Revert "xfrm: xfrm_state_mtu should return at least 1280 for ipv6"

This reverts commit b515d2637276a3810d6595e10ab02c13bfd0b63a.

Commit b515d2637276a3810d6595e10ab02c13bfd0b63a ("xfrm: xfrm_state_mtu
should return at least 1280 for ipv6") in v5.14 breaks the TCP MSS
calculation in ipsec transport mode, resulting complete stalls of TCP
connections. This happens when the (P)MTU is 1280 or slighly larger.

The desired formula for the MSS is:
MSS = (MTU - ESP_overhead) - IP header - TCP header

However, the above commit clamps the (MTU - ESP_overhead) to a
minimum of 1280, turning the formula into
MSS = max(MTU - ESP overhead, 1280) -  IP header - TCP header

With the (P)MTU near 1280, the calculated MSS is too large and the
resulting TCP packets never make it to the destination because they
are over the actual PMTU.

The above commit also causes suboptimal double fragmentation in
xfrm tunnel mode, as described in
https://lore.kernel.org/netdev/20210429202529.codhwpc7w6kbudug@dwarf.suse.cz/

The original problem the above commit was trying to fix is now fixed
by commit 6596a0229541270fb8d38d989f91b78838e5e9da ("xfrm: fix MTU
regression").

Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 743dd1da506e86835d4dcd6bd169c65956380af4..76aa6f11a540946c9d429f1cca4fe13b1d2a9385 100644 (file)
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1568,7 +1568,6 @@ 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 851f542928a33bfed77f50ba1fc2185f2eefa187..e1b1d080e908d4b13561e641cb21437686db6cee 100644 (file)
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -671,7 +671,7 @@ 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 8bb2c407b46b3f6dec99ddb9ccc3f21a0255323a..7591160edce14d4eb75abdf5c2d72099ea92ae68 100644 (file)
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -707,7 +707,7 @@ 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 1ba6fbfe8cdbcb0fd340641b31c9efb1f1325a2e..b749935152ba5ae1bc3994ad1b57caefbcab2c4c 100644 (file)
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2579,7 +2579,7 @@ 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;
@@ -2610,17 +2610,7 @@ 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);
-
-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;
-}
+EXPORT_SYMBOL_GPL(xfrm_state_mtu);
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {