/* Execute compiled code */

/* XXX TO DO:

   XXX speed up searching for keywords by using a dictionary

   XXX document it!

   */

/* enable more aggressive intra-module optimizations, where available */

#define PY_LOCAL_AGGRESSIVE

#include "Python.h"

#include "code.h"

#include "frameobject.h"

#include "eval.h"

#include "opcode.h"

#include "structmember.h"

#include <ctype.h>

#ifndef WITH_TSC

#define READ_TIMESTAMP(var)

#else

typedef unsigned long long uint64;

#if defined(__ppc__) /* <- Don't know if this is the correct symbol; this

			   section should work for GCC on any PowerPC

			   platform, irrespective of OS.

			   POWER?  Who knows :-) */

#define READ_TIMESTAMP(var) ppc_getcounter(&var)

static void

ppc_getcounter(uint64 *v)

{

	register unsigned long tbu, tb, tbu2;

  loop:

	asm volatile ("mftbu %0" : "=r" (tbu) );

	asm volatile ("mftb  %0" : "=r" (tb)  );

	asm volatile ("mftbu %0" : "=r" (tbu2));

	if (__builtin_expect(tbu != tbu2, 0)) goto loop;

	/* The slightly peculiar way of writing the next lines is

	   compiled better by GCC than any other way I tried. */

	((long*)(v))[0] = tbu;

	((long*)(v))[1] = tb;

}

#else /* this is for linux/x86 (and probably any other GCC/x86 combo) */

#define READ_TIMESTAMP(val) \

     __asm__ __volatile__("rdtsc" : "=A" (val))

#endif

void dump_tsc(int opcode, int ticked, uint64 inst0, uint64 inst1,

	      uint64 loop0, uint64 loop1, uint64 intr0, uint64 intr1)

{

	uint64 intr, inst, loop;

	PyThreadState *tstate = PyThreadState_Get();

	if (!tstate->interp->tscdump)

		return;

	intr = intr1 - intr0;

	inst = inst1 - inst0 - intr;

	loop = loop1 - loop0 - intr;

	fprintf(stderr, "opcode=%03d t=%d inst=%06lld loop=%06lld\n",

		opcode, ticked, inst, loop);

}

#endif

/* Turn this on if your compiler chokes on the big switch: */

/* #define CASE_TOO_BIG 1 */

#ifdef Py_DEBUG

/* For debugging the interpreter: */

#define LLTRACE  1	/* Low-level trace feature */

#define CHECKEXC 1	/* Double-check exception checking */

#endif

typedef PyObject *(*callproc)(PyObject *, PyObject *, PyObject *);

/* Forward declarations */

#ifdef WITH_TSC

static PyObject * call_function(PyObject ***, int, uint64*, uint64*);

#else

static PyObject * call_function(PyObject ***, int);

#endif

static PyObject * fast_function(PyObject *, PyObject ***, int, int, int);

static PyObject * do_call(PyObject *, PyObject ***, int, int);

static PyObject * ext_do_call(PyObject *, PyObject ***, int, int, int);

static PyObject * update_keyword_args(PyObject *, int, PyObject ***,

				      PyObject *);

static PyObject * update_star_args(int, int, PyObject *, PyObject ***);

static PyObject * load_args(PyObject ***, int);

#define CALL_FLAG_VAR 1

#define CALL_FLAG_KW 2

#ifdef LLTRACE

static int lltrace;

static int prtrace(PyObject *, char *);

#endif

static int call_trace(Py_tracefunc, PyObject *, PyFrameObject *,

		      int, PyObject *);

static int call_trace_protected(Py_tracefunc, PyObject *,

				 PyFrameObject *, int, PyObject *);

static void call_exc_trace(Py_tracefunc, PyObject *, PyFrameObject *);

static int maybe_call_line_trace(Py_tracefunc, PyObject *,

				  PyFrameObject *, int *, int *, int *);

static PyObject * apply_slice(PyObject *, PyObject *, PyObject *);

static int assign_slice(PyObject *, PyObject *,

			PyObject *, PyObject *);

static PyObject * cmp_outcome(int, PyObject *, PyObject *);

static PyObject * import_from(PyObject *, PyObject *);

static int import_all_from(PyObject *, PyObject *);

static PyObject * build_class(PyObject *, PyObject *, PyObject *);

static int exec_statement(PyFrameObject *,

			  PyObject *, PyObject *, PyObject *);

static void set_exc_info(PyThreadState *, PyObject *, PyObject *, PyObject *);

static void reset_exc_info(PyThreadState *);

static void format_exc_check_arg(PyObject *, char *, PyObject *);

static PyObject * string_concatenate(PyObject *, PyObject *,

				    PyFrameObject *, unsigned char *);

