Merge branch 'ptrace' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc into ptrace

1 files changed, 279 insertions, 96 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index dc17929ab78a..c15e9792b088 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -124,7 +124,7 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
 
 static int recalc_sigpending_tsk(struct task_struct *t)
 {
-        if (t->signal->group_stop_count > 0 ||
+        if ((t->group_stop & GROUP_STOP_PENDING) ||
             PENDING(&t->pending, &t->blocked) ||
             PENDING(&t->signal->shared_pending, &t->blocked)) {
                 set_tsk_thread_flag(t, TIF_SIGPENDING);
@@ -223,6 +223,83 @@ static inline void print_dropped_signal(int sig)
                                 current->comm, current->pid, sig);
 }
 
+/**
+ * task_clear_group_stop_trapping - clear group stop trapping bit
+ * @task: target task
+ *
+ * If GROUP_STOP_TRAPPING is set, a ptracer is waiting for us.  Clear it
+ * and wake up the ptracer.  Note that we don't need any further locking.
+ * @task->siglock guarantees that @task->parent points to the ptracer.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ */
+static void task_clear_group_stop_trapping(struct task_struct *task)
+{
+        if (unlikely(task->group_stop & GROUP_STOP_TRAPPING)) {
+                task->group_stop &= ~GROUP_STOP_TRAPPING;
+                __wake_up_sync(&task->parent->signal->wait_chldexit,
+                               TASK_UNINTERRUPTIBLE, 1);
+        }
+}
+
+/**
+ * task_clear_group_stop_pending - clear pending group stop
+ * @task: target task
+ *
+ * Clear group stop states for @task.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ */
+void task_clear_group_stop_pending(struct task_struct *task)
+{
+        task->group_stop &= ~(GROUP_STOP_PENDING | GROUP_STOP_CONSUME |
+                              GROUP_STOP_DEQUEUED);
+}
+
+/**
+ * task_participate_group_stop - participate in a group stop
+ * @task: task participating in a group stop
+ *
+ * @task has GROUP_STOP_PENDING set and is participating in a group stop.
+ * Group stop states are cleared and the group stop count is consumed if
+ * %GROUP_STOP_CONSUME was set.  If the consumption completes the group
+ * stop, the appropriate %SIGNAL_* flags are set.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ *
+ * RETURNS:
+ * %true if group stop completion should be notified to the parent, %false
+ * otherwise.
+ */
+static bool task_participate_group_stop(struct task_struct *task)
+{
+        struct signal_struct *sig = task->signal;
+        bool consume = task->group_stop & GROUP_STOP_CONSUME;
+
+        WARN_ON_ONCE(!(task->group_stop & GROUP_STOP_PENDING));
+
+        task_clear_group_stop_pending(task);
+
+        if (!consume)
+                return false;
+
+        if (!WARN_ON_ONCE(sig->group_stop_count == 0))
+                sig->group_stop_count--;
+
+        /*
+         * Tell the caller to notify completion iff we are entering into a
+         * fresh group stop.  Read comment in do_signal_stop() for details.
+         */
+        if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
+                sig->flags = SIGNAL_STOP_STOPPED;
+                return true;
+        }
+        return false;
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
@@ -527,7 +604,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
                  * is to alert stop-signal processing code when another
                  * processor has come along and cleared the flag.
                  */
-                tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
+                current->group_stop |= GROUP_STOP_DEQUEUED;
         }
         if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
                 /*
@@ -727,34 +804,14 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
         } else if (sig == SIGCONT) {
                 unsigned int why;
                 /*
-                 * Remove all stop signals from all queues,
-                 * and wake all threads.
+                 * Remove all stop signals from all queues, wake all threads.
                  */
                 rm_from_queue(SIG_KERNEL_STOP_MASK, &signal->shared_pending);
                 t = p;
                 do {
-                        unsigned int state;
+                        task_clear_group_stop_pending(t);
                         rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
-                        /*
-                         * If there is a handler for SIGCONT, we must make
-                         * sure that no thread returns to user mode before
-                         * we post the signal, in case it was the only
-                         * thread eligible to run the signal handler--then
-                         * it must not do anything between resuming and
-                         * running the handler.  With the TIF_SIGPENDING
-                         * flag set, the thread will pause and acquire the
-                         * siglock that we hold now and until we've queued
-                         * the pending signal.
-                         *
-                         * Wake up the stopped thread _after_ setting
-                         * TIF_SIGPENDING
-                         */
-                        state = __TASK_STOPPED;
-                        if (sig_user_defined(t, SIGCONT) && !sigismember(&t->blocked, SIGCONT)) {
-                                set_tsk_thread_flag(t, TIF_SIGPENDING);
-                                state |= TASK_INTERRUPTIBLE;
-                        }
-                        wake_up_state(t, state);
+                        wake_up_state(t, __TASK_STOPPED);
                 } while_each_thread(p, t);
 
