Fix the internals of our hash functions to used unsigned values during hash
computation as the overflow behavior of signed integers is undefined.
In practice we require compiling everything with -fwrapv which forces overflow
to be defined as twos compliment but this keeps the code cleaner for checkers
or in the case where someone has compiled it without -fwrapv or their
compiler's equivalent.
Found by Clang trunk's Undefined Behavior Sanitizer (UBSan).
Cleanup only - no functionality or hash values change.
diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index 796e400..ef3a5a1 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -873,7 +873,7 @@
{
register Py_ssize_t len;
register unsigned char *p;
- register Py_hash_t x;
+ register Py_uhash_t x; /* Unsigned for defined overflow behavior. */
#ifdef Py_DEBUG
assert(_Py_HashSecret_Initialized);
diff --git a/Objects/setobject.c b/Objects/setobject.c
index 3abeefb..d8401f4 100644
--- a/Objects/setobject.c
+++ b/Objects/setobject.c
@@ -77,7 +77,7 @@
static setentry *
set_lookkey(PySetObject *so, PyObject *key, register Py_hash_t hash)
{
- register Py_ssize_t i;
+ register size_t i; /* Unsigned for defined overflow behavior. */
register size_t perturb;
register setentry *freeslot;
register size_t mask = so->mask;
@@ -159,7 +159,7 @@
static setentry *
set_lookkey_unicode(PySetObject *so, PyObject *key, register Py_hash_t hash)
{
- register Py_ssize_t i;
+ register size_t i; /* Unsigned for defined overflow behavior. */
register size_t perturb;
register setentry *freeslot;
register size_t mask = so->mask;
@@ -768,7 +768,7 @@
frozenset_hash(PyObject *self)
{
PySetObject *so = (PySetObject *)self;
- Py_hash_t h, hash = 1927868237L;
+ Py_uhash_t h, hash = 1927868237UL;
setentry *entry;
Py_ssize_t pos = 0;
@@ -783,11 +783,11 @@
hashes so that many distinct combinations collapse to only
a handful of distinct hash values. */
h = entry->hash;
- hash ^= (h ^ (h << 16) ^ 89869747L) * 3644798167u;
+ hash ^= (h ^ (h << 16) ^ 89869747UL) * 3644798167UL;
}
- hash = hash * 69069L + 907133923L;
+ hash = hash * 69069UL + 907133923UL;
if (hash == -1)
- hash = 590923713L;
+ hash = 590923713UL;
so->hash = hash;
return hash;
}
diff --git a/Objects/tupleobject.c b/Objects/tupleobject.c
index b345460..c725227 100644
--- a/Objects/tupleobject.c
+++ b/Objects/tupleobject.c
@@ -315,11 +315,11 @@
static Py_hash_t
tuplehash(PyTupleObject *v)
{
- register Py_hash_t x, y;
+ register Py_uhash_t x, y; /* Unsigned for defined overflow behavior. */
register Py_ssize_t len = Py_SIZE(v);
register PyObject **p;
- Py_hash_t mult = _PyHASH_MULTIPLIER;
- x = 0x345678L;
+ Py_uhash_t mult = _PyHASH_MULTIPLIER;
+ x = 0x345678UL;
p = v->ob_item;
while (--len >= 0) {
y = PyObject_Hash(*p++);
@@ -327,9 +327,9 @@
return -1;
x = (x ^ y) * mult;
/* the cast might truncate len; that doesn't change hash stability */
- mult += (Py_hash_t)(82520L + len + len);
+ mult += (Py_uhash_t)(82520UL + len + len);
}
- x += 97531L;
+ x += 97531UL;
if (x == -1)
x = -2;
return x;
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 565d298..bb45b20 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -7686,7 +7686,7 @@
{
Py_ssize_t len;
Py_UNICODE *p;
- Py_hash_t x;
+ Py_uhash_t x; /* Unsigned for defined overflow behavior. */
#ifdef Py_DEBUG
assert(_Py_HashSecret_Initialized);