diff options
| -rw-r--r-- | drivers/net/vxlan.c | 32 | ||||
| -rw-r--r-- | include/net/nsh.h | 307 | ||||
| -rw-r--r-- | include/net/tun_proto.h | 49 | ||||
| -rw-r--r-- | include/net/vxlan.h | 6 | ||||
| -rw-r--r-- | include/uapi/linux/if_ether.h | 1 | ||||
| -rw-r--r-- | net/Kconfig | 1 | ||||
| -rw-r--r-- | net/Makefile | 1 | ||||
| -rw-r--r-- | net/nsh/Kconfig | 9 | ||||
| -rw-r--r-- | net/nsh/Makefile | 1 | ||||
| -rw-r--r-- | net/nsh/nsh.c | 91 |
10 files changed, 467 insertions, 31 deletions
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ae3a1da703c2..d7c49cf1d5e9 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -26,6 +26,7 @@ #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/tun_proto.h> #include <net/vxlan.h> #if IS_ENABLED(CONFIG_IPV6) @@ -1261,19 +1262,9 @@ static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed, if (gpe->oam_flag) return false; - switch (gpe->next_protocol) { - case VXLAN_GPE_NP_IPV4: - *protocol = htons(ETH_P_IP); - break; - case VXLAN_GPE_NP_IPV6: - *protocol = htons(ETH_P_IPV6); - break; - case VXLAN_GPE_NP_ETHERNET: - *protocol = htons(ETH_P_TEB); - break; - default: + *protocol = tun_p_to_eth_p(gpe->next_protocol); + if (!*protocol) return false; - } unparsed->vx_flags &= ~VXLAN_GPE_USED_BITS; return true; @@ -1799,19 +1790,10 @@ static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, u32 vxflags, struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; - - switch (protocol) { - case htons(ETH_P_IP): - gpe->next_protocol = VXLAN_GPE_NP_IPV4; - return 0; - case htons(ETH_P_IPV6): - gpe->next_protocol = VXLAN_GPE_NP_IPV6; - return 0; - case htons(ETH_P_TEB): - gpe->next_protocol = VXLAN_GPE_NP_ETHERNET; - return 0; - } - return -EPFNOSUPPORT; + gpe->next_protocol = tun_p_from_eth_p(protocol); + if (!gpe->next_protocol) + return -EPFNOSUPPORT; + return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, diff --git a/include/net/nsh.h b/include/net/nsh.h new file mode 100644 index 000000000000..a1eaea20be96 --- /dev/null +++ b/include/net/nsh.h @@ -0,0 +1,307 @@ +#ifndef __NET_NSH_H +#define __NET_NSH_H 1 + +#include <linux/skbuff.h> + +/* + * Network Service Header: + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |Ver|O|U| TTL | Length |U|U|U|U|MD Type| Next Protocol | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Service Path Identifier (SPI) | Service Index | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * ~ Mandatory/Optional Context Headers ~ + * | | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Version: The version field is used to ensure backward compatibility + * going forward with future NSH specification updates. It MUST be set + * to 0x0 by the sender, in this first revision of NSH. Given the + * widespread implementation of existing hardware that uses the first + * nibble after an MPLS label stack for ECMP decision processing, this + * document reserves version 01b and this value MUST NOT be used in + * future versions of the protocol. Please see [RFC7325] for further + * discussion of MPLS-related forwarding requirements. + * + * O bit: Setting this bit indicates an Operations, Administration, and + * Maintenance (OAM) packet. The actual format and processing of SFC + * OAM packets is outside the scope of this specification (see for + * example [I-D.ietf-sfc-oam-framework] for one approach). + * + * The O bit MUST be set for OAM packets and MUST NOT be set for non-OAM + * packets. The O bit MUST NOT be modified along the SFP. + * + * SF/SFF/SFC Proxy/Classifier implementations that do not support SFC + * OAM procedures SHOULD discard packets with O bit set, but MAY support + * a configurable parameter to enable forwarding received SFC OAM + * packets unmodified to the next element in the chain. Forwarding OAM + * packets unmodified by SFC elements that do not support SFC OAM + * procedures may be acceptable for a subset of OAM functions, but