gh-93382: Cache result of `PyCode_GetCode` in codeobject (GH-93383)

Co-authored-by: Kumar Aditya <59607654+kumaraditya303@users.noreply.github.com>
Co-authored-by: Dennis Sweeney <36520290+sweeneyde@users.noreply.github.com>

diff --git a/Include/cpython/code.h b/Include/cpython/code.h
index ba7324b48d8675eeb51e3a8783236f695c5d12db..f544ea87406e250975d59fe9800df19c2de84d7b 100644 (file)
--- a/Include/cpython/code.h
+++ b/Include/cpython/code.h
@@ -88,6 +88,7 @@ typedef uint16_t _Py_CODEUNIT;
     PyObject *co_qualname;        /* unicode (qualname, for reference) */      \
     PyObject *co_linetable;       /* bytes object that holds location info */  \
     PyObject *co_weakreflist;     /* to support weakrefs to code objects */    \
+    void *_co_code;               /* cached co_code object/attribute */        \
     /* Scratch space for extra data relating to the code object.               \
        Type is a void* to keep the format private in codeobject.c to force     \
        people to go through the proper APIs. */                                \

diff --git a/Misc/NEWS.d/next/Core and Builtins/2022-05-31-16-36-30.gh-issue-93382.Jf6gAj.rst b/Misc/NEWS.d/next/Core and Builtins/2022-05-31-16-36-30.gh-issue-93382.Jf6gAj.rst
new file mode 100644 (file)
index 0000000..04b9e8b
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2022-05-31-16-36-30.gh-issue-93382.Jf6gAj.rst
@@ -0,0 +1 @@
+Speed up the :c:func:`PyCode_GetCode` function which also improves accessing the :attr:`~types.CodeType.co_code` attribute in Python.

diff --git a/Objects/codeobject.c b/Objects/codeobject.c
index 68b0b1efb2e14c4b35d761a2ec1807c208a741e9..dc6dec1b2a549bc6f15d1f213a600fdbf21ebf50 100644 (file)
--- a/Objects/codeobject.c
+++ b/Objects/codeobject.c
@@ -334,6 +334,7 @@ init_code(PyCodeObject *co, struct _PyCodeConstructor *con)
     /* not set */
     co->co_weakreflist = NULL;
     co->co_extra = NULL;
+    co->_co_code = NULL;
 
     co->co_warmup = QUICKENING_INITIAL_WARMUP_VALUE;
     memcpy(_PyCode_CODE(co), PyBytes_AS_STRING(con->code),
@@ -1367,12 +1368,17 @@ deopt_code(_Py_CODEUNIT *instructions, Py_ssize_t len)
 PyObject *
 _PyCode_GetCode(PyCodeObject *co)
 {
+    if (co->_co_code != NULL) {
+        return Py_NewRef(co->_co_code);
+    }
     PyObject *code = PyBytes_FromStringAndSize((const char *)_PyCode_CODE(co),
                                                _PyCode_NBYTES(co));
     if (code == NULL) {
         return NULL;
     }
     deopt_code((_Py_CODEUNIT *)PyBytes_AS_STRING(code), Py_SIZE(co));
+    assert(co->_co_code == NULL);
+    co->_co_code = (void *)Py_NewRef(code);
     return code;
 }
 
@@ -1531,6 +1537,7 @@ code_dealloc(PyCodeObject *co)
     Py_XDECREF(co->co_qualname);
     Py_XDECREF(co->co_linetable);
     Py_XDECREF(co->co_exceptiontable);
+    Py_XDECREF(co->_co_code);
     if (co->co_weakreflist != NULL) {
         PyObject_ClearWeakRefs((PyObject*)co);
     }

