| Message ID | 20220718114748.2623-5-namit@vmware.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | userfaultfd: support access/write hints | expand |
On 18.07.22 13:47, Nadav Amit wrote: > From: Nadav Amit <namit@vmware.com> > > When userfaultfd provides a zeropage in response to ioctl, it provides a > readonly alias to the zero page. If the page is later written (which is > the likely scenario), page-fault occurs and the page-fault allocator > allocates a page and rewires the page-tables. > > This is an expensive flow for cases in which a page is likely be written > to. Users can use the copy ioctl to initialize zero page (by copying > zeros), but this is also wasteful. > > Allow userfaultfd users to efficiently map initialized zero-pages that > are writable. IF UFFDIO_ZEROPAGE_MODE_WRITE_LIKELY is provided would map > a clear page instead of an alias to the zero page. > > Suggested-by: David Hildenbrand <david@redhat.com> > Cc: Mike Kravetz <mike.kravetz@oracle.com> > Cc: Hugh Dickins <hughd@google.com> > Cc: Andrew Morton <akpm@linux-foundation.org> > Cc: Axel Rasmussen <axelrasmussen@google.com> > Cc: Mike Rapoport <rppt@linux.ibm.com> > Acked-by: Peter Xu <peterx@redhat.com> > Signed-off-by: Nadav Amit <namit@vmware.com> > --- > mm/userfaultfd.c | 35 +++++++++++++++++++++++++++++++++++ > 1 file changed, 35 insertions(+) > > diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c > index c15679f3eb6a..954c6980b29f 100644 > --- a/mm/userfaultfd.c > +++ b/mm/userfaultfd.c > @@ -241,6 +241,37 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm, > return ret; > } > > +static int mfill_clearpage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, > + struct vm_area_struct *dst_vma, > + unsigned long dst_addr, > + uffd_flags_t uffd_flags) > +{ > + struct page *page; > + int ret; > + > + ret = -ENOMEM; > + page = alloc_zeroed_user_highpage_movable(dst_vma, dst_addr); > + if (!page) > + goto out; > + > + /* The PTE is not marked as dirty unconditionally */ > + SetPageDirty(page); > + __SetPageUptodate(page); > + > + if (mem_cgroup_charge(page_folio(page), dst_vma->vm_mm, GFP_KERNEL)) > + goto out_release; > + > + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, > + page, true, uffd_flags); > + if (ret) > + goto out_release; > +out: > + return ret; > +out_release: > + put_page(page); > + goto out; > +} > + > /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ > static int mcontinue_atomic_pte(struct mm_struct *dst_mm, > pmd_t *dst_pmd, > @@ -500,6 +531,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, > err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, > dst_addr, src_addr, page, > uffd_flags); > + else if (!(uffd_flags & UFFD_FLAGS_WP) && > + (uffd_flags & UFFD_FLAGS_WRITE_LIKELY)) > + err = mfill_clearpage_pte(dst_mm, dst_pmd, dst_vma, > + dst_addr, uffd_flags); > else > err = mfill_zeropage_pte(dst_mm, dst_pmd, > dst_vma, dst_addr, uffd_flags); Reviewed-by: David Hildenbrand <david@redhat.com>
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c15679f3eb6a..954c6980b29f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -241,6 +241,37 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm, return ret; } +static int mfill_clearpage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + uffd_flags_t uffd_flags) +{ + struct page *page; + int ret; + + ret = -ENOMEM; + page = alloc_zeroed_user_highpage_movable(dst_vma, dst_addr); + if (!page) + goto out; + + /* The PTE is not marked as dirty unconditionally */ + SetPageDirty(page); + __SetPageUptodate(page); + + if (mem_cgroup_charge(page_folio(page), dst_vma->vm_mm, GFP_KERNEL)) + goto out_release; + + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, true, uffd_flags); + if (ret) + goto out_release; +out: + return ret; +out_release: + put_page(page); + goto out; +} + /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, @@ -500,6 +531,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page, uffd_flags); + else if (!(uffd_flags & UFFD_FLAGS_WP) && + (uffd_flags & UFFD_FLAGS_WRITE_LIKELY)) + err = mfill_clearpage_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, uffd_flags); else err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, dst_addr, uffd_flags);