vxlan: Add an attribute to make VXLAN header validation configurable

The set of bits that the VXLAN netdevice currently considers reserved is
defined by the features enabled at the netdevice construction. In order to
make this configurable, add an attribute, IFLA_VXLAN_RESERVED_BITS. The
payload is a pair of big-endian u32's covering the VXLAN header. This is
validated against the set of flags used by the various enabled VXLAN
features, and attempts to override bits used by an enabled feature are
bounced.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/c657275e5ceed301e62c69fe8e559e32909442e2.1733412063.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index ff5684a2103a855c4ca03b3c83eb2f37d1e60728..43cf672b7b9fc64da442f6a7502845f4112a2f23 100644 (file)
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3428,6 +3428,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
        [IFLA_VXLAN_VNIFILTER]  = { .type = NLA_U8 },
        [IFLA_VXLAN_LOCALBYPASS]        = NLA_POLICY_MAX(NLA_U8, 1),
        [IFLA_VXLAN_LABEL_POLICY]       = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX),
+       [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)),
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -4315,13 +4316,44 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
                used_bits.vx_flags |= VXLAN_GPE_USED_BITS;
        }
 
-       /* For backwards compatibility, only allow reserved fields to be
-        * used by VXLAN extensions if explicitly requested.
-        */
-       conf->reserved_bits = (struct vxlanhdr) {
-               .vx_flags = ~used_bits.vx_flags,
-               .vx_vni = ~used_bits.vx_vni,
-       };
+       if (data[IFLA_VXLAN_RESERVED_BITS]) {
+               struct vxlanhdr reserved_bits;
+
+               if (changelink) {
+                       NL_SET_ERR_MSG_ATTR(extack,
+                                           data[IFLA_VXLAN_RESERVED_BITS],
+                                           "Cannot change reserved_bits");
+                       return -EOPNOTSUPP;
+               }
+
+               nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS],
+                          sizeof(reserved_bits));
+               if (used_bits.vx_flags & reserved_bits.vx_flags ||
+                   used_bits.vx_vni & reserved_bits.vx_vni) {
+                       __be64 ub_be64, rb_be64;
+
+                       memcpy(&ub_be64, &used_bits, sizeof(ub_be64));
+                       memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64));
+
+                       NL_SET_ERR_MSG_ATTR_FMT(extack,
+                                               data[IFLA_VXLAN_RESERVED_BITS],
+                                               "Used bits %#018llx cannot overlap reserved bits %#018llx",
+                                               be64_to_cpu(ub_be64),
+                                               be64_to_cpu(rb_be64));
+                       return -EINVAL;
+               }
+
+               conf->reserved_bits = reserved_bits;
+       } else {
+               /* For backwards compatibility, only allow reserved fields to be
+                * used by VXLAN extensions if explicitly requested.
+                */
+               conf->reserved_bits = (struct vxlanhdr) {
+                       .vx_flags = ~used_bits.vx_flags,
+                       .vx_vni = ~used_bits.vx_vni,
+               };
+       }
+
        if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) {
                err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL,
                                    VXLAN_F_REMCSUM_NOPARTIAL, changelink,
@@ -4506,6 +4538,8 @@ static size_t vxlan_get_size(const struct net_device *dev)
                nla_total_size(0) + /* IFLA_VXLAN_GPE */
                nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */
                nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */
+               /* IFLA_VXLAN_RESERVED_BITS */
+               nla_total_size(sizeof(struct vxlanhdr)) +
                0;
 }
 
@@ -4608,6 +4642,11 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
                       !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)))
                goto nla_put_failure;
 
+       if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS,
+                   sizeof(vxlan->cfg.reserved_bits),
+                   &vxlan->cfg.reserved_bits))
+               goto nla_put_failure;
+
        return 0;
 
 nla_put_failure:

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 2575e0cd9b482e78984ca6528dd7d4a24f03e290..77730c340c8f3191bfc810f39662315370fd43b1 100644 (file)
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1394,6 +1394,7 @@ enum {
        IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
        IFLA_VXLAN_LOCALBYPASS,
        IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
+       IFLA_VXLAN_RESERVED_BITS,
        __IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)