing the refcount for an EVP_MD object to avoid extreme
cache contention when using a single EVP_MD at high frequency on
multiple threads. This changes performance in 3.0 from being double
that of 1.1 to only slightly higher than that of 1.1.
Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17857)
This header files are included by multiple other headers.
It's better to add define guards to prevent multi-inclusion.
Adhere to the coding style, all preprocessor directives inside
the guards gain a space.
Signed-off-by: Weiguo Li <liwg06@foxmail.com>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Matthias St. Pierre <Matthias.St.Pierre@ncp-e.com>
(Merged from https://github.com/openssl/openssl/pull/17666)
Fixes#13944
Moved "opt_printf_stderr" out of apps.c to avoid duplicate definition in tests.
Added function "asn1_string_to_time_t" including tests.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17645)
Add copyright to files that were missing it.
Update license from OpenSSL to Apache as needed.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17606)
The private key for rsa, dsa, dh and ecx was being included when the
selector was just the public key. (ec was working correctly).
This matches the documented behaviour.
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17200)
Increase the block numbers to 8 for every iteration. Increase the hash
table capacity. Make use of EOR3 instruction to improve the performance.
This can improve performance 25-40% on out-of-order microarchitectures
with a large number of fast execution units, such as Neoverse V1. We also
see 20-30% performance improvements on other architectures such as the M1.
Assembly code reviewd by Tom Cosgrove (ARM).
Reviewed-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15916)
Assembly code reviewed by Shricharan Srivatsan <ssrivat@us.ibm.com>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16854)
This patch implements the SM4 optimization for ARM processor,
using SM4 HW instruction, which is an optional feature of
crypto extension for aarch64 V8.
Tested on some modern ARM micro-architectures with SM4 support, the
performance uplift can be observed around 8X~40X over existing
C implementation in openssl. Algorithms that can be parallelized
(like CTR, ECB, CBC decryption) are on higher end, with algorithm
like CBC encryption on lower end (due to inter-block dependency)
Perf data on Yitian-710 2.75GHz hardware, before and after optimization:
Before:
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
SM4-CTR 105787.80k 107837.87k 108380.84k 108462.08k 108549.46k 108554.92k
SM4-ECB 111924.58k 118173.76k 119776.00k 120093.70k 120264.02k 120274.94k
SM4-CBC 106428.09k 109190.98k 109674.33k 109774.51k 109827.41k 109827.41k
After (7.4x - 36.6x faster):
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
SM4-CTR 781979.02k 2432994.28k 3437753.86k 3834177.88k 3963715.58k 3974556.33k
SM4-ECB 937590.69k 2941689.02k 3945751.81k 4328655.87k 4459181.40k 4468692.31k
SM4-CBC 890639.88k 1027746.58k 1050621.78k 1056696.66k 1058613.93k 1058701.31k
Signed-off-by: Daniel Hu <Daniel.Hu@arm.com>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/17455)
This fixes "undefined reference to `aes_gcm_dec_128_kernel' in function
`armv8_aes_gcm_decrypt'" and similar
Fixes#16949
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16951)
In all initializing functions for functionality that use an EVP_PKEY, the
coded logic was to find an KEYMGMT implementation first, and then try to
find the operation method (for example, SIGNATURE implementation) in the
same provider.
This implies that in providers where there is a KEYMGMT implementation,
there must also be a SIGNATURE implementation, along with a KEYEXCH,
ASYM_CIPHER, etc implementation.
The intended design was, however, the opposite implication, i.e. that
where there is a SIGNATURE implementation, there must also be KEYMGMT.
This change reverses the logic of the code to be closer to the intended
design.
There is a consequence; we now use the query_operation_name function from
the KEYMGMT of the EVP_PKEY given by the EVP_PKEY_CTX (ultimately given by
the application). Previously, we used the query_operation_name function
from the KEYMGMT found alongside the SIGNATURE implementation.
Another minor consequence is that the |keymgmt| field in EVP_PKEY_CTX
is now always a reference to the KEYMGMT of the |pkey| field if that
one is given (|pkey| isn't NULL) and is provided (|pkey->keymgmt|
isn't NULL).
