On 07/11/2014 20:47, Mario Smarduch wrote: >> That can happen if the error occurred in the final >> copy to userspace, after page tables have been modified. > > Upon error return userspace should terminate logging, error out whether > used for migration or other use cases, with some stale spte TLBs cached > read/write, which doesn't appear to be harmful. Fair enough; for x86 I elected to always do the TLB flush, but you can do it differently. Perhaps add a comment with the above paragraph, thouhg. > But you mention 'final copy' which makes me think I'm missing something? I meant final copy before leaving the function. Paolo _______________________________________________ kvmarm mailing list kvmarm@xxxxxxxxxxxxxxxxxxxxx https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
