linux/lib/siphash.c

539 lines
12 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
/* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
*
* SipHash: a fast short-input PRF
* https://131002.net/siphash/
*
* This implementation is specifically for SipHash2-4 for a secure PRF
* and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
* hashtables.
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
*/
#include <linux/siphash.h>
#include <linux/unaligned.h>
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
#include <linux/dcache.h>
#include <asm/word-at-a-time.h>
#endif
#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3)
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
#define PREAMBLE(len) \
u64 v0 = SIPHASH_CONST_0; \
u64 v1 = SIPHASH_CONST_1; \
u64 v2 = SIPHASH_CONST_2; \
u64 v3 = SIPHASH_CONST_3; \
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
u64 b = ((u64)(len)) << 56; \
v3 ^= key->key[1]; \
v2 ^= key->key[0]; \
v1 ^= key->key[1]; \
v0 ^= key->key[0];
#define POSTAMBLE \
v3 ^= b; \
SIPROUND; \
SIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
SIPROUND; \
SIPROUND; \
SIPROUND; \
SIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
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>
2021-11-29 15:39:29 +00:00
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
PREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = le64_to_cpup(data);
v3 ^= m;
SIPROUND;
SIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48; fallthrough;
case 6: b |= ((u64)end[5]) << 40; fallthrough;
case 5: b |= ((u64)end[4]) << 32; fallthrough;
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
case 4: b |= le32_to_cpup(data); break;
case 3: b |= ((u64)end[2]) << 16; fallthrough;
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
#endif
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_aligned);
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>
2021-11-29 15:39:29 +00:00
#endif
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
PREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = get_unaligned_le64(data);
v3 ^= m;
SIPROUND;
SIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48; fallthrough;
case 6: b |= ((u64)end[5]) << 40; fallthrough;
case 5: b |= ((u64)end[4]) << 32; fallthrough;
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
case 4: b |= get_unaligned_le32(end); break;
case 3: b |= ((u64)end[2]) << 16; fallthrough;
siphash: add cryptographically secure PRF SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first usage: There are a variety of attacks known as "hashtable poisoning" in which an attacker forms some data such that the hash of that data will be the same, and then preceeds to fill up all entries of a hashbucket. This is a realistic and well-known denial-of-service vector. Currently hashtables use jhash, which is fast but not secure, and some kind of rotating key scheme (or none at all, which isn't good). SipHash is meant as a replacement for jhash in these cases. There are a modicum of places in the kernel that are vulnerable to hashtable poisoning attacks, either via userspace vectors or network vectors, and there's not a reliable mechanism inside the kernel at the moment to fix it. The first step toward fixing these issues is actually getting a secure primitive into the kernel for developers to use. Then we can, bit by bit, port things over to it as deemed appropriate. While SipHash is extremely fast for a cryptographically secure function, it is likely a bit slower than the insecure jhash, and so replacements will be evaluated on a case-by-case basis based on whether or not the difference in speed is negligible and whether or not the current jhash usage poses a real security risk. For the second usage: A few places in the kernel are using MD5 or SHA1 for creating secure sequence numbers, syn cookies, port numbers, or fast random numbers. SipHash is a faster and more fitting, and more secure replacement for MD5 in those situations. Replacing MD5 and SHA1 with SipHash for these uses is obvious and straight-forward, and so is submitted along with this patch series. There shouldn't be much of a debate over its efficacy. Dozens of languages are already using this internally for their hash tables and PRFs. Some of the BSDs already use this in their kernels. SipHash is a widely known high-speed solution to a widely known set of problems, and it's time we catch-up. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: David Laight <David.Laight@aculab.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-08 12:54:00 +00:00
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
#endif
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_unaligned);
/**
* siphash_1u64 - compute 64-bit siphash PRF value of a u64
* @first: first u64
* @key: the siphash key
*/
u64 siphash_1u64(const u64 first, const siphash_key_t *key)
{
PREAMBLE(8)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_1u64);
/**
* siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
* @first: first u64
* @second: second u64
* @key: the siphash key
*/
u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
{
PREAMBLE(16)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_2u64);
/**
* siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
* @first: first u64
* @second: second u64
* @third: third u64
* @key: the siphash key
*/
u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
const siphash_key_t *key)
{
PREAMBLE(24)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
v3 ^= third;
SIPROUND;
SIPROUND;
v0 ^= third;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_3u64);
/**
* siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
* @first: first u64
* @second: second u64
* @third: third u64
* @forth: forth u64
* @key: the siphash key
*/
u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
const u64 forth, const siphash_key_t *key)
{
PREAMBLE(32)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
v3 ^= third;
SIPROUND;
SIPROUND;
v0 ^= third;
v3 ^= forth;
SIPROUND;
SIPROUND;
v0 ^= forth;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_4u64);
u64 siphash_1u32(const u32 first, const siphash_key_t *key)
{
PREAMBLE(4)
b |= first;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_1u32);
u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
const siphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
PREAMBLE(12)
v3 ^= combined;
SIPROUND;
SIPROUND;
v0 ^= combined;
b |= third;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_3u32);
#if BITS_PER_LONG == 64
/* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for
* performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3.
