On Tue, Aug 23, 2011 at 10:40:05AM +0200, Sebastian Andrzej Siewior wrote: > * Greg KH | 2011-08-22 17:49:43 [-0700]: > > >> > Cc: Anthony Foiani <anthony.foi...@gmail.com> > > > >Why, it's not fixing a bug that anyone hits, right? > > "earlier" the interrupt handler was executed either with interrupts > enabled or disabled if IRQF_DISABLED was specified. Later the latter > become default even if IRQF_DISABLED was not specified. This lead to the > splat Anthony reported because the irq handler was entered with IRQs > disabled and the ISR enabled them via spin_unlock_irq(). My initial > patch simply used spin_unlock_irqrestore() (and its counterpart) to have > the same state as we had. > > So the bug Anthony hit was that the interrupts were enabled where they > should not be. > > >greg k-h > > Sebastian >
Greg, I'll change the commit message so that it becomes clear, and send you a pull request. There is also one more UIO patch pending. Do you want a separate branch for -stable, or can you cherry-pick that from one UIO branch? Thanks, Hans _______________________________________________ stable mailing list stable@linux.kernel.org http://linux.kernel.org/mailman/listinfo/stable
