From 1d0dd1db15bc5dedc25bcdebf3dd382436f11f8a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Apr 2013 12:55:41 +0000 Subject: 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 Tested-by: Tom Parkin Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_fragment.c | 15 +++++++++++---- net/ipv6/reassembly.c | 13 +++++++++++-- 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8e2887170bc2..4a40457d8d14 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -251,8 +251,7 @@ 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); @@ -517,8 +516,16 @@ found: qp->q.last_in |= INET_FRAG_FIRST_IN; 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 5ff412f45a5a..6bda7aa551b8 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -385,8 +385,17 @@ 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); -- cgit v1.2.3