cosmopolitan/third_party/python/repl.c
Justine Tunney 226aaf3547 Improve memory safety
This commit makes numerous refinements to cosmopolitan memory handling.

The default stack size has been reduced from 2mb to 128kb. A new macro
is now provided so you can easily reconfigure the stack size to be any
value you want. Work around the breaking change by adding to your main:

    STATIC_STACK_SIZE(0x00200000);  // 2mb stack

If you're not sure how much stack you need, then you can use:

    STATIC_YOINK("stack_usage_logging");

After which you can `sort -nr o/$MODE/stack.log`. Based on the unit test
suite, nothing in the Cosmopolitan repository (except for Python) needs
a stack size greater than 30kb. There are also new macros for detecting
the size and address of the stack at runtime, e.g. GetStackAddr(). We
also now support sigaltstack() so if you want to see nice looking crash
reports whenever a stack overflow happens, you can put this in main():

    ShowCrashReports();

Under `make MODE=dbg` and `make MODE=asan` the unit testing framework
will now automatically print backtraces of memory allocations when
things like memory leaks happen. Bugs are now fixed in ASAN global
variable overrun detection. The memtrack and asan runtimes also handle
edge cases now. The new tools helped to identify a few memory leaks,
which are fixed by this change.

This change should fix an issue reported in #288 with ARG_MAX limits.
Fixing this doubled the performance of MKDEPS.COM and AR.COM yet again.
2021-10-13 17:27:13 -07:00

