| Message ID | 1445818286-4870-4-git-send-email-thomasfherbert@gmail.com |
|---|---|
| State | Not Applicable |
| Headers | show |
On Sun, Oct 25, 2015 at 5:11 PM, Thomas F Herbert <thomasfherbert@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. Outer > TPID is also encoded in the flow key. > > Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com> This patch does not apply on current master due to conflicts related net-branch merge. > --- > net/openvswitch/actions.c | 6 +- > net/openvswitch/flow.c | 76 ++++++++++++---- > net/openvswitch/flow.h | 8 +- > net/openvswitch/flow_netlink.c | 199 +++++++++++++++++++++++++++++++++++++---- > net/openvswitch/vport-netdev.c | 4 +- > 5 files changed, 252 insertions(+), 41 deletions(-) > > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c > index c8db44a..ed19e2b 100644 > --- a/net/openvswitch/flow.c > +++ b/net/openvswitch/flow.c > @@ -302,24 +302,68 @@ static bool icmp6hdr_ok(struct sk_buff *skb) > sizeof(struct icmp6hdr)); > } > > -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) > +/* Parse vlan tag from vlan header. > + * Returns ERROR on memory error. > + * Returns 0 if it encounters a non-vlan or incomplete packet. > + * Returns 1 after successfully parsing vlan tag. > + */ > + > +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *vlan) > { > - struct qtag_prefix { > - __be16 eth_type; /* ETH_P_8021Q */ > - __be16 tci; > - }; > - struct qtag_prefix *qp; > + struct vlan_head *qp = (struct vlan_head *)skb->data; > + > + if (likely(!eth_type_vlan(qp->tpid))) > + return 0; > > - if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16))) > + if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16))) > return 0; Why do we need extra sizeof(__be16) bytes here? > > - if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) + > - sizeof(__be16)))) > + if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) + > + sizeof(__be16)))) > return -ENOMEM; > > - qp = (struct qtag_prefix *) skb->data; > - key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT); > - __skb_pull(skb, sizeof(struct qtag_prefix)); > + vlan->tci = qp->tci | htons(VLAN_TAG_PRESENT); > + vlan->tpid = qp->tpid; > + > + __skb_pull(skb, sizeof(struct vlan_head)); > + return 1; > +} > + ... > diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c > index c92d6a2..7e90f8c 100644 > --- a/net/openvswitch/flow_netlink.c > +++ b/net/openvswitch/flow_netlink.c ... > + > +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; > + u64 v_attrs = 0; > + > + if (!is_mask) { > + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, > + false, a, is_mask, log); > + if (err) > + return err; > + > + /* Another encap attribute here indicates > + * the presence of a double tagged vlan. > + */ > + encap = a[OVS_KEY_ATTR_ENCAP]; > + > + err = parse_flow_nlattrs(encap, a, &v_attrs, log); > + if (err) > + return err; > + > + if ((v_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && > + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { > + if (!((v_attrs & (1 << OVS_KEY_ATTR_VLAN)) && > + (v_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { > + OVS_NLERR(log, "Invalid Inner VLAN frame"); > + return -EINVAL; > + } > + *ie_valid = true; > + err = __parse_vlan_from_nlattrs(&encap, match, &v_attrs, > + true, a, is_mask, log); > + if (err) > + return err; > + *key_attrs |= v_attrs; > + } > + } else { > + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, > + false, a, is_mask, log); > + if (err) > + return err; > + > + encap = a[OVS_KEY_ATTR_ENCAP]; > + > + err = parse_flow_nlattrs(encap, a, &v_attrs, log); > + if (err) > + return err; > + > + if (v_attrs & 1 << OVS_KEY_ATTR_ENCAP) { Missing parentheses ... > @@ -1099,25 +1240,27 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, > > if ((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && > (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && > - (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) { > + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { > __be16 tci; > > - if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && > - (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { > + if (!