Pull x86 asm updates from Thomas Gleixner:
"The lowlevel and ASM code updates for x86:
- Make stack trace unwinding more reliable
- ASM instruction updates for better code generation
- Various cleanups"
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/entry/64: Add two more instruction suffixes
x86/asm/64: Use 32-bit XOR to zero registers
x86/build/vdso: Simplify 'cmd_vdso2c'
x86/build/vdso: Remove unused vdso-syms.lds
x86/stacktrace: Enable HAVE_RELIABLE_STACKTRACE for the ORC unwinder
x86/unwind/orc: Detect the end of the stack
x86/stacktrace: Do not fail for ORC with regs on stack
x86/stacktrace: Clarify the reliable success paths
x86/stacktrace: Remove STACKTRACE_DUMP_ONCE
x86/stacktrace: Do not unwind after user regs
x86/asm: Use CC_SET/CC_OUT in percpu_cmpxchg8b_double() to micro-optimize code generation
It turns out I had misunderstood how the x86_match_cpu() function works.
It evaluates a logical OR of the matching conditions, not logical AND.
This caused the CPU feature checks for AEGIS to pass even if only SSE2
(but not AES-NI) was supported (or vice versa), leading to potential
crashes if something tried to use the registered algs.
This patch switches the checks to a simpler method that is used e.g. in
the Camellia x86 code.
The patch also removes the MODULE_DEVICE_TABLE declarations which
actually seem to cause the modules to be auto-loaded at boot, which is
not desired. The crypto API on-demand module loading is sufficient.
Fixes: 1d373d4e8e ("crypto: x86 - Add optimized AEGIS implementations")
Fixes: 6ecc9d9ff9 ("crypto: x86 - Add optimized MORUS implementations")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Tested-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Some ahash algorithms set .cra_type = &crypto_ahash_type. But this is
redundant with the C structure type ('struct ahash_alg'), and
crypto_register_ahash() already sets the .cra_type automatically.
Apparently the useless assignment has just been copy+pasted around.
So, remove the useless assignment from all the ahash algorithms.
This patch shouldn't change any actual behavior.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Many ahash algorithms set .cra_flags = CRYPTO_ALG_TYPE_AHASH. But this
is redundant with the C structure type ('struct ahash_alg'), and
crypto_register_ahash() already sets the type flag automatically,
clearing any type flag that was already there. Apparently the useless
assignment has just been copy+pasted around.
So, remove the useless assignment from all the ahash algorithms.
This patch shouldn't change any actual behavior.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Many shash algorithms set .cra_flags = CRYPTO_ALG_TYPE_SHASH. But this
is redundant with the C structure type ('struct shash_alg'), and
crypto_register_shash() already sets the type flag automatically,
clearing any type flag that was already there. Apparently the useless
assignment has just been copy+pasted around.
So, remove the useless assignment from all the shash algorithms.
This patch shouldn't change any actual behavior.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
With all the crypto modules enabled on x86, and with a CPU that supports
AVX-2 but not SHA-NI instructions (e.g. Haswell, Broadwell, Skylake),
the "multibuffer" implementations of SHA-1, SHA-256, and SHA-512 are the
highest priority. However, these implementations only perform well when
many hash requests are being submitted concurrently, filling all 8 AVX-2
lanes. Otherwise, they are incredibly slow, as they waste time waiting
for more requests to arrive before proceeding to execute each request.
For example, here are the speeds I see hashing 4096-byte buffers with a
single thread on a Haswell-based processor:
generic avx2 mb (multibuffer)
------- -------- ----------------
sha1 602 MB/s 997 MB/s 0.61 MB/s
sha256 228 MB/s 412 MB/s 0.61 MB/s
sha512 312 MB/s 559 MB/s 0.61 MB/s
So, the multibuffer implementation is 500 to 1000 times slower than the
other implementations. Note that with smaller buffers or more update()s
per digest, the difference would be even greater.
I believe the vast majority of people are in the boat where the
multibuffer code is much slower, and only a small minority are doing the
highly parallel, hashing-intensive, latency-flexible workloads (maybe
IPsec on servers?) where the multibuffer code may be beneficial. Yet,
people often aren't familiar with all the crypto config options and so
the multibuffer code may inadvertently be built into the kernel.
Also the multibuffer code apparently hasn't been very well tested,
seeing as it was sometimes computing the wrong SHA-256 digest.
So, let's make the multibuffer algorithms low priority. Users who want
to use them can either request them explicitly by driver name, or use
NETLINK_CRYPTO (crypto_user) to increase their priority at runtime.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add explicit RETs to the tail calls of AEGIS and MORUS crypto algorithms
otherwise they run into INT3 padding due to
("x86/asm: Pad assembly functions with INT3 instructions")
leading to spurious debug exceptions.
Mike Galbraith <efault@gmx.de> took care of all the remaining callsites.
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Ondrej Mosnacek <omosnacek@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The x86 assembly implementations of Salsa20 use the frame base pointer
register (%ebp or %rbp), which breaks frame pointer convention and
breaks stack traces when unwinding from an interrupt in the crypto code.
Recent (v4.10+) kernels will warn about this, e.g.
