Received-SPF: pass (google.com: domain of linux-kernel+bounces-109246-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Precedence: bulk
MIME-Version: 1.0
References: <20240319212316.4193790-1-daeho43@gmail.com> <712f380c-68ef-4743-bd9b-7342e838ced7@kernel.org>
In-Reply-To: <712f380c-68ef-4743-bd9b-7342e838ced7@kernel.org>
From: Daeho Jeong <daeho43@gmail.com>
Date: Wed, 20 Mar 2024 10:42:01 -0700
Message-ID: <CACOAw_yAWGbx2Bx2or1OyVUUw6HSgTd=fo3e151d1JHU+Op5qQ@mail.gmail.com>
Subject: Re: [f2fs-dev] [PATCH v3] f2fs: prevent writing without fallocate()
 for pinned files
To: Chao Yu <chao@kernel.org>
Cc: linux-kernel@vger.kernel.org, linux-f2fs-devel@lists.sourceforge.net, 
	kernel-team@android.com, Daeho Jeong <daehojeong@google.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Mar 20, 2024 at 2:38=E2=80=AFAM Chao Yu <chao@kernel.org> wrote:
>
> On 2024/3/20 5:23, Daeho Jeong wrote:
> > From: Daeho Jeong <daehojeong@google.com>
> >
> > In a case writing without fallocate(), we can't guarantee it's allocate=
d
> > in the conventional area for zoned stroage.
> >
> > Signed-off-by: Daeho Jeong <daehojeong@google.com>
> > ---
> > v2: covered the direct io case
> > v3: covered the mkwrite case
> > ---
> >   fs/f2fs/data.c | 14 ++++++++++++--
> >   fs/f2fs/file.c | 16 ++++++++--------
> >   2 files changed, 20 insertions(+), 10 deletions(-)
> >
> > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> > index c21b92f18463..d3e5ab2736a6 100644
> > --- a/fs/f2fs/data.c
> > +++ b/fs/f2fs/data.c
> > @@ -1584,8 +1584,11 @@ int f2fs_map_blocks(struct inode *inode, struct =
f2fs_map_blocks *map, int flag)
> >
> >       /* use out-place-update for direct IO under LFS mode */
> >       if (map->m_may_create &&
> > -         (is_hole || (f2fs_lfs_mode(sbi) && flag =3D=3D F2FS_GET_BLOCK=
_DIO))) {
> > -             if (unlikely(f2fs_cp_error(sbi))) {
> > +         (is_hole || (f2fs_lfs_mode(sbi) && flag =3D=3D F2FS_GET_BLOCK=
_DIO &&
> > +                      !f2fs_is_pinned_file(inode)))) {
> > +             if (unlikely(f2fs_cp_error(sbi)) ||
> > +                 (f2fs_is_pinned_file(inode) && is_hole &&
> > +                  flag !=3D F2FS_GET_BLOCK_PRE_DIO)) {
> >                       err =3D -EIO;
> >                       goto sync_out;
> >               }
> > @@ -3378,6 +3381,8 @@ static int prepare_write_begin(struct f2fs_sb_inf=
o *sbi,
> >               f2fs_map_lock(sbi, flag);
> >               locked =3D true;
> >       } else if ((pos & PAGE_MASK) >=3D i_size_read(inode)) {
> > +             if (f2fs_is_pinned_file(inode))
> > +                     return -EIO;
> >               f2fs_map_lock(sbi, flag);
> >               locked =3D true;
> >       }
> > @@ -3407,6 +3412,11 @@ static int prepare_write_begin(struct f2fs_sb_in=
fo *sbi,
> >
> >       if (!f2fs_lookup_read_extent_cache_block(inode, index,
> >                                                &dn.data_blkaddr)) {
> > +             if (f2fs_is_pinned_file(inode)) {
> > +                     err =3D -EIO;
> > +                     goto out;
> > +             }
> > +
> >               if (locked) {
> >                       err =3D f2fs_reserve_block(&dn, index);
> >                       goto out;
> > diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> > index 82277e95c88f..4db3b21c804b 100644
> > --- a/fs/f2fs/file.c
> > +++ b/fs/f2fs/file.c
> > @@ -57,7 +57,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_faul=
t *vmf)
> >       struct inode *inode =3D file_inode(vmf->vma->vm_file);
> >       struct f2fs_sb_info *sbi =3D F2FS_I_SB(inode);
> >       struct dnode_of_data dn;
> > -     bool need_alloc =3D true;
> > +     bool need_alloc =3D !f2fs_is_pinned_file(inode);
>
> Will this check races w/ pinfile get|set?

Do you mean "set/clear" case? I believe "set" case is okay, since we
can't set if the inode already has a data block. For "clear" case, I
believe mkwrite failure is okay in racy conditions caused by clearing
the pin flag. What do you think?

>
> Thanks,
>
> >       int err =3D 0;
> >       vm_fault_t ret;
> >
> > @@ -114,19 +114,15 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_=
fault *vmf)
> >               goto out_sem;
> >       }
> >
> > +     set_new_dnode(&dn, inode, NULL, NULL, 0);
> >       if (need_alloc) {
> >               /* block allocation */
> > -             set_new_dnode(&dn, inode, NULL, NULL, 0);
> >               err =3D f2fs_get_block_locked(&dn, page->index);
> > -     }
> > -
> > -#ifdef CONFIG_F2FS_FS_COMPRESSION
> > -     if (!need_alloc) {
> > -             set_new_dnode(&dn, inode, NULL, NULL, 0);
> > +     } else {
> >               err =3D f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_N=
ODE);
> >               f2fs_put_dnode(&dn);
> >       }
> > -#endif
> > +
> >       if (err) {
> >               unlock_page(page);
> >               goto out_sem;
> > @@ -4611,6 +4607,10 @@ static int f2fs_preallocate_blocks(struct kiocb =
*iocb, struct iov_iter *iter,
> >                       return ret;
> >       }
> >
> > +     /* For pinned files, it should be fallocate()-ed in advance. */
> > +     if (f2fs_is_pinned_file(inode))
> > +             return 0;
> > +
> >       /* Do not preallocate blocks that will be written partially in 4K=
B. */
> >       map.m_lblk =3D F2FS_BLK_ALIGN(pos);
> >       map.m_len =3D F2FS_BYTES_TO_BLK(pos + count);