net: sched: take reference to psample group in flow_action infra

With recent patch set that removed rtnl lock dependency from cls hardware
offload API rtnl lock is only taken when reading action data and can be
released after action-specific data is parsed into intermediate
representation. However, sample action psample group is passed by pointer
without obtaining reference to it first, which makes it possible to
concurrently overwrite the action and deallocate object pointed by
psample_group pointer after rtnl lock is released but before driver
finished using the pointer.

To prevent such race condition, obtain reference to psample group while it
is used by flow_action infra. Extend psample API with function
psample_group_take() that increments psample group reference counter.
Extend struct tc_action_ops with new get_psample_group() API. Implement the
API for action sample using psample_group_take() and already existing
psample_group_put() as a destructor. Use it in tc_setup_flow_action() to
take reference to psample group pointed to by entry->sample.psample_group
and release it in tc_cleanup_flow_action().

Disable bh when taking psample_groups_lock. The lock is now taken while
holding action tcf_lock that is used by data path and requires bh to be
disabled, so doing the same for psample_groups_lock is necessary to
preserve SOFTIRQ-irq-safety.

Fixes: 918190f50eb6 ("net: sched: flower: don't take rtnl lock for cls hw offloads API")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 38 insertions, 2 deletions

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 10229124a992..692c4c9040fd 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -252,6 +252,32 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static void tcf_psample_group_put(void *priv)
+{
+	struct psample_group *group = priv;
+
+	psample_group_put(group);
+}
+
+static struct psample_group *
+tcf_sample_get_group(const struct tc_action *a,
+		     tc_action_priv_destructor *destructor)
+{
+	struct tcf_sample *s = to_sample(a);
+	struct psample_group *group;
+
+	spin_lock_bh(&s->tcf_lock);
+	group = rcu_dereference_protected(s->psample_group,
+					  lockdep_is_held(&s->tcf_lock));
+	if (group) {
+		psample_group_take(group);
+		*destructor = tcf_psample_group_put;
+	}
+	spin_unlock_bh(&s->tcf_lock);
+
+	return group;
+}
+
 static struct tc_action_ops act_sample_ops = {
 	.kind	  = "sample",
 	.id	  = TCA_ID_SAMPLE,
@@ -262,6 +288,7 @@ static struct tc_action_ops act_sample_ops = {
 	.cleanup  = tcf_sample_cleanup,
 	.walk	  = tcf_sample_walker,
 	.lookup	  = tcf_sample_search,
+	.get_psample_group = tcf_sample_get_group,
 	.size	  = sizeof(struct tcf_sample),
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c668195379bd..60d44b14750a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3324,6 +3324,16 @@ static int tcf_tunnel_encap_get_tunnel(struct flow_action_entry *entry,
 	return 0;
 }
 
+static void tcf_sample_get_group(struct flow_action_entry *entry,
+				 const struct tc_action *act)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	entry->sample.psample_group =
+		act->ops->get_psample_group(act, &entry->destructor);
+	entry->destructor_priv = entry->sample.psample_group;
+#endif
+}
+
 int tc_setup_flow_action(struct flow_action *flow_action,
 			 const struct tcf_exts *exts, bool rtnl_held)
 {
@@ -3417,11 +3427,10 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->mark = tcf_skbedit_mark(act);
 		} else if (is_tcf_sample(act)) {
 			entry->id = FLOW_ACTION_SAMPLE;
-			entry->sample.psample_group =
-				tcf_sample_psample_group(act);
 			entry->sample.trunc_size = tcf_sample_trunc_size(act);
 			entry->sample.truncate = tcf_sample_truncate(act);
 			entry->sample.rate = tcf_sample_rate(act);
+			tcf_sample_get_group(entry, act);
 		} else if (is_tcf_police(act)) {
 			entry->id = FLOW_ACTION_POLICE;
 			entry->police.burst = tcf_police_tcfp_burst(act);