#define NAME_ERROR_MSG \

	"name '%.200s' is not defined"

#define GLOBAL_NAME_ERROR_MSG \

	"global name '%.200s' is not defined"

#define UNBOUNDLOCAL_ERROR_MSG \

	"local variable '%.200s' referenced before assignment"

#define UNBOUNDFREE_ERROR_MSG \

	"free variable '%.200s' referenced before assignment" \

        " in enclosing scope"

/* Dynamic execution profile */

#ifdef DYNAMIC_EXECUTION_PROFILE

#ifdef DXPAIRS

static long dxpairs[257][256];

#define dxp dxpairs[256]

#else

static long dxp[256];

#endif

#endif

/* Function call profile */

#ifdef CALL_PROFILE

#define PCALL_NUM 11

static int pcall[PCALL_NUM];

#define PCALL_ALL 0

#define PCALL_FUNCTION 1

#define PCALL_FAST_FUNCTION 2

#define PCALL_FASTER_FUNCTION 3

#define PCALL_METHOD 4

#define PCALL_BOUND_METHOD 5

#define PCALL_CFUNCTION 6

#define PCALL_TYPE 7

#define PCALL_GENERATOR 8

#define PCALL_OTHER 9

#define PCALL_POP 10

/* Notes about the statistics

   PCALL_FAST stats

   FAST_FUNCTION means no argument tuple needs to be created.

   FASTER_FUNCTION means that the fast-path frame setup code is used.

   If there is a method call where the call can be optimized by changing

   the argument tuple and calling the function directly, it gets recorded

   twice.

   As a result, the relationship among the statistics appears to be

   PCALL_ALL == PCALL_FUNCTION + PCALL_METHOD - PCALL_BOUND_METHOD +

                PCALL_CFUNCTION + PCALL_TYPE + PCALL_GENERATOR + PCALL_OTHER

   PCALL_FUNCTION > PCALL_FAST_FUNCTION > PCALL_FASTER_FUNCTION

   PCALL_METHOD > PCALL_BOUND_METHOD

*/

#define PCALL(POS) pcall[POS]++

PyObject *

PyEval_GetCallStats(PyObject *self)

{

	return Py_BuildValue("iiiiiiiiiii",

			     pcall[0], pcall[1], pcall[2], pcall[3],

			     pcall[4], pcall[5], pcall[6], pcall[7],

			     pcall[8], pcall[9], pcall[10]);

}

#else

#define PCALL(O)

PyObject *

PyEval_GetCallStats(PyObject *self)

{

	Py_INCREF(Py_None);

	return Py_None;

}

#endif

#ifdef WITH_THREAD

#ifdef HAVE_ERRNO_H

#include <errno.h>

#endif

#include "pythread.h"

static PyThread_type_lock interpreter_lock = 0; /* This is the GIL */

static long main_thread = 0;

int

PyEval_ThreadsInitialized(void)

{

	return interpreter_lock != 0;

}

void

PyEval_InitThreads(void)

{

	if (interpreter_lock)

		return;

	interpreter_lock = PyThread_allocate_lock();

	PyThread_acquire_lock(interpreter_lock, 1);

	main_thread = PyThread_get_thread_ident();

}

void

PyEval_AcquireLock(void)

{

	PyThread_acquire_lock(interpreter_lock, 1);

}

void

PyEval_ReleaseLock(void)

{

	PyThread_release_lock(interpreter_lock);

}

void

PyEval_AcquireThread(PyThreadState *tstate)

{

	if (tstate == NULL)

		Py_FatalError("PyEval_AcquireThread: NULL new thread state");

	/* Check someone has called PyEval_InitThreads() to create the lock */

	assert(interpreter_lock);

	PyThread_acquire_lock(interpreter_lock, 1);

	if (PyThreadState_Swap(tstate) != NULL)

		Py_FatalError(

			"PyEval_AcquireThread: non-NULL old thread state");

