On Mon, Dec 15, 2014 at 01:02:08AM +0200, Kirill A. Shutemov wrote: > But it seems the problem is bigger than what the patch fixes. To me we are > too permisive on what vma can be remapped. > > How can we know that it's okay to move vma around for random driver which > provide .mmap? Or I miss something obvious? Most drivers do not care if a vma is moved within the virtual address space of a process. The aio ring buffer is special in that it gets unmapped when userspace does an io_destroy(), and io_destroy() has to know what the address is moved to in order to perform the unmap. Normal drivers don't perform the unmap themselves. -ben -- "Thought is the essence of where you are now." -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>