mirror of
https://github.com/python/cpython.git
synced 2025-08-04 17:08:35 +00:00

* Correctly pre-check for int-to-str conversion (#96537) Converting a large enough `int` to a decimal string raises `ValueError` as expected. However, the raise comes _after_ the quadratic-time base-conversion algorithm has run to completion. For effective DOS prevention, we need some kind of check before entering the quadratic-time loop. Oops! =) The quick fix: essentially we catch _most_ values that exceed the threshold up front. Those that slip through will still be on the small side (read: sufficiently fast), and will get caught by the existing check so that the limit remains exact. The justification for the current check. The C code check is: ```c max_str_digits / (3 * PyLong_SHIFT) <= (size_a - 11) / 10 ``` In GitHub markdown math-speak, writing $M$ for `max_str_digits`, $L$ for `PyLong_SHIFT` and $s$ for `size_a`, that check is: $$\left\lfloor\frac{M}{3L}\right\rfloor \le \left\lfloor\frac{s - 11}{10}\right\rfloor$$ From this it follows that $$\frac{M}{3L} < \frac{s-1}{10}$$ hence that $$\frac{L(s-1)}{M} > \frac{10}{3} > \log_2(10).$$ So $$2^{L(s-1)} > 10^M.$$ But our input integer $a$ satisfies $|a| \ge 2^{L(s-1)}$, so $|a|$ is larger than $10^M$. This shows that we don't accidentally capture anything _below_ the intended limit in the check. <!-- gh-issue-number: gh-95778 --> * Issue: gh-95778 <!-- /gh-issue-number --> Co-authored-by: Gregory P. Smith [Google LLC] <greg@krypto.org> Co-authored-by: Christian Heimes <christian@python.org> Co-authored-by: Mark Dickinson <dickinsm@gmail.com>
194 lines
5.2 KiB
C
194 lines
5.2 KiB
C
#ifndef Py_INTERNAL_INTERP_H
|
|
#define Py_INTERNAL_INTERP_H
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#ifndef Py_BUILD_CORE
|
|
# error "this header requires Py_BUILD_CORE define"
|
|
#endif
|
|
|
|
#include "pycore_atomic.h" /* _Py_atomic_address */
|
|
#include "pycore_gil.h" /* struct _gil_runtime_state */
|
|
#include "pycore_gc.h" /* struct _gc_runtime_state */
|
|
#include "pycore_warnings.h" /* struct _warnings_runtime_state */
|
|
|
|
/* ceval state */
|
|
|
|
struct _pending_calls {
|
|
PyThread_type_lock lock;
|
|
/* Request for running pending calls. */
|
|
_Py_atomic_int calls_to_do;
|
|
/* Request for looking at the `async_exc` field of the current
|
|
thread state.
|
|
Guarded by the GIL. */
|
|
int async_exc;
|
|
#define NPENDINGCALLS 32
|
|
struct {
|
|
int (*func)(void *);
|
|
void *arg;
|
|
} calls[NPENDINGCALLS];
|
|
int first;
|
|
int last;
|
|
};
|
|
|
|
struct _ceval_state {
|
|
int recursion_limit;
|
|
/* Records whether tracing is on for any thread. Counts the number
|
|
of threads for which tstate->c_tracefunc is non-NULL, so if the
|
|
value is 0, we know we don't have to check this thread's
|
|
c_tracefunc. This speeds up the if statement in
|
|
_PyEval_EvalFrameDefault() after fast_next_opcode. */
|
|
int tracing_possible;
|
|
/* This single variable consolidates all requests to break out of
|
|
the fast path in the eval loop. */
|
|
_Py_atomic_int eval_breaker;
|
|
/* Request for dropping the GIL */
|
|
_Py_atomic_int gil_drop_request;
|
|
struct _pending_calls pending;
|
|
};
|
|
|
|
/* fs_codec.encoding is initialized to NULL.
|
|
Later, it is set to a non-NULL string by _PyUnicode_InitEncodings(). */
|
|
struct _Py_unicode_fs_codec {
|
|
char *encoding; // Filesystem encoding (encoded to UTF-8)
|
|
int utf8; // encoding=="utf-8"?
|
|
char *errors; // Filesystem errors (encoded to UTF-8)
|
|
_Py_error_handler error_handler;
|
|
};
|
|
|
|
struct _Py_unicode_state {
|
|
struct _Py_unicode_fs_codec fs_codec;
|
|
};
|
|
|
|
|
|
/* interpreter state */
|
|
|
|
#define _PY_NSMALLPOSINTS 257
|
|
#define _PY_NSMALLNEGINTS 5
|
|
|
|
// The PyInterpreterState typedef is in Include/pystate.h.
