> I think what you're getting with this is the ability to unmap MAP_PRIVATE pages > from one process but if there are multiple processes, the second process could > still end up referencing the poisoned MAP_PRIVATE page. Is this accurate? Even > if it is, I guess it's still an improvement over what currently happens. The only real requirement is that all PTEs pointing to that page get replaced by poisoned PTEs. (that's essentially always "late kill" mode) -Andi -- ak@xxxxxxxxxxxxxxx -- Speaking for myself only. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>