ipv4: IP defragmentation must be ECN aware
RFC3168 (The Addition of Explicit Congestion Notification to IP)
states :
5.3. Fragmentation
ECN-capable packets MAY have the DF (Don't Fragment) bit set.
Reassembly of a fragmented packet MUST NOT lose indications of
congestion. In other words, if any fragment of an IP packet to be
reassembled has the CE codepoint set, then one of two actions MUST be
taken:
* Set the CE codepoint on the reassembled packet. However, this
MUST NOT occur if any of the other fragments contributing to
this reassembly carries the Not-ECT codepoint.
* The packet is dropped, instead of being reassembled, for any
other reason.
This patch implements this requirement for IPv4, choosing the first
action :
If one fragment had NO-ECT codepoint
reassembled frame has NO-ECT
ElIf one fragment had CE codepoint
reassembled frame has CE
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e6215bd..a1151b8 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -45,6 +45,7 @@
#include <linux/udp.h>
#include <linux/inet.h>
#include <linux/netfilter_ipv4.h>
+#include <net/inet_ecn.h>
/* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
* code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
@@ -70,11 +71,28 @@
__be32 daddr;
__be16 id;
u8 protocol;
+ u8 ecn; /* RFC3168 support */
int iif;
unsigned int rid;
struct inet_peer *peer;
};
+#define IPFRAG_ECN_CLEAR 0x01 /* one frag had INET_ECN_NOT_ECT */
+#define IPFRAG_ECN_SET_CE 0x04 /* one frag had INET_ECN_CE */
+
+static inline u8 ip4_frag_ecn(u8 tos)
+{
+ tos = (tos & INET_ECN_MASK) + 1;
+ /*
+ * After the last operation we have (in binary):
+ * INET_ECN_NOT_ECT => 001
+ * INET_ECN_ECT_1 => 010
+ * INET_ECN_ECT_0 => 011
+ * INET_ECN_CE => 100
+ */
+ return (tos & 2) ? 0 : tos;
+}
+
static struct inet_frags ip4_frags;
int ip_frag_nqueues(struct net *net)
@@ -137,6 +155,7 @@
qp->protocol = arg->iph->protocol;
qp->id = arg->iph->id;
+ qp->ecn = ip4_frag_ecn(arg->iph->tos);
qp->saddr = arg->iph->saddr;
qp->daddr = arg->iph->daddr;
qp->user = arg->user;
@@ -316,6 +335,7 @@
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
qp->iif = 0;
+ qp->ecn = 0;
return 0;
}
@@ -328,6 +348,7 @@
int flags, offset;
int ihl, end;
int err = -ENOENT;
+ u8 ecn;
if (qp->q.last_in & INET_FRAG_COMPLETE)
goto err;
@@ -339,6 +360,7 @@
goto err;
}
+ ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
@@ -472,6 +494,7 @@
}
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
+ qp->ecn |= ecn;
atomic_add(skb->truesize, &qp->q.net->mem);
if (offset == 0)
qp->q.last_in |= INET_FRAG_FIRST_IN;
@@ -583,6 +606,17 @@
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
+ /* RFC3168 5.3 Fragmentation support
+ * If one fragment had INET_ECN_NOT_ECT,
+ * reassembled frame also has INET_ECN_NOT_ECT
+ * Elif one fragment had INET_ECN_CE
+ * reassembled frame also has INET_ECN_CE
+ */
+ if (qp->ecn & IPFRAG_ECN_CLEAR)
+ iph->tos &= ~INET_ECN_MASK;
+ else if (qp->ecn & IPFRAG_ECN_SET_CE)
+ iph->tos |= INET_ECN_CE;
+
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;