aboutsummaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorArnd Bergmann2021-11-29 10:39:29 -0500
committerJakub Kicinski2021-11-29 19:50:50 -0800
commitf7e5b9bfa6c8820407b64eabc1f29c9a87e8993d (patch)
tree3dabfbea501db644fc7bc3df870695c0e78939db /lib
parent4e3fd721710553832460c179c2ee5ce67ef7f1e0 (diff)
siphash: use _unaligned version by default
On ARM v6 and later, we define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS because the ordinary load/store instructions (ldr, ldrh, ldrb) can tolerate any misalignment of the memory address. However, load/store double and load/store multiple instructions (ldrd, ldm) may still only be used on memory addresses that are 32-bit aligned, and so we have to use the CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS macro with care, or we may end up with a severe performance hit due to alignment traps that require fixups by the kernel. Testing shows that this currently happens with clang-13 but not gcc-11. In theory, any compiler version can produce this bug or other problems, as we are dealing with undefined behavior in C99 even on architectures that support this in hardware, see also https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100363. Fortunately, the get_unaligned() accessors do the right thing: when building for ARMv6 or later, the compiler will emit unaligned accesses using the ordinary load/store instructions (but avoid the ones that require 32-bit alignment). When building for older ARM, those accessors will emit the appropriate sequence of ldrb/mov/orr instructions. And on architectures that can truly tolerate any kind of misalignment, the get_unaligned() accessors resolve to the leXX_to_cpup accessors that operate on aligned addresses. Since the compiler will in fact emit ldrd or ldm instructions when building this code for ARM v6 or later, the solution is to use the unaligned accessors unconditionally on architectures where this is known to be fast. The _aligned version of the hash function is however still needed to get the best performance on architectures that cannot do any unaligned access in hardware. This new version avoids the undefined behavior and should produce the fastest hash on all architectures we support. Link: https://lore.kernel.org/linux-arm-kernel/20181008211554.5355-4-ard.biesheuvel@linaro.org/ Link: https://lore.kernel.org/linux-crypto/CAK8P3a2KfmmGDbVHULWevB0hv71P2oi2ZCHEAqT=8dQfa0=cqQ@mail.gmail.com/ Reported-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Fixes: 2c956a60778c ("siphash: add cryptographically secure PRF") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com> Acked-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'lib')
-rw-r--r--lib/siphash.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/lib/siphash.c b/lib/siphash.c
index a90112ee72a1..72b9068ab57b 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -49,6 +49,7 @@
SIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_aligned);
+#endif
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_unaligned);
-#endif
/**
* siphash_1u64 - compute 64-bit siphash PRF value of a u64
@@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32);
HSIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
@@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
/**
* hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
@@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32);
HSIPROUND; \
return v1 ^ v3;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u32));
@@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
@@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
/**
* hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32