((key_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) && > + (key_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) { This is not required change. > OVS_NLERR(log, "Invalid Vlan frame."); > return -EINVAL; > } > > - key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); > tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); > encap = a[OVS_KEY_ATTR_ENCAP]; > - key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); > encap_valid = true; > > if (tci & htons(VLAN_TAG_PRESENT)) { After checks in encode_vlan_from_nlattrs() function there is no need to have checks here. > - err = parse_flow_nlattrs(encap, a, &key_attrs, log); > + err = parse_vlan_from_nlattrs(&encap, match, > + &key_attrs, > + &i_encap_valid, a, false, > + log); > if (err) > return err; > + Added white space. > } else if (!tci) { > /* Corner case for truncated 802.1Q header. */ > if (nla_len(encap)) { > @@ -1169,7 +1312,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, > goto free_newmask; > > /* Always match on tci. */ > - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); > + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true); Also need to exact match on inner tci. > > if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) { > __be16 eth_type = 0; > @@ -1188,10 +1331,13 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, > if (eth_type == htons(0xffff)) { Same as above, after checks in encode_vlan_from_nlattrs() these checks looks redundant. > mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); > encap = a[OVS_KEY_ATTR_ENCAP]; > - err = parse_flow_mask_nlattrs(encap, a, > - &mask_attrs, log); > + err = parse_vlan_from_nlattrs(&nla_mask, match, > + &mask_attrs, > + &i_encap_valid, > + a, true, log); > if (err) > goto free_newmask; > + > } else { > OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).", > ntohs(eth_type)); ... > @@ -1368,17 +1515,29 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, > ether_addr_copy(eth_key->eth_src, output->eth.src); > ether_addr_copy(eth_key->eth_dst, output->eth.dst); > > - if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { > - __be16 eth_type; > - eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff); > - if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || > - nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci)) > + if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { > + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, > + output->eth.vlan.tpid) || > + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.vlan.tci)) > goto nla_put_failure; > encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); > - if (!swkey->eth.tci) > + if (!swkey->eth.vlan.tci) > goto unencap; > - } else > + if (swkey->eth.cvlan.tci) { > + /* Customer tci is nested but uses same key attribute. > + */ > + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, > + output->eth.cvlan.tpid) || > + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, > + output->eth.cvlan.tci)) > + goto nla_put_failure; > + in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); > + if (!swkey->eth.cvlan.tci) > + goto unencap; (!swkey->eth.cvlan.tci) is never going to be true. since inside if (swkey->eth.cvlan.tci) block.
On 10/26/15 10:10 PM, Pravin Shelar wrote: Thanks for the review. > On Sun, Oct 25, 2015 at 5:11 PM, Thomas F Herbert > <thomasfherbert@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. Outer >> TPID is also encoded in the flow key. >> >> Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com> > This patch does not apply on current master due to conflicts related > net-branch merge. OK, I will rebase. > >> --- >> net/openvswitch/actions.c | 6 +- >> net/openvswitch/flow.c | 76 ++++++++++++---- >> net/openvswitch/flow.h | 8 +- >> net/openvswitch/flow_netlink.c | 199 +++++++++++++++++++++++++++++++++++++---- >> net/openvswitch/vport-netdev.c | 4 +- >> 5 files changed, 252 insertions(+), 41 deletions(-) >> >> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c >> index c8db44a..ed19e2b 100644 >> --- a/net/openvswitch/flow.c >> +++ b/net/openvswitch/flow.c >> @@ -302,24 +302,68 @@ static bool icmp6hdr_ok(struct sk_buff *skb) >> sizeof(struct icmp6hdr)); >> } >> >> -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) >> +/* Parse vlan tag from vlan header. >> + * Returns ERROR on memory error. >> + * Returns 0 if it encounters a non-vlan or incomplete packet. >> + * Returns 1 after successfully parsing vlan tag. >> + */ >> + >> +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *vlan) >> { >> - struct qtag_prefix { >> - __be16 eth_type; /* ETH_P_8021Q */ >> - __be16 tci; >> - }; >> - struct qtag_prefix *qp; >> + struct vlan_head *qp = (struct vlan_head *)skb->data; >> + >> + if (likely(!eth_type_vlan(qp->tpid))) >> + return 0; >> >> - if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16))) >> + if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16))) >> return 0; > Why do we need extra sizeof(__be16) bytes here? I don't have an answer to your question. I didn't write this code and have wondered about why the extra two bytes were reserved. I don't know why it should be necessarily for inner or outer vlans or the HW accelerated case or for the non-accelerated case. If no reviewer can state a case for it, I will remove it with the next version of this patch. > >> - if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) + >> - sizeof(__be16)))) >> + if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) + >> + sizeof(__be16)))) >> return -ENOMEM; >> >> - qp = (struct qtag_prefix *) skb->data; >> - key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT); >> - __skb_pull(skb, sizeof(struct qtag_prefix)); >> + vlan->tci = qp->tci | htons(VLAN_TAG_PRESENT); >> + vlan->tpid = qp->tpid; >> + >> + __skb_pull(skb, sizeof(struct vlan_head)); >> + return 1; >> +} >> + > ... > >> diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c >> index c92d6a2..7e90f8c 100644 >> --- a/net/openvswitch/flow_netlink.c >> +++ b/net/openvswitch/flow_netlink.c > ... > >> + >> +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; >> + u64 v_attrs = 0; >> + >> + if (!is_mask) { >> + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, >> + false, a, is_mask, log); >> + if (err) >> + return err; >> + >> + /* Another encap attribute here indicates >> + * the presence of a double tagged vlan. >> + */ >> + encap = a[OVS_KEY_ATTR_ENCAP]; >> + >> + err = parse_flow_nlattrs(encap, a, &v_attrs, log); >> + if (err) >> + return err; >> + >> + if ((v_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && >> + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { >> + if (!((v_attrs & (1 << OVS_KEY_ATTR_VLAN)) && >> + (v_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { >> + OVS_NLERR(log, "Invalid Inner VLAN frame"); >> + return -EINVAL; >> + } >> + *ie_valid = true; >> + err = __parse_vlan_from_nlattrs(&encap, match, &v_attrs, >> + true, a, is_mask, log); >> + if (err) >> + return err; >> + *key_attrs |= v_attrs; >> + } >> + } else { >> + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, >> + false, a, is_mask, log); >> + if (err) >> + return err; >> + >> + encap = a[OVS_KEY_ATTR_ENCAP]; >> + >> + err = parse_flow_nlattrs(encap, a, &v_attrs, log); >> + if (err) >> + return err; >> + >> + if (v_attrs & 1 << OVS_KEY_ATTR_ENCAP) { > Missing parentheses Yes, thanks for spotting this. > > ... >> @@ -1099,25 +1240,27 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, >> >> if ((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && >> (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && >> - (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) { >> + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { >> __be16 tci; >> >> - if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && >> - (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { >> + if (!((key_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) && >> + (key_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) { > This is not required change. Yes, we already agreed that forcing to a 64 bit constant was not necessary and should be removed for consistency. Sorry but it crept back into this version via cut and paste when refactoring. Thanks for spotting this and I will fix. > >> OVS_NLERR(log, "Invalid Vlan frame."); >> return -EINVAL; >> } >> >> - key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); >> tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); >> encap = a[OVS_KEY_ATTR_ENCAP]; >> - key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); >> encap_valid = true; >> >> if (tci & htons(VLAN_TAG_PRESENT)) { > After checks in encode_vlan_from_nlattrs() function there is no need > to have checks here. Yes, some of this code is redundant and should be removed. > >> - err = parse_flow_nlattrs(encap, a, &key_attrs, log); >> + err = parse_vlan_from_nlattrs(&encap, match, >> + &key_attrs, >> + &i_encap_valid, a, false, >> + log); >> if (err) >> return err; >> + > Added white space. Fixed in next version. >> } else if (!tci) { >> /* Corner case for truncated 802.1Q header. */ >> if (nla_len(encap)) { >> @@ -1169,7 +1312,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, >> goto free_newmask; >> >> /* Always match on tci. */ >> - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); >> + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true); > Also need to exact match on inner tci. This code sets a match on tci even if no vlan is present. Is this is for the case where there is no explicit mask specified in the netlink encoded flow? If that is correct, then it does need to be done for the inner vlan too. > >> if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) { >> __be16 eth_type = 0; >> @@ -1188,10 +1331,13 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, >> if (eth_type == htons(0xffff)) { > Same as above, after checks in encode_vlan_from_nlattrs() these checks > looks redundant. I agree. This patch makes this the extra check redundant with new code in encode_vlan_from_nlattrs() and can be removed. > >> mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); >> encap = a[OVS_KEY_ATTR_ENCAP]; >> - err = parse_flow_mask_nlattrs(encap, a, >> - &mask_attrs, log); >> + err = parse_vlan_from_nlattrs(&nla_mask, match, >> + &mask_attrs, >> + &i_encap_valid, >> + a, true, log); >> if (err) >> goto free_newmask; >> + >> } else { >> OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).", >> ntohs(eth_type)); > ... >> @@ -1368,17 +1515,29 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, >> ether_addr_copy(eth_key->eth_src, output->eth.src); >> ether_addr_copy(eth_key->eth_dst, output->eth.dst); >> >> - if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { >> - __be16 eth_type; >> - eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff); >> - if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || >> - nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci)) >> + if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { >> + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, >> + output->eth.vlan.tpid) || >> + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.vlan.tci)) >> goto nla_put_failure; >> encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); >> - if (!swkey->eth.tci) >> + if (!swkey->eth.vlan.tci) >> goto unencap; >> - } else >> + if (swkey->eth.cvlan.tci) { >> + /* Customer tci is nested but uses same key attribute. >> + */ >> + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, >> + output->eth.cvlan.tpid) || >> + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, >> + output->eth.cvlan.tci)) >> + goto nla_put_failure; >> + in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); >> + if (!swkey->eth.cvlan.tci) >> + goto unencap; > (!swkey->eth.cvlan.tci) is never going to be true. since inside if > (swkey->eth.cvlan.tci) block. Yes, it will be removed.
On Tue, Oct 27, 2015 at 9:45 AM, Thomas F Herbert <thomasfherbert@gmail.com> wrote: > On 10/26/15 10:10 PM, Pravin Shelar wrote: > Thanks for the review. >> >> On Sun, Oct 25, 2015 at 5:11 PM, Thomas F Herbert >> <thomasfherbert@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. >>> Outer >>> TPID is also encoded in the flow key. >>> >>> Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com> >> >> This patch does not apply on current master due to conflicts related >> net-branch merge. > > OK, I will rebase. > >> >>> --- >>> net/openvswitch/actions.c | 6 +- >>> net/openvswitch/flow.c | 76 ++++++++++++---- >>> net/openvswitch/flow.h | 8 +- >>> net/openvswitch/flow_netlink.c | 199 >>> +++++++++++++++++++++++++++++++++++++---- >>> net/openvswitch/vport-netdev.c | 4 +- >>> 5 files changed, 252 insertions(+), 41 deletions(-) >>> >>> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c >>> index c8db44a..ed19e2b 100644 >>> --- a/net/openvswitch/flow.c >>> +++ b/net/openvswitch/flow.c >>> @@ -302,24 +302,68 @@ static bool icmp6hdr_ok(struct sk_buff *skb) >>> sizeof(struct icmp6hdr)); >>> } >>> >>> -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) >>> +/* Parse vlan tag from vlan header. >>> + * Returns ERROR on memory error. >>> + * Returns 0 if it encounters a non-vlan or incomplete packet. >>> + * Returns 1 after successfully parsing vlan tag. >>> + */ >>> + >>> +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *vlan) >>> { >>> - struct qtag_prefix { >>> - __be16 eth_type; /* ETH_P_8021Q */ >>> - __be16 tci; >>> - }; >>> - struct qtag_prefix *qp; >>> + struct vlan_head *qp = (struct vlan_head *)skb->data; >>> + >>> + if (likely(!eth_type_vlan(qp->tpid))) >>> + return 0; >>> >>> - if (unlikely(skb->len < sizeof(struct qtag_prefix) + >>> sizeof(__be16))) >>> + if (unlikely(skb->len < sizeof(struct vlan_head) + >>> sizeof(__be16))) >>> return 0; >> >> Why do we need extra sizeof(__be16) bytes here? > > I don't have an answer to your question. I didn't write this code and have > wondered about why the extra two bytes were reserved. I don't know why it > should be necessarily for inner or outer vlans or the HW accelerated case or > for the non-accelerated case. If no reviewer can state a case for it, I will > remove it with the next version of this patch. > Looks like it is optimization for parsing ethertype, So lets keep it. >>> >>> } else if (!tci) { >>> /* Corner case for truncated 802.1Q header. */ >>> if (nla_len(encap)) { >>> @@ -1169,7 +1312,7 @@ int ovs_nla_get_match(struct net *net, struct >>> sw_flow_match *match, >>> goto free_newmask; >>> >>> /* Always match on tci. */ >>> - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); >>> + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), >>> true); >> >> Also need to exact match on inner tci. > > This code sets a match on tci even if no vlan is present. Is this is for the > case where there is no explicit mask specified in the netlink encoded flow? > If that is correct, then it does need to be done for the inner vlan too. Yes, By default it needs to be matched. userspace can overwrite it with different wildcard.
