net/sched: tcindex: update imperfect hash filters respecting rcu

The imperfect hash area can be updated while packets are traversing,
which will cause a use-after-free when 'tcf_exts_exec()' is called
with the destroyed tcf_ext.

CPU 0:               CPU 1:
tcindex_set_parms    tcindex_classify
tcindex_lookup
                     tcindex_lookup
tcf_exts_change
                     tcf_exts_exec [UAF]

Stop operating on the shared area directly, by using a local copy,
and update the filter with 'rcu_replace_pointer()'. Delete the old
filter version only after a rcu grace period elapsed.

Fixes: 9b0d4446b569 ("net: sched: avoid atomic swap in tcf_exts_change")
Reported-by: valis <sec@valis.email>
Suggested-by: valis <sec@valis.email>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20230209143739.279867-1-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 30 insertions, 4 deletions

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index ee2a050c887b..ba7f22a49397 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/refcount.h>
+#include <linux/rcupdate.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
@@ -339,6 +340,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	struct tcf_result cr = {};
 	int err, balloc = 0;
 	struct tcf_exts e;
+	bool update_h = false;
 
 	err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 	if (err < 0)
@@ -456,10 +458,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		}
 	}
 
-	if (cp->perfect)
+	if (cp->perfect) {
 		r = cp->perfect + handle;
-	else
-		r = tcindex_lookup(cp, handle) ? : &new_filter_result;
+	} else {
+		/* imperfect area is updated in-place using rcu */
+		update_h = !!tcindex_lookup(cp, handle);
+		r = &new_filter_result;
+	}
 
 	if (r == &new_filter_result) {
 		f = kzalloc(sizeof(*f), GFP_KERNEL);
@@ -485,7 +490,28 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	rcu_assign_pointer(tp->root, cp);
 
-	if (r == &new_filter_result) {
+	if (update_h) {
+		struct tcindex_filter __rcu **fp;
+		struct tcindex_filter *cf;
+
+		f->result.res = r->res;
+		tcf_exts_change(&f->result.exts, &r->exts);
+
+		/* imperfect area bucket */
+		fp = cp->h + (handle % cp->hash);
+
+		/* lookup the filter, guaranteed to exist */
+		for (cf = rcu_dereference_bh_rtnl(*fp); cf;
+		     fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp))
+			if (cf->key == handle)
+				break;
+
+		f->next = cf->next;
+
+		cf = rcu_replace_pointer(*fp, f, 1);
+		tcf_exts_get_net(&cf->result.exts);
+		tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work);
+	} else if (r == &new_filter_result) {
 		struct tcindex_filter *nfp;
 		struct tcindex_filter __rcu **fp;