mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-30 12:49:36 +00:00
![Tycho Andersen](/assets/img/avatar_default.png)
This patch is the first step in enabling checkpoint/restore of processes with seccomp enabled. One of the things CRIU does while dumping tasks is inject code into them via ptrace to collect information that is only available to the process itself. However, if we are in a seccomp mode where these processes are prohibited from making these syscalls, then what CRIU does kills the task. This patch adds a new ptrace option, PTRACE_O_SUSPEND_SECCOMP, that enables a task from the init user namespace which has CAP_SYS_ADMIN and no seccomp filters to disable (and re-enable) seccomp filters for another task so that they can be successfully dumped (and restored). We restrict the set of processes that can disable seccomp through ptrace because although today ptrace can be used to bypass seccomp, there is some discussion of closing this loophole in the future and we would like this patch to not depend on that behavior and be future proofed for when it is removed. Note that seccomp can be suspended before any filters are actually installed; this behavior is useful on criu restore, so that we can suspend seccomp, restore the filters, unmap our restore code from the restored process' address space, and then resume the task by detaching and have the filters resumed as well. v2 changes: * require that the tracer have no seccomp filters installed * drop TIF_NOTSC manipulation from the patch * change from ptrace command to a ptrace option and use this ptrace option as the flag to check. This means that as soon as the tracer detaches/dies, seccomp is re-enabled and as a corrollary that one can not disable seccomp across PTRACE_ATTACHs. v3 changes: * get rid of various #ifdefs everywhere * report more sensible errors when PTRACE_O_SUSPEND_SECCOMP is incorrectly used v4 changes: * get rid of may_suspend_seccomp() in favor of a capable() check in ptrace directly v5 changes: * check that seccomp is not enabled (or suspended) on the tracer Signed-off-by: Tycho Andersen <tycho.andersen@canonical.com> CC: Will Drewry <wad@chromium.org> CC: Roland McGrath <roland@hack.frob.com> CC: Pavel Emelyanov <xemul@parallels.com> CC: Serge E. Hallyn <serge.hallyn@ubuntu.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Andy Lutomirski <luto@amacapital.net> [kees: access seccomp.mode through seccomp_mode() instead] Signed-off-by: Kees Cook <keescook@chromium.org>
1232 lines
30 KiB
C
1232 lines
30 KiB
C
/*
|
|
* linux/kernel/ptrace.c
|
|
*
|
|
* (C) Copyright 1999 Linus Torvalds
|
|
*
|
|
* Common interfaces for "ptrace()" which we do not want
|
|
* to continually duplicate across every architecture.
|
|
*/
|
|
|
|
#include <linux/capability.h>
|
|
#include <linux/export.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/security.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/audit.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/regset.h>
|
|
#include <linux/hw_breakpoint.h>
|
|
#include <linux/cn_proc.h>
|
|
#include <linux/compat.h>
|
|
|
|
|
|
/*
|
|
* ptrace a task: make the debugger its new parent and
|
|
* move it to the ptrace list.
|
|
*
|
|
* Must be called with the tasklist lock write-held.
|
|
*/
|
|
void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
|
|
{
|
|
BUG_ON(!list_empty(&child->ptrace_entry));
|
|
list_add(&child->ptrace_entry, &new_parent->ptraced);
|
|
child->parent = new_parent;
|
|
}
|
|
|
|
/**
|
|
* __ptrace_unlink - unlink ptracee and restore its execution state
|
|
* @child: ptracee to be unlinked
|
|
*
|
|
* Remove @child from the ptrace list, move it back to the original parent,
|
|
* and restore the execution state so that it conforms to the group stop
|
|
* state.
|
|
*
|
|
* Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer
|
|
* exiting. For PTRACE_DETACH, unless the ptracee has been killed between
|
|
* ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED.
|
|
* If the ptracer is exiting, the ptracee can be in any state.
|
|
*
|
|
* After detach, the ptracee should be in a state which conforms to the
|
|
* group stop. If the group is stopped or in the process of stopping, the
|
|
* ptracee should be put into TASK_STOPPED; otherwise, it should be woken
|
|
* up from TASK_TRACED.
|
|
*
|
|
* If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED,
|
|
* it goes through TRACED -> RUNNING -> STOPPED transition which is similar
|
|
* to but in the opposite direction of what happens while attaching to a
|
|
* stopped task. However, in this direction, the intermediate RUNNING
|
|
* state is not hidden even from the current ptracer and if it immediately
|
|
* re-attaches and performs a WNOHANG wait(2), it may fail.
|
|
*
|
|
* CONTEXT:
|
|
* write_lock_irq(tasklist_lock)
|
|
*/
|
|
void __ptrace_unlink(struct task_struct *child)
|
|
{
|
|
BUG_ON(!child->ptrace);
|
|
|
|
child->ptrace = 0;
|
|
child->parent = child->real_parent;
|
|
list_del_init(&child->ptrace_entry);
|
|
|
|
spin_lock(&child->sighand->siglock);
|
|
|
|
/*
|
|
* Clear all pending traps and TRAPPING. TRAPPING should be
|
|
* cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly.
|
|
*/
|
|
task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK);
|
|
task_clear_jobctl_trapping(child);
|
|
|
|
/*
|
|
* Reinstate JOBCTL_STOP_PENDING if group stop is in effect and
|
|
* @child isn't dead.