can + * result in unexpected outcomes for others, thus it is recommended to + * analyze the impact of forwarding an OAM packet for all OAM functions + * prior to enabling this behavior. The configurable parameter MUST be + * disabled by default. + * + * TTL: Indicates the maximum SFF hops for an SFP. This field is used + * for service plane loop detection. The initial TTL value SHOULD be + * configurable via the control plane; the configured initial value can + * be specific to one or more SFPs. If no initial value is explicitly + * provided, the default initial TTL value of 63 MUST be used. Each SFF + * involved in forwarding an NSH packet MUST decrement the TTL value by + * 1 prior to NSH forwarding lookup. Decrementing by 1 from an incoming + * value of 0 shall result in a TTL value of 63. The packet MUST NOT be + * forwarded if TTL is, after decrement, 0. + * + * All other flag fields, marked U, are unassigned and available for + * future use, see Section 11.2.1. Unassigned bits MUST be set to zero + * upon origination, and MUST be ignored and preserved unmodified by + * other NSH supporting elements. Elements which do not understand the + * meaning of any of these bits MUST NOT modify their actions based on + * those unknown bits. + * + * Length: The total length, in 4-byte words, of NSH including the Base + * Header, the Service Path Header, the Fixed Length Context Header or + * Variable Length Context Header(s). The length MUST be 0x6 for MD + * Type equal to 0x1, and MUST be 0x2 or greater for MD Type equal to + * 0x2. The length of the NSH header MUST be an integer multiple of 4 + * bytes, thus variable length metadata is always padded out to a + * multiple of 4 bytes. + * + * MD Type: Indicates the format of NSH beyond the mandatory Base Header + * and the Service Path Header. MD Type defines the format of the + * metadata being carried. + * + * 0x0 - This is a reserved value. Implementations SHOULD silently + * discard packets with MD Type 0x0. + * + * 0x1 - This indicates that the format of the header includes a fixed + * length Context Header (see Figure 4 below). + * + * 0x2 - This does not mandate any headers beyond the Base Header and + * Service Path Header, but may contain optional variable length Context + * Header(s). The semantics of the variable length Context Header(s) + * are not defined in this document. The format of the optional + * variable length Context Headers is provided in Section 2.5.1. + * + * 0xF - This value is reserved for experimentation and testing, as per + * [RFC3692]. Implementations not explicitly configured to be part of + * an experiment SHOULD silently discard packets with MD Type 0xF. + * + * Next Protocol: indicates the protocol type of the encapsulated data. + * NSH does not alter the inner payload, and the semantics on the inner + * protocol remain unchanged due to NSH service function chaining. + * Please see the IANA Considerations section below, Section 11.2.5. + * + * This document defines the following Next Protocol values: + * + * 0x1: IPv4 + * 0x2: IPv6 + * 0x3: Ethernet + * 0x4: NSH + * 0x5: MPLS + * 0xFE: Experiment 1 + * 0xFF: Experiment 2 + * + * Packets with Next Protocol values not supported SHOULD be silently + * dropped by default, although an implementation MAY provide a + * configuration parameter to forward them. Additionally, an + * implementation not explicitly configured for a specific experiment + * [RFC3692] SHOULD silently drop packets with Next Protocol values 0xFE + * and 0xFF. + * + * Service Path Identifier (SPI): Identifies a service path. + * Participating nodes MUST use this identifier for Service Function + * Path selection. The initial classifier MUST set the appropriate SPI + * for a given classification result. + * + * Service Index (SI): Provides location within the SFP. The initial + * classifier for a given SFP SHOULD set the SI to 255, however