Re: [PATCH ghak90 V9 10/13] audit: add support for containerid to network namespaces

[Paul Moore <paul@paul-moore.com>]

On Sat, Jun 27, 2020 at 9:23 AM Richard Guy Briggs <rgb@redhat.com> wrote:
>
> This also adds support to qualify NETFILTER_PKT records.
>
> Audit events could happen in a network namespace outside of a task
> context due to packets received from the net that trigger an auditing
> rule prior to being associated with a running task.  The network
> namespace could be in use by multiple containers by association to the
> tasks in that network namespace.  We still want a way to attribute
> these events to any potential containers.  Keep a list per network
> namespace to track these audit container identifiiers.
>
> Add/increment the audit container identifier on:
> - initial setting of the audit container identifier via /proc
> - clone/fork call that inherits an audit container identifier
> - unshare call that inherits an audit container identifier
> - setns call that inherits an audit container identifier
> Delete/decrement the audit container identifier on:
> - an inherited audit container identifier dropped when child set
> - process exit
> - unshare call that drops a net namespace
> - setns call that drops a net namespace
>
> Add audit container identifier auxiliary record(s) to NETFILTER_PKT
> event standalone records.  Iterate through all potential audit container
> identifiers associated with a network namespace.
>
> Please see the github audit kernel issue for contid net support:
>   https://github.com/linux-audit/audit-kernel/issues/92
> Please see the github audit testsuiite issue for the test case:
>   https://github.com/linux-audit/audit-testsuite/issues/64
> Please see the github audit wiki for the feature overview:
>   https://github.com/linux-audit/audit-kernel/wiki/RFE-Audit-Container-ID
> Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
> Acked-by: Neil Horman <nhorman@tuxdriver.com>
> Reviewed-by: Ondrej Mosnacek <omosnace@redhat.com>
> ---
>  include/linux/audit.h    |  20 ++++++
>  kernel/audit.c           | 156 ++++++++++++++++++++++++++++++++++++++++++++++-
>  kernel/nsproxy.c         |   4 ++
>  net/netfilter/nft_log.c  |  11 +++-
>  net/netfilter/xt_AUDIT.c |  11 +++-
>  5 files changed, 195 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/audit.h b/include/linux/audit.h
> index c4a755ae0d61..304fbb7c3c5b 100644
> --- a/include/linux/audit.h
> +++ b/include/linux/audit.h
> @@ -128,6 +128,13 @@ struct audit_task_info {
>
>  extern struct audit_task_info init_struct_audit;
>
> +struct audit_contobj_netns {
> +       struct list_head        list;
> +       struct audit_contobj    *obj;
> +       int                     count;

This seems like it might be a good candidate for refcount_t, yes?

> +       struct rcu_head         rcu;
> +};

...

> diff --git a/kernel/audit.c b/kernel/audit.c
> index 997c34178ee8..a862721dfd9b 100644
> --- a/kernel/audit.c
> +++ b/kernel/audit.c
> @@ -437,6 +452,136 @@ static struct sock *audit_get_sk(const struct net *net)
>         return aunet->sk;
>  }
>
> +void audit_netns_contid_add(struct net *net, struct audit_contobj *cont)
> +{
> +       struct audit_net *aunet;
> +       struct list_head *contobj_list;
> +       struct audit_contobj_netns *contns;
> +
> +       if (!net)
> +               return;
> +       if (!cont)
> +               return;
> +       aunet = net_generic(net, audit_net_id);
> +       if (!aunet)
> +               return;
> +       contobj_list = &aunet->contobj_list;
> +       rcu_read_lock();
> +       spin_lock(&aunet->contobj_list_lock);
> +       list_for_each_entry_rcu(contns, contobj_list, list)
> +               if (contns->obj == cont) {
> +                       contns->count++;
> +                       goto out;
> +               }
> +       contns = kmalloc(sizeof(*contns), GFP_ATOMIC);
> +       if (contns) {
> +               INIT_LIST_HEAD(&contns->list);
> +               contns->obj = cont;
> +               contns->count = 1;
> +               list_add_rcu(&contns->list, contobj_list);
> +       }
> +out:
> +       spin_unlock(&aunet->contobj_list_lock);
> +       rcu_read_unlock();
> +}
> +
> +void audit_netns_contid_del(struct net *net, struct audit_contobj *cont)
> +{
> +       struct audit_net *aunet;
> +       struct list_head *contobj_list;
> +       struct audit_contobj_netns *contns = NULL;
> +
> +       if (!net)
> +               return;
> +       if (!cont)
> +               return;
> +       aunet = net_generic(net, audit_net_id);
> +       if (!aunet)
> +               return;
> +       contobj_list = &aunet->contobj_list;
> +       rcu_read_lock();
> +       spin_lock(&aunet->contobj_list_lock);
> +       list_for_each_entry_rcu(contns, contobj_list, list)
> +               if (contns->obj == cont) {
> +                       contns->count--;
> +                       if (contns->count < 1) {

One could simplify this with "(--countns->count) < 1", although if it
is changed to a refcount_t (which seems like a smart thing), the
normal decrement/test would be the best choice.


> +                               list_del_rcu(&contns->list);
> +                               kfree_rcu(contns, rcu);
> +                       }
> +                       break;
> +               }
> +       spin_unlock(&aunet->contobj_list_lock);
> +       rcu_read_unlock();
> +}

--
paul moore
www.paul-moore.com