Unlike many other structure types defined in the crypto API, the
'shash_desc' structure is permitted to live on the stack, which
implies its contents may not be accessed by DMA masters. (This is
due to the fact that the stack may be located in the vmalloc area,
which requires a different virtual-to-physical translation than the
one implemented by the DMA subsystem)
Our definition of CRYPTO_MINALIGN_ATTR is based on ARCH_KMALLOC_MINALIGN,
which may take DMA constraints into account on architectures that support
non-cache coherent DMA such as ARM and arm64. In this case, the value is
chosen to reflect the largest cacheline size in the system, in order to
ensure that explicit cache maintenance as required by non-coherent DMA
masters does not affect adjacent, unrelated slab allocations. On arm64,
this value is currently set at 128 bytes.
This means that applying CRYPTO_MINALIGN_ATTR to struct shash_desc is both
unnecessary (as it is never used for DMA), and undesirable, given that it
wastes stack space (on arm64, performing the alignment costs 112 bytes in
the worst case, and the hole between the 'tfm' and '__ctx' members takes
up another 120 bytes, resulting in an increased stack footprint of up to
232 bytes.) So instead, let's switch to the minimum SLAB alignment, which
does not take DMA constraints into account.
Note that this is a no-op for x86.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add the following additional dependencies for CRYPTO_DEV_KEEMBAY_OCS_HCU:
- HAS_IOMEM to prevent build failures
- ARCH_KEEMBAY to prevent asking the user about this driver when
configuring a kernel without Intel Keem Bay platform support.
Signed-off-by: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The first argument to WARN() is a condition and the messages is the
second argument is the string, so this WARN() will only display the
__func__ part of the message.
Fixes: ae832e329a ("crypto: keembay-ocs-hcu - Add HMAC support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The Camellia, Serpent and Twofish related header files only contain
declarations that are shared between different implementations of the
respective algorithms residing under arch/x86/crypto, and none of their
contents should be used elsewhere. So move the header files into the
same location, and use local #includes instead.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
All dependencies on the x86 glue helper module have been replaced by
local instantiations of the new ECB/CBC preprocessor helper macros, so
the glue helper module can be retired.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the glue helper dependency with implementations of ECB and CBC
based on the new CPP macros, which avoid the need for indirect calls.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the glue helper dependency with implementations of ECB and CBC
based on the new CPP macros, which avoid the need for indirect calls.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the glue helper dependency with implementations of ECB and CBC
based on the new CPP macros, which avoid the need for indirect calls.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the glue helper dependency with implementations of ECB and CBC
based on the new CPP macros, which avoid the need for indirect calls.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the glue helper dependency with implementations of ECB and CBC
based on the new CPP macros, which avoid the need for indirect calls.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The x86 glue helper module is starting to show its age:
- It relies heavily on function pointers to invoke asm helper functions that
operate on fixed input sizes that are relatively small. This means the
performance is severely impacted by retpolines.
- It goes to great lengths to amortize the cost of kernel_fpu_begin()/end()
over as much work as possible, which is no longer necessary now that FPU
save/restore is done lazily, and doing so may cause unbounded scheduling
blackouts due to the fact that enabling the FPU in kernel mode disables
preemption.
- The CBC mode decryption helper makes backward strides through the input, in
order to avoid a single block size memcpy() between chunks. Consuming the
input in this manner is highly likely to defeat any hardware prefetchers,
so it is better to go through the data linearly, and perform the extra
memcpy() where needed (which is turned into direct loads and stores by the
compiler anyway). Note that benchmarks won't show this effect, given that
the memory they use is always cache hot.
- It implements blockwise XOR in terms of le128 pointers, which imply an
alignment that is not guaranteed by the API, violating the C standard.
GCC does not seem to be smart enough to elide the indirect calls when the
function pointers are passed as arguments to static inline helper routines
modeled after the existing ones. So instead, let's create some CPP macros
that encapsulate the core of the ECB and CBC processing, so we can wire
them up for existing users of the glue helper module, i.e., Camellia,
Serpent, Twofish and CAST6.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Blowfish in counter mode is never used in the kernel, so there
is no point in keeping an accelerated implementation around.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
DES or Triple DES in counter mode is never used in the kernel, so there
is no point in keeping an accelerated implementation around.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The glue helper's CTR routines are no longer used, so drop them.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Twofish in CTR mode is never used by the kernel directly, and is highly
unlikely to be relied upon by dm-crypt or algif_skcipher. So let's drop
the accelerated CTR mode implementation, and instead, rely on the CTR
template and the bare cipher.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
CAST6 in CTR mode is never used by the kernel directly, and is highly
unlikely to be relied upon by dm-crypt or algif_skcipher. So let's drop
the accelerated CTR mode implementation, and instead, rely on the CTR
template and the bare cipher.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
CAST5 in CTR mode is never used by the kernel directly, and is highly
unlikely to be relied upon by dm-crypt or algif_skcipher. So let's drop
the accelerated CTR mode implementation, and instead, rely on the CTR
template and the bare cipher.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Serpent in CTR mode is never used by the kernel directly, and is highly
unlikely to be relied upon by dm-crypt or algif_skcipher. So let's drop
the accelerated CTR mode implementation, and instead, rely on the CTR
template and the bare cipher.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Camellia in CTR mode is never used by the kernel directly, and is highly
unlikely to be relied upon by dm-crypt or algif_skcipher. So let's drop
the accelerated CTR mode implementation, and instead, rely on the CTR
template and the bare cipher.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The glue helper's XTS routines are no longer used, so drop them.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that the XTS template can wrap accelerated ECB modes, it can be
used to implement Twofish in XTS mode as well, which turns out to
be at least as fast, and sometimes even faster
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that the XTS template can wrap accelerated ECB modes, it can be
used to implement Serpent in XTS mode as well, which turns out to
be at least as fast, and sometimes even faster
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that the XTS template can wrap accelerated ECB modes, it can be
used to implement CAST6 in XTS mode as well, which turns out to
be at least as fast, and sometimes even faster
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that the XTS template can wrap accelerated ECB modes, it can be
used to implement Camellia in XTS mode as well, which turns out to
be at least as fast, and sometimes even faster.
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Register SEC device to uacce framework for user space.
Signed-off-by: Kai Ye <yekai13@huawei.com>
Reviewed-by: Zhou Wang <wangzhou1@hisilicon.com>
Reviewed-by: Zaibo Xu <xuzaibo@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Register HPRE device to uacce framework for user space.
Signed-off-by: Kai Ye <yekai13@huawei.com>
Reviewed-by: Zhou Wang <wangzhou1@hisilicon.com>
Reviewed-by: Zaibo Xu <xuzaibo@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add 'uacce_mode' parameter for ZIP, which can be set as 0(default) or 1.
'0' means ZIP is only registered to kernel crypto, and '1' means it's
registered to both kernel crypto and UACCE.
Signed-off-by: Kai Ye <yekai13@huawei.com>
Reviewed-by: Zhou Wang <wangzhou1@hisilicon.com>
Reviewed-by: Zaibo Xu <xuzaibo@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Kunpeng920 SEC/HPRE/ZIP cannot support running user space SVA and kernel
Crypto at the same time. Therefore, the algorithms should not be registered
to Crypto as user space SVA is enabled.
Signed-off-by: Kai Ye <yekai13@huawei.com>
Reviewed-by: Zaibo Xu <xuzaibo@huawei.com>
Reviewed-by: Zhou Wang <wangzhou1@hisilicon.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Renaming 'struct device_private' to 'struct bcm_device_private',
because it clashes with 'struct device_private' from
'drivers/base/base.h'.
While it's not a functional problem, it's causing two distinct
type hierarchies in BTF data. It also breaks build with options:
CONFIG_DEBUG_INFO_BTF=y
CONFIG_CRYPTO_DEV_BCM_SPU=y
as reported by Qais Yousef [1].
[1] https://lore.kernel.org/lkml/20201229151352.6hzmjvu3qh6p2qgg@e107158-lin/
Fixes: 9d12ba86f8 ("crypto: brcm - Add Broadcom SPU driver")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Restrict size of field to what is required by the operation.
This issue was detected by smatch:
drivers/crypto/qat/qat_common/qat_asym_algs.c:328 qat_dh_compute_value() error: dma_map_single_attrs() '&qat_req->in.dh.in.b' too small (8 vs 64)
Signed-off-by: Adam Guerin <adam.guerin@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cast ADF_SIZE_TO_RING_SIZE_IN_BYTES() so it can return a 64 bit value.
This issue was detected by smatch:
drivers/crypto/qat/qat_common/adf_transport_debug.c:65 adf_ring_show() warn: should '(1 << (ring->ring_size - 1)) << 7' be a 64 bit type?
Signed-off-by: Adam Guerin <adam.guerin@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Sanitize ring_num value coming from configuration (and potentially
from user space) before it is used as index in the banks array.
This issue was detected by smatch:
drivers/crypto/qat/qat_common/adf_transport.c:233 adf_create_ring() warn: potential spectre issue 'bank->rings' [r] (local cap)
Signed-off-by: Adam Guerin <adam.guerin@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The hardware specific function adf_get_arbiter_mapping() modifies
the static array thrd_to_arb_map to disable mappings for AEs
that are disabled. This static array is used for each device
of the same type. If the ae mask is not identical for all devices
of the same type then the arbiter mapping returned by
adf_get_arbiter_mapping() may be wrong.
This patch fixes this problem by ensuring the static arbiter
mapping is unchanged and the device arbiter mapping is re-calculated
each time based on the static mapping.
Signed-off-by: Wojciech Ziemba <wojciech.ziemba@intel.com>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the function pointers in the GCM implementation with static branches,
which are based on code patching, which occurs only at module load time.
This avoids the severe performance penalty caused by the use of retpolines.
In order to retain the ability to switch between different versions of the
implementation based on the input size on cores that support AVX and AVX2,
use static branches instead of static calls.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Currently, the gcm(aes-ni) driver open codes the scatterlist handling
that is encapsulated by the skcipher walk API. So let's switch to that
instead.
Also, move the handling at the end of gcmaes_crypt_by_sg() that is
dependent on whether we are encrypting or decrypting into the callers,
which always do one or the other.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The gcm(aes-ni) driver is only built for x86_64, which does not make
use of highmem. So testing for PageHighMem is pointless and can be
omitted.
While at it, replace GFP_ATOMIC with the appropriate runtime decided
value based on the context.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Drop some prototypes that are declared but never called.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The GCM mode driver uses 16 byte aligned buffers on the stack to pass
the IV to the asm helpers, but unfortunately, the x86 port does not
guarantee that the stack pointer is 16 byte aligned upon entry in the
first place. Since the compiler is not aware of this, it will not emit
the additional stack realignment sequence that is needed, and so the
alignment is not guaranteed to be more than 8 bytes.
So instead, allocate some padding on the stack, and realign the IV
pointer by hand.
Cc: <stable@vger.kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Use CRYPTO_LIB_AES in place of CRYPTO_AES in the dependences for the QAT
common code.
Fixes: c0e583ab20 ("crypto: qat - add CRYPTO_AES to Kconfig dependencies")
Reported-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Marco Chiappero <marco.chiappero@intel.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch changes the cast in stm32_cryp_check_ctr_counter from
u32 to __be32 to match the prototype of stm32_cryp_hw_write_iv
correctly.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch moves the extern algorithm declarations into a header
file so that a number of compiler warnings are silenced.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The AES-NI driver implements XTS via the glue helper, which consumes
a struct with sets of function pointers which are invoked on chunks
of input data of the appropriate size, as annotated in the struct.
Let's get rid of this indirection, so that we can perform direct calls
to the assembler helpers. Instead, let's adopt the arm64 strategy, i.e.,
provide a helper which can consume inputs of any size, provided that the
penultimate, full block is passed via the last call if ciphertext stealing
needs to be applied.
This also allows us to enable the XTS mode for i386.
Tested-by: Eric Biggers <ebiggers@google.com> # x86_64
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The XTS asm helper arrangement is a bit odd: the 8-way stride helper
consists of back-to-back calls to the 4-way core transforms, which
are called indirectly, based on a boolean that indicates whether we
are performing encryption or decryption.
Given how costly indirect calls are on x86, let's switch to direct
calls, and given how the 8-way stride doesn't really add anything
substantial, use a 4-way stride instead, and make the asm core
routine deal with any multiple of 4 blocks. Since 512 byte sectors
or 4 KB blocks are the typical quantities XTS operates on, increase
the stride exported to the glue helper to 512 bytes as well.
As a result, the number of indirect calls is reduced from 3 per 64 bytes
of in/output to 1 per 512 bytes of in/output, which produces a 65% speedup
when operating on 1 KB blocks (measured on a Intel(R) Core(TM) i7-8650U CPU)
Fixes: 9697fa39ef ("x86/retpoline/crypto: Convert crypto assembler indirect jumps")
Tested-by: Eric Biggers <ebiggers@google.com> # x86_64
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
PicoXcell has had nothing but treewide cleanups for at least the last 8
years and no signs of activity. The most recent activity is a yocto vendor
kernel based on v3.0 in 2015.
Cc: Jamie Iles <jamie@jamieiles.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-crypto@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add a NEON-accelerated implementation of BLAKE2b.
On Cortex-A7 (which these days is the most common ARM processor that
doesn't have the ARMv8 Crypto Extensions), this is over twice as fast as
SHA-256, and slightly faster than SHA-1. It is also almost three times
as fast as the generic implementation of BLAKE2b:
Algorithm Cycles per byte (on 4096-byte messages)
=================== =======================================
blake2b-256-neon 14.0
sha1-neon 16.3
blake2s-256-arm 18.8
sha1-asm 20.8
blake2s-256-generic 26.0
sha256-neon 28.9
sha256-asm 32.0
blake2b-256-generic 38.9
This implementation isn't directly based on any other implementation,
but it borrows some ideas from previous NEON code I've written as well
as from chacha-neon-core.S. At least on Cortex-A7, it is faster than
the other NEON implementations of BLAKE2b I'm aware of (the
implementation in the BLAKE2 official repository using intrinsics, and
Andrew Moon's implementation which can be found in SUPERCOP). It does
only one block at a time, so it performs well on short messages too.
