summaryrefslogtreecommitdiffstats
path: root/kernel/ptrace.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2011-03-23 10:37:00 +0100
committerTejun Heo <tj@kernel.org>2011-03-23 10:37:00 +0100
commitd79fdd6d96f46fabb779d86332e3677c6f5c2a4f (patch)
tree2797e34888c687b47997b7c7ea3150468bcbb737 /kernel/ptrace.c
parent5224fa3660ad3881d2f2ad726d22614117963f10 (diff)
downloadlinux-d79fdd6d96f46fabb779d86332e3677c6f5c2a4f.tar.bz2
ptrace: Clean transitions between TASK_STOPPED and TRACED
Currently, if the task is STOPPED on ptrace attach, it's left alone and the state is silently changed to TRACED on the next ptrace call. The behavior breaks the assumption that arch_ptrace_stop() is called before any task is poked by ptrace and is ugly in that a task manipulates the state of another task directly. With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and TRACED can be made clean. The tracer can use the flag to tell the tracee to retry stop on attach and detach. On retry, the tracee will enter the desired state in the correct way. The lower 16bits of task->group_stop is used to remember the signal number which caused the last group stop. This is used while retrying for ptrace attach as the original group_exit_code could have been consumed with wait(2) by then. As the real parent may wait(2) and consume the group_exit_code anytime, the group_exit_code needs to be saved separately so that it can be used when switching from regular sleep to ptrace_stop(). This is recorded in the lower 16bits of task->group_stop. If a task is already stopped and there's no intervening SIGCONT, a ptrace request immediately following a successful PTRACE_ATTACH should always succeed even if the tracer doesn't wait(2) for attach completion; however, with this change, the tracee might still be TASK_RUNNING trying to enter TASK_TRACED which would cause the following request to fail with -ESRCH. This intermediate state is hidden from the ptracer by setting GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait for it to clear on its signal->wait_chldexit. Completing the transition or getting killed clears TRAPPING and wakes up the tracer. Note that the STOPPED -> RUNNING -> TRACED transition is still visible to other threads which are in the same group as the ptracer and the reverse transition is visible to all. Please read the comments for details. Oleg: * Spotted a race condition where a task may retry group stop without proper bookkeeping. Fixed by redoing bookkeeping on retry. * Spotted that the transition is visible to userland in several different ways. Most are fixed with GROUP_STOP_TRAPPING. Unhandled corner case is documented. * Pointed out not setting GROUP_STOP_SIGMASK on an already stopped task would result in more consistent behavior. * Pointed out that calling ptrace_stop() from do_signal_stop() in TASK_STOPPED can race with group stop start logic and then confuse the TRAPPING wait in ptrace_check_attach(). ptrace_stop() is now called with TASK_RUNNING. * Suggested using signal->wait_chldexit instead of bit wait. * Spotted a race condition between TRACED transition and clearing of TRAPPING. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Diffstat (limited to 'kernel/ptrace.c')
-rw-r--r--kernel/ptrace.c49
1 files changed, 44 insertions, 5 deletions
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 6acf8954017c..745fc2dd00c5 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -49,14 +49,22 @@ static void ptrace_untrace(struct task_struct *child)
spin_lock(&child->sighand->siglock);
if (task_is_traced(child)) {
/*
- * If the group stop is completed or in progress,
- * this thread was already counted as stopped.
+ * 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)
- __set_task_state(child, TASK_STOPPED);
- else
- signal_wake_up(child, 1);
+ child->group_stop |= GROUP_STOP_PENDING;
+ signal_wake_up(child, 1);
}
spin_unlock(&child->sighand->siglock);
}
@@ -165,6 +173,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
static int ptrace_attach(struct task_struct *task)
{
+ bool wait_trap = false;
int retval;
audit_ptrace(task);
@@ -204,12 +213,42 @@ static int ptrace_attach(struct task_struct *task)
__ptrace_link(task, current);
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+ spin_lock(&task->sighand->siglock);
+
+ /*
+ * If the task is already STOPPED, set GROUP_STOP_PENDING 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->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING;
+ signal_wake_up(task, 1);
+ wait_trap = true;
+ }
+
+ 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 (wait_trap)
+ wait_event(current->signal->wait_chldexit,
+ !(task->group_stop & GROUP_STOP_TRAPPING));
return retval;
}