This is a series that attempts to unify and fix the current tlb gather implementations. Only s390 is left unconverted and most aren't event compiled but other than that its mostly complete (ia64, arm, sh are compile tested). This second installment doesn't try to change flush_tlb_range() for all architectures but simply uses a fake vma and fills in VM_EXEC and VM_HUGETLB. This series depends on the mmu_gather rework -v2 series send last week: https://lkml.org/lkml/2011/3/2/323 which is also available (including the anon_vma refcount simplification, mm preemtibilidy and davem's sparc64 gup_fast implementation) as a git tree based on next-20110307: git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-mmu_gather.git mmu_gather The whole series, including the depending patches is available through: git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-mmu_gather.git mmu_unify -- 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/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>