diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 6 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 12 | ||||
-rw-r--r-- | net/ipv4/fib_lookup.h | 1 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 650 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 33 | ||||
-rw-r--r-- | net/ipv4/fou.c | 142 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 7 | ||||
-rw-r--r-- | net/ipv4/route.c | 82 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 17 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 49 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 12 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 11 | ||||
-rw-r--r-- | net/ipv4/tcp_metrics.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 8 |
15 files changed, 643 insertions, 399 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eab3ebde981e..08a8430f5647 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -136,6 +136,10 @@ void inet_sock_destruct(struct sock *sk) struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); + if (sk->sk_rx_skb_cache) { + __kfree_skb(sk->sk_rx_skb_cache); + sk->sk_rx_skb_cache = NULL; + } __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim(sk); @@ -156,7 +160,7 @@ void inet_sock_destruct(struct sock *sk) WARN_ON(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); - dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); + dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(sk->sk_rx_dst); sk_refcnt_debug_dec(sk); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ed14ec245584..15f779bd26b3 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -307,7 +307,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) - return FIB_RES_PREFSRC(net, res); + return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } @@ -324,16 +324,16 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) for (ret = 0; ret < fi->fib_nhs; ret++) { struct fib_nh *nh = &fi->fib_nh[ret]; - if (nh->nh_dev == dev) { + if (nh->fib_nh_dev == dev) { dev_match = true; break; - } else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + } else if (l3mdev_master_ifindex_rcu(nh->fib_nh_dev) == dev->ifindex) { dev_match = true; break; } } #else - if (fi->fib_nh[0].nh_dev == dev) + if (fi->fib_nh[0].fib_nh_dev == dev) dev_match = true; #endif @@ -390,7 +390,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dev_match = fib_info_nh_uses_dev(res.fi, dev); if (dev_match) { - ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) @@ -402,7 +402,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) - ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index e6ff282bb7f4..7945f0534db7 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -45,6 +45,7 @@ static inline void fib_result_assign(struct fib_result *res, { /* we used to play games with refcounts, but we now use RCU */ res->fi = fi; + res->nhc = fib_info_nhc(fi, 0); } struct fib_prop { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 8e185b5a2bf6..8e0cb1687a74 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -45,6 +45,7 @@ #include <net/nexthop.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> +#include <net/addrconf.h> #include "fib_lookup.h" @@ -204,18 +205,34 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) free_percpu(rtp); } +void fib_nh_common_release(struct fib_nh_common *nhc) +{ + if (nhc->nhc_dev) + dev_put(nhc->nhc_dev); + + lwtstate_put(nhc->nhc_lwtstate); +} +EXPORT_SYMBOL_GPL(fib_nh_common_release); + +void fib_nh_release(struct net *net, struct fib_nh *fib_nh) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + if (fib_nh->nh_tclassid) + net->ipv4.fib_num_tclassid_users--; +#endif + fib_nh_common_release(&fib_nh->nh_common); + free_nh_exceptions(fib_nh); + rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output); + rt_fibinfo_free(&fib_nh->nh_rth_input); +} + /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); change_nexthops(fi) { - if (nexthop_nh->nh_dev) - dev_put(nexthop_nh->nh_dev); - lwtstate_put(nexthop_nh->nh_lwtstate); - free_nh_exceptions(nexthop_nh); - rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); - rt_fibinfo_free(&nexthop_nh->nh_rth_input); + fib_nh_release(fi->fib_net, nexthop_nh); } endfor_nexthops(fi); ip_fib_metrics_put(fi->fib_metrics); @@ -230,12 +247,7 @@ void free_fib_info(struct fib_info *fi) return; } fib_info_cnt--; -#ifdef CONFIG_IP_ROUTE_CLASSID - change_nexthops(fi) { - if (nexthop_nh->nh_tclassid) - fi->fib_net->ipv4.fib_num_tclassid_users--; - } endfor_nexthops(fi); -#endif + call_rcu(&fi->rcu, free_fib_info_rcu); } EXPORT_SYMBOL_GPL(free_fib_info); @@ -248,7 +260,7 @@ void fib_release_info(struct fib_info *fi) if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); change_nexthops(fi) { - if (!nexthop_nh->nh_dev) + if (!nexthop_nh->fib_nh_dev) continue; hlist_del(&nexthop_nh->nh_hash); } endfor_nexthops(fi) @@ -263,17 +275,17 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) const struct fib_nh *onh = ofi->fib_nh; for_nexthops(fi) { - if (nh->nh_oif != onh->nh_oif || - nh->nh_gw != onh->nh_gw || - nh->nh_scope != onh->nh_scope || + if (nh->fib_nh_oif != onh->fib_nh_oif || + nh->fib_nh_gw4 != onh->fib_nh_gw4 || + nh->fib_nh_scope != onh->fib_nh_scope || #ifdef CONFIG_IP_ROUTE_MULTIPATH - nh->nh_weight != onh->nh_weight || + nh->fib_nh_weight != onh->fib_nh_weight || #endif #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif - lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) || - ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK)) + lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) || + ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK)) return -1; onh++; } endfor_nexthops(fi); @@ -298,7 +310,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) val ^= (__force u32)fi->fib_prefsrc; val ^= fi->fib_priority; for_nexthops(fi) { - val ^= fib_devindex_hashfn(nh->nh_oif); + val ^= fib_devindex_hashfn(nh->fib_nh_oif); } endfor_nexthops(fi) return (val ^ (val >> 7) ^ (val >> 12)) & mask; @@ -347,9 +359,9 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; hlist_for_each_entry(nh, head, nh_hash) { - if (nh->nh_dev == dev && - nh->nh_gw == gw && - !(nh->nh_flags & RTNH_F_DEAD)) { + if (nh->fib_nh_dev == dev && + nh->fib_nh_gw4 == gw && + !