view mercurial/cext/util.h @ 40626:87a872555e90

revlog: detect incomplete revlog reads

_readsegment() is supposed to return N bytes of revlog revision
data starting at a file offset. Surprisingly, its behavior before
this patch never verified that it actually read and returned N
bytes! Instead, it would perform the read(), then return whatever
data was available. And even more surprisingly, nothing in the
call chain appears to have been validating that it received all
the data it was expecting.

This behavior could lead to partial or incomplete revision chunks
being operated on. This could result in e.g. cached deltas being
applied against incomplete base revisions. The delta application
process would happily perform this operation. Only hash
verification would detect the corruption and save us.

This commit changes the behavior of raw revlog reading to validate
that we actually read() the number of bytes that were requested.
We will raise a more specific error faster, rather than possibly
have it go undetected or manifest later in the call stack, at
delta application or hash verification.

Differential Revision: https://phab.mercurial-scm.org/D5266

/*
 util.h - utility functions for interfacing with the various python APIs.

 This software may be used and distributed according to the terms of
 the GNU General Public License, incorporated herein by reference.
*/

#ifndef _HG_UTIL_H_
#define _HG_UTIL_H_

#include "compat.h"

#if PY_MAJOR_VERSION >= 3
#define IS_PY3K
#endif

/* helper to switch things like string literal depending on Python version */
#ifdef IS_PY3K
#define PY23(py2, py3) py3
#else
#define PY23(py2, py3) py2
#endif

/* clang-format off */
typedef struct {
	PyObject_HEAD
	char state;
	int mode;
	int size;
	int mtime;
} dirstateTupleObject;
/* clang-format on */

extern PyTypeObject dirstateTupleType;
#define dirstate_tuple_check(op) (Py_TYPE(op) == &dirstateTupleType)

#ifndef MIN
#define MIN(a, b) (((a) < (b)) ? (a) : (b))
#endif
/* VC9 doesn't include bool and lacks stdbool.h based on my searching */
#if defined(_MSC_VER) || __STDC_VERSION__ < 199901L
#define true 1
#define false 0
typedef unsigned char bool;
#else
#include <stdbool.h>
#endif

static inline PyObject *_dict_new_presized(Py_ssize_t expected_size)
{
	/* _PyDict_NewPresized expects a minused parameter, but it actually
	   creates a dictionary that's the nearest power of two bigger than the
	   parameter. For example, with the initial minused = 1000, the
	   dictionary created has size 1024. Of course in a lot of cases that
	   can be greater than the maximum load factor Python's dict object
	   expects (= 2/3), so as soon as we cross the threshold we'll resize
	   anyway. So create a dictionary that's at least 3/2 the size. */
	return _PyDict_NewPresized(((1 + expected_size) / 2) * 3);
}

/* Convert a PyInt or PyLong to a long. Returns false if there is an
   error, in which case an exception will already have been set. */
static inline bool pylong_to_long(PyObject *pylong, long *out)
{
	*out = PyLong_AsLong(pylong);
	/* Fast path to avoid hitting PyErr_Occurred if the value was obviously
	 * not an error. */
	if (*out != -1) {
		return true;
	}
	return PyErr_Occurred() == NULL;
}

#endif /* _HG_UTIL_H_ */