|
|
struct _is {
|
|
|
|
struct _is *next;
|
|
struct _ts *tstate_head;
|
|
|
|
/* Reference to the _PyRuntime global variable. This field exists
|
|
to not have to pass runtime in addition to tstate to a function.
|
|
Get runtime from tstate: tstate->interp->runtime. */
|
|
struct pyruntimestate *runtime;
|
|
|
|
int64_t id;
|
|
int64_t id_refcount;
|
|
int requires_idref;
|
|
PyThread_type_lock id_mutex;
|
|
|
|
int finalizing;
|
|
|
|
struct _ceval_state ceval;
|
|
struct _gc_runtime_state gc;
|
|
|
|
PyObject *modules;
|
|
PyObject *modules_by_index;
|
|
PyObject *sysdict;
|
|
PyObject *builtins;
|
|
PyObject *importlib;
|
|
|
|
/* Used in Modules/_threadmodule.c. */
|
|
long num_threads;
|
|
/* Support for runtime thread stack size tuning.
|
|
A value of 0 means using the platform's default stack size
|
|
or the size specified by the THREAD_STACK_SIZE macro. */
|
|
/* Used in Python/thread.c. */
|
|
size_t pythread_stacksize;
|
|
|
|
PyObject *codec_search_path;
|
|
PyObject *codec_search_cache;
|
|
PyObject *codec_error_registry;
|
|
int codecs_initialized;
|
|
|
|
struct _Py_unicode_state unicode;
|
|
|
|
PyConfig config;
|
|
#ifdef HAVE_DLOPEN
|
|
int dlopenflags;
|
|
#endif
|
|
|
|
PyObject *dict; /* Stores per-interpreter state */
|
|
|
|
PyObject *builtins_copy;
|
|
PyObject *import_func;
|
|
/* Initialized to PyEval_EvalFrameDefault(). */
|
|
_PyFrameEvalFunction eval_frame;
|
|
|
|
Py_ssize_t co_extra_user_count;
|
|
freefunc co_extra_freefuncs[MAX_CO_EXTRA_USERS];
|
|
|
|
#ifdef HAVE_FORK
|
|
PyObject *before_forkers;
|
|
PyObject *after_forkers_parent;
|
|
PyObject *after_forkers_child;
|
|
#endif
|
|
/* AtExit module */
|
|
void (*pyexitfunc)(PyObject *);
|
|
PyObject *pyexitmodule;
|
|
|
|
uint64_t tstate_next_unique_id;
|
|
|
|
struct _warnings_runtime_state warnings;
|
|
|
|
PyObject *audit_hooks;
|
|
|
|
struct {
|
|
struct {
|
|
int level;
|
|
int atbol;
|
|
} listnode;
|
|
} parser;
|
|
|
|
#if _PY_NSMALLNEGINTS + _PY_NSMALLPOSINTS > 0
|
|
/* Small integers are preallocated in this array so that they
|
|
can be shared.
|
|
The integers that are preallocated are those in the range
|
|
-_PY_NSMALLNEGINTS (inclusive) to _PY_NSMALLPOSINTS (not inclusive).
|
|
*/
|
|
PyLongObject* small_ints[_PY_NSMALLNEGINTS + _PY_NSMALLPOSINTS];
|
|
#endif
|
|
|
|
int int_max_str_digits;
|
|
};
|
|
|
|
/* Used by _PyImport_Cleanup() */
|
|
extern void _PyInterpreterState_ClearModules(PyInterpreterState *interp);
|
|
|
|
extern PyStatus _PyInterpreterState_SetConfig(
|
|
PyInterpreterState *interp,
|
|
const PyConfig *config);
|
|
|
|
|
|
|
|
/* cross-interpreter data registry */
|
|
|
|
/* For now we use a global registry of shareable classes. An
|
|
alternative would be to add a tp_* slot for a class's
|
|
crossinterpdatafunc. It would be simpler and more efficient. */
|
|
|
|
struct _xidregitem;
|
|
|
|
struct _xidregitem {
|
|
PyTypeObject *cls;
|
|
crossinterpdatafunc getdata;
|
|
struct _xidregitem *next;
|
|
};
|
|
|
|
PyAPI_FUNC(struct _is*) _PyInterpreterState_LookUpID(int64_t);
|
|
|
|
PyAPI_FUNC(int) _PyInterpreterState_IDInitref(struct _is *);
|
|
PyAPI_FUNC(void) _PyInterpreterState_IDIncref(struct _is *);
|
|
PyAPI_FUNC(void) _PyInterpreterState_IDDecref(struct _is *);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
#endif /* !Py_INTERNAL_INTERP_H */
|
|
|