diff options
| -rw-r--r-- | MAINTAINERS | 7 | ||||
| -rw-r--r-- | include/net/ife.h | 51 | ||||
| -rw-r--r-- | include/net/tc_act/tc_ife.h | 3 | ||||
| -rw-r--r-- | include/uapi/linux/Kbuild | 1 | ||||
| -rw-r--r-- | include/uapi/linux/ife.h | 18 | ||||
| -rw-r--r-- | include/uapi/linux/tc_act/tc_ife.h | 10 | ||||
| -rw-r--r-- | net/Kconfig | 1 | ||||
| -rw-r--r-- | net/Makefile | 1 | ||||
| -rw-r--r-- | net/ife/Kconfig | 16 | ||||
| -rw-r--r-- | net/ife/Makefile | 5 | ||||
| -rw-r--r-- | net/ife/ife.c | 142 | ||||
| -rw-r--r-- | net/sched/Kconfig | 1 | ||||
| -rw-r--r-- | net/sched/act_ife.c | 110 |
13 files changed, 276 insertions, 90 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 5e637e2b3ff9..2abda6cb3150 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6250,6 +6250,13 @@ F: include/net/cfg802154.h F: include/net/ieee802154_netdev.h F: Documentation/networking/ieee802154.txt +IFE PROTOCOL +M: Yotam Gigi <yotamg@mellanox.com> +M: Jamal Hadi Salim <jhs@mojatatu.com> +F: net/ife +F: include/net/ife.h +F: include/uapi/linux/ife.h + IGORPLUG-USB IR RECEIVER M: Sean Young <sean@mess.org> L: linux-media@vger.kernel.org diff --git a/include/net/ife.h b/include/net/ife.h new file mode 100644 index 000000000000..2d87d6898b0a --- /dev/null +++ b/include/net/ife.h @@ -0,0 +1,51 @@ +#ifndef __NET_IFE_H +#define __NET_IFE_H + +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/module.h> +#include <uapi/linux/ife.h> + +#if IS_ENABLED(CONFIG_NET_IFE) + +void *ife_encode(struct sk_buff *skb, u16 metalen); +void *ife_decode(struct sk_buff *skb, u16 *metalen); + +void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen); +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval); + +void *ife_tlv_meta_next(void *skbdata); + +#else + +static inline void *ife_encode(struct sk_buff *skb, u16 metalen) +{ + return NULL; +} + +static inline void *ife_decode(struct sk_buff *skb, u16 *metalen) +{ + return NULL; +} + +static inline void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, + u16 *totlen) +{ + return NULL; +} + +static inline int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval) +{ + return 0; +} + +static inline void *ife_tlv_meta_next(void *skbdata) +{ + return NULL; +} + +#endif + +#endif /* __NET_IFE_H */ diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 9fd2bea0a6e0..30ba459ddd34 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -6,7 +6,6 @@ #include <linux/rtnetlink.h> #include <linux/module.h> -#define IFE_METAHDRLEN 2 struct tcf_ife_info { struct tc_action common; u8 eth_dst[ETH_ALEN]; @@ -45,8 +44,6 @@ struct tcf_meta_ops { int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); -int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, - const void *dval); int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 486e050e64c5..a2e90722a4c4 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -195,6 +195,7 @@ header-y += if_tun.h header-y += if_tunnel.h header-y += if_vlan.h header-y += if_x25.h +header-y += ife.h header-y += igmp.h header-y += ila.h header-y += in6.h diff --git a/include/uapi/linux/ife.h b/include/uapi/linux/ife.h new file mode 100644 index 000000000000..2954da32e012 --- /dev/null +++ b/include/uapi/linux/ife.h @@ -0,0 +1,18 @@ +#ifndef __UAPI_IFE_H +#define __UAPI_IFE_H + +#define IFE_METAHDRLEN 2 + +enum { + IFE_META_SKBMARK = 1, + IFE_META_HASHID, + IFE_META_PRIO, + IFE_META_QMAP, + IFE_META_TCINDEX, + __IFE_META_MAX +}; + +/*Can be overridden at runtime by module option*/ +#define IFE_META_MAX (__IFE_META_MAX - 1) + +#endif diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index cd18360eca24..7c2817866c97 