On Wed, Sep 30, 2015 at 8:33 PM, Thomas F Herbert
<thomasfherb...@gmail.com> wrote:
> Add support for 802.1ad including the ability to push and pop double
> tagged vlans. Add support for 802.1ad to netlink parsing and flow
> conversion. Uses double nested encap attributes to represent double
> tagged vlan. Inner TPID encoded along with ctci in nested attributes.
>
> Signed-off-by: Thomas F Herbert <thomasfherb...@gmail.com>
> ---
> net/openvswitch/actions.c | 4 +-
> net/openvswitch/flow.c | 87 +++++++++++++++++----
> net/openvswitch/flow.h | 11 ++-
> net/openvswitch/flow_netlink.c | 167
> +++++++++++++++++++++++++++++++++++++----
> net/openvswitch/vport-netdev.c | 4 +-
> 5 files changed, 239 insertions(+), 34 deletions(-)
>
> diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
> index 315f533..c544371 100644
> --- a/net/openvswitch/actions.c
> +++ b/net/openvswitch/actions.c
> @@ -236,7 +236,7 @@ static int pop_vlan(struct sk_buff *skb, struct
> sw_flow_key *key)
> if (skb_vlan_tag_present(skb))
> invalidate_flow_key(key);
> else
> - key->eth.tci = 0;
> + key->eth.vlan.tci = 0;
Since new tpid field is introduced, it needs to be updated here.
> return err;
> }
>
> @@ -246,7 +246,7 @@ static int push_vlan(struct sk_buff *skb, struct
> sw_flow_key *key,
> if (skb_vlan_tag_present(skb))
> invalidate_flow_key(key);
> else
> - key->eth.tci = vlan->vlan_tci;
> + key->eth.vlan.tci = vlan->vlan_tci;
Same as above, tpid needs to be updated here.
> return skb_vlan_push(skb, vlan->vlan_tpid,
> ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
> }
> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> index c8db44a..86a2cb0 100644
> --- a/net/openvswitch/flow.c
> +++ b/net/openvswitch/flow.c
> @@ -305,21 +305,78 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
> static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
> {
> struct qtag_prefix {
> - __be16 eth_type; /* ETH_P_8021Q */
> + __be16 eth_type; /* ETH_P_8021Q or ETH_P_8021AD */
> __be16 tci;
> };
> - struct qtag_prefix *qp;
> + struct qtag_prefix *qp = (struct qtag_prefix *)skb->data;
>
> - if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16)))
> + struct qinqtag_prefix {
> + __be16 eth_type; /* ETH_P_8021Q or ETH_P_8021AD */
> + __be16 tci;
> + __be16 inner_tpid; /* ETH_P_8021Q */
> + __be16 ctci;
> + };
> +
> + if (likely(skb_vlan_tag_present(skb))) {
> + key->eth.vlan.tci = htons(skb->vlan_tci);
> + key->eth.vlan.tpid = skb->vlan_proto;
> +
> + /* Case where upstream
> + * processing has already stripped the outer vlan tag.
> + */
> + if (unlikely(skb->vlan_proto == htons(ETH_P_8021AD))) {
> + if (unlikely(skb->len < sizeof(struct qtag_prefix) +
> + sizeof(__be16))) {
> + key->eth.vlan.tci = 0;
> + return 0;
> + }
> +
> + if (unlikely(!pskb_may_pull(skb,
> + sizeof(struct
> qtag_prefix) +
> + sizeof(__be16))))
> + return -ENOMEM;
> +
Comment regarding qp pointer is ignored from previous review. Most of
comment in this function from earlier review still apply.
> + key->eth.cvlan.tci =
> + qp->tci | htons(VLAN_TAG_PRESENT);
> + key->eth.cvlan.tpid = qp->eth_type;
> +
> + __skb_pull(skb, sizeof(struct qtag_prefix));
> + }
> return 0;
>
> - if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
> - sizeof(__be16))))
> - return -ENOMEM;
> + } else if (qp->eth_type == htons(ETH_P_8021AD)) {
> + struct qinqtag_prefix *qinqp =
> + (struct qinqtag_prefix *)skb->data;
> +
This code can be further simplified by just defining struct
qtag_prefix. and parsing it twice in this case.