*/
#define HSIPROUND SIPROUND
#define HPREAMBLE(len) PREAMBLE(len)
#define HPOSTAMBLE \
v3 ^= b; \
HSIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
HSIPROUND; \
HSIPROUND; \
HSIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
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>
2021-11-29 15:39:29 +00:00
#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));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = le64_to_cpup(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48; fallthrough;
case 6: b |= ((u64)end[5]) << 40; fallthrough;
case 5: b |= ((u64)end[4]) << 32; fallthrough;
case 4: b |= le32_to_cpup(data); break;
case 3: b |= ((u64)end[2]) << 16; fallthrough;
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
#endif
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
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>
2021-11-29 15:39:29 +00:00
#endif
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = get_unaligned_le64(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48; fallthrough;
case 6: b |= ((u64)end[5]) << 40; fallthrough;
case 5: b |= ((u64)end[4]) << 32; fallthrough;
case 4: b |= get_unaligned_le32(end); break;
case 3: b |= ((u64)end[2]) << 16; fallthrough;
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
#endif
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
/**
* hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
* @first: first u32
* @key: the hsiphash key
*/
u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
{
HPREAMBLE(4)
b |= first;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_1u32);
/**
* hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
* @first: first u32
* @second: second u32
* @key: the hsiphash key
*/
u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(8)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_2u32);
/**
* hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @key: the hsiphash key
*/
u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(12)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
b |= third;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_3u32);
/**
* hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @forth: forth u32
* @key: the hsiphash key
*/
u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
const u32 forth, const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(16)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
combined = (u64)forth << 32 | third;
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_4u32);
#else
#define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3)
#define HPREAMBLE(len) \
u32 v0 = HSIPHASH_CONST_0; \
u32 v1 = HSIPHASH_CONST_1; \
u32 v2 = HSIPHASH_CONST_2; \
u32 v3 = HSIPHASH_CONST_3; \
u32 b = ((u32)(len)) << 24; \
v3 ^= key->key[1]; \
v2 ^= key->key[0]; \
v1 ^= key->key[1]; \
v0 ^= key->key[0];
#define HPOSTAMBLE \
v3 ^= b; \
HSIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
HSIPROUND; \
HSIPROUND; \
HSIPROUND; \
return v1 ^ v3;
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>
2021-11-29 15:39:29 +00:00
#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));
const u8 left = len & (sizeof(u32) - 1);
u32 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u32)) {
m = le32_to_cpup(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
switch (left) {
case 3: b |= ((u32)end[2]) << 16; fallthrough;
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
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>
2021-11-29 15:39:29 +00:00
#endif
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u32));
const u8 left = len & (sizeof(u32) - 1);
u32 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u32)) {
m = get_unaligned_le32(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
switch (left) {
case 3: b |= ((u32)end[2]) << 16; fallthrough;
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
/**
* hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
* @first: first u32
* @key: the hsiphash key
*/
u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
{
HPREAMBLE(4)
v3 ^= first;
HSIPROUND;
v0 ^= first;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_1u32);
/**
* hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
* @first: first u32
* @second: second u32
* @key: the hsiphash key
*/
u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
{
HPREAMBLE(8)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_2u32);
/**
* hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @key: the hsiphash key
*/
u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
const hsiphash_key_t *key)
{
HPREAMBLE(12)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
v3 ^= third;
HSIPROUND;
v0 ^= third;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_3u32);
/**
* hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @forth: forth u32
* @key: the hsiphash key
*/
u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
const u32 forth, const hsiphash_key_t *key)
{
HPREAMBLE(16)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
v3 ^= third;
HSIPROUND;
v0 ^= third;
v3 ^= forth;
HSIPROUND;
v0 ^= forth;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_4u32);
#endif