| Message ID | 1427739356-28113-5-git-send-email-rshearma@brocade.com |
|---|---|
| State | Deferred, archived |
| Delegated to: | David Miller |
| Headers | show |
Robert Shearman <rshearma@brocade.com> writes: > RFC 4182 s2 states that if an IPv4 Explicit NULL label is the only > label on the stack, then after popping the resulting packet must be > treated as a IPv4 packet and forwarded based on the IPv4 header. The > same is true for IPv6 Explicit NULL with an IPv6 packet following. > > Therefore, when installing the IPv4/IPv6 Explicit NULL label routes, > add an attribute that specifies the expected payload type for use at > forwarding time for determining the type of the encapsulated packet > instead of inspecting the first nibble of the packet. This looks pretty reasonable. I suspect the multiple returns instead of using a single variable might generate slightly worse machine but whatever. Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> > Cc: "Eric W. Biederman" <ebiederm@xmission.com> > Signed-off-by: Robert Shearman <rshearma@brocade.com> > --- > net/mpls/af_mpls.c | 72 ++++++++++++++++++++++++++++++++---------------------- > 1 file changed, 43 insertions(+), 29 deletions(-) > > diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c > index 0b0420bf110d..e9ce5799449d 100644 > --- a/net/mpls/af_mpls.c > +++ b/net/mpls/af_mpls.c > @@ -23,13 +23,25 @@ > /* This maximum ha length copied from the definition of struct neighbour */ > #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) > > +enum mpls_payload_type { > + MPT_UNSPEC, /* IPv4 or IPv6 */ > + MPT_IPV4 = 4, > + MPT_IPV6 = 6, > + > + /* Other types not implemented: > + * - Pseudo-wire with or without control word (RFC4385) > + * - GAL (RFC5586) > + */ > +}; > + > struct mpls_route { /* next hop label forwarding entry */ > struct net_device __rcu *rt_dev; > struct rcu_head rt_rcu; > u32 rt_label[MAX_NEW_LABELS]; > u8 rt_protocol; /* routing protocol that set this entry */ > u8 rt_unlabeled : 1; > - u8 rt_labels : 7; > + u8 rt_payload_type : 3; > + u8 rt_labels : 4; > u8 rt_via_alen; > u8 rt_via_table; > u8 rt_via[0]; > @@ -90,16 +102,7 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) > static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, > struct mpls_entry_decoded dec) > { > - /* RFC4385 and RFC5586 encode other packets in mpls such that > - * they don't conflict with the ip version number, making > - * decoding by examining the ip version correct in everything > - * except for the strangest cases. > - * > - * The strange cases if we choose to support them will require > - * manual configuration. > - */ > - struct iphdr *hdr4; > - bool success = true; > + enum mpls_payload_type payload_type; > > /* The IPv4 code below accesses through the IPv4 header > * checksum, which is 12 bytes into the packet. > @@ -114,24 +117,31 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, > if (!pskb_may_pull(skb, 12)) > return false; > > - /* Use ip_hdr to find the ip protocol version */ > - hdr4 = ip_hdr(skb); > - if (hdr4->version == 4) { > + payload_type = rt->rt_payload_type; > + if (payload_type == MPT_UNSPEC) > + payload_type = ip_hdr(skb)->version; > + > + switch (payload_type) { > + case MPT_IPV4: { > + struct iphdr *hdr4 = ip_hdr(skb); > skb->protocol = htons(ETH_P_IP); > csum_replace2(&hdr4->check, > htons(hdr4->ttl << 8), > htons(dec.ttl << 8)); > hdr4->ttl = dec.ttl; > + return true; > } > - else if (hdr4->version == 6) { > + case MPT_IPV6: { > struct ipv6hdr *hdr6 = ipv6_hdr(skb); > skb->protocol = htons(ETH_P_IPV6); > hdr6->hop_limit = dec.ttl; > + return true; > + } > + case MPT_UNSPEC: > + break; > } > - else > - /* version 0 and version 1 are used by pseudo wires */ > - success = false; > - return success; > + > + return false; > } > > static int mpls_forward(struct sk_buff *skb, struct net_device *dev, > @@ -254,16 +264,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { > }; > > struct mpls_route_config { > - u32 rc_protocol; > - u32 rc_ifindex; > - u16 rc_via_table; > - u16 rc_via_alen; > - u8 rc_via[MAX_VIA_ALEN]; > - u32 rc_label; > - u32 rc_output_labels; > - u32 rc_output_label[MAX_NEW_LABELS]; > - u32 rc_nlflags; > - struct nl_info rc_nlinfo; > + u32 rc_protocol; > + u32 rc_ifindex; > + u16 rc_via_table; > + u16 rc_via_alen; > + u8 rc_via[MAX_VIA_ALEN]; > + u32 rc_label; > + u32 rc_output_labels; > + u32 rc_output_label[MAX_NEW_LABELS]; > + u32 rc_nlflags; > + enum mpls_payload_type rc_payload_type; > + struct nl_info rc_nlinfo; > }; > > static struct mpls_route *mpls_rt_alloc(size_t alen) > @@ -414,6 +425,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) > } > rt->rt_protocol = cfg->rc_protocol; > RCU_INIT_POINTER(rt->rt_dev, dev); > + rt->rt_payload_type = cfg->rc_payload_type; > rt->rt_via_table = cfg->rc_via_table; > memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); > > @@ -949,6 +961,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) > goto nort0; > RCU_INIT_POINTER(rt0->rt_dev, lo); > rt0->rt_protocol = RTPROT_KERNEL; > + rt0->rt_payload_type = MPT_IPV4; > rt0->rt_via_table = NEIGH_LINK_TABLE; > memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); > } > @@ -959,6 +972,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) > goto nort2; > RCU_INIT_POINTER(rt2->rt_dev, lo); > rt2->rt_protocol = RTPROT_KERNEL; > + rt2->rt_payload_type = MPT_IPV6; > rt2->rt_via_table = NEIGH_LINK_TABLE; > memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); > } -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 07/04/15 18:19, Eric W. Biederman wrote: > Robert Shearman <rshearma@brocade.com> writes: > >> RFC 4182 s2 states that if an IPv4 Explicit NULL label is the only >> label on the stack, then after popping the resulting packet must be >> treated as a IPv4 packet and forwarded based on the IPv4 header. The >> same is true for IPv6 Explicit NULL with an IPv6 packet following. >> >> Therefore, when installing the IPv4/IPv6 Explicit NULL label routes, >> add an attribute that specifies the expected payload type for use at >> forwarding time for determining the type of the encapsulated packet >> instead of inspecting the first nibble of the packet. > > This looks pretty reasonable. > > I suspect the multiple returns instead of using a single variable > might generate slightly worse machine but whatever. That's a good point - the way the changes are structured now means that the removal of the local variable doesn't add anything, so if it's OK with you I'll change that. > > Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Thanks for the review Eric. Rob > > >> Cc: "Eric W. Biederman" <ebiederm@xmission.com> >> Signed-off-by: Robert Shearman <rshearma@brocade.com> >> --- >> net/mpls/af_mpls.c | 72 ++++++++++++++++++++++++++++++++---------------------- >> 1 file changed, 43 insertions(+), 29 deletions(-) >> >> diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c >> index 0b0420bf110d..e9ce5799449d 100644 >> --- a/net/mpls/af_mpls.c >> +++ b/net/mpls/af_mpls.c >> @@ -23,13 +23,25 @@ >> /* This maximum ha length copied from the definition of struct neighbour */ >> #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) >> >> +enum mpls_payload_type { >> + MPT_UNSPEC, /* IPv4 or IPv6 */ >> + MPT_IPV4 = 4, >> + MPT_IPV6 = 6, >> + >> + /* Other types not implemented: >> + * - Pseudo-wire with or without control word (RFC4385) >> + * - GAL (RFC5586) >> + */ >> +}; >> + >> struct mpls_route { /* next hop label forwarding entry */ >> struct net_device __rcu *rt_dev; >> struct rcu_head rt_rcu; >> u32 rt_label[MAX_NEW_LABELS]; >> u8 rt_protocol; /* routing protocol that set this entry */ >> u8 rt_unlabeled : 1; >> - u8 rt_labels : 7; >> + u8 rt_payload_type : 3; >> + u8 rt_labels : 4; >> u8 rt_via_alen; >> u8 rt_via_table; >> u8 rt_via[0]; >> @@ -90,16 +102,7 