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/pkt_cls.h> +#include <linux/ife.h> #define TCA_ACT_IFE 25 /* Flag bits for now just encoding/decoding; mutually exclusive */ @@ -28,13 +29,4 @@ enum { }; #define TCA_IFE_MAX (__TCA_IFE_MAX - 1) -#define IFE_META_SKBMARK 1 -#define IFE_META_HASHID 2 -#define IFE_META_PRIO 3 -#define IFE_META_QMAP 4 -#define IFE_META_TCINDEX 5 -/*Can be overridden at runtime by module option*/ -#define __IFE_META_MAX 6 -#define IFE_META_MAX (__IFE_META_MAX - 1) - #endif diff --git a/net/Kconfig b/net/Kconfig index ce4aee69fc0d..2f2842d2d3ed 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -391,6 +391,7 @@ source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" source "net/psample/Kconfig" +source "net/ife/Kconfig" config LWTUNNEL bool "Network light weight tunnels" diff --git a/net/Makefile b/net/Makefile index 7d41de48310e..9b681550e3a3 100644 --- a/net/Makefile +++ b/net/Makefile @@ -71,6 +71,7 @@ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_PSAMPLE) += psample/ +obj-$(CONFIG_NET_IFE) += ife/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ obj-$(CONFIG_MPLS) += mpls/ diff --git a/net/ife/Kconfig b/net/ife/Kconfig new file mode 100644 index 000000000000..31e48b652c7c --- /dev/null +++ b/net/ife/Kconfig @@ -0,0 +1,16 @@ +# +# IFE subsystem configuration +# + +menuconfig NET_IFE + depends on NET + tristate "Inter-FE based on IETF ForCES InterFE LFB" + default n + help + Say Y here to add support of IFE encapsulation protocol + For details refer to netdev01 paper: + "Distributing Linux Traffic Control Classifier-Action Subsystem" + Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + + To compile this support as a module, choose M here: the module will + be called ife. diff --git a/net/ife/Makefile b/net/ife/Makefile new file mode 100644 index 000000000000..2a90d97746cc --- /dev/null +++ b/net/ife/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the IFE encapsulation protocol +# + +obj-$(CONFIG_NET_IFE) += ife.o diff --git a/net/ife/ife.c b/net/ife/ife.c new file mode 100644 index 000000000000..f360341c72eb --- /dev/null +++ b/net/ife/ife.c @@ -0,0 +1,142 @@ +/* + * net/ife/ife.c - Inter-FE protocol based on ForCES WG InterFE LFB + * Copyright (c) 2015 Jamal Hadi Salim <jhs@mojatatu.com> + * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> + * + * Refer to: draft-ietf-forces-interfelfb-03 and netdev01 paper: + * "Distributing Linux Traffic Control Classifier-Action Subsystem" + * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/module.h> +#include <linux/init.h> +#include <net/net_namespace.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <linux/etherdevice.h> +#include <net/ife.h> + +struct ifeheadr { + __be16 metalen; + u8 tlv_data[]; +}; + +void *ife_encode(struct sk_buff *skb, u16 metalen) +{ + /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA + * where ORIGDATA = original ethernet header ... + */ + int hdrm = metalen + IFE_METAHDRLEN; + int total_push = hdrm + skb->dev->hard_header_len; + struct ifeheadr *ifehdr; + struct ethhdr *iethh; /* inner ether header */ + int skboff = 0; + int err; + + err = skb_cow_head(skb, total_push); + if (unlikely(err)) + return NULL; + + iethh = (struct ethhdr *) skb->data; + + __skb_push(skb, total_push); + memcpy(skb->data, iethh, skb->dev->hard_header_len); + skb_reset_mac_header(skb); + skboff += skb->dev->hard_header_len; + + /* total metadata length */ + ifehdr = (struct ifeheadr *) (skb->data + skboff); + metalen += IFE_METAHDRLEN; + ifehdr->metalen = htons(metalen); + + return ifehdr->tlv_data; +} +EXPORT_SYMBOL_GPL(ife_encode); + +void *ife_decode(struct sk_buff *skb, u16 *metalen) +{ + struct