the + * control plane MAY configure the initial value of SI as appropriate + * (i.e., taking into account the length of the service function path). + * The Service Index MUST be decremented by a value of 1 by Service + * Functions or by SFC Proxy nodes after performing required services + * and the new decremented SI value MUST be used in the egress packet's + * NSH. The initial Classifier MUST send the packet to the first SFF in + * the identified SFP for forwarding along an SFP. If re-classification + * occurs, and that re-classification results in a new SPI, the + * (re)classifier is, in effect, the initial classifier for the + * resultant SPI. + * + * The SI is used in conjunction the with Service Path Identifier for + * Service Function Path Selection and for determining the next SFF/SF + * in the path. The SI is also valuable when troubleshooting or + * reporting service paths. Additionally, while the TTL field is the + * main mechanism for service plane loop detection, the SI can also be + * used for detecting service plane loops. + * + * When the Base Header specifies MD Type = 0x1, a Fixed Length Context + * Header (16-bytes) MUST be present immediately following the Service + * Path Header. The value of a Fixed Length Context + * Header that carries no metadata MUST be set to zero. + * + * When the base header specifies MD Type = 0x2, zero or more Variable + * Length Context Headers MAY be added, immediately following the + * Service Path Header (see Figure 5). Therefore, Length = 0x2, + * indicates that only the Base Header followed by the Service Path + * Header are present. The optional Variable Length Context Headers + * MUST be of an integer number of 4-bytes. The base header Length + * field MUST be used to determine the offset to locate the original + * packet or frame for SFC nodes that require access to that + * information. + * + * The format of the optional variable length Context Headers + * + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Metadata Class | Type |U| Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Variable Metadata | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Metadata Class (MD Class): Defines the scope of the 'Type' field to + * provide a hierarchical namespace. The IANA Considerations + * Section 11.2.4 defines how the MD Class values can be allocated to + * standards bodies, vendors, and others. + * + * Type: Indicates the explicit type of metadata being carried. The + * definition of the Type is the responsibility of the MD Class owner. + * + * Unassigned bit: One unassigned bit is available for future use. This + * bit MUST NOT be set, and MUST be ignored on receipt. + * + * Length: Indicates the length of the variable metadata, in bytes. In + * case the metadata length is not an integer number of 4-byte words, + * the sender MUST add pad bytes immediately following the last metadata + * byte to extend the metadata to an integer number of 4-byte words. + * The receiver MUST round up the length field to the nearest 4-byte + * word boundary, to locate and process the next field in the packet. + * The receiver MUST access only those bytes in the metadata indicated + * by the length field (i.e., actual number of bytes) and MUST ignore + * the remaining bytes up to the nearest 4-byte word boundary. The + * Length may be 0 or greater. + * + * A value of 0 denotes a Context Header without a Variable Metadata + * field. + * + * [0] https://datatracker.ietf.org/doc/draft-ietf-sfc-nsh/ + */ + +/** + * struct nsh_md1_ctx - Keeps track of NSH context data + * @nshc<1-4>: NSH Contexts. + */ +struct nsh_md1_ctx { + __be32 context[4]; +}; + +struct nsh_md2_tlv { + __be16 md_class; + u8 type; + u8 length; + u8 md_value[]; +}; + +struct nshhdr { + __be16 ver_flags_ttl_len; + u8 mdtype; + u8 np; + __be32 path_hdr; + union { + struct nsh_md1_ctx md1; + struct nsh_md2_tlv md2; + }; +}; + +/* Masking