|
|
*/
|
|
if (!(child->flags & PF_EXITING) &&
|
|
(child->signal->flags & SIGNAL_STOP_STOPPED ||
|
|
child->signal->group_stop_count)) {
|
|
child->jobctl |= JOBCTL_STOP_PENDING;
|
|
|
|
/*
|
|
* This is only possible if this thread was cloned by the
|
|
* traced task running in the stopped group, set the signal
|
|
* for the future reports.
|
|
* FIXME: we should change ptrace_init_task() to handle this
|
|
* case.
|
|
*/
|
|
if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
|
|
child->jobctl |= SIGSTOP;
|
|
}
|
|
|
|
/*
|
|
* If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
|
|
* @child in the butt. Note that @resume should be used iff @child
|
|
* is in TASK_TRACED; otherwise, we might unduly disrupt
|
|
* TASK_KILLABLE sleeps.
|
|
*/
|
|
if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
|
|
ptrace_signal_wake_up(child, true);
|
|
|
|
spin_unlock(&child->sighand->siglock);
|
|
}
|
|
|
|
/* Ensure that nothing can wake it up, even SIGKILL */
|
|
static bool ptrace_freeze_traced(struct task_struct *task)
|
|
{
|
|
bool ret = false;
|
|
|
|
/* Lockless, nobody but us can set this flag */
|
|
if (task->jobctl & JOBCTL_LISTENING)
|
|
return ret;
|
|
|
|
spin_lock_irq(&task->sighand->siglock);
|
|
if (task_is_traced(task) && !__fatal_signal_pending(task)) {
|
|
task->state = __TASK_TRACED;
|
|
ret = true;
|
|
}
|
|
spin_unlock_irq(&task->sighand->siglock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void ptrace_unfreeze_traced(struct task_struct *task)
|
|
{
|
|
if (task->state != __TASK_TRACED)
|
|
return;
|
|
|
|
WARN_ON(!task->ptrace || task->parent != current);
|
|
|
|
spin_lock_irq(&task->sighand->siglock);
|
|
if (__fatal_signal_pending(task))
|
|
wake_up_state(task, __TASK_TRACED);
|
|
else
|
|
task->state = TASK_TRACED;
|
|
spin_unlock_irq(&task->sighand->siglock);
|
|
}
|
|
|
|
/**
|
|
* ptrace_check_attach - check whether ptracee is ready for ptrace operation
|
|
* @child: ptracee to check for
|
|
* @ignore_state: don't check whether @child is currently %TASK_TRACED
|
|
*
|
|
* Check whether @child is being ptraced by %current and ready for further
|
|
* ptrace operations. If @ignore_state is %false, @child also should be in
|
|
* %TASK_TRACED state and on return the child is guaranteed to be traced
|
|
* and not executing. If @ignore_state is %true, @child can be in any
|
|
* state.
|
|
*
|
|
* CONTEXT:
|
|
* Grabs and releases tasklist_lock and @child->sighand->siglock.
|
|
*
|
|
* RETURNS:
|
|
* 0 on success, -ESRCH if %child is not ready.
|
|
*/
|
|
static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
|
|
{
|
|
int ret = -ESRCH;
|
|
|
|
/*
|
|
* We take the read lock around doing both checks to close a
|
|
* possible race where someone else was tracing our child and
|
|
* detached between these two checks. After this locked check,
|
|
* we are sure that this is our traced child and that can only
|
|
* be changed by us so it's not changing right after this.
|
|
*/
|
|
read_lock(&tasklist_lock);
|
|
if (child->ptrace && child->parent == current) {
|
|
WARN_ON(child->state == __TASK_TRACED);
|
|
/*
|
|
* child->sighand can't be NULL, release_task()
|
|
* does ptrace_unlink() before __exit_signal().
|
|
*/
|
|
if (ignore_state || ptrace_freeze_traced(child))
|
|
ret = 0;
|
|
}
|
|
read_unlock(&tasklist_lock);
|
|
|
|
if (!ret && !ignore_state) {
|
|
if (!wait_task_inactive(child, __TASK_TRACED)) {
|
|
/*
|
|
* This can only happen if may_ptrace_stop() fails and
|
|
* ptrace_stop() changes ->state back to TASK_RUNNING,
|
|
* so we should not worry about leaking __TASK_TRACED.
|
|
*/
|
|
WARN_ON(child->state == __TASK_TRACED);
|
|
ret = -ESRCH;
|
|
}
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
|
|
{
|
|
if (mode & PTRACE_MODE_NOAUDIT)
|
|
return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
|
|
else
|
|
return has_ns_capability(current, ns, CAP_SYS_PTRACE);
|
|
}
|
|
|
|
/* Returns 0 on success, -errno on denial. */
|
|
static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
|
|
{
|
|
const struct cred *cred = current_cred(), *tcred;
|
|
|
|
/* May we inspect the given task?
|
|
* This check is used both for attaching with ptrace
|
|
* and for allowing access to sensitive information in /proc.
|
|
*
|
|
* ptrace_attach denies several cases that /proc allows
|
|
* because setting up the necessary parent/child relationship
|
|
* or halting the specified task is impossible.