349 lines
10 KiB
C

/*-*- mode:c;indent-tabs-mode:nil;c-basic-offset:4;tab-width:8;coding:utf-8 -*-│
│vi: set net ft=c ts=4 sts=4 sw=4 fenc=utf-8 :vi│
╞══════════════════════════════════════════════════════════════════════════════╡
│ Python 3 │
│ https://docs.python.org/3/license.html │
╚─────────────────────────────────────────────────────────────────────────────*/
#define PY_SSIZE_T_CLEAN
#include "libc/bits/bits.h"
#include "libc/bits/safemacros.internal.h"
#include "libc/bits/weaken.h"
#include "libc/calls/calls.h"
#include "libc/dce.h"
#include "libc/errno.h"
#include "libc/log/check.h"
#include "libc/log/log.h"
#include "libc/mem/mem.h"
#include "libc/runtime/gc.internal.h"
#include "libc/runtime/runtime.h"
#include "libc/runtime/symbols.internal.h"
#include "libc/stdio/stdio.h"
#include "libc/str/str.h"
#include "libc/sysv/consts/fileno.h"
#include "libc/sysv/consts/sig.h"
#include "libc/unicode/locale.h"
#include "libc/x/x.h"
#include "third_party/linenoise/linenoise.h"
#include "third_party/python/Include/abstract.h"
#include "third_party/python/Include/ceval.h"
#include "third_party/python/Include/dictobject.h"
#include "third_party/python/Include/fileutils.h"
#include "third_party/python/Include/funcobject.h"
#include "third_party/python/Include/import.h"
#include "third_party/python/Include/listobject.h"
#include "third_party/python/Include/moduleobject.h"
#include "third_party/python/Include/object.h"
#include "third_party/python/Include/pydebug.h"
#include "third_party/python/Include/pyerrors.h"
#include "third_party/python/Include/pylifecycle.h"
#include "third_party/python/Include/pymem.h"
#include "third_party/python/Include/pyport.h"
#include "third_party/python/Include/pythonrun.h"
#include "third_party/python/Include/unicodeobject.h"
#include "third_party/python/Include/yoink.h"
/* clang-format off */
STATIC_STACK_SIZE(0x100000);
STATIC_YOINK("__die");
STATIC_YOINK("zip_uri_support");
PYTHON_YOINK("cosmo");
PYTHON_YOINK("_locale");
PYTHON_YOINK("_bootlocale");
PYTHON_YOINK("encodings.aliases");
PYTHON_YOINK("encodings.latin_1");
PYTHON_YOINK("encodings.utf_8");
extern char kLaunchPythonModuleName[]; /* optionally generated by pyobj.com */
const struct _frozen *PyImport_FrozenModules = _PyImport_FrozenModules;
struct _inittab *PyImport_Inittab = _PyImport_Inittab;
static int g_gotint;
static void
OnKeyboardInterrupt(int sig)
{
g_gotint = sig;
}
static void
AddCompletion(linenoiseCompletions *c, char *s)
{
char **p = c->cvec;
size_t n = c->len + 1;
if ((p = realloc(p, n * sizeof(*p)))) {
p[n - 1] = s;
c->cvec = p;
c->len = n;
}
}
static void
CompleteModule(const char *s, const char *p, linenoiseCompletions *c)
{
const char *name;
struct _inittab *it;
Py_ssize_t plen, namelen;
PyObject *m, *f, *g, *i, *v, *n;
plen = strlen(p);
for (it = PyImport_Inittab; it->name; ++it) {
if (startswith(it->name, p)) {
AddCompletion(c, xasprintf("%s%s", s, it->name + plen));
}
}
if ((m = PyImport_ImportModule("pkgutil"))) {
if ((f = PyObject_GetAttrString(m, "iter_modules"))) {
if ((g = PyObject_CallFunctionObjArgs(f, 0))) {
if ((i = PyObject_GetIter(g))) {
while ((v = PyIter_Next(i))) {
if ((n = PyObject_GetAttrString(v, "name"))) {
if (((name = PyUnicode_AsUTF8AndSize(n, &namelen)) &&
namelen >= plen && !bcmp(name, p, plen))) {
AddCompletion(c, xasprintf("%s%s", s, name + plen));
}
Py_DECREF(n);
}
Py_DECREF(v);
}
Py_DECREF(i);
}
Py_DECREF(g);
}
Py_DECREF(f);
}
Py_DECREF(m);
}
}
static void
CompleteDict(const char *b, const char *q, const char *p,
linenoiseCompletions *c, PyObject *o)
{
const char *s;
PyObject *k, *v;
Py_ssize_t i, m;
for (i = 0; PyDict_Next(o, &i, &k, &v);) {
if ((v != Py_None && PyUnicode_Check(k) &&
(s = PyUnicode_AsUTF8AndSize(k, &m)) &&
m >= q - p && !bcmp(s, p, q - p))) {
AddCompletion(c, xasprintf("%.*s%.*s", p - b, b, m, s));
}
}
}
static void
CompleteDir(const char *b, const char *q, const char *p,
linenoiseCompletions *c, PyObject *o)
{
Py_ssize_t m;
const char *s;
PyObject *d, *i, *k;
if ((d = PyObject_Dir(o))) {
if ((i = PyObject_GetIter(d))) {
while ((k = PyIter_Next(i))) {
if (((s = PyUnicode_AsUTF8AndSize(k, &m)) &&
m >= q - p && !bcmp(s, p, q - p))) {
AddCompletion(c, xasprintf("%.*s%.*s", p - b, b, m, s));