WARNING: kernel stack regs at 00000000a8291e69 in syzkaller047086:4677 has bad 'bp' value 000000001077994c
[...]
But after looking into it, I believe there's very little reason to still
retain the x86 Salsa20 code. First, these are *not* vectorized
(SSE2/SSSE3/AVX2) implementations, which would be needed to get anywhere
close to the best Salsa20 performance on any remotely modern x86
processor; they're just regular x86 assembly. Second, it's still
unclear that anyone is actually using the kernel's Salsa20 at all,
especially given that now ChaCha20 is supported too, and with much more
efficient SSSE3 and AVX2 implementations. Finally, in benchmarks I did
on both Intel and AMD processors with both gcc 8.1.0 and gcc 4.9.4, the
x86_64 salsa20-asm is actually slightly *slower* than salsa20-generic
(~3% slower on Skylake, ~10% slower on Zen), while the i686 salsa20-asm
is only slightly faster than salsa20-generic (~15% faster on Skylake,
~20% faster on Zen). The gcc version made little difference.
So, the x86_64 salsa20-asm is pretty clearly useless. That leaves just
the i686 salsa20-asm, which based on my tests provides a 15-20% speed
boost. But that's without updating the code to not use %ebp. And given
the maintenance cost, the small speed difference vs. salsa20-generic,
the fact that few people still use i686 kernels, the doubt that anyone
is even using the kernel's Salsa20 at all, and the fact that a SSE2
implementation would almost certainly be much faster on any remotely
modern x86 processor yet no one has cared enough to add one yet, I don't
think it's worthwhile to keep.
Thus, just remove both the x86_64 and i686 salsa20-asm implementations.
Reported-by: syzbot+ffa3a158337bbc01ff09@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Commit 56e8e57fc3 ("crypto: morus - Add common SIMD glue code for
MORUS") accidetally consiedered the glue code to be usable by different
architectures, but it seems to be only usable on x86.
This patch moves it under arch/x86/crypto and adds 'depends on X86' to
the Kconfig options and also removes the prompt to hide these internal
options from the user.
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Ondrej Mosnacek <omosnacek@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
AEGIS-256 key is two blocks, not one.
Fixes: 1d373d4e8e ("crypto: x86 - Add optimized AEGIS implementations")
Reported-by: Eric Biggers <ebiggers3@gmail.com>
Signed-off-by: Ondrej Mosnacek <omosnacek@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch adds optimized implementations of MORUS-640 and MORUS-1280,
utilizing the SSE2 and AVX2 x86 extensions.
For MORUS-1280 (which operates on 256-bit blocks) we provide both AVX2
and SSE2 implementation. Although SSE2 MORUS-1280 is slower than AVX2
MORUS-1280, it is comparable in speed to the SSE2 MORUS-640.
Signed-off-by: Ondrej Mosnacek <omosnacek@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This patch adds optimized implementations of AEGIS-128, AEGIS-128L,
and AEGIS-256, utilizing the AES-NI and SSE2 x86 extensions.
Signed-off-by: Ondrej Mosnacek <omosnacek@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Trivial fix to spelling mistake in module description text
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
There are no users of the original glue_fpu_begin() anymore, so rename
glue_skwalk_fpu_begin() to glue_fpu_begin() so that it matches
glue_fpu_end() again.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that all glue_helper users have been switched from the blkcipher
interface over to the skcipher interface, remove the versions of the
glue_helper functions that handled the blkcipher interface.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Now that all users of lrw_crypt() have been removed in favor of the LRW
template wrapping an ECB mode algorithm, remove lrw_crypt(). Also
remove crypto/lrw.h as that is no longer needed either; and fold
'struct lrw_table_ctx' into 'struct priv', lrw_init_table() into
setkey(), and lrw_free_table() into exit_tfm().
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the AESNI AVX and AESNI AVX2 implementations of Camellia from
the (deprecated) ablkcipher and blkcipher interfaces over to the
skcipher interface. Note that this includes replacing the use of
ablk_helper with crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the x86 asm implementation of Camellia from the (deprecated)
blkcipher interface over to the skcipher interface.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The XTS template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic XTS code themselves via xts_crypt().
Remove the xts-camellia-asm algorithm which did this. Users who request
xts(camellia) and previously would have gotten xts-camellia-asm will now
get xts(ecb-camellia-asm) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-camellia-asm algorithm which did this. Users who request
lrw(camellia) and previously would have gotten lrw-camellia-asm will now
get lrw(ecb-camellia-asm) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-camellia-aesni-avx2 algorithm which did this. Users who
request lrw(camellia) and previously would have gotten
lrw-camellia-aesni-avx2 will now get lrw(ecb-camellia-aesni-avx2)
instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-camellia-aesni algorithm which did this. Users who
request lrw(camellia) and previously would have gotten
lrw-camellia-aesni will now get lrw(ecb-camellia-aesni) instead, which
is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the x86 asm implementation of Triple DES from the (deprecated)
blkcipher interface over to the skcipher interface.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the x86 asm implementation of Blowfish from the (deprecated)
blkcipher interface over to the skcipher interface.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the AVX implementation of CAST6 from the (deprecated) ablkcipher
and blkcipher interfaces over to the skcipher interface. Note that this
includes replacing the use of ablk_helper with crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-cast6-avx algorithm which did this. Users who request
lrw(cast6) and previously would have gotten lrw-cast6-avx will now get
lrw(ecb-cast6-avx) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the AVX implementation of CAST5 from the (deprecated) ablkcipher
and blkcipher interfaces over to the skcipher interface. Note that this
includes replacing the use of ablk_helper with crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
With ecb-cast5-avx, if a 128+ byte scatterlist element followed a
shorter one, then the algorithm accidentally encrypted/decrypted only 8
bytes instead of the expected 128 bytes. Fix it by setting the
encryption/decryption 'fn' correctly.
