pull request (net-next): ipsec-next 2023-04-19
Subsystems (3)
Steffen Klassert
maintainercover pull request (net-next): ipsec-next 2023-04-19
1) Remove inner/outer modes from input/output path. These are not needed anymore. From Herbert Xu.
Please pull or let me know if there are problems.
Thanks!
The following changes since commit 95b744508d4d5135ae2a096ff3f0ee882bcc52b3:
qede: remove linux/version.h and linux/compiler.h (2023-03-10 21:29:54 -0800)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git tags/ipsec-next-2023-04-19
for you to fetch changes up to f4796398f21b9844017a2dac883b1dd6ad6edd60:
xfrm: Remove inner/outer modes from output path (2023-03-13 11:51:13 +0100)
----------------------------------------------------------------
ipsec-next-2023-04-19
----------------------------------------------------------------
Herbert Xu (2):
xfrm: Remove inner/outer modes from input path
xfrm: Remove inner/outer modes from output path
net/xfrm/xfrm_input.c | 66 ++++++++++++++++++-------------------------------- net/xfrm/xfrm_output.c | 33 +++++++++---------------- 2 files changed, 34 insertions(+), 65 deletions(-)
Steffen Klassert
maintainerPATCH 1/2 xfrm: Remove inner/outer modes from input path
From: Herbert Xu <[email protected]>
The inner/outer modes were added to abstract out common code that were once duplicated between IPv4 and IPv6. As time went on the abstractions have been removed and we are now left with empty shells that only contain duplicate information. These can be removed one-by-one as the same information is already present elsewhere in the xfrm_state object.
Removing them from the input path actually allows certain valid combinations that are currently disallowed. In particular, when a transport mode SA sits beneath a tunnel mode SA that changes address families, at present the transport mode SA cannot have AF_UNSPEC as its selector because it will be erroneously be treated as inter-family itself even though it simply sits beneath one.
This is a serious problem because you can't set the selector to non-AF_UNSPEC either as that will cause the selector match to fail as we always match selectors to the inner-most traffic.
--- net/xfrm/xfrm_input.c | 66 +++++++++++++++---------------------------- 1 file changed, 23 insertions(+), 43 deletions(-)
net/xfrm/xfrm_input.c +23 -43
@@ -231,9 +231,6 @@ static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) {int err = -EINVAL ; -if (XFRM_MODE_SKB_CB (skb)->protocol !=IPPROTO_IPIP ) - goto out; -if (!pskb_may_pull (skb,sizeof (struct iphdr ))) goto out;
@@ -269,8 +266,6 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) {int err = -EINVAL ; -if (XFRM_MODE_SKB_CB (skb)->protocol !=IPPROTO_IPV6 ) - goto out;if (!pskb_may_pull (skb,sizeof (struct ipv6hdr ))) goto out;
@@ -331,22 +326,26 @@ static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)*/ static int xfrm_inner_mode_encap_remove (struct xfrm_state *x, -const struct xfrm_mode *inner_mode,struct sk_buff *skb) { -switch (inner_mode->encap) { +switch (x->props.mode) {case XFRM_MODE_BEET : -if (inner_mode->family ==AF_INET ) +switch (XFRM_MODE_SKB_CB (skb)->protocol) { +case IPPROTO_IPIP : +case IPPROTO_BEETPH :return xfrm4_remove_beet_encap (x, skb); -if (inner_mode->family ==AF_INET6 ) +case IPPROTO_IPV6 :return xfrm6_remove_beet_encap (x, skb); + }break ;case XFRM_MODE_TUNNEL : -if (inner_mode->family ==AF_INET ) +switch (XFRM_MODE_SKB_CB (skb)->protocol) { +case IPPROTO_IPIP :return xfrm4_remove_tunnel_encap (x, skb); -if (inner_mode->family ==AF_INET6 ) +case IPPROTO_IPV6 :return xfrm6_remove_tunnel_encap (x, skb);break ; + } }WARN_ON_ONCE (1 );
@@ -355,9 +354,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,static int xfrm_prepare_input (struct xfrm_state *x,struct sk_buff *skb) { -const struct xfrm_mode *inner_mode = &x->inner_mode; - -switch (x->outer_mode.family) { +switch (x->props.family) {case AF_INET :xfrm4_extract_header (skb);break ;
@@ -369,17 +366,12 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)return -EAFNOSUPPORT ; } -if (x->sel.family ==AF_UNSPEC ) { - inner_mode =xfrm_ip2inner_mode (x,XFRM_MODE_SKB_CB (skb)->protocol); -if (!inner_mode) -return -EAFNOSUPPORT ; - } - -switch (inner_mode->family) { -case AF_INET : +switch (XFRM_MODE_SKB_CB (skb)->protocol) { +case IPPROTO_IPIP : +case IPPROTO_BEETPH : skb->protocol =htons (ETH_P_IP );break ; -case AF_INET6 : +case IPPROTO_IPV6 : skb->protocol =htons (ETH_P_IPV6 );break ;default :
@@ -387,7 +379,7 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)break ; } -return xfrm_inner_mode_encap_remove (x, inner_mode, skb); +return xfrm_inner_mode_encap_remove (x, skb); }/* Remove encapsulation header.
