Getting process base address in Mac OSX - macos

I'm trying to read the memory of a process using task_for_pid / vm_read.
uint32_t sz;
pointer_t buf;
task_t task;
pid_t pid = 9484;
kern_return_t error = task_for_pid(current_task(), pid, &task);
vm_read(task, 0x10e448000, 2048, &buf, &sz);
In this case I read the first 2048 bytes.
This works when I know the base address of the process (which I can find out using gdb "info shared" - in this case 0x10e448000), but how do I find out the base address at runtime (without looking at it with gdb)?

Answering my own question. I was able to get the base address using mach_vm_region_recurse like below. The offset lands in vmoffset. If there is another way that is more "right" - don't hesitate to comment!
#include <stdio.h>
#include <mach/mach_init.h>
#include <sys/sysctl.h>
#include <mach/mach_vm.h>
...
mach_port_name_t task;
vm_map_offset_t vmoffset;
vm_map_size_t vmsize;
uint32_t nesting_depth = 0;
struct vm_region_submap_info_64 vbr;
mach_msg_type_number_t vbrcount = 16;
kern_return_t kr;
if ((kr = mach_vm_region_recurse(task, &vmoffset, &vmsize,
&nesting_depth,
(vm_region_recurse_info_t)&vbr,
&vbrcount)) != KERN_SUCCESS)
{
printf("FAIL");
}

Since you're calling current_task(), I assume you're aiming at your own process at runtime. So the base address you mentioned should be the dynamic base address, i.e. static base address + image slide caused by ASLR, right? Based on this assumption, you can use "Section and Segment Accessors" to get the static base address of your process, and then use the dyld functions to get the image slide. Here's a snippet:
#import <Foundation/Foundation.h>
#include </usr/include/mach-o/getsect.h>
#include <stdio.h>
#include </usr/include/mach-o/dyld.h>
#include <string.h>
uint64_t StaticBaseAddress(void)
{
const struct segment_command_64* command = getsegbyname("__TEXT");
uint64_t addr = command->vmaddr;
return addr;
}
intptr_t ImageSlide(void)
{
char path[1024];
uint32_t size = sizeof(path);
if (_NSGetExecutablePath(path, &size) != 0) return -1;
for (uint32_t i = 0; i < _dyld_image_count(); i++)
{
if (strcmp(_dyld_get_image_name(i), path) == 0)
return _dyld_get_image_vmaddr_slide(i);
}
return 0;
}
uint64_t DynamicBaseAddress(void)
{
return StaticBaseAddress() + ImageSlide();
}
int main (int argc, const char *argv[])
{
printf("dynamic base address (%0llx) = static base address (%0llx) + image slide (%0lx)\n", DynamicBaseAddress(), StaticBaseAddress(), ImageSlide());
while (1) {}; // you can attach to this process via gdb/lldb to view the base address now :)
return 0;
}
Hope it helps!