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) >> static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, >> struct mpls_entry_decoded dec) >> { >> - /* RFC4385 and RFC5586 encode other packets in mpls such that >> - * they don't conflict with the ip version number, making >> - * decoding by examining the ip version correct in everything >> - * except for the strangest cases. >> - * >> - * The strange cases if we choose to support them will require >> - * manual configuration. >> - */ >> - struct iphdr *hdr4; >> - bool success = true; >> + enum mpls_payload_type payload_type; >> >> /* The IPv4 code below accesses through the IPv4 header >> * checksum, which is 12 bytes into the packet. >> @@ -114,24 +117,31 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, >> if (!pskb_may_pull(skb, 12)) >> return false; >> >> - /* Use ip_hdr to find the ip protocol version */ >> - hdr4 = ip_hdr(skb); >> - if (hdr4->version == 4) { >> + payload_type = rt->rt_payload_type; >> + if (payload_type == MPT_UNSPEC) >> + payload_type = ip_hdr(skb)->version; >> + >> + switch (payload_type) { >> + case MPT_IPV4: { >> + struct iphdr *hdr4 = ip_hdr(skb); >> skb->protocol = htons(ETH_P_IP); >> csum_replace2(&hdr4->check, >> htons(hdr4->ttl << 8), >> htons(dec.ttl << 8)); >> hdr4->ttl = dec.ttl; >> + return true; >> } >> - else if (hdr4->version == 6) { >> + case MPT_IPV6: { >> struct ipv6hdr *hdr6 = ipv6_hdr(skb); >> skb->protocol = htons(ETH_P_IPV6); >> hdr6->hop_limit = dec.ttl; >> + return true; >> + } >> + case MPT_UNSPEC: >> + break; >> } >> - else >> - /* version 0 and version 1 are used by pseudo wires */ >> - success = false; >> - return success; >> + >> + return false; >> } >> >> static int mpls_forward(struct sk_buff *skb, struct net_device *dev, >> @@ -254,16 +264,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { >> }; >> >> struct mpls_route_config { >> - u32 rc_protocol; >> - u32 rc_ifindex; >> - u16 rc_via_table; >> - u16 rc_via_alen; >> - u8 rc_via[MAX_VIA_ALEN]; >> - u32 rc_label; >> - u32 rc_output_labels; >> - u32 rc_output_label[MAX_NEW_LABELS]; >> - u32 rc_nlflags; >> - struct nl_info rc_nlinfo; >> + u32 rc_protocol; >> + u32 rc_ifindex; >> + u16 rc_via_table; >> + u16 rc_via_alen; >> + u8 rc_via[MAX_VIA_ALEN]; >> + u32 rc_label; >> + u32 rc_output_labels; >> + u32 rc_output_label[MAX_NEW_LABELS]; >> + u32 rc_nlflags; >> + enum mpls_payload_type rc_payload_type; >> + struct nl_info rc_nlinfo; >> }; >> >> static struct mpls_route *mpls_rt_alloc(size_t alen) >> @@ -414,6 +425,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) >> } >> rt->rt_protocol = cfg->rc_protocol; >> RCU_INIT_POINTER(rt->rt_dev, dev); >> + rt->rt_payload_type = cfg->rc_payload_type; >> rt->rt_via_table = cfg->rc_via_table; >> memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); >> >> @@ -949,6 +961,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) >> goto nort0; >> RCU_INIT_POINTER(rt0->rt_dev, lo); >> rt0->rt_protocol = RTPROT_KERNEL; >> + rt0->rt_payload_type = MPT_IPV4; >> rt0->rt_via_table = NEIGH_LINK_TABLE; >> memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); >> } >> @@ -959,6 +972,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) >> goto nort2; >> RCU_INIT_POINTER(rt2->rt_dev, lo); >> rt2->rt_protocol = RTPROT_KERNEL; >> + rt2->rt_payload_type = MPT_IPV6; >> rt2->rt_via_table = NEIGH_LINK_TABLE; >> memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); >> } -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0b0420bf110d..e9ce5799449d 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -23,13 +23,25 @@ /* This maximum ha length copied from the definition of struct neighbour */ #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) +enum mpls_payload_type { + MPT_UNSPEC, /* IPv4 or IPv6 */ + MPT_IPV4 = 4, + MPT_IPV6 = 6, + + /* Other types not implemented: + * - Pseudo-wire with or without control word (RFC4385) + * - GAL (RFC5586) + */ +}; + struct mpls_route { /* next hop label forwarding