Fixes: c12ab20b16 ("crypto: cast5/avx - avoid using temporary stack buffers")
Cc: <stable@vger.kernel.org> # v3.8+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the AVX implementation of Twofish from the (deprecated)
ablkcipher and blkcipher interfaces over to the skcipher interface.
Note that this includes replacing the use of ablk_helper with
crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-twofish-avx algorithm which did this. Users who request
lrw(twofish) and previously would have gotten lrw-twofish-avx will now
get lrw(ecb-twofish-avx) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the 3-way implementation of Twofish from the (deprecated)
blkcipher interface over to the skcipher interface.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The XTS template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic XTS code themselves via xts_crypt().
Remove the xts-twofish-3way algorithm which did this. Users who request
xts(twofish) and previously would have gotten xts-twofish-3way will now
get xts(ecb-twofish-3way) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-twofish-3way algorithm which did this. Users who request
lrw(twofish) and previously would have gotten lrw-twofish-3way will now
get lrw(ecb-twofish-3way) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the AVX and AVX2 implementations of Serpent from the
(deprecated) ablkcipher and blkcipher interfaces over to the skcipher
interface. Note that this includes replacing the use of ablk_helper
with crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-serpent-avx algorithm which did this. Users who request
lrw(serpent) and previously would have gotten lrw-serpent-avx will now
get lrw(ecb-serpent-avx) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-serpent-avx2 algorithm which did this. Users who request
lrw(serpent) and previously would have gotten lrw-serpent-avx2 will now
get lrw(ecb-serpent-avx2) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert the SSE2 implementation of Serpent from the (deprecated)
ablkcipher and blkcipher interfaces over to the skcipher interface.
Note that this includes replacing the use of ablk_helper with
crypto_simd.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The XTS template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic XTS code themselves via xts_crypt().
Remove the xts-serpent-sse2 algorithm which did this. Users who request
xts(serpent) and previously would have gotten xts-serpent-sse2 will now
get xts(ecb-serpent-sse2) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The LRW template now wraps an ECB mode algorithm rather than the block
cipher directly. Therefore it is now redundant for crypto modules to
wrap their ECB code with generic LRW code themselves via lrw_crypt().
Remove the lrw-serpent-sse2 algorithm which did this. Users who request
lrw(serpent) and previously would have gotten lrw-serpent-sse2 will now
get lrw(ecb-serpent-sse2) instead, which is just as fast.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add ECB, CBC, and CTR functions to glue_helper which use skcipher_walk
rather than blkcipher_walk. This will allow converting the remaining
x86 algorithms from the blkcipher interface over to the skcipher
interface, after which we'll be able to remove the blkcipher_walk
versions of these functions.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Add gcmaes_crypt_by_sg routine, that will do scatter/gather
by sg. Either src or dst may contain multiple buffers, so
iterate over both at the same time if they are different.
If the input is the same as the output, iterate only over one.
Currently both the AAD and TAG must be linear, so copy them out
with scatterlist_map_and_copy. If first buffer contains the
entire AAD, we can optimize and not copy. Since the AAD
can be any size, if copied it must be on the heap. TAG can
be on the stack since it is always < 16 bytes.
Only the SSE routines are updated so far, so leave the previous
gcmaes_en/decrypt routines, and branch to the sg ones if the
keysize is inappropriate for avx, or we are SSE only.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The asm macros are all set up now, introduce entry points.
GCM_INIT and GCM_COMPLETE have arguments supplied, so that
the new scatter/gather entry points don't have to take all the
arguments, and only the ones they need.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
We can fast-path any < 16 byte read if the full message is > 16 bytes,
and shift over by the appropriate amount. Usually we are
reading > 16 bytes, so this should be faster than the READ_PARTIAL
macro introduced in b20209c91e for the average case.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Before this diff, multiple calls to GCM_ENC_DEC will
succeed, but only if all calls are a multiple of 16 bytes.
Handle partial blocks at the start of GCM_ENC_DEC, and update
aadhash as appropriate.
The data offset %r11 is also updated after the partial block.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
HashKey computation only needs to happen once per scatter/gather operation,
save it between calls in gcm_context struct instead of on the stack.
Since the asm no longer stores anything on the stack, we can use
%rsp directly, and clean up the frame save/restore macros a bit.
Hashkeys actually only need to be calculated once per key and could
be moved to when set_key is called, however, the current glue code
falls back to generic aes code if fpu is disabled.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
