Messages in this thread | | | Date | Fri, 29 Aug 2008 13:00:02 -0400 | From | Gregory Haskins <> | Subject | Re: [PATCH] seqlock: serialize against writers |
| |
Andi Kleen wrote: >> I could just force all of the seqbegins to hit the slowpath by hacking >> the code and see what happens (aside from slowing down, of course ;) >> > > Only if you don't believe it will really crash? I think it's pretty > clear even without trying it. >
Well, I guess it was just to prove to myself that I broke something because I dont understand how the vsyscall interface works. But given your expertise here, I have no problem with just taking your word for it.
> >> Question: Which seqlock_t does userspace use? I assume it uses >> seqlock_t and not raw_seqlock_t. >> > > >> But the only reason that I ask is that >> I converted raw_seqlock_t to use the new style as well to be consistent, >> > > There's no raw_seqlock_t anywhere in mainline? > Yeah, understood. There is both in -rt and I was just saying that we technically only need the seqlock_t fix in -rt. So if raw_seqlock_t could be left pristine and solve this problem, that is an acceptable compromise to me.
> Anyways the variable is declared (in mainline) in asm-x86/vgtod.h > > >> even though it is not strictly necessary for the same reasons. So if >> perchance userspace uses the raw variant, I could solve this issue by >> only re-working the seqlock_t variant. Kind of a long shot, but figured >> I would mention it :) >> > > I guess you could define a new seqlock_t which is explicitely user space > safe. That might avoid such issues in the future. But then > that would likely require some code duplication and be ugly. > > On the other hand whatever problem you fixing in the kernel > (to be honest it's still unclear to me what the problem is) > needs to be likely fixed for the userland lock too. >
Yeah, it would possibly be a problem in both cases.
The problem I am addressing only exists in -rt since it has seqlock_t and raw_seqlock_t (with the former using preemptible spinlock_t's). Since the underlying seqlock_t->spinlock_t is preemptible, you can see that one thread that does:
{ write_seqlock(); /* asl */ write_sequnlock(); }
while other high-prio threads do
do { read_seqbegin(); /* asl */; } while (read_seqretry());
The readers could preempt the writer mid critical section and enter a live-locked loop.
raw_seqlock_t (which is equivalent to a mainline seqlock_t) do not have this problem because the spinlock acquisition inside the write_seqlock disables preemption.
HTH
-Greg
[unhandled content-type:application/pgp-signature] | |