An ancient gcc bug (first reported in 2003) has apparently resurfaced
on MIPS, where kernelci.org reports an overly large stack frame in the
whirlpool hash algorithm:
crypto/wp512.c:987:1: warning: the frame size of 1112 bytes is larger than 1024 bytes [-Wframe-larger-than=]
With some testing in different configurations, I'm seeing large
variations in stack frames size up to 1500 bytes for what should have
around 300 bytes at most. I also checked the reference implementation,
which is essentially the same code but also comes with some test and
benchmarking infrastructure.
It seems that recent compiler versions on at least arm, arm64 and powerpc
have a partial fix for this problem, but enabling "-fsched-pressure", but
even with that fix they suffer from the issue to a certain degree. Some
testing on arm64 shows that the time needed to hash a given amount of
data is roughly proportional to the stack frame size here, which makes
sense given that the wp512 implementation is doing lots of loads for
table lookups, and the problem with the overly large stack is a result
of doing a lot more loads and stores for spilled registers (as seen from
inspecting the object code).
Disabling -fschedule-insns consistently fixes the problem for wp512,
in my collection of cross-compilers, the results are consistently better
or identical when comparing the stack sizes in this function, though
some architectures (notable x86) have schedule-insns disabled by
default.
The four columns are:
default: -O2
press: -O2 -fsched-pressure
nopress: -O2 -fschedule-insns -fno-sched-pressure
nosched: -O2 -no-schedule-insns (disables sched-pressure)
default press nopress nosched
alpha-linux-gcc-4.9.3 1136 848 1136 176
am33_2.0-linux-gcc-4.9.3 2100 2076 2100 2104
arm-linux-gnueabi-gcc-4.9.3 848 848 1048 352
cris-linux-gcc-4.9.3 272 272 272 272
frv-linux-gcc-4.9.3 1128 1000 1128 280
hppa64-linux-gcc-4.9.3 1128 336 1128 184
hppa-linux-gcc-4.9.3 644 308 644 276
i386-linux-gcc-4.9.3 352 352 352 352
m32r-linux-gcc-4.9.3 720 656 720 268
microblaze-linux-gcc-4.9.3 1108 604 1108 256
mips64-linux-gcc-4.9.3 1328 592 1328 208
mips-linux-gcc-4.9.3 1096 624 1096 240
powerpc64-linux-gcc-4.9.3 1088 432 1088 160
powerpc-linux-gcc-4.9.3 1080 584 1080 224
s390-linux-gcc-4.9.3 456 456 624 360
sh3-linux-gcc-4.9.3 292 292 292 292
sparc64-linux-gcc-4.9.3 992 240 992 208
sparc-linux-gcc-4.9.3 680 592 680 312
x86_64-linux-gcc-4.9.3 224 240 272 224
xtensa-linux-gcc-4.9.3 1152 704 1152 304
aarch64-linux-gcc-7.0.0 224 224 1104 208
arm-linux-gnueabi-gcc-7.0.1 824 824 1048 352
mips-linux-gcc-7.0.0 1120 648 1120 272
x86_64-linux-gcc-7.0.1 240 240 304 240
arm-linux-gnueabi-gcc-4.4.7 840 392
arm-linux-gnueabi-gcc-4.5.4 784 728 784 320
arm-linux-gnueabi-gcc-4.6.4 736 728 736 304
arm-linux-gnueabi-gcc-4.7.4 944 784 944 352
arm-linux-gnueabi-gcc-4.8.5 464 464 760 352
arm-linux-gnueabi-gcc-4.9.3 848 848 1048 352
arm-linux-gnueabi-gcc-5.3.1 824 824 1064 336
arm-linux-gnueabi-gcc-6.1.1 808 808 1056 344
arm-linux-gnueabi-gcc-7.0.1 824 824 1048 352
Trying the same test for serpent-generic, the picture is a bit different,
and while -fno-schedule-insns is generally better here than the default,
-fsched-pressure wins overall, so I picked that instead.
