[PATCH] fix send_sigqueue() vs thread exit race

posix_timer_event() first checks that the thread (SIGEV_THREAD_ID case)
does not have PF_EXITING flag, then it calls send_sigqueue() which locks
task list.  But if the thread exits in between the kernel will oops
(->sighand == NULL after __exit_sighand).

This patch moves the PF_EXITING check into the send_sigqueue(), it must be
done atomically under tasklist_lock.  When send_sigqueue() detects exiting
thread it returns -1.  In that case posix_timer_event will send the signal
to thread group.

Also, this patch fixes task_struct use-after-free in posix_timer_event.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 38798a2ff994e96c017010b8c2c62db578fe2002..b7b532acd9fc419050f03de66b12acb14d5c4077 100644 (file)
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -427,21 +427,23 @@ int posix_timer_event(struct k_itimer *timr,int si_private)
        timr->sigq->info.si_code = SI_TIMER;
        timr->sigq->info.si_tid = timr->it_id;
        timr->sigq->info.si_value = timr->it_sigev_value;
+
        if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
-               if (unlikely(timr->it_process->flags & PF_EXITING)) {
-                       timr->it_sigev_notify = SIGEV_SIGNAL;
-                       put_task_struct(timr->it_process);
-                       timr->it_process = timr->it_process->group_leader;
-                       goto group;
-               }
-               return send_sigqueue(timr->it_sigev_signo, timr->sigq,
-                       timr->it_process);
-       }
-       else {
-       group:
-               return send_group_sigqueue(timr->it_sigev_signo, timr->sigq,
-                       timr->it_process);
+               struct task_struct *leader;
+               int ret = send_sigqueue(timr->it_sigev_signo, timr->sigq,
+                                       timr->it_process);
+
+               if (likely(ret >= 0))
+                       return ret;
+
+               timr->it_sigev_notify = SIGEV_SIGNAL;
+               leader = timr->it_process->group_leader;
+               put_task_struct(timr->it_process);
+               timr->it_process = leader;
        }
+
+       return send_group_sigqueue(timr->it_sigev_signo, timr->sigq,
+                                  timr->it_process);
 }
 EXPORT_SYMBOL_GPL(posix_timer_event);
 

diff --git a/kernel/signal.c b/kernel/signal.c
index 56e33df2b67f02c52e9df7db5a094dc37ebb9aa3..4980a073237ff45ed28c39b38225c40923da0848 100644 (file)
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1366,16 +1366,16 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
        unsigned long flags;
        int ret = 0;
 
-       /*
-        * We need the tasklist lock even for the specific
-        * thread case (when we don't need to follow the group
-        * lists) in order to avoid races with "p->sighand"
-        * going away or changing from under us.
-        */
        BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
-       read_lock(&tasklist_lock);  
+       read_lock(&tasklist_lock);
+
+       if (unlikely(p->flags & PF_EXITING)) {
+               ret = -1;
+               goto out_err;
+       }
+
        spin_lock_irqsave(&p->sighand->siglock, flags);
-       
+
        if (unlikely(!list_empty(&q->list))) {
                /*
                 * If an SI_TIMER entry is already queue just increment
@@ -1385,7 +1385,7 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
                        BUG();
                q->info.si_overrun++;
                goto out;
-       } 
+       }
        /* Short-circuit ignored signals.  */
        if (sig_ignored(p, sig)) {
                ret = 1;
@@ -1400,8 +1400,10 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
 
 out:
        spin_unlock_irqrestore(&p->sighand->siglock, flags);
+out_err:
        read_unlock(&tasklist_lock);
-       return(ret);
+
+       return ret;
 }
 
 int