Re: BUG: dead loop in PowerPC hcall tracepoint (Was: [LTP] [PATCHv2] Add ftrace-stress-test to LTP)

[Steven Rostedt]

On Mon, 2010-10-18 at 11:19 +0800, Li Zefan wrote:

> This is a dead loop:
> 
> trace_hcall_entry() -> trace_clock_global() -> trace_hcall_entry() ..
> 
> And this is a PPC specific bug. Hope some ppc guys will fix it?
> Or we kill trace_clock_global() if no one actually uses it..

trace_clock_global() is used by many. I use it (and recommend using it)
on boxes where the TSC is horribly out of sync, and the trace needs
synchronization between CPUs.

The trace_hcall_entry and exit has wrappers already. Just add recursion
protection there.

Perhaps something like this:

(Not compiled nor ran)

+static DEFINE_PER_CPU(hcall_trace_disable);
+
 void hcall_tracepoint_regfunc(void)
 {
 	hcall_tracepoint_refcount++;
 }

 void hcall_tracepoint_unregfunc(void)
 {
 	hcall_tracepoint_refcount--;
 }

+int __trace_disable_check(void)
+{
+	if (!hcall_tracepoint_refcount)
+		return 1;
+
+	if (get_cpu_var(hcall_trace_disable)) {
+		put_cpu_var(hcall_trace_disable);
+		return 1;
+	}
+
+	__get_cpu_var(hcall_trace_disable)++;
+
+	return 0;
+}
+
+void __trace_disable_put(void)
+{
+	__get_cpu_var(hcall_trace_disable)--;
+	put_cpu_var(hcall_trace_disable);
+}
+
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 {
+	int trace_disable;
+
+	if (__trace_disable_check())
+		return;
+
 	trace_hcall_entry(opcode, args);
+	__trace_disable_put();
 }

 void __trace_hcall_exit(long opcode, unsigned long retval,
 			unsigned long *retbuf)
 {
+	if (__trace_disable_check())
+		return;
+
 	trace_hcall_exit(opcode, retval, retbuf);
+	__trace_disable_put();
 }

-- Steve


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/