Pravin, please look at comment inline below: On 10/27/15 1:22 PM, Pravin Shelar wrote: > On Tue, Oct 27, 2015 at 9:45 AM, Thomas F Herbert > <thomasfherbert@gmail.com> wrote: >> On 10/26/15 10:10 PM, Pravin Shelar wrote: >> Thanks for the review. >>> On Sun, Oct 25, 2015 at 5:11 PM, Thomas F Herbert >>> <thomasfherbert@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. >>>> Outer >>>> TPID is also encoded in the flow key. >>>> >>>> Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com> >>> This patch does not apply on current master due to conflicts related >>> net-branch merge. >> OK, I will rebase. Pravin, I implemented all reviewer comments and completing rebasing to latest net-next upstream. The patch works well and flows install properly. However, there may be one remaining issue. The vport-dev transmit function now calls dev_queue_transmit() directly because it is registered as the vport send op. The affect of this is that the vlan mtu adjustment code in ovs_netdev_send() that was patched for mtu adjustment for single and double tagged vlans is gone.Could you please verify that the size adjustment is no longer needed. >> >>>> --- >>>> net/openvswitch/actions.c | 6 +- >>>> net/openvswitch/flow.c | 76 ++++++++++++---- >>>> net/openvswitch/flow.h | 8 +- >>>> net/openvswitch/flow_netlink.c | 199 >>>> +++++++++++++++++++++++++++++++++++++---- >>>> net/openvswitch/vport-netdev.c | 4 +- >>>> 5 files changed, 252 insertions(+), 41 deletions(-) >>>> >>>> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c >>>> index c8db44a..ed19e2b 100644 >>>> --- a/net/openvswitch/flow.c >>>> +++ b/net/openvswitch/flow.c >>>> @@ -302,24 +302,68 @@ static bool icmp6hdr_ok(struct sk_buff *skb) >>>> sizeof(struct icmp6hdr)); >>>> } >>>> >>>> -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) >>>> +/* Parse vlan tag from vlan header. >>>> + * Returns ERROR on memory error. >>>> + * Returns 0 if it encounters a non-vlan or incomplete packet. >>>> + * Returns 1 after successfully parsing vlan tag. >>>> + */ >>>> + >>>> +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *vlan) >>>> { >>>> - struct qtag_prefix { >>>> - __be16 eth_type; /* ETH_P_8021Q */ >>>> - __be16 tci; >>>> - }; >>>> - struct qtag_prefix *qp; >>>> + struct vlan_head *qp = (struct vlan_head *)skb->data; >>>> + >>>> + if (likely(!eth_type_vlan(qp->tpid))) >>>> + return 0; >>>> >>>> - if (unlikely(skb->len < sizeof(struct qtag_prefix) + >>>> sizeof(__be16))) >>>> + if (unlikely(skb->len < sizeof(struct vlan_head) + >>>> sizeof(__be16))) >>>> return 0; >>> Why do we need extra sizeof(__be16) bytes here? >> I don't have an answer to your question. I didn't write this code and have >> wondered about why the extra two bytes were reserved. I don't know why it >> should be necessarily for inner or outer vlans or the HW accelerated case or >> for the non-accelerated case. If no reviewer can state a case for it, I will >> remove it with the next version of this patch. >> > Looks like it is optimization for parsing ethertype, So lets keep it. > >>>> } else if (!tci) { >>>> /* Corner case for truncated 802.1Q header. */ >>>> if (nla_len(encap)) { >>>> @@ -1169,7 +1312,7 @@ int ovs_nla_get_match(struct net *net, struct >>>> sw_flow_match *match, >>>> goto free_newmask; >>>> >>>> /* Always match on tci. */ >>>> - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); >>>> + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), >>>> true); >>> Also need to exact match on inner tci. >> This code sets a match on tci even if no vlan is present. Is this is for the >> case where there is no explicit mask specified in the netlink encoded flow? >> If that is correct, then it does need to be done for the inner vlan too. > Yes, By default it needs to be matched. userspace can overwrite it > with different wildcard.