default press nopress nosched
alpha-linux-gcc-4.9.3 1392 864 1392 960
am33_2.0-linux-gcc-4.9.3 536 524 536 528
arm-linux-gnueabi-gcc-4.9.3 552 552 776 536
cris-linux-gcc-4.9.3 528 528 528 528
frv-linux-gcc-4.9.3 536 400 536 504
hppa64-linux-gcc-4.9.3 524 208 524 480
hppa-linux-gcc-4.9.3 768 472 768 508
i386-linux-gcc-4.9.3 564 564 564 564
m32r-linux-gcc-4.9.3 712 576 712 532
microblaze-linux-gcc-4.9.3 724 392 724 512
mips64-linux-gcc-4.9.3 720 384 720 496
mips-linux-gcc-4.9.3 728 384 728 496
powerpc64-linux-gcc-4.9.3 704 304 704 480
powerpc-linux-gcc-4.9.3 704 296 704 480
s390-linux-gcc-4.9.3 560 560 592 536
sh3-linux-gcc-4.9.3 540 540 540 540
sparc64-linux-gcc-4.9.3 544 352 544 496
sparc-linux-gcc-4.9.3 544 344 544 496
x86_64-linux-gcc-4.9.3 528 536 576 528
xtensa-linux-gcc-4.9.3 752 544 752 544
aarch64-linux-gcc-7.0.0 432 432 656 480
arm-linux-gnueabi-gcc-7.0.1 616 616 808 536
mips-linux-gcc-7.0.0 720 464 720 488
x86_64-linux-gcc-7.0.1 536 528 600 536
arm-linux-gnueabi-gcc-4.4.7 592 440
arm-linux-gnueabi-gcc-4.5.4 776 448 776 544
arm-linux-gnueabi-gcc-4.6.4 776 448 776 544
arm-linux-gnueabi-gcc-4.7.4 768 448 768 544
arm-linux-gnueabi-gcc-4.8.5 488 488 776 544
arm-linux-gnueabi-gcc-4.9.3 552 552 776 536
arm-linux-gnueabi-gcc-5.3.1 552 552 776 536
arm-linux-gnueabi-gcc-6.1.1 560 560 776 536
arm-linux-gnueabi-gcc-7.0.1 616 616 808 536
I did not do any runtime tests with serpent, so it is possible that stack
frame size does not directly correlate with runtime performance here and
it actually makes things worse, but it's more likely to help here, and
the reduced stack frame size is probably enough reason to apply the patch,
especially given that the crypto code is often used in deep call chains.
Link: https://kernelci.org/build/id/58797d7559b5149efdf6c3a9/logs/
Link: http://www.larc.usp.br/~pbarreto/WhirlpoolPage.html
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=11488
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Lookup table based AES is sensitive to timing attacks, which is due to
the fact that such table lookups are data dependent, and the fact that
8 KB worth of tables covers a significant number of cachelines on any
architecture, resulting in an exploitable correlation between the key
and the processing time for known plaintexts.
For network facing algorithms such as CTR, CCM or GCM, this presents a
security risk, which is why arch specific AES ports are typically time
invariant, either through the use of special instructions, or by using
SIMD algorithms that don't rely on table lookups.
For generic code, this is difficult to achieve without losing too much
performance, but we can improve the situation significantly by switching
to an implementation that only needs 256 bytes of table data (the actual
S-box itself), which can be prefetched at the start of each block to
eliminate data dependent latencies.
This code encrypts at ~25 cycles per byte on ARM Cortex-A57 (while the
ordinary generic AES driver manages 18 cycles per byte on this
hardware). Decryption is substantially slower.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Both asn1 headers are included by rsa_helper.c, so rsa_helper.o
should explicitly depend on them.
Signed-off-by: David Michael <david.michael@coreos.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch adds the simd skcipher helper which is meant to be
a replacement for ablk helper. It replaces the underlying blkcipher
interface with skcipher, and also presents the top-level algorithm
as an skcipher.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add a synchronous back-end (scomp) to acomp. This allows to easily
expose the already present compression algorithms in LKCF via acomp.
Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch removes the old crypto_grab_skcipher helper and replaces
it with crypto_grab_skcipher2.
As this is the final entry point into givcipher this patch also
removes all traces of the top-level givcipher interface, including
all implicit IV generators such as chainiv.
The bottom-level givcipher interface remains until the drivers
using it are converted.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
* Implement ECDH under kpp API
* Provide ECC software support for curve P-192 and
P-256.