}

void

PyEval_ReleaseThread(PyThreadState *tstate)

{

	if (tstate == NULL)

		Py_FatalError("PyEval_ReleaseThread: NULL thread state");

	if (PyThreadState_Swap(NULL) != tstate)

		Py_FatalError("PyEval_ReleaseThread: wrong thread state");

	PyThread_release_lock(interpreter_lock);

}

/* This function is called from PyOS_AfterFork to ensure that newly

   created child processes don't hold locks referring to threads which

   are not running in the child process.  (This could also be done using

   pthread_atfork mechanism, at least for the pthreads implementation.) */

void

PyEval_ReInitThreads(void)

{

	PyObject *threading, *result;

	PyThreadState *tstate;

	if (!interpreter_lock)

		return;

	/*XXX Can't use PyThread_free_lock here because it does too

	  much error-checking.  Doing this cleanly would require

	  adding a new function to each thread_*.h.  Instead, just

	  create a new lock and waste a little bit of memory */

	interpreter_lock = PyThread_allocate_lock();

	PyThread_acquire_lock(interpreter_lock, 1);

	main_thread = PyThread_get_thread_ident();

	/* Update the threading module with the new state.

	 */

	tstate = PyThreadState_GET();

	threading = PyMapping_GetItemString(tstate->interp->modules,

					    "threading");

	if (threading == NULL) {

		/* threading not imported */

		PyErr_Clear();

		return;

	}

	result = PyObject_CallMethod(threading, "_after_fork", NULL);

	if (result == NULL)

		PyErr_WriteUnraisable(threading);

	else

		Py_DECREF(result);

	Py_DECREF(threading);

}

#endif

/* Functions save_thread and restore_thread are always defined so

   dynamically loaded modules needn't be compiled separately for use

   with and without threads: */

PyThreadState *

PyEval_SaveThread(void)

{

	PyThreadState *tstate = PyThreadState_Swap(NULL);

	if (tstate == NULL)

		Py_FatalError("PyEval_SaveThread: NULL tstate");

#ifdef WITH_THREAD

	if (interpreter_lock)

		PyThread_release_lock(interpreter_lock);

#endif

	return tstate;

}

void

PyEval_RestoreThread(PyThreadState *tstate)

{

	if (tstate == NULL)

		Py_FatalError("PyEval_RestoreThread: NULL tstate");

#ifdef WITH_THREAD

	if (interpreter_lock) {

		int err = errno;

		PyThread_acquire_lock(interpreter_lock, 1);

		errno = err;

	}

#endif

	PyThreadState_Swap(tstate);

}

/* Mechanism whereby asynchronously executing callbacks (e.g. UNIX

   signal handlers or Mac I/O completion routines) can schedule calls

   to a function to be called synchronously.

   The synchronous function is called with one void* argument.

   It should return 0 for success or -1 for failure -- failure should

   be accompanied by an exception.

   If registry succeeds, the registry function returns 0; if it fails

   (e.g. due to too many pending calls) it returns -1 (without setting

   an exception condition).

   Note that because registry may occur from within signal handlers,

   or other asynchronous events, calling malloc() is unsafe!

#ifdef WITH_THREAD

   Any thread can schedule pending calls, but only the main thread

   will execute them.

#endif

   XXX WARNING!  ASYNCHRONOUSLY EXECUTING CODE!

   There are two possible race conditions:

   (1) nested asynchronous registry calls;

   (2) registry calls made while pending calls are being processed.

   While (1) is very unlikely, (2) is a real possibility.

   The current code is safe against (2), but not against (1).

   The safety against (2) is derived from the fact that only one

   thread (the main thread) ever takes things out of the queue.

   XXX Darn!  With the advent of thread state, we should have an array

   of pending calls per thread in the thread state!  Later...