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 315f533..09cc1c9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -236,7 +236,8 @@ 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; + key->eth.vlan.tpid = 0; return err; } @@ -246,7 +247,8 @@ 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; + key->eth.vlan.tpid = vlan->vlan_tpid; 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..ed19e2b 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -302,24 +302,68 @@ static bool icmp6hdr_ok(struct sk_buff *skb) sizeof(struct icmp6hdr)); } -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) +/* Parse vlan tag from vlan header. + * Returns ERROR on memory error. + * Returns 0 if it encounters a non-vlan or incomplete packet. + * Returns 1 after successfully parsing vlan tag. + */ + +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *vlan) { - struct qtag_prefix { - __be16 eth_type; /* ETH_P_8021Q */ - __be16 tci; - }; - struct qtag_prefix *qp; + struct vlan_head *qp = (struct vlan_head *)skb->data; + + if (likely(!eth_type_vlan(qp->tpid))) + return 0; - if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16))) + if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16))) return 0; - if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) + - sizeof(__be16)))) + if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) + + sizeof(__be16)))) return -ENOMEM; - qp = (struct qtag_prefix *) skb->data; - key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT); - __skb_pull(skb, sizeof(struct qtag_prefix)); + vlan->tci = qp->tci | htons(VLAN_TAG_PRESENT); + vlan->tpid = qp->tpid; + + __skb_pull(skb, sizeof(struct vlan_head)); + return 1; +} + +static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) +{ + int res; + + key->eth.vlan.tci = 0; + key->eth.vlan.tpid = 0; + key->eth.cvlan.tci = 0; + key->eth.cvlan.tpid = 0; + + if (likely(skb_vlan_tag_present(skb))) { + key->eth.vlan.tci = htons(skb->vlan_tci); + key->eth.vlan.tpid = skb->vlan_proto; + + /* Case where ingress processing has already stripped + * the outer vlan tag. + */ + res = parse_vlan_tag(skb, &key->eth.cvlan); + if (res < 0) + return res; + /* For inner tag, return 0 because neither + * non-existent nor partial inner tag is an error. + */ + return 0; + } + res = parse_vlan_tag(skb, &key->eth.vlan); + if (res <= 0) + /* This is an outer tag in the non-accelerated VLAN + * case. Return error unless it is a complete vlan tag. + */ + return res; + + /* Parse inner vlan tag if present for non-accelerated case. */ + res = parse_vlan_tag(skb, &key->eth.cvlan); + if (res <= 0) + return res; return 0; } @@ -480,12 +524,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) * update skb->csum here. */ - key->eth.tci = 0; - if (skb_vlan_tag_present(skb)) - key->eth.tci = htons(skb->vlan_tci); - else if (eth->h_proto == htons(ETH_P_8021Q)) - if (unlikely(parse_vlan(skb, key))) - return -ENOMEM; + if (unlikely(parse_vlan(skb, key))) + return -ENOMEM; key->eth.type = parse_ethertype(skb); if (unlikely(key->eth.type == htons(0))) diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fe527d2..7ea8deb 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -50,6 +50,11 @@ struct ovs_tunnel_info { struct metadata_dst *tun_dst; }; +struct vlan_head { + __be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/ + __be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */ +}; + #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ FIELD_SIZEOF(struct sw_flow_key, recirc_id)) @@ -68,7 +73,8 @@ struct sw_flow_key { struct { u8 src[ETH_ALEN]; /* Ethernet source address. */ u8 dst[ETH_ALEN]; /* Ethernet destination address. */ - __be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */ + struct vlan_head vlan; + struct vlan_head cvlan; __be16 type; /* Ethernet frame type. */ } eth; union { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c92d6a2..7e90f8c 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -845,7 +845,7 @@ 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 +1064,146 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val) nlattr_set(attr, val, ovs_key_lens); } +static