|
|
*/
|
|
int dumpable = 0;
|
|
/* Don't let security modules deny introspection */
|
|
if (same_thread_group(task, current))
|
|
return 0;
|
|
rcu_read_lock();
|
|
tcred = __task_cred(task);
|
|
if (uid_eq(cred->uid, tcred->euid) &&
|
|
uid_eq(cred->uid, tcred->suid) &&
|
|
uid_eq(cred->uid, tcred->uid) &&
|
|
gid_eq(cred->gid, tcred->egid) &&
|
|
gid_eq(cred->gid, tcred->sgid) &&
|
|
gid_eq(cred->gid, tcred->gid))
|
|
goto ok;
|
|
if (ptrace_has_cap(tcred->user_ns, mode))
|
|
goto ok;
|
|
rcu_read_unlock();
|
|
return -EPERM;
|
|
ok:
|
|
rcu_read_unlock();
|
|
smp_rmb();
|
|
if (task->mm)
|
|
dumpable = get_dumpable(task->mm);
|
|
rcu_read_lock();
|
|
if (dumpable != SUID_DUMP_USER &&
|
|
!ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
|
|
rcu_read_unlock();
|
|
return -EPERM;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return security_ptrace_access_check(task, mode);
|
|
}
|
|
|
|
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
|
|
{
|
|
int err;
|
|
task_lock(task);
|
|
err = __ptrace_may_access(task, mode);
|
|
task_unlock(task);
|
|
return !err;
|
|
}
|
|
|
|
static int ptrace_attach(struct task_struct *task, long request,
|
|
unsigned long addr,
|
|
unsigned long flags)
|
|
{
|
|
bool seize = (request == PTRACE_SEIZE);
|
|
int retval;
|
|
|
|
retval = -EIO;
|
|
if (seize) {
|
|
if (addr != 0)
|
|
goto out;
|
|
if (flags & ~(unsigned long)PTRACE_O_MASK)
|
|
goto out;
|
|
flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
|
|
} else {
|
|
flags = PT_PTRACED;
|
|
}
|
|
|
|
audit_ptrace(task);
|
|
|
|
retval = -EPERM;
|
|
if (unlikely(task->flags & PF_KTHREAD))
|
|
goto out;
|
|
if (same_thread_group(task, current))
|
|
goto out;
|
|
|
|
/*
|
|
* Protect exec's credential calculations against our interference;
|
|
* SUID, SGID and LSM creds get determined differently
|
|
* under ptrace.
|
|
*/
|
|
retval = -ERESTARTNOINTR;
|
|
if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
|
|
goto out;
|
|
|
|
task_lock(task);
|
|
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
|
|
task_unlock(task);
|
|
if (retval)
|
|
goto unlock_creds;
|
|
|
|
write_lock_irq(&tasklist_lock);
|
|
retval = -EPERM;
|
|
if (unlikely(task->exit_state))
|
|
goto unlock_tasklist;
|
|
if (task->ptrace)
|
|
goto unlock_tasklist;
|
|
|
|
if (seize)
|
|
flags |= PT_SEIZED;
|
|
rcu_read_lock();
|
|
if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
|
|
flags |= PT_PTRACE_CAP;
|
|
rcu_read_unlock();
|
|
task->ptrace = flags;
|
|
|
|
__ptrace_link(task, current);
|
|
|
|
/* SEIZE doesn't trap tracee on attach */
|
|
if (!seize)
|
|
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
|
|
|
|
spin_lock(&task->sighand->siglock);
|
|
|
|
/*
|
|
* If the task is already STOPPED, set JOBCTL_TRAP_STOP and
|
|
* TRAPPING, and kick it so that it transits to TRACED. TRAPPING
|
|
* will be cleared if the child completes the transition or any
|
|
* event which clears the group stop states happens. We'll wait
|
|
* for the transition to complete before returning from this
|
|
* function.
|
|
*
|
|
* This hides STOPPED -> RUNNING -> TRACED transition from the
|
|
* attaching thread but a different thread in the same group can
|
|
* still observe the transient RUNNING state. IOW, if another
|
|
* thread's WNOHANG wait(2) on the stopped tracee races against
|
|
* ATTACH, the wait(2) may fail due to the transient RUNNING.
|
|
*
|
|
* The following task_is_stopped() test is safe as both transitions
|
|
* in and out of STOPPED are protected by siglock.
|
|
*/
|
|
if (task_is_stopped(task) &&
|
|
task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
|
|
signal_wake_up_state(task, __TASK_STOPPED);
|
|
|
|
spin_unlock(&task->sighand->siglock);
|
|
|
|
retval = 0;
|
|
unlock_tasklist:
|
|
write_unlock_irq(&tasklist_lock);
|
|
unlock_creds:
|
|
mutex_unlock(&task->signal->cred_guard_mutex);
|
|
out:
|
|
if (!retval) {
|
|
wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
|
|
TASK_UNINTERRUPTIBLE);
|
|
proc_ptrace_connector(task, PTRACE_ATTACH);
|
|
}
|
|
|
|
return retval;
|
|
}
|
|
|
|
/**
|
|
* ptrace_traceme -- helper for PTRACE_TRACEME
|
|
*
|
|
* Performs checks and sets PT_PTRACED.
|
|
* Should be used by all ptrace implementations for PTRACE_TRACEME.
|
|
*/
|
|
static int ptrace_traceme(void)
|
|
{
|
|
int ret = -EPERM;
|
|
|
|
write_lock_irq(&tasklist_lock);
|
|
/* Are we already being traced? */
|
|
if (!current->ptrace) {
|
|
ret = security_ptrace_traceme(current->parent);
|
|
/*
|
|
* Check PF_EXITING to ensure ->real_parent has not passed
|
|
* exit_ptrace(). Otherwise we don't report the error but
|
|
* pretend ->real_parent untraces us right after return.