                 /*
@@ -780,13 +837,6 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
                         signal->flags = why | SIGNAL_STOP_CONTINUED;
                         signal->group_stop_count = 0;
                         signal->group_exit_code = 0;
-                } else {
-                        /*
-                         * We are not stopped, but there could be a stop
-                         * signal in the middle of being processed after
-                         * being removed from the queue.  Clear that too.
-                         */
-                        signal->flags &= ~SIGNAL_STOP_DEQUEUED;
                 }
         }
 
@@ -875,6 +925,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
                         signal->group_stop_count = 0;
                         t = p;
                         do {
+                                task_clear_group_stop_pending(t);
                                 sigaddset(&t->pending.signal, SIGKILL);
                                 signal_wake_up(t, 1);
                         } while_each_thread(p, t);
@@ -1109,6 +1160,7 @@ int zap_other_threads(struct task_struct *p)
         p->signal->group_stop_count = 0;
 
         while_each_thread(p, t) {
+                task_clear_group_stop_pending(t);
                 count++;
 
                 /* Don't bother with already dead threads */
@@ -1536,16 +1588,30 @@ int do_notify_parent(struct task_struct *tsk, int sig)
         return ret;
 }
 
-static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
+/**
+ * do_notify_parent_cldstop - notify parent of stopped/continued state change
+ * @tsk: task reporting the state change
+ * @for_ptracer: the notification is for ptracer
+ * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report
+ *
+ * Notify @tsk's parent that the stopped/continued state has changed.  If
+ * @for_ptracer is %false, @tsk's group leader notifies to its real parent.
+ * If %true, @tsk reports to @tsk->parent which should be the ptracer.
+ *
+ * CONTEXT:
+ * Must be called with tasklist_lock at least read locked.
+ */
+static void do_notify_parent_cldstop(struct task_struct *tsk,
+                                     bool for_ptracer, int why)
 {
         struct siginfo info;
         unsigned long flags;
         struct task_struct *parent;
         struct sighand_struct *sighand;
 
-        if (task_ptrace(tsk))
+        if (for_ptracer) {
                 parent = tsk->parent;
-        else {
+        } else {
                 tsk = tsk->group_leader;
                 parent = tsk->real_parent;
         }
@@ -1621,6 +1687,15 @@ static int sigkill_pending(struct task_struct *tsk)
 }
 
 /*
+ * Test whether the target task of the usual cldstop notification - the
+ * real_parent of @child - is in the same group as the ptracer.
+ */
+static bool real_parent_is_ptracer(struct task_struct *child)
+{
+        return same_thread_group(child->parent, child->real_parent);
+}
+
+/*
  * This must be called with current->sighand->siglock held.
  *
  * This should be the path for all ptrace stops.
@@ -1631,10 +1706,12 @@ static int sigkill_pending(struct task_struct *tsk)
  * If we actually decide not to stop at all because the tracer
  * is gone, we keep current->exit_code unless clear_code.
  */
-static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
+static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
         __releases(&current->sighand->siglock)
         __acquires(&current->sighand->siglock)
 {
+        bool gstop_done = false;
+
         if (arch_ptrace_stop_needed(exit_code, info)) {
                 /*
                  * The arch code has something special to do before a
@@ -1655,21 +1732,49 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
         }
 