int encode_vlan_from_nlattrs(struct sw_flow_match *match, + const struct nlattr *a[], + bool is_mask, bool inner, bool log) +{ + __be16 tci = 0; + __be16 tpid = 0; + + if (a[OVS_KEY_ATTR_VLAN]) + tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); + + if (a[OVS_KEY_ATTR_ETHERTYPE]) + tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); + + if (is_mask && tpid != htons(0xffff)) { + if (likely(!inner)) + OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).", + ntohs(tpid)); + else + OVS_NLERR(log, "VLAN frames must have an exact match on the CTPID (mask=%x).", + ntohs(tpid)); + return -EINVAL; + } + if (!(tci & htons(VLAN_TAG_PRESENT))) { + if (is_mask) + if (likely(!inner)) + OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit."); + else + OVS_NLERR(log, "VLAN CTCI mask does not have exact match for VLAN_TAG_PRESENT bit."); + else + if (likely(!inner)) + OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set."); + else + OVS_NLERR(log, "VLAN CTCI does not have VLAN_TAG_PRESENT bit set."); + return -EINVAL; + } + if (likely(!inner)) { + SW_FLOW_KEY_PUT(match, eth.vlan.tpid, tpid, is_mask); + SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask); + } else { + SW_FLOW_KEY_PUT(match, eth.cvlan.tpid, tpid, is_mask); + SW_FLOW_KEY_PUT(match, eth.cvlan.tci, tci, is_mask); + } + return 0; +} + +static int __parse_vlan_from_nlattrs(const struct nlattr **nla, + struct sw_flow_match *match, + u64 *key_attrs, bool inner, + const struct nlattr **a, bool is_mask, + bool log) +{ + int err; + u64 v_attrs = *key_attrs; + + err = encode_vlan_from_nlattrs(match, a, is_mask, inner, log); + if (err) + return err; + + v_attrs &= ~(1 << OVS_KEY_ATTR_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; + + return 0; +} + +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; + u64 v_attrs = 0; + + if (!is_mask) { + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, + false, a, is_mask, log); + if (err) + return err; + + /* Another encap attribute here indicates + * the presence of a double tagged vlan. + */ + encap = a[OVS_KEY_ATTR_ENCAP]; + + err = parse_flow_nlattrs(encap, a, &v_attrs, log); + if (err) + return err; + + if ((v_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { + if (!((v_attrs & (1 << OVS_KEY_ATTR_VLAN)) && + (v_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { + OVS_NLERR(log, "Invalid Inner VLAN frame"); + return -EINVAL; + } + *ie_valid = true; + err = __parse_vlan_from_nlattrs(&encap, match, &v_attrs, + true, a, is_mask, log); + if (err) + return err; + *key_attrs |= v_attrs; + } + } else { + err = __parse_vlan_from_nlattrs(nla, match, key_attrs, + false, a, is_mask, log); + if (err) + return err; + + encap = a[OVS_KEY_ATTR_ENCAP]; + + err = parse_flow_nlattrs(encap, a, &v_attrs, log); + if (err) + return err; + + if (v_attrs & 1 << OVS_KEY_ATTR_ENCAP) { + if (!*ie_valid) { + OVS_NLERR(log, "Encap mask attribute is set for non-CVLAN frame."); + return -EINVAL; + } + err = __parse_vlan_from_nlattrs(nla, match, + &v_attrs, true, a, + is_mask, + log); + if (err) + return err; + *key_attrs |= v_attrs; + } + } + return 0; +} + /** * ovs_nla_get_match - parses Netlink attributes into a flow key and * mask. In case the 'mask' is NULL, the flow is treated as exact match @@ -1091,6 +1231,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, u64 key_attrs = 0; u64 mask_attrs = 0; bool encap_valid = false; + bool i_encap_valid = false; int err; err = parse_flow_nlattrs(nla_key, a, &key_attrs, log); @@ -1099,25 +1240,27 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, if ((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && - (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) { + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]))) { __be16 tci; - if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && - (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { + if (!