On 03/22/2013 10:11 AM, Xiao Guangrong wrote: >> The modifications should be contained to kvm_mmu_get_page() mostly, >> correct? (would also have to keep counters to increase SLAB freeing >> ratio, relative to number of outdated shadow pages). > > Yes. > >> >> And then have codepaths that nuke shadow pages break from the spinlock, > > I think this is not needed any more. We can let mmu_notify use the generation > number to invalid all shadow pages, then we only need to free them after > all vcpus down and mmu_notify unregistered - at this point, no lock contention, > we can directly free them. Sorry. This is wrong since after call ->release(), the memory will be freed. zap-all-sp can not be delayed. Will think out a good way to handle this... -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html