         /*
-         * If there is a group stop in progress,
-         * we must participate in the bookkeeping.
+         * If @why is CLD_STOPPED, we're trapping to participate in a group
+         * stop.  Do the bookkeeping.  Note that if SIGCONT was delievered
+         * while siglock was released for the arch hook, PENDING could be
+         * clear now.  We act as if SIGCONT is received after TASK_TRACED
+         * is entered - ignore it.
          */
-        if (current->signal->group_stop_count > 0)
-                --current->signal->group_stop_count;
+        if (why == CLD_STOPPED && (current->group_stop & GROUP_STOP_PENDING))
+                gstop_done = task_participate_group_stop(current);
 
         current->last_siginfo = info;
         current->exit_code = exit_code;
 
-        /* Let the debugger run.  */
-        __set_current_state(TASK_TRACED);
+        /*
+         * TRACED should be visible before TRAPPING is cleared; otherwise,
+         * the tracer might fail do_wait().
+         */
+        set_current_state(TASK_TRACED);
+
+        /*
+         * We're committing to trapping.  Clearing GROUP_STOP_TRAPPING and
+         * transition to TASK_TRACED should be atomic with respect to
+         * siglock.  This hsould be done after the arch hook as siglock is
+         * released and regrabbed across it.
+         */
+        task_clear_group_stop_trapping(current);
+
         spin_unlock_irq(&current->sighand->siglock);
         read_lock(&tasklist_lock);
         if (may_ptrace_stop()) {
-                do_notify_parent_cldstop(current, CLD_TRAPPED);
+                /*
+                 * Notify parents of the stop.
+                 *
+                 * While ptraced, there are two parents - the ptracer and
+                 * the real_parent of the group_leader.  The ptracer should
+                 * know about every stop while the real parent is only
+                 * interested in the completion of group stop.  The states
+                 * for the two don't interact with each other.  Notify
+                 * separately unless they're gonna be duplicates.
+                 */
+                do_notify_parent_cldstop(current, true, why);
+                if (gstop_done && !real_parent_is_ptracer(current))
+                        do_notify_parent_cldstop(current, false, why);
+
                 /*
                  * Don't want to allow preemption here, because
                  * sys_ptrace() needs this task to be inactive.
@@ -1684,7 +1789,16 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
                 /*
                  * By the time we got the lock, our tracer went away.
                  * Don't drop the lock yet, another tracer may come.
+                 *
+                 * If @gstop_done, the ptracer went away between group stop
+                 * completion and here.  During detach, it would have set
+                 * GROUP_STOP_PENDING on us and we'll re-enter TASK_STOPPED
+                 * in do_signal_stop() on return, so notifying the real
+                 * parent of the group stop completion is enough.
                  */
+                if (gstop_done)
+                        do_notify_parent_cldstop(current, false, why);
+
                 __set_current_state(TASK_RUNNING);
                 if (clear_code)
                         current->exit_code = 0;
@@ -1728,7 +1842,7 @@ void ptrace_notify(int exit_code)
 
         /* Let the debugger run.  */
         spin_lock_irq(&current->sighand->siglock);
-        ptrace_stop(exit_code, 1, &info);
+        ptrace_stop(exit_code, CLD_TRAPPED, 1, &info);
         spin_unlock_irq(&current->sighand->siglock);
 }
 
@@ -1741,66 +1855,115 @@ void ptrace_notify(int exit_code)
 static int do_signal_stop(int signr)
 {
         struct signal_struct *sig = current->signal;
-        int notify;
 
-        if (!sig->group_stop_count) {
+        if (!(current->group_stop & GROUP_STOP_PENDING)) {
+                unsigned int gstop = GROUP_STOP_PENDING | GROUP_STOP_CONSUME;
                 struct task_struct *t;
 
