sched: stop the unbound recursion in preempt_schedule_context()

preempt_schedule_context() does preempt_enable_notrace() at the end
and this can call the same function again; exception_exit() is heavy
and it is quite possible that need-resched is true again.

1. Change this code to dec preempt_count() and check need_resched()
   by hand.

2. As Linus suggested, we can use the PREEMPT_ACTIVE bit and avoid
   the enable/disable dance around __schedule(). But in this case
   we need to move into sched/core.c.

3. Cosmetic, but x86 forgets to declare this function. This doesn't
   really matter because it is only called by asm helpers, still it
   make sense to add the declaration into asm/preempt.h to match
   preempt_schedule().

Reported-by: Sasha Levin <[email protected]>
Signed-off-by: Oleg Nesterov <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alexander Graf <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Peter Anvin <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: Chuck Ebbert <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

arch/x86/include/asm/preempt.h

@@ -105,6 +105,7 @@ static __always_inline bool should_resched(void)
 # ifdef CONFIG_CONTEXT_TRACKING
     extern asmlinkage void ___preempt_schedule_context(void);
 #   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+    extern asmlinkage void preempt_schedule_context(void);
 # endif
 #endif
 

kernel/context_tracking.c

@@ -107,46 +107,6 @@ void context_tracking_user_enter(void)
 }
 NOKPROBE_SYMBOL(context_tracking_user_enter);
 
-#ifdef CONFIG_PREEMPT
-/**
- * preempt_schedule_context - preempt_schedule called by tracing
- *
- * The tracing infrastructure uses preempt_enable_notrace to prevent
- * recursion and tracing preempt enabling caused by the tracing
- * infrastructure itself. But as tracing can happen in areas coming
- * from userspace or just about to enter userspace, a preempt enable
- * can occur before user_exit() is called. This will cause the scheduler
- * to be called when the system is still in usermode.
- *
- * To prevent this, the preempt_enable_notrace will use this function
- * instead of preempt_schedule() to exit user context if needed before
- * calling the scheduler.
- */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
-{
-	enum ctx_state prev_ctx;
-
-	if (likely(!preemptible()))
-		return;
-
-	/*
-	 * Need to disable preemption in case user_exit() is traced
-	 * and the tracer calls preempt_enable_notrace() causing
-	 * an infinite recursion.
-	 */
-	preempt_disable_notrace();
-	prev_ctx = exception_enter();
-	preempt_enable_no_resched_notrace();
-
-	preempt_schedule();
-
-	preempt_disable_notrace();
-	exception_exit(prev_ctx);
-	preempt_enable_notrace();
-}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_PREEMPT */
-
 /**
  * context_tracking_user_exit - Inform the context tracking that the CPU is
  *                              exiting userspace mode and entering the kernel.

kernel/sched/core.c

@@ -2951,6 +2951,47 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 }
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+{
+	enum ctx_state prev_ctx;
+
+	if (likely(!preemptible()))
+		return;
+
+	do {
+		__preempt_count_add(PREEMPT_ACTIVE);
+		/*
+		 * Needs preempt disabled in case user_exit() is traced
+		 * and the tracer calls preempt_enable_notrace() causing
+		 * an infinite recursion.
+		 */
+		prev_ctx = exception_enter();
+		__schedule();
+		exception_exit(prev_ctx);
+
+		__preempt_count_sub(PREEMPT_ACTIVE);
+		barrier();
+	} while (need_resched());
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #endif /* CONFIG_PREEMPT */
 
 /*