> + if (unlikely(skb->len < sizeof(struct qinqtag_prefix) +
> + sizeof(__be16)))
> + return 0;
> +
> + if (unlikely(!pskb_may_pull(skb, sizeof(struct
> qinqtag_prefix) +
> + sizeof(__be16))))
> + return -ENOMEM;
> + key->eth.vlan.tci = qinqp->tci | htons(VLAN_TAG_PRESENT);
> + key->eth.vlan.tpid = qp->eth_type;
> + key->eth.cvlan.tci = qinqp->ctci | htons(VLAN_TAG_PRESENT);
> + key->eth.cvlan.tpid = qinqp->inner_tpid;
> +
> + __skb_pull(skb, sizeof(struct qinqtag_prefix));
>
> - qp = (struct qtag_prefix *) skb->data;
> - key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT);
> - __skb_pull(skb, sizeof(struct qtag_prefix));
> + return 0;
> +
> + } else if (qp->eth_type == htons(ETH_P_8021Q)) {
> + if (unlikely(skb->len < sizeof(struct qtag_prefix) +
> + sizeof(__be16)))
> + return 0;
> +
> + if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
> + sizeof(__be16))))
> + return -ENOMEM;
> + key->eth.vlan.tci = qp->tci | htons(VLAN_TAG_PRESENT);
> + key->eth.vlan.tpid = qp->eth_type;
> +
> + __skb_pull(skb, sizeof(struct qtag_prefix));
> + }
>
> return 0;
> }
...
> diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
> index c92d6a2..08f56ab 100644
> --- a/net/openvswitch/flow_netlink.c
> +++ b/net/openvswitch/flow_netlink.c
> @@ -811,6 +811,27 @@ static int metadata_from_nlattrs(struct net *net, struct
> sw_flow_match *match,
> return 0;
> }
>
...
> static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
> u64 attrs, const struct nlattr **a,
> bool is_mask, bool log)
> @@ -845,7 +866,7 @@ static int ovs_key_from_nlattrs(struct net *net, struct
> sw_flow_match *match,
> return -EINVAL;
> }
>
> - SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
> + SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask);
> attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
> }
>
> @@ -1064,6 +1085,93 @@ static void mask_set_nlattr(struct nlattr *attr, u8
> val)
> nlattr_set(attr, val, ovs_key_lens);
> }
>
> +static int parse_vlan_from_nlattrs(const struct nlattr **nla,
> + struct sw_flow_match *match,
> + u64 *key_attrs, bool *ie_valid,
> + const struct nlattr **a, bool is_mask,
> + bool log)
> +{
> + int err;
> + const struct nlattr *encap;
> +
> + if (!is_mask) {
> + u64 v_attrs = 0;
> +
> + err = parse_flow_nlattrs(*nla, a, &v_attrs, log);
> + if (err)
> + return err;
> + /* Another encap attribute here indicates
> + * the presence of a double tagged vlan.
> + */
> + if ((v_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) &&
> + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) {
> + if (!((v_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) &&
> + (v_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) {
> + OVS_NLERR(log, "Invalid Inner VLAN frame");
> + return -EINVAL;
> + }
> + SW_FLOW_KEY_PUT(match, eth.vlan.tpid,
> +
> nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]),
> + is_mask);
eth.vlan.tpid is only set in case of double nested vlan case.
> + encap = a[OVS_KEY_ATTR_ENCAP];
> + v_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
> +
This bit masking can be grouped with the following operation.
> + err = cust_vlan_from_nlattrs(match, a, is_mask, log);
> + if (err)
> + return err;
> + *ie_valid = true;
> + *nla = encap;
> +
> + /* Insure that tci key attribute isn't
> + * overwritten by encapsulated customer tci.
> + * Ethertype is cleared because it is c_tpid.
> + */
> + v_attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
> + v_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
> + }
> + *key_attrs |= v_attrs;
> +
> + if (*ie_valid) {
> + err = parse_flow_nlattrs(*nla, a, key_attrs, log);
> + if (err)
> + return err;
> + }
Why is the parsing is not done inside the nested block?
> +
> + } else {
> + u64 mask_v_attrs = 0;
> +
> + err = parse_flow_mask_nlattrs(*nla, a, &mask_v_attrs, log);
> + if (err)
> + return err;
> +
> + if (mask_v_attrs & 1 << OVS_KEY_ATTR_ENCAP) {
> + if (!*ie_valid) {
> + OVS_NLERR(log, "Encap mask attribute is set
> for non-CVLAN frame.");
> + err = -EINVAL;
> + return err;
> + }
Double nested eth-type mask should be 0xffff. Same as single nested
eth-type check
> + encap = a[OVS_KEY_ATTR_ENCAP];
> + mask_v_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
> +
> + err = cust_vlan_from_nlattrs(match, a, is_mask, log);
> + if (err)
> + return err;
> + *nla = encap;
> +
> + mask_v_attrs &= ~(1ULL << OVS_KEY_ATTR_VLAN);
> + mask_v_attrs &= ~(1ULL << OVS_KEY_ATTR_ETHERTYPE);
> + }
> +
> + *key_attrs |= mask_v_attrs;
> + if (*ie_valid) {
> + err = parse_flow_mask_nlattrs(*nla, a, key_attrs,
> log);
Same as above. I think the parsing can be done inside the nested block.
> + if (err)
> + return err;
> + }
> + }
> + return 0;
> +}
> +
...
> @@ -1525,6 +1660,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key
> *swkey,
> unencap:
> if (encap)
> nla_nest_end(skb, encap);
> + if (in_encap)
> + nla_nest_end(skb, in_encap);
>
Inner nested encap should end first.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
