Re: [PATCH 1/6] tracefs/eventfs: Use dput to free the toplevel events directory

[Ajay Kaher]

> On 07-Sep-2023, at 8:17 AM, Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:
>
> !! External Email
>
> From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>
>
> Currently when rmdir on an instance is done, eventfs_remove_events_dir()
> is called and it does a dput on the dentry and then frees the
> eventfs_inode that represents the events directory.
>
> But there's no protection against a reader reading the top level events
> directory at the same time and we can get a use after free error. Instead,
> use the dput() associated to the dentry to also free the eventfs_inode
> associated to the events directory, as that will get called when the last
> reference to the directory is released.
>

Nice catch Steve. Changes looks good to me.

Would like to know how did you map the backtrace with
use-after-free of eventfs_inode.

Thinking if same problem could happen for sub folder/files of eventfs as
free_ef() may get call earlier then dput().

-Ajay

> Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@xxxxxxxxxx/
>
> Cc: Ajay Kaher <akaher@xxxxxxxxxx>
> Fixes: 5bdcd5f5331a2 eventfs: ("Implement removal of meta data from eventfs")
> Reported-by: Zheng Yejian <zhengyejian1@xxxxxxxxxx>
> Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
> ---
> Changes since v1: https://lore.kernel.org/linux-trace-kernel/20230905183332.628d7cc0@xxxxxxxxxxxxxxxxxx
> - Removed left over "ei" variable (kernel test robot)
>
> fs/tracefs/event_inode.c | 17 ++++++++++++-----
> fs/tracefs/inode.c       |  2 +-
> fs/tracefs/internal.h    |  5 +++--
> 3 files changed, 16 insertions(+), 8 deletions(-)
>
> diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
> index fa1a1679a886..609ccb5b7cfc 100644
> --- a/fs/tracefs/event_inode.c
> +++ b/fs/tracefs/event_inode.c
> @@ -185,17 +185,27 @@ static struct dentry *create_dir(const char *name, struct dentry *parent, void *
>
> /**
>  * eventfs_set_ef_status_free - set the ef->status to free
> + * @ti: the tracefs_inode of the dentry
>  * @dentry: dentry who's status to be freed
>  *
>  * eventfs_set_ef_status_free will be called if no more
>  * references remain
>  */
> -void eventfs_set_ef_status_free(struct dentry *dentry)
> +void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry)
> {
>        struct tracefs_inode *ti_parent;
> +       struct eventfs_inode *ei;
>        struct eventfs_file *ef;
>
>        mutex_lock(&eventfs_mutex);
> +
> +       /* The top level events directory may be freed by this */
> +       if (unlikely(ti->flags & TRACEFS_EVENT_TOP_INODE)) {
> +               ei = ti->private;
> +               kfree(ei);
> +               goto out;
> +       }
> +
>        ti_parent = get_tracefs(dentry->d_parent->d_inode);
>        if (!ti_parent || !(ti_parent->flags & TRACEFS_EVENT_INODE))
>                goto out;
> @@ -510,7 +520,7 @@ struct dentry *eventfs_create_events_dir(const char *name,
>        INIT_LIST_HEAD(&ei->e_top_files);
>
>        ti = get_tracefs(inode);
> -       ti->flags |= TRACEFS_EVENT_INODE;
> +       ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
>        ti->private = ei;
>
>        inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
> @@ -806,7 +816,6 @@ void eventfs_remove(struct eventfs_file *ef)
> void eventfs_remove_events_dir(struct dentry *dentry)
> {
>        struct tracefs_inode *ti;
> -       struct eventfs_inode *ei;
>
>        if (!dentry || !dentry->d_inode)
>                return;
> @@ -815,8 +824,6 @@ void eventfs_remove_events_dir(struct dentry *dentry)
>        if (!ti || !(ti->flags & TRACEFS_EVENT_INODE))
>                return;
>
> -       ei = ti->private;
>        d_invalidate(dentry);
>        dput(dentry);
> -       kfree(ei);
> }
> diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
> index 3b8dd938b1c8..891653ba9cf3 100644
> --- a/fs/tracefs/inode.c
> +++ b/fs/tracefs/inode.c
> @@ -385,7 +385,7 @@ static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
>
>        ti = get_tracefs(inode);
>        if (ti && ti->flags & TRACEFS_EVENT_INODE)
> -               eventfs_set_ef_status_free(dentry);
> +               eventfs_set_ef_status_free(ti, dentry);
>        iput(inode);
> }
>
> diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
> index 69c2b1d87c46..4f2e49e2197b 100644
> --- a/fs/tracefs/internal.h
> +++ b/fs/tracefs/internal.h
> @@ -3,7 +3,8 @@
> #define _TRACEFS_INTERNAL_H
>
> enum {
> -       TRACEFS_EVENT_INODE     = BIT(1),
> +       TRACEFS_EVENT_INODE             = BIT(1),
> +       TRACEFS_EVENT_TOP_INODE         = BIT(2),
> };
>
> struct tracefs_inode {
> @@ -24,6 +25,6 @@ struct inode *tracefs_get_inode(struct super_block *sb);
> struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
> struct dentry *eventfs_failed_creating(struct dentry *dentry);
> struct dentry *eventfs_end_creating(struct dentry *dentry);
> -void eventfs_set_ef_status_free(struct dentry *dentry);
> +void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry);
>
> #endif /* _TRACEFS_INTERNAL_H */
> --
> 2.40.1
>
> !! External Email: This email originated from outside of the organization. Do not click links or open attachments unless you recognize the sender.