net: drop dst before queueing fragments

[ Upstream commit 97599dc792b45b1669c3cdb9a4b365aad0232f65 ]

Commit 4a94445c9a5c (net: Use ip_route_input_noref() in input path)
added a bug in IP defragmentation handling, as non refcounted
dst could escape an RCU protected section.

Commit 64f3b9e203bd068 (net: ip_expire() must revalidate route) fixed
the case of timeouts, but not the general problem.

Tom Parkin noticed crashes in UDP stack and provided a patch,
but further analysis permitted us to pinpoint the root cause.

Before queueing a packet into a frag list, we must drop its dst,
as this dst has limited lifetime (RCU protected)

When/if a packet is finally reassembled, we use the dst of the very
last skb, still protected by RCU and valid, as the dst of the
reassembled packet.

Use same logic in IPv6, as there is no need to hold dst references.

Reported-by: Tom Parkin <tparkin@katalix.com>
Tested-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a8fc332d07f7e33255728ef7d112d1b3610d164c..0fcfee37227edac26a8a18132bbf3132c07bb685 100644 (file)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -255,8 +255,7 @@ static void ip_expire(unsigned long arg)
                if (!head->dev)
                        goto out_rcu_unlock;
 
-               /* skb dst is stale, drop it, and perform route lookup again */
-               skb_dst_drop(head);
+               /* skb has no dst, perform route lookup again */
                iph = ip_hdr(head);
                err = ip_route_input_noref(head, iph->daddr, iph->saddr,
                                           iph->tos, head->dev);
@@ -525,8 +524,16 @@ found:
                qp->q.max_size = skb->len + ihl;
 
        if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-           qp->q.meat == qp->q.len)
-               return ip_frag_reasm(qp, prev, dev);
+           qp->q.meat == qp->q.len) {
+               unsigned long orefdst = skb->_skb_refdst;
+
+               skb->_skb_refdst = 0UL;
+               err = ip_frag_reasm(qp, prev, dev);
+               skb->_skb_refdst = orefdst;
+               return err;
+       }
+
+       skb_dst_drop(skb);
 
        write_lock(&ip4_frags.lock);
        list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index d9ba8a27fde329a4dc6176ae8b6536a598c12e43..7a610a673638e62b813f344a81c9bf86563b5387 100644 (file)
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -342,8 +342,17 @@ found:
        }
 
        if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-           fq->q.meat == fq->q.len)
-               return ip6_frag_reasm(fq, prev, dev);
+           fq->q.meat == fq->q.len) {
+               int res;
+               unsigned long orefdst = skb->_skb_refdst;
+
+               skb->_skb_refdst = 0UL;
+               res = ip6_frag_reasm(fq, prev, dev);
+               skb->_skb_refdst = orefdst;
+               return res;
+       }
+
+       skb_dst_drop(skb);
 
        write_lock(&ip6_frags.lock);
        list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);