*/

#define NPENDINGCALLS 32

static struct {

	int (*func)(void *);

	void *arg;

} pendingcalls[NPENDINGCALLS];

static volatile int pendingfirst = 0;

static volatile int pendinglast = 0;

static volatile int things_to_do = 0;

int

Py_AddPendingCall(int (*func)(void *), void *arg)

{

	static volatile int busy = 0;

	int i, j;

	/* XXX Begin critical section */

	/* XXX If you want this to be safe against nested

	   XXX asynchronous calls, you'll have to work harder! */

	if (busy)

		return -1;

	busy = 1;

	i = pendinglast;

	j = (i + 1) % NPENDINGCALLS;

	if (j == pendingfirst) {

		busy = 0;

		return -1; /* Queue full */

	}

	pendingcalls[i].func = func;

	pendingcalls[i].arg = arg;

	pendinglast = j;

	_Py_Ticker = 0;

	things_to_do = 1; /* Signal main loop */

	busy = 0;

	/* XXX End critical section */

	return 0;

}

int

Py_MakePendingCalls(void)

{

	static int busy = 0;

#ifdef WITH_THREAD

	if (main_thread && PyThread_get_thread_ident() != main_thread)

		return 0;

#endif

	if (busy)

		return 0;

	busy = 1;

	things_to_do = 0;

	for (;;) {

		int i;

		int (*func)(void *);

		void *arg;

		i = pendingfirst;

		if (i == pendinglast)

			break; /* Queue empty */

		func = pendingcalls[i].func;

		arg = pendingcalls[i].arg;

		pendingfirst = (i + 1) % NPENDINGCALLS;

		if (func(arg) < 0) {

			busy = 0;

			things_to_do = 1; /* We're not done yet */

			return -1;

		}

	}

	busy = 0;

	return 0;

}

/* The interpreter's recursion limit */

#ifndef Py_DEFAULT_RECURSION_LIMIT

#define Py_DEFAULT_RECURSION_LIMIT 1000

#endif

static int recursion_limit = Py_DEFAULT_RECURSION_LIMIT;

int _Py_CheckRecursionLimit = Py_DEFAULT_RECURSION_LIMIT;

int

Py_GetRecursionLimit(void)

{

	return recursion_limit;

}

void

Py_SetRecursionLimit(int new_limit)

{

	recursion_limit = new_limit;

	_Py_CheckRecursionLimit = recursion_limit;

}

/* the macro Py_EnterRecursiveCall() only calls _Py_CheckRecursiveCall()

   if the recursion_depth reaches _Py_CheckRecursionLimit.

   If USE_STACKCHECK, the macro decrements _Py_CheckRecursionLimit

   to guarantee that _Py_CheckRecursiveCall() is regularly called.

   Without USE_STACKCHECK, there is no need for this. */

int

_Py_CheckRecursiveCall(char *where)

{

	PyThreadState *tstate = PyThreadState_GET();

#ifdef USE_STACKCHECK

	if (PyOS_CheckStack()) {

		--tstate->recursion_depth;

		PyErr_SetString(PyExc_MemoryError, "Stack overflow");

		return -1;

	}

#endif

	if (tstate->recursion_depth > recursion_limit) {

		--tstate->recursion_depth;

		PyErr_Format(PyExc_RuntimeError,

			     "maximum recursion depth exceeded%s",

			     where);

		return -1;

	}

	_Py_CheckRecursionLimit = recursion_limit;

	return 0;

}

/* Status code for main loop (reason for stack unwind) */

enum why_code {

		WHY_NOT =	0x0001,	/* No error */

		WHY_EXCEPTION = 0x0002,	/* Exception occurred */

		WHY_RERAISE =	0x0004,	/* Exception re-raised by 'finally' */

		WHY_RETURN =	0x0008,	/* 'return' statement */

		WHY_BREAK =	0x0010,	/* 'break' statement */

		WHY_CONTINUE =	0x0020,	/* 'continue' statement */

		WHY_YIELD =	0x0040	/* 'yield' operator */

};

static enum why_code do_raise(PyObject *, PyObject *, PyObject *);

static int unpack_iterable(PyObject *, int, PyObject **);

/* for manipulating the thread switch and periodic "stuff" - used to be

   per thread, now just a pair o' globals */

int _Py_CheckInterval = 100;

volatile int _Py_Ticker = 100;

PyObject *

PyEval_EvalCode(PyCodeObject *co, PyObject *globals, PyObject *locals)

{

	return PyEval_EvalCodeEx(co,

			  globals, locals,

			  (PyObject **)NULL, 0,

			  (PyObject **)NULL, 0,

			  (PyObject **)NULL, 0,

			  NULL);

}

/* Interpreter main loop */

PyObject *

PyEval_EvalFrame(PyFrameObject *f) {

	/* This is for backward compatibility with extension modules that