Fixes#16614
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16725)
A header file was missing but only in no-deprecated builds.
Also add some ending comments for #if preprocessor statements.
Move function declaration inside #ifdef guard for header.
Reviewed-by: Tim Hudson <tjh@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16412)
Previously the length of the SM2 plaintext could be incorrectly calculated.
The plaintext length was calculated by taking the ciphertext length and
taking off an "overhead" value.
The overhead value was assumed to have a "fixed" element of 10 bytes.
This is incorrect since in some circumstances it can be more than 10 bytes.
Additionally the overhead included the length of two integers C1x and C1y,
which were assumed to be the same length as the field size (32 bytes for
the SM2 curve). However in some cases these integers can have an additional
padding byte when the msb is set, to disambiguate them from negative
integers. Additionally the integers can also be less than 32 bytes in
length in some cases.
If the calculated overhead is incorrect and larger than the actual value
this can result in the calculated plaintext length being too small.
Applications are likely to allocate buffer sizes based on this and therefore
a buffer overrun can occur.
CVE-2021-3711
Issue reported by John Ouyang.
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
ASN.1 strings may not be NUL terminated. Don't assume they are.
CVE-2021-3712
Reviewed-by: Viktor Dukhovni <viktor@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: David Benjamin <davidben@google.com>
Calls to the API function EVP_default_properties_enable_fips() will
automatically attempt to load the default config file if it is not
already loaded. Therefore this function should not be called from inside
code to process the config file.
Fixes#16165
Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16168)
It is possible to have a custom EVP_PKEY_METHOD implementation without
having an engine. In those cases we were failing to use that custom
implementation.
Fixes#16088
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Nicola Tuveri <nic.tuv@gmail.com>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16118)
Fixes#16010
Signed-off-by: Randall S. Becker <rsbecker@nexbridge.com>
Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Ben Kaduk <kaduk@mit.edu>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/16011)
Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15974)
If there are keymgmts and en/decoders from the same provider, try to
combine them first.
This avoids unnecessary export/import dances, and also tries to avoid
issues where the keymgmt doesn't fully support exporting and importing,
which we can assume will be the case for HSM protected keys.
Fixes#15932
Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15933)
This is refactored to use inner_ossl_decoder_fetch() without any given
name, which is just there to ensure all decoder implementations are
made into methods, and then use ossl_method_store_do_all() to list
them all.
This also adds the internal ossl_decoder_do_all_prefetched(), which
can be used if pre-fetching needs to be done separately from listing
all the decoder implementations, or if listing may happen multiple
times.
Fixes#15538Fixes#14837
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15604)
Previously all the SubjectPublicKeyInfo decoders were specific to a key
type. We would iterate over all them until a match was found for the correct
key type. Each one would fully decode the key before then testing whether
it was a match or not - throwing it away if not. This was very inefficient.
Instead we introduce a generic SubjectPublicKeyInfo decoder which figures
out what type of key is contained within it, before subsequently passing on
the data to a key type specific SubjectPublicKeyInfo decoder.
Fixes#15646
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15662)
Fixes#5430
Added the configuration file option "date_opt" to the openssl applications ca,
crl and x509.
Added ASN1_TIME_print_ex which supports the new datetime format using the
flag ASN1_DTFLGS_ISO8601
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/14384)
The function pem_read_bio_key_legacy() is a fallback route if we
failed to load a key via a provider. We should be using the legacy
specific d2i functions to force legacy otherwise we end up using a
provider anyway
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15504)
Unfortunately in terms of fips.sources this does not mean much
given the way how the .h files are added via the dependency
information from the compiler.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15622)
For functions that exist in 1.1.1 provide a simple aliases via #define.
Fixes#15236
Functions with OSSL_DECODER_, OSSL_ENCODER_, OSSL_STORE_LOADER_,
EVP_KEYEXCH_, EVP_KEM_, EVP_ASYM_CIPHER_, EVP_SIGNATURE_,
EVP_KEYMGMT_, EVP_RAND_, EVP_MAC_, EVP_KDF_, EVP_PKEY_,
EVP_MD_, and EVP_CIPHER_ prefixes are renamed.
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15405)
Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/14587)
Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/15535)
