*/
#include <linux/capability.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/cn_proc.h>
+static int ptrace_trapping_sleep_fn(void *flags)
+{
+ schedule();
+ return 0;
+}
+
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
child->parent = new_parent;
}
-/*
- * Turn a tracing stop into a normal stop now, since with no tracer there
- * would be no way to wake it up with SIGCONT or SIGKILL. If there was a
- * signal sent that would resume the child, but didn't because it was in
- * TASK_TRACED, resume it now.
- * Requires that irqs be disabled.
- */
-static void ptrace_untrace(struct task_struct *child)
-{
- spin_lock(&child->sighand->siglock);
- if (task_is_traced(child)) {
- /*
- * If group stop is completed or in progress, it should
- * participate in the group stop. Set GROUP_STOP_PENDING
- * before kicking it.
- *
- * This involves 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.
- */
- if (child->signal->flags & SIGNAL_STOP_STOPPED ||
- child->signal->group_stop_count)
- child->group_stop |= GROUP_STOP_PENDING;
- signal_wake_up(child, 1);
- }
- spin_unlock(&child->sighand->siglock);
-}
-
-/*
- * unptrace a task: move it back to its original parent and
- * remove it from the ptrace list.
+/**
+ * __ptrace_unlink - unlink ptracee and restore its execution state
+ * @child: ptracee to be unlinked
*
- * Must be called with the tasklist lock write-held.
+ * 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)
{
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
- if (task_is_traced(child))
- ptrace_untrace(child);
+ 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))
+ signal_wake_up(child, task_is_traced(child));
+
+ spin_unlock(&child->sighand->siglock);
}
-/*
- * Check that we have indeed attached to the thing..
+/**
+ * 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.
*/
-int ptrace_check_attach(struct task_struct *child, int kill)
+int ptrace_check_attach(struct task_struct *child, bool ignore_state)
{
int ret = -ESRCH;
*/
read_lock(&tasklist_lock);
if ((child->ptrace & PT_PTRACED) && child->parent == current) {
- ret = 0;
/*
* child->sighand can't be NULL, release_task()
* does ptrace_unlink() before __exit_signal().
*/
spin_lock_irq(&child->sighand->siglock);
- if (task_is_stopped(child))
- child->state = TASK_TRACED;
- else if (!task_is_traced(child) && !kill)
- ret = -ESRCH;
+ WARN_ON_ONCE(task_is_stopped(child));
+ if (ignore_state || (task_is_traced(child) &&
+ !(child->jobctl & JOBCTL_LISTENING)))
+ ret = 0;
spin_unlock_irq(&child->sighand->siglock);
}
read_unlock(&tasklist_lock);
- if (!ret && !kill)
+ if (!ret && !ignore_state)
ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
/* All systems go.. */
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);
+}
+
int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
const struct cred *cred = current_cred(), *tcred;
return 0;
rcu_read_lock();
tcred = __task_cred(task);
- if ((cred->uid != tcred->euid ||
- cred->uid != tcred->suid ||
- cred->uid != tcred->uid ||
- cred->gid != tcred->egid ||
- cred->gid != tcred->sgid ||
- cred->gid != tcred->gid) &&
- !capable(CAP_SYS_PTRACE)) {
- rcu_read_unlock();
- return -EPERM;
- }
+ 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);
- if (!dumpable && !capable(CAP_SYS_PTRACE))
+ if (!dumpable && !ptrace_has_cap(task_user_ns(task), mode))
return -EPERM;
return security_ptrace_access_check(task, mode);
return !err;
}
-static int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task, long request,
+ unsigned long addr,
+ unsigned long flags)
{
- bool wait_trap = false;
+ 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;
/*
* Protect exec's credential calculations against our interference;
- * interference; SUID, SGID and LSM creds get determined differently
+ * SUID, SGID and LSM creds get determined differently
* under ptrace.
