mirrors/passt
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
passt/siphash.c
Stefano Brivio a48c5c2abf treewide: Disable gcc strict aliasing rules as needed, drop workarounds 
Recently, commit 4ddbcb9c0c ("tcp: Disable optimisations
for tcp_hash()") worked around yet another issue we hit with gcc 12
and '-flto -O2': some stores affecting the input data to siphash_20b()
were omitted altogether, and tcp_hash() wouldn't get the correct hash
for incoming connections.

Digging further into this revealed that, at least according to gcc's
interpretation of C99 aliasing rules, passing pointers to functions
with different types compared to the effective type of the object
(for example, a uint8_t pointer to an anonymous struct, as it happens
in tcp_hash()), doesn't guarantee that stores are not reordered
across the function call.

This means that, in general, our checksum and hash functions might
not see parts of input data that was intended to be provided by
callers.

Not even switching from uint8_t to character types, which should be
appropriate here, according to C99 (ISO/IEC 9899, TC3, draft N1256),
section 6.5, "Expressions", paragraph 7:

  An object shall have its stored value accessed only by an lvalue
  expression that has one of the following types:

  [...]

  — a character type.

does the trick. I guess this is also subject to interpretation:
casting passed pointers to character types, and then using those as
different types, might still violate (dubious) aliasing rules.

Disable gcc strict aliasing rules for potentially affected functions,
which, in turn, disables gcc's Type-Based Alias Analysis (TBAA)
optimisations based on those function arguments.

Drop the existing workarounds. Also the (seemingly?) bogus
'maybe-uninitialized' warning on the tcp_tap_handler() > tcp_hash() >
siphash_20b() path goes away with -fno-strict-aliasing on
siphash_20b().