Related

How to drive my credential provider with CredUIPromptForWindowsCredentials

I've been working on a credential provider and I've been debugging it through logging. Recently learned about CredUIPromptForWindowsCredentials() API to be able to invoke it from other than login screen or remote desktop connection. The only way at this time I can seem to get my credential to display is to set the last param to CREDUIWIN_SECURE_PROMPT. I've tried various schemes of the flags with no luck. My CP works, that's not the problem. Problem is easier debugging. Only once have I had to go to rescue mode when I made my laptop unbootable. ;) The problem with using the CREDUIWIN_SECURE_PROMPT flag is that then I don't have access to the debugger because login takes over the screen and I can't get back to my debugger. I suppose the only workaround would be to remote debug on another machine with this API, but I'd prefer not to hassle with that.
My CP is registered at HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows\CurrentVersion\Authentication\Credential Providers\{55157584-ff0f-48ce-9178-a4e290901663} and the default property is "MyCredProvider" (for this example). (GUID, prop name changed to protect the guilty. Also ignore LsaString where bad things would happen on a copy--of which I'm not doing.)
Any way to get my custom CP without using the secure prompt?
#include <windows.h>
#include <iostream>
#include <EvoApi.h>
#include <decrypt.h>
#include <atlbase.h>
#include <Lmwksta.h>
#include <StrSafe.h>
#include <LMAPIbuf.h>
#include <LMJoin.h>
#include <wincred.h>
#include <NTSecAPI.h>
#pragma warning(disable : 4996)
#pragma comment(lib, "netapi32.lib")
#pragma comment(lib, "credui.lib")
#pragma comment(lib, "secur32")
using namespace std;
template <size_t SIZE = 256>
struct LsaString : public LSA_STRING
{
LsaString()
{
MaximumLength = SIZE;
Length = 0;
Buffer = pBuf.get();
}
LsaString(LPCSTR pWhat)
{
MaximumLength = SIZE;
Length = 0;
Buffer = pBuf.get();
Init(pWhat);
}
void Init(LPCSTR pWhat)
{
size_t len = strlen(pWhat);
if (len >= SIZE)
throw;
strcpy(Buffer, pWhat);
Length = (USHORT) len;
}
unique_ptr<char[]> pBuf = make_unique< char[] >(SIZE);
};
int _tmain(int argc, wchar_t* argv[])
{
#if 1
wstring me(_T("MYLOGING"));
wstring url(_T("Header"));
wstring message(_T("Enter credentials for ..."));
CREDUI_INFOW credInfo;
credInfo.pszCaptionText = url.c_str();
credInfo.hbmBanner = nullptr;
credInfo.hwndParent = NULL;
credInfo.pszMessageText = message.c_str();
credInfo.cbSize = sizeof(CREDUI_INFOW);
ULONG authPackage = 0;
LSAHANDLE lsaHandle;
LsaConnectUntrusted(&lsaHandle);
LsaString<> lsaString("MyCredProvider");
//LsaString<> lsaString(MICROSOFT_KERBEROS_NAME_A); // works ... as far as finding in LsaLookupAuth...
//LsaString<> lsaString(NEGOSSP_NAME_A); // works ... as far as finding in LsaLookupAuth...
ULONG ulPackage = 0;
LsaLookupAuthenticationPackage(lsaHandle, &lsaString, &ulPackage);
void* pBlob;
ULONG blobSize = 0;
DWORD dwFlags = CREDUIWIN_GENERIC; //CREDUIWIN_SECURE_PROMPT
CredUIPromptForWindowsCredentials(&credInfo, 0, &ulPackage, NULL, 0, &pBlob, &blobSize, FALSE, dwFlags);
if (pBlob) CoTaskMemFree(pBlob);
return 0;
}

json-c: segmentation fault when in json_tokener_parse

I am using json-c to parse json files in my project. I tried creating json_tokener_parse but this has resulted in seg-fault. could any please check and tell me the reason for segfault.
#include <sys/mman.h>
#include <sys/stat.h>
#include <fcntl.h> // O_RDONLY
#include<stdlib.h>
#include<stdio.h>
#include<unistd.h>
#include<json-c/json.h>
int main() {
int oflag = O_RDONLY;
const char *path = "file.json";
const int fd = open(path, oflag);
// use stat to find the file size
struct stat stat;
int ret = fstat(fd, &stat);
int mflags = MAP_SHARED; // information about handling the mapped data
int mprot = PROT_READ|PROT_WRITE; // access permissions to the data being mapped
size_t size = stat.st_size;
void *addr = mmap(NULL, size, mprot, mflags, fd, 0);
const char *file = (char *)addr;
json_object * jobj = json_tokener_parse(addr);
//json_parse(jobj);
}
json_tokener_parse() takes a null-terminated string. A text file is not null-terminated. You'll have to use json_tokener_parse_ex() and specify the length.

Catch system calls on Mac OS X

I'm trying to catch all systems-calls called by a given PID with a self-made program (I cant use any of strace, dtruss, gdb...). So i used the function
kern_return_t task_set_emulation(task_t target_port, vm_address_t routine_entry_pt, int routine_number) declared in /usr/include/mach/task.h .
I've written a little program to catch the syscall write :
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <mach/mach.h>
#include <mach/mach_vm.h>
void do_exit(char *msg)
{
printf("Error::%s\n", msg);
exit(42);
}
int main(void)
{
mach_port_t the_task;
mach_vm_address_t address;
mach_vm_size_t size;
mach_port_t the_thread;
kern_return_t kerr;
//Initialisation
address = 0;
size = 1ul * 1024;
the_task = mach_task_self(); //Get the current program task
kerr = mach_vm_allocate(the_task, &address, size, VM_MEMORY_MALLOC); //Allocate a new address for the test
if (kerr != KERN_SUCCESS)
{ do_exit("vm_allocate"); }
printf("address::%llx, size::%llu\n", address, size); //debug
//Process
kerr = task_set_emulation(the_task, address, SYS_write); //About to catch write syscalls
the_thread = mach_thread_self(); //Verify if a thread is opened (even if it's obvious)
printf("kerr::%d, thread::%d\n", kerr, the_thread); //debug
if (kerr != KERN_SUCCESS)
{ do_exit("set_emulation"); }
//Use some writes for the example
write(1, "Bonjour\n", 8);
write(1, "Bonjour\n", 8);
}
The Output is :
address::0x106abe000, size::1024
kerr::46, thread::1295
Error::set_emulation
The kernel error 46 corresponds to the macro KERN_NOT_SUPPORTED described as an "Empty thread activation (No thread linked to it)" in /usr/include/mach/kern_return.h, and happend even before i'm calling write.
My question is: What did I do wrong in this process? Kern_not_supported does mean that it's not implemented yet, instead of a meaningless thread problem?
The source code in XNU for the task_set_emulation is:
kern_return_t
task_set_emulation(
__unused task_t task,
__unused vm_offset_t routine_entry_pt,
__unused int routine_number)
{
return KERN_NOT_SUPPORTED;
}
Which means task_set_emulation is not supported.

