view mercurial/exewrapper.c @ 37054:40206e227412

wireproto: define and implement protocol for issuing requests

The existing HTTP and SSH wire protocols suffer from a host of flaws
and shortcomings. I've been wanting to rewrite the protocol for a while
now. Supporting partial clone - which will require new wire protocol
commands and capabilities - and other advanced server functionality
will be much easier if we start from a clean slate and don't have
to be constrained by limitations of the existing wire protocol.

This commit starts to introduce a new data exchange format for
use over the wire protocol.

The new protocol is built on top of "frames," which are atomic
units of metadata + data. Frames will make it easier to implement
proxies and other mechanisms that want to inspect data without
having to maintain state. The existing frame metadata is very
minimal and it will evolve heavily. (We will eventually support
things like concurrent requests, out-of-order responses,
compression, side-channels for status updates, etc. Some of
these will require additions to the frame header.)

Another benefit of frames is that all reads are of a fixed size.
A reader works by consuming a frame header, extracting the payload
length, then reading that many bytes. No lookahead, buffering, or
memory reallocations are needed.

The new protocol attempts to be transport agnostic. I want all that's
required to use the new protocol to be a pair of unidirectional,
half-duplex pipes. (Yes, we will eventually make use of full-duplex
pipes, but that's for another commit.) Notably, when the SSH
transport switches to this new protocol, stderr will be unused.
This is by design: the lack of stderr on HTTP harms protocol
behavior there. By shoehorning everything into a pair of pipes,
we can have more consistent behavior across transports.

We currently only define the client side parts of the new protocol,
specifically the bits for requesting that a command run. This keeps
the new code and feature small and somewhat easy to review.

We add support to `hg debugwireproto` for writing frames into
HTTP request bodies. Our tests that issue commands to the new
HTTP endpoint have been updated to transmit frames. The server
bits haven't been touched to consume the frames yet. This will
occur in the next commit...

Astute readers may notice that the command name is transmitted in
both the HTTP request URL and the command request frame. This is
partially a kludge from me initially implementing the frame-based
protocol for SSH first. But it is also a feature: I intend to
eventually support issuing multiple commands per HTTP request. This
will allow us to replace the abomination that is the "batch" wire
protocol command with a protocol-level mechanism for performing
multi-dispatch. Because I want the frame-based protocol to be
as similar as possible across transports, I'd rather we (redundantly)
include the command name in the frame than differ behavior between
transports that have out-of-band routing information (like HTTP)
readily available.

Differential Revision: https://phab.mercurial-scm.org/D2851

/*
 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;
}