-                if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
+                /* signr will be recorded in task->group_stop for retries */
+                WARN_ON_ONCE(signr & ~GROUP_STOP_SIGMASK);
+
+                if (!likely(current->group_stop & GROUP_STOP_DEQUEUED) ||
                     unlikely(signal_group_exit(sig)))
                         return 0;
                 /*
-                 * There is no group stop already in progress.
-                 * We must initiate one now.
+                 * There is no group stop already in progress.  We must
+                 * initiate one now.
+                 *
+                 * While ptraced, a task may be resumed while group stop is
+                 * still in effect and then receive a stop signal and
+                 * initiate another group stop.  This deviates from the
+                 * usual behavior as two consecutive stop signals can't
+                 * cause two group stops when !ptraced.  That is why we
+                 * also check !task_is_stopped(t) below.
+                 *
+                 * The condition can be distinguished by testing whether
+                 * SIGNAL_STOP_STOPPED is already set.  Don't generate
+                 * group_exit_code in such case.
+                 *
+                 * This is not necessary for SIGNAL_STOP_CONTINUED because
+                 * an intervening stop signal is required to cause two
+                 * continued events regardless of ptrace.
                  */
-                sig->group_exit_code = signr;
+                if (!(sig->flags & SIGNAL_STOP_STOPPED))
+                        sig->group_exit_code = signr;
+                else
+                        WARN_ON_ONCE(!task_ptrace(current));
 
+                current->group_stop &= ~GROUP_STOP_SIGMASK;
+                current->group_stop |= signr | gstop;
                 sig->group_stop_count = 1;
-                for (t = next_thread(current); t != current; t = next_thread(t))
+                for (t = next_thread(current); t != current;
+                     t = next_thread(t)) {
+                        t->group_stop &= ~GROUP_STOP_SIGMASK;
                         /*
                          * Setting state to TASK_STOPPED for a group
                          * stop is always done with the siglock held,
                          * so this check has no races.
                          */
-                        if (!(t->flags & PF_EXITING) &&
-                            !task_is_stopped_or_traced(t)) {
+                        if (!(t->flags & PF_EXITING) && !task_is_stopped(t)) {
+                                t->group_stop |= signr | gstop;
                                 sig->group_stop_count++;
                                 signal_wake_up(t, 0);
                         }
+                }
         }
-        /*
-         * If there are no other threads in the group, or if there is
-         * a group stop in progress and we are the last to stop, report
-         * to the parent.  When ptraced, every thread reports itself.
-         */
-        notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
-        notify = tracehook_notify_jctl(notify, CLD_STOPPED);
-        /*
-         * tracehook_notify_jctl() can drop and reacquire siglock, so
-         * we keep ->group_stop_count != 0 before the call. If SIGCONT
-         * or SIGKILL comes in between ->group_stop_count == 0.
-         */
-        if (sig->group_stop_count) {
-                if (!--sig->group_stop_count)
-                        sig->flags = SIGNAL_STOP_STOPPED;
-                current->exit_code = sig->group_exit_code;
+retry:
+        if (likely(!task_ptrace(current))) {
+                int notify = 0;
+
+                /*
+                 * If there are no other threads in the group, or if there
+                 * is a group stop in progress and we are the last to stop,
+                 * report to the parent.
+                 */
+                if (task_participate_group_stop(current))
+                        notify = CLD_STOPPED;
+
                 __set_current_state(TASK_STOPPED);
+                spin_unlock_irq(&current->sighand->siglock);
+
+                /*
+                 * Notify the parent of the group stop completion.  Because
+                 * we're not holding either the siglock or tasklist_lock
+                 * here, ptracer may attach inbetween; however, this is for
+                 * group stop and should always be delivered to the real
+                 * parent of the group leader.  The new ptracer will get
+                 * its notification when this task transitions into
+                 * TASK_TRACED.
+                 */
+                if (notify) {
+                        read_lock(&tasklist_lock);
+                        do_notify_parent_cldstop(current, false, notify);
+                        read_unlock(&tasklist_lock);
+                }
+
+                /* Now we don't run again until woken by SIGCONT or SIGKILL */
+                schedule();
+
+                spin_lock_irq(&current->sighand->siglock);
+        } else {
+                ptrace_stop(current->group_stop & GROUP_STOP_SIGMASK,
+                            CLD_STOPPED, 0, NULL);
+                current->exit_code = 0;
         }
-        spin_unlock_irq(&current->sighand->siglock);
 
-        if (notify) {
-                read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(current, notify);
-                read_unlock(&tasklist_lock);
+        /*
+         * GROUP_STOP_PENDING could be set if another group stop has
+         * started since being woken up or ptrace wants us to transit
+         * between TASK_STOPPED and TRACED.  Retry group stop.
+         */
+        if (current->group_stop & GROUP_STOP_PENDING) {
+                WARN_ON_ONCE(!(current->group_stop & GROUP_STOP_SIGMASK));
+                goto retry;
         }
 
