From 6bf0a5cb5034a7e684dcc3500e841785237ce2dd Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 19:32:43 +0200 Subject: Adding upstream version 1:115.7.0. Signed-off-by: Daniel Baumann --- .../chromium/base/third_party/cityhash/city.cc | 532 +++++++++++++++++++++ 1 file changed, 532 insertions(+) create mode 100644 security/sandbox/chromium/base/third_party/cityhash/city.cc (limited to 'security/sandbox/chromium/base/third_party/cityhash/city.cc') diff --git a/security/sandbox/chromium/base/third_party/cityhash/city.cc b/security/sandbox/chromium/base/third_party/cityhash/city.cc new file mode 100644 index 0000000000..b0d2294aab --- /dev/null +++ b/security/sandbox/chromium/base/third_party/cityhash/city.cc @@ -0,0 +1,532 @@ +// Copyright (c) 2011 Google, Inc. +// +// Permission is hereby granted, free of charge, to any person obtaining a copy +// of this software and associated documentation files (the "Software"), to deal +// in the Software without restriction, including without limitation the rights +// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +// copies of the Software, and to permit persons to whom the Software is +// furnished to do so, subject to the following conditions: +// +// The above copyright notice and this permission notice shall be included in +// all copies or substantial portions of the Software. +// +// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +// THE SOFTWARE. +// +// CityHash, by Geoff Pike and Jyrki Alakuijala +// +// This file provides CityHash64() and related functions. +// +// It's probably possible to create even faster hash functions by +// writing a program that systematically explores some of the space of +// possible hash functions, by using SIMD instructions, or by +// compromising on hash quality. + +#include "city.h" + +#include // for memcpy and memset +#include + +using std::make_pair; +using std::pair; + +#ifdef _MSC_VER + +#include +#define bswap_32(x) _byteswap_ulong(x) +#define bswap_64(x) _byteswap_uint64(x) + +#elif defined(__APPLE__) + +// Mac OS X / Darwin features +#include +#define bswap_32(x) OSSwapInt32(x) +#define bswap_64(x) OSSwapInt64(x) + +#elif defined(__sun) || defined(sun) + +#include +#define bswap_32(x) BSWAP_32(x) +#define bswap_64(x) BSWAP_64(x) + +#elif defined(__FreeBSD__) + +#include +#define bswap_32(x) bswap32(x) +#define bswap_64(x) bswap64(x) + +#elif defined(__OpenBSD__) + +#include +#define bswap_32(x) swap32(x) +#define bswap_64(x) swap64(x) + +#elif defined(__NetBSD__) + +#include +#include +#if defined(__BSWAP_RENAME) && !defined(__bswap_32) +#define bswap_32(x) bswap32(x) +#define bswap_64(x) bswap64(x) +#endif + +#else + +// XXX(cavalcanti): building 'native_client' fails with this header. +//#include + +// Falling back to compiler builtins instead. +#define bswap_32(x) __builtin_bswap32(x) +#define bswap_64(x) __builtin_bswap64(x) + +#endif + +namespace base { +namespace internal { +namespace cityhash_v111 { + +#ifdef WORDS_BIGENDIAN +#define uint32_in_expected_order(x) (bswap_32(x)) +#define uint64_in_expected_order(x) (bswap_64(x)) +#else +#define uint32_in_expected_order(x) (x) +#define uint64_in_expected_order(x) (x) +#endif + +#if !defined(LIKELY) +#if HAVE_BUILTIN_EXPECT +#define LIKELY(x) (__builtin_expect(!!