How to dump/list all kernel symbols with addresses from Linux kernel module?

In a kernel module, how to list all the kernel symbols with their addresses?
The kernel should not be re-compiled.
I know "cat /proc/kallsyms" in an interface, but how to get them directly from kernel data structures, using functions like kallsyms_lookup_name.
Example
Working module code:
#include <linux/module.h>
#include <linux/kallsyms.h>
static int prsyms_print_symbol(void *data, const char *namebuf,
struct module *module, unsigned long address)
{
pr_info("### %lx\t%s\n", address, namebuf);
return 0;
}
static int __init prsyms_init(void)
{
kallsyms_on_each_symbol(prsyms_print_symbol, NULL);
return 0;
}
static void __exit prsyms_exit(void)
{
}
module_init(prsyms_init);
module_exit(prsyms_exit);
MODULE_AUTHOR("Sam Protsenko");
MODULE_DESCRIPTION("Module for printing all kernel symbols");
MODULE_LICENSE("GPL");
Explanation
kernel/kallsyms.c implements /proc/kallsyms. Some of its functions are available for external usage. They are exported via EXPORT_SYMBOL_GPL() macro. Yes, your module should have GPL license to use it. Those functions are:
kallsyms_lookup_name()
kallsyms_on_each_symbol()
sprint_symbol()
sprint_symbol_no_offset()
To use those functions, include <linux/kallsyms.h> in your module. It should be mentioned that CONFIG_KALLSYMS must be enabled (=y) in your kernel configuration.
To print all the symbols you obviously have to use kallsyms_on_each_symbol() function. The documentation says next about it:
/* Call a function on each kallsyms symbol in the core kernel */
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long), void *data);
where fn is your callback function that should be called for each symbol found, and data is a pointer to some private data of yours (will be passed as first parameter to your callback function).
Callback function must have next signature:
int fn(void *data, const char *namebuf, struct module *module,
unsigned long address);
This function will be called for each kernel symbol with next parameters:
data: will contain pointer to your private data you passed as last argument to kallsyms_on_each_symbol()
namebuf: will contain name of current kernel symbol
module: will always be NULL, just ignore that
address: will contain address of current kernel symbol
Return value should always be 0 (on non-zero return value the iteration through symbols will be interrupted).
Supplemental
Answering the questions in your comment.
Also, is there a way to output the size of each function?
Yes, you can use sprint_symbol() function I mentioned above to do that. It will print symbol information in next format:
symbol_name+offset/size [module_name]
Example:
psmouse_poll+0x0/0x30 [psmouse]
Module name part can be omitted if symbol is built-in.
I tried the module and see the result with "dmesg". But a lot of symbols are missing such as "futex_requeue". The output symbol number is about 10K, while it is 100K when I use "nm vmlinux".
This is most likely because your printk buffer size is insufficient to store all the output of module above.
Let's improve above module a bit, so it provides symbols information via miscdevice. Also let's add function size to the output, as requested. The code as follows:
#include <linux/device.h>
#include <linux/fs.h>
#include <linux/kallsyms.h>
#include <linux/module.h>
#include <linux/miscdevice.h>
#include <linux/sizes.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#define DEVICE_NAME "prsyms2"
/* 16 MiB is sufficient to store information about approx. 200K symbols */
#define SYMBOLS_BUF_SIZE SZ_16M
struct symbols {
char *buf;
size_t pos;
};
static struct symbols symbols;
/* ---- misc char device definitions ---- */
static ssize_t prsyms2_read(struct file *file, char __user *buf, size_t count,
loff_t *pos)
{
return simple_read_from_buffer(buf, count, pos, symbols.buf,
symbols.pos);
}
static const struct file_operations prsyms2_fops = {
.owner = THIS_MODULE,
.read = prsyms2_read,
};
static struct miscdevice prsyms2_misc = {
.minor = MISC_DYNAMIC_MINOR,
.name = DEVICE_NAME,
.fops = &prsyms2_fops,
};
/* ---- module init/exit definitions ---- */
static int prsyms2_store_symbol(void *data, const char *namebuf,
struct module *module, unsigned long address)
{
struct symbols *s = data;
int count;
/* Append address of current symbol */
count = sprintf(s->buf + s->pos, "%lx\t", address);
s->pos += count;
/* Append name, offset, size and module name of current symbol */
count = sprint_symbol(s->buf + s->pos, address);
s->pos += count;
s->buf[s->pos++] = '\n';
if (s->pos >= SYMBOLS_BUF_SIZE)
return -ENOMEM;
return 0;
}
static int __init prsyms2_init(void)
{
int ret;
ret = misc_register(&prsyms2_misc);
if (ret)
return ret;
symbols.pos = 0;
symbols.buf = vmalloc(SYMBOLS_BUF_SIZE);
if (symbols.buf == NULL) {
ret = -ENOMEM;
goto err1;
}
dev_info(prsyms2_misc.this_device, "Populating symbols buffer...\n");
ret = kallsyms_on_each_symbol(prsyms2_store_symbol, &symbols);
if (ret != 0) {
ret = -EINVAL;
goto err2;
}
symbols.buf[symbols.pos] = '\0';
dev_info(prsyms2_misc.this_device, "Symbols buffer is ready!\n");
return 0;
err2:
vfree(symbols.buf);
err1:
misc_deregister(&prsyms2_misc);
return ret;
}
static void __exit prsyms2_exit(void)
{
vfree(symbols.buf);
misc_deregister(&prsyms2_misc);
}
module_init(prsyms2_init);
module_exit(prsyms2_exit);
MODULE_AUTHOR("Sam Protsenko");
MODULE_DESCRIPTION("Module for printing all kernel symbols");
MODULE_LICENSE("GPL");
And here is how to use it:
$ sudo insmod prsyms2.ko
$ sudo cat /dev/prsyms2 >symbols.txt
$ wc -l symbols.txt
$ sudo rmmod prsyms2
File symbols.txt will contain all kernel symbols (both built-in and from loaded modules) in next format:
ffffffffc01dc0d0 psmouse_poll+0x0/0x30 [psmouse]
It seems that I can use kallsyms_lookup_name() to find the address of the function, can then use a function pointer to call the function?
Yes, you can. If I recall correctly, it's called reflection. Below is an example how to do so:
typedef int (*custom_print)(const char *fmt, ...);
custom_print my_print;
my_print = (custom_print)kallsyms_lookup_name("printk");
if (my_print == 0) {
pr_err("Unable to find printk\n");
return -EINVAL;
}
my_print(KERN_INFO "### printk found!\n");

