Re: [PATCH ghak90 (was ghak32) V4 09/10] audit: NETFILTER_PKT: record each container ID associated with a netNS

[Richard Guy Briggs]

On 2018-10-19 19:18, Paul Moore wrote:
> On Sun, Aug 5, 2018 at 4:33 AM Richard Guy Briggs <rgb@xxxxxxxxxx> wrote:
> > 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.
> >
> > Signed-off-by: Richard Guy Briggs <rgb@xxxxxxxxxx>
> > ---
> >  include/linux/audit.h    |  5 +++++
> >  kernel/audit.c           | 26 ++++++++++++++++++++++++++
> >  net/netfilter/xt_AUDIT.c | 12 ++++++++++--
> >  3 files changed, 41 insertions(+), 2 deletions(-)
> 
> ...
> 
> > diff --git a/include/linux/audit.h b/include/linux/audit.h
> > index 9a02095..8755f4d 100644
> > --- a/include/linux/audit.h
> > +++ b/include/linux/audit.h
> > @@ -169,6 +169,8 @@ extern int audit_log_contid(struct audit_context *context,
> >  extern void audit_netns_contid_add(struct net *net, u64 contid);
> >  extern void audit_netns_contid_del(struct net *net, u64 contid);
> >  extern void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p);
> > +extern void audit_log_netns_contid_list(struct net *net,
> > +                                struct audit_context *context);
> >
> >  extern int                 audit_update_lsm_rules(void);
> >
> > @@ -228,6 +230,9 @@ static inline void audit_netns_contid_del(struct net *net, u64 contid)
> >  { }
> >  static inline void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p)
> >  { }
> > +static inline void audit_log_netns_contid_list(struct net *net,
> > +                                       struct audit_context *context)
> > +{ }
> >
> >  #define audit_enabled AUDIT_OFF
> >  #endif /* CONFIG_AUDIT */
> > diff --git a/kernel/audit.c b/kernel/audit.c
> > index c5fed3b..b23711c 100644
> > --- a/kernel/audit.c
> > +++ b/kernel/audit.c
> > @@ -392,6 +392,32 @@ void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p)
> >                 audit_netns_contid_add(new->net_ns, contid);
> >  }
> >
> > +void audit_log_netns_contid_list(struct net *net, struct audit_context *context)
> > +{
> > +       spinlock_t *lock = audit_get_netns_contid_list_lock(net);
> > +       struct audit_buffer *ab;
> > +       struct audit_contid *cont;
> > +       bool first = true;
> > +
> > +       /* Generate AUDIT_CONTAINER record with container ID CSV list */
> > +       ab = audit_log_start(context, GFP_ATOMIC, AUDIT_CONTAINER);
> > +       if (!ab) {
> > +               audit_log_lost("out of memory in audit_log_netns_contid_list");
> > +               return;
> > +       }
> > +       audit_log_format(ab, "contid=");
> > +       spin_lock(lock);
> > +       list_for_each_entry(cont, audit_get_netns_contid_list(net), list) {
> > +               if (!first)
> > +                       audit_log_format(ab, ",");
> > +               audit_log_format(ab, "%llu", cont->id);
> > +               first = false;
> > +       }
> > +       spin_unlock(lock);
> 
> This is looking like potentially a lot of work to be doing under a
> spinlock, not to mention a single spinlock that is shared across CPUs.
> Considering that I expect changes to the list to be somewhat
> infrequent, this might be a good candidate for a RCU based locking
> scheme.

Would something like this look reasonable?
(This is on top of a patch to make contid list lock and unlock
functions.)

diff --git a/include/linux/audit.h b/include/linux/audit.h
index be5d6eb..9428fc3 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -92,6 +92,7 @@ struct audit_contid {
 	struct list_head	list;
 	u64			id;
 	refcount_t		refcount;
+	struct rcu_head		rcu;
 };
 
 extern int is_audit_feature_set(int which);
diff --git a/kernel/audit.c b/kernel/audit.c
index d5b58163..6f84c25 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -106,7 +106,6 @@
 struct audit_net {
 	struct sock *sk;
 	struct list_head contid_list;
-	spinlock_t contid_list_lock;
 };
 
 /**
@@ -327,26 +326,6 @@ struct list_head *audit_get_netns_contid_list(const struct net *net)
 	return &aunet->contid_list;
 }
 