|
|
*/
|
|
if (!ret && !(current->real_parent->flags & PF_EXITING)) {
|
|
current->ptrace = PT_PTRACED;
|
|
__ptrace_link(current, current->real_parent);
|
|
}
|
|
}
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Called with irqs disabled, returns true if childs should reap themselves.
|
|
*/
|
|
static int ignoring_children(struct sighand_struct *sigh)
|
|
{
|
|
int ret;
|
|
spin_lock(&sigh->siglock);
|
|
ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) ||
|
|
(sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT);
|
|
spin_unlock(&sigh->siglock);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Called with tasklist_lock held for writing.
|
|
* Unlink a traced task, and clean it up if it was a traced zombie.
|
|
* Return true if it needs to be reaped with release_task().
|
|
* (We can't call release_task() here because we already hold tasklist_lock.)
|
|
*
|
|
* If it's a zombie, our attachedness prevented normal parent notification
|
|
* or self-reaping. Do notification now if it would have happened earlier.
|
|
* If it should reap itself, return true.
|
|
*
|
|
* If it's our own child, there is no notification to do. But if our normal
|
|
* children self-reap, then this child was prevented by ptrace and we must
|
|
* reap it now, in that case we must also wake up sub-threads sleeping in
|
|
* do_wait().
|
|
*/
|
|
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
|
|
{
|
|
bool dead;
|
|
|
|
__ptrace_unlink(p);
|
|
|
|
if (p->exit_state != EXIT_ZOMBIE)
|
|
return false;
|
|
|
|
dead = !thread_group_leader(p);
|
|
|
|
if (!dead && thread_group_empty(p)) {
|
|
if (!same_thread_group(p->real_parent, tracer))
|
|
dead = do_notify_parent(p, p->exit_signal);
|
|
else if (ignoring_children(tracer->sighand)) {
|
|
__wake_up_parent(p, tracer);
|
|
dead = true;
|
|
}
|
|
}
|
|
/* Mark it as in the process of being reaped. */
|
|
if (dead)
|
|
p->exit_state = EXIT_DEAD;
|
|
return dead;
|
|
}
|
|
|
|
static int ptrace_detach(struct task_struct *child, unsigned int data)
|
|
{
|
|
if (!valid_signal(data))
|
|
return -EIO;
|
|
|
|
/* Architecture-specific hardware disable .. */
|
|
ptrace_disable(child);
|
|
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
|
|
|
|
write_lock_irq(&tasklist_lock);
|
|
/*
|
|
* We rely on ptrace_freeze_traced(). It can't be killed and
|
|
* untraced by another thread, it can't be a zombie.
|
|
*/
|
|
WARN_ON(!child->ptrace || child->exit_state);
|
|
/*
|
|
* tasklist_lock avoids the race with wait_task_stopped(), see
|
|
* the comment in ptrace_resume().
|
|
*/
|
|
child->exit_code = data;
|
|
__ptrace_detach(current, child);
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
proc_ptrace_connector(child, PTRACE_DETACH);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Detach all tasks we were using ptrace on. Called with tasklist held
|
|
* for writing.
|
|
*/
|
|
void exit_ptrace(struct task_struct *tracer, struct list_head *dead)
|
|
{
|
|
struct task_struct *p, *n;
|
|
|
|
list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
|
|
if (unlikely(p->ptrace & PT_EXITKILL))
|
|
send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
|
|
|
|
if (__ptrace_detach(tracer, p))
|
|
list_add(&p->ptrace_entry, dead);
|
|
}
|
|
}
|
|
|
|
int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
|
|
{
|
|
int copied = 0;
|
|
|
|
while (len > 0) {
|
|
char buf[128];
|
|
int this_len, retval;
|
|
|
|
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
|
|
retval = access_process_vm(tsk, src, buf, this_len, 0);
|
|
if (!retval) {
|
|
if (copied)
|
|
break;
|
|
return -EIO;
|
|
}
|
|
if (copy_to_user(dst, buf, retval))
|
|
return -EFAULT;
|
|
copied += retval;
|
|
src += retval;
|
|
dst += retval;
|
|
len -= retval;
|
|
}
|
|
return copied;
|
|
}
|
|
|
|
int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len)
|
|
{
|
|
int copied = 0;
|
|
|
|
while (len > 0) {
|
|
char buf[128];
|
|
int this_len, retval;
|
|
|
|
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
|
|
if (copy_from_user(buf, src, this_len))
|
|
return -EFAULT;
|
|
retval = access_process_vm(tsk, dst, buf, this_len, 1);
|
|
if (!retval) {
|
|
if (copied)
|
|
break;
|
|
return -EIO;
|
|
}
|
|
copied += retval;
|
|
src += retval;
|
|
dst += retval;
|
|
len -= retval;
|
|
}
|
|
return copied;
|
|
}
|
|
|
|
static int ptrace_setoptions(struct task_struct *child, unsigned long data)
|
|
{
|
|
unsigned flags;
|
|
|
|
if (data & ~(unsigned long)PTRACE_O_MASK)
|
|
return -EINVAL;
|
|
|
|
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
|
|
if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
|
|
!config_enabled(CONFIG_SECCOMP))
|
|
