Use SipHash-1-3 instead of SipHash-2-4.

methane · methane · commit de12cebee17c · 2021-10-06T14:21:50.000+09:00
diff --git a/Include/pyhash.h b/Include/pyhash.h
@@ -114,24 +114,24 @@ PyAPI_FUNC(PyHash_FuncDef*) PyHash_GetFuncDef(void);
 
 /* hash algorithm selection
  *
- * The values for Py_HASH_SIPHASH24 and Py_HASH_FNV are hard-coded in the
+ * The values for Py_HASH_SIPHASH13 and Py_HASH_FNV are hard-coded in the
  * configure script.
  *
  * - FNV is available on all platforms and architectures.
- * - SIPHASH24 only works on platforms that don't require aligned memory for integers.
+ * - SIPHASH only works on platforms that don't require aligned memory for integers.
  * - With EXTERNAL embedders can provide an alternative implementation with::
  *
  *     PyHash_FuncDef PyHash_Func = {...};
  *
  * XXX: Figure out __declspec() for extern PyHash_FuncDef.
  */
 #define Py_HASH_EXTERNAL 0
-#define Py_HASH_SIPHASH24 1
+#define Py_HASH_SIPHASH 1
 #define Py_HASH_FNV 2
 
 #ifndef Py_HASH_ALGORITHM
 #  ifndef HAVE_ALIGNED_REQUIRED
-#    define Py_HASH_ALGORITHM Py_HASH_SIPHASH24
+#    define Py_HASH_ALGORITHM Py_HASH_SIPHASH
 #  else
 #    define Py_HASH_ALGORITHM Py_HASH_FNV
 #  endif /* uint64_t && uint32_t && aligned */
diff --git a/Python/pyhash.c b/Python/pyhash.c
@@ -364,15 +364,13 @@ static PyHash_FuncDef PyHash_Func = {fnv, "fnv", 8 * SIZEOF_PY_HASH_T,
     d = ROTATE(d, t) ^ c;           \
     a = ROTATE(a, 32);
 
-#define DOUBLE_ROUND(v0,v1,v2,v3)       \
-    HALF_ROUND(v0,v1,v2,v3,13,16);      \
-    HALF_ROUND(v2,v1,v0,v3,17,21);      \
+#define SINGLE_ROUND(v0,v1,v2,v3)       \
     HALF_ROUND(v0,v1,v2,v3,13,16);      \
     HALF_ROUND(v2,v1,v0,v3,17,21);
 
 
 static uint64_t
-siphash24(uint64_t k0, uint64_t k1, const void *src, Py_ssize_t src_sz) {
+siphash13(uint64_t k0, uint64_t k1, const void *src, Py_ssize_t src_sz) {
     uint64_t b = (uint64_t)src_sz << 56;
     const uint8_t *in = (const uint8_t*)src;
 
@@ -391,7 +389,7 @@ siphash24(uint64_t k0, uint64_t k1, const void *src, Py_ssize_t src_sz) {
         in += sizeof(mi);
         src_sz -= sizeof(mi);
         v3 ^= mi;
-        DOUBLE_ROUND(v0,v1,v2,v3);
+        SINGLE_ROUND(v0,v1,v2,v3);
         v0 ^= mi;
     }
 
@@ -409,11 +407,12 @@ siphash24(uint64_t k0, uint64_t k1, const void *src, Py_ssize_t src_sz) {
     b |= _le64toh(t);
 
     v3 ^= b;
-    DOUBLE_ROUND(v0,v1,v2,v3);
+    SINGLE_ROUND(v0,v1,v2,v3);
     v0 ^= b;
     v2 ^= 0xff;
-    DOUBLE_ROUND(v0,v1,v2,v3);
-    DOUBLE_ROUND(v0,v1,v2,v3);
+    SINGLE_ROUND(v0,v1,v2,v3);
+    SINGLE_ROUND(v0,v1,v2,v3);
+    SINGLE_ROUND(v0,v1,v2,v3);
 
     /* modified */
     t = (v0 ^ v1) ^ (v2 ^ v3);
@@ -423,19 +422,19 @@ siphash24(uint64_t k0, uint64_t k1, const void *src, Py_ssize_t src_sz) {
 uint64_t
 _Py_KeyedHash(uint64_t key, const void *src, Py_ssize_t src_sz)
 {
-    return siphash24(key, 0, src, src_sz);
+    return siphash13(key, 0, src, src_sz);
 }
 
 
-#if Py_HASH_ALGORITHM == Py_HASH_SIPHASH24
+#if Py_HASH_ALGORITHM == Py_HASH_SIPHASH
 static Py_hash_t
 pysiphash(const void *src, Py_ssize_t src_sz) {
-    return (Py_hash_t)siphash24(
+    return (Py_hash_t)siphash13(
         _le64toh(_Py_HashSecret.siphash.k0), _le64toh(_Py_HashSecret.siphash.k1),
         src, src_sz);
 }
 
-static PyHash_FuncDef PyHash_Func = {pysiphash, "siphash24", 64, 128};
+static PyHash_FuncDef PyHash_Func = {pysiphash, "siphash13", 64, 128};
 #endif
 
 #ifdef __cplusplus
diff --git a/configure.ac b/configure.ac
@@ -3036,17 +3036,17 @@ fi
 # str, bytes and memoryview hash algorithm
 AH_TEMPLATE(Py_HASH_ALGORITHM,
   [Define hash algorithm for str, bytes and memoryview.
-   SipHash24: 1, FNV: 2, externally defined: 0])
+   SipHash: 1, FNV: 2, externally defined: 0])
 
 AC_MSG_CHECKING(for --with-hash-algorithm)
 dnl quadrigraphs "@<:@" and "@:>@" produce "[" and "]" in the output
 AC_ARG_WITH(hash_algorithm,
-            AS_HELP_STRING([--with-hash-algorithm=@<:@fnv|siphash24@:>@],
-                           [select hash algorithm for use in Python/pyhash.c (default is SipHash24)]),
+            AS_HELP_STRING([--with-hash-algorithm=@<:@fnv|siphash@:>@],
+                           [select hash algorithm for use in Python/pyhash.c (default is SipHash)]),
 [
 AC_MSG_RESULT($withval)
 case "$withval" in
-    siphash24)
+    siphash)
         AC_DEFINE(Py_HASH_ALGORITHM, 1)
         ;;
     fnv)
