python源码阅读笔记之函数的运行机制

函数这个对象的实现由如下：
typedef struct {
    PyObject_HEAD
    PyObject *func_code;    /* A code object */
    PyObject *func_globals;    /* A dictionary (other mappings won't do) */
    PyObject *func_defaults;    /* NULL or a tuple */
    PyObject *func_closure;    /* NULL or a tuple of cell objects */
    PyObject *func_doc;        /* The __doc__ attribute, can be anything */
    PyObject *func_name;    /* The __name__ attribute, a string object */
    PyObject *func_dict;    /* The __dict__ attribute, a dict or NULL */
    PyObject *func_weakreflist;    /* List of weak references */
    PyObject *func_module;    /* The __module__ attribute, can be anything */

    /* Invariant:
     *     func_closure contains the bindings for func_code->co_freevars, so
     *     PyTuple_Size(func_closure) == PyCode_GetNumFree(func_code)
     *     (func_closure may be NULL if PyCode_GetNumFree(func_code) == 0).
     */
} PyFunctionObject;

这个与之前的区别在于：
这个对象的指针可以关联到与之相关的PyCodeObject，通过func_code

使用dis函数可看到：
a = "def f(): \
       print('sf')"
dis.dis(a)
  1           0 LOAD_CONST               0 (<code object f at 0x00000225C8A9E1E0, file "<dis>", line 1>)
              3 LOAD_CONST               1 ('f')
              6 MAKE_FUNCTION            0
              9 STORE_NAME               0 (f)
             12 LOAD_CONST               2 (None)
             15 RETURN_VALUE
 
从上述的字节码中，注意到没，函数的声明和实现是分离的

从MAKE_FUNCTION看出：
        case MAKE_FUNCTION:
            v = POP(); /* code object */
            x = PyFunction_New(v, f->f_globals);
            Py_DECREF(v);
            if (x != NULL && oparg > 0) {
                v = PyTuple_New(oparg);
                if (v == NULL) {
                    Py_DECREF(x);
                    x = NULL;
                    break;
                }
                while (--oparg >= 0) {
                    w = POP();
                    PyTuple_SET_ITEM(v, oparg, w);
                }
                err = PyFunction_SetDefaults(x, v);
                Py_DECREF(v);
            }
            PUSH(x);
            break;
简单解释下，将函数f对应的PyCodeObject对象从运行时栈弹出，以当前维护的名字空间f_globals为参数，
通过PyFunction_New，创建新的对象。最后再压入运行时栈
PyObject *
PyFunction_New(PyObject *code, PyObject *globals)
{
    PyFunctionObject *op = PyObject_GC_New(PyFunctionObject,
                                        &PyFunction_Type);
    static PyObject *__name__ = 0;
    if (op != NULL) {
        PyObject *doc;
        PyObject *consts;
        PyObject *module;
        op->func_weakreflist = NULL;
        Py_INCREF(code);
        op->func_code = code;
        Py_INCREF(globals);
        op->func_globals = globals;
        op->func_name = ((PyCodeObject *)code)->co_name;
        Py_INCREF(op->func_name);
        op->func_defaults = NULL; /* No default arguments */
        op->func_closure = NULL;
        consts = ((PyCodeObject *)code)->co_consts;
        if (PyTuple_Size(consts) >= 1) {
            doc = PyTuple_GetItem(consts, 0);
            if (!PyString_Check(doc) && !PyUnicode_Check(doc))
                doc = Py_None;
        }
        else
            doc = Py_None;
        Py_INCREF(doc);
        op->func_doc = doc;
        op->func_dict = NULL;
        op->func_module = NULL;

        /* __module__: If module name is in globals, use it.
           Otherwise, use None.
        */
        if (!__name__) {
            __name__ = PyString_InternFromString("__name__");
            if (!__name__) {
                Py_DECREF(op);
                return NULL;
            }
        }
        module = PyDict_GetItem(globals, __name__);
        if (module) {
            Py_INCREF(module);
            op->func_module = module;
        }
    }
    else
        return NULL;
    _PyObject_GC_TRACK(op);
    return (PyObject *)op;
}

现在看看函数的调用
case CALL_FUNCTION:
        {
            PyObject **sp;
            PCALL(PCALL_ALL);
            sp = stack_pointer;
#ifdef WITH_TSC
            x = call_function(&sp, oparg, &intr0, &intr1);
#else
            x = call_function(&sp, oparg);
#endif
            stack_pointer = sp;
            PUSH(x);
            if (x != NULL)
                continue;
            break;
        }
在拿到栈顶指针后，直接使用了call_function
static PyObject *
call_function(PyObject ***pp_stack, int oparg
#ifdef WITH_TSC
                , uint64* pintr0, uint64* pintr1
#endif
                )
{
    int na = oparg & 0xff;/*神奇的位运算操作，这里的指令参数的长度是两个字节，低字节记录着位置参数的个数，
    高字节记录着键参数的个数。na*/
    int nk = (oparg>>8) & 0xff;
    int n = na + 2 * nk;/*这个参数与回退到运行时栈的核心*/
    PyObject **pfunc = (*pp_stack) - n - 1;
    PyObject *func = *pfunc;
    PyObject *x, *w;

    /* Always dispatch PyCFunction first, because these are
       presumed to be the most frequent callable object.
    */
    if (PyCFunction_Check(func) && nk == 0) {
        int flags = PyCFunction_GET_FLAGS(func);
        PyThreadState *tstate = PyThreadState_GET();

        PCALL(PCALL_CFUNCTION);
        if (flags & (METH_NOARGS | METH_O)) {
            PyCFunction meth = PyCFunction_GET_FUNCTION(func);
            PyObject *self = PyCFunction_GET_SELF(func);
            if (flags & METH_NOARGS && na == 0) {
                C_TRACE(x, (*meth)(self,NULL));
            }
            else if (flags & METH_O && na == 1) {
                PyObject *arg = EXT_POP(*pp_stack);
                C_TRACE(x, (*meth)(self,arg));
                Py_DECREF(arg);
            }
            else {
                err_args(func, flags, na);
                x = NULL;
            }
        }
        else {
            PyObject *callargs;
            callargs = load_args(pp_stack, na);
            READ_TIMESTAMP(*pintr0);
            C_TRACE(x, PyCFunction_Call(func,callargs,NULL));
            READ_TIMESTAMP(*pintr1);
            Py_XDECREF(callargs);
        }
    } else {
        if (PyMethod_Check(func) && PyMethod_GET_SELF(func) != NULL) {
            /* optimize access to bound methods */
            PyObject *self = PyMethod_GET_SELF(func);
            PCALL(PCALL_METHOD);
            PCALL(PCALL_BOUND_METHOD);
            Py_INCREF(self);
            func = PyMethod_GET_FUNCTION(func);
            Py_INCREF(func);
            Py_DECREF(*pfunc);
            *pfunc = self;
            na++;
            n++;
        } else
            Py_INCREF(func);
        READ_TIMESTAMP(*pintr0);
        if (PyFunction_Check(func))
            x = fast_function(func, pp_stack, n, na, nk);
        else
            x = do_call(func, pp_stack, na, nk);
        READ_TIMESTAMP(*pintr1);
        Py_DECREF(func);
    }

    /* Clear the stack of the function object.  Also removes
       the arguments in case they weren't consumed already
       (fast_function() and err_args() leave them on the stack).
     */
    while ((*pp_stack) > pfunc) {
        w = EXT_POP(*pp_stack);
        Py_DECREF(w);
        PCALL(PCALL_POP);
    }
    return x;
}
 
这里的运行实际是将栈中的代码实现，实际上和平常运行的表达式没什么两样
从无参函数的fast_function可以看出：
static PyObject *
fast_function(PyObject *func, PyObject ***pp_stack, int n, int na, int nk)
{
    PyCodeObject *co = (PyCodeObject *)PyFunction_GET_CODE(func);
    PyObject *globals = PyFunction_GET_GLOBALS(func);
    PyObject *argdefs = PyFunction_GET_DEFAULTS(func);
    PyObject **d = NULL;
    int nd = 0;

    PCALL(PCALL_FUNCTION);
    PCALL(PCALL_FAST_FUNCTION);
    if (argdefs == NULL && co->co_argcount == n && nk==0 &&
        co->co_flags == (CO_OPTIMIZED | CO_NEWLOCALS | CO_NOFREE)) {
        PyFrameObject *f;
        PyObject *retval = NULL;
        PyThreadState *tstate = PyThreadState_GET();
        PyObject **fastlocals, **stack;
        int i;

        PCALL(PCALL_FASTER_FUNCTION);
        assert(globals != NULL);
        /* XXX Perhaps we should create a specialized
           PyFrame_New() that doesn't take locals, but does
           take builtins without sanity checking them.
        */
        assert(tstate != NULL);
        f = PyFrame_New(tstate, co, globals, NULL);
        if (f == NULL)
            return NULL;

        fastlocals = f->f_localsplus;
        stack = (*pp_stack) - n;

        for (i = 0; i < n; i++) {
            Py_INCREF(*stack);
            fastlocals[i] = *stack++;
        }
        retval = PyEval_EvalFrameEx(f,0);
        ++tstate->recursion_depth;
        Py_DECREF(f);
        --tstate->recursion_depth;
        return retval;
    }
    if (argdefs != NULL) {
        d = &PyTuple_GET_ITEM(argdefs, 0);
        nd = Py_SIZE(argdefs);
    }
    return PyEval_EvalCodeEx(co, globals,
                             (PyObject *)NULL, (*pp_stack)-n, na,
                             (*pp_stack)-2*nk, nk, d, nd,
                             PyFunction_GET_CLOSURE(func));
}

一个比较好玩的一点是，在C语言中函数是否被调用，取决于函数出现的位置，但是在python中则是名字空间


在这里有四种函数参数：
1.位置参数
2.键参数
3.扩展位置参数，传入的是列表
4.扩展键参数，传入的是字典