On Thu, Jul 24, 2014 at 03:51:57PM -0700, Andrew Morton wrote: > On Thu, 17 Jul 2014 14:46:49 -0400 j.glisse@xxxxxxxxx wrote: > > > New user of the mmu_notifier interface need to lookup vma in order to > > perform the invalidation operation. Instead of redoing a vma lookup > > inside the callback just pass through the vma from the call site where > > it is already available. > > Well.. what's wrong with performing the vma lookup within the > callback? Is it a correctness thing? Deadlock avoidance, for example? > > Or is it a performance thing? If so, that's a bit surprising - please > provide details? No i have no benchmark showing any issue on that, just that 99% of call place to mmu_notifier already had the vma handy and i thought it would be helpful to other but all current user are not using vma. So as there is no strong argument in favor of this change if you feel it is unnecessary and fear any kind of regression than just ignore it and i will live with vma lookup inside my code. Cheers, Jérôme -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>