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
2023-02-27 18:54:13 +01:00

243 lines
6.6 KiB
C
Raw Blame History

// SPDX-License-Identifier: AGPL-3.0-or-later
/* PASST - Plug A Simple Socket Transport
* for qemu/UNIX domain socket mode
*
* PASTA - Pack A Subtle Tap Abstraction
* for network namespace/tap device mode
*
* siphash.c - SipHash routines
*
* Copyright (c) 2020-2021 Red Hat GmbH
* Author: Stefano Brivio <sbrivio@redhat.com>
*
* This is an implementation of the SipHash-2-4-64 functions needed for TCP
* initial sequence numbers and socket lookup table hash for IPv4 and IPv6, see:
*
* Aumasson, J.P. and Bernstein, D.J., 2012, December. SipHash: a fast
* short-input PRF. In International Conference on Cryptology in India
* (pp. 489-508). Springer, Berlin, Heidelberg.
*
* http://cr.yp.to/siphash/siphash-20120918.pdf
*
* This includes code from the reference SipHash implementation at
* https://github.com/veorq/SipHash/ originally licensed as follows:
*
* --
* SipHash reference C implementation
*
* Copyright (c) 2012-2021 Jean-Philippe Aumasson
* <jeanphilippe.aumasson@gmail.com>
* Copyright (c) 2012-2014 Daniel J. Bernstein <djb@cr.yp.to>
*
* To the extent possible under law, the author(s) have dedicated all copyright
* and related and neighboring rights to this software to the public domain
* worldwide. This software is distributed without any warranty.
*
* You should have received a copy of the CC0 Public Domain Dedication along
* with
* this software. If not, see
* <http://creativecommons.org/publicdomain/zero/1.0/>.
* --
*
* and from the Linux kernel implementation (lib/siphash.c), originally licensed
* as follows:
*
* --
* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*
* This file is provided under a dual BSD/GPLv2 license.
* --
*
*/
#include <stdint.h>
#include "siphash.h"
#define ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b))))
#define PREAMBLE(len) \
uint64_t v[4] = { 0x736f6d6570736575ULL, 0x646f72616e646f6dULL, \
0x6c7967656e657261ULL, 0x7465646279746573ULL }; \
uint64_t b = (uint64_t)(len) << 56; \
uint32_t ret; \
int __i; \
\
do { \
for (__i = sizeof(v) / sizeof(v[0]) - 1; __i >= 0; __i--) \
v[__i] = k[__i % 2]; \
} while (0)
#define SIPROUND(n) \
do { \
for (__i = 0; __i < (n); __i++) { \
v[0] += v[1]; \
v[1] = ROTL(v[1], 13) ^ v[0]; \
v[0] = ROTL(v[0], 32); \
v[2] += v[3]; \
v[3] = ROTL(v[3], 16) ^ v[2]; \
v[0] += v[3]; \
v[3] = ROTL(v[3], 21) ^ v[0]; \
v[2] += v[1]; \
v[1] = ROTL(v[1], 17) ^ v[2]; \
v[2] = ROTL(v[2], 32); \
} \
} while (0)
#define POSTAMBLE \
do { \
v[3] ^= b; \
SIPROUND(2); \
v[0] ^= b; \
v[2] ^= 0xff; \
SIPROUND(4); \
b = (v[0] ^ v[1]) ^ (v[2] ^ v[3]); \
ret = (uint32_t)(b >> 32) ^ (uint32_t)b; \
(void)ret; \
} while (0)
/**
* siphash_8b() - Table index or timestamp offset for TCP over IPv4 (8 bytes in)
* @in: Input data (remote address and two ports, or two addresses)
* @k: Hash function key, 128 bits
*
* Return: the 64-bit hash output
*/
/* Type-Based Alias Analysis (TBAA) optimisation in gcc 11 and 12 (-flto -O2)
* makes these functions essentially useless by allowing reordering of stores of
* input data across function calls. Not even declaring @in as char pointer is
* enough: disable gcc's interpretation of strict aliasing altogether. See also:
*
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106706
* https://stackoverflow.com/questions/2958633/gcc-strict-aliasing-and-horror-stories
* https://lore.kernel.org/all/alpine.LFD.2.00.0901121128080.6528__33422.5328093909$1232291247$gmane$org@localhost.localdomain/
*/
/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
__attribute__((optimize("-fno-strict-aliasing")))
/* cppcheck-suppress unusedFunction */
uint64_t siphash_8b(const uint8_t *in, const uint64_t *k)
{
PREAMBLE(8);
v[3] ^= *(uint64_t *)in;
SIPROUND(2);
v[0] ^= *(uint64_t *)in;
POSTAMBLE;
return b;
}
/**
* siphash_12b() - Initial sequence number for TCP over IPv4 (12 bytes in)
* @in: Input data (two addresses, two ports)
* @k: Hash function key, 128 bits
*
* Return: 32 bits obtained by XORing the two halves of the 64-bit hash output
*/
/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
__attribute__((optimize("-fno-strict-aliasing"))) /* See siphash_8b() */
/* cppcheck-suppress unusedFunction */
uint32_t siphash_12b(const uint8_t *in, const uint64_t *k)
{
uint32_t *in32 = (uint32_t *)in;
uint64_t combined;
combined = (uint64_t)(*(in32 + 1)) << 32 | *in32;
PREAMBLE(12);
v[3] ^= combined;
SIPROUND(2);
v[0] ^= combined;
b |= *(in32 + 2);
POSTAMBLE;
return ret;
}
/**
* siphash_20b() - Table index for TCP over IPv6 (20 bytes in)
* @in: Input data (remote address, two ports)
* @k: Hash function key, 128 bits
*
* Return: the 64-bit hash output
*/
/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
__attribute__((optimize("-fno-strict-aliasing"))) /* See siphash_8b() */
uint64_t siphash_20b(const uint8_t *in, const uint64_t *k)
{
uint32_t *in32 = (uint32_t *)in;
int i;
PREAMBLE(20);
for (i = 0; i < 2; i++, in32 += 2) {
uint64_t combined = (uint64_t)(*(in32 + 1)) << 32 | *in32;
v[3] ^= combined;
SIPROUND(2);
v[0] ^= combined;
}
b |= *in32;
POSTAMBLE;
return b;
}
/**
* siphash_32b() - Timestamp offset for TCP over IPv6 (32 bytes in)
* @in: Input data (two addresses)
* @k: Hash function key, 128 bits
*
* Return: the 64-bit hash output
*/
/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
__attribute__((optimize("-fno-strict-aliasing"))) /* See siphash_8b() */
/* cppcheck-suppress unusedFunction */
uint32_t siphash_32b(const uint8_t *in, const uint64_t *k)
{
uint64_t *in64 = (uint64_t *)in;
int i;
PREAMBLE(32);
for (i = 0; i < 4; i++, in64++) {
v[3] ^= *in64;
SIPROUND(2);
v[0] ^= *in64;
}
POSTAMBLE;
return b;
}
/**
* siphash_36b() - Initial sequence number for TCP over IPv6 (36 bytes in)
* @in: Input data (two addresses, two ports)
* @k: Hash function key, 128 bits
*
* Return: 32 bits obtained by XORing the two halves of the 64-bit hash output
*/
/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
__attribute__((optimize("-fno-strict-aliasing"))) /* See siphash_8b() */
uint32_t siphash_36b(const uint8_t *in, const uint64_t *k)
{
uint32_t *in32 = (uint32_t *)in;
int i;
PREAMBLE(36);
for (i = 0; i < 4; i++, in32 += 2) {
uint64_t combined = (uint64_t)(*(in32 + 1)) << 32 | *in32;
v[3] ^= combined;
SIPROUND(2);
v[0] ^= combined;
}
b |= *in32;
POSTAMBLE;
return ret;
}
Reference in a new issue View git blame Copy permalink