Re: [PATCH v3] ceph: correctly release memory from capsnap

[Ilya Dryomov <idryomov@gmail.com>]

On Wed, Aug 18, 2021 at 3:25 AM <xiubli@redhat.com> wrote:
>
> From: Xiubo Li <xiubli@redhat.com>
>
> When force umounting, it will try to remove all the session caps.
> If there has any capsnap is in the flushing list, the remove session
> caps callback will try to release the capsnap->flush_cap memory to
> "ceph_cap_flush_cachep" slab cache, while which is allocated from
> kmalloc-256 slab cache.
>
> At the same time switch to list_del_init() because just in case the
> force umount has removed it from the lists and the
> handle_cap_flushsnap_ack() comes then the seconds list_del_init()
> won't crash the kernel.
>
> URL: https://tracker.ceph.com/issues/52283
> Signed-off-by: Xiubo Li <xiubli@redhat.com>
> ---
>
> V3:
> - rebase to the upstream
>
>
>  fs/ceph/caps.c       | 18 ++++++++++++++----
>  fs/ceph/mds_client.c |  7 ++++---
>  2 files changed, 18 insertions(+), 7 deletions(-)
>
> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
> index 1b9ca437da92..e239f06babbc 100644
> --- a/fs/ceph/caps.c
> +++ b/fs/ceph/caps.c
> @@ -1712,7 +1712,16 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
>
>  struct ceph_cap_flush *ceph_alloc_cap_flush(void)
>  {
> -       return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
> +       struct ceph_cap_flush *cf;
> +
> +       cf = kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
> +       /*
> +        * caps == 0 always means for the capsnap
> +        * caps > 0 means dirty caps being flushed
> +        * caps == -1 means preallocated, not used yet
> +        */

Hi Xiubo,

This comment should be in super.h, on struct ceph_cap_flush
definition.

But more importantly, are you sure that overloading cf->caps this way
is safe?  For example, __kick_flushing_caps() tests for cf->caps != 0
and cf->caps == -1 would be interpreted as a cue to call __prep_cap().

Thanks,

                Ilya

> +       cf->caps = -1;
> +       return cf;
>  }
>
>  void ceph_free_cap_flush(struct ceph_cap_flush *cf)
> @@ -1747,7 +1756,7 @@ static bool __detach_cap_flush_from_mdsc(struct ceph_mds_client *mdsc,
>                 prev->wake = true;
>                 wake = false;
>         }
> -       list_del(&cf->g_list);
> +       list_del_init(&cf->g_list);
>         return wake;
>  }
>
> @@ -1762,7 +1771,7 @@ static bool __detach_cap_flush_from_ci(struct ceph_inode_info *ci,
>                 prev->wake = true;
>                 wake = false;
>         }
> -       list_del(&cf->i_list);
> +       list_del_init(&cf->i_list);
>         return wake;
>  }
>
> @@ -3642,7 +3651,8 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
>                 cf = list_first_entry(&to_remove,
>                                       struct ceph_cap_flush, i_list);
>                 list_del(&cf->i_list);
> -               ceph_free_cap_flush(cf);
> +               if (cf->caps)
> +                       ceph_free_cap_flush(cf);
>         }
>
>         if (wake_ci)
> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> index 1e013fb09d73..a44adbd1841b 100644
> --- a/fs/ceph/mds_client.c
> +++ b/fs/ceph/mds_client.c
> @@ -1636,7 +1636,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
>                 spin_lock(&mdsc->cap_dirty_lock);
>
>                 list_for_each_entry(cf, &to_remove, i_list)
> -                       list_del(&cf->g_list);
> +                       list_del_init(&cf->g_list);
>
>                 if (!list_empty(&ci->i_dirty_item)) {
>                         pr_warn_ratelimited(
> @@ -1688,8 +1688,9 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
>                 struct ceph_cap_flush *cf;
>                 cf = list_first_entry(&to_remove,
>                                       struct ceph_cap_flush, i_list);
> -               list_del(&cf->i_list);
> -               ceph_free_cap_flush(cf);
> +               list_del_init(&cf->i_list);
> +               if (cf->caps)
> +                       ceph_free_cap_flush(cf);
>         }
>
>         wake_up_all(&ci->i_cap_wq);
> --
> 2.27.0
>