Re: [v3 PATCH 4/5] mm: shmem: don't truncate page if memory failure happens

[Peter Xu <peterx@redhat.com>]

On Tue, Oct 12, 2021 at 12:17:33PM -0700, Yang Shi wrote:
> On Mon, Oct 11, 2021 at 6:57 PM Peter Xu <peterx@redhat.com> wrote:
> >
> > On Thu, Sep 30, 2021 at 02:53:10PM -0700, Yang Shi wrote:
> > > diff --git a/mm/shmem.c b/mm/shmem.c
> > > index 88742953532c..75c36b6a405a 100644
> > > --- a/mm/shmem.c
> > > +++ b/mm/shmem.c
> > > @@ -2456,6 +2456,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
> > >       struct inode *inode = mapping->host;
> > >       struct shmem_inode_info *info = SHMEM_I(inode);
> > >       pgoff_t index = pos >> PAGE_SHIFT;
> > > +     int ret = 0;
> > >
> > >       /* i_rwsem is held by caller */
> > >       if (unlikely(info->seals & (F_SEAL_GROW |
> > > @@ -2466,7 +2467,17 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
> > >                       return -EPERM;
> > >       }
> > >
> > > -     return shmem_getpage(inode, index, pagep, SGP_WRITE);
> > > +     ret = shmem_getpage(inode, index, pagep, SGP_WRITE);
> > > +
> > > +     if (*pagep) {
> > > +             if (PageHWPoison(*pagep)) {
> > > +                     unlock_page(*pagep);
> > > +                     put_page(*pagep);
> > > +                     ret = -EIO;
> > > +             }
> > > +     }
> > > +
> > > +     return ret;
> > >  }
> > >
> > >  static int
> > > @@ -2555,6 +2566,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
> > >                       unlock_page(page);
> > >               }
> > >
> > > +             if (page && PageHWPoison(page)) {
> > > +                     error = -EIO;
> > > +                     break;
> > > +             }
> > > +
> > >               /*
> > >                * We must evaluate after, since reads (unlike writes)
> > >                * are called without i_rwsem protection against truncate
> >
> > [...]
> >
> > > @@ -4193,6 +4216,10 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
> > >               page = ERR_PTR(error);
> > >       else
> > >               unlock_page(page);
> > > +
> > > +     if (PageHWPoison(page))
> > > +             page = ERR_PTR(-EIO);
> > > +
> > >       return page;
> > >  #else
> > >       /*
> > > diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> > > index 7a9008415534..b688d5327177 100644
> > > --- a/mm/userfaultfd.c
> > > +++ b/mm/userfaultfd.c
> > > @@ -233,6 +233,11 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
> > >               goto out;
> > >       }
> > >
> > > +     if (PageHWPoison(page)) {
> > > +             ret = -EIO;
> > > +             goto out_release;
> > > +     }
> > > +
> > >       ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
> > >                                      page, false, wp_copy);
> > >       if (ret)
> > > --
> > > 2.26.2
> > >
> >
> > These are shmem_getpage_gfp() call sites:
> >
> >   shmem_getpage[151]             return shmem_getpage_gfp(inode, index, pagep, sgp,
> >   shmem_fault[2112]              err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE,
> >   shmem_read_mapping_page_gfp[4188] error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE,
> >
> > These are further shmem_getpage() call sites:
> >
> >   collapse_file[1735]            if (shmem_getpage(mapping->host, index, &page,
> >   shmem_undo_range[965]          shmem_getpage(inode, start - 1, &page, SGP_READ);
> >   shmem_undo_range[980]          shmem_getpage(inode, end, &page, SGP_READ);
> >   shmem_write_begin[2467]        return shmem_getpage(inode, index, pagep, SGP_WRITE);
> >   shmem_file_read_iter[2544]     error = shmem_getpage(inode, index, &page, sgp);
> >   shmem_fallocate[2733]          error = shmem_getpage(inode, index, &page, SGP_FALLOC);
> >   shmem_symlink[3079]            error = shmem_getpage(inode, 0, &page, SGP_WRITE);
> >   shmem_get_link[3120]           error = shmem_getpage(inode, 0, &page, SGP_READ);
> >   mcontinue_atomic_pte[235]      ret = shmem_getpage(inode, pgoff, &page, SGP_READ);
> >
> > Wondering whether this patch covered all of them.
> 
> No, it doesn't need. Not all places care about hwpoison page, for
> example, truncate, hole punch, etc. Only the APIs which return the
> data back to userspace or write back to disk need care about if the
> data is corrupted or not since. This has been elaborated in the cover
> letter.

I see, sorry I missed that.  However I still have two entries unsure in above
list that this patch didn't cover (besides fault path, truncate, ...):

  collapse_file[1735]            if (shmem_getpage(mapping->host, index, &page,
  shmem_get_link[3120]           error = shmem_getpage(inode, 0, &page, SGP_READ);

IIUC the 1st one is when we want to collapse a file thp, should we stop the
attempt if we see a hwpoison small page?

The 2nd one should be where we had a symlink shmem file and the 1st page which
stores the link got corrupted.  Should we fail the get_link() then?

-- 
Peter Xu