@@ -433,17 +425,16 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) }static int xfrm_inner_mode_input (struct xfrm_state *x, -const struct xfrm_mode *inner_mode,struct sk_buff *skb) { -switch (inner_mode->encap) { +switch (x->props.mode) {case XFRM_MODE_BEET :case XFRM_MODE_TUNNEL :return xfrm_prepare_input (x, skb);case XFRM_MODE_TRANSPORT : -if (inner_mode->family ==AF_INET ) +if (x->props.family ==AF_INET )return xfrm4_transport_input (x, skb); -if (inner_mode->family ==AF_INET6 ) +if (x->props.family ==AF_INET6 )return xfrm6_transport_input (x, skb);break ;case XFRM_MODE_ROUTEOPTIMIZATION :
@@ -461,7 +452,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) {const struct xfrm_state_afinfo *afinfo;struct net *net =dev_net (skb->dev); -const struct xfrm_mode *inner_mode;int err;__be32 seq;__be32 seq_hi;
@@ -491,7 +481,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - family = x->outer_mode.family; + family = x->props.family;/* An encap_type of -1 indicates async resumption. */ if (encap_type ==-1 ) {
@@ -676,17 +666,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)XFRM_MODE_SKB_CB (skb)->protocol = nexthdr; - inner_mode = &x->inner_mode; - -if (x->sel.family ==AF_UNSPEC ) { - inner_mode =xfrm_ip2inner_mode (x,XFRM_MODE_SKB_CB (skb)->protocol); -if (inner_mode ==NULL ) { -XFRM_INC_STATS (net,LINUX_MIB_XFRMINSTATEMODEERROR ); - goto drop; - } - } - -if (xfrm_inner_mode_input (x, inner_mode, skb)) { +if (xfrm_inner_mode_input (x, skb)) {XFRM_INC_STATS (net,LINUX_MIB_XFRMINSTATEMODEERROR ); goto drop; }
@@ -701,7 +681,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)* transport mode so the outer address is identical. */ daddr = &x->id.daddr; - family = x->outer_mode.family; + family = x->props.family; err =xfrm_parse_spi (skb, nexthdr, &spi, &seq);if (err <0 ) {
@@ -732,7 +712,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) err = -EAFNOSUPPORT ;rcu_read_lock (); - afinfo =xfrm_state_afinfo_get_rcu (x->inner_mode.family); + afinfo =xfrm_state_afinfo_get_rcu (x->props.family);if (likely (afinfo)) err = afinfo->transport_finish (skb, xfrm_gro || async);rcu_read_unlock ();
Signature · 1 line
2.34.1
Steffen Klassert
maintainerPATCH 2/2 xfrm: Remove inner/outer modes from output path
In reply to Steffen KlassertFrom: Herbert Xu <[email protected]>
The inner/outer modes were added to abstract out common code that were once duplicated between IPv4 and IPv6. As time went on the abstractions have been removed and we are now left with empty shells that only contain duplicate information. These can be removed one-by-one as the same information is already present elsewhere in the xfrm_state object.
Just like the input-side, removing this from the output code makes it possible to use transport-mode SAs underneath an inter-family tunnel mode SA.