diff --git a/Objects/frameobject.c b/Objects/frameobject.c
index a448ba3a6c6f90a1e1a821530b67c55019f2c514..545c1b6b90f1a8344eaa14c7471b2aa55762471b 100644 (file)
--- a/Objects/frameobject.c
+++ b/Objects/frameobject.c
@@ -458,22 +458,30 @@ _PyFrame_GetState(PyFrameObject *frame)
 static void
 add_load_fast_null_checks(PyCodeObject *co)
 {
+    int changed = 0;
     _Py_CODEUNIT *instructions = _PyCode_CODE(co);
     for (Py_ssize_t i = 0; i < Py_SIZE(co); i++) {
         switch (_Py_OPCODE(instructions[i])) {
             case LOAD_FAST:
             case LOAD_FAST__LOAD_FAST:
             case LOAD_FAST__LOAD_CONST:
+                changed = 1;
                 _Py_SET_OPCODE(instructions[i], LOAD_FAST_CHECK);
                 break;
             case LOAD_CONST__LOAD_FAST:
+                changed = 1;
                 _Py_SET_OPCODE(instructions[i], LOAD_CONST);
                 break;
             case STORE_FAST__LOAD_FAST:
+                changed = 1;
                 _Py_SET_OPCODE(instructions[i], STORE_FAST);
                 break;
         }
     }
+    if (changed) {
+        // invalidate cached co_code object
+        Py_CLEAR(co->_co_code);
+    }
 }
 
 /* Setter for f_lineno - you can set f_lineno from within a trace function in

diff --git a/Programs/test_frozenmain.h b/Programs/test_frozenmain.h
index e6e2ef26b1c373b78088fa721bb72d12e1d2c16f..8d4ba94bd76ee0d4d7318cebf42b70d1325516a2 100644 (file)
--- a/Programs/test_frozenmain.h
+++ b/Programs/test_frozenmain.h
@@ -1,7 +1,7 @@
 // Auto-generated by Programs/freeze_test_frozenmain.py
 unsigned char M_test_frozenmain[] = {
     227,0,0,0,0,0,0,0,0,0,0,0,0,8,0,0,
-    0,0,0,0,0,115,160,0,0,0,151,0,100,0,100,1,
+    0,0,0,0,0,243,160,0,0,0,151,0,100,0,100,1,
     108,0,90,0,100,0,100,1,108,1,90,1,2,0,101,2,
     100,2,171,1,0,0,0,0,0,0,0,0,1,0,2,0,
     101,2,100,3,101,0,106,3,0,0,0,0,0,0,0,0,
@@ -23,10 +23,10 @@ unsigned char M_test_frozenmain[] = {
     32,122,2,58,32,41,7,218,3,115,121,115,218,17,95,116,
     101,115,116,105,110,116,101,114,110,97,108,99,97,112,105,218,
     5,112,114,105,110,116,218,4,97,114,103,118,218,11,103,101,
-    116,95,99,111,110,102,105,103,115,114,2,0,0,0,218,3,
+    116,95,99,111,110,102,105,103,115,114,3,0,0,0,218,3,
     107,101,121,169,0,243,0,0,0,0,250,18,116,101,115,116,
     95,102,114,111,122,101,110,109,97,105,110,46,112,121,250,8,
-    60,109,111,100,117,108,101,62,114,17,0,0,0,1,0,0,
+    60,109,111,100,117,108,101,62,114,18,0,0,0,1,0,0,
     0,115,140,0,0,0,248,240,6,0,1,11,128,10,128,10,
     128,10,216,0,24,208,0,24,208,0,24,208,0,24,224,0,
     5,128,5,208,6,26,212,0,27,208,0,27,216,0,5,128,
@@ -36,5 +36,5 @@ unsigned char M_test_frozenmain[] = {
     67,240,14,0,5,10,128,69,208,10,40,144,67,208,10,40,
     208,10,40,152,54,160,35,156,59,208,10,40,208,10,40,212,
     4,41,208,4,41,208,4,41,240,15,7,1,42,240,0,7,
-    1,42,114,15,0,0,0,
+    1,42,114,16,0,0,0,
 };