return -EINVAL;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED ||
|
|
current->ptrace & PT_SUSPEND_SECCOMP)
|
|
return -EPERM;
|
|
}
|
|
|
|
/* Avoid intermediate state when all opts are cleared */
|
|
flags = child->ptrace;
|
|
flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);
|
|
flags |= (data << PT_OPT_FLAG_SHIFT);
|
|
child->ptrace = flags;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
|
|
{
|
|
unsigned long flags;
|
|
int error = -ESRCH;
|
|
|
|
if (lock_task_sighand(child, &flags)) {
|
|
error = -EINVAL;
|
|
if (likely(child->last_siginfo != NULL)) {
|
|
*info = *child->last_siginfo;
|
|
error = 0;
|
|
}
|
|
unlock_task_sighand(child, &flags);
|
|
}
|
|
return error;
|
|
}
|
|
|
|
static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
|
|
{
|
|
unsigned long flags;
|
|
int error = -ESRCH;
|
|
|
|
if (lock_task_sighand(child, &flags)) {
|
|
error = -EINVAL;
|
|
if (likely(child->last_siginfo != NULL)) {
|
|
*child->last_siginfo = *info;
|
|
error = 0;
|
|
}
|
|
unlock_task_sighand(child, &flags);
|
|
}
|
|
return error;
|
|
}
|
|
|
|
static int ptrace_peek_siginfo(struct task_struct *child,
|
|
unsigned long addr,
|
|
unsigned long data)
|
|
{
|
|
struct ptrace_peeksiginfo_args arg;
|
|
struct sigpending *pending;
|
|
struct sigqueue *q;
|
|
int ret, i;
|
|
|
|
ret = copy_from_user(&arg, (void __user *) addr,
|
|
sizeof(struct ptrace_peeksiginfo_args));
|
|
if (ret)
|
|
return -EFAULT;
|
|
|
|
if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED)
|
|
return -EINVAL; /* unknown flags */
|
|
|
|
if (arg.nr < 0)
|
|
return -EINVAL;
|
|
|
|
if (arg.flags & PTRACE_PEEKSIGINFO_SHARED)
|
|
pending = &child->signal->shared_pending;
|
|
else
|
|
pending = &child->pending;
|
|
|
|
for (i = 0; i < arg.nr; ) {
|
|
siginfo_t info;
|
|
s32 off = arg.off + i;
|
|
|
|
spin_lock_irq(&child->sighand->siglock);
|
|
list_for_each_entry(q, &pending->list, list) {
|
|
if (!off--) {
|
|
copy_siginfo(&info, &q->info);
|
|
break;
|
|
}
|
|
}
|
|
spin_unlock_irq(&child->sighand->siglock);
|
|
|
|
if (off >= 0) /* beyond the end of the list */
|
|
break;
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
if (unlikely(is_compat_task())) {
|
|
compat_siginfo_t __user *uinfo = compat_ptr(data);
|
|
|
|
if (copy_siginfo_to_user32(uinfo, &info) ||
|
|
__put_user(info.si_code, &uinfo->si_code)) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
|
|
} else
|
|
#endif
|
|
{
|
|
siginfo_t __user *uinfo = (siginfo_t __user *) data;
|
|
|
|
if (copy_siginfo_to_user(uinfo, &info) ||
|
|
__put_user(info.si_code, &uinfo->si_code)) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
}
|
|
|
|
data += sizeof(siginfo_t);
|
|
i++;
|
|
|
|
if (signal_pending(current))
|
|
break;
|
|
|
|
cond_resched();
|
|
}
|
|
|
|
if (i > 0)
|
|
return i;
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef PTRACE_SINGLESTEP
|
|
#define is_singlestep(request) ((request) == PTRACE_SINGLESTEP)
|
|
#else
|
|
#define is_singlestep(request) 0
|
|
#endif
|
|
|
|
#ifdef PTRACE_SINGLEBLOCK
|
|
#define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK)
|
|
#else
|
|
#define is_singleblock(request) 0
|
|
#endif
|
|
|
|
#ifdef PTRACE_SYSEMU
|
|
#define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP)
|
|
#else
|
|
#define is_sysemu_singlestep(request) 0
|
|
#endif
|
|
|
|
static int ptrace_resume(struct task_struct *child, long request,
|
|
unsigned long data)
|
|
{
|
|
bool need_siglock;
|
|
|
|
if (!valid_signal(data))
|
|
return -EIO;
|
|
|
|
if (request == PTRACE_SYSCALL)
|
|
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
|
|
else
|
|
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
|
|
|
|
#ifdef TIF_SYSCALL_EMU
|
|
if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
|
|
set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
|
|
else
|
|
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
|
|
#endif
|
|
|
|
if (is_singleblock(request)) {
|
|
if (unlikely(!arch_has_block_step()))
|
|
return -EIO;
|
|
user_enable_block_step(child);
|
|
} else if (is_singlestep(request) || is_sysemu_singlestep(request)) {
|
|
if (unlikely(!arch_has_single_step()))
|
|
return -EIO;
|
|
user_enable_single_step(child);
|
|
} else {
|
|
user_disable_single_step(child);
|
|
}
|
|
|
|
/*
|
|
* Change ->exit_code and ->state under siglock to avoid the race
|
|
* with wait_task_stopped() in between; a non-zero ->exit_code will
|
|
* wrongly look like another report from tracee.
|
|
*
|
|
* Note that we need siglock even if ->exit_code == data and/or this
|
|
* status was not reported yet, the new status must not be cleared by
|
|
* wait_task_stopped() after resume.
