[Cluster-devel] [PATCH v5 05/12] iov_iter: Introduce fault_in_iov_iter_writeable

[Andreas Gruenbacher]

On Tue, Aug 3, 2021 at 9:18 PM Andreas Gruenbacher <agruenba at redhat.com> wrote:
> Introduce a new fault_in_iov_iter_writeable helper for safely faulting in an
> iterator for writing.  Uses get_user_pages() to fault in the pages without
> actually writing to them, which would be destructive.
>
> We'll use fault_in_iov_iter_writeable in gfs2 once we've determined that the
> iterator passed to .read_iter isn't in memory.
>
> Signed-off-by: Andreas Gruenbacher <agruenba at redhat.com>
> ---
>  include/linux/pagemap.h |  1 +
>  include/linux/uio.h     |  1 +
>  lib/iov_iter.c          | 41 +++++++++++++++++++++++++++
>  mm/gup.c                | 61 +++++++++++++++++++++++++++++++++++++++++
>  4 files changed, 104 insertions(+)
>
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 7c9edc9694d9..a629807edb8c 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -737,6 +737,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
>   * Fault in userspace address range.
>   */
>  size_t fault_in_writeable(char __user *uaddr, size_t size);
> +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
>  size_t fault_in_readable(const char __user *uaddr, size_t size);
>
>  int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
> diff --git a/include/linux/uio.h b/include/linux/uio.h
> index 12d30246c2e9..ffa431aeb067 100644
> --- a/include/linux/uio.h
> +++ b/include/linux/uio.h
> @@ -120,6 +120,7 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
>  void iov_iter_advance(struct iov_iter *i, size_t bytes);
>  void iov_iter_revert(struct iov_iter *i, size_t bytes);
>  size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
> +size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
>  size_t iov_iter_single_seg_count(const struct iov_iter *i);
>  size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
>                          struct iov_iter *i);
> diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> index c0fa1618561c..4ffc76801eaa 100644
> --- a/lib/iov_iter.c
> +++ b/lib/iov_iter.c
> @@ -471,6 +471,47 @@ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size)
>  }
>  EXPORT_SYMBOL(fault_in_iov_iter_readable);
>
> +/*
> + * fault_in_iov_iter_writeable - fault in iov iterator for writing
> + * @i: iterator
> + * @size: maximum length
> + *
> + * Faults in the iterator using get_user_pages(), i.e., without triggering
> + * hardware page faults.  This is primarily useful when we know that some or
> + * all of the pages in @i aren't in memory.
> + *
> + * Returns the number of bytes faulted in, or 0 if no bytes could be faulted in
> + * (i.e., because the address is invalid).
> + *
> + * Always returns the number of avaliable bytes for non-user space iterators.
> + */
> +size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
> +{
> +       if (size > i->count)
> +               size = i->count;
> +
> +       if (iter_is_iovec(i)) {
> +               const struct iovec *p;
> +               size_t bytes = size;
> +               size_t skip;
> +
> +               for (p = i->iov, skip = i->iov_offset; bytes; p++, skip = 0) {
> +                       size_t len = min(bytes, p->iov_len - skip);
> +                       size_t ret;
> +
> +                       if (unlikely(!len))
> +                               continue;
> +                       ret = fault_in_safe_writeable(p->iov_base + skip, len);
> +                       bytes -= ret;
> +                       if (ret != len)
> +                               break;
> +               }
> +               return size - bytes;
> +       }
> +       return size;
> +}
> +EXPORT_SYMBOL(fault_in_iov_iter_writeable);
> +
>  void iov_iter_init(struct iov_iter *i, unsigned int direction,
>                         const struct iovec *iov, unsigned long nr_segs,
>                         size_t count)
> diff --git a/mm/gup.c b/mm/gup.c
> index d04984d5d93c..7218e27c2481 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1694,6 +1694,67 @@ size_t fault_in_writeable(char __user *uaddr, size_t size)
>  }
>  EXPORT_SYMBOL(fault_in_writeable);
>
> +/**
> + * fault_in_safe_writeable - fault in an address range for writing
> + * @uaddr: start of address range
> + * @size: length of address range
> + *
> + * Faults in an address range using get_user_pages, i.e., without triggering
> + * hardware page faults.  This is primarily useful when we know that some or
> + * all of the pages in the address range aren't in memory.
> + *
> + * Other than fault_in_writeable(), this function is non-destructive.
> + *
> + * Note that we don't pin or otherwise hold the pages referenced that we fault
> + * in.  There's no guarantee that they'll stay in memory for any duration of
> + * time.
> + *
> + * Returns the number of bytes faulted in from @uaddr.
> + */
> +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
> +{
> +       unsigned long start = (unsigned long)uaddr;
> +       unsigned long end, nstart, nend;
> +       struct mm_struct *mm = current->mm;
> +       struct vm_area_struct *vma = NULL;
> +       int locked = 0;
> +
> +       /* FIXME: Protect against overflow! */
> +
> +       end = PAGE_ALIGN(start + size);
> +       for (nstart = start & PAGE_MASK; nstart < end; nstart = nend) {
> +               unsigned long nr_pages;
> +               long ret;
> +
> +               if (!locked) {
> +                       locked = 1;
> +                       mmap_read_lock(mm);
> +                       vma = find_vma(mm, nstart);
> +               } else if (nstart >= vma->vm_end)
> +                       vma = vma->vm_next;
> +               if (!vma || vma->vm_start >= end)
> +                       break;
> +               nend = min(end, vma->vm_end);
> +               if (vma->vm_flags & (VM_IO | VM_PFNMAP))
> +                       continue;

Shouldn't we disallow read()ing into those kinds of vmas? If we skip
over them here and then the actual write results in -EFAULT, we'll end
up in a loop.

> +               if (nstart < vma->vm_start)
> +                       nstart = vma->vm_start;

Likewise, shouldn't we fail for memory ranges not covered by a vma?

> +               nr_pages = (nend - nstart) / PAGE_SIZE;
> +               ret = __get_user_pages_locked(mm, nstart, nr_pages,
> +                                             NULL, NULL, &locked,
> +                                             FOLL_TOUCH | FOLL_WRITE);
> +               if (ret <= 0)
> +                       break;
> +               nend = nstart + ret * PAGE_SIZE;
> +       }
> +       if (locked)
> +               mmap_read_unlock(mm);
> +       if (nstart > start)
> +               return min(nstart - start, size);
> +       return 0;
> +}
> +EXPORT_SYMBOL(fault_in_safe_writeable);
> +
>  size_t fault_in_readable(const char __user *uaddr, size_t size)
>  {
>         const char __user *start = uaddr, *end;
> --
> 2.26.3
>

Thanks,
Andreas