(nh->fib_nh_flags & RTNH_F_DEAD)) { spin_unlock(&fib_info_lock); return 0; } @@ -384,10 +396,10 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) /* grab encap info */ for_nexthops(fi) { - if (nh->nh_lwtstate) { + if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ nh_encapsize += lwtunnel_get_encap_size( - nh->nh_lwtstate); + nh->fib_nh_lws); /* RTA_ENCAP */ nh_encapsize += nla_total_size(2); } @@ -438,7 +450,7 @@ static int fib_detect_death(struct fib_info *fi, int order, struct neighbour *n; int state = NUD_NONE; - n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev); + n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].fib_nh_gw4, fi->fib_dev); if (n) { state = n->nud_state; neigh_release(n); @@ -457,6 +469,71 @@ static int fib_detect_death(struct fib_info *fi, int order, return 1; } +int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap, + u16 encap_type, void *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack) +{ + if (encap) { + struct lwtunnel_state *lwtstate; + int err; + + if (encap_type == LWTUNNEL_ENCAP_NONE) { + NL_SET_ERR_MSG(extack, "LWT encap type not specified"); + return -EINVAL; + } + err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family, + cfg, &lwtstate, extack); + if (err) + return err; + + nhc->nhc_lwtstate = lwtstate_get(lwtstate); + } + + return 0; +} +EXPORT_SYMBOL_GPL(fib_nh_common_init); + +int fib_nh_init(struct net *net, struct fib_nh *nh, + struct fib_config *cfg, int nh_weight, + struct netlink_ext_ack *extack) +{ + int err = -ENOMEM; + + nh->fib_nh_family = AF_INET; + + nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); + if (!nh->nh_pcpu_rth_output) + goto err_out; + + err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap, + cfg->fc_encap_type, cfg, GFP_KERNEL, extack); + if (err) + goto init_failure; + + nh->fib_nh_oif = cfg->fc_oif; + if (cfg->fc_gw) { + nh->fib_nh_gw4 = cfg->fc_gw; + nh->fib_nh_has_gw = 1; + } + nh->fib_nh_flags = cfg->fc_flags; + +#ifdef CONFIG_IP_ROUTE_CLASSID + nh->nh_tclassid = cfg->fc_flow; + if (nh->nh_tclassid) + net->ipv4.fib_num_tclassid_users++; +#endif +#ifdef CONFIG_IP_ROUTE_MULTIPATH + nh->fib_nh_weight = nh_weight; +#endif + return 0; + +init_failure: + rt_fibinfo_free_cpus(nh->nh_pcpu_rth_output); + nh->nh_pcpu_rth_output = NULL; +err_out: + return err; +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, @@ -483,11 +560,15 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, struct netlink_ext_ack *extack) { + struct net *net = fi->fib_net; + struct fib_config fib_cfg; int ret; change_nexthops(fi) { int attrlen; + memset(&fib_cfg, 0, sizeof(fib_cfg)); + if (!rtnh_ok(rtnh, remaining)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - extra data after nexthop"); @@ -500,56 +581,54 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, return -EINVAL; } - nexthop_nh->nh_flags = - (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; - nexthop_nh->nh_oif = rtnh->rtnh_ifindex; - nexthop_nh->nh_weight = rtnh->rtnh_hops + 1; + fib_cfg.fc_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; + fib_cfg.fc_oif = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0; -#ifdef CONFIG_IP_ROUTE_CLASSID + if (nla) + fib_cfg.fc_gw = nla_get_in_addr(nla); + nla = nla_find(attrs, attrlen, RTA_FLOW); - nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; - if (nexthop_nh->nh_tclassid) - fi->fib_net->ipv4.fib_num_tclassid_users++; -#endif - nla = nla_find(attrs, attrlen, RTA_ENCAP); - if (nla) { - struct lwtunnel_state *lwtstate; - struct nlattr *nla_entype; - - nla_entype = nla_find(attrs, attrlen, - RTA_ENCAP_TYPE); - if (!nla_entype) { - NL_SET_BAD_ATTR(extack, nla); - NL_SET_ERR_MSG(extack, - "Encap type is missing"); - goto err_inval; - } + if (nla) + fib_cfg.fc_flow = nla_get_u32(nla); - ret = lwtunnel_build_state(nla_get_u16( - nla_entype), - nla, AF_INET, cfg, - &lwtstate, extack); - if (ret) - goto errout; - nexthop_nh->nh_lwtstate = - lwtstate_get(lwtstate); - } + fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + if (nla) + fib_cfg.fc_encap_type = nla_get_u16(nla); } + ret = fib_nh_init(net, nexthop_nh, &fib_cfg, + rtnh->rtnh_hops + 1, extack); + if (ret) + goto errout; + rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); - return 0; - -err_inval: ret = -EINVAL; - + if (cfg->fc_oif && fi->fib_nh->fib_nh_oif != cfg->fc_oif) { + NL_SET_ERR_MSG(extack, + "Nexthop device index does not match RTA_OIF"); + goto errout; + } + if (cfg->fc_gw && fi->fib_nh->fib_nh_gw4 != cfg->fc_gw) { + NL_SET_ERR_MSG(extack, + "Nexthop gateway does not match RTA_GATEWAY"); + goto errout; + } +#ifdef CONFIG_IP_ROUTE_CLASSID + if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) { + NL_SET_ERR_MSG(extack, + "Nexthop class id does not match RTA_FLOW"); + goto errout; + } +#endif + ret = 0; errout: return ret; } @@ -558,49 +637,51 @@ static void fib_rebalance(struct fib_info *fi) { int total; int w; - struct in_device *in_dev; if (fi->fib_nhs < 2) return; total = 0; for_nexthops(fi) { - if (nh->nh_flags & RTNH_F_DEAD) + if (nh->fib_nh_flags & RTNH_F_DEAD) continue; - in_dev = __in_dev_get_rtnl(nh->nh_dev); - - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - nh->nh_flags & RTNH_F_LINKDOWN) + if (ip_ignore_linkdown(nh->fib_nh_dev) && + nh->fib_nh_flags & RTNH_F_LINKDOWN) continue; - total += nh->nh_weight; + total += nh->fib_nh_weight; } endfor_nexthops(fi); w = 0; change_nexthops(fi) { int upper_bound; - in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev); - - if (nexthop_nh->nh_flags & RTNH_F_DEAD) { + if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; - } else if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - nexthop_nh->nh_flags & RTNH_F_LINKDOWN) { + } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && + nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { upper_bound = -1; } else { - w += nexthop_nh->nh_weight; + w += nexthop_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; } - atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); + atomic_set(&nexthop_nh->fib_nh_upper_bound, upper_bound); } endfor_nexthops(fi); } #else /* CONFIG_IP_ROUTE_MULTIPATH */ +static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, + int remaining, struct fib_config *cfg, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Multipath support not enabled in kernel"); + + return -EINVAL; +} + #define fib_rebalance(fi) do { } while (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -620,7 +701,7 @@ static int fib_encap_match(u16 encap_type, ret = lwtunnel_build_state(encap_type, encap, AF_INET, cfg, &lwtstate, extack); if (!ret) { - result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); + result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws); lwtstate_free(lwtstate); } @@ -649,8 +730,8 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, cfg->fc_flow != fi->fib_nh->nh_tclassid) return 1; #endif - if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && - (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) + if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->fib_nh_oif) && + (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->fib_nh_gw4)) return 0; return 1; } @@ -668,7 +749,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif) + if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->fib_nh_oif) return 1; attrlen = rtnh_attrlen(rtnh); @@ -676,7 +757,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - if (nla && nla_get_in_addr(nla) != nh->nh_gw) + if (nla && nla_get_in_addr(nla) != nh->fib_nh_gw4) return 1; #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); @@ -783,10 +864,10 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, struct net_device *dev; net = cfg->fc_nlinfo.nl_net; - if (nh->nh_gw) { + if (nh->fib_nh_gw4) { struct fib_result res; - if (nh->nh_flags & RTNH_F_ONLINK) { + if (nh->fib_nh_flags & RTNH_F_ONLINK) { unsigned int addr_type; if (cfg->fc_scope >= RT_SCOPE_LINK) { @@ -794,7 +875,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, "Nexthop has invalid scope"); return -EINVAL; } - dev = __dev_get_by_index(net, nh->nh_oif); + dev = __dev_get_by_index(net, nh->fib_nh_oif); if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); return -ENODEV; @@ -804,26 +885,27 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, "Nexthop device is not up"); return -ENETDOWN; } - addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); + addr_type = inet_addr_type_dev_table(net, dev, + nh->fib_nh_gw4); if (addr_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); return -EINVAL; } if (!netif_carrier_ok(dev)) - nh->nh_flags |= RTNH_F_LINKDOWN; - nh->nh_dev = dev; + nh->fib_nh_flags |= RTNH_F_LINKDOWN; + nh->fib_nh_dev = dev; dev_hold(dev); - nh->nh_scope = RT_SCOPE_LINK; + nh->fib_nh_scope = RT_SCOPE_LINK; return 0; } rcu_read_lock(); { struct fib_table *tbl = NULL; struct flowi4 fl4 = { - .daddr = nh->nh_gw, + .daddr = nh->fib_nh_gw4, .flowi4_scope = cfg->fc_scope + 1, - .flowi4_oif = nh->nh_oif, + .flowi4_oif = nh->fib_nh_oif, .flowi4_iif = LOOPBACK_IFINDEX, }; @@ -860,9 +942,9 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); goto out; } - nh->nh_scope = res.scope; - nh->nh_oif = FIB_RES_OIF(res); - nh->nh_dev = dev = FIB_RES_DEV(res); + nh->fib_nh_scope = res.scope; + nh->fib_nh_oif = FIB_RES_OIF(res); + nh->fib_nh_dev = dev = FIB_RES_DEV(res); if (!dev) { NL_SET_ERR_MSG(extack, "No egress device for nexthop gateway"); @@ -870,19 +952,19 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, } dev_hold(dev); if (!netif_carrier_ok(dev)) - nh->nh_flags |= RTNH_F_LINKDOWN; + nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; } else { struct in_device *in_dev; - if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) { + if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) { NL_SET_ERR_MSG(extack, "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set"); return -EINVAL; } rcu_read_lock(); err = -ENODEV; - in_dev = inetdev_by_index(net, nh->nh_oif); + in_dev = inetdev_by_index(net, nh->fib_nh_oif); if (!in_dev) goto out; err = -ENETDOWN; @@ -890,11 +972,11 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, NL_SET_ERR_MSG(extack, "Device for nexthop is not up"); goto out; } - nh->nh_dev = in_dev->dev; - dev_hold(nh->nh_dev); - nh->nh_scope = RT_SCOPE_HOST; - if (!netif_carrier_ok(nh->nh_dev)) - nh->nh_flags |= RTNH_F_LINKDOWN; + nh->fib_nh_dev = in_dev->dev; + dev_hold(nh->fib_nh_dev); + nh->fib_nh_scope = RT_SCOPE_HOST; + if (!netif_carrier_ok(nh->fib_nh_dev)) + nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; } out: @@ -986,14 +1068,29 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) { - nh->nh_saddr = inet_select_addr(nh->nh_dev, - nh->nh_gw, + nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, + nh->fib_nh_gw4, nh->nh_parent->fib_scope); nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); return nh->nh_saddr; } +__be32 fib_result_prefsrc(struct net *net, struct fib_result *res) +{ + struct fib_nh_common *nhc = res->nhc; + struct fib_nh *nh; + + if (res->fi->fib_prefsrc) + return res->fi->fib_prefsrc; + + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) + return nh->nh_saddr; + + return fib_info_update_nh_saddr(net, nh); +} + static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) { if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || @@ -1096,69 +1193,15 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi->fib_nhs = nhs; change_nexthops(fi) { nexthop_nh->nh_parent = fi; - nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); - if (!nexthop_nh->nh_pcpu_rth_output) - goto failure; } endfor_nexthops(fi) - if (cfg->fc_mp) { -#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (cfg->fc_mp) err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); - if (err != 0) - goto failure; - if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) { - NL_SET_ERR_MSG(extack, - "Nexthop device index does not match RTA_OIF"); - goto err_inval; - } - if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) { - NL_SET_ERR_MSG(extack, - "Nexthop gateway does not match RTA_GATEWAY"); - goto err_inval; - } -#ifdef CONFIG_IP_ROUTE_CLASSID - if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) { - NL_SET_ERR_MSG(extack, - "Nexthop class id does not match RTA_FLOW"); - goto err_inval; - } -#endif -#else - NL_SET_ERR_MSG(extack, - "Multipath support not enabled in kernel"); - goto err_inval; -#endif - } else { - struct fib_nh *nh = fi->fib_nh; - - if (cfg->fc_encap) { - struct lwtunnel_state *lwtstate; - - if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) { - NL_SET_ERR_MSG(extack, - "LWT encap type not specified"); - goto err_inval; - } - err = lwtunnel_build_state(cfg->fc_encap_type, - cfg->fc_encap, AF_INET, cfg, - &lwtstate, extack); - if (err) - goto failure; + else + err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack); - nh->nh_lwtstate = lwtstate_get(lwtstate); - } - nh->nh_oif = cfg->fc_oif; - nh->nh_gw = cfg->fc_gw; - nh->nh_flags = cfg->fc_flags; -#ifdef CONFIG_IP_ROUTE_CLASSID - nh->nh_tclassid = cfg->fc_flow; - if (nh->nh_tclassid) - fi->fib_net->ipv4.fib_num_tclassid_users++; -#endif -#ifdef CONFIG_IP_ROUTE_MULTIPATH - nh->nh_weight = 1; -#endif - } + if (err != 0) + goto failure; if (fib_props[cfg->fc_type].error) { if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) { @@ -1195,15 +1238,15 @@ struct fib_info *fib_create_info(struct fib_config *cfg, "Route with host scope can not have multiple nexthops"); goto