Re: Request for help: what did I do wrong with idtentry?

2014-11-15 Thread Andy Lutomirski
On Sat, Nov 15, 2014 at 10:28 AM, Andi Kleen wrote: >> I'm not >> completely thrilled with what it does to double_fault, though. If we >> somehow get a double fault caused by an interrupt hitting userspace >> with a bad kernel_stack, then we'll end up page faulting in the >> double_fault

Re: Request for help: what did I do wrong with idtentry?

2014-11-15 Thread Andi Kleen
> I'm not > completely thrilled with what it does to double_fault, though. If we > somehow get a double fault caused by an interrupt hitting userspace > with a bad kernel_stack, then we'll end up page faulting in the > double_fault prologue. I'm not convinced that this is worth worrying > about.

Re: Request for help: what did I do wrong with idtentry?

2014-11-15 Thread Andi Kleen
I'm not completely thrilled with what it does to double_fault, though. If we somehow get a double fault caused by an interrupt hitting userspace with a bad kernel_stack, then we'll end up page faulting in the double_fault prologue. I'm not convinced that this is worth worrying about. It

Re: Request for help: what did I do wrong with idtentry?

2014-11-15 Thread Andy Lutomirski
On Sat, Nov 15, 2014 at 10:28 AM, Andi Kleen a...@firstfloor.org wrote: I'm not completely thrilled with what it does to double_fault, though. If we somehow get a double fault caused by an interrupt hitting userspace with a bad kernel_stack, then we'll end up page faulting in the

Re: Request for help: what did I do wrong with idtentry?

2014-11-14 Thread Andy Lutomirski
On Fri, Nov 14, 2014 at 4:52 PM, Luck, Tony wrote: >> causes Tony's MCE stress test to fail, presumably when some CPU either >> becomes permanently non-interruptable or otherwise wanders off into >> the weeds. > > It might be that recent "improvements" I made to my test harness have > messed

RE: Request for help: what did I do wrong with idtentry?

2014-11-14 Thread Luck, Tony
> causes Tony's MCE stress test to fail, presumably when some CPU either > becomes permanently non-interruptable or otherwise wanders off into > the weeds. It might be that recent "improvements" I made to my test harness have messed things up. I trimmed one delay (between injection and

RE: Request for help: what did I do wrong with idtentry?

2014-11-14 Thread Luck, Tony
causes Tony's MCE stress test to fail, presumably when some CPU either becomes permanently non-interruptable or otherwise wanders off into the weeds. It might be that recent improvements I made to my test harness have messed things up. I trimmed one delay (between injection and consumption),

Re: Request for help: what did I do wrong with idtentry?

2014-11-14 Thread Andy Lutomirski
On Fri, Nov 14, 2014 at 4:52 PM, Luck, Tony tony.l...@intel.com wrote: causes Tony's MCE stress test to fail, presumably when some CPU either becomes permanently non-interruptable or otherwise wanders off into the weeds. It might be that recent improvements I made to my test harness have