job control: reorganize wait_task_stopped()

wait_task_stopped() tested task_stopped_code() without acquiring
siglock and, if stop condition existed, called wait_task_stopped() and
directly returned the result.  This patch moves the initial
task_stopped_code() testing into wait_task_stopped() and make
wait_consider_task() fall through to wait_task_continue() on 0 return.

This is for the following two reasons.

* Because the initial task_stopped_code() test is done without
  acquiring siglock, it may race against SIGCONT generation.  The
  stopped condition might have been replaced by continued state by the
  time wait_task_stopped() acquired siglock.  This may lead to
  unexpected failure of WNOHANG waits.

  This reorganization addresses this single race case but there are
  other cases - TASK_RUNNING -> TASK_STOPPED transition and EXIT_*
  transitions.

* Scheduled ptrace updates require changes to the initial test which
  would fit better inside wait_task_stopped().

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>

diff --git a/kernel/exit.c b/kernel/exit.c
index 5cbc83e83a5d7858a2a3309a41ae59d422c044c7..33837936b98cbea299cfa8fd4e7daba4f7f10277 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1377,11 +1377,23 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace)
        return NULL;
 }
 
-/*
- * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
- * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
- * the lock and this task is uninteresting.  If we return nonzero, we have
- * released the lock and the system call should return.
+/**
+ * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED
+ * @wo: wait options
+ * @ptrace: is the wait for ptrace
+ * @p: task to wait for
+ *
+ * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED.
+ *
+ * CONTEXT:
+ * read_lock(&tasklist_lock), which is released if return value is
+ * non-zero.  Also, grabs and releases @p->sighand->siglock.
+ *
+ * RETURNS:
+ * 0 if wait condition didn't exist and search for other wait conditions
+ * should continue.  Non-zero return, -errno on failure and @p's pid on
+ * success, implies that tasklist_lock is released and wait condition
+ * search should terminate.
  */
 static int wait_task_stopped(struct wait_opts *wo,
                                int ptrace, struct task_struct *p)
@@ -1397,6 +1409,9 @@ static int wait_task_stopped(struct wait_opts *wo,
        if (!ptrace && !(wo->wo_flags & WUNTRACED))
                return 0;
 
+       if (!task_stopped_code(p, ptrace))
+               return 0;
+
        exit_code = 0;
        spin_lock_irq(&p->sighand->siglock);
 
@@ -1607,8 +1622,9 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
         * Wait for stopped.  Depending on @ptrace, different stopped state
         * is used and the two don't interact with each other.
         */
-       if (task_stopped_code(p, ptrace))
-               return wait_task_stopped(wo, ptrace, p);
+       ret = wait_task_stopped(wo, ptrace, p);
+       if (ret)
+               return ret;
 
        /*
         * Wait for continued.  There's only one continued state and the