On Tue, Jun 21, 2022 at 10:48:51AM +0200, David Hildenbrand wrote: > > @@ -1871,6 +1877,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) > > struct uffdio_continue uffdio_continue; > > struct uffdio_continue __user *user_uffdio_continue; > > struct userfaultfd_wake_range range; > > + uffd_flags_t uffd_flags; > > > > user_uffdio_continue = (struct uffdio_continue __user *)arg; > > > > @@ -1898,10 +1905,12 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) > > if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) > > goto out; > > > > + uffd_flags = UFFD_FLAGS_ACCESS_LIKELY; > > Can we add a comment why that makes sense? I think I know why -- someone > is stuck waiting for that continue to happen :) I think we shouldn't apply it by default for CONTINUE at all, at least not sololy for CONTINUE. CONTINUE can be used similarly as COPY at least in VM migration use case, afaict, so we can proactively install pgtables even if the page was not faulted. [...] > > diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h > > index 005e5e306266..d9c8ce9ba777 100644 > > --- a/include/uapi/linux/userfaultfd.h > > +++ b/include/uapi/linux/userfaultfd.h > > @@ -38,7 +38,8 @@ > > UFFD_FEATURE_MINOR_HUGETLBFS | \ > > UFFD_FEATURE_MINOR_SHMEM | \ > > UFFD_FEATURE_EXACT_ADDRESS | \ > > - UFFD_FEATURE_WP_HUGETLBFS_SHMEM) > > + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ > > + UFFD_FEATURE_ACCESS_HINTS) Is the access_hint feature gonna cover the next dirty bit patch? If so I'd suggest we add the feature declaration in a separate patch after all bits ready. Thanks, -- Peter Xu
