On Wednesday 01 November 2006 20:52, Linus Torvalds wrote: > > On Wed, 1 Nov 2006, Andi Kleen wrote: > > > > Fix race in IO-APIC routing entry setup. > > > > Interrupt could happen between setting the IO-APIC entry > > and setting its interrupt data. > > This doesn't fix anything at all. > > The interrupt can come in on another CPU, Only BP should be active at this point. At least not until we implement IO-APIC hotplug, but so far that isn't there. Ok in theory the BIOS could have put the other CPUs into weird states where they are still doing something and causing interrupts, but that would be a BIOS bug. I suppose it could happen with kexec, but that has still other problems anyways. The common case of no kexec shouldn't be affected at least. -Andi
