diff mbox series

[ipsec] xfrm: xfrm_state_mtu should return at least 1280 for ipv6

Message ID 62a73daeec236ed1346a89042050fe4b2fd06226.1618394317.git.sd@queasysnail.net (mailing list archive)
State Awaiting Upstream
Delegated to: Netdev Maintainers
Headers show
Series [ipsec] xfrm: xfrm_state_mtu should return at least 1280 for ipv6 | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Guessed tree name to be net-next
netdev/subject_prefix warning Target tree name not specified in the subject
netdev/cc_maintainers fail 2 blamed authors not CCed: davem@davemloft.net bpoirier@suse.de; 6 maintainers not CCed: dsahern@kernel.org yoshfuji@linux-ipv6.org herbert@gondor.apana.org.au davem@davemloft.net bpoirier@suse.de kuba@kernel.org
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 315 this patch: 315
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 270 this patch: 270
netdev/header_inline success Link

Commit Message

Sabrina Dubroca April 16, 2021, 9:27 a.m. UTC
Jianwen reported that IPv6 Interoperability tests are failing in an
IPsec case where one of the links between the IPsec peers has an MTU
of 1280. The peer generates a packet larger than this MTU, the router
replies with a "Packet too big" message indicating an MTU of 1280.
When the peer tries to send another large packet, xfrm_state_mtu
returns 1280 - ipsec_overhead, which causes ip6_setup_cork to fail
with EINVAL.

We can fix this by forcing xfrm_state_mtu to return IPV6_MIN_MTU when
IPv6 is used. After going through IPsec, the packet will then be
fragmented to obey the actual network's PMTU, just before leaving the
host.

Currently, TFC padding is capped to PMTU - overhead to avoid
fragementation: after padding and encapsulation, we still fit within
the PMTU. That behavior is preserved in this patch.

Fixes: 91657eafb64b ("xfrm: take net hdr len into account for esp payload size calculation")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
---
 include/net/xfrm.h    |  1 +
 net/ipv4/esp4.c       |  2 +-
 net/ipv6/esp6.c       |  2 +-
 net/xfrm/xfrm_state.c | 14 ++++++++++++--
 4 files changed, 15 insertions(+), 4 deletions(-)

Comments

Steffen Klassert April 20, 2021, 11:59 a.m. UTC | #1
On Fri, Apr 16, 2021 at 11:27:59AM +0200, Sabrina Dubroca wrote:
> Jianwen reported that IPv6 Interoperability tests are failing in an
> IPsec case where one of the links between the IPsec peers has an MTU
> of 1280. The peer generates a packet larger than this MTU, the router
> replies with a "Packet too big" message indicating an MTU of 1280.
> When the peer tries to send another large packet, xfrm_state_mtu
> returns 1280 - ipsec_overhead, which causes ip6_setup_cork to fail
> with EINVAL.
> 
> We can fix this by forcing xfrm_state_mtu to return IPV6_MIN_MTU when
> IPv6 is used. After going through IPsec, the packet will then be
> fragmented to obey the actual network's PMTU, just before leaving the
> host.
> 
> Currently, TFC padding is capped to PMTU - overhead to avoid
> fragementation: after padding and encapsulation, we still fit within
> the PMTU. That behavior is preserved in this patch.
> 
> Fixes: 91657eafb64b ("xfrm: take net hdr len into account for esp payload size calculation")
> Reported-by: Jianwen Ji <jiji@redhat.com>
> Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>

Applied, thanks Sabrina!
diff mbox series

Patch

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c58a6d4eb610..6232a5f048bd 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1546,6 +1546,7 @@  void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 int xfrm_init_replay(struct xfrm_state *x);
+u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu);
 u32 xfrm_state_mtu(struct xfrm_state *x, int mtu);
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4b834bbf95e0..ed9857b2875d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -673,7 +673,7 @@  static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 727d791ed5e6..9d1327b36bd3 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -708,7 +708,7 @@  static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 4496f7efa220..c25586156c6a 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2518,7 +2518,7 @@  void xfrm_state_delete_tunnel(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_delete_tunnel);
 
-u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
+u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu)
 {
 	const struct xfrm_type *type = READ_ONCE(x->type);
 	struct crypto_aead *aead;
@@ -2549,7 +2549,17 @@  u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
-EXPORT_SYMBOL_GPL(xfrm_state_mtu);
+EXPORT_SYMBOL_GPL(__xfrm_state_mtu);
+
+u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
+{
+	mtu = __xfrm_state_mtu(x, mtu);
+
+	if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU)
+		return IPV6_MIN_MTU;
+
+	return mtu;
+}
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {