On Wed, 2012-09-05 at 19:09 +0200, Peter Zijlstra wrote: > On Wed, 2012-09-05 at 10:20 -0400, Steven Rostedt wrote: > > Well, the branch tracer was active. That means all 'if()'s were being > > traced. It comes down to how you define 'if' ;-) > > Yeah, I tried making an argument for: > > we tell lockdep irqs are enabled hit an if() end up in lockdep code > through the branch tracer and find borken state, or vice-versa. > > Just couldn't find it in the provided stack-trace. Might be I didn't > look hard enough, might be there's something else entirely. > > All I know is I've never seen it on real hardware, then again, I hardly > ever have CONFIG_PARAVIRT or CONFIG_TRACE_BRANCH_PROFILING, let alone > both. >
This looks very familiar to Fengguang's previous bug report. I can't seem to find it on LKML.org. Probably because of the two attachments (dmesg and config) caused lkml to nuke it. I'll forward it to you. -- Steve -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
