net/packet: remove data races in fanout operations

af_packet fanout uses RCU rules to ensure f->arr elements are not dismantled before RCU grace period. However, it lacks rcu accessors to make sure KCSAN and other tools wont detect data races. Stupid compilers could also play games. Fixes: dc99f60 ("packet: Add fanout support.") Signed-off-by: Eric Dumazet <[email protected]> Reported-by: "Gong, Sishuai" <[email protected]> Cc: Willem de Bruijn <[email protected]> Signed-off-by: David S. Miller <[email protected]>
torvalds · Apr 14, 2021 · 94f633e · 94f633e
1 parent ae1ea84
commit 94f633e
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 7 deletions.
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
@@ -1359,7 +1359,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 	struct packet_sock *po, *po_next, *po_skip = NULL;
 	unsigned int i, j, room = ROOM_NONE;
 
-	po = pkt_sk(f->arr[idx]);
+	po = pkt_sk(rcu_dereference(f->arr[idx]));
 
 	if (try_self) {
 		room = packet_rcv_has_room(po, skb);
@@ -1371,7 +1371,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 
 	i = j = min_t(int, po->rollover->sock, num - 1);
 	do {
-		po_next = pkt_sk(f->arr[i]);
+		po_next = pkt_sk(rcu_dereference(f->arr[i]));
 		if (po_next != po_skip && !READ_ONCE(po_next->pressure) &&
 		    packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) {
 			if (i != j)
@@ -1466,7 +1466,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER))
 		idx = fanout_demux_rollover(f, skb, idx, true, num);
 
-	po = pkt_sk(f->arr[idx]);
+	po = pkt_sk(rcu_dereference(f->arr[idx]));
 	return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev);
 }
 
@@ -1480,7 +1480,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	struct packet_fanout *f = po->fanout;
 
 	spin_lock(&f->lock);
-	f->arr[f->num_members] = sk;
+	rcu_assign_pointer(f->arr[f->num_members], sk);
 	smp_wmb();
 	f->num_members++;
 	if (f->num_members == 1)
@@ -1495,11 +1495,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 
 	spin_lock(&f->lock);
 	for (i = 0; i < f->num_members; i++) {
-		if (f->arr[i] == sk)
+		if (rcu_dereference_protected(f->arr[i],
+					      lockdep_is_held(&f->lock)) == sk)
 			break;
 	}
 	BUG_ON(i >= f->num_members);
-	f->arr[i] = f->arr[f->num_members - 1];
+	rcu_assign_pointer(f->arr[i],
+			   rcu_dereference_protected(f->arr[f->num_members - 1],
+						     lockdep_is_held(&f->lock)));
 	f->num_members--;
 	if (f->num_members == 0)
 		__dev_remove_pack(&f->prot_hook);

diff --git a/net/packet/internal.h b/net/packet/internal.h
@@ -94,7 +94,7 @@ struct packet_fanout {
 	spinlock_t		lock;
 	refcount_t		sk_ref;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
-	struct sock		*arr[];
+	struct sock	__rcu	*arr[];
 };
 
 struct packet_rollover {