entry */ struct net_device __rcu *rt_dev; struct rcu_head rt_rcu; u32 rt_label[MAX_NEW_LABELS]; u8 rt_protocol; /* routing protocol that set this entry */ u8 rt_unlabeled : 1; - u8 rt_labels : 7; + u8 rt_payload_type : 3; + u8 rt_labels : 4; u8 rt_via_alen; u8 rt_via_table; u8 rt_via[0]; @@ -90,16 +102,7 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { - /* RFC4385 and RFC5586 encode other packets in mpls such that - * they don't conflict with the ip version number, making - * decoding by examining the ip version correct in everything - * except for the strangest cases. - * - * The strange cases if we choose to support them will require - * manual configuration. - */ - struct iphdr *hdr4; - bool success = true; + enum mpls_payload_type payload_type; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. @@ -114,24 +117,31 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, if (!pskb_may_pull(skb, 12)) return false; - /* Use ip_hdr to find the ip protocol version */ - hdr4 = ip_hdr(skb); - if (hdr4->version == 4) { + payload_type = rt->rt_payload_type; + if (payload_type == MPT_UNSPEC) + payload_type = ip_hdr(skb)->version; + + switch (payload_type) { + case MPT_IPV4: { + struct iphdr *hdr4 = ip_hdr(skb); skb->protocol = htons(ETH_P_IP); csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(dec.ttl << 8)); hdr4->ttl = dec.ttl; + return true; } - else if (hdr4->version == 6) { + case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); hdr6->hop_limit = dec.ttl; + return true; + } + case MPT_UNSPEC: + break; } - else - /* version 0 and version 1 are used by pseudo wires */ - success = false; - return success; + + return false; } static int mpls_forward(struct sk_buff *skb, struct net_device *dev, @@ -254,16 +264,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { }; struct mpls_route_config { - u32 rc_protocol; - u32 rc_ifindex; - u16 rc_via_table; - u16 rc_via_alen; - u8 rc_via[MAX_VIA_ALEN]; - u32 rc_label; - u32 rc_output_labels; - u32 rc_output_label[MAX_NEW_LABELS]; - u32 rc_nlflags; - struct nl_info rc_nlinfo; + u32 rc_protocol; + u32 rc_ifindex; + u16 rc_via_table; + u16 rc_via_alen; + u8 rc_via[MAX_VIA_ALEN]; + u32 rc_label; + u32 rc_output_labels; + u32 rc_output_label[MAX_NEW_LABELS]; + u32 rc_nlflags; + enum mpls_payload_type rc_payload_type; + struct nl_info rc_nlinfo; }; static struct mpls_route *mpls_rt_alloc(size_t alen) @@ -414,6 +425,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) } rt->rt_protocol = cfg->rc_protocol; RCU_INIT_POINTER(rt->rt_dev, dev); + rt->rt_payload_type = cfg->rc_payload_type; rt->rt_via_table = cfg->rc_via_table; memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); @@ -949,6 +961,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort0; RCU_INIT_POINTER(rt0->rt_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; + rt0->rt_payload_type = MPT_IPV4; rt0->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); } @@ -959,6 +972,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort2; RCU_INIT_POINTER(rt2->rt_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; + rt2->rt_payload_type = MPT_IPV6; rt2->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); }
RFC 4182 s2 states that if an IPv4 Explicit NULL label is the only label on the stack, then after popping the resulting packet must be treated as a IPv4 packet and forwarded based on the IPv4 header. The same is true for IPv6 Explicit NULL with an IPv6 packet following. Therefore, when installing the IPv4/IPv6 Explicit NULL label routes, add an attribute that specifies the expected payload type for use at forwarding time for determining the type of the encapsulated packet instead of inspecting the first nibble of the packet. Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Robert Shearman <rshearma@brocade.com> --- net/mpls/af_mpls.c | 72 ++++++++++++++++++++++++++++++++---------------------- 1 file changed, 43 insertions(+), 29 deletions(-)