((key_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) && + (key_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) { OVS_NLERR(log, "Invalid Vlan frame."); return -EINVAL; } - key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); encap = a[OVS_KEY_ATTR_ENCAP]; - key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); encap_valid = true; if (tci & htons(VLAN_TAG_PRESENT)) { - err = parse_flow_nlattrs(encap, a, &key_attrs, log); + err = parse_vlan_from_nlattrs(&encap, match, + &key_attrs, + &i_encap_valid, a, false, + log); if (err) return err; + } else if (!tci) { /* Corner case for truncated 802.1Q header. */ if (nla_len(encap)) { @@ -1169,7 +1312,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, goto free_newmask; /* Always match on tci. */ - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true); if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) { __be16 eth_type = 0; @@ -1188,10 +1331,13 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, if (eth_type == htons(0xffff)) { mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); encap = a[OVS_KEY_ATTR_ENCAP]; - err = parse_flow_mask_nlattrs(encap, a, - &mask_attrs, log); + err = parse_vlan_from_nlattrs(&nla_mask, match, + &mask_attrs, + &i_encap_valid, + a, true, log); if (err) goto free_newmask; + } else { OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).", ntohs(eth_type)); @@ -1320,6 +1466,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, { struct ovs_key_ethernet *eth_key; struct nlattr *nla, *encap; + struct nlattr *in_encap = NULL; if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id)) goto nla_put_failure; @@ -1368,17 +1515,29 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ether_addr_copy(eth_key->eth_src, output->eth.src); ether_addr_copy(eth_key->eth_dst, output->eth.dst); - if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { - __be16 eth_type; - eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff); - if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || - nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci)) + if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, + output->eth.vlan.tpid) || + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.vlan.tci)) goto nla_put_failure; encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); - if (!swkey->eth.tci) + if (!swkey->eth.vlan.tci) goto unencap; - } else + if (swkey->eth.cvlan.tci) { + /* Customer tci is nested but uses same key attribute. + */ + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, + output->eth.cvlan.tpid) || + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, + output->eth.cvlan.tci)) + goto nla_put_failure; + in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); + if (!swkey->eth.cvlan.tci) + goto unencap; + } + } else { encap = NULL; + } if (swkey->eth.type == htons(ETH_P_802_2)) { /* @@ -1523,6 +1682,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, } unencap: + if (in_encap) + nla_nest_end(skb, in_encap); if (encap) nla_nest_end(skb, encap); @@ -2174,7 +2335,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_PUSH_VLAN: vlan = nla_data(a); - if (vlan->vlan_tpid != htons(ETH_P_8021Q)) + if (!eth_type_vlan(vlan->vlan_tpid)) return -EINVAL; if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT))) return -EINVAL; @@ -2279,7 +2440,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type, - key->eth.tci, log); + key->eth.vlan.tci, log); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index f7e8dcc..d2581b7 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -194,7 +194,9 @@ static unsigned int packet_length(const struct sk_buff *skb) { unsigned int length = skb->len - ETH_HLEN; - if (skb->protocol == htons(ETH_P_8021Q)) + if (eth_type_vlan(skb->protocol)) + length -= VLAN_HLEN; + if (skb->protocol == htons(ETH_P_8021AD)) length -= VLAN_HLEN; return length;
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. Outer TPID is also encoded in the flow key. Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com> --- net/openvswitch/actions.c | 6 +- net/openvswitch/flow.c | 76 ++++++++++++---- net/openvswitch/flow.h | 8 +- net/openvswitch/flow_netlink.c | 199 +++++++++++++++++++++++++++++++++++++---- net/openvswitch/vport-netdev.c | 4 +- 5 files changed, 252 insertions(+), 41 deletions(-)