diff options
-rw-r--r-- | Documentation/networking/mpls-sysctl.txt | 8 | ||||
-rw-r--r-- | include/net/mpls_iptunnel.h | 2 | ||||
-rw-r--r-- | include/net/netns/mpls.h | 1 | ||||
-rw-r--r-- | include/uapi/linux/mpls_iptunnel.h | 2 | ||||
-rw-r--r-- | net/mpls/af_mpls.c | 11 | ||||
-rw-r--r-- | net/mpls/mpls_iptunnel.c | 73 |
6 files changed, 84 insertions, 13 deletions
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 9badd1d6685f..2f24a1912a48 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -30,6 +30,14 @@ ip_ttl_propagate - BOOL 0 - disabled / RFC 3443 [Short] Pipe Model 1 - enabled / RFC 3443 Uniform Model (default) +default_ttl - BOOL + Default TTL value to use for MPLS packets where it cannot be + propagated from an IP header, either because one isn't present + or ip_ttl_propagate has been disabled. + + Possible values: 1 - 255 + Default: 255 + conf/<interface>/input - BOOL Control whether packets can be input on this interface. diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h index 179253f9dcfd..a18af6a16eb5 100644 --- a/include/net/mpls_iptunnel.h +++ b/include/net/mpls_iptunnel.h @@ -19,6 +19,8 @@ struct mpls_iptunnel_encap { u32 label[MAX_NEW_LABELS]; u8 labels; + u8 ttl_propagate; + u8 default_ttl; }; static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index 08652eedabb2..6608b3693385 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -10,6 +10,7 @@ struct ctl_table_header; struct netns_mpls { int ip_ttl_propagate; + int default_ttl; size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h index d80a0498f77e..f5e45095b0bb 100644 --- a/include/uapi/linux/mpls_iptunnel.h +++ b/include/uapi/linux/mpls_iptunnel.h @@ -16,11 +16,13 @@ /* MPLS tunnel attributes * [RTA_ENCAP] = { * [MPLS_IPTUNNEL_DST] + * [MPLS_IPTUNNEL_TTL] * } */ enum { MPLS_IPTUNNEL_UNSPEC, MPLS_IPTUNNEL_DST, + MPLS_IPTUNNEL_TTL, __MPLS_IPTUNNEL_MAX, }; #define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e1046f21af8..0c5d111abe36 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -34,6 +34,7 @@ static int zero = 0; static int one = 1; static int label_limit = (1 << 20) - 1; +static int ttl_max = 255; static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, @@ -2042,6 +2043,15 @@ static const struct ctl_table mpls_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "default_ttl", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &ttl_max, + }, { } }; @@ -2053,6 +2063,7 @@ static int mpls_net_init(struct net *net) net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; + net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index e4e4424f9eb1..22f71fce0bfb 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -29,6 +29,7 @@ static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, + [MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 }, }; static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) @@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb) struct rtable *rt = NULL; struct rt6_info *rt6 = NULL; struct mpls_dev *out_mdev; + struct net *net; int err = 0; bool bos; int i; @@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb) /* Find the output device */ out_dev = dst->dev; - - /* Obtain the ttl */ - if (dst->ops->family == AF_INET) { - ttl = ip_hdr(skb)->ttl; - rt = (struct rtable *)dst; - } else if (dst->ops->family == AF_INET6) { - ttl = ipv6_hdr(skb)->hop_limit; - rt6 = (struct rt6_info *)dst; - } else { - goto drop; - } + net = dev_net(out_dev); skb_orphan(skb); @@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb) tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate); + /* Obtain the ttl using the following set of rules. + * + * LWT ttl propagation setting: + * - disabled => use default TTL value from LWT + * - enabled => use TTL value from IPv4/IPv6 header + * - default => + * Global ttl propagation setting: + * - disabled => use default TTL value from global setting + * - enabled => use TTL value from IPv4/IPv6 header + */ + if (dst->ops->family == AF_INET) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + } else if (dst->ops->family == AF_INET6) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + } else { + goto drop; + } + /* Verify the destination can hold the packet */ new_header_size = mpls_encap_size(tun_encap_info); mtu = mpls_dev_mtu(out_dev); @@ -160,6 +184,17 @@ static int mpls_build_state(struct nlattr *nla, &tun_encap_info->labels, tun_encap_info->label); if (ret) goto errout; + + tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT; + + if (tb[MPLS_IPTUNNEL_TTL]) { + tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]); + /* TTL 0 implies propagate from IP header */ + tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ? + MPLS_TTL_PROP_DISABLED : + MPLS_TTL_PROP_ENABLED; + } + newts->type = LWTUNNEL_ENCAP_MPLS; newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; newts->headroom = mpls_encap_size(tun_encap_info); @@ -186,6 +221,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb, tun_encap_info->label)) goto nla_put_failure; + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT && + nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -195,10 +234,16 @@ nla_put_failure: static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) { struct mpls_iptunnel_encap *tun_encap_info; + int nlsize; tun_encap_info = mpls_lwtunnel_encap(lwtstate); - return nla_total_size(tun_encap_info->labels * 4); + nlsize = nla_total_size(tun_encap_info->labels * 4); + + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT) + nlsize += nla_total_size(1); + + return nlsize; } static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) @@ -207,7 +252,9 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); int l; - if (a_hdr->labels != b_hdr->labels) + if (a_hdr->labels != b_hdr->labels || + a_hdr->ttl_propagate != b_hdr->ttl_propagate || + a_hdr->default_ttl != b_hdr->default_ttl) return 1; for (l = 0; l < MAX_NEW_LABELS; l++) |