[openib-general] Re: [PATCH][RFC][0/4] InfiniBand userspace verbs implementation

[Andrew Morton]

Roland Dreier <roland at topspin.com> wrote:
>
>     Timur> With mlock(), we don't need to use get_user_pages() at all.
>      Timur> Arjan tells me the only time an mlocked page can move is
>      Timur> with hot (un)plug of memory, but that isn't supported on
>      Timur> the systems that we support.  We actually prefer mlock()
>      Timur> over get_user_pages(), because if the process dies, the
>      Timur> locks automatically go away too.
> 
>  There actually is another way pages can move, with both
>  get_user_pages() and mlock(): copy-on-write after a fork().  If
>  userspace does a fork(), then all PTEs are marked read-only, and if
>  the original process touches the page after the fork(), a new page
>  will be allocated and mapped at the original virtual address.

Do we care about that?  A straightforward scenario under which this can
happen is:

a) app starts some read I/O in an asynchronous manner
b) app forks
c) child writes to one of the pages which is still under read I/O
d) the read I/O completes
e) the child is left with the old data plus the child's modification instead
   of the new data

which is a very silly application which is giving itself unpredictable
memory contents anyway.

I assume there's a more sensible scenario?