}
Py_DECREF(k);
}
Py_DECREF(i);
}
Py_DECREF(d);
}
}
static void
Complete(const char *p, linenoiseCompletions *c)
{
PyObject *o, *t, *i;
const char *q, *s, *b;
if (startswith(p, "import ")) {
for (q = p + 7; *q; ++q) {
if (!isalnum(*q) && *q != '_') {
return;
}
}
CompleteModule(p, p + 7, c);
return;
}
for (b = p, p += strlen(p); p > b; --p) {
if (!isalnum(p[-1]) && p[-1] != '.' && p[-1] != '_') {
break;
}
}
o = PyModule_GetDict(PyImport_AddModule("__main__"));
if (!*(q = strchrnul(p, '.'))) {
CompleteDict(b, q, p, c, o);
CompleteDir(b, q, p, c, PyDict_GetItemString(o, "__builtins__"));
} else {
s = strndup(p, q - p);
if ((t = PyDict_GetItemString(o, s))) {
Py_INCREF(t);
} else {
o = PyDict_GetItemString(o, "__builtins__");
if (PyObject_HasAttrString(o, s)) {
t = PyObject_GetAttrString(o, s);
}
}
while ((p = q + 1), (o = t)) {
if (*(q = strchrnul(p, '.'))) {
t = PyObject_GetAttrString(o, gc(strndup(p, q - p)));
Py_DECREF(o);
} else {
CompleteDir(b, q, p, c, o);
Py_DECREF(o);
break;
}
}
free(s);
}
}
static void
TerminalCompletion(const char *p, linenoiseCompletions *c)
{
Complete(p, c);
if (PyErr_Occurred()) {
PyErr_Clear();
}
}
static char *
TerminalHint(const char *p, const char **ansi1, const char **ansi2)
{
char *h = 0;
linenoiseCompletions c = {0};
TerminalCompletion(p, &c);
if (c.len == 1) h = strdup(c.cvec[0] + strlen(p));
linenoiseFreeCompletions(&c);
return h;
}
static char *
ReinterpretCommand(const char *line)
{
size_t n;
n = strlen(line);
if (n && line[n - 1] == '?') {
return xstrcat("help(", gc(strndup(gc(line), n - 1)), ')');
} else {
return line;
}
}
static char *
TerminalReadline(FILE *sys_stdin, FILE *sys_stdout, const char *prompt)
{
size_t n;
char *p, *q;
PyOS_sighandler_t saint;
saint = PyOS_setsig(SIGINT, OnKeyboardInterrupt);
p = linenoiseWithHistory(prompt, "python");
PyOS_setsig(SIGINT, saint);
if (g_gotint) {
PyOS_setsig(SIGINT, saint);
g_gotint = 0;
q = 0;
} else if (p) {
p = ReinterpretCommand(p);
n = strlen(p);
q = PyMem_RawMalloc(n + 2);
strcpy(mempcpy(q, p, n), "\n");
clearerr(sys_stdin);
} else if ((q = PyMem_RawMalloc(1))) {
*q = 0;
}
free(p);
return q;
}
int
RunPythonModule(int argc, char **argv)
{
char *launchargs[4];
wchar_t **argv_copy;
/* We need a second copy, as Python might modify the first one. */
wchar_t **argv_copy2;
int i, res;
char *oldloc;
if (argc == 1 && weaken(kLaunchPythonModuleName)) {
launchargs[0] = argv[0];
launchargs[1] = strdup("-m");
launchargs[2] = strdup(kLaunchPythonModuleName);
launchargs[3] = 0;
argc = 3;
argv = launchargs;
}
PyOS_ReadlineFunctionPointer = TerminalReadline;
linenoiseSetCompletionCallback(TerminalCompletion);
linenoiseSetHintsCallback(TerminalHint);
linenoiseSetFreeHintsCallback(free);
#if IsModeDbg()
/* Force malloc() allocator to bootstrap Python */
_PyMem_SetupAllocators("malloc");
#endif
argv_copy = (wchar_t **)PyMem_RawMalloc(sizeof(wchar_t*) * (argc+1));
argv_copy2 = (wchar_t **)PyMem_RawMalloc(sizeof(wchar_t*) * (argc+1));
if (!argv_copy || !argv_copy2) {
fprintf(stderr, "out of memory\n");
return 1;
}
/* 754 requires that FP exceptions run in "no stop" mode by default,
* and until C vendors implement C99's ways to control FP exceptions,
* Python requires non-stop mode. Alas, some platforms enable FP
* exceptions by default. Here we disable them.
*/
#ifdef __FreeBSD__
fedisableexcept(FE_OVERFLOW);
#endif
oldloc = _PyMem_RawStrdup(setlocale(LC_ALL, NULL));
if (!oldloc) {
fprintf(stderr, "out of memory\n");
return 1;
}
setlocale(LC_ALL, "");
for (i = 0; i < argc; i++) {
argv_copy[i] = Py_DecodeLocale(argv[i], NULL);
if (!argv_copy[i]) {
PyMem_RawFree(oldloc);
fprintf(stderr, "Fatal Python error: "
"unable to decode the command line argument #%i\n",
i + 1);
return 1;
}
argv_copy2[i] = argv_copy[i];
}
argv_copy2[argc] = argv_copy[argc] = NULL;
setlocale(LC_ALL, oldloc);
PyMem_RawFree(oldloc);
res = Py_Main(argc, argv_copy);
#if IsModeDbg()
/* Force again malloc() allocator to release memory blocks allocated
before Py_Main() */
_PyMem_SetupAllocators("malloc");
#endif
for (i = 0; i < argc; i++) {
PyMem_RawFree(argv_copy2[i]);
}
PyMem_RawFree(argv_copy);
PyMem_RawFree(argv_copy2);
return res;
}
int
main(int argc, char **argv)
{
return RunPythonModule(argc, argv);
}