NSH header fields. */ +#define NSH_VER_MASK 0xc000 +#define NSH_VER_SHIFT 14 +#define NSH_FLAGS_MASK 0x3000 +#define NSH_FLAGS_SHIFT 12 +#define NSH_TTL_MASK 0x0fc0 +#define NSH_TTL_SHIFT 6 +#define NSH_LEN_MASK 0x003f +#define NSH_LEN_SHIFT 0 + +#define NSH_MDTYPE_MASK 0x0f +#define NSH_MDTYPE_SHIFT 0 + +#define NSH_SPI_MASK 0xffffff00 +#define NSH_SPI_SHIFT 8 +#define NSH_SI_MASK 0x000000ff +#define NSH_SI_SHIFT 0 + +/* MD Type Registry. */ +#define NSH_M_TYPE1 0x01 +#define NSH_M_TYPE2 0x02 +#define NSH_M_EXP1 0xFE +#define NSH_M_EXP2 0xFF + +/* NSH Base Header Length */ +#define NSH_BASE_HDR_LEN 8 + +/* NSH MD Type 1 header Length. */ +#define NSH_M_TYPE1_LEN 24 + +/* NSH header maximum Length. */ +#define NSH_HDR_MAX_LEN 256 + +/* NSH context headers maximum Length. */ +#define NSH_CTX_HDRS_MAX_LEN 248 + +static inline struct nshhdr *nsh_hdr(struct sk_buff *skb) +{ + return (struct nshhdr *)skb_network_header(skb); +} + +static inline u16 nsh_hdr_len(const struct nshhdr *nsh) +{ + return ((ntohs(nsh->ver_flags_ttl_len) & NSH_LEN_MASK) + >> NSH_LEN_SHIFT) << 2; +} + +static inline u8 nsh_get_ver(const struct nshhdr *nsh) +{ + return (ntohs(nsh->ver_flags_ttl_len) & NSH_VER_MASK) + >> NSH_VER_SHIFT; +} + +static inline u8 nsh_get_flags(const struct nshhdr *nsh) +{ + return (ntohs(nsh->ver_flags_ttl_len) & NSH_FLAGS_MASK) + >> NSH_FLAGS_SHIFT; +} + +static inline u8 nsh_get_ttl(const struct nshhdr *nsh) +{ + return (ntohs(nsh->ver_flags_ttl_len) & NSH_TTL_MASK) + >> NSH_TTL_SHIFT; +} + +static inline void __nsh_set_xflag(struct nshhdr *nsh, u16 xflag, u16 xmask) +{ + nsh->ver_flags_ttl_len + = (nsh->ver_flags_ttl_len & ~htons(xmask)) | htons(xflag); +} + +static inline void nsh_set_flags_and_ttl(struct nshhdr *nsh, u8 flags, u8 ttl) +{ + __nsh_set_xflag(nsh, ((flags << NSH_FLAGS_SHIFT) & NSH_FLAGS_MASK) | + ((ttl << NSH_TTL_SHIFT) & NSH_TTL_MASK), + NSH_FLAGS_MASK | NSH_TTL_MASK); +} + +static inline void nsh_set_flags_ttl_len(struct nshhdr *nsh, u8 flags, + u8 ttl, u8 len) +{ + len = len >> 2; + __nsh_set_xflag(nsh, ((flags << NSH_FLAGS_SHIFT) & NSH_FLAGS_MASK) | + ((ttl << NSH_TTL_SHIFT) & NSH_TTL_MASK) | + ((len << NSH_LEN_SHIFT) & NSH_LEN_MASK), + NSH_FLAGS_MASK | NSH_TTL_MASK | NSH_LEN_MASK); +} + +#endif /* __NET_NSH_H */ diff --git a/include/net/tun_proto.h b/include/net/tun_proto.h new file mode 100644 index 000000000000..2ea3deba4c99 --- /dev/null +++ b/include/net/tun_proto.h @@ -0,0 +1,49 @@ +#ifndef __NET_TUN_PROTO_H +#define __NET_TUN_PROTO_H + +#include <linux/kernel.h> + +/* One byte protocol values as defined by VXLAN-GPE and NSH. These will + * hopefully get a shared IANA registry. + */ +#define TUN_P_IPV4 0x01 +#define TUN_P_IPV6 0x02 +#define TUN_P_ETHERNET 0x03 +#define TUN_P_NSH 0x04 +#define TUN_P_MPLS_UC 0x05 + +static inline __be16 tun_p_to_eth_p(u8 proto) +{ + switch (proto) { + case TUN_P_IPV4: + return htons(ETH_P_IP); + case TUN_P_IPV6: + return htons(ETH_P_IPV6); + case TUN_P_ETHERNET: + return htons(ETH_P_TEB); + case TUN_P_NSH: + return htons(ETH_P_NSH); + case TUN_P_MPLS_UC: + return htons(ETH_P_MPLS_UC); + } + return 0; +} + +static inline u8 tun_p_from_eth_p(__be16 proto) +{ + switch (proto) { + case htons(ETH_P_IP): + return TUN_P_IPV4; + case htons(ETH_P_IPV6): + return TUN_P_IPV6; + case htons(ETH_P_TEB): + return TUN_P_ETHERNET; + case htons(ETH_P_NSH): + return TUN_P_NSH; + case htons(ETH_P_MPLS_UC): + return TUN_P_MPLS_UC; + } + return 0; +} + +#endif diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3f430e38ab82..4e3876dde295 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -168,12 +168,6 @@ reserved_flags2:2; #define VXLAN_GPE_USED_BITS (VXLAN_HF_VER | VXLAN_HF_NP | VXLAN_HF_OAM | \ cpu_to_be32(0xff)) -/* VXLAN-GPE header Next Protocol. */ -#define VXLAN_GPE_NP_IPV4 0x01 -#define VXLAN_GPE_NP_IPV6 0x02 -#define VXLAN_GPE_NP_ETHERNET 0x03 -#define VXLAN_GPE_NP_NSH 0x04 - struct