NEON-accelerated BLAKE2b is useful because there is interest in using
BLAKE2b-256 for dm-verity on low-end Android devices (specifically,
devices that lack the ARMv8 Crypto Extensions) to replace SHA-1. On
these devices, the performance cost of upgrading to SHA-256 may be
unacceptable, whereas BLAKE2b-256 would actually improve performance.
Although BLAKE2b is intended for 64-bit platforms (unlike BLAKE2s which
is intended for 32-bit platforms), on 32-bit ARM processors with NEON,
BLAKE2b is actually faster than BLAKE2s. This is because NEON supports
64-bit operations, and because BLAKE2s's block size is too small for
NEON to be helpful for it. The best I've been able to do with BLAKE2s
on Cortex-A7 is 18.8 cpb with an optimized scalar implementation.
(I didn't try BLAKE2sp and BLAKE3, which in theory would be faster, but
they're more complex as they require running multiple hashes at once.
Note that BLAKE2b already uses all the NEON bandwidth on the Cortex-A7,
so I expect that any speedup from BLAKE2sp or BLAKE3 would come only
from the smaller number of rounds, not from the extra parallelism.)
For now this BLAKE2b implementation is only wired up to the shash API,
since there is no library API for BLAKE2b yet. However, I've tried to
keep things consistent with BLAKE2s, e.g. by defining
blake2b_compress_arch() which is analogous to blake2s_compress_arch()
and could be exported for use by the library API later if needed.
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The file comment for blake2b_generic.c makes it sound like it's the
reference implementation of BLAKE2b with only minor changes. But it's
actually been changed a lot. Update the comment to make this clearer.
Reviewed-by: David Sterba <dsterba@suse.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Sync the BLAKE2b code with the BLAKE2s code as much as possible:
- Move a lot of code into new headers <crypto/blake2b.h> and
<crypto/internal/blake2b.h>, and adjust it to be like the
corresponding BLAKE2s code, i.e. like <crypto/blake2s.h> and
<crypto/internal/blake2s.h>.
- Rename constants, e.g. BLAKE2B_*_DIGEST_SIZE => BLAKE2B_*_HASH_SIZE.
- Use a macro BLAKE2B_ALG() to define the shash_alg structs.
- Export blake2b_compress_generic() for use as a fallback.
This makes it much easier to add optimized implementations of BLAKE2b,
as optimized implementations can use the helper functions
crypto_blake2b_{setkey,init,update,final}() and
blake2b_compress_generic(). The ARM implementation will use these.
But this change is also helpful because it eliminates unnecessary
differences between the BLAKE2b and BLAKE2s code, so that the same
improvements can easily be made to both. (The two algorithms are
basically identical, except for the word size and constants.) It also
makes it straightforward to add a library API for BLAKE2b in the future
if/when it's needed.
This change does make the BLAKE2b code slightly more complicated than it
needs to be, as it doesn't actually provide a library API yet. For
example, __blake2b_update() doesn't really need to exist yet; it could
just be inlined into crypto_blake2b_update(). But I believe this is
outweighed by the benefits of keeping the code in sync.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
When available, select the new implementation of BLAKE2s for 32-bit ARM.
This is faster than the generic C implementation.
Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add an ARM scalar optimized implementation of BLAKE2s.
NEON isn't very useful for BLAKE2s because the BLAKE2s block size is too
small for NEON to help. Each NEON instruction would depend on the
previous one, resulting in poor performance.
With scalar instructions, on the other hand, we can take advantage of
ARM's "free" rotations (like I did in chacha-scalar-core.S) to get an
implementation get runs much faster than the C implementation.
Performance results on Cortex-A7 in cycles per byte using the shash API:
4096-byte messages:
blake2s-256-arm: 18.8
blake2s-256-generic: 26.0
500-byte messages:
blake2s-256-arm: 20.3
blake2s-256-generic: 27.9
100-byte messages:
blake2s-256-arm: 29.7
blake2s-256-generic: 39.2
32-byte messages:
blake2s-256-arm: 50.6
blake2s-256-generic: 66.2
Except on very short messages, this is still slower than the NEON
implementation of BLAKE2b which I've written; that is 14.0, 16.4, 25.8,
and 76.1 cpb on 4096, 500, 100, and 32-byte messages, respectively.
However, optimized BLAKE2s is useful for cases where BLAKE2s is used
instead of BLAKE2b, such as WireGuard.
This new implementation is added in the form of a new module
blake2s-arm.ko, which is analogous to blake2s-x86_64.ko in that it
provides blake2s_compress_arch() for use by the library API as well as
optionally register the algorithms with the shash API.
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