* Add kpp test for ECDH with data generated by OpenSSL
Signed-off-by: Salvatore Benedetto <salvatore.benedetto@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add key-agreement protocol primitives (kpp) API which allows to
implement primitives required by protocols such as DH and ECDH.
The API is composed mainly by the following functions
* set_secret() - It allows the user to set his secret, also
referred to as his private key, along with the parameters
known to both parties involved in the key-agreement session.
* generate_public_key() - It generates the public key to be sent to
the other counterpart involved in the key-agreement session. The
function has to be called after set_params() and set_secret()
* generate_secret() - It generates the shared secret for the session
Other functions such as init() and exit() are provided for allowing
cryptographic hardware to be inizialized properly before use
Signed-off-by: Salvatore Benedetto <salvatore.benedetto@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now block cipher engines need to implement and maintain their own queue/thread
for processing requests, moreover currently helpers provided for only the queue
itself (in crypto_enqueue_request() and crypto_dequeue_request()) but they
don't help with the mechanics of driving the hardware (things like running the
request immediately, DMA map it or providing a thread to process the queue in)
even though a lot of that code really shouldn't vary that much from device to
device.
Thus this patch provides a mechanism for pushing requests to the hardware
as it becomes free that drivers could use. And this framework is patterned
on the SPI code and has worked out well there.
(https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/
drivers/spi/spi.c?id=ffbbdd21329f3e15eeca6df2d4bc11c04d9d91c0)
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The generic crc32 implementation is currently called crc32. This
is a problem because it clashes with the lib implementation of crc32.
This patch renames the crypto crc32 to crc32_generic so that it is
consistent with crc32c. An alias for the driver is also added.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch adds PKCS#1 v1.5 standard RSA padding as a separate template.
This way an RSA cipher with padding can be obtained by instantiating
"pkcs1pad(rsa)". The reason for adding this is that RSA is almost
never used without this padding (or OAEP) so it will be needed for
either certificate work in the kernel or the userspace, and I also hear
that it is likely implemented by hardware RSA in which case hardware
implementations of the whole of pkcs1pad(rsa) can be provided.
Signed-off-by: Andrew Zaborowski <andrew.zaborowski@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Setkey function has been split into set_priv_key and set_pub_key.
Akcipher requests takes sgl for src and dst instead of void *.
Users of the API i.e. two existing RSA implementation and
test mgr code have been updated accordingly.
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch introduces the crypto skcipher interface which aims
to replace both blkcipher and ablkcipher.
It's very similar to the existing ablkcipher interface. The
main difference is the removal of the givcrypt interface. In
order to make the transition easier for blkcipher users, there
is a helper SKCIPHER_REQUEST_ON_STACK which can be used to place
a request on the stack for synchronous transforms.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The Kconfig option NULL2 has been added as CRYPTO_MANAGER now
depends indirectly on NULL2. However, the Makefile was not updated
to use the new option, resulting in potential build failures when
only NULL2 is enabled.
Fixes: 149a39717d ("crypto: aead - Add type-safe geniv init/exit helpers")
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The core of the Jitter RNG is intended to be compiled with -O0. To
ensure that the Jitter RNG can be compiled on all architectures,
separate out the RNG core into a stand-alone C file that can be compiled
with -O0 which does not depend on any kernel include file.
As no kernel includes can be used in the C file implementing the core
RNG, any dependencies on kernel code must be extracted.
A second file provides the link to the kernel and the kernel crypto API
that can be compiled with the regular compile options of the kernel.
Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add a new rsa generic SW implementation.
This implements only cryptographic primitives.
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Added select on ASN1.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add Public Key Encryption API.
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Made CRYPTO_AKCIPHER invisible like other type config options.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Replace the global -O0 compiler flag from the Makefile with GCC
pragmas to mark only the functions required to be compiled without
optimizations.
This patch also adds a comment describing the rationale for the
functions chosen to be compiled without optimizations.
Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Arnd Bergmann
Ard Biesheuvel
Herbert Xu
David Michael
Giovanni Cabiddu
Salvatore Benedetto
Jeff Garzik
Baolin Wang
Joonsoo Kim
Andrzej Zaborowski
Stephan Mueller
Tadeusz Struk