err_inval; } - if (nh->nh_gw) { + if (nh->fib_nh_gw4) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); goto err_inval; } - nh->nh_scope = RT_SCOPE_NOWHERE; - nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); + nh->fib_nh_scope = RT_SCOPE_NOWHERE; + nh->fib_nh_dev = dev_get_by_index(net, fi->fib_nh->fib_nh_oif); err = -ENODEV; - if (!nh->nh_dev) + if (!nh->fib_nh_dev) goto failure; } else { int linkdown = 0; @@ -1212,7 +1255,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, err = fib_check_nh(cfg, nexthop_nh, extack); if (err != 0) goto failure; - if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) + if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) linkdown++; } endfor_nexthops(fi) if (linkdown == fi->fib_nhs) @@ -1254,9 +1297,9 @@ link_it: struct hlist_head *head; unsigned int hash; - if (!nexthop_nh->nh_dev) + if (!nexthop_nh->fib_nh_dev) continue; - hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex); + hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex); head = &fib_info_devhash[hash]; hlist_add_head(&nexthop_nh->nh_hash, head); } endfor_nexthops(fi) @@ -1275,6 +1318,126 @@ failure: return ERR_PTR(err); } +int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, + unsigned int *flags, bool skip_oif) +{ + if (nhc->nhc_flags & RTNH_F_DEAD) + *flags |= RTNH_F_DEAD; + + if (nhc->nhc_flags & RTNH_F_LINKDOWN) { + *flags |= RTNH_F_LINKDOWN; + + rcu_read_lock(); + switch (nhc->nhc_family) { + case AF_INET: + if (ip_ignore_linkdown(nhc->nhc_dev)) + *flags |= RTNH_F_DEAD; + break; + case AF_INET6: + if (ip6_ignore_linkdown(nhc->nhc_dev)) + *flags |= RTNH_F_DEAD; + break; + } + rcu_read_unlock(); + } + + if (nhc->nhc_has_gw) { + switch (nhc->nhc_family) { + case AF_INET: + if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4)) + goto nla_put_failure; + break; + case AF_INET6: + if (nla_put_in6_addr(skb, RTA_GATEWAY, + &nhc->nhc_gw.ipv6) < 0) + goto nla_put_failure; + break; + } + } + + *flags |= (nhc->nhc_flags & RTNH_F_ONLINK); + if (nhc->nhc_flags & RTNH_F_OFFLOAD) + *flags |= RTNH_F_OFFLOAD; + + if (!skip_oif && nhc->nhc_dev && + nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex)) + goto nla_put_failure; + + if (nhc->nhc_lwtstate && + lwtunnel_fill_encap(skb, nhc->nhc_lwtstate) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(fib_nexthop_info); + +#if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) +int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, + int nh_weight) +{ + const struct net_device *dev = nhc->nhc_dev; + struct rtnexthop *rtnh; + unsigned int flags = 0; + + rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); + if (!rtnh) + goto nla_put_failure; + + rtnh->rtnh_hops = nh_weight - 1; + rtnh->rtnh_ifindex = dev ? dev->ifindex : 0; + + if (fib_nexthop_info(skb, nhc, &flags, true) < 0) + goto nla_put_failure; + + rtnh->rtnh_flags = flags; + + /* length of rtnetlink header + attributes */ + rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(fib_add_nexthop); +#endif + +#ifdef CONFIG_IP_ROUTE_MULTIPATH +static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) +{ + struct nlattr *mp; + + mp = nla_nest_start(skb, RTA_MULTIPATH); + if (!mp) + goto nla_put_failure; + + for_nexthops(fi) { + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight) < 0) + goto nla_put_failure; +#ifdef CONFIG_IP_ROUTE_CLASSID + if (nh->nh_tclassid && + nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) + goto nla_put_failure; +#endif + } endfor_nexthops(fi); + + nla_nest_end(skb, mp); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} +#else +static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) +{ + return 0; +} +#endif + int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) @@ -1315,80 +1478,23 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc)) goto nla_put_failure; if (fi->fib_nhs == 1) { - if (fi->fib_nh->nh_gw && - nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) - goto nla_put_failure; - if (fi->fib_nh->nh_oif && - nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) + struct fib_nh *nh = &fi->fib_nh[0]; + unsigned int flags = 0; + + if (fib_nexthop_info(skb, &nh->nh_common, &flags, false) < 0) goto nla_put_failure; - if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev); - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) - rtm->rtm_flags |= RTNH_F_DEAD; - rcu_read_unlock(); - } - if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD) - rtm->rtm_flags |= RTNH_F_OFFLOAD; + + rtm->rtm_flags = flags; #ifdef CONFIG_IP_ROUTE_CLASSID - if (fi->fib_nh[0].nh_tclassid && - nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) + if (nh->nh_tclassid && + nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif - if (fi->fib_nh->nh_lwtstate && - lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0) + } else { + if (fib_add_multipath(skb, fi) < 0) goto nla_put_failure; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - if (fi->fib_nhs > 1) { - struct rtnexthop *rtnh; - struct nlattr *mp; - - mp = nla_nest_start(skb, RTA_MULTIPATH); - if (!mp) - goto nla_put_failure; - - for_nexthops(fi) { - rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); - if (!rtnh) - goto nla_put_failure; - - rtnh->rtnh_flags = nh->nh_flags & 0xFF; - if (nh->nh_flags & RTNH_F_LINKDOWN) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(nh->nh_dev); - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) - rtnh->rtnh_flags |= RTNH_F_DEAD; - rcu_read_unlock(); - } - rtnh->rtnh_hops = nh->nh_weight - 1; - rtnh->rtnh_ifindex = nh->nh_oif; - - if (nh->nh_gw && - nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw)) - goto nla_put_failure; -#ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; -#endif - if (nh->nh_lwtstate && - lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0) - goto nla_put_failure; - /* length of rtnetlink header + attributes */ - rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; - } endfor_nexthops(fi); - - nla_nest_end(skb, mp); - } -#endif nlmsg_end(skb, nlh); return 0; @@ -1427,28 +1533,26 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) return ret; } -static int call_fib_nh_notifiers(struct fib_nh *fib_nh, +static int call_fib_nh_notifiers(struct fib_nh *nh, enum fib_event_type event_type) { - struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev); + bool ignore_link_down = ip_ignore_linkdown(nh->fib_nh_dev); struct fib_nh_notifier_info info = { - .fib_nh = fib_nh, + .fib_nh = nh, }; switch (event_type) { case FIB_EVENT_NH_ADD: - if (fib_nh->nh_flags & RTNH_F_DEAD) + if (nh->fib_nh_flags & RTNH_F_DEAD) break; - if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->nh_flags & RTNH_F_LINKDOWN) + if (ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) break; - return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type, + return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type, &info.info); case FIB_EVENT_NH_DEL: - if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->nh_flags & RTNH_F_LINKDOWN) || - (fib_nh->nh_flags & RTNH_F_DEAD)) - return call_fib4_notifiers(dev_net(fib_nh->nh_dev), + if ((ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) || + (nh->fib_nh_flags & RTNH_F_DEAD)) + return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type, &info.info); default: break; @@ -1502,7 +1606,7 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) struct fib_nh *nh; hlist_for_each_entry(nh, head, nh_hash) { - if (nh->nh_dev == dev) + if (nh->fib_nh_dev == dev) nh_update_mtu(nh, dev->mtu, orig_mtu); } } @@ -1530,22 +1634,22 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) int dead; BUG_ON(!fi->fib_nhs); - if (nh->nh_dev != dev || fi == prev_fi) + if (nh->fib_nh_dev != dev || fi == prev_fi) continue; prev_fi = fi; dead = 0; change_nexthops(fi) { - if (nexthop_nh->nh_flags & RTNH_F_DEAD) + if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) dead++; - else if (nexthop_nh->nh_dev == dev && - nexthop_nh->nh_scope != scope) { + else if (nexthop_nh->fib_nh_dev == dev && + nexthop_nh->fib_nh_scope != scope) { switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: - nexthop_nh->nh_flags |= RTNH_F_DEAD; + nexthop_nh->fib_nh_flags |= RTNH_F_DEAD; /* fall through */ case NETDEV_CHANGE: - nexthop_nh->nh_flags |= RTNH_F_LINKDOWN; + nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN; break; } call_fib_nh_notifiers(nexthop_nh, @@ -1554,7 +1658,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (event == NETDEV_UNREGISTER && - nexthop_nh->nh_dev == dev) { + nexthop_nh->fib_nh_dev == dev) { dead = fi->fib_nhs; break; } @@ -1614,8 +1718,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; - if (!next_fi->fib_nh[0].nh_gw || - next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) + if (!next_fi->fib_nh[0].fib_nh_gw4 || + next_fi->fib_nh[0].fib_nh_scope != RT_SCOPE_LINK) continue; fib_alias_accessed(fa); @@ -1686,24 +1790,24 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) int alive; BUG_ON(!fi->fib_nhs); - if (nh->nh_dev != dev || fi == prev_fi) + if (nh->fib_nh_dev != dev || fi == prev_fi) continue; prev_fi = fi; alive = 0; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags & nh_flags)) { + if (!(nexthop_nh->fib_nh_flags & nh_flags)) { alive++; continue; } - if (!nexthop_nh->nh_dev || - !(nexthop_nh->nh_dev->flags & IFF_UP)) + if (!nexthop_nh->fib_nh_dev || + !(nexthop_nh->fib_nh_dev->flags & IFF_UP)) continue; - if (nexthop_nh->nh_dev != dev || + if (nexthop_nh->fib_nh_dev != dev || !__in_dev_get_rtnl(dev)) continue; alive++; - nexthop_nh->nh_flags &= ~nh_flags; + nexthop_nh->fib_nh_flags &= ~nh_flags; call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD); } endfor_nexthops(fi) @@ -1723,13 +1827,13 @@ static bool fib_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; - if (nh->nh_scope == RT_SCOPE_LINK) { + if (nh->fib_nh_scope == RT_SCOPE_LINK) { struct neighbour *n; rcu_read_lock_bh(); - n = __ipv4_neigh_lookup_noref(nh->nh_dev, - (__force u32)nh->nh_gw); + n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, + (__force u32)nh->fib_nh_gw4); if (n) state = n->nud_state; @@ -1745,20 +1849,22 @@ void fib_select_multipath(struct fib_result *res, int hash) struct net *net = fi->fib_net; bool first = false; - for_nexthops(fi) { + change_nexthops(fi) { if (net->ipv4.sysctl_fib_multipath_use_neigh) { - if (!fib_good_nh(nh)) + if (!fib_good_nh(nexthop_nh)) continue; if (!first) { res->nh_sel = nhsel; + res->nhc = &nexthop_nh->nh_common; first = true; } } - if (hash > atomic_read(&nh->nh_upper_bound)) + if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound)) continue; res->nh_sel = nhsel; + res->nhc = &nexthop_nh->nh_common; return; } endfor_nexthops(fi); } @@ -1785,5 +1891,5 @@ void fib_select_path(struct net *net, struct fib_result *res, check_saddr: if (!fl4->saddr) - fl4->saddr = FIB_RES_PREFSRC(net, *res); + fl4->saddr = fib_result_prefsrc(net, res); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index a573e37e0615..334f723bdf80 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -183,14 +183,16 @@ struct trie { }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); -static size_t tnode_free_size; +static unsigned int tnode_free_size; /* - * synchronize_rcu after call_rcu for that many pages; it should be especially - * useful before resizing the root node with PREEMPT_NONE configs; the value was - * obtained experimentally, aiming to avoid visible slowdown. + * synchronize_rcu after call_rcu for outstanding dirty memory; it should be + * especially useful before resizing the root node with PREEMPT_NONE configs; + * the value was obtained experimentally, aiming to avoid visible slowdown. */ -static const int sync_pages = 128; +unsigned int sysctl_fib_sync_mem = 512 * 1024; +unsigned int sysctl_fib_sync_mem_min = 64 * 1024; +unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; @@ -504,7 +506,7 @@ static void tnode_free(struct key_vector *tn) tn = container_of(head, struct tnode, rcu)->kv; } - if (tnode_free_size >= PAGE_SIZE * sync_pages) { + if (tnode_free_size >= sysctl_fib_sync_mem) { tnode_free_size = 0; synchronize_rcu(); } @@ -1468,19 +1470,17 @@ found: if (fi->fib_flags & RTNH_F_DEAD) continue; for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { - const struct fib_nh *nh = &fi->fib_nh[nhsel]; - struct in_device *in_dev = __in_dev_get_rcu(nh->nh_dev); + struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); - if (nh->nh_flags & RTNH_F_DEAD) + if (nhc->nhc_flags & RTNH_F_DEAD) continue; - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - nh->nh_flags & RTNH_F_LINKDOWN && + if (ip_ignore_linkdown(nhc->nhc_dev) && + nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { if (flp->flowi4_oif && - flp->flowi4_oif != nh->nh_oif) + flp->flowi4_oif != nhc->nhc_oif) continue; } @@ -1490,6 +1490,7 @@ found: res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; + res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->fi = fi; @@ -1498,7 +1499,7 @@ found: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif - trace_fib_table_lookup(tb->tb_id, flp, nh, err); + trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } @@ -2651,7 +2652,7 @@ static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; - if (fi && fi->fib_nh->nh_gw) + if (fi && fi->fib_nh->fib_nh_gw4) flags |= RTF_GATEWAY; if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; @@ -2702,7 +2703,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) "%d\t%08X\t%d\t%u\t%u", fi->fib_dev ? fi->fib_dev->name : "*", prefix, - fi->fib_nh->nh_gw, flags, 0, 0, + fi->fib_nh->fib_nh_gw4, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 79e98e21cdd7..100e63f57ea6 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -499,15 +499,45 @@ out_unlock: return err; } -static int fou_add_to_port_list(struct net *net, struct fou *fou) +static bool fou_cfg_cmp(struct fou *fou, struct fou_cfg *cfg) +{ + struct sock *sk = fou->sock->sk; + struct udp_port_cfg *udp_cfg = &cfg->udp_config; + + if (fou->family != udp_cfg->family || + fou->port != udp_cfg->local_udp_port || + sk->sk_dport != udp_cfg->peer_udp_port || + sk->sk_bound_dev_if != udp_cfg->bind_ifindex) + return false; + + if (fou->family == AF_INET) { + if (sk->sk_rcv_saddr != udp_cfg->local_ip.s_addr || + sk->sk_daddr != udp_cfg->peer_ip.s_addr) + return false; + else + return true; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, &udp_cfg->local_ip6) || + ipv6_addr_cmp(&sk->sk_v6_daddr, &udp_cfg->peer_ip6)) + return false; + else + return true; +#endif + } + + return false; +} + +static int fou_add_to_port_list(struct net *net, struct fou *fou, + struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { - if (fou->port == fout->port && - fou->family == fout->family) { + if (fou_cfg_cmp(fout, cfg)) { mutex_unlock(&fn->fou_lock); return -EALREADY; } @@ -585,7 +615,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk->sk_allocation = GFP_ATOMIC; - err = fou_add_to_port_list(net, fou); + err = fou_add_to_port_list(net, fou, cfg); if (err) goto error; @@ -605,14 +635,12 @@ error: static int fou_destroy(struct net *net, struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); - __be16 port = cfg->udp_config.local_udp_port; - u8 family = cfg->udp_config.family; int err = -EINVAL; struct fou *fou; mutex_lock(&fn->fou_lock); list_for_each_entry(fou, &fn->fou_list, list) { - if (fou->port == port && fou->family == family) { + if (fou_cfg_cmp(fou, cfg)) { fou_release(fou); err = 0; break; @@ -626,16 +654,27 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg) static struct genl_family fou_nl_family; static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { - [FOU_ATTR_PORT] = { .type = NLA_U16, }, - [FOU_ATTR_AF] = { .type = NLA_U8, }, - [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, - [FOU_ATTR_TYPE] = { .type = NLA_U8, }, - [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, + [FOU_ATTR_PORT] = { .type = NLA_U16, }, + [FOU_ATTR_AF] = { .type = NLA_U8, }, + [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, + [FOU_ATTR_TYPE] = { .type = NLA_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, + [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, + [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, + [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, + [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; static int parse_nl_config(struct genl_info *info, struct fou_cfg *cfg) { + bool has_local = false, has_peer = false; + struct nlattr *attr; + int ifindex; + __be16 port; + memset(cfg, 0, sizeof(*cfg)); cfg->udp_config.family = AF_INET; @@ -657,8 +696,7 @@ static int parse_nl_config(struct genl_info *info, } if (info->attrs[FOU_ATTR_PORT]) { - __be16 port = nla_get_be16(info->attrs[FOU_ATTR_PORT]); - + port = nla_get_be16(info->attrs[FOU_ATTR_PORT]); cfg->udp_config.local_udp_port = port; } @@ -671,6 +709,52 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL]) cfg->flags |= FOU_F_REMCSUM_NOPARTIAL; + if (cfg->udp_config.family == AF_INET) { + if (info->attrs[FOU_ATTR_LOCAL_V4]) { + attr = info->attrs[FOU_ATTR_LOCAL_V4]; + cfg->udp_config.local_ip.s_addr = nla_get_in_addr(attr); + has_local = true; + } + + if (info->attrs[FOU_ATTR_PEER_V4]) { + attr = info->attrs[FOU_ATTR_PEER_V4]; + cfg->udp_config.peer_ip.s_addr = nla_get_in_addr(attr); + has_peer = true; + } +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (info->attrs[FOU_ATTR_LOCAL_V6]) { + attr = info->attrs[FOU_ATTR_LOCAL_V6]; + cfg->udp_config.local_ip6 = nla_get_in6_addr(attr); + has_local = true; + } + + if (info->attrs[FOU_ATTR_PEER_V6]) { + attr = info->attrs[FOU_ATTR_PEER_V6]; + cfg->udp_config.peer_ip6 = nla_get_in6_addr(attr); + has_peer = true; + } +#endif + } + + if (has_peer) { + if (info->attrs[FOU_ATTR_PEER_PORT]) { + port = nla_get_be16(info->attrs[FOU_ATTR_PEER_PORT]); + cfg->udp_config.peer_udp_port = port; + } else { + return -EINVAL; + } + } + + if (info->attrs[FOU_ATTR_IFINDEX]) { + if (!has_local) + return -EINVAL; + + ifindex = nla_get_s32(info->attrs[FOU_ATTR_IFINDEX]); + + cfg->udp_config.bind_ifindex = ifindex; + } + return 0; } @@ -702,15 +786,37 @@ static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info) static int fou_fill_info(struct fou *fou, struct sk_buff *msg) { + struct sock *sk = fou->sock->sk; + if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) || nla_put_be16(msg, FOU_ATTR_PORT, fou->port) || + nla_put_be16(msg, FOU_ATTR_PEER_PORT, sk->sk_dport) || nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) || - nla_put_u8(msg, FOU_ATTR_TYPE, fou->type)) + nla_put_u8(msg, FOU_ATTR_TYPE, fou->type) || + nla_put_s32(msg, FOU_ATTR_IFINDEX, sk->sk_bound_dev_if)) return -1; if (fou->flags & FOU_F_REMCSUM_NOPARTIAL) if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL)) return -1; + + if (fou->sock->sk->sk_family == AF_INET) { + if (nla_put_in_addr(msg, FOU_ATTR_LOCAL_V4, sk->sk_rcv_saddr)) + return -1; + + if (nla_put_in_addr(msg, FOU_ATTR_PEER_V4, sk->sk_daddr)) + return -1; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put_in6_addr(msg, FOU_ATTR_LOCAL_V6, + &sk->sk_v6_rcv_saddr)) + return -1; + + if (nla_put_in6_addr(msg, FOU_ATTR_PEER_V6, &sk->sk_v6_daddr)) + return -1; +#endif + } + return 0; } @@ -763,7 +869,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info) ret = -ESRCH; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { - if (port == fout->port && family == fout->family) { + if (fou_cfg_cmp(fout, &cfg)) { ret = fou_dump_info(fout, info->snd_portid, info->snd_seq, 0, msg, info->genlhdr->cmd); @@ -808,20 +914,17 @@ static const struct genl_ops fou_nl_ops[] = { { .cmd = FOU_CMD_ADD, .doit = fou_nl_cmd_add_port, - .policy = fou_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = FOU_CMD_DEL, .doit = fou_nl_cmd_rm_port, - .policy = fou_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = FOU_CMD_GET, .doit = fou_nl_cmd_get_port, .dumpit = fou_nl_dump, - .policy = fou_nl_policy, }, }; @@ -830,6 +933,7 @@ static struct genl_family fou_nl_family __ro_after_init = { .name = FOU_GENL_NAME, .version = FOU_GENL_VERSION, .maxattr = FOU_ATTR_MAX, + .policy = fou_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = fou_nl_ops, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c80188875f39..10b35328cfbc 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -693,11 +693,8 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return 0; } - while (frag) { - skb = frag->next; - kfree_skb(frag); - frag = skb; - } + kfree_skb_list(frag); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a5da63e5faa2..f3f2adf630d4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -500,15 +500,17 @@ EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { - static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; - net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); - hash = jhash_3words((__force u32)iph->daddr, + hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol ^ net_hash_mix(net), - ip_idents_hashrnd); + iph->protocol, + &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } @@ -642,7 +644,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, unsigned int i; int depth; - genid = fnhe_genid(dev_net(nh->nh_dev)); + genid = fnhe_genid(dev_net(nh->fib_nh_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); @@ -776,8 +778,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh *nh; + nh = container_of(nhc, struct fib_nh, nh_common); update_or_create_fnhe(nh, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); @@ -1025,8 +1029,10 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) rcu_read_lock(); if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh *nh; + nh = container_of(nhc, struct fib_nh, nh_common); update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } @@ -1176,7 +1182,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or - * DST_OBSOLETE_DEAD by dst_free(). + * DST_OBSOLETE_DEAD. */ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; @@ -1233,7 +1239,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) - src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res); + src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), @@ -1352,9 +1358,9 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { + struct fib_nh_common *nhc = res->nhc; + struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; - struct fib_nh *nh = &fi->fib_nh[res->nh_sel]; - struct net_device *dev = nh->nh_dev; u32 mtu = 0; if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || @@ -1362,6 +1368,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) mtu = fi->fib_mtu; if (likely(!mtu)) { + struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); struct fib_nh_exception *fnhe; fnhe = find_exception(nh, daddr); @@ -1372,7 +1379,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); - return mtu - lwtunnel_headroom(nh->nh_lwtstate, mtu); + return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, @@ -1527,10 +1534,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, bool cached = false; if (fi) { - struct fib_nh *nh = &FIB_RES_NH(*res); + struct fib_nh_common *nhc = FIB_RES_NHC(*res); + struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) { - rt->rt_gateway = nh->nh_gw; + if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) { + rt->rt_gateway = nh->fib_nh_gw4; rt->rt_uses_gateway = 1; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); @@ -1538,7 +1546,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif - rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); + rt->dst.lwtstate = lwtstate_get(nh->fib_nh_lws); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) @@ -1697,15 +1705,18 @@ static int __mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { + struct fib_nh_common *nhc = FIB_RES_NHC(*res); + struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; + struct fib_nh *nh; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ - out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); + out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; @@ -1722,10 +1733,13 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && - skb->protocol == htons(ETH_P_IP) && - (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) - IPCB(skb)->flags |= IPSKB_DOREDIRECT; + skb->protocol == htons(ETH_P_IP)) { + __be32 gw = nhc->nhc_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; + + if (IN_DEV_SHARED_MEDIA(out_dev) || + inet_addr_onlink(out_dev, saddr, gw)) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; + } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -1742,12 +1756,13 @@ static int __mkroute_input(struct sk_buff *skb, } } - fnhe = find_exception(&FIB_RES_NH(*res), daddr); + nh = container_of(nhc, struct fib_nh, nh_common); + fnhe = find_exception(nh, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + rth = rcu_dereference(nh->nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2041,7 +2056,11 @@ local_input: do_cache = false; if (res->fi) { if (!itag) { - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + struct fib_nh_common *nhc = FIB_RES_NHC(*res); + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + rth = rcu_dereference(nh->nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -2071,15 +2090,17 @@ local_input: } if (do_cache) { - struct fib_nh *nh = &FIB_RES_NH(*res); + struct fib_nh_common *nhc = FIB_RES_NHC(*res); + struct fib_nh *nh; - rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); + rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } + nh = container_of(nhc, struct fib_nh, nh_common); if (unlikely(!rt_cache_route(nh, rth))) rt_add_uncached_list(rth); } @@ -2251,8 +2272,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fnhe = NULL; do_cache &= fi != NULL; if (fi) { + struct fib_nh_common *nhc = FIB_RES_NHC(*res); + struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); struct rtable __rcu **prth; - struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); if (!do_cache) @@ -2262,8 +2284,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { + !(nhc->nhc_has_gw && + nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index e531344611a0..008545f63667 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -216,16 +216,15 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); - if (!inet_csk_reqsk_queue_add(sk, req, child)) { - bh_unlock_sock(child); - sock_put(child); - child = NULL; - reqsk_put(req); - } - } else { - reqsk_free(req); + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; + + bh_unlock_sock(child); + sock_put(child); } - return child; + __reqsk_free(req); + + return NULL; } EXPORT_SYMBOL(tcp_get_cookie_sock); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ba0fc4b18465..2316c08e9591 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -549,6 +549,15 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "fib_sync_mem", + .data = &sysctl_fib_sync_mem, + .maxlen = sizeof(sysctl_fib_sync_mem), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = &sysctl_fib_sync_mem_min, + .extra2 = &sysctl_fib_sync_mem_max, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6baa6dc1b13b..603e770d59b3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -865,6 +865,18 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, { struct sk_buff *skb; + if (likely(!size)) { + skb = sk->sk_tx_skb_cache; + if (skb && !skb_cloned(skb)) { + skb->truesize -= skb->data_len; + sk->sk_tx_skb_cache = NULL; + pskb_trim(skb, 0); + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); + skb_shinfo(skb)->tx_flags = 0; + memset(TCP_SKB_CB(skb), 0, sizeof(struct tcp_skb_cb)); + return skb; + } + } /* The TCP header must be at least 32-bit aligned. */ size = ALIGN(size, 4); @@ -1098,30 +1110,6 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, } EXPORT_SYMBOL(tcp_sendpage); -/* Do not bother using a page frag for very small frames. - * But use this heuristic only for the first skb in write queue. - * - * Having no payload in skb->head allows better SACK shifting - * in tcp_shift_skb_data(), reducing sack/rack overhead, because - * write queue has less skbs. - * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB. - * This also speeds up tso_fragment(), since it wont fallback - * to tcp_fragment(). - */ -static int linear_payload_sz(bool first_skb) -{ - if (first_skb) - return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); - return 0; -} - -static int select_size(bool first_skb, bool zc) -{ - if (zc) - return 0; - return linear_payload_sz(first_skb); -} - void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { @@ -1272,7 +1260,6 @@ restart: if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; - int linear; new_segment: if (!sk_stream_memory_free(sk)) @@ -1283,8 +1270,7 @@ new_segment: goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - linear = select_size(first_skb, zc); - skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; @@ -2552,6 +2538,11 @@ void tcp_write_queue_purge(struct sock *sk) sk_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); + skb = sk->sk_tx_skb_cache; + if (skb) { + __kfree_skb(skb); + sk->sk_tx_skb_cache = NULL; + } INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); @@ -2587,6 +2578,10 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); + if (sk->sk_rx_skb_cache) { + __kfree_skb(sk->sk_rx_skb_cache); + sk->sk_rx_skb_cache = NULL; + } tp->copied_seq = tp->rcv_nxt; tp->urg_data = 0; tcp_write_queue_purge(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5def3c48870e..6660ce2a7333 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6263,6 +6263,11 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) * congestion control: Linux DCTCP asserts ECT on all packets, * including SYN, which is most optimal solution; however, * others, such as FreeBSD do not. + * + * Exception: At least one of the reserved bits of the TCP header (th->res1) is + * set, indicating the use of a future TCP extension (such as AccECN). See + * RFC8311 ยง4.3 which updates RFC3168 to allow the development of such + * extensions. */ static void tcp_ecn_create_request(struct request_sock *req, const struct sk_buff *skb, @@ -6282,7 +6287,7 @@ static void tcp_ecn_create_request(struct request_sock *req, ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; - if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || + if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || (ecn_ok_dst & DST_FEATURE_ECN_CA) || tcp_bpf_ca_needs_ecn((struct sock *)req)) inet_rsk(req)->ecn_ok = 1; @@ -6502,8 +6507,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, reqsk_fastopen_remove(fastopen_sk, req, false); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); - reqsk_put(req); - goto drop; + goto drop_and_free; } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); @@ -6527,7 +6531,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, drop_and_release: dst_release(dst); drop_and_free: - reqsk_free(req); + __reqsk_free(req); drop: tcp_listendrop(sk); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2f8039a26b08..faa6fa619f59 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1774,6 +1774,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); const struct iphdr *iph; const struct tcphdr *th; @@ -1905,11 +1906,17 @@ process: tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { + skb_to_free = sk->sk_rx_skb_cache; + sk->sk_rx_skb_cache = NULL; ret = tcp_v4_do_rcv(sk, skb); - } else if (tcp_add_backlog(sk, skb)) { - goto discard_and_relse; + } else { + if (tcp_add_backlog(sk, skb)) + goto discard_and_relse; + skb_to_free = NULL; } bh_unlock_sock(sk); + if (skb_to_free) + __kfree_skb(skb_to_free); put_and_return: if (refcounted) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index b467a7cabf40..4ccec4c705f7 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -953,12 +953,10 @@ static const struct genl_ops tcp_metrics_nl_ops[] = { .cmd = TCP_METRICS_CMD_GET, .doit = tcp_metrics_nl_cmd_get, .dumpit = tcp_metrics_nl_dump, - .policy = tcp_metrics_nl_policy, }, { .cmd = TCP_METRICS_CMD_DEL, .doit = tcp_metrics_nl_cmd_del, - .policy = tcp_metrics_nl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -968,6 +966,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .name = TCP_METRICS_GENL_NAME, .version = TCP_METRICS_GENL_VERSION, .maxattr = TCP_METRICS_ATTR_MAX, + .policy = tcp_metrics_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = tcp_metrics_nl_ops, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4522579aaca2..e265d1aeeb66 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -52,12 +52,8 @@ void tcp_mstamp_refresh(struct tcp_sock *tp) { u64 val = tcp_clock_ns(); - if (val > tp->tcp_clock_cache) - tp->tcp_clock_cache = val; - - val = div_u64(val, NSEC_PER_USEC); - if (val > tp->tcp_mstamp) - tp->tcp_mstamp = val; + tp->tcp_clock_cache = val; + tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC); } static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, |