// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (c) 2015 Nicira, Inc. */ #include <linux/module.h>#include <linux/openvswitch.h>#include <linux/tcp.h>#include <linux/udp.h>#include <linux/sctp.h>#include <linux/static_key.h>#include <linux/string_helpers.h>#include <net/ip.h>#include <net/genetlink.h>#include <net/netfilter/nf_conntrack_core.h>#include <net/netfilter/nf_conntrack_count.h>#include <net/netfilter/nf_conntrack_helper.h>#include <net/netfilter/nf_conntrack_labels.h>#include <net/netfilter/nf_conntrack_seqadj.h>#include <net/netfilter/nf_conntrack_timeout.h>#include <net/netfilter/nf_conntrack_zones.h>#include <net/netfilter/ipv6/nf_defrag_ipv6.h>#include <net/ipv6_frag.h> #if IS_ENABLED(CONFIG_NF_NAT)#include <net/netfilter/nf_nat.h>#endif #include <net/netfilter/nf_conntrack_act_ct.h> #include "datapath.h"#include "drop.h"#include "conntrack.h"#include "flow.h"#include "flow_netlink.h" struct ovs_ct_len_tbl { int maxlen; int minlen;}; /* Metadata mark for masked write to conntrack mark */struct md_mark { u32 value; u32 mask;}; /* Metadata label for masked write to conntrack label. */struct md_labels { struct ovs_key_ct_labels value; struct ovs_key_ct_labels mask;}; enum ovs_ct_nat { OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */ OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */ OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */}; /* Conntrack action context for execution. */struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ u8 force : 1; u8 have_eventmask : 1; u16 family; u32 eventmask; /* Mask of 1 << IPCT_*. */ struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; struct nf_ct_timeout *nf_ct_timeout;#if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */#endif}; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)#define OVS_CT_LIMIT_UNLIMITED 0#define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED#define CT_LIMIT_HASH_BUCKETS 512static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled); struct ovs_ct_limit { /* Elements in ovs_ct_limit_info->limits hash table */ struct hlist_node hlist_node; struct rcu_head rcu; u16 zone; u32 limit;}; struct ovs_ct_limit_info { u32 default_limit; struct hlist_head *limits; struct nf_conncount_data *data;}; static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = { [OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, },};#endif static bool labels_nonzero(const struct ovs_key_ct_labels *labels); static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); static u16 key_to_nfproto(const struct sw_flow_key *key){ switch (ntohs(key->eth.type)) { case ETH_P_IP: return NFPROTO_IPV4; case ETH_P_IPV6: return NFPROTO_IPV6; default: return NFPROTO_UNSPEC; }} /* Map SKB connection state into the values used by flow definition. */static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo){ u8 ct_state = OVS_CS_F_TRACKED; switch (ctinfo) { case IP_CT_ESTABLISHED_REPLY: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_REPLY_DIR; break; default: break; } switch (ctinfo) { case IP_CT_ESTABLISHED: case IP_CT_ESTABLISHED_REPLY: ct_state |= OVS_CS_F_ESTABLISHED; break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_RELATED; break; case IP_CT_NEW: ct_state |= OVS_CS_F_NEW; break; default: break; } return ct_state;} static u32 ovs_ct_get_mark(const struct nf_conn *ct){#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) return ct ? READ_ONCE(ct->mark) : 0;#else return 0;#endif} /* Guard against conntrack labels max size shrinking below 128 bits. */#if NF_CT_LABELS_MAX_SIZE < 16#error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes#endif static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels){ struct nf_conn_labels *cl = NULL; if (ct) { if (ct->master && !nf_ct_is_confirmed(ct)) ct = ct->master; cl = nf_ct_labels_find(ct); } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else memset(labels, 0, OVS_CT_LABELS_LEN);} static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, const struct nf_conntrack_tuple *orig, u8 icmp_proto){ key->ct_orig_proto = orig->dst.protonum; if (orig->dst.protonum == icmp_proto) { key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); } else { key->ct.orig_tp.src = orig->src.u.all; key->ct.orig_tp.dst = orig->dst.u.all; }} static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct){ key->ct_state = state; key->ct_zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels); if (ct) { const struct nf_conntrack_tuple *orig; /* Use the master if we have one. */ if (ct->master) ct = ct->master; orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* IP version must match with the master connection. */ if (key->eth.type == htons(ETH_P_IP) && nf_ct_l3num(ct) == NFPROTO_IPV4) { key->ipv4.ct_orig.src = orig->src.u3.ip; key->ipv4.ct_orig.dst = orig->dst.u3.ip; __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); return; } else if (key->eth.type == htons(ETH_P_IPV6) && !sw_flow_key_is_nd(key) && nf_ct_l3num(ct) == NFPROTO_IPV6) { key->ipv6.ct_orig.src = orig->src.u3.in6; key->ipv6.ct_orig.dst = orig->dst.u3.in6; __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); return; } } /* Clear 