|
|
*
|
|
* If data == 0 we do not care if wait_task_stopped() reports the old
|
|
* status and clears the code too; this can't race with the tracee, it
|
|
* takes siglock after resume.
|
|
*/
|
|
need_siglock = data && !thread_group_empty(current);
|
|
if (need_siglock)
|
|
spin_lock_irq(&child->sighand->siglock);
|
|
child->exit_code = data;
|
|
wake_up_state(child, __TASK_TRACED);
|
|
if (need_siglock)
|
|
spin_unlock_irq(&child->sighand->siglock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
|
|
|
|
static const struct user_regset *
|
|
find_regset(const struct user_regset_view *view, unsigned int type)
|
|
{
|
|
const struct user_regset *regset;
|
|
int n;
|
|
|
|
for (n = 0; n < view->n; ++n) {
|
|
regset = view->regsets + n;
|
|
if (regset->core_note_type == type)
|
|
return regset;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
|
|
struct iovec *kiov)
|
|
{
|
|
const struct user_regset_view *view = task_user_regset_view(task);
|
|
const struct user_regset *regset = find_regset(view, type);
|
|
int regset_no;
|
|
|
|
if (!regset || (kiov->iov_len % regset->size) != 0)
|
|
return -EINVAL;
|
|
|
|
regset_no = regset - view->regsets;
|
|
kiov->iov_len = min(kiov->iov_len,
|
|
(__kernel_size_t) (regset->n * regset->size));
|
|
|
|
if (req == PTRACE_GETREGSET)
|
|
return copy_regset_to_user(task, view, regset_no, 0,
|
|
kiov->iov_len, kiov->iov_base);
|
|
else
|
|
return copy_regset_from_user(task, view, regset_no, 0,
|
|
kiov->iov_len, kiov->iov_base);
|
|
}
|
|
|
|
/*
|
|
* This is declared in linux/regset.h and defined in machine-dependent
|
|
* code. We put the export here, near the primary machine-neutral use,
|
|
* to ensure no machine forgets it.
|
|
*/
|
|
EXPORT_SYMBOL_GPL(task_user_regset_view);
|
|
#endif
|
|
|
|
int ptrace_request(struct task_struct *child, long request,
|
|
unsigned long addr, unsigned long data)
|
|
{
|
|
bool seized = child->ptrace & PT_SEIZED;
|
|
int ret = -EIO;
|
|
siginfo_t siginfo, *si;
|
|
void __user *datavp = (void __user *) data;
|
|
unsigned long __user *datalp = datavp;
|
|
unsigned long flags;
|
|
|
|
switch (request) {
|
|
case PTRACE_PEEKTEXT:
|
|
case PTRACE_PEEKDATA:
|
|
return generic_ptrace_peekdata(child, addr, data);
|
|
case PTRACE_POKETEXT:
|
|
case PTRACE_POKEDATA:
|
|
return generic_ptrace_pokedata(child, addr, data);
|
|
|
|
#ifdef PTRACE_OLDSETOPTIONS
|
|
case PTRACE_OLDSETOPTIONS:
|
|
#endif
|
|
case PTRACE_SETOPTIONS:
|
|
ret = ptrace_setoptions(child, data);
|
|
break;
|
|
case PTRACE_GETEVENTMSG:
|
|
ret = put_user(child->ptrace_message, datalp);
|
|
break;
|
|
|
|
case PTRACE_PEEKSIGINFO:
|
|
ret = ptrace_peek_siginfo(child, addr, data);
|
|
break;
|
|
|
|
case PTRACE_GETSIGINFO:
|
|
ret = ptrace_getsiginfo(child, &siginfo);
|
|
if (!ret)
|
|
ret = copy_siginfo_to_user(datavp, &siginfo);
|
|
break;
|
|
|
|
case PTRACE_SETSIGINFO:
|
|
if (copy_from_user(&siginfo, datavp, sizeof siginfo))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = ptrace_setsiginfo(child, &siginfo);
|
|
break;
|
|
|
|
case PTRACE_GETSIGMASK:
|
|
if (addr != sizeof(sigset_t)) {
|
|
ret = -EINVAL;
|
|
break;
|
|
}
|
|
|
|
if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t)))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
case PTRACE_SETSIGMASK: {
|
|
sigset_t new_set;
|
|
|
|
if (addr != sizeof(sigset_t)) {
|
|
ret = -EINVAL;
|
|
break;
|
|
}
|
|
|
|
if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
|
|
sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));
|
|
|
|
/*
|
|
* Every thread does recalc_sigpending() after resume, so
|
|
* retarget_shared_pending() and recalc_sigpending() are not
|
|
* called here.
|
|
*/
|
|
spin_lock_irq(&child->sighand->siglock);
|
|
child->blocked = new_set;
|
|
spin_unlock_irq(&child->sighand->siglock);
|
|
|
|
ret = 0;
|
|
break;
|
|
}
|
|
|
|
case PTRACE_INTERRUPT:
|
|
/*
|
|
* Stop tracee without any side-effect on signal or job
|
|
* control. At least one trap is guaranteed to happen
|
|
* after this request. If @child is already trapped, the
|
|
* current trap is not disturbed and another trap will
|
|
* happen after the current trap is ended with PTRACE_CONT.
|
|
*
|
|
* The actual trap might not be PTRACE_EVENT_STOP trap but
|
|
* the pending condition is cleared regardless.
