Re: [PATCH v9 1/8] mm: Introduce memfd_restricted system call to create restricted user memory

[Chao Peng]

On Thu, Dec 01, 2022 at 06:16:46PM -0800, Vishal Annapurve wrote:
> On Tue, Oct 25, 2022 at 8:18 AM Chao Peng <chao.p.peng@linux.intel.com> wrote:
> >
...
> > +}
> > +
> > +SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
> > +{
> 
> Looking at the underlying shmem implementation, there seems to be no
> way to enable transparent huge pages specifically for restricted memfd
> files.
> 
> Michael discussed earlier about tweaking
> /sys/kernel/mm/transparent_hugepage/shmem_enabled setting to allow
> hugepages to be used while backing restricted memfd. Such a change
> will affect the rest of the shmem usecases as well. Even setting the
> shmem_enabled policy to "advise" wouldn't help unless file based
> advise for hugepage allocation is implemented.

Had a look at fadvise() and looks it does not support HUGEPAGE for any
filesystem yet.

> 
> Does it make sense to provide a flag here to allow creating restricted
> memfds backed possibly by huge pages to give a more granular control?

We do have a unused 'flags' can be extended for such usage, but I would
let Kirill have further look, perhaps need more discussions.

Chao
> 
> > +       struct file *file, *restricted_file;
> > +       int fd, err;
> > +
> > +       if (flags)
> > +               return -EINVAL;
> > +
> > +       fd = get_unused_fd_flags(0);
> > +       if (fd < 0)
> > +               return fd;
> > +
> > +       file = shmem_file_setup("memfd:restrictedmem", 0, VM_NORESERVE);
> > +       if (IS_ERR(file)) {
> > +               err = PTR_ERR(file);
> > +               goto err_fd;
> > +       }
> > +       file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
> > +       file->f_flags |= O_LARGEFILE;
> > +
> > +       restricted_file = restrictedmem_file_create(file);
> > +       if (IS_ERR(restricted_file)) {
> > +               err = PTR_ERR(restricted_file);
> > +               fput(file);
> > +               goto err_fd;
> > +       }
> > +
> > +       fd_install(fd, restricted_file);
> > +       return fd;
> > +err_fd:
> > +       put_unused_fd(fd);
> > +       return err;
> > +}
> > +
> > +void restrictedmem_register_notifier(struct file *file,
> > +                                    struct restrictedmem_notifier 
> > *notifier)
> > +{
> > +       struct restrictedmem_data *data = file->f_mapping->private_data;
> > +
> > +       mutex_lock(&data->lock);
> > +       list_add(&notifier->list, &data->notifiers);
> > +       mutex_unlock(&data->lock);
> > +}
> > +EXPORT_SYMBOL_GPL(restrictedmem_register_notifier);
> > +
> > +void restrictedmem_unregister_notifier(struct file *file,
> > +                                      struct restrictedmem_notifier 
> > *notifier)
> > +{
> > +       struct restrictedmem_data *data = file->f_mapping->private_data;
> > +
> > +       mutex_lock(&data->lock);
> > +       list_del(&notifier->list);
> > +       mutex_unlock(&data->lock);
> > +}
> > +EXPORT_SYMBOL_GPL(restrictedmem_unregister_notifier);
> > +
> > +int restrictedmem_get_page(struct file *file, pgoff_t offset,
> > +                          struct page **pagep, int *order)
> > +{
> > +       struct restrictedmem_data *data = file->f_mapping->private_data;
> > +       struct file *memfd = data->memfd;
> > +       struct page *page;
> > +       int ret;
> > +
> > +       ret = shmem_getpage(file_inode(memfd), offset, &page, SGP_WRITE);
> > +       if (ret)
> > +               return ret;
> > +
> > +       *pagep = page;
> > +       if (order)
> > +               *order = thp_order(compound_head(page));
> > +
> > +       SetPageUptodate(page);
> > +       unlock_page(page);
> > +
> > +       return 0;
> > +}
> > +EXPORT_SYMBOL_GPL(restrictedmem_get_page);
> > --
> > 2.25.1
> >