nfproxy module writing: written part of the firegex lib, frontend refactored and improved, c++ improves

This commit is contained in:
Domingo Dirutigliano
2025-02-20 19:51:28 +01:00
parent d6e7cab353
commit 8652f40235
51 changed files with 1864 additions and 343 deletions

View File

@@ -1,18 +1,87 @@
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include "proxytun/settings.cpp"
#include "proxytun/proxytun.cpp"
#include "pyproxy/settings.cpp"
#include "pyproxy/pyproxy.cpp"
#include "classes/netfilter.cpp"
#include <syncstream>
#include <iostream>
#include <stdexcept>
#include <cstdlib>
#include <endian.h>
using namespace std;
using namespace Firegex::PyProxy;
using Firegex::NfQueue::MultiThreadQueue;
/*
How python code is handles:
User code example:
```python
from firegex.nfproxy import DROP, ACCEPT, pyfilter
@pyfilter
def invalid_curl_agent(http):
if "curl" in http.headers.get("User-Agent", ""):
return DROP
return ACCEPT
```
The code is now edited adding an intestation and a end statement:
```python
global __firegex_pyfilter_enabled, __firegex_proto
__firegex_pyfilter_enabled = ["invalid_curl_agent", "func3"] # This list is dynamically generated by firegex backend
__firegex_proto = "http"
import firegex.nfproxy.internals
<user_code>
firegex.nfproxy.internals.compile() # This function can save other global variables, to use by the packet handler and is used generally to check and optimize the code
````
This code will be executed only once, and is needed to build the global and local context to use
The globals and locals generated here are copied for each connection, and are used to handle the packets
Using C API will be injected in global context the following informations:
__firegex_packet_info = {
"data" = b"raw data found on L4",
"raw_packet" = b"raw packet",
"is_input" = True, # If the packet is incoming from a client
"is_ipv6" = False, # If the packet is ipv6
"is_tcp" = True, # If the packet is tcp
}
As result the packet handler is responsible to return a dictionary in the global context with the following dictionary:
__firegex_pyfilter_result = {
"action": REJECT, # One of PyFilterResponse
"matched_by": "invalid_curl_agent", # The function that matched the packet (used if action = DROP or REJECT or MANGLE)
"mangled_packet": b"new packet" # The new packet to send to the kernel (used if action = MANGLE)
}
PyFilterResponse {
ACCEPT = 0,
DROP = 1,
REJECT = 2,
MANGLE = 3,
EXCEPTION = 4,
INVALID = 5
};
Every time a packet is received, the packet handler will execute the following code:
```python
firegex.nfproxy.internals.handle_packet()
````
The TCP stream is sorted by libtins using c++ code, but the c++ code is not responsabile di buffer the stream, but only to sort those
So firegex handle_packet has to implement a way to limit memory usage, this dipends on what methods you choose to use to filter packets
firegex lib will give you all the needed possibilities to do this is many ways
Final note: is not raccomanded to use variables that starts with __firegex_ in your code, because they may break the nfproxy
*/
ssize_t read_check(int __fd, void *__buf, size_t __nbytes){
ssize_t bytes = read(__fd, __buf, __nbytes);
if (bytes == 0){
@@ -30,7 +99,10 @@ void config_updater (){
while (true){
uint32_t code_size;
read_check(STDIN_FILENO, &code_size, 4);
vector<uint8_t> code(code_size);
//Python will send number always in little endian
code_size = le32toh(code_size);
string code;
code.resize(code_size);
read_check(STDIN_FILENO, code.data(), code_size);
cerr << "[info] [updater] Updating configuration" << endl;
try{
@@ -44,10 +116,12 @@ void config_updater (){
}
}
int main(int argc, char *argv[]){
Py_Initialize();
atexit(Py_Finalize);
init_handle_packet_code(); //Compile the static code used to handle packets
if (freopen(nullptr, "rb", stdin) == nullptr){ // We need to read from stdin binary data
cerr << "[fatal] [main] Failed to reopen stdin in binary mode" << endl;