(x), 1)) +#else +#define LIKELY(x) (x) +#endif +#endif + +static uint64 UNALIGNED_LOAD64(const char* p) { + uint64 result; + memcpy(&result, p, sizeof(result)); + return result; +} + +static uint32 UNALIGNED_LOAD32(const char* p) { + uint32 result; + memcpy(&result, p, sizeof(result)); + return result; +} + +static uint64 Fetch64(const char* p) { + return uint64_in_expected_order(UNALIGNED_LOAD64(p)); +} + +static uint32 Fetch32(const char* p) { + return uint32_in_expected_order(UNALIGNED_LOAD32(p)); +} + +// Some primes between 2^63 and 2^64 for various uses. +static const uint64 k0 = 0xc3a5c85c97cb3127ULL; +static const uint64 k1 = 0xb492b66fbe98f273ULL; +static const uint64 k2 = 0x9ae16a3b2f90404fULL; + +// Magic numbers for 32-bit hashing. Copied from Murmur3. +static const uint32 c1 = 0xcc9e2d51; +static const uint32 c2 = 0x1b873593; + +// A 32-bit to 32-bit integer hash copied from Murmur3. +static uint32 fmix(uint32 h) { + h ^= h >> 16; + h *= 0x85ebca6b; + h ^= h >> 13; + h *= 0xc2b2ae35; + h ^= h >> 16; + return h; +} + +static uint32 Rotate32(uint32 val, int shift) { + // Avoid shifting by 32: doing so yields an undefined result. + return shift == 0 ? val : ((val >> shift) | (val << (32 - shift))); +} + +#undef PERMUTE3 +#define PERMUTE3(a, b, c) \ + do { \ + std::swap(a, b); \ + std::swap(a, c); \ + } while (0) + +static uint32 Mur(uint32 a, uint32 h) { + // Helper from Murmur3 for combining two 32-bit values. + a *= c1; + a = Rotate32(a, 17); + a *= c2; + h ^= a; + h = Rotate32(h, 19); + return h * 5 + 0xe6546b64; +} + +static uint32 Hash32Len13to24(const char* s, size_t len) { + uint32 a = Fetch32(s - 4 + (len >> 1)); + uint32 b = Fetch32(s + 4); + uint32 c = Fetch32(s + len - 8); + uint32 d = Fetch32(s + (len >> 1)); + uint32 e = Fetch32(s); + uint32 f = Fetch32(s + len - 4); + uint32 h = len; + + return fmix(Mur(f, Mur(e, Mur(d, Mur(c, Mur(b, Mur(a, h))))))); +} + +static uint32 Hash32Len0to4(const char* s, size_t len) { + uint32 b = 0; + uint32 c = 9; + for (size_t i = 0; i < len; i++) { + signed char v = s[i]; + b = b * c1 + v; + c ^= b; + } + return fmix(Mur(b, Mur(len, c))); +} + +static uint32 Hash32Len5to12(const char* s, size_t len) { + uint32 a = len, b = len * 5, c = 9, d = b; + a += Fetch32(s); + b += Fetch32(s + len - 4); + c += Fetch32(s + ((len >> 1) & 4)); + return fmix(Mur(c, Mur(b, Mur(a, d)))); +} + +uint32 CityHash32(const char* s, size_t len) { + if (len <= 24) { + return len <= 12 + ? (len <= 4 ? Hash32Len0to4(s, len) : Hash32Len5to12(s, len)) + : Hash32Len13to24(s, len); + } + + // len > 24 + uint32 h = len, g = c1 * len, f = g; + uint32 a0 = Rotate32(Fetch32(s + len - 4) * c1, 17) * c2; + uint32 a1 = Rotate32(Fetch32(s + len - 8) * c1, 17) * c2; + uint32 a2 = Rotate32(Fetch32(s + len - 16) * c1, 17) * c2; + uint32 a3 = Rotate32(Fetch32(s + len - 12) * c1, 17) * c2; + uint32 a4 = Rotate32(Fetch32(s + len - 20) * c1, 17) * c2; + h ^= a0; + h = Rotate32(h, 19); + h = h * 5 + 0xe6546b64; + h ^= a2; + h = Rotate32(h, 19); + h = h * 5 + 0xe6546b64; + g ^= a1; + g = Rotate32(g, 19); + g = g * 5 + 0xe6546b64; + g ^= a3; + g = Rotate32(g, 19); + g = g * 5 + 0xe6546b64; + f += a4; + f = Rotate32(f, 19); + f = f * 5 + 0xe6546b64; + size_t iters = (len - 1) / 20; + do { + a0 = Rotate32(Fetch32(s) * c1, 17) * c2; + a1 = Fetch32(s + 4); + a2 = Rotate32(Fetch32(s + 8) * c1, 17) * c2; + a3 = Rotate32(Fetch32(s + 12) * c1, 17) * c2; + a4 = Fetch32(s + 16); + h ^= a0; + h = Rotate32(h, 18); + h = h * 5 + 0xe6546b64; + f += a1; + f = Rotate32(f, 19); + f = f * c1; + g += a2; + g = Rotate32(g, 18); + g = g * 5 + 0xe6546b64; + h ^= a3 + a1; + h = Rotate32(h, 19); + h = h * 5 + 0xe6546b64; + g ^= a4; + g = bswap_32(g) * 5; + h += a4 * 5; + h = bswap_32(h); + f += a0; + PERMUTE3(f, h, g); + s += 20; + } while (--iters != 0); + g = Rotate32(g, 11) * c1; + g = Rotate32(g, 17) * c1; + f = Rotate32(f, 11) * c1; + f = Rotate32(f, 17) * c1; + h = Rotate32(h + g, 19); + h = h * 5 + 0xe6546b64; + h = Rotate32(h, 17) * c1; + h = Rotate32(h + f, 19); + h = h * 5 + 0xe6546b64; + h = Rotate32(h, 17) * c1; + return h; +} + +// Bitwise right rotate. Normally this will compile to a single +// instruction, especially if the shift is a manifest constant. +static uint64 Rotate(uint64 val, int shift) { + // Avoid shifting by 64: doing so yields an undefined result. + return shift == 0 ? val : ((val >> shift) | (val << (64 - shift))); +} + +static uint64 ShiftMix(uint64 val) { + return val ^ (val >> 47); +} + +static uint64 HashLen16(uint64 u, uint64 v) { + return Hash128to64(uint128(u, v)); +} + +static uint64 HashLen16(uint64 u, uint64 v, uint64 mul) { + // Murmur-inspired hashing. + uint64 a = (u ^ v) * mul; + a ^= (a >> 47); + uint64 b = (v ^ a) * mul; + b ^= (b >> 47); + b *= mul; + return b; +} + +static uint64 HashLen0to16(const char* s, size_t len) { + if (len >= 8) { + uint64 mul = k2 + len * 2; + uint64 a = Fetch64(s) + k2; + uint64 b = Fetch64(s + len - 8); + uint64 c = Rotate(b, 37) * mul + a; + uint64 d = (Rotate(a, 25) + b) * mul; + return HashLen16(c, d, mul); + } + if (len >= 4) { + uint64 mul = k2 + len * 2; + uint64 a = Fetch32(s); + return HashLen16(len + (a << 3), Fetch32(s + len - 4), mul); + } + if (len > 0) { + uint8 a = s[0]; + uint8 b = s[len >> 1]; + uint8 c = s[len - 1]; + uint32 y = static_cast(a) + (static_cast(b) << 8); + uint32 z = len + (static_cast(c) << 2); + return ShiftMix(y * k2 ^ z * k0) * k2; + } + return k2; +} + +// This probably works well for 16-byte strings as well, but it may be overkill +// in that case. +static uint64 HashLen17to32(const char* s, size_t len) { + uint64 mul = k2 + len * 2; + uint64 a = Fetch64(s) * k1; + uint64 b = Fetch64(s + 8); + uint64 c = Fetch64(s + len - 8) * mul; + uint64 d = Fetch64(s + len - 16) * k2; + return HashLen16(Rotate(a + b, 43) + Rotate(c, 30) + d, + a + Rotate(b + k2, 18) + c, mul); +} + +// Return a 16-byte hash for 48 bytes. Quick and dirty. +// Callers do best to use "random-looking" values for a and b. +static pair WeakHashLen32WithSeeds(uint64 w, + uint64 x, + uint64 y, + uint64 z, + uint64 a, + uint64 