vxlan_metadata { u32 gbp; }; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index f68f6bf4a253..61f7ccce5b69 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -99,6 +99,7 @@ #define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */ #define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */ #define ETH_P_HSR 0x892F /* IEC 62439-3 HSRv1 */ +#define ETH_P_NSH 0x894F /* Network Service Header */ #define ETH_P_LOOPBACK 0x9000 /* Ethernet loopback packet, per IEEE 802.3 */ #define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ diff --git a/net/Kconfig b/net/Kconfig index 8614a9ccfbef..e0e7c62c88f0 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -235,6 +235,7 @@ source "net/openvswitch/Kconfig" source "net/vmw_vsock/Kconfig" source "net/netlink/Kconfig" source "net/mpls/Kconfig" +source "net/nsh/Kconfig" source "net/hsr/Kconfig" source "net/switchdev/Kconfig" source "net/l3mdev/Kconfig" diff --git a/net/Makefile b/net/Makefile index 3d3feff3643b..ae2fe2283d2f 100644 --- a/net/Makefile +++ b/net/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_NET_IFE) += ife/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ obj-$(CONFIG_MPLS) += mpls/ +obj-$(CONFIG_NET_NSH) += nsh/ obj-$(CONFIG_HSR) += hsr/ ifneq ($(CONFIG_NET_SWITCHDEV),) obj-y += switchdev/ diff --git a/net/nsh/Kconfig b/net/nsh/Kconfig new file mode 100644 index 000000000000..bafc3dd60c2c --- /dev/null +++ b/net/nsh/Kconfig @@ -0,0 +1,9 @@ +menuconfig NET_NSH + tristate "Network Service Header (NSH) protocol" + default n + ---help--- + Network Service Header is an implementation of Service Function + Chaining (RFC 7665). The current implementation in Linux supports + only MD type 1 and only with the openvswitch module. + + If unsure, say N. diff --git a/net/nsh/Makefile b/net/nsh/Makefile new file mode 100644 index 000000000000..c93c787385ca --- /dev/null +++ b/net/nsh/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_NET_NSH) += nsh.o diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c new file mode 100644 index 000000000000..58fb827439a8 --- /dev/null +++ b/net/nsh/nsh.c @@ -0,0 +1,91 @@ +/* + * Network Service Header + * + * Copyright (c) 2017 Red Hat, Inc. -- Jiri Benc <jbenc@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/nsh.h> +#include <net/tun_proto.h> + +static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int nsh_len, mac_len; + __be16 proto; + int nhoff; + + skb_reset_network_header(skb); + + nhoff = skb->network_header - skb->mac_header; + mac_len = skb->mac_len; + + if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) + goto out; + nsh_len = nsh_hdr_len(nsh_hdr(skb)); + if (unlikely(!pskb_may_pull(skb, nsh_len))) + goto out; + + proto = tun_p_to_eth_p(nsh_hdr(skb)->np); + if (!proto) + goto out; + + __skb_pull(skb, nsh_len); + + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + skb->protocol = proto; + + features &= NETIF_F_SG; + segs = skb_mac_gso_segment(skb, features); + if (IS_ERR_OR_NULL(segs)) { + skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, + skb->network_header - nhoff, + mac_len); + goto out; + } + + for (skb = segs; skb; skb = skb->next) { + skb->protocol = htons(ETH_P_NSH); + __skb_push(skb, nsh_len); + skb_set_mac_header(skb, -nhoff); + skb->network_header = skb->mac_header + mac_len; + skb->mac_len = mac_len; + } + +out: + return segs; +} + +static struct packet_offload nsh_packet_offload __read_mostly = { + .type = htons(ETH_P_NSH), + .priority = 15, + .callbacks = { + .gso_segment = nsh_gso_segment, + }, +}; + +static int __init nsh_init_module(void) +{ + dev_add_offload(&nsh_packet_offload); + return 0; +} + +static void __exit nsh_cleanup_module(void) +{ + dev_remove_offload(&nsh_packet_offload); +} + +module_init(nsh_init_module); +module_exit(nsh_cleanup_module); + +MODULE_AUTHOR("Jiri Benc <jbenc@redhat.com>"); +MODULE_DESCRIPTION("NSH protocol"); +MODULE_LICENSE("GPL v2"); |