[PATCH 4.4 58/65] inet: frags: get rif of inet_frag_evicting()

From: Greg Kroah-Hartman
Date: Mon Feb 04 2019 - 05:42:02 EST


4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <edumazet@xxxxxxxxxx>

commit 399d1404be660d355192ff4df5ccc3f4159ec1e4 upstream.

This refactors ip_expire() since one indentation level is removed.

Note: in the future, we should try hard to avoid the skb_clone()
since this is a serious performance cost.
Under DDOS, the ICMP message wont be sent because of rate limits.

Fact that ip6_expire_frag_queue() does not use skb_clone() is
disturbing too. Presumably IPv6 should have the same
issue than the one we fixed in commit ec4fbd64751d
("inet: frag: release spinlock before calling icmp_send()")

Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Mao Wenan <maowenan@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
include/net/inet_frag.h | 5 ---
net/ipv4/ip_fragment.c | 66 +++++++++++++++++++++++-------------------------
net/ipv6/reassembly.c | 4 --
3 files changed, 32 insertions(+), 43 deletions(-)

--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -123,11 +123,6 @@ static inline void inet_frag_put(struct
inet_frag_destroy(q, f);
}

-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
- return !hlist_unhashed(&q->list_evictor);
-}
-
/* Memory Tracking Functions. */

static inline int frag_mem_limit(struct netns_frags *nf)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -194,8 +194,11 @@ static bool frag_expire_skip_icmp(u32 us
*/
static void ip_expire(unsigned long arg)
{
- struct ipq *qp;
+ struct sk_buff *clone, *head;
+ const struct iphdr *iph;
struct net *net;
+ struct ipq *qp;
+ int err;

qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -209,45 +212,40 @@ static void ip_expire(unsigned long arg)
ipq_kill(qp);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);

- if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *clone, *head = qp->q.fragments;
- const struct iphdr *iph;
- int err;
-
- IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
+ head = qp->q.fragments;

- if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
- goto out;
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);

- head->dev = dev_get_by_index_rcu(net, qp->iif);
- if (!head->dev)
- goto out;
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;

+ head->dev = dev_get_by_index_rcu(net, qp->iif);
+ if (!head->dev)
+ goto out;

- /* skb has no dst, perform route lookup again */
- iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+ /* 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);
- if (err)
- goto out;
+ if (err)
+ goto out;
+
+ /* Only an end host needs to send an ICMP
+ * "Fragment Reassembly Timeout" message, per RFC792.
+ */
+ if (frag_expire_skip_icmp(qp->user) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL))
+ goto out;
+
+ clone = skb_clone(head, GFP_ATOMIC);

- /* Only an end host needs to send an ICMP
- * "Fragment Reassembly Timeout" message, per RFC792.
- */
- if (frag_expire_skip_icmp(qp->user) &&
- (skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out;
-
- clone = skb_clone(head, GFP_ATOMIC);
-
- /* Send an ICMP "Fragment Reassembly Timeout" message. */
- if (clone) {
- spin_unlock(&qp->q.lock);
- icmp_send(clone, ICMP_TIME_EXCEEDED,
- ICMP_EXC_FRAGTIME, 0);
- consume_skb(clone);
- goto out_rcu_unlock;
- }
+ /* Send an ICMP "Fragment Reassembly Timeout" message. */
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
}
out:
spin_unlock(&qp->q.lock);
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -146,10 +146,6 @@ void ip6_expire_frag_queue(struct net *n
goto out_rcu_unlock;

IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
- if (inet_frag_evicting(&fq->q))
- goto out_rcu_unlock;
-
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);

/* Don't send error if the first segment did not arrive. */