Date: Wed, 6 Sep 2023 17:37:33 GMT From: Gordon Tetlow <gordon@FreeBSD.org> To: src-committers@FreeBSD.org, dev-commits-src-all@FreeBSD.org, dev-commits-src-branches@FreeBSD.org Subject: git: 41b7760991ef - releng/13.2 - pf: handle multiple IPv6 fragment headers Message-ID: <202309061737.386HbXXZ086487@gitrepo.freebsd.org>
next in thread | raw e-mail | index | archive | help
The branch releng/13.2 has been updated by gordon: URL: https://cgit.FreeBSD.org/src/commit/?id=41b7760991efda33f696c45d9eeaefd8bc63a847 commit 41b7760991efda33f696c45d9eeaefd8bc63a847 Author: Kristof Provost <kp@FreeBSD.org> AuthorDate: 2023-07-13 08:25:49 +0000 Commit: Gordon Tetlow <gordon@FreeBSD.org> 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 bassetti@di.uniroma1.it (NetSecurityLab @ Sapienza University of Rome) Sponsored by: Rubicon Communications, LLC ("Netgate") Approved by: so Security: FreeBSD-SA-23:10.pf 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; +again: + 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); fragment: + 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; shortpkt: REASON_SET(reason, PFRES_SHORT);
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?202309061737.386HbXXZ086487>