ifeheadr *ifehdr; + int total_pull; + u16 ifehdrln; + + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); + ifehdrln = ntohs(ifehdr->metalen); + total_pull = skb->dev->hard_header_len + ifehdrln; + + if (unlikely(ifehdrln < 2)) + return NULL; + + if (unlikely(!pskb_may_pull(skb, total_pull))) + return NULL; + + skb_set_mac_header(skb, total_pull); + __skb_pull(skb, total_pull); + *metalen = ifehdrln - IFE_METAHDRLEN; + + return &ifehdr->tlv_data; +} +EXPORT_SYMBOL_GPL(ife_decode); + +struct meta_tlvhdr { + __be16 type; + __be16 len; +}; + +/* Caller takes care of presenting data in network order + */ +void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +{ + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + + *dlen = ntohs(tlv->len) - NLA_HDRLEN; + *attrtype = ntohs(tlv->type); + + if (totlen) + *totlen = nla_total_size(*dlen); + + return skbdata + sizeof(struct meta_tlvhdr); +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_decode); + +void *ife_tlv_meta_next(void *skbdata) +{ + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + u16 tlvlen = ntohs(tlv->len); + + tlvlen = NLA_ALIGN(tlvlen); + + return skbdata + tlvlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_next); + +/* Caller takes care of presenting data in network order + */ +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) +{ + __be32 *tlv = (__be32 *) (skbdata); + u16 totlen = nla_total_size(dlen); /*alignment + hdr */ + char *dptr = (char *) tlv + NLA_HDRLEN; + u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN); + + *tlv = htonl(htlv); + memset(dptr, 0, totlen - NLA_HDRLEN); + memcpy(dptr, dval, dlen); + + return totlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); + +MODULE_AUTHOR("Jamal Hadi Salim <jhs@mojatatu.com>"); +MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>"); +MODULE_DESCRIPTION("Inter-FE LFB action"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 72cfa3a6bac0..403790cce7d2 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -776,6 +776,7 @@ config NET_ACT_SKBMOD config NET_ACT_IFE tristate "Inter-FE action based on IETF ForCES InterFE LFB" depends on NET_CLS_ACT + select NET_IFE ---help--- Say Y here to allow for sourcing and terminating metadata For details refer to netdev01 paper: diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 921fb20eaa7c..71e7ff22f7c9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -32,6 +32,7 @@ #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> #include <linux/etherdevice.h> +#include <net/ife.h> #define IFE_TAB_MASK 15 @@ -46,23 +47,6 @@ static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { [TCA_IFE_TYPE] = { .type = NLA_U16}, }; -/* Caller takes care of presenting data in network order -*/ -int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) -{ - u32 *tlv = (u32 *)(skbdata); - u16 totlen = nla_total_size(dlen); /*alignment + hdr */ - char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN); - - *tlv = htonl(htlv); - memset(dptr, 0, totlen - NLA_HDRLEN); - memcpy(dptr, dval, dlen); - - return totlen; -} -EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); - int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi) { u16 edata = 0; @@ -637,69 +621,59 @@ int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, return 0; } -struct ifeheadr { - __be16 metalen; - u8 tlv_data[]; -}; - -struct meta_tlvhdr { - __be16 type; - __be16 len; -}; - static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; - struct ifeheadr *ifehdr = (struct ifeheadr *)skb->data; - int ifehdrln = (int)ifehdr->metalen; - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *)(ifehdr->tlv_data); + u8 *ifehdr_end; + u8 *tlv_data; + u16 