'ct_orig_proto' to mark the non-existence of conntrack * original direction key fields. */ key->ct_orig_proto = 0;} /* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has * previously sent the packet to conntrack via the ct action. If * 'keep_nat_flags' is true, the existing NAT flags retained, else they are * initialized from the connection status. */static void ovs_ct_update_key(const struct sk_buff *skb, const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct, bool keep_nat_flags){ const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; struct nf_conn *ct; u8 state = 0; ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); /* All unconfirmed entries are NEW connections. */ if (!nf_ct_is_confirmed(ct)) state |= OVS_CS_F_NEW; /* OVS persists the related flag for the duration of the * connection. */ if (ct->master) state |= OVS_CS_F_RELATED; if (keep_nat_flags) { state |= key->ct_state & OVS_CS_F_NAT_MASK; } else { if (ct->status & IPS_SRC_NAT) state |= OVS_CS_F_SRC_NAT; if (ct->status & IPS_DST_NAT) state |= OVS_CS_F_DST_NAT; } zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; if (info) zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct);} /* This is called to initialize CT key fields possibly coming in from the local * stack. */void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key, bool post_ct){ ovs_ct_update_key(skb, NULL, key, post_ct, false);} int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb){ if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), &output->ct.labels)) return -EMSGSIZE; if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ct_tuple_ipv4 orig; memset(&orig, 0, sizeof(orig)); orig.ipv4_src = output->ipv4.ct_orig.src; orig.ipv4_dst = output->ipv4.ct_orig.dst; orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv4_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ct_tuple_ipv6 orig; memset(&orig, 0, sizeof(orig)); memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, sizeof(orig.ipv6_src)); memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, sizeof(orig.ipv6_dst)); orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv6_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; } } return 0;} static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, u32 ct_mark, u32 mask){#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; } return 0;#else return -ENOTSUPP;#endif} static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct){ struct nf_conn_labels *cl; cl = nf_ct_labels_find(ct); if (!cl) { nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } return cl;} /* Initialize labels for a new, yet to be committed conntrack entry. Note that * since the new connection is not yet confirmed, and thus no-one else has * access to it's labels, we simply write them over. */static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask){ struct nf_conn_labels *cl, *master_cl; bool have_mask = labels_nonzero(mask); /* Inherit master's labels to the related connection? */ master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL; if (!master_cl && !have_mask) return 0; /* Nothing to do. */ cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; /* Inherit the master's labels, if any. */ if (master_cl) *cl = *master_cl; if (have_mask) { u32 *dst = (u32 *)cl->bits; int i; for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) dst[i] = (dst[i] & ~mask->ct_labels_32[i]) | (labels->ct_labels_32[i] & mask->ct_labels_32[i]); } /* Labels are included in the IPCTNL_MSG_CT_NEW event only if the * IPCT_LABEL bit is set in the event cache. */ nf_conntrack_event_cache(IPCT_LABEL, ct); memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0;} static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask){ struct nf_conn_labels *cl; int err; cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; err = nf_connlabels_replace(ct, labels->ct_labels_32, mask->ct_labels_32, OVS_CT_LABELS_LEN_32); if (err) return err; memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0;} static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, int family, struct sk_buff *skb){ struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); if (err) return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); key->ip.frag = OVS_FRAG_TYPE_NONE; *OVS_CB(skb) = ovs_cb; return 0;} /* This replicates logic from nf_conntrack_core.c that is not exported. */static enum ip_conntrack_infoovs_ct_get_info(const struct nf_conntrack_tuple_hash *h){ const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) return IP_CT_ESTABLISHED_REPLY; /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) return IP_CT_ESTABLISHED; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) return IP_CT_RELATED; return IP_CT_NEW;} /* Find an existing connection which this packet belongs to without * re-attributing statistics or modifying the connection state. This allows an * skb->_nfct lost due to an upcall to be recovered during actions execution. * * Must be called with rcu_read_lock. * * On success, populates skb->_nfct and returns the connection. Returns NULL * if there is no existing entry. */static struct nf_conn *ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 l3num, struct sk_buff *skb, bool natted){ struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, net, &tuple)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); return NULL;Lines 1–500 of 2063. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Nicira, Inc. */ #include <linux/module.h> #include <linux/openvswitch.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/static_key.h> #include <linux/string_helpers.h> #include <net/ip.h> #include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_count.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/ipv6_frag.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #endif #include <net/netfilter/nf_conntrack_act_ct.h> #include "datapath.h" #include "drop.h" #include "conntrack.h" #include "flow.h" #include "flow_netlink.h" struct ovs_ct_len_tbl { int maxlen; int minlen; }; /* Metadata mark for masked write to conntrack mark */ struct md_mark { u32 value; u32 mask; }; /* Metadata label for masked write to conntrack label. */ struct md_labels { struct ovs_key_ct_labels value; struct ovs_key_ct_labels mask; }; enum ovs_ct_nat { OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */ OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */ OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */ }; /* Conntrack action context for execution. */ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ u8 force : 1; u8 have_eventmask : 1; u16 family; u32 eventmask; /* Mask of 1 << IPCT_*. */ struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; struct nf_ct_timeout *nf_ct_timeout; #if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif }; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) #define OVS_CT_LIMIT_UNLIMITED 0 #define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED #define CT_LIMIT_HASH_BUCKETS 512 static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled); struct ovs_ct_limit { /* Elements in ovs_ct_limit_info->limits hash table */ struct hlist_node hlist_node; struct rcu_head rcu; u16 zone; u32 limit; }; struct ovs_ct_limit_info { u32 default_limit; struct hlist_head *limits; struct nf_conncount_data *data; }; static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = { [OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, }, }; #endif static bool labels_nonzero(const struct ovs_key_ct_labels *labels); static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); static u16 key_to_nfproto(const struct sw_flow_key *key) { switch (ntohs(key->eth.type)) { case ETH_P_IP: return NFPROTO_IPV4; case ETH_P_IPV6: return NFPROTO_IPV6; default: return NFPROTO_UNSPEC; } } /* Map SKB connection state into the values used by flow definition. */ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) { u8 ct_state = OVS_CS_F_TRACKED; switch (ctinfo) { case IP_CT_ESTABLISHED_REPLY: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_REPLY_DIR; break; default: break; } switch (ctinfo) { case IP_CT_ESTABLISHED: case IP_CT_ESTABLISHED_REPLY: ct_state |= OVS_CS_F_ESTABLISHED; break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_RELATED; break; case IP_CT_NEW: ct_state |= OVS_CS_F_NEW; break; default: break; } return ct_state; } static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif } /* Guard against conntrack labels max size shrinking below 128 bits. */ #if NF_CT_LABELS_MAX_SIZE < 16 #error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes #endif static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = NULL; if (ct) { if (ct->master && !nf_ct_is_confirmed(ct)) ct = ct->master; cl = nf_ct_labels_find(ct); } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else memset(labels, 0, OVS_CT_LABELS_LEN); } static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, const struct nf_conntrack_tuple *orig, u8 icmp_proto) { key->ct_orig_proto = orig->dst.protonum; if (orig->dst.protonum == icmp_proto) { key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); } else { key->ct.orig_tp.src = orig->src.u.all; key->ct.orig_tp.dst = orig->dst.u.all; } } static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct) { key->ct_state = state; key->ct_zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels); if (ct) { const struct nf_conntrack_tuple *orig; /* Use the master if we have one. */ if (ct->master) ct = ct->master; orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* IP version must match with the master connection. */ if (key->eth.type == htons(ETH_P_IP) && nf_ct_l3num(ct) == NFPROTO_IPV4) { key->ipv4.ct_orig.src = orig->src.u3.ip; key->ipv4.ct_orig.dst = orig->dst.u3.ip; __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); return; } else if (key->eth.type == htons(ETH_P_IPV6) && !sw_flow_key_is_nd(key) && nf_ct_l3num(ct) == NFPROTO_IPV6) { key->ipv6.ct_orig.src = orig->src.u3.in6; key->ipv6.ct_orig.dst = orig->dst.u3.in6; __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); return; } } /* Clear 'ct_orig_proto' to mark the non-existence of conntrack * original direction key fields. */ key->ct_orig_proto = 0; } /* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has * previously sent the packet to conntrack via the ct action. If * 'keep_nat_flags' is true, the existing NAT flags retained, else they are * initialized from the connection status. */ static void ovs_ct_update_key(const struct sk_buff *skb, const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct, bool keep_nat_flags) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; struct nf_conn *ct; u8 state = 0; ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); /* All unconfirmed entries are NEW connections. */ if (!nf_ct_is_confirmed(ct)) state |= OVS_CS_F_NEW; /* OVS persists the related flag for the duration of the * connection. */ if (ct->master) state |= OVS_CS_F_RELATED; if (keep_nat_flags) { state |= key->ct_state & OVS_CS_F_NAT_MASK; } else { if (ct->status & IPS_SRC_NAT) state |= OVS_CS_F_SRC_NAT; if (ct->status & IPS_DST_NAT) state |= OVS_CS_F_DST_NAT; } zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; if (info) zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct); } /* This is called to initialize CT key fields possibly coming in from the local * stack. */ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key, bool post_ct) { ovs_ct_update_key(skb, NULL, key, post_ct, false); } int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), &output->ct.labels)) return -EMSGSIZE; if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ct_tuple_ipv4 orig; memset(&orig, 0, sizeof(orig)); orig.ipv4_src = output->ipv4.ct_orig.src; orig.ipv4_dst = output->ipv4.ct_orig.dst; orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv4_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ct_tuple_ipv6 orig; memset(&orig, 0, sizeof(orig)); memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, sizeof(orig.ipv6_src)); memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, sizeof(orig.ipv6_dst)); orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv6_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; } } return 0; } static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, u32 ct_mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; } return 0; #else return -ENOTSUPP; #endif } static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct) { struct nf_conn_labels *cl; cl = nf_ct_labels_find(ct); if (!cl) { nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } return cl; } /* Initialize labels for a new, yet to be committed conntrack entry. Note that * since the new connection is not yet confirmed, and thus no-one else has * access to it's labels, we simply write them over. */ static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask) { struct nf_conn_labels *cl, *master_cl; bool have_mask = labels_nonzero(mask); /* Inherit master's labels to the related connection? */ master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL; if (!master_cl && !have_mask) return 0; /* Nothing to do. */ cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; /* Inherit the master's labels, if any. */ if (master_cl) *cl = *master_cl; if (have_mask) { u32 *dst = (u32 *)cl->bits; int i; for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) dst[i] = (dst[i] & ~mask->ct_labels_32[i]) | (labels->ct_labels_32[i] & mask->ct_labels_32[i]); } /* Labels are included in the IPCTNL_MSG_CT_NEW event only if the * IPCT_LABEL bit is set in the event cache. */ nf_conntrack_event_cache(IPCT_LABEL, ct); memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0; } static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask) { struct nf_conn_labels *cl; int err; cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; err = nf_connlabels_replace(ct, labels->ct_labels_32, mask->ct_labels_32, OVS_CT_LABELS_LEN_32); if (err) return err; memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0; } static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, int family, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); if (err) return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); key->ip.frag = OVS_FRAG_TYPE_NONE; *OVS_CB(skb) = ovs_cb; return 0; } /* This replicates logic from nf_conntrack_core.c that is not exported. */ static enum ip_conntrack_info ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h) { const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) return IP_CT_ESTABLISHED_REPLY; /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) return IP_CT_ESTABLISHED; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) return IP_CT_RELATED; return IP_CT_NEW; } /* Find an existing connection which this packet belongs to without * re-attributing statistics or modifying the connection state. This allows an * skb->_nfct lost due to an upcall to be recovered during actions execution. * * Must be called with rcu_read_lock. * * On success, populates skb->_nfct and returns the connection. Returns NULL * if there is no existing entry. */ static struct nf_conn * ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 l3num, struct sk_buff *skb, bool natted) { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, net, &tuple)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); return NULL;