*/
retval = -ERESTARTNOINTR;
if (task->ptrace)
goto unlock_tasklist;
- task->ptrace = PT_PTRACED;
- if (capable(CAP_SYS_PTRACE))
- task->ptrace |= PT_PTRACE_CAP;
+ if (seize)
+ flags |= PT_SEIZED;
+ if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE))
+ flags |= PT_PTRACE_CAP;
+ task->ptrace = flags;
__ptrace_link(task, current);
- send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+
+ /* 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 GROUP_STOP_PENDING and
+ * 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
* 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->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING;
+ if (task_is_stopped(task) &&
+ task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
signal_wake_up(task, 1);
- wait_trap = true;
- }
spin_unlock(&task->sighand->siglock);
unlock_creds:
mutex_unlock(&task->signal->cred_guard_mutex);
out:
- if (wait_trap)
- wait_event(current->signal->wait_chldexit,
- !(task->group_stop & GROUP_STOP_TRAPPING));
+ if (!retval) {
+ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
+ ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE);
+ proc_ptrace_connector(task, PTRACE_ATTACH);
+ }
+
return retval;
}
*/
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
{
+ bool dead;
+
__ptrace_unlink(p);
- if (p->exit_state == EXIT_ZOMBIE) {
- if (!task_detached(p) && thread_group_empty(p)) {
- if (!same_thread_group(p->real_parent, tracer))
- do_notify_parent(p, p->exit_signal);
- else if (ignoring_children(tracer->sighand)) {
- __wake_up_parent(p, tracer);
- p->exit_signal = -1;
- }
- }
- if (task_detached(p)) {
- /* Mark it as in the process of being reaped. */
- p->exit_state = EXIT_DEAD;
- return true;
+ 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;
}
}
-
- return false;
+ /* 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)
}
write_unlock_irq(&tasklist_lock);
+ proc_ptrace_connector(child, PTRACE_DETACH);
if (unlikely(dead))
release_task(child);
static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
- child->ptrace &= ~PT_TRACE_MASK;
+ unsigned flags;
- if (data & PTRACE_O_TRACESYSGOOD)
- child->ptrace |= PT_TRACESYSGOOD;
-
- if (data & PTRACE_O_TRACEFORK)
- child->ptrace |= PT_TRACE_FORK;
-
- if (data & PTRACE_O_TRACEVFORK)
- child->ptrace |= PT_TRACE_VFORK;
-
- if (data & PTRACE_O_TRACECLONE)
- child->ptrace |= PT_TRACE_CLONE;
-
- if (data & PTRACE_O_TRACEEXEC)
- child->ptrace |= PT_TRACE_EXEC;
-
- if (data & PTRACE_O_TRACEVFORKDONE)
- child->ptrace |= PT_TRACE_VFORK_DONE;
+ if (data & ~(unsigned long)PTRACE_O_MASK)
+ return -EINVAL;
- if (data & PTRACE_O_TRACEEXIT)
- child->ptrace |= PT_TRACE_EXIT;
+ /* 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 (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
+ return 0;
}
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
}
child->exit_code = data;
- wake_up_process(child);
+ wake_up_state(child, __TASK_TRACED);
return 0;
}
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;
+ siginfo_t siginfo, *si;
void __user *datavp = (void __user *) data;
unsigned long __user *datalp = datavp;
+ unsigned long flags;
switch (request) {
case PTRACE_PEEKTEXT:
ret = ptrace_setsiginfo(child, &siginfo);
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)))
+ 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)
+ 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;
goto out;
}
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
+ 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.
goto out_put_task_struct;
}
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+ request == PTRACE_INTERRUPT);
if (ret < 0)
goto out_put_task_struct;
goto out;
}
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
+ 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.
goto out_put_task_struct;
}
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+ request == PTRACE_INTERRUPT);
if (!ret)
ret = compat_arch_ptrace(child, request, addr, data);
return ret;
}
#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+ return 0;
+
+ return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+ flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */