Do unsigned cast from PInt to Java long for hashes

Author: fangerer

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/objects/PythonAbstractObject.java

@@ -133,6 +133,7 @@
 import com.oracle.graal.python.nodes.util.CastToJavaLongExactNode;
 import com.oracle.graal.python.nodes.util.CastToJavaLongLossyNode;
 import com.oracle.graal.python.nodes.util.CastToJavaStringNode;
+import com.oracle.graal.python.nodes.util.CastUnsignedToJavaLongNode;
 import com.oracle.graal.python.runtime.PythonContext;
 import com.oracle.graal.python.runtime.PythonOptions;
 import com.oracle.graal.python.runtime.exception.PException;
@@ -771,7 +772,7 @@ public long hashWithState(ThreadState state,
                     @Shared("methodLib") @CachedLibrary(limit = "2") PythonObjectLibrary methodLib,
                     @Cached LookupInheritedAttributeNode.Dynamic lookupGet,
                     @Shared("raise") @Cached PRaiseNode raise,
-                    @Exclusive @Cached CastToJavaLongExactNode castToLong) {
+                    @Exclusive @Cached CastUnsignedToJavaLongNode castUnsignedToJavaLongNode) {
         Object hashMethod = lib.lookupAttributeOnType(this, __HASH__);
         if (!methodLib.isCallable(hashMethod) && lookupGet.execute(hashMethod, __GET__) == PNone.NO_VALUE) {
             throw raise.raise(PythonBuiltinClassType.TypeError, ErrorMessages.UNHASHABLE_TYPE, this);
@@ -780,7 +781,7 @@ public long hashWithState(ThreadState state,
         // see PyObject_GetHash and slot_tp_hash in CPython. The result of the
         // hash call is always a plain long, forcibly and lossy read from memory.
         try {
-            return castToLong.execute(result);
+            return castUnsignedToJavaLongNode.execute(result);
         } catch (CannotCastException e) {
             throw raise.raise(PythonBuiltinClassType.TypeError, ErrorMessages.HASH_SHOULD_RETURN_INTEGER);
         }

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/nodes/util/CastUnsignedToJavaLongNode.java

@@ -0,0 +1,82 @@
+/*
+ * Copyright (c) 2020, Oracle and/or its affiliates. All rights reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * The Universal Permissive License (UPL), Version 1.0
+ *
+ * Subject to the condition set forth below, permission is hereby granted to any
+ * person obtaining a copy of this software, associated documentation and/or
+ * data (collectively the "Software"), free of charge and under any and all
+ * copyright rights in the Software, and any and all patent rights owned or
+ * freely licensable by each licensor hereunder covering either (i) the
+ * unmodified Software as contributed to or provided by such licensor, or (ii)
+ * the Larger Works (as defined below), to deal in both
+ *
+ * (a) the Software, and
+ *
+ * (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+ * one is included with the Software each a "Larger Work" to which the Software
+ * is contributed by such licensors),
+ *
+ * without restriction, including without limitation the rights to copy, create
+ * derivative works of, display, perform, and distribute the Software and make,
+ * use, sell, offer for sale, import, export, have made, and have sold the
+ * Software and the Larger Work(s), and to sublicense the foregoing rights on
+ * either these or other terms.
+ *
+ * This license is subject to the following condition:
+ *
+ * The above copyright notice and either this complete permission notice or at a
+ * minimum a reference to the UPL must 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.
+ */
+package com.oracle.graal.python.nodes.util;
+
+import static com.oracle.graal.python.builtins.PythonBuiltinClassType.OverflowError;
+
+import com.oracle.graal.python.builtins.objects.ints.PInt;
+import com.oracle.graal.python.nodes.ErrorMessages;
+import com.oracle.graal.python.nodes.PRaiseNode;
+import com.oracle.graal.python.util.OverflowException;
+import com.oracle.truffle.api.dsl.Cached;
+import com.oracle.truffle.api.dsl.GenerateUncached;
+import com.oracle.truffle.api.dsl.Specialization;
+
+/**
+ * Casts a Python integer to a Java long without coercion. The difference to
+ * {@link CastToJavaLongExactNode} is that if a {@link PInt} is larger than
+ * {@link Integer#MAX_VALUE} but still just requires 64-bits, we will still to the cast resulting in
+ * a negative Java long. This is useful for hash functions where the sign bit does not really matter
+ * but just the bits.
+ * 
+ * <b>ATTENTION:</b> If the cast isn't possible, the node will throw a {@link CannotCastException}.
+ */
+@GenerateUncached
+public abstract class CastUnsignedToJavaLongNode extends CastToJavaLongNode {
+
+    @Specialization(rewriteOn = OverflowException.class, insertBefore = "doNativeObject")
+    static long toLongNoOverflow(PInt x) throws OverflowException {
+        return x.longValueExact();
+    }
+
+    @Specialization(replaces = "toLongNoOverflow", insertBefore = "doNativeObject")
+    static long toLong(PInt x,
+                    @Cached PRaiseNode raiseNode) {
+        try {
+            return x.longValueExact();
+        } catch (OverflowException e) {
+            if (x.isZeroOrPositive() && x.bitLength() <= 64) {
+                return x.longValue();
+            }
+            throw raiseNode.raise(OverflowError, ErrorMessages.PYTHON_INT_TOO_LARGE_TO_CONV_TO, "long");
+        }
+    }
+}