b) { + a += w; + b = Rotate(b + a + z, 21); + uint64 c = a; + a += x; + a += y; + b += Rotate(a, 44); + return make_pair(a + z, b + c); +} + +// Return a 16-byte hash for s[0] ... s[31], a, and b. Quick and dirty. +static pair WeakHashLen32WithSeeds(const char* s, + uint64 a, + uint64 b) { + return WeakHashLen32WithSeeds(Fetch64(s), Fetch64(s + 8), Fetch64(s + 16), + Fetch64(s + 24), a, b); +} + +// Return an 8-byte hash for 33 to 64 bytes. +static uint64 HashLen33to64(const char* s, size_t len) { + uint64 mul = k2 + len * 2; + uint64 a = Fetch64(s) * k2; + uint64 b = Fetch64(s + 8); + uint64 c = Fetch64(s + len - 24); + uint64 d = Fetch64(s + len - 32); + uint64 e = Fetch64(s + 16) * k2; + uint64 f = Fetch64(s + 24) * 9; + uint64 g = Fetch64(s + len - 8); + uint64 h = Fetch64(s + len - 16) * mul; + uint64 u = Rotate(a + g, 43) + (Rotate(b, 30) + c) * 9; + uint64 v = ((a + g) ^ d) + f + 1; + uint64 w = bswap_64((u + v) * mul) + h; + uint64 x = Rotate(e + f, 42) + c; + uint64 y = (bswap_64((v + w) * mul) + g) * mul; + uint64 z = e + f + c; + a = bswap_64((x + z) * mul + y) + b; + b = ShiftMix((z + a) * mul + d + h) * mul; + return b + x; +} + +uint64 CityHash64(const char* s, size_t len) { + if (len <= 32) { + if (len <= 16) { + return HashLen0to16(s, len); + } else { + return HashLen17to32(s, len); + } + } else if (len <= 64) { + return HashLen33to64(s, len); + } + + // For strings over 64 bytes we hash the end first, and then as we + // loop we keep 56 bytes of state: v, w, x, y, and z. + uint64 x = Fetch64(s + len - 40); + uint64 y = Fetch64(s + len - 16) + Fetch64(s + len - 56); + uint64 z = HashLen16(Fetch64(s + len - 48) + len, Fetch64(s + len - 24)); + pair v = WeakHashLen32WithSeeds(s + len - 64, len, z); + pair w = WeakHashLen32WithSeeds(s + len - 32, y + k1, x); + x = x * k1 + Fetch64(s); + + // Decrease len to the nearest multiple of 64, and operate on 64-byte chunks. + len = (len - 1) & ~static_cast(63); + do { + x = Rotate(x + y + v.first + Fetch64(s + 8), 37) * k1; + y = Rotate(y + v.second + Fetch64(s + 48), 42) * k1; + x ^= w.second; + y += v.first + Fetch64(s + 40); + z = Rotate(z + w.first, 33) * k1; + v = WeakHashLen32WithSeeds(s, v.second * k1, x + w.first); + w = WeakHashLen32WithSeeds(s + 32, z + w.second, y + Fetch64(s + 16)); + std::swap(z, x); + s += 64; + len -= 64; + } while (len != 0); + return HashLen16(HashLen16(v.first, w.first) + ShiftMix(y) * k1 + z, + HashLen16(v.second, w.second) + x); +} + +uint64 CityHash64WithSeed(const char* s, size_t len, uint64 seed) { + return CityHash64WithSeeds(s, len, k2, seed); +} + +uint64 CityHash64WithSeeds(const char* s, + size_t len, + uint64 seed0, + uint64 seed1) { + return HashLen16(CityHash64(s, len) - seed0, seed1); +} + +// A subroutine for CityHash128(). Returns a decent 128-bit hash for strings +// of any length representable in signed long. Based on City and Murmur. +static uint128 CityMurmur(const char* s, size_t len, uint128 seed) { + uint64 a = Uint128Low64(seed); + uint64 b = Uint128High64(seed); + uint64 c = 0; + uint64 d = 0; + signed long l = len - 16; + if (l <= 0) { // len <= 16 + a = ShiftMix(a * k1) * k1; + c = b * k1 + HashLen0to16(s, len); + d = ShiftMix(a + (len >= 8 ? Fetch64(s) : c)); + } else { // len > 16 + c = HashLen16(Fetch64(s + len - 8) + k1, a); + d = HashLen16(b + len, c + Fetch64(s + len - 16)); + a += d; + do { + a ^= ShiftMix(Fetch64(s) * k1) * k1; + a *= k1; + b ^= a; + c ^= ShiftMix(Fetch64(s + 8) * k1) * k1; + c *= k1; + d ^= c; + s += 16; + l -= 16; + } while (l > 0); + } + a = HashLen16(a, c); + b = HashLen16(d, b); + return uint128(a ^ b, HashLen16(b, a)); +} + +uint128 CityHash128WithSeed(const char* s, size_t len, uint128 seed) { + if (len < 128) { + return CityMurmur(s, len, seed); + } + + // We expect len >= 128 to be the common case. Keep 56 bytes of state: + // v, w, x, y, and z. + pair v, w; + uint64 x = Uint128Low64(seed); + uint64 y = Uint128High64(seed); + uint64 z = len * k1; + v.first = Rotate(y ^ k1, 49) * k1 + Fetch64(s); + v.second = Rotate(v.first, 42) * k1 + Fetch64(s + 8); + w.first = Rotate(y + z, 35) * k1 + x; + w.second = Rotate(x + Fetch64(s + 88), 53) * k1; + + // This is the same inner loop as CityHash64(), manually unrolled. + do { + x = Rotate(x + y + v.first + Fetch64(s + 8), 37) * k1; + y = Rotate(y + v.second + Fetch64(s + 48), 42) * k1; + x ^= w.second; + y += v.first + Fetch64(s + 40); + z = Rotate(z + w.first, 33) * k1; + v = WeakHashLen32WithSeeds(s, v.second * k1, x + w.first); + w = WeakHashLen32WithSeeds(s + 32, z + w.second, y + Fetch64(s + 16)); + std::swap(z, x); + s += 64; + x = Rotate(x + y + v.first + Fetch64(s + 8), 37) * k1; + y = Rotate(y + v.second + Fetch64(s + 48), 42) * k1; + x ^= w.second; + y += v.first + Fetch64(s + 40); + z = Rotate(z + w.first, 33) * k1; + v = WeakHashLen32WithSeeds(s, v.second * k1, x + w.first); + w = WeakHashLen32WithSeeds(s + 32, z + w.second, y + Fetch64(s + 16)); + std::swap(z, x); + s += 64; + len -= 128; + } while (LIKELY(len >= 128)); + x += Rotate(v.first + z, 49) * k0; + y = y * k0 + Rotate(w.second, 37); + z = z * k0 + Rotate(w.first, 27); + w.first *= 9; + v.first *= k0; + // If 0 < len < 128, hash up to 4 chunks of 32 bytes each from the end of s. + for (size_t tail_done = 0; tail_done < len;) { + tail_done += 32; + y = Rotate(x + y, 42) * k0 + v.second; + w.first += Fetch64(s + len - tail_done + 16); + x = x * k0 + w.first; + z += w.second + Fetch64(s + len - tail_done); + w.second += v.first; + v = WeakHashLen32WithSeeds(s + len - tail_done, v.first + z, v.second); + v.first *= k0; + } + // At this point our 56 bytes of state should contain more than + // enough information for a strong 128-bit hash. We use two + // different 56-byte-to-8-byte hashes to get a 16-byte final result. + x = HashLen16(x, v.first); + y = HashLen16(y + z, w.first); + return uint128(HashLen16(x + v.second, w.second) + y, + HashLen16(x + w.second, y + v.second)); +} + +uint128 CityHash128(const char* s, size_t len) { + return len >= 16 + ? CityHash128WithSeed(s + 16, len - 16, + uint128(Fetch64(s), Fetch64(s + 8) + k0)) + : CityHash128WithSeed(s, len, uint128(k0, k1)); +} + +} // namespace cityhash_v111 +} // namespace internal +} // namespace base -- cgit v1.2.3