On Tue, May 14, 2019 at 7:32 AM Mike Rapoport <rppt@xxxxxxxxxxxxx> wrote:
>
> When get_user_pages*() is called with pages = NULL, the processing of
> VM_FAULT_RETRY terminates early without actually retrying to fault-in all
> the pages.
>
> If the pages in the requested range belong to a VMA that has userfaultfd
> registered, handle_userfault() returns VM_FAULT_RETRY *after* user space
> has populated the page, but for the gup pre-fault case there's no actual
> retry and the caller will get no pages although they are present.
>
> This issue was uncovered when running post-copy memory restore in CRIU
> after commit d9c9ce34ed5c ("x86/fpu: Fault-in user stack if
> copy_fpstate_to_sigframe() fails").
>
> After this change, the copying of FPU state to the sigframe switched from
> copy_to_user() variants which caused a real page fault to get_user_pages()
> with pages parameter set to NULL.
>
> In post-copy mode of CRIU, the destination memory is managed with
> userfaultfd and lack of the retry for pre-fault case in get_user_pages()
> causes a crash of the restored process.
>
> Making the pre-fault behavior of get_user_pages() the same as the "normal"
> one fixes the issue.
>
Tested-by: Andrei Vagin <avagin@xxxxxxxxx>
https://travis-ci.org/avagin/linux/builds/533184940
> Fixes: d9c9ce34ed5c ("x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails")
> Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
> ---
> mm/gup.c | 15 ++++++++-------
> 1 file changed, 8 insertions(+), 7 deletions(-)
>
> diff --git a/mm/gup.c b/mm/gup.c
> index 91819b8..c32ae5a 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -936,10 +936,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
> BUG_ON(ret >= nr_pages);
> }
>
> - if (!pages)
> - /* If it's a prefault don't insist harder */
> - return ret;
> -
> if (ret > 0) {
> nr_pages -= ret;
> pages_done += ret;
> @@ -955,8 +951,12 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
> pages_done = ret;
> break;
> }
> - /* VM_FAULT_RETRY triggered, so seek to the faulting offset */
> - pages += ret;
> + /*
> + * VM_FAULT_RETRY triggered, so seek to the faulting offset.
> + * For the prefault case (!pages) we only update counts.
> + */
> + if (likely(pages))
> + pages += ret;
> start += ret << PAGE_SHIFT;
>
> /*
> @@ -979,7 +979,8 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
> pages_done++;
> if (!nr_pages)
> break;
> - pages++;
> + if (likely(pages))
> + pages++;
> start += PAGE_SIZE;
> }
> if (lock_dropped && *locked) {
> --
> 2.7.4
>
