BACKPORT: net: xfrm: support setting an output mark.
On systems that use mark-based routing it may be necessary for
routing lookups to use marks in order for packets to be routed
correctly. An example of such a system is Android, which uses
socket marks to route packets via different networks.
Currently, routing lookups in tunnel mode always use a mark of
zero, making routing incorrect on such systems.
This patch adds a new output_mark element to the xfrm state and
a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output
mark differs from the existing xfrm mark in two ways:
1. The xfrm mark is used to match xfrm policies and states, while
the xfrm output mark is used to set the mark (and influence
the routing) of the packets emitted by those states.
2. The existing mark is constrained to be a subset of the bits of
the originating socket or transformed packet, but the output
mark is arbitrary and depends only on the state.
The use of a separate mark provides additional flexibility. For
example:
- A packet subject to two transforms (e.g., transport mode inside
tunnel mode) can have two different output marks applied to it,
one for the transport mode SA and one for the tunnel mode SA.
- On a system where socket marks determine routing, the packets
emitted by an IPsec tunnel can be routed based on a mark that
is determined by the tunnel, not by the marks of the
unencrypted packets.
- Support for setting the output marks can be introduced without
breaking any existing setups that employ both mark-based
routing and xfrm tunnel mode. Simply changing the code to use
the xfrm mark for routing output packets could xfrm mark could
change behaviour in a way that breaks these setups.
If the output mark is unspecified or set to zero, the mark is not
set or changed.
[backport of upstream 077fbac405bfc6d41419ad6c1725804ad4e9887c]
Bug: 63589535
Test: https://android-review.googlesource.com/452776/ passes
Tested: make allyesconfig; make -j64
Tested: https://android-review.googlesource.com/452776
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Change-Id: I76120fba036e21780ced31ad390faf491ea81e52
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 835c30e..9b6e6a4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -155,6 +155,7 @@
int header_len;
int trailer_len;
u32 extra_flags;
+ u32 output_mark;
} props;
struct xfrm_lifetime_cfg lft;
@@ -284,10 +285,12 @@
struct dst_entry *(*dst_lookup)(struct net *net,
int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr);
+ const xfrm_address_t *daddr,
+ u32 mark);
int (*get_saddr)(struct net *net, int oif,
xfrm_address_t *saddr,
- xfrm_address_t *daddr);
+ xfrm_address_t *daddr,
+ u32 mark);
void (*decode_session)(struct sk_buff *skb,
struct flowi *fl,
int reverse);
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 1fc62b2..7d75e56 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -303,6 +303,8 @@
XFRMA_PROTO, /* __u8 */
XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
XFRMA_PAD,
+ XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */
+ XFRMA_OUTPUT_MARK, /* __u32 */
__XFRMA_MAX
#define XFRMA_MAX (__XFRMA_MAX - 1)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6a7ff69..7f9a8df 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -22,7 +22,8 @@
static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct rtable *rt;
@@ -30,6 +31,7 @@
fl4->daddr = daddr->a4;
fl4->flowi4_tos = tos;
fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
+ fl4->flowi4_mark = mark;
if (saddr)
fl4->saddr = saddr->a4;
@@ -44,20 +46,22 @@
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct flowi4 fl4;
- return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr);
+ return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark);
}
static int xfrm4_get_saddr(struct net *net, int oif,
- xfrm_address_t *saddr, xfrm_address_t *daddr)
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ u32 mark)
{
struct dst_entry *dst;
struct flowi4 fl4;
- dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr);
+ dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index e0f71c0..4003b28 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -29,7 +29,8 @@
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
- const xfrm_address_t *daddr)
+ const xfrm_address_t *daddr,
+ u32 mark)
{
struct flowi6 fl6;
struct dst_entry *dst;
@@ -38,6 +39,7 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+ fl6.flowi6_mark = mark;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
@@ -54,12 +56,13 @@
}
static int xfrm6_get_saddr(struct net *net, int oif,
- xfrm_address_t *saddr, xfrm_address_t *daddr)
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ u32 mark)
{
struct dst_entry *dst;
struct net_device *dev;
- dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr);
+ dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 637387b..d864a6d 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,6 +66,9 @@
goto error_nolock;
}
+ if (x->props.output_mark)
+ skb->mark = x->props.output_mark;
+
err = x->outer_mode->output(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8ce5711..77fbfbd 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -125,7 +125,7 @@
int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr,
- int family)
+ int family, u32 mark)
{
struct xfrm_policy_afinfo *afinfo;
struct dst_entry *dst;
@@ -134,7 +134,7 @@
if (unlikely(afinfo == NULL))
return ERR_PTR(-EAFNOSUPPORT);
- dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr);
+ dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark);
xfrm_policy_put_afinfo(afinfo);
@@ -145,7 +145,7 @@
int tos, int oif,
xfrm_address_t *prev_saddr,
xfrm_address_t *prev_daddr,
- int family)
+ int family, u32 mark)
{
struct net *net = xs_net(x);
xfrm_address_t *saddr = &x->props.saddr;
@@ -161,7 +161,7 @@
daddr = x->coaddr;
}
- dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family);
+ dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark);
if (!IS_ERR(dst)) {
if (prev_saddr != saddr)
@@ -1427,14 +1427,14 @@
static int
xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
- xfrm_address_t *remote, unsigned short family)
+ xfrm_address_t *remote, unsigned short family, u32 mark)
{
int err;
struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
if (unlikely(afinfo == NULL))
return -EINVAL;
- err = afinfo->get_saddr(net, oif, local, remote);
+ err = afinfo->get_saddr(net, oif, local, remote, mark);
xfrm_policy_put_afinfo(afinfo);
return err;
}
@@ -1465,7 +1465,7 @@
if (xfrm_addr_any(local, tmpl->encap_family)) {
error = xfrm_get_saddr(net, fl->flowi_oif,
&tmp, remote,
- tmpl->encap_family);
+ tmpl->encap_family, 0);
if (error)
goto fail;
local = &tmp;
@@ -1744,7 +1744,8 @@
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
- &saddr, &daddr, family);
+ &saddr, &daddr, family,
+ xfrm[i]->props.output_mark);
err = PTR_ERR(dst);
if (IS_ERR(dst))
goto put_states;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b2bba35..ed4f571 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -584,6 +584,9 @@
xfrm_mark_get(attrs, &x->mark);
+ if (attrs[XFRMA_OUTPUT_MARK])
+ x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]);
+
err = __xfrm_init_state(x, false);
if (err)
goto error;
@@ -871,6 +874,11 @@
goto out;
if (x->security)
ret = copy_sec_ctx(x->security, skb);
+ if (x->props.output_mark) {
+ ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark);
+ if (ret)
+ goto out;
+ }
out:
return ret;
}
@@ -2419,6 +2427,7 @@
[XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 },
[XFRMA_PROTO] = { .type = NLA_U8 },
[XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) },
+ [XFRMA_OUTPUT_MARK] = { .len = NLA_U32 },
};
static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2635,6 +2644,8 @@
l += nla_total_size(sizeof(*x->coaddr));
if (x->props.extra_flags)
l += nla_total_size(sizeof(x->props.extra_flags));
+ if (x->props.output_mark)
+ l += nla_total_size(sizeof(x->props.output_mark));
/* Must count x->lastused as it may become non-zero behind our back. */
l += nla_total_size_64bit(sizeof(u64));
