On Tue, Aug 23, 2011 at 12:57:42PM +0200, Hans J. Koch wrote: > 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?
Forget it, I just saw you already added it to your tree. Thanks, Hans _______________________________________________ stable mailing list stable@linux.kernel.org http://linux.kernel.org/mailman/listinfo/stable