tap: Explicitly drop IPv4 fragments, and give a warning

We don't handle defragmentation of IP packets coming from the tap side,
and we're unlikely to any time soon (with our large MTU, it's not useful
for practical use cases).  Currently, however, we simply ignore the
fragmentation flags and treat fragments as though they were whole IP
packets.  This isn't ideal and can lead to rather cryptic behaviour if we
do receive IP fragments.

Change the code to explicitly drop fragmented packets, and print a rate
limited warning if we do encounter them.

Link: https://bugs.passt.top/show_bug.cgi?id=62
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

1 files changed, 31 insertions, 0 deletions

diff --git a/tap.c b/tap.c
index e323529..a6a73d3 100644
--- a/tap.c
+++ b/tap.c
@@ -62,6 +62,7 @@ static PACKET_POOL_NOINIT(pool_tap4, TAP_MSGS, pkt_buf);
 static PACKET_POOL_NOINIT(pool_tap6, TAP_MSGS, pkt_buf);
 
 #define TAP_SEQS		128 /* Different L4 tuples in one batch */
+#define FRAGMENT_MSG_RATE	10  /* # seconds between fragment warnings */
 
 /**
  * tap_send() - Send frame, with qemu socket header if needed
@@ -544,6 +545,32 @@ static void tap_packet_debug(const struct iphdr *iph,
 }
 
 /**
+ * tap4_is_fragment() - Determine if a packet is an IP fragment
+ * @iph:	IPv4 header (length already validated)
+ * @now:	Current timestamp
+ *
+ * Return: true if iph is an IP fragment, false otherwise
+ */
+static bool tap4_is_fragment(const struct iphdr *iph,
+			     const struct timespec *now)
+{
+	if (ntohs(iph->frag_off) & ~IP_DF) {
+		/* Ratelimit messages */
+		static time_t last_message;
+		static unsigned num_dropped;
+
+		num_dropped++;
+		if (now->tv_sec - last_message > FRAGMENT_MSG_RATE) {
+			warn("Can't process IPv4 fragments (%lu dropped)", num_dropped);
+			last_message = now->tv_sec;
+			num_dropped = 0;
+		}
+		return true;
+	}
+	return false;
+}
+
+/**
  * tap4_handler() - IPv4 and ARP packet handler for tap file descriptor
  * @c:		Execution context
  * @in:		Ingress packet pool, packets with Ethernet headers
@@ -591,6 +618,10 @@ resume:
 		    hlen > l3_len)
 			continue;
 
+		/* We don't handle IP fragments, drop them */
+		if (tap4_is_fragment(iph, now))
+			continue;
+
 		l4_len = l3_len - hlen;
 
 		if (iph->saddr && c->ip4.addr_seen.s_addr != iph->saddr) {