mercurial/exewrapper.c

debugcommands: add debugwireproto command

We currently don't have a low-level mechanism for sending
arbitrary wire protocol commands. Having a generic and robust
mechanism for sending wire protocol commands, examining wire
data, etc would make it vastly easier to test the wire protocol
and debug server operation. This is a problem I've wanted a
solution for numerous times, especially recently as I've been
hacking on a new version of the wire protocol.

This commit establishes a `hg debugwireproto` command for sending
data to a peer.

The command invents a mini language for specifying actions to take.
This will enable a lot of flexibility for issuing commands and testing
variations for how commands are sent.

Right now, we only support low-level raw sends and receives. These
are probably the least valuable commands to intended users of this
command. But they are the most useful commands to implement to
bootstrap the feature (I've chosen to reimplement test-ssh-proto.t
using this command to prove its usefulness).

My eventual goal of `hg debugwireproto` is to allow calling wire
protocol commands with a human-friendly interface. Essentially,
people can type in a command name and arguments and
`hg debugwireproto` will figure out how to send that on the wire.
I'd love to eventually be able to save the server's raw response
to a file. This would allow us to e.g. call "getbundle" wire
protocol commands easily.

test-ssh-proto.t has been updated to use the new command in lieu
of piping directly to a server process. As part of the transition,
test behavior improved. Before, we piped all request data to the
server at once. Now, we have explicit control over the ordering of
operations. e.g. we can send one command, receive its response,
then send another command. This will allow us to more robustly
test race conditions, buffering behavior, etc.

There were some subtle changes in test behavior. For example,
previous behavior would often send trailing newlines to the server.
The new mechanism doesn't treat literal newlines specially and
requires newlines be escaped in the payload.

Because the new logging code is very low level, it is easy to
introduce race conditions in tests. For example, the number of bytes
returned by a read() may vary depending on load. This is why tests
make heavy use of "readline" for consuming data: the result of
that operation should be deterministic and not subject to race
conditions. There are still some uses of "readavailable." However,
those are only for reading from stderr. I was able to reproduce
timing issues with my system under load when using "readavailable"
globally. But if I "readline" to grab stdout, "readavailable"
appears to work deterministically for stderr. I think this is
because the server writes to stderr first. As long as the OS
delivers writes to pipes in the same order they were made, this
should work. If there are timing issues, we can introduce a
mechanism to readline from stderr.

Differential Revision: https://phab.mercurial-scm.org/D2392

/*
 exewrapper.c - wrapper for calling a python script on Windows

 Copyright 2012 Adrian Buehlmann <[e-mail]> and others

 This software may be used and distributed according to the terms of the
 GNU General Public License version 2 or any later version.
*/

#include <stdio.h>
#include <windows.h>

#include "hgpythonlib.h"

#ifdef __GNUC__
int strcat_s(char *d, size_t n, const char *s)
{
	return !strncat(d, s, n);
}
int strcpy_s(char *d, size_t n, const char *s)
{
	return !strncpy(d, s, n);
}
#endif

static char pyscript[MAX_PATH + 10];
static char pyhome[MAX_PATH + 10];
static char envpyhome[MAX_PATH + 10];
static char pydllfile[MAX_PATH + 10];

int main(int argc, char *argv[])
{
	char *p;
	int ret;
	int i;
	int n;
	char **pyargv;
	WIN32_FIND_DATA fdata;
	HANDLE hfind;
	const char *err;
	HMODULE pydll;
	void(__cdecl * Py_SetPythonHome)(char *home);
	int(__cdecl * Py_Main)(int argc, char *argv[]);

	if (GetModuleFileName(NULL, pyscript, sizeof(pyscript)) == 0) {
		err = "GetModuleFileName failed";
		goto bail;
	}

	p = strrchr(pyscript, '.');
	if (p == NULL) {
		err = "malformed module filename";
		goto bail;
	}
	*p = 0; /* cut trailing ".exe" */
	strcpy_s(pyhome, sizeof(pyhome), pyscript);

	hfind = FindFirstFile(pyscript, &fdata);
	if (hfind != INVALID_HANDLE_VALUE) {
		/* pyscript exists, close handle */
		FindClose(hfind);
	} else {
		/* file pyscript isn't there, take <pyscript>exe.py */
		strcat_s(pyscript, sizeof(pyscript), "exe.py");
	}

	pydll = NULL;

	p = strrchr(pyhome, '\\');
	if (p == NULL) {
		err = "can't find backslash in module filename";
		goto bail;
	}
	*p = 0; /* cut at directory */

	/* check for private Python of HackableMercurial */
	strcat_s(pyhome, sizeof(pyhome), "\\hg-python");

	hfind = FindFirstFile(pyhome, &fdata);
	if (hfind != INVALID_HANDLE_VALUE) {
		/* Path .\hg-python exists. We are probably in HackableMercurial
		scenario, so let's load python dll from this dir. */
		FindClose(hfind);
		strcpy_s(pydllfile, sizeof(pydllfile), pyhome);
		strcat_s(pydllfile, sizeof(pydllfile), "\\" HGPYTHONLIB ".dll");
		pydll = LoadLibrary(pydllfile);
		if (pydll == NULL) {
			err = "failed to load private Python DLL " HGPYTHONLIB
			      ".dll";
			goto bail;
		}
		Py_SetPythonHome =
		    (void *)GetProcAddress(pydll, "Py_SetPythonHome");
		if (Py_SetPythonHome == NULL) {
			err = "failed to get Py_SetPythonHome";
			goto bail;
		}
		Py_SetPythonHome(pyhome);
	}

	if (pydll == NULL) {
		pydll = LoadLibrary(HGPYTHONLIB ".dll");
		if (pydll == NULL) {
			err = "failed to load Python DLL " HGPYTHONLIB ".dll";
			goto bail;
		}
	}

	Py_Main = (void *)GetProcAddress(pydll, "Py_Main");
	if (Py_Main == NULL) {
		err = "failed to get Py_Main";
		goto bail;
	}

	/*
	Only add the pyscript to the args, if it's not already there. It may
	already be there, if the script spawned a child process of itself, in
	the same way as it got called, that is, with the pyscript already in
	place. So we optionally accept the pyscript as the first argument
	(argv[1]), letting our exe taking the role of the python interpreter.
	*/
	if (argc >= 2 && strcmp(argv[1], pyscript) == 0) {
		/*
		pyscript is already in the args, so there is no need to copy
		the args and we can directly call the python interpreter with
		the original args.
		*/
		return Py_Main(argc, argv);
	}

	/*
	Start assembling the args for the Python interpreter call. We put the
	name of our exe (argv[0]) in the position where the python.exe
	canonically is, and insert the pyscript next.
	*/
	pyargv = malloc((argc + 5) * sizeof(char *));
	if (pyargv == NULL) {
		err = "not enough memory";
		goto bail;
	}
	n = 0;
	pyargv[n++] = argv[0];
	pyargv[n++] = pyscript;

	/* copy remaining args from the command line */
	for (i = 1; i < argc; i++)
		pyargv[n++] = argv[i];
	/* argv[argc] is guaranteed to be NULL, so we forward that guarantee */
	pyargv[n] = NULL;

	ret = Py_Main(n, pyargv); /* The Python interpreter call */

	free(pyargv);
	return ret;

bail:
	fprintf(stderr, "abort: %s\n", err);
	return 255;
}