-static int audit_netns_contid_lock(const struct net *net)
-{
-	struct audit_net *aunet = net_generic(net, audit_net_id);
-
-	if (!aunet)
-		return -EINVAL;
-	spin_lock(aunet->contid_list_lock);
-	return 0;
-}
-
-static int audit_netns_contid_unlock(const struct net *net)
-{
-	struct audit_net *aunet = net_generic(net, audit_net_id);
-
-	if (!aunet)
-		return -EINVAL;
-	spin_unlock(aunet->contid_list_lock);
-	return 0;
-}
-
 void audit_netns_contid_add(struct net *net, u64 contid)
 {
 	struct list_head *contid_list = audit_get_netns_contid_list(net);
@@ -354,10 +333,9 @@ void audit_netns_contid_add(struct net *net, u64 contid)
 
 	if (!audit_contid_valid(contid))
 		return;
-	if (audit_netns_contid_lock(net))
-		return;
+	rcu_read_lock();
 	if (!list_empty(contid_list))
-		list_for_each_entry(cont, contid_list, list)
+		list_for_each_entry_rcu(cont, contid_list, list)
 			if (cont->id == contid) {
 				refcount_inc(&cont->refcount);
 				goto out;
@@ -367,10 +345,16 @@ void audit_netns_contid_add(struct net *net, u64 contid)
 		INIT_LIST_HEAD(&cont->list);
 		cont->id = contid;
 		refcount_set(&cont->refcount, 1);
-		list_add(&cont->list, contid_list);
+		list_add_rcu(&cont->list, contid_list);
 	}
 out:
-	audit_netns_contid_unlock(net);
+	rcu_read_unlock();
+}
+
+audit_free_contid_rcu(struct rcu_head *head) {
+	struct audit_contid *contid = container_of(head, struct audit_contid, rcu);
+
+	kfree(contid);
 }
 
 void audit_netns_contid_del(struct net *net, u64 contid)
@@ -380,17 +364,16 @@ void audit_netns_contid_del(struct net *net, u64 contid)
 
 	if (!audit_contid_valid(contid))
 		return;
-	if (audit_netns_contid_lock(net))
-		return;
+	rcu_read_lock();
 	if (!list_empty(contid_list))
-		list_for_each_entry(cont, contid_list, list)
+		list_for_each_entry_rcu(cont, contid_list, list)
 			if (cont->id == contid) {
-				list_del(&cont->list);
+				list_del_rcu(&cont->list);
 				if (refcount_dec_and_test(&cont->refcount))
-					kfree(cont);
+					call_rcu(&cont->rcu, audit_free_contid_rcu);
 				break;
 			}
-	audit_netns_contid_unlock(net);
+	rcu_read_unlock();
 }
 
 void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p)
@@ -418,15 +401,14 @@ void audit_log_netns_contid_list(struct net *net, struct audit_context *context)
 		return;
 	}
 	audit_log_format(ab, "ref=net contid=");
-	if (audit_netns_contid_lock(net))
-		return;
-	list_for_each_entry(cont, audit_get_netns_contid_list(net), list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(cont, audit_get_netns_contid_list(net), list) {
 		if (!first)
 			audit_log_format(ab, ",");
 		audit_log_format(ab, "%llu", cont->id);
 		first = false;
 	}
-	audit_netns_contid_unlock(net);
+	rcu_read_unlock();
 	audit_log_end(ab);
 }
 EXPORT_SYMBOL(audit_log_netns_contid_list);
@@ -1674,7 +1656,6 @@ static int __net_init audit_net_init(struct net *net)
 		.flags	= NL_CFG_F_NONROOT_RECV,
 		.groups	= AUDIT_NLGRP_MAX,
 	};
-
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
@@ -1684,8 +1665,6 @@ static int __net_init audit_net_init(struct net *net)
 	}
 	aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
 	INIT_LIST_HEAD(&aunet->contid_list);
-	spin_lock_init(&aunet->contid_list_lock);
-
 	return 0;
 }
 
> 
> > +       audit_log_end(ab);
> > +}
> > +EXPORT_SYMBOL(audit_log_netns_contid_list);
> >
> >  void audit_panic(const char *message)
> >  {
> >         switch (audit_failure) {
> > diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
> > index af883f1..44fac3f 100644
> > --- a/net/netfilter/xt_AUDIT.c
> > +++ b/net/netfilter/xt_AUDIT.c
> > @@ -71,10 +71,13 @@ static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
> >  {
> >         struct audit_buffer *ab;
> >         int fam = -1;
> > +       struct audit_context *context;
> > +       struct net *net;
> >
> >         if (audit_enabled == AUDIT_OFF)
> > -               goto errout;
> > -       ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
> > +               goto out;
> > +       context = audit_alloc_local(GFP_ATOMIC);
> > +       ab = audit_log_start(context, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
> >         if (ab == NULL)
> >                 goto errout;
> >
> > @@ -104,7 +107,12 @@ static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
> >
> >         audit_log_end(ab);
> >
> > +       net = xt_net(par);
> > +       audit_log_netns_contid_list(net, context);
> > +
> >  errout:
> > +       audit_free_context(context);
> > +out:
> >         return XT_CONTINUE;
> >  }
> >
> 
> --
> paul moore
> www.paul-moore.com

- RGB

--
Richard Guy Briggs <rgb@xxxxxxxxxx>
Sr. S/W Engineer, Kernel Security, Base Operating Systems
Remote, Ottawa, Red Hat Canada
IRC: rgb, SunRaycer
Voice: +1.647.777.2635, Internal: (81) 32635