* 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 _______________________________________________ stable mailing list stable@linux.kernel.org http://linux.kernel.org/mailman/listinfo/stable
