From: Frederic Weisbecker <fweisbec@xxxxxxxxx> Date: Sat, 17 Apr 2010 18:59:25 +0200 > This could be also a tracing recursion somewhere. > One good way to know is to put pause_graph_tracing() > and unpause_graph_tracing() in the very beginning and > end of the tracing paths. > > /me goes to try this. Last night I still couldn't get the stack overflow checks to trigger, even once i accounted for dynamic ftrace patchin, unfortunately. But... I added a tracing_off() call to the hrtimer deadlock avoidance case and the machine doesn't crash after that triggers. So I went to look at the per-cpu trace of the processor on which the hrtimer deadlock avoidance triggered, and it has a looping sequence of timestamps which looks really strange. The other per-cpu traces look just fine. This is a major clue I think, so I'll keep snooping around trying to dig more deeply into this. -- To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