--- net/xfrm/xfrm_output.c | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-)
net/xfrm/xfrm_output.c +11 -22
@@ -412,7 +412,7 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)IPCB (skb)->flags |=IPSKB_XFRM_TUNNEL_SIZE ; skb->protocol =htons (ETH_P_IP ); -switch (x->outer_mode.encap) { +switch (x->props.mode) {case XFRM_MODE_BEET :return xfrm4_beet_encap_add (x, skb);case XFRM_MODE_TUNNEL :
@@ -435,7 +435,7 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) skb->ignore_df =1 ; skb->protocol =htons (ETH_P_IPV6 ); -switch (x->outer_mode.encap) { +switch (x->props.mode) {case XFRM_MODE_BEET :return xfrm6_beet_encap_add (x, skb);case XFRM_MODE_TUNNEL :
@@ -451,22 +451,22 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)static int xfrm_outer_mode_output (struct xfrm_state *x,struct sk_buff *skb) { -switch (x->outer_mode.encap) { +switch (x->props.mode) {case XFRM_MODE_BEET :case XFRM_MODE_TUNNEL : -if (x->outer_mode.family ==AF_INET ) +if (x->props.family ==AF_INET )return xfrm4_prepare_output (x, skb); -if (x->outer_mode.family ==AF_INET6 ) +if (x->props.family ==AF_INET6 )return xfrm6_prepare_output (x, skb);break ;case XFRM_MODE_TRANSPORT : -if (x->outer_mode.family ==AF_INET ) +if (x->props.family ==AF_INET )return xfrm4_transport_output (x, skb); -if (x->outer_mode.family ==AF_INET6 ) +if (x->props.family ==AF_INET6 )return xfrm6_transport_output (x, skb);break ;case XFRM_MODE_ROUTEOPTIMIZATION : -if (x->outer_mode.family ==AF_INET6 ) +if (x->props.family ==AF_INET6 )return xfrm6_ro_output (x, skb);WARN_ON_ONCE (1 );break ;
@@ -875,21 +875,10 @@ static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)static int xfrm_inner_extract_output (struct xfrm_state *x,struct sk_buff *skb) { -const struct xfrm_mode *inner_mode; - -if (x->sel.family ==AF_UNSPEC ) - inner_mode =xfrm_ip2inner_mode (x, -xfrm_af2proto (skb_dst (skb)->ops->family)); -else - inner_mode = &x->inner_mode; - -if (inner_mode ==NULL ) -return -EAFNOSUPPORT ; - -switch (inner_mode->family) { -case AF_INET : +switch (skb->protocol) { +case htons (ETH_P_IP ):return xfrm4_extract_output (x, skb); -case AF_INET6 : +case htons (ETH_P_IPV6 ):return xfrm6_extract_output (x, skb); }
Signature · 1 line
2.34.1
Re: [PATCH 2/2] xfrm: Remove inner/outer modes from output path
Hi Steffen, Herbert,
Quoted 14 lines
(quoted diff) +0
-10@@ -875,21 +875,10 @@ static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode; - - if (x->sel.family == AF_UNSPEC) - inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb_dst(skb)->ops->family)); - else - inner_mode = &x->inner_mode; - - if (inner_mode == NULL) - return -EAFNOSUPPORT;
Review static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) · line 883
Quoted 10 lines
(quoted diff) +3
-4- - switch (inner_mode->family) { - case AF_INET: + switch (skb->protocol) { + case htons(ETH_P_IP): return xfrm4_extract_output(x, skb); - case AF_INET6: + case htons(ETH_P_IPV6): return xfrm6_extract_output(x, skb); }
The changes in this function indirectly break tunneling IPv4 packets sent from RAW sockets. Such packets currently don't have skb->protocol set, so this results in EAFNOSUPPORT. For IPv6, this isn't a problem because the protocol is set since v3.11, or more specifically 9c9c9ad5fae7 ("ipv6: set skb->protocol on tcp, raw and ip6_append_data genereated skbs"). For IPv4, that's not the case. I wonder why this hasn't been an issue so far (e.g. with MTU calculation as mentioned in that commit for IPv6).
To fix this, we basically need the patch below. The question is how it should be marked with regards to a Fixes: tag. Should it actually reference this xfrm-specific commit? Or should it even get backported further (e.g. reference the ipv6 commit above)? (The question then would be if this change could have unintended side-effects.)
net/ipv4/raw.c +1 -0
@@ -350,6 +350,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error;skb_reserve (skb, hlen); + skb->protocol =htons (ETH_P_IP ); skb->priority =READ_ONCE (sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time;
Regards,
Tobias