|
|
*/
|
|
if (unlikely(!seized || !lock_task_sighand(child, &flags)))
|
|
break;
|
|
|
|
/*
|
|
* INTERRUPT doesn't disturb existing trap sans one
|
|
* exception. If ptracer issued LISTEN for the current
|
|
* STOP, this INTERRUPT should clear LISTEN and re-trap
|
|
* tracee into STOP.
|
|
*/
|
|
if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
|
|
ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
|
|
|
|
unlock_task_sighand(child, &flags);
|
|
ret = 0;
|
|
break;
|
|
|
|
case PTRACE_LISTEN:
|
|
/*
|
|
* Listen for events. Tracee must be in STOP. It's not
|
|
* resumed per-se but is not considered to be in TRACED by
|
|
* wait(2) or ptrace(2). If an async event (e.g. group
|
|
* stop state change) happens, tracee will enter STOP trap
|
|
* again. Alternatively, ptracer can issue INTERRUPT to
|
|
* finish listening and re-trap tracee into STOP.
|
|
*/
|
|
if (unlikely(!seized || !lock_task_sighand(child, &flags)))
|
|
break;
|
|
|
|
si = child->last_siginfo;
|
|
if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) {
|
|
child->jobctl |= JOBCTL_LISTENING;
|
|
/*
|
|
* If NOTIFY is set, it means event happened between
|
|
* start of this trap and now. Trigger re-trap.
|
|
*/
|
|
if (child->jobctl & JOBCTL_TRAP_NOTIFY)
|
|
ptrace_signal_wake_up(child, true);
|
|
ret = 0;
|
|
}
|
|
unlock_task_sighand(child, &flags);
|
|
break;
|
|
|
|
case PTRACE_DETACH: /* detach a process that was attached. */
|
|
ret = ptrace_detach(child, data);
|
|
break;
|
|
|
|
#ifdef CONFIG_BINFMT_ELF_FDPIC
|
|
case PTRACE_GETFDPIC: {
|
|
struct mm_struct *mm = get_task_mm(child);
|
|
unsigned long tmp = 0;
|
|
|
|
ret = -ESRCH;
|
|
if (!mm)
|
|
break;
|
|
|
|
switch (addr) {
|
|
case PTRACE_GETFDPIC_EXEC:
|
|
tmp = mm->context.exec_fdpic_loadmap;
|
|
break;
|
|
case PTRACE_GETFDPIC_INTERP:
|
|
tmp = mm->context.interp_fdpic_loadmap;
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
mmput(mm);
|
|
|
|
ret = put_user(tmp, datalp);
|
|
break;
|
|
}
|
|
#endif
|
|
|
|
#ifdef PTRACE_SINGLESTEP
|
|
case PTRACE_SINGLESTEP:
|
|
#endif
|
|
#ifdef PTRACE_SINGLEBLOCK
|
|
case PTRACE_SINGLEBLOCK:
|
|
#endif
|
|
#ifdef PTRACE_SYSEMU
|
|
case PTRACE_SYSEMU:
|
|
case PTRACE_SYSEMU_SINGLESTEP:
|
|
#endif
|
|
case PTRACE_SYSCALL:
|
|
case PTRACE_CONT:
|
|
return ptrace_resume(child, request, data);
|
|
|
|
case PTRACE_KILL:
|
|
if (child->exit_state) /* already dead */
|
|
return 0;
|
|
return ptrace_resume(child, request, SIGKILL);
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
|
|
case PTRACE_GETREGSET:
|
|
case PTRACE_SETREGSET: {
|
|
struct iovec kiov;
|
|
struct iovec __user *uiov = datavp;
|
|
|
|
if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
|
|
return -EFAULT;
|
|
|
|
if (__get_user(kiov.iov_base, &uiov->iov_base) ||
|
|
__get_user(kiov.iov_len, &uiov->iov_len))
|
|
return -EFAULT;
|
|
|
|
ret = ptrace_regset(child, request, addr, &kiov);
|
|
if (!ret)
|
|
ret = __put_user(kiov.iov_len, &uiov->iov_len);
|
|
break;
|
|
}
|
|
#endif
|
|
default:
|
|
break;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static struct task_struct *ptrace_get_task_struct(pid_t pid)
|
|
{
|
|
struct task_struct *child;
|
|
|
|
rcu_read_lock();
|
|
child = find_task_by_vpid(pid);
|
|
if (child)
|
|
get_task_struct(child);
|
|
rcu_read_unlock();
|
|
|
|
if (!child)
|
|
return ERR_PTR(-ESRCH);
|
|
return child;
|
|
}
|
|
|
|
#ifndef arch_ptrace_attach
|
|
#define arch_ptrace_attach(child) do { } while (0)
|
|
#endif
|
|
|
|
SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
|
|
unsigned long, data)
|
|
{
|
|
struct task_struct *child;
|
|
long ret;
|
|
|
|
if (request == PTRACE_TRACEME) {
|
|
ret = ptrace_traceme();
|
|
if (!ret)
|
|
arch_ptrace_attach(current);
|
|
goto out;
|
|
}
|
|
|
|
child = ptrace_get_task_struct(pid);
|
|
if (IS_ERR(child)) {
|
|
ret = PTR_ERR(child);
|
|
goto out;
|
|
}
|
|
|
|
if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
|
|
ret = ptrace_attach(child, request, addr, data);
|
|
/*
|
|
* Some architectures need to do book-keeping after
|
|
* a ptrace attach.
