git: 41b7760991ef - releng/13.2 - pf: handle multiple IPv6 fragment headers

From: Gordon Tetlow <>
Date: Wed, 06 Sep 2023 17:37:33 UTC
The branch releng/13.2 has been updated by gordon:


commit 41b7760991efda33f696c45d9eeaefd8bc63a847
Author:     Kristof Provost <>
AuthorDate: 2023-07-13 08:25:49 +0000
Commit:     Gordon Tetlow <>
CommitDate: 2023-09-06 16:58:39 +0000

    pf: handle multiple IPv6 fragment headers
    With 'scrub fragment reassemble' if a packet contains multiple IPv6
    fragment headers we would reassemble the packet and immediately
    continue processing it.
    That is, we'd remove the first fragment header and expect the next
    header to be a final header (i.e. TCP, UDP, ICMPv6, ...). However, if
    it's another fragment header we'd not treat the packet correctly.
    That is, we'd fail to recognise the payload and treat it as if it were
    an IPv6 fragment rather than as its actual payload.
    Fix this by restarting the normalisation on the reassembled packet.
    If there are multiple fragment headers drop the packet.
    Reported by:    Enrico Bassetti (NetSecurityLab @ Sapienza University of Rome)
    Sponsored by:   Rubicon Communications, LLC ("Netgate")
    Approved by:    so
    Security:       CVE-2023-4809
    (cherry picked from commit 76afcbb52492f9b3e72ee7d4c4ed0a54c25e1c48)
    (cherry picked from commit 3a0461f23a4f4fe8fc82b3445285d3d07787b016)
 sys/netpfil/pf/pf_norm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/sys/netpfil/pf/pf_norm.c b/sys/netpfil/pf/pf_norm.c
index 56b30faf7e52..d4eb3c98eed5 100644
--- a/sys/netpfil/pf/pf_norm.c
+++ b/sys/netpfil/pf/pf_norm.c
@@ -1216,6 +1216,8 @@ pf_normalize_ip6(struct mbuf **m0, int dir, struct pfi_kkif *kif,
 	if (sizeof(struct ip6_hdr) + IPV6_MAXPACKET < m->m_pkthdr.len)
 		goto drop;
+	h = mtod(m, struct ip6_hdr *);
 	plen = ntohs(h->ip6_plen);
 	/* jumbo payload option not supported */
 	if (plen == 0)
@@ -1286,6 +1288,8 @@ pf_normalize_ip6(struct mbuf **m0, int dir, struct pfi_kkif *kif,
 	return (PF_PASS);
+	if (pd->flags & PFDESC_IP_REAS)
+		return (PF_DROP);
 	if (sizeof(struct ip6_hdr) + plen > m->m_pkthdr.len)
 		goto shortpkt;
@@ -1303,7 +1307,7 @@ pf_normalize_ip6(struct mbuf **m0, int dir, struct pfi_kkif *kif,
 		return (PF_DROP);
 	pd->flags |= PFDESC_IP_REAS;
-	return (PF_PASS);
+	goto again;