gethostbyname fails on OSX (Yosemite 10.10.4)

"gethostbyname" returns a pointer to this structure:
struct hostent {
char *h_name; /* official name of host */
char **h_aliases; /* alias list */
int h_addrtype; /* host address type */
int h_length; /* length of address */
char **h_addr_list; /* list of addresses from name server */
};
When I try to use it, h_name points to a valid string: the partial name I supply is expanded to the correct fully qualified host name.
The value of h_addr_list is 4
h_name is valid
h_aliasis is a valid pointer to a null pointer
h_addrtype is 2 (AF_INET, IPV4)
h_length is 0 (should be 4, or perhaps a multiple of 4)
h_addr_list is 4, fails when dereferenced.
I'm running a 32 bit process (MS Office), the h_name pointer is a valid 32 bit pointer. WTF am I doing wrong? Does gethostbyname work for other people, or on other versions of OSX?
I was able to run this small example successfully on 10.10.4 (taken from paulschreiber.com)
#include <netdb.h>
#include <stdio.h>
#include <stdlib.h>
#include <arpa/inet.h>
int main(int argc, char **argv) {
if (argc < 2) {
printf("Usage: %s hostname", argv[0]);
exit(-1);
}
struct hostent *hp = gethostbyname(argv[1]);
if (hp == NULL) {
printf("gethostbyname() failed\n");
} else {
printf("%s = ", hp->h_name);
unsigned int i=0;
while ( hp -> h_addr_list[i] != NULL) {
printf( "%s ", inet_ntoa( *( struct in_addr*)( hp -> h_addr_list[i])));
i++;
}
printf("\n");
}
}
However, it did segfault on 64-bit without #include <arpa/inet.h: without that, no prototype for inet_ntoa is found, the return type is assumed to be an int (when it's actually a char *), and on 64-bit this truncates the pointer and causes a segfault.

Resources