|
|
*/
|
|
if (!ret)
|
|
arch_ptrace_attach(child);
|
|
goto out_put_task_struct;
|
|
}
|
|
|
|
ret = ptrace_check_attach(child, request == PTRACE_KILL ||
|
|
request == PTRACE_INTERRUPT);
|
|
if (ret < 0)
|
|
goto out_put_task_struct;
|
|
|
|
ret = arch_ptrace(child, request, addr, data);
|
|
if (ret || request != PTRACE_DETACH)
|
|
ptrace_unfreeze_traced(child);
|
|
|
|
out_put_task_struct:
|
|
put_task_struct(child);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
|
|
unsigned long data)
|
|
{
|
|
unsigned long tmp;
|
|
int copied;
|
|
|
|
copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0);
|
|
if (copied != sizeof(tmp))
|
|
return -EIO;
|
|
return put_user(tmp, (unsigned long __user *)data);
|
|
}
|
|
|
|
int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
|
|
unsigned long data)
|
|
{
|
|
int copied;
|
|
|
|
copied = access_process_vm(tsk, addr, &data, sizeof(data), 1);
|
|
return (copied == sizeof(data)) ? 0 : -EIO;
|
|
}
|
|
|
|
#if defined CONFIG_COMPAT
|
|
|
|
int compat_ptrace_request(struct task_struct *child, compat_long_t request,
|
|
compat_ulong_t addr, compat_ulong_t data)
|
|
{
|
|
compat_ulong_t __user *datap = compat_ptr(data);
|
|
compat_ulong_t word;
|
|
siginfo_t siginfo;
|
|
int ret;
|
|
|
|
switch (request) {
|
|
case PTRACE_PEEKTEXT:
|
|
case PTRACE_PEEKDATA:
|
|
ret = access_process_vm(child, addr, &word, sizeof(word), 0);
|
|
if (ret != sizeof(word))
|
|
ret = -EIO;
|
|
else
|
|
ret = put_user(word, datap);
|
|
break;
|
|
|
|
case PTRACE_POKETEXT:
|
|
case PTRACE_POKEDATA:
|
|
ret = access_process_vm(child, addr, &data, sizeof(data), 1);
|
|
ret = (ret != sizeof(data) ? -EIO : 0);
|
|
break;
|
|
|
|
case PTRACE_GETEVENTMSG:
|
|
ret = put_user((compat_ulong_t) child->ptrace_message, datap);
|
|
break;
|
|
|
|
case PTRACE_GETSIGINFO:
|
|
ret = ptrace_getsiginfo(child, &siginfo);
|
|
if (!ret)
|
|
ret = copy_siginfo_to_user32(
|
|
(struct compat_siginfo __user *) datap,
|
|
&siginfo);
|
|
break;
|
|
|
|
case PTRACE_SETSIGINFO:
|
|
memset(&siginfo, 0, sizeof siginfo);
|
|
if (copy_siginfo_from_user32(
|
|
&siginfo, (struct compat_siginfo __user *) datap))
|
|
ret = -EFAULT;
|
|
else
|
|
ret = ptrace_setsiginfo(child, &siginfo);
|
|
break;
|
|
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
|
|
case PTRACE_GETREGSET:
|
|
case PTRACE_SETREGSET:
|
|
{
|
|
struct iovec kiov;
|
|
struct compat_iovec __user *uiov =
|
|
(struct compat_iovec __user *) datap;
|
|
compat_uptr_t ptr;
|
|
compat_size_t len;
|
|
|
|
if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
|
|
return -EFAULT;
|
|
|
|
if (__get_user(ptr, &uiov->iov_base) ||
|
|
__get_user(len, &uiov->iov_len))
|
|
return -EFAULT;
|
|
|
|
kiov.iov_base = compat_ptr(ptr);
|
|
kiov.iov_len = len;
|
|
|
|
ret = ptrace_regset(child, request, addr, &kiov);
|
|
if (!ret)
|
|
ret = __put_user(kiov.iov_len, &uiov->iov_len);
|
|
break;
|
|
}
|
|
#endif
|
|
|
|
default:
|
|
ret = ptrace_request(child, request, addr, data);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
|
|
compat_long_t, addr, compat_long_t, data)
|
|
{
|
|
struct task_struct *child;
|
|
long ret;
|
|
|
|
if (request == PTRACE_TRACEME) {
|
|
ret = ptrace_traceme();
|
|
goto out;
|
|
}
|
|
|
|
child = ptrace_get_task_struct(pid);
|
|
if (IS_ERR(child)) {
|
|
ret = PTR_ERR(child);
|
|
goto out;
|
|
}
|
|
|
|
if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
|
|
ret = ptrace_attach(child, request, addr, data);
|
|
/*
|
|
* Some architectures need to do book-keeping after
|
|
* a ptrace attach.
|
|
*/
|
|
if (!ret)
|
|
arch_ptrace_attach(child);
|
|
goto out_put_task_struct;
|
|
}
|
|
|
|
ret = ptrace_check_attach(child, request == PTRACE_KILL ||
|
|
request == PTRACE_INTERRUPT);
|
|
if (!ret) {
|
|
ret = compat_arch_ptrace(child, request, addr, data);
|
|
if (ret || request != PTRACE_DETACH)
|
|
ptrace_unfreeze_traced(child);
|
|
}
|
|
|
|
out_put_task_struct:
|
|
put_task_struct(child);
|
|
out:
|
|
return ret;
|
|
}
|
|
#endif /* CONFIG_COMPAT */
|