metalen; spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); tcf_lastuse_update(&ife->tcf_tm); spin_unlock(&ife->tcf_lock); - ifehdrln = ntohs(ifehdrln); - if (unlikely(!pskb_may_pull(skb, ifehdrln))) { + if (skb_at_tc_ingress(skb)) + skb_push(skb, skb->dev->hard_header_len); + + tlv_data = ife_decode(skb, &metalen); + if (unlikely(!tlv_data)) { spin_lock(&ife->tcf_lock); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } - skb_set_mac_header(skb, ifehdrln); - __skb_pull(skb, ifehdrln); - skb->protocol = eth_type_trans(skb, skb->dev); - ifehdrln -= IFE_METAHDRLEN; - - while (ifehdrln > 0) { - u8 *tlvdata = (u8 *)tlv; - u16 mtype = tlv->type; - u16 mlen = tlv->len; - u16 alen; + ifehdr_end = tlv_data + metalen; + for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) { + u8 *curr_data; + u16 mtype; + u16 dlen; - mtype = ntohs(mtype); - mlen = ntohs(mlen); - alen = NLA_ALIGN(mlen); + curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); - if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), - (void *)(tlvdata + NLA_HDRLEN))) { + if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ - pr_info_ratelimited("Unknown metaid %d alnlen %d\n", - mtype, mlen); + pr_info_ratelimited("Unknown metaid %d dlen %d\n", + mtype, dlen); ife->tcf_qstats.overlimits++; } + } - tlvdata += alen; - ifehdrln -= alen; - tlv = (struct meta_tlvhdr *)tlvdata; + if (WARN_ON(tlv_data != ifehdr_end)) { + spin_lock(&ife->tcf_lock); + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; } + skb->protocol = eth_type_trans(skb, skb->dev); skb_reset_network_header(skb); + return action; } @@ -727,7 +701,6 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; struct ethhdr *oethh; /* outer ether header */ - struct ethhdr *iethh; /* inner eth header */ struct tcf_meta_info *e; /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA @@ -735,10 +708,11 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, */ u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; - unsigned int skboff = skb->dev->hard_header_len; + unsigned int skboff = 0; int new_len = skb->len + hdrm; bool exceed_mtu = false; - int err; + void *ife_meta; + int err = 0; if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) @@ -765,27 +739,10 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - err = skb_cow_head(skb, hdrm); - if (unlikely(err)) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - return TC_ACT_SHOT; - } - if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); - iethh = (struct ethhdr *)skb->data; - __skb_push(skb, hdrm); - memcpy(skb->data, iethh, skb->mac_len); - skb_reset_mac_header(skb); - oethh = eth_hdr(skb); - - /*total metadata length */ - metalen += IFE_METAHDRLEN; - metalen = htons(metalen); - memcpy((skb->data + skboff), &metalen, IFE_METAHDRLEN); - skboff += IFE_METAHDRLEN; + ife_meta = ife_encode(skb, metalen); /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by @@ -793,7 +750,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, */ list_for_each_entry(e, &ife->metalist, metalist) { if (e->ops->encode) { - err = e->ops->encode(skb, (void *)(skb->data + skboff), + err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { @@ -804,15 +761,12 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } skboff += err; } + oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(ife->eth_src)) ether_addr_copy(oethh->h_source, ife->eth_src); - else - ether_addr_copy(oethh->h_source, iethh->h_source); if (!is_zero_ether_addr(ife->eth_dst)) ether_addr_copy(oethh->h_dest, ife->eth_dst); - else - ether_addr_copy(oethh->h_dest, iethh->h_dest); oethh->h_proto = htons(ife->eth_type); if (skb_at_tc_ingress(skb)) |