-        /* Now we don't run again until woken by SIGCONT or SIGKILL */
-        do {
-                schedule();
-        } while (try_to_freeze());
+        /* PTRACE_ATTACH might have raced with task killing, clear trapping */
+        task_clear_group_stop_trapping(current);
+
+        spin_unlock_irq(&current->sighand->siglock);
 
         tracehook_finish_jctl();
-        current->exit_code = 0;
 
         return 1;
 }
@@ -1814,7 +1977,7 @@ static int ptrace_signal(int signr, siginfo_t *info,
         ptrace_signal_deliver(regs, cookie);
 
         /* Let the debugger run.  */
-        ptrace_stop(signr, 0, info);
+        ptrace_stop(signr, CLD_TRAPPED, 0, info);
 
         /* We're back.  Did the debugger cancel the sig?  */
         signr = current->exit_code;
@@ -1869,18 +2032,36 @@ relock:
          * the CLD_ si_code into SIGNAL_CLD_MASK bits.
          */
         if (unlikely(signal->flags & SIGNAL_CLD_MASK)) {
-                int why = (signal->flags & SIGNAL_STOP_CONTINUED)
-                                ? CLD_CONTINUED : CLD_STOPPED;
+                struct task_struct *leader;
+                int why;
+
+                if (signal->flags & SIGNAL_CLD_CONTINUED)
+                        why = CLD_CONTINUED;
+                else
+                        why = CLD_STOPPED;
+
                 signal->flags &= ~SIGNAL_CLD_MASK;
 
-                why = tracehook_notify_jctl(why, CLD_CONTINUED);
                 spin_unlock_irq(&sighand->siglock);
 
-                if (why) {
-                        read_lock(&tasklist_lock);
-                        do_notify_parent_cldstop(current->group_leader, why);
-                        read_unlock(&tasklist_lock);
-                }
+                /*
+                 * Notify the parent that we're continuing.  This event is
+                 * always per-process and doesn't make whole lot of sense
+                 * for ptracers, who shouldn't consume the state via
+                 * wait(2) either, but, for backward compatibility, notify
+                 * the ptracer of the group leader too unless it's gonna be
+                 * a duplicate.
+                 */
+                read_lock(&tasklist_lock);
+
+                do_notify_parent_cldstop(current, false, why);
+
+                leader = current->group_leader;
+                if (task_ptrace(leader) && !real_parent_is_ptracer(leader))
+                        do_notify_parent_cldstop(leader, true, why);
+
+                read_unlock(&tasklist_lock);
+
                 goto relock;
         }
 
@@ -1897,8 +2078,8 @@ relock:
                 if (unlikely(signr != 0))
                         ka = return_ka;
                 else {
-                        if (unlikely(signal->group_stop_count > 0) &&
-                            do_signal_stop(0))
+                        if (unlikely(current->group_stop &
+                                     GROUP_STOP_PENDING) && do_signal_stop(0))
                                 goto relock;
 
                         signr = dequeue_signal(current, &current->blocked,
@@ -2045,17 +2226,19 @@ void exit_signals(struct task_struct *tsk)
                 if (!signal_pending(t) && !(t->flags & PF_EXITING))
                         recalc_sigpending_and_wake(t);
 
-        if (unlikely(tsk->signal->group_stop_count) &&
-                        !--tsk->signal->group_stop_count) {
-                tsk->signal->flags = SIGNAL_STOP_STOPPED;
-                group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
-        }
+        if (unlikely(tsk->group_stop & GROUP_STOP_PENDING) &&
+            task_participate_group_stop(tsk))
+                group_stop = CLD_STOPPED;
 out:
         spin_unlock_irq(&tsk->sighand->siglock);
 
+        /*
+         * If group stop has completed, deliver the notification.  This
+         * should always go to the real parent of the group leader.
+         */
         if (unlikely(group_stop)) {
                 read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(tsk, group_stop);
+                do_notify_parent_cldstop(tsk, false, group_stop);
                 read_unlock(&tasklist_lock);
         }
 }