From: Frederic Weisbecker <fweisbec@xxxxxxxxx> Date: Tue, 6 Apr 2010 12:19:28 +0200 > It means having such interrupt reentrancy is not a problem. It's not reentrancy. It's the fact that local_irq_disable() (read it again, it's the "disable" that re-renables NMIs on sparc64) turns NMIs back on even in code where we are still trying to figure out how to service the NMI still. It's because we implement NMIs on sparc64 by having the performance counter interrupt come in on the level